From 0d6f55403a47b317c0d9511a80545c19ab0ef52f Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 9 Jul 2020 15:29:41 +0206 Subject: crash: add VMCOREINFO macro to define offset in a struct declared by typedef The existing macro VMCOREINFO_OFFSET() can't be used for structures declared via typedef because "struct" is not part of type definition. Create another macro for this purpose. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Acked-by: Baoquan He Acked-by: Sergey Senozhatsky Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20200709132344.760-2-john.ogness@linutronix.de --- include/linux/crash_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 525510a9f965..43b51c9df571 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -53,6 +53,9 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_OFFSET(name, field) \ vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ (unsigned long)offsetof(struct name, field)) +#define VMCOREINFO_TYPE_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(name, field)) #define VMCOREINFO_LENGTH(name, value) \ vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) #define VMCOREINFO_NUMBER(name) \ -- cgit v1.2.3 From 9fadd6d1e2977bbd449d4fb99cde41ed6f71f668 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 16 Jul 2020 14:02:08 +0200 Subject: drm/ttm: remove TTM_MEMTYPE_FLAG_MAPPABLE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Not used any more. And it is bad design to use a TTM flag to do a check inside a driver. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/378245/ --- include/drm/ttm/ttm_bo_driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 71b195e78c7c..9b251853afe2 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -46,7 +46,6 @@ #define TTM_MAX_BO_PRIORITY 4U #define TTM_MEMTYPE_FLAG_FIXED (1 << 0) /* Fixed (on-card) PCI memory */ -#define TTM_MEMTYPE_FLAG_MAPPABLE (1 << 1) /* Memory mappable */ struct ttm_mem_type_manager; -- cgit v1.2.3 From 2c2b0d880f1b4c01f30e14242977b82fa527342d Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Thu, 23 Jul 2020 23:09:57 -0400 Subject: drm/amdkfd: Add thermal throttling SMI event Add support for reporting thermal throttling events through SMI. Also, add a counter to count the number of throttling interrupts observed and report the count in the SMI event message. Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f738c3b53f4e..df6c7a43aadc 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -450,7 +450,8 @@ struct kfd_ioctl_import_dmabuf_args { * KFD SMI(System Management Interface) events */ /* Event type (defined by bitmask) */ -#define KFD_SMI_EVENT_VMFAULT 0x0000000000000001 +#define KFD_SMI_EVENT_VMFAULT 0x0000000000000001 +#define KFD_SMI_EVENT_THERMAL_THROTTLE 0x0000000000000002 struct kfd_ioctl_smi_events_args { __u32 gpuid; /* to KFD */ -- cgit v1.2.3 From 7d8365771ffb0edc336f2cd45e96ef8214a83dca Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Fri, 3 Jul 2020 16:29:38 +0200 Subject: moduleparams: Add hexint type parameter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For bitmasks printing values in hex is more convenient. Prefix with `0x` to make it clear, that it’s a hex value, and pad it out. Using the helper for `amdgpu.ppfeaturemask`, it will look like below. Before: $ more /sys/module/amdgpu/parameters/ppfeaturemask 4294950911 After: $ more /sys/module/amdgpu/parameters/ppfeaturemask 0xffffbfff Cc: linux-kernel@vger.kernel.org Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Paul Menzel Acked-by: Linus Torvalds Reviewed-by: Christian König Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/374726/ --- include/linux/moduleparam.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 3ef917ff0964..cff7261e98bb 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -118,7 +118,7 @@ struct kparam_array * you can create your own by defining those variables. * * Standard types are: - * byte, short, ushort, int, uint, long, ulong + * byte, hexint, short, ushort, int, uint, long, ulong * charp: a character pointer * bool: a bool, values 0/1, y/n, Y/N. * invbool: the above, only sense-reversed (N = true). @@ -448,6 +448,11 @@ extern int param_set_ullong(const char *val, const struct kernel_param *kp); extern int param_get_ullong(char *buffer, const struct kernel_param *kp); #define param_check_ullong(name, p) __param_check(name, p, unsigned long long) +extern const struct kernel_param_ops param_ops_hexint; +extern int param_set_hexint(const char *val, const struct kernel_param *kp); +extern int param_get_hexint(char *buffer, const struct kernel_param *kp); +#define param_check_hexint(name, p) param_check_uint(name, p) + extern const struct kernel_param_ops param_ops_charp; extern int param_set_charp(const char *val, const struct kernel_param *kp); extern int param_get_charp(char *buffer, const struct kernel_param *kp); -- cgit v1.2.3 From be1213a341a289afc51f89181c310e368fba0b66 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 21 Jul 2020 09:58:13 +0200 Subject: drm/ttm: remove TTM_MEMTYPE_FLAG_FIXED v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead use a boolean field in the memory manager structure. Also invert the meaning of the field since the use of a TT structure is the special case here. v2: cleanup zero init. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Reviewed-by: Thomas Zimmermann Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/382079/ --- include/drm/ttm/ttm_bo_driver.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 9b251853afe2..adac4cd0ba23 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -45,8 +45,6 @@ #define TTM_MAX_BO_PRIORITY 4U -#define TTM_MEMTYPE_FLAG_FIXED (1 << 0) /* Fixed (on-card) PCI memory */ - struct ttm_mem_type_manager; struct ttm_mem_type_manager_func { @@ -173,7 +171,7 @@ struct ttm_mem_type_manager { bool has_type; bool use_type; - uint32_t flags; + bool use_tt; uint64_t size; uint32_t available_caching; uint32_t default_caching; -- cgit v1.2.3 From 1a3fb590856a9d7e8392d970fc07791b6703de94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 23 Jul 2020 17:13:47 +0200 Subject: drm/ttm: remove the init_mem_type callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is a very strange concept to call a function which just calls back the caller for the functions parameters. Signed-off-by: Christian König Reviewed-by: Thomas Zimmermann Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/382085/ --- include/drm/ttm/ttm_bo_driver.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index adac4cd0ba23..f76f1332fdc5 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -157,7 +157,6 @@ struct ttm_mem_type_manager_func { * @move: The fence of the last pipelined move operation. * * This structure is used to identify and manage memory types for a device. - * It's set up by the ttm_bo_driver::init_mem_type method. */ @@ -203,8 +202,6 @@ struct ttm_mem_type_manager { * struct ttm_bo_driver * * @create_ttm_backend_entry: Callback to create a struct ttm_backend. - * @init_mem_type: Callback to initialize a struct ttm_mem_type_manager - * structure. * @evict_flags: Callback to obtain placement flags when a buffer is evicted. * @move: Callback for a driver to hook in accelerated functions to * move a buffer. @@ -247,9 +244,6 @@ struct ttm_bo_driver { */ void (*ttm_tt_unpopulate)(struct ttm_tt *ttm); - int (*init_mem_type)(struct ttm_bo_device *bdev, uint32_t type, - struct ttm_mem_type_manager *man); - /** * struct ttm_bo_driver member eviction_valuable * -- cgit v1.2.3 From c3ee8c65f63799b02e1fb828bac99fd5008fb565 Mon Sep 17 00:00:00 2001 From: Bernard Zhao Date: Sat, 1 Aug 2020 20:02:13 +0800 Subject: drm/panel: remove return value of function drm_panel_add The function "int drm_panel_add(struct drm_panel *panel)" always returns 0, this return value is meaningless. Also, there is no need to check return value which calls "drm_panel_add and", error branch code will never run. Signed-off-by: Bernard Zhao Reviewed-by: Linus Walleij Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20200801120216.8488-1-bernard@vivo.com --- include/drm/drm_panel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 6193cb555acc..ff066524cb70 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -175,7 +175,7 @@ void drm_panel_init(struct drm_panel *panel, struct device *dev, const struct drm_panel_funcs *funcs, int connector_type); -int drm_panel_add(struct drm_panel *panel); +void drm_panel_add(struct drm_panel *panel); void drm_panel_remove(struct drm_panel *panel); int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector); -- cgit v1.2.3 From 2d05f56af8f52d52dc614ddf4d51c00ea5afb67f Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Wed, 29 Jul 2020 15:41:44 +0200 Subject: fbdev: Remove trailing whitespace Removes trailing whitespaces in several places. Signed-off-by: Thomas Zimmermann Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200729134148.6855-2-tzimmermann@suse.de --- include/linux/fb.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 2b530e6d86e4..714187bc13ac 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -124,7 +124,7 @@ struct fb_cursor_user { * Register/unregister for framebuffer events */ -/* The resolution of the passed in fb_info about to change */ +/* The resolution of the passed in fb_info about to change */ #define FB_EVENT_MODE_CHANGE 0x01 #ifdef CONFIG_GUMSTIX_AM200EPD @@ -459,12 +459,12 @@ struct fb_info { #if IS_ENABLED(CONFIG_FB_BACKLIGHT) /* assigned backlight device */ - /* set before framebuffer registration, + /* set before framebuffer registration, remove after unregister */ struct backlight_device *bl_dev; /* Backlight level curve */ - struct mutex bl_curve_mutex; + struct mutex bl_curve_mutex; u8 bl_curve[FB_BACKLIGHT_LEVELS]; #endif #ifdef CONFIG_FB_DEFERRED_IO @@ -483,8 +483,8 @@ struct fb_info { char __iomem *screen_base; /* Virtual address */ char *screen_buffer; }; - unsigned long screen_size; /* Amount of ioremapped VRAM or 0 */ - void *pseudo_palette; /* Fake palette of 16 colors */ + unsigned long screen_size; /* Amount of ioremapped VRAM or 0 */ + void *pseudo_palette; /* Fake palette of 16 colors */ #define FBINFO_STATE_RUNNING 0 #define FBINFO_STATE_SUSPENDED 1 u32 state; /* Hardware state i.e suspend */ @@ -587,11 +587,11 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { * `Generic' versions of the frame buffer device operations */ -extern int fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var); -extern int fb_pan_display(struct fb_info *info, struct fb_var_screeninfo *var); +extern int fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var); +extern int fb_pan_display(struct fb_info *info, struct fb_var_screeninfo *var); extern int fb_blank(struct fb_info *info, int blank); -extern void cfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect); -extern void cfb_copyarea(struct fb_info *info, const struct fb_copyarea *area); +extern void cfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect); +extern void cfb_copyarea(struct fb_info *info, const struct fb_copyarea *area); extern void cfb_imageblit(struct fb_info *info, const struct fb_image *image); /* * Drawing operations where framebuffer is in system RAM -- cgit v1.2.3 From 522ec6e0eed0ab0678e7d5b5bf00487dfe83f7ce Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Thu, 30 Jul 2020 18:04:33 -0400 Subject: drm/amdkfd: Replace bitmask with event idx in SMI event msg Event bitmask is a 64-bit mask with only 1 bit set. Sending this event bitmask in KFD SMI event message is both wasteful of memory and potentially limiting to only 64 events. Instead send event index in SMI event message. Please note this change does not break the ABI for the two event types defined so far. The new index is identical to the mask used before. Signed-off-by: Mukul Joshi Suggested-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index df6c7a43aadc..cb1f963a84e0 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -449,9 +449,13 @@ struct kfd_ioctl_import_dmabuf_args { /* * KFD SMI(System Management Interface) events */ -/* Event type (defined by bitmask) */ -#define KFD_SMI_EVENT_VMFAULT 0x0000000000000001 -#define KFD_SMI_EVENT_THERMAL_THROTTLE 0x0000000000000002 +enum kfd_smi_event { + KFD_SMI_EVENT_NONE = 0, /* not used */ + KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ + KFD_SMI_EVENT_THERMAL_THROTTLE = 2, +}; + +#define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1)) struct kfd_ioctl_smi_events_args { __u32 gpuid; /* to KFD */ -- cgit v1.2.3 From 46bca88bbdd3046db31b8b7e053a909ae79e285b Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:38 +1000 Subject: drm/ttm/amdgpu: consolidate ttm reserve paths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop the WARN_ON and consolidate the two paths into one. Use the consolidate slowpath in the execbuf utils code. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-6-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 91 ++++++++--------------------------------- 1 file changed, 17 insertions(+), 74 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index f76f1332fdc5..44b4d24e73a2 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -599,29 +599,30 @@ int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible); void ttm_mem_io_unlock(struct ttm_mem_type_manager *man); /** - * __ttm_bo_reserve: + * ttm_bo_reserve: * * @bo: A pointer to a struct ttm_buffer_object. * @interruptible: Sleep interruptible if waiting. * @no_wait: Don't sleep while trying to reserve, rather return -EBUSY. * @ticket: ticket used to acquire the ww_mutex. * - * Will not remove reserved buffers from the lru lists. - * Otherwise identical to ttm_bo_reserve. + * Locks a buffer object for validation. (Or prevents other processes from + * locking it for validation), while taking a number of measures to prevent + * deadlocks. * * Returns: * -EDEADLK: The reservation may cause a deadlock. * Release all buffer reservations, wait for @bo to become unreserved and - * try again. (only if use_sequence == 1). + * try again. * -ERESTARTSYS: A wait for the buffer to become unreserved was interrupted by * a signal. Release all buffer reservations and return to user-space. * -EBUSY: The function needed to sleep, but @no_wait was true * -EALREADY: Bo already reserved using @ticket. This error code will only * be returned if @use_ticket is set to true. */ -static inline int __ttm_bo_reserve(struct ttm_buffer_object *bo, - bool interruptible, bool no_wait, - struct ww_acquire_ctx *ticket) +static inline int ttm_bo_reserve(struct ttm_buffer_object *bo, + bool interruptible, bool no_wait, + struct ww_acquire_ctx *ticket) { int ret = 0; @@ -643,59 +644,6 @@ static inline int __ttm_bo_reserve(struct ttm_buffer_object *bo, return ret; } -/** - * ttm_bo_reserve: - * - * @bo: A pointer to a struct ttm_buffer_object. - * @interruptible: Sleep interruptible if waiting. - * @no_wait: Don't sleep while trying to reserve, rather return -EBUSY. - * @ticket: ticket used to acquire the ww_mutex. - * - * Locks a buffer object for validation. (Or prevents other processes from - * locking it for validation) and removes it from lru lists, while taking - * a number of measures to prevent deadlocks. - * - * Deadlocks may occur when two processes try to reserve multiple buffers in - * different order, either by will or as a result of a buffer being evicted - * to make room for a buffer already reserved. (Buffers are reserved before - * they are evicted). The following algorithm prevents such deadlocks from - * occurring: - * Processes attempting to reserve multiple buffers other than for eviction, - * (typically execbuf), should first obtain a unique 32-bit - * validation sequence number, - * and call this function with @use_ticket == 1 and @ticket->stamp == the unique - * sequence number. If upon call of this function, the buffer object is already - * reserved, the validation sequence is checked against the validation - * sequence of the process currently reserving the buffer, - * and if the current validation sequence is greater than that of the process - * holding the reservation, the function returns -EDEADLK. Otherwise it sleeps - * waiting for the buffer to become unreserved, after which it retries - * reserving. - * The caller should, when receiving an -EDEADLK error - * release all its buffer reservations, wait for @bo to become unreserved, and - * then rerun the validation with the same validation sequence. This procedure - * will always guarantee that the process with the lowest validation sequence - * will eventually succeed, preventing both deadlocks and starvation. - * - * Returns: - * -EDEADLK: The reservation may cause a deadlock. - * Release all buffer reservations, wait for @bo to become unreserved and - * try again. (only if use_sequence == 1). - * -ERESTARTSYS: A wait for the buffer to become unreserved was interrupted by - * a signal. Release all buffer reservations and return to user-space. - * -EBUSY: The function needed to sleep, but @no_wait was true - * -EALREADY: Bo already reserved using @ticket. This error code will only - * be returned if @use_ticket is set to true. - */ -static inline int ttm_bo_reserve(struct ttm_buffer_object *bo, - bool interruptible, bool no_wait, - struct ww_acquire_ctx *ticket) -{ - WARN_ON(!kref_read(&bo->kref)); - - return __ttm_bo_reserve(bo, interruptible, no_wait, ticket); -} - /** * ttm_bo_reserve_slowpath: * @bo: A pointer to a struct ttm_buffer_object. @@ -710,20 +658,15 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo, bool interruptible, struct ww_acquire_ctx *ticket) { - int ret = 0; - - WARN_ON(!kref_read(&bo->kref)); - - if (interruptible) - ret = dma_resv_lock_slow_interruptible(bo->base.resv, - ticket); - else - dma_resv_lock_slow(bo->base.resv, ticket); - - if (ret == -EINTR) - ret = -ERESTARTSYS; - - return ret; + if (interruptible) { + int ret = dma_resv_lock_slow_interruptible(bo->base.resv, + ticket); + if (ret == -EINTR) + ret = -ERESTARTSYS; + return ret; + } + dma_resv_lock_slow(bo->base.resv, ticket); + return 0; } /** -- cgit v1.2.3 From 20784cdf4b8c81359289aff73a89f557c7bc9e76 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:39 +1000 Subject: drm/ttm: use a helper for unlocked moves to the lru tail MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pattern was repeated a few times, just make an inline for it. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-7-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 44b4d24e73a2..049ebf85712f 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -669,6 +669,13 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo, return 0; } +static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo) +{ + spin_lock(&ttm_bo_glob.lru_lock); + ttm_bo_move_to_lru_tail(bo, NULL); + spin_unlock(&ttm_bo_glob.lru_lock); +} + /** * ttm_bo_unreserve * @@ -678,9 +685,7 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo, */ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo) { - spin_lock(&ttm_bo_glob.lru_lock); - ttm_bo_move_to_lru_tail(bo, NULL); - spin_unlock(&ttm_bo_glob.lru_lock); + ttm_bo_move_to_lru_tail_unlocked(bo); dma_resv_unlock(bo->base.resv); } -- cgit v1.2.3 From a2ff1e81d04eb938a670bce206de2963d98950d8 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:41 +1000 Subject: drm/ttm: export memory type debug entrypoint. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As suggested on review, just export the memory type debug for drivers to use, while also making the debug callback optional (don't need to test for system as it won't init it). rename it to be more consistent with object name for now. (we may rename all the objects later.) Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-9-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 049ebf85712f..ee11ae621c3b 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -806,4 +806,12 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); extern const struct ttm_mem_type_manager_func ttm_bo_manager_func; +/** + * ttm_mem_type_manager_debug + * + * @man: manager type to dump. + * @p: printer to use for debug. + */ +void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man, + struct drm_printer *p); #endif -- cgit v1.2.3 From 747074bb04b5a6be8e562d06b5a312d6ddb253d0 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:46 +1000 Subject: drm/ttm: split the mm manager init code (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This will allow the driver to control the ordering here better. Eventually the old path will be removed. v2: add docs for new APIs. rename new path to ttm_mem_type_manager_init/set_used(for now) Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-14-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 15 +++++++++++++++ include/drm/ttm/ttm_bo_driver.h | 15 +++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index b1c705a93517..cc876cd3b82c 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -54,6 +54,8 @@ struct ttm_place; struct ttm_lru_bulk_move; +struct ttm_mem_type_manager; + /** * struct ttm_bus_placement * @@ -531,6 +533,19 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size, uint32_t page_alignment, bool interruptible, struct ttm_buffer_object **p_bo); +/** + * ttm_mem_type_manager_init + * + * @bdev: Pointer to a ttm_bo_device struct. + * @man: memory manager object to init + * @p_size: size managed area in pages. + * + * Initialise core parts of a a manager object. + */ +void ttm_mem_type_manager_init(struct ttm_bo_device *bdev, + struct ttm_mem_type_manager *man, + unsigned long p_size); + /** * ttm_bo_init_mm * diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index ee11ae621c3b..02aa1b996b3a 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -689,6 +689,21 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo) dma_resv_unlock(bo->base.resv); } +/** + * ttm_mem_type_manager_set_used + * + * @man: A memory manager object. + * @used: usage state to set. + * + * Set the manager in use flag. If disabled the manager is no longer + * used for object placement. + */ +static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *man, bool used) +{ + man->has_type = true; + man->use_type = used; +} + /* * ttm_bo_util.c */ -- cgit v1.2.3 From 3c90424bd7df15eb062ae9e6518886a706ed0d84 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:47 +1000 Subject: drm/ttm: provide a driver-led init path for range mm manager. (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This lets the generic range mm manager be initialised by the driver. v2: add docs. rename api to range_man_init for now. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-15-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 02aa1b996b3a..23352053df36 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -819,6 +819,20 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo); */ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); +/** + * ttm_range_man_init + * + * @bdev: ttm device + * @man: the manager to initialise with the range manager. + * @p_size: size of area to be managed in pages. + * + * Initialise a generic range manager for the selected memory type. + * The range manager is installed for this device in the type slot. + */ +int ttm_range_man_init(struct ttm_bo_device *bdev, + struct ttm_mem_type_manager *man, + unsigned long p_size); + extern const struct ttm_mem_type_manager_func ttm_bo_manager_func; /** -- cgit v1.2.3 From 98399abd52b234b82457ef6c40c41543d806d3b7 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:56 +1000 Subject: drm/ttm: purge old manager init path. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-24-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 18 ------------------ include/drm/ttm/ttm_bo_driver.h | 15 --------------- 2 files changed, 33 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index cc876cd3b82c..56d207b983e9 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -546,24 +546,6 @@ void ttm_mem_type_manager_init(struct ttm_bo_device *bdev, struct ttm_mem_type_manager *man, unsigned long p_size); -/** - * ttm_bo_init_mm - * - * @bdev: Pointer to a ttm_bo_device struct. - * @mem_type: The memory type. - * @p_size: size managed area in pages. - * - * Initialize a manager for a given memory type. - * Note: if part of driver firstopen, it must be protected from a - * potentially racing lastclose. - * Returns: - * -EINVAL: invalid size or memory type. - * -ENOMEM: Not enough memory. - * May also return driver-specified errors. - */ -int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type, - unsigned long p_size); - /** * ttm_bo_clean_mm * diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 23352053df36..303014250767 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -48,19 +48,6 @@ struct ttm_mem_type_manager; struct ttm_mem_type_manager_func { - /** - * struct ttm_mem_type_manager member init - * - * @man: Pointer to a memory type manager. - * @p_size: Implementation dependent, but typically the size of the - * range to be managed in pages. - * - * Called to initialize a private range manager. The function is - * expected to initialize the man::priv member. - * Returns 0 on success, negative error code on failure. - */ - int (*init)(struct ttm_mem_type_manager *man, unsigned long p_size); - /** * struct ttm_mem_type_manager member takedown * @@ -833,8 +820,6 @@ int ttm_range_man_init(struct ttm_bo_device *bdev, struct ttm_mem_type_manager *man, unsigned long p_size); -extern const struct ttm_mem_type_manager_func ttm_bo_manager_func; - /** * ttm_mem_type_manager_debug * -- cgit v1.2.3 From 4265accbfc724a68894f91737e765e2cce43fe4e Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:58 +1000 Subject: drm/ttm: make some inline helper functions for cleanup paths. (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The disable path is just temporary for now, it will be dropped once has_type is gone in a later patch. v2: add docs. rename to ttm_mem_type_manager namespace Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-26-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 303014250767..30dfb9d5f6c9 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -691,6 +691,32 @@ static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *ma man->use_type = used; } +/** + * ttm_mem_type_manager_disable. + * + * @man: A memory manager object. + * + * Indicate the manager is not to be used and deregistered. (temporary during rework). + */ +static inline void ttm_mem_type_manager_disable(struct ttm_mem_type_manager *man) +{ + man->has_type = false; + man->use_type = false; +} + +/** + * ttm_mem_type_manager_cleanup + * + * @man: A memory manager object. + * + * Cleanup the move fences from the memory manager object. + */ +static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man) +{ + dma_fence_put(man->move); + man->move = NULL; +} + /* * ttm_bo_util.c */ -- cgit v1.2.3 From 56ee8b1c71ffb556b8758f2d9e3098f4f80b4d01 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:55:59 +1000 Subject: drm/ttm: start allowing drivers to use new takedown path (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow the takedown path callback to be optional as well. v2: use fini for range manager Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-27-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 30dfb9d5f6c9..811ace1416b3 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -717,6 +717,18 @@ static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man man->move = NULL; } +/* + * ttm_mem_type_manager_force_list_clean + * + * @bdev - device to use + * @man - manager to use + * + * Force all the objects out of a memory manager until clean. + * Part of memory manager cleanup sequence. + */ +int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev, + struct ttm_mem_type_manager *man); + /* * ttm_bo_util.c */ @@ -846,6 +858,17 @@ int ttm_range_man_init(struct ttm_bo_device *bdev, struct ttm_mem_type_manager *man, unsigned long p_size); +/** + * ttm_range_man_fini + * + * @bdev: ttm device + * @type: memory manager type + * + * Remove the generic range manager from a slot and tear it down. + */ +int ttm_range_man_fini(struct ttm_bo_device *bdev, + struct ttm_mem_type_manager *man); + /** * ttm_mem_type_manager_debug * @@ -854,4 +877,5 @@ int ttm_range_man_init(struct ttm_bo_device *bdev, */ void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man, struct drm_printer *p); + #endif -- cgit v1.2.3 From 0cf0a7984268c64e906b63a96df3e331ca61f989 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:08 +1000 Subject: drm/ttm: make TTM responsible for cleaning system only. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers should all be cleaning up their memory managers themselves now, so let the core just clean the system one up. Remove the legacy cleaning interface. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-36-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 28 ---------------------------- include/drm/ttm/ttm_bo_driver.h | 10 ---------- 2 files changed, 38 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 56d207b983e9..045f283d79e8 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -546,34 +546,6 @@ void ttm_mem_type_manager_init(struct ttm_bo_device *bdev, struct ttm_mem_type_manager *man, unsigned long p_size); -/** - * ttm_bo_clean_mm - * - * @bdev: Pointer to a ttm_bo_device struct. - * @mem_type: The memory type. - * - * Take down a manager for a given memory type after first walking - * the LRU list to evict any buffers left alive. - * - * Normally, this function is part of lastclose() or unload(), and at that - * point there shouldn't be any buffers left created by user-space, since - * there should've been removed by the file descriptor release() method. - * However, before this function is run, make sure to signal all sync objects, - * and verify that the delayed delete queue is empty. The driver must also - * make sure that there are no NO_EVICT buffers present in this memory type - * when the call is made. - * - * If this function is part of a VT switch, the caller must make sure that - * there are no appications currently validating buffers before this - * function is called. The caller can do that by first taking the - * struct ttm_bo_device::ttm_lock in write mode. - * - * Returns: - * -EINVAL: invalid or uninitialized memory type. - * -EBUSY: There are still buffers left in this memory type. - */ -int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type); - /** * ttm_bo_evict_mm * diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 811ace1416b3..c76301a808ae 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -48,16 +48,6 @@ struct ttm_mem_type_manager; struct ttm_mem_type_manager_func { - /** - * struct ttm_mem_type_manager member takedown - * - * @man: Pointer to a memory type manager. - * - * Called to undo the setup done in init. All allocated resources - * should be freed. - */ - int (*takedown)(struct ttm_mem_type_manager *man); - /** * struct ttm_mem_type_manager member get_node * -- cgit v1.2.3 From 9eca33f4a13919bb17b8a02809a32f8299f5c9bf Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:09 +1000 Subject: drm/ttm: add wrapper to get manager from bdev. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This will allow different abstractions later. Acked-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-37-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index c76301a808ae..c8ea5eab719d 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -444,6 +444,12 @@ struct ttm_bo_device { bool no_retry; }; +static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev, + int mem_type) +{ + return &bdev->man[mem_type]; +} + /** * struct ttm_lru_bulk_move_pos * -- cgit v1.2.3 From 01057278bc68610389e32ffe3a8335aff38a84ce Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:16 +1000 Subject: drm/ttm: rename manager variable to make sure wrapper is used. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Other users of this should notice this change and switch to wrapper. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-44-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index c8ea5eab719d..f97c047b6a3a 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -415,7 +415,10 @@ struct ttm_bo_device { */ struct list_head device_list; struct ttm_bo_driver *driver; - struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES]; + /* + * access via ttm_manager_type. + */ + struct ttm_mem_type_manager man_priv[TTM_NUM_MEM_TYPES]; /* * Protected by internal locks. @@ -447,7 +450,7 @@ struct ttm_bo_device { static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev, int mem_type) { - return &bdev->man[mem_type]; + return &bdev->man_priv[mem_type]; } /** -- cgit v1.2.3 From d398811ebfa80329269932803a6e78dc01c79bf1 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:17 +1000 Subject: drm/ttm: allow drivers to provide their own manager subclasses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This will get removed eventually and all drivers will use this. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-45-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index f97c047b6a3a..ce15eb075241 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -419,7 +419,7 @@ struct ttm_bo_device { * access via ttm_manager_type. */ struct ttm_mem_type_manager man_priv[TTM_NUM_MEM_TYPES]; - + struct ttm_mem_type_manager *man_drv[TTM_NUM_MEM_TYPES]; /* * Protected by internal locks. */ @@ -450,9 +450,18 @@ struct ttm_bo_device { static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev, int mem_type) { + if (bdev->man_drv[mem_type]) + return bdev->man_drv[mem_type]; return &bdev->man_priv[mem_type]; } +static inline void ttm_set_driver_manager(struct ttm_bo_device *bdev, + int type, + struct ttm_mem_type_manager *manager) +{ + bdev->man_drv[type] = manager; +} + /** * struct ttm_lru_bulk_move_pos * -- cgit v1.2.3 From 37205891d84f9269de61d6e85c24607209478a85 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:19 +1000 Subject: drm/ttm: make ttm_range_man_init/takedown take type + args MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This makes it easier to move these to a driver allocated system Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-47-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index ce15eb075241..7490de8f53af 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -856,14 +856,20 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); * ttm_range_man_init * * @bdev: ttm device - * @man: the manager to initialise with the range manager. + * @type: memory manager type + * @available_caching: TTM_PL_FLAG_* for allowed caching modes + * @default_caching: default caching mode + * @use_tt: if the memory manager uses tt * @p_size: size of area to be managed in pages. * * Initialise a generic range manager for the selected memory type. * The range manager is installed for this device in the type slot. */ int ttm_range_man_init(struct ttm_bo_device *bdev, - struct ttm_mem_type_manager *man, + unsigned type, + uint32_t available_caching, + uint32_t default_caching, + bool use_tt, unsigned long p_size); /** @@ -875,7 +881,7 @@ int ttm_range_man_init(struct ttm_bo_device *bdev, * Remove the generic range manager from a slot and tear it down. */ int ttm_range_man_fini(struct ttm_bo_device *bdev, - struct ttm_mem_type_manager *man); + unsigned type); /** * ttm_mem_type_manager_debug -- cgit v1.2.3 From 7ee6c95e05e9b06741d347107cff13559e9f81d9 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:24 +1000 Subject: drm/ttm: drop priv pointer in memory manager MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This isn't needed anymore by any drivers. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-52-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 7490de8f53af..8c39901d8717 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -123,7 +123,6 @@ struct ttm_mem_type_manager_func { * @default_caching: The default caching policy used for a buffer object * placed in this memory type if the user doesn't provide one. * @func: structure pointer implementing the range manager. See above - * @priv: Driver private closure for @func. * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions * reserved by the TTM vm system. @@ -152,7 +151,6 @@ struct ttm_mem_type_manager { uint32_t available_caching; uint32_t default_caching; const struct ttm_mem_type_manager_func *func; - void *priv; struct mutex io_reserve_mutex; bool use_io_reserve_lru; spinlock_t move_lock; -- cgit v1.2.3 From 7541ce1a6f2be9ab056a5b5105e08aef8d3287b1 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:26 +1000 Subject: drm/ttm: drop man->bdev link. This link isn't needed anymore, drop it from the init interface. Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-54-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 6 ++---- include/drm/ttm/ttm_bo_driver.h | 2 -- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 045f283d79e8..95d6c648d5c6 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -536,14 +536,12 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size, /** * ttm_mem_type_manager_init * - * @bdev: Pointer to a ttm_bo_device struct. * @man: memory manager object to init * @p_size: size managed area in pages. * - * Initialise core parts of a a manager object. + * Initialise core parts of a manager object. */ -void ttm_mem_type_manager_init(struct ttm_bo_device *bdev, - struct ttm_mem_type_manager *man, +void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man, unsigned long p_size); /** diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 8c39901d8717..e17975466b7f 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -138,8 +138,6 @@ struct ttm_mem_type_manager_func { struct ttm_mem_type_manager { - struct ttm_bo_device *bdev; - /* * No protection. Constant from start. */ -- cgit v1.2.3 From a751612d4cb77779669da0a6d19fbc4f7e72ba6f Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:27 +1000 Subject: drm/ttm: drop list of memory managers from device. (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver now controls these, the core just controls the system memory one. v2: init sysman explicitly and assign it as a driver manager to simplify the lookup sequence. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-55-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index e17975466b7f..2cb8721398ee 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -414,7 +414,7 @@ struct ttm_bo_device { /* * access via ttm_manager_type. */ - struct ttm_mem_type_manager man_priv[TTM_NUM_MEM_TYPES]; + struct ttm_mem_type_manager sysman; struct ttm_mem_type_manager *man_drv[TTM_NUM_MEM_TYPES]; /* * Protected by internal locks. @@ -446,9 +446,7 @@ struct ttm_bo_device { static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev, int mem_type) { - if (bdev->man_drv[mem_type]) - return bdev->man_drv[mem_type]; - return &bdev->man_priv[mem_type]; + return bdev->man_drv[mem_type]; } static inline void ttm_set_driver_manager(struct ttm_bo_device *bdev, -- cgit v1.2.3 From 90a0489a718b87bc0674792f9eafac007e0ea3d6 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:28 +1000 Subject: drm/ttm: drop type manager has_type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit under driver control, this flag isn't needed anymore, remove the API that used to access it, and consoldiate with the used api. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-56-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 2cb8721398ee..a6076ab89a51 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -111,7 +111,6 @@ struct ttm_mem_type_manager_func { /** * struct ttm_mem_type_manager * - * @has_type: The memory type has been initialized. * @use_type: The memory type is enabled. * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory * managed by this memory type. @@ -141,8 +140,6 @@ struct ttm_mem_type_manager { /* * No protection. Constant from start. */ - - bool has_type; bool use_type; bool use_tt; uint64_t size; @@ -689,23 +686,9 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo) */ static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *man, bool used) { - man->has_type = true; man->use_type = used; } -/** - * ttm_mem_type_manager_disable. - * - * @man: A memory manager object. - * - * Indicate the manager is not to be used and deregistered. (temporary during rework). - */ -static inline void ttm_mem_type_manager_disable(struct ttm_mem_type_manager *man) -{ - man->has_type = false; - man->use_type = false; -} - /** * ttm_mem_type_manager_cleanup * -- cgit v1.2.3 From 3f48f938ad21a1ab1cec5631af3e468baabe41c8 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:29 +1000 Subject: drm/ttm: add a wrapper for checking if manager is in use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This converts vmwgfx over to using an interface to set the in use and check the in use flag. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-57-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index a6076ab89a51..31264a09ec63 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -689,6 +689,20 @@ static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *ma man->use_type = used; } +/** + * ttm_mem_type_manager_used + * + * @man: Manager to get used state for + * + * Get the in use flag for a manager. + * Returns: + * true is used, false if not. + */ +static inline bool ttm_mem_type_manager_used(struct ttm_mem_type_manager *man) +{ + return man->use_type; +} + /** * ttm_mem_type_manager_cleanup * -- cgit v1.2.3 From 9de59bc201496f28bb8835c2bcbae3ddb186b548 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:31 +1000 Subject: drm/ttm: rename ttm_mem_type_manager -> ttm_resource_manager. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This name makes a lot more sense, since these are about managing driver resources rather than just memory ranges. Acked-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-59-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 6 ++--- include/drm/ttm/ttm_bo_driver.h | 60 ++++++++++++++++++++--------------------- 2 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 95d6c648d5c6..7b0655bc13da 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -54,7 +54,7 @@ struct ttm_place; struct ttm_lru_bulk_move; -struct ttm_mem_type_manager; +struct ttm_resource_manager; /** * struct ttm_bus_placement @@ -534,14 +534,14 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size, struct ttm_buffer_object **p_bo); /** - * ttm_mem_type_manager_init + * ttm_resource_manager_init * * @man: memory manager object to init * @p_size: size managed area in pages. * * Initialise core parts of a manager object. */ -void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man, +void ttm_resource_manager_init(struct ttm_resource_manager *man, unsigned long p_size); /** diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 31264a09ec63..d17e25ba80d4 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -45,11 +45,11 @@ #define TTM_MAX_BO_PRIORITY 4U -struct ttm_mem_type_manager; +struct ttm_resource_manager; -struct ttm_mem_type_manager_func { +struct ttm_resource_manager_func { /** - * struct ttm_mem_type_manager member get_node + * struct ttm_resource_manager member get_node * * @man: Pointer to a memory type manager. * @bo: Pointer to the buffer object we're allocating space for. @@ -69,20 +69,20 @@ struct ttm_mem_type_manager_func { * the function should return a negative error code. * * Note that @mem::mm_node will only be dereferenced by - * struct ttm_mem_type_manager functions and optionally by the driver, + * struct ttm_resource_manager functions and optionally by the driver, * which has knowledge of the underlying type. * * This function may not be called from within atomic context, so * an implementation can and must use either a mutex or a spinlock to * protect any data structures managing the space. */ - int (*get_node)(struct ttm_mem_type_manager *man, + int (*get_node)(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, struct ttm_mem_reg *mem); /** - * struct ttm_mem_type_manager member put_node + * struct ttm_resource_manager member put_node * * @man: Pointer to a memory type manager. * @mem: Pointer to a struct ttm_mem_reg to be filled in. @@ -91,11 +91,11 @@ struct ttm_mem_type_manager_func { * and that are identified by @mem::mm_node and @mem::start. May not * be called from within atomic context. */ - void (*put_node)(struct ttm_mem_type_manager *man, + void (*put_node)(struct ttm_resource_manager *man, struct ttm_mem_reg *mem); /** - * struct ttm_mem_type_manager member debug + * struct ttm_resource_manager member debug * * @man: Pointer to a memory type manager. * @printer: Prefix to be used in printout to identify the caller. @@ -104,12 +104,12 @@ struct ttm_mem_type_manager_func { * type manager to aid debugging of out-of-memory conditions. * It may not be called from within atomic context. */ - void (*debug)(struct ttm_mem_type_manager *man, + void (*debug)(struct ttm_resource_manager *man, struct drm_printer *printer); }; /** - * struct ttm_mem_type_manager + * struct ttm_resource_manager * * @use_type: The memory type is enabled. * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory @@ -136,7 +136,7 @@ struct ttm_mem_type_manager_func { -struct ttm_mem_type_manager { +struct ttm_resource_manager { /* * No protection. Constant from start. */ @@ -145,7 +145,7 @@ struct ttm_mem_type_manager { uint64_t size; uint32_t available_caching; uint32_t default_caching; - const struct ttm_mem_type_manager_func *func; + const struct ttm_resource_manager_func *func; struct mutex io_reserve_mutex; bool use_io_reserve_lru; spinlock_t move_lock; @@ -390,7 +390,7 @@ extern struct ttm_bo_global { * struct ttm_bo_device - Buffer object driver device-specific data. * * @driver: Pointer to a struct ttm_bo_driver struct setup by the driver. - * @man: An array of mem_type_managers. + * @man: An array of resource_managers. * @vma_manager: Address space manager (pointer) * lru_lock: Spinlock that protects the buffer+device lru lists and * ddestroy lists. @@ -411,8 +411,8 @@ struct ttm_bo_device { /* * access via ttm_manager_type. */ - struct ttm_mem_type_manager sysman; - struct ttm_mem_type_manager *man_drv[TTM_NUM_MEM_TYPES]; + struct ttm_resource_manager sysman; + struct ttm_resource_manager *man_drv[TTM_NUM_MEM_TYPES]; /* * Protected by internal locks. */ @@ -440,7 +440,7 @@ struct ttm_bo_device { bool no_retry; }; -static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev, +static inline struct ttm_resource_manager *ttm_manager_type(struct ttm_bo_device *bdev, int mem_type) { return bdev->man_drv[mem_type]; @@ -448,7 +448,7 @@ static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device static inline void ttm_set_driver_manager(struct ttm_bo_device *bdev, int type, - struct ttm_mem_type_manager *manager) + struct ttm_resource_manager *manager) { bdev->man_drv[type] = manager; } @@ -581,8 +581,8 @@ void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo); int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo); void ttm_mem_io_free_vm(struct ttm_buffer_object *bo); -int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible); -void ttm_mem_io_unlock(struct ttm_mem_type_manager *man); +int ttm_mem_io_lock(struct ttm_resource_manager *man, bool interruptible); +void ttm_mem_io_unlock(struct ttm_resource_manager *man); /** * ttm_bo_reserve: @@ -676,7 +676,7 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo) } /** - * ttm_mem_type_manager_set_used + * ttm_resource_manager_set_used * * @man: A memory manager object. * @used: usage state to set. @@ -684,13 +684,13 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo) * Set the manager in use flag. If disabled the manager is no longer * used for object placement. */ -static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *man, bool used) +static inline void ttm_resource_manager_set_used(struct ttm_resource_manager *man, bool used) { man->use_type = used; } /** - * ttm_mem_type_manager_used + * ttm_resource_manager_used * * @man: Manager to get used state for * @@ -698,26 +698,26 @@ static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *ma * Returns: * true is used, false if not. */ -static inline bool ttm_mem_type_manager_used(struct ttm_mem_type_manager *man) +static inline bool ttm_resource_manager_used(struct ttm_resource_manager *man) { return man->use_type; } /** - * ttm_mem_type_manager_cleanup + * ttm_resource_manager_cleanup * * @man: A memory manager object. * * Cleanup the move fences from the memory manager object. */ -static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man) +static inline void ttm_resource_manager_cleanup(struct ttm_resource_manager *man) { dma_fence_put(man->move); man->move = NULL; } /* - * ttm_mem_type_manager_force_list_clean + * ttm_resource_manager_force_list_clean * * @bdev - device to use * @man - manager to use @@ -725,8 +725,8 @@ static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man * Force all the objects out of a memory manager until clean. * Part of memory manager cleanup sequence. */ -int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev, - struct ttm_mem_type_manager *man); +int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev, + struct ttm_resource_manager *man); /* * ttm_bo_util.c @@ -875,12 +875,12 @@ int ttm_range_man_fini(struct ttm_bo_device *bdev, unsigned type); /** - * ttm_mem_type_manager_debug + * ttm_resource_manager_debug * * @man: manager type to dump. * @p: printer to use for debug. */ -void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man, +void ttm_resource_manager_debug(struct ttm_resource_manager *man, struct drm_printer *p); #endif -- cgit v1.2.3 From 2966141ad2dda23d1b37997de6a4389b7864c169 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 4 Aug 2020 12:56:32 +1000 Subject: drm/ttm: rename ttm_mem_reg to ttm_resource. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This name better reflects what the object does. I didn't rename all the pointers it seemed too messy. Signed-off-by: Dave Airlie Acked-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-60-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 10 ++++----- include/drm/ttm/ttm_bo_driver.h | 48 ++++++++++++++++++++--------------------- include/drm/ttm/ttm_tt.h | 10 ++++----- 3 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 7b0655bc13da..770ad2195875 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -81,7 +81,7 @@ struct ttm_bus_placement { /** - * struct ttm_mem_reg + * struct ttm_resource * * @mm_node: Memory manager node. * @size: Requested size of memory region. @@ -94,7 +94,7 @@ struct ttm_bus_placement { * buffer object. */ -struct ttm_mem_reg { +struct ttm_resource { void *mm_node; unsigned long start; unsigned long size; @@ -187,7 +187,7 @@ struct ttm_buffer_object { * Members protected by the bo::resv::reserved lock. */ - struct ttm_mem_reg mem; + struct ttm_resource mem; struct file *persistent_swap_storage; struct ttm_tt *ttm; bool evicted; @@ -316,12 +316,12 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, bool interruptible, bool no_wait); * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo * * @placement: Return immediately if buffer is busy. - * @mem: The struct ttm_mem_reg indicating the region where the bo resides + * @mem: The struct ttm_resource indicating the region where the bo resides * @new_flags: Describes compatible placement found * * Returns true if the placement is compatible */ -bool ttm_bo_mem_compat(struct ttm_placement *placement, struct ttm_mem_reg *mem, +bool ttm_bo_mem_compat(struct ttm_placement *placement, struct ttm_resource *mem, uint32_t *new_flags); /** diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index d17e25ba80d4..eb1c3312e175 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -55,7 +55,7 @@ struct ttm_resource_manager_func { * @bo: Pointer to the buffer object we're allocating space for. * @placement: Placement details. * @flags: Additional placement flags. - * @mem: Pointer to a struct ttm_mem_reg to be filled in. + * @mem: Pointer to a struct ttm_resource to be filled in. * * This function should allocate space in the memory type managed * by @man. Placement details if @@ -79,20 +79,20 @@ struct ttm_resource_manager_func { int (*get_node)(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_mem_reg *mem); + struct ttm_resource *mem); /** * struct ttm_resource_manager member put_node * * @man: Pointer to a memory type manager. - * @mem: Pointer to a struct ttm_mem_reg to be filled in. + * @mem: Pointer to a struct ttm_resource to be filled in. * * This function frees memory type resources previously allocated * and that are identified by @mem::mm_node and @mem::start. May not * be called from within atomic context. */ void (*put_node)(struct ttm_resource_manager *man, - struct ttm_mem_reg *mem); + struct ttm_resource *mem); /** * struct ttm_resource_manager member debug @@ -251,7 +251,7 @@ struct ttm_bo_driver { */ int (*move)(struct ttm_buffer_object *bo, bool evict, struct ttm_operation_ctx *ctx, - struct ttm_mem_reg *new_mem); + struct ttm_resource *new_mem); /** * struct ttm_bo_driver_member verify_access @@ -277,7 +277,7 @@ struct ttm_bo_driver { */ void (*move_notify)(struct ttm_buffer_object *bo, bool evict, - struct ttm_mem_reg *new_mem); + struct ttm_resource *new_mem); /* notify the driver we are taking a fault on this BO * and have reserved it */ int (*fault_reserve_notify)(struct ttm_buffer_object *bo); @@ -294,9 +294,9 @@ struct ttm_bo_driver { * are balanced. */ int (*io_mem_reserve)(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem); + struct ttm_resource *mem); void (*io_mem_free)(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem); + struct ttm_resource *mem); /** * Return the pfn for a given page_offset inside the BO. @@ -503,15 +503,15 @@ ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask) */ /** - * ttm_mem_reg_is_pci + * ttm_resource_is_pci * * @bdev: Pointer to a struct ttm_bo_device. - * @mem: A valid struct ttm_mem_reg. + * @mem: A valid struct ttm_resource. * * Returns true if the memory described by @mem is PCI memory, * false otherwise. */ -bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem); +bool ttm_resource_is_pci(struct ttm_bo_device *bdev, struct ttm_resource *mem); /** * ttm_bo_mem_space @@ -519,7 +519,7 @@ bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem); * @bo: Pointer to a struct ttm_buffer_object. the data of which * we want to allocate space for. * @proposed_placement: Proposed new placement for the buffer object. - * @mem: A struct ttm_mem_reg. + * @mem: A struct ttm_resource. * @interruptible: Sleep interruptible when sliping. * @no_wait_gpu: Return immediately if the GPU is busy. * @@ -534,10 +534,10 @@ bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem); */ int ttm_bo_mem_space(struct ttm_buffer_object *bo, struct ttm_placement *placement, - struct ttm_mem_reg *mem, + struct ttm_resource *mem, struct ttm_operation_ctx *ctx); -void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem); +void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_resource *mem); int ttm_bo_device_release(struct ttm_bo_device *bdev); @@ -733,16 +733,16 @@ int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev, */ int ttm_mem_io_reserve(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem); + struct ttm_resource *mem); void ttm_mem_io_free(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem); + struct ttm_resource *mem); /** * ttm_bo_move_ttm * * @bo: A pointer to a struct ttm_buffer_object. * @interruptible: Sleep interruptible if waiting. * @no_wait_gpu: Return immediately if the GPU is busy. - * @new_mem: struct ttm_mem_reg indicating where to move. + * @new_mem: struct ttm_resource indicating where to move. * * Optimized move function for a buffer object with both old and * new placement backed by a TTM. The function will, if successful, @@ -756,7 +756,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev, int ttm_bo_move_ttm(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - struct ttm_mem_reg *new_mem); + struct ttm_resource *new_mem); /** * ttm_bo_move_memcpy @@ -764,7 +764,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo, * @bo: A pointer to a struct ttm_buffer_object. * @interruptible: Sleep interruptible if waiting. * @no_wait_gpu: Return immediately if the GPU is busy. - * @new_mem: struct ttm_mem_reg indicating where to move. + * @new_mem: struct ttm_resource indicating where to move. * * Fallback move function for a mappable buffer object in mappable memory. * The function will, if successful, @@ -778,7 +778,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo, int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - struct ttm_mem_reg *new_mem); + struct ttm_resource *new_mem); /** * ttm_bo_free_old_node @@ -795,7 +795,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo); * @bo: A pointer to a struct ttm_buffer_object. * @fence: A fence object that signals when moving is complete. * @evict: This is an evict move. Don't return until the buffer is idle. - * @new_mem: struct ttm_mem_reg indicating where to move. + * @new_mem: struct ttm_resource indicating where to move. * * Accelerated move function to be called when an accelerated move * has been scheduled. The function will create a new temporary buffer object @@ -806,7 +806,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo); */ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct dma_fence *fence, bool evict, - struct ttm_mem_reg *new_mem); + struct ttm_resource *new_mem); /** * ttm_bo_pipeline_move. @@ -814,14 +814,14 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, * @bo: A pointer to a struct ttm_buffer_object. * @fence: A fence object that signals when moving is complete. * @evict: This is an evict move. Don't return until the buffer is idle. - * @new_mem: struct ttm_mem_reg indicating where to move. + * @new_mem: struct ttm_resource indicating where to move. * * Function for pipelining accelerated moves. Either free the memory * immediately or hang it on a temporary buffer object. */ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo, struct dma_fence *fence, bool evict, - struct ttm_mem_reg *new_mem); + struct ttm_resource *new_mem); /** * ttm_bo_pipeline_gutting. diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index c0e928abf592..2ac34219ecb5 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -30,7 +30,7 @@ #include struct ttm_tt; -struct ttm_mem_reg; +struct ttm_resource; struct ttm_buffer_object; struct ttm_operation_ctx; @@ -53,14 +53,14 @@ struct ttm_backend_func { * struct ttm_backend_func member bind * * @ttm: Pointer to a struct ttm_tt. - * @bo_mem: Pointer to a struct ttm_mem_reg describing the + * @bo_mem: Pointer to a struct ttm_resource describing the * memory type and location for binding. * * Bind the backend pages into the aperture in the location * indicated by @bo_mem. This function should be able to handle * differences between aperture and system page sizes. */ - int (*bind) (struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem); + int (*bind) (struct ttm_tt *ttm, struct ttm_resource *bo_mem); /** * struct ttm_backend_func member unbind @@ -179,11 +179,11 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma); * ttm_ttm_bind: * * @ttm: The struct ttm_tt containing backing pages. - * @bo_mem: The struct ttm_mem_reg identifying the binding location. + * @bo_mem: The struct ttm_resource identifying the binding location. * * Bind the pages of @ttm to an aperture location identified by @bo_mem */ -int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem, +int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem, struct ttm_operation_ctx *ctx); /** -- cgit v1.2.3 From 16c642ec3fe9a144fbe1e97dc56f13a6308f1381 Mon Sep 17 00:00:00 2001 From: Pierre-Eric Pelloux-Prayer Date: Thu, 30 Jul 2020 15:54:59 +0200 Subject: drm/amdgpu: new ids flag for tmz (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allows UMD to know if TMZ is supported and enabled. This commit also bumps KMS_DRIVER_MINOR because if we don't UMD can't tell if "ids_flags & AMDGPU_IDS_FLAGS_TMZ == 0" means "tmz is not enabled" or "tmz may be enabled but the kernel doesn't report it". v2: use amdgpu_is_tmz() and reworded commit message. Signed-off-by: Pierre-Eric Pelloux-Prayer Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 3218576e109d..c5ff2b275fcd 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -673,6 +673,7 @@ struct drm_amdgpu_cs_chunk_data { */ #define AMDGPU_IDS_FLAGS_FUSION 0x1 #define AMDGPU_IDS_FLAGS_PREEMPTION 0x2 +#define AMDGPU_IDS_FLAGS_TMZ 0x4 /* indicate if acceleration can be working */ #define AMDGPU_INFO_ACCEL_WORKING 0x00 -- cgit v1.2.3 From 87154ff86bf69ecf76600e56ecab0b79fc3f71ea Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 2 Aug 2020 09:43:59 -0700 Subject: drm: Remove unnecessary drm_panel_attach and drm_panel_detach These functions are now empty and no longer useful so remove the functions and their uses. Signed-off-by: Joe Perches Cc: Bernard Zhao Cc: Maarten Lankhorst Cc: Maxime Ripard , Cc: Thomas Zimmermann Cc: Thierry Reding Cc: David Airlie Cc: Daniel Vetter Cc: Linus Walleij Cc: Icenowy Zheng , Cc: Jagan Teki Cc: Laurent Pinchart Cc: Robert Chiras Cc: dri-devel@lists.freedesktop.org, Cc: linux-kernel@vger.kernel.org Cc: opensource.kernel@vivo.com Signed-off-by: Sam Ravnborg # Fixed build and a few warnings Link: https://patchwork.freedesktop.org/patch/msgid/9e13761020750b1ce2f1fabee23ef6e2a2942882.camel@perches.com --- include/drm/drm_panel.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index ff066524cb70..45a1b5a2275d 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -178,9 +178,6 @@ void drm_panel_init(struct drm_panel *panel, struct device *dev, void drm_panel_add(struct drm_panel *panel); void drm_panel_remove(struct drm_panel *panel); -int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector); -void drm_panel_detach(struct drm_panel *panel); - int drm_panel_prepare(struct drm_panel *panel); int drm_panel_unprepare(struct drm_panel *panel); -- cgit v1.2.3 From e5b92773287c3eb3108a44785986a6c997866df8 Mon Sep 17 00:00:00 2001 From: Oleg Vasilev Date: Fri, 24 Apr 2020 18:20:51 +0530 Subject: drm: report dp downstream port type as a subconnector property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, downstream port type is only reported in debugfs. This information should be considered important since it reflects the actual physical connector type. Some userspace (e.g. window compositors) may want to show this info to a user. The 'subconnector' property is already utilized for DVI-I and TV-out for reporting connector subtype. The initial motivation for this feature came from i2c test [1]. It is supposed to be skipped on VGA connectors, but it cannot detect VGA over DP and fails instead. v2: - Ville: utilized drm_dp_is_branch() - Ville: implement DP 1.0 downstream type info - Replaced create_dp_properties with add_dp_subconnector_property - Added dp_set_subconnector_property helper v4: - Ville: add DP1.0 best assumption about subconnector - Ville: assume DVI is DVI-D - Ville: reuse Writeback enum value for Virtual subconnector - Renamed #defines: HDMI -> HDMIA, DP -> DisplayPort v5: rebase v6: - Jani Nikula: renamed a function name - Jani Nikula: addressed the issues with documentation [1]: https://bugs.freedesktop.org/show_bug.cgi?id=104097 Cc: Ville Syrjälä Cc: intel-gfx@lists.freedesktop.org Signed-off-by: Jeevan B Signed-off-by: Oleg Vasilev Reviewed-by: Emil Velikov Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/1587732655-17544-1-git-send-email-jeevan.b@intel.com --- include/drm/drm_connector.h | 3 +++ include/drm/drm_dp_helper.h | 8 ++++++++ include/drm/drm_mode_config.h | 6 ++++++ include/uapi/drm/drm_mode.h | 21 +++++++++++++-------- 4 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index af145608b5ed..928136556174 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1604,10 +1604,13 @@ const char *drm_get_dvi_i_subconnector_name(int val); const char *drm_get_dvi_i_select_name(int val); const char *drm_get_tv_subconnector_name(int val); const char *drm_get_tv_select_name(int val); +const char *drm_get_dp_subconnector_name(int val); const char *drm_get_content_protection_name(int val); const char *drm_get_hdcp_content_type_name(int val); int drm_mode_create_dvi_i_properties(struct drm_device *dev); +void drm_connector_attach_dp_subconnector_property(struct drm_connector *connector); + int drm_mode_create_tv_margin_properties(struct drm_device *dev); int drm_mode_create_tv_properties(struct drm_device *dev, unsigned int num_modes, diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index e47dc22ebf50..5c2819924862 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -26,6 +26,7 @@ #include #include #include +#include /* * Unless otherwise noted, all values are from the DP 1.1a spec. Note that @@ -1619,6 +1620,13 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4], struct drm_dp_aux *aux); +enum drm_mode_subconnector +drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +void drm_dp_set_subconnector_property(struct drm_connector *connector, + enum drm_connector_status status, + const u8 *dpcd, + const u8 port_cap[4]); void drm_dp_remote_aux_init(struct drm_dp_aux *aux); void drm_dp_aux_init(struct drm_dp_aux *aux); diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index ffb9852a0638..f768c7cf7de3 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -680,6 +680,12 @@ struct drm_mode_config { */ struct drm_property *dvi_i_select_subconnector_property; + /** + * @dp_subconnector_property: Optional DP property to differentiate + * between different DP downstream port types. + */ + struct drm_property *dp_subconnector_property; + /** * @tv_subconnector_property: Optional TV property to differentiate * between different TV connector types. diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index deea447e5f22..863eda048265 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -332,14 +332,19 @@ struct drm_mode_get_encoder { /* This is for connectors with multiple signal types. */ /* Try to match DRM_MODE_CONNECTOR_X as closely as possible. */ enum drm_mode_subconnector { - DRM_MODE_SUBCONNECTOR_Automatic = 0, - DRM_MODE_SUBCONNECTOR_Unknown = 0, - DRM_MODE_SUBCONNECTOR_DVID = 3, - DRM_MODE_SUBCONNECTOR_DVIA = 4, - DRM_MODE_SUBCONNECTOR_Composite = 5, - DRM_MODE_SUBCONNECTOR_SVIDEO = 6, - DRM_MODE_SUBCONNECTOR_Component = 8, - DRM_MODE_SUBCONNECTOR_SCART = 9, + DRM_MODE_SUBCONNECTOR_Automatic = 0, /* DVI-I, TV */ + DRM_MODE_SUBCONNECTOR_Unknown = 0, /* DVI-I, TV, DP */ + DRM_MODE_SUBCONNECTOR_VGA = 1, /* DP */ + DRM_MODE_SUBCONNECTOR_DVID = 3, /* DVI-I DP */ + DRM_MODE_SUBCONNECTOR_DVIA = 4, /* DVI-I */ + DRM_MODE_SUBCONNECTOR_Composite = 5, /* TV */ + DRM_MODE_SUBCONNECTOR_SVIDEO = 6, /* TV */ + DRM_MODE_SUBCONNECTOR_Component = 8, /* TV */ + DRM_MODE_SUBCONNECTOR_SCART = 9, /* TV */ + DRM_MODE_SUBCONNECTOR_DisplayPort = 10, /* DP */ + DRM_MODE_SUBCONNECTOR_HDMIA = 11, /* DP */ + DRM_MODE_SUBCONNECTOR_Native = 15, /* DP */ + DRM_MODE_SUBCONNECTOR_Wireless = 18, /* DP */ }; #define DRM_MODE_CONNECTOR_Unknown 0 -- cgit v1.2.3 From e92ae67d6ed881e9c6d6d432eb6b5817f150a115 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 3 Aug 2020 15:06:38 +0200 Subject: drm/ttm: rename ttm_resource_manager_func callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The names get/put are associated with reference counting in the Linux kernel, use alloc/free instead. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/384340/?series=80346&rev=1 --- include/drm/ttm/ttm_bo_driver.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index eb1c3312e175..bfdda61edadb 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -49,7 +49,7 @@ struct ttm_resource_manager; struct ttm_resource_manager_func { /** - * struct ttm_resource_manager member get_node + * struct ttm_resource_manager_func member alloc * * @man: Pointer to a memory type manager. * @bo: Pointer to the buffer object we're allocating space for. @@ -76,13 +76,13 @@ struct ttm_resource_manager_func { * an implementation can and must use either a mutex or a spinlock to * protect any data structures managing the space. */ - int (*get_node)(struct ttm_resource_manager *man, - struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource *mem); + int (*alloc)(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource *mem); /** - * struct ttm_resource_manager member put_node + * struct ttm_resource_manager_func member free * * @man: Pointer to a memory type manager. * @mem: Pointer to a struct ttm_resource to be filled in. @@ -91,11 +91,11 @@ struct ttm_resource_manager_func { * and that are identified by @mem::mm_node and @mem::start. May not * be called from within atomic context. */ - void (*put_node)(struct ttm_resource_manager *man, - struct ttm_resource *mem); + void (*free)(struct ttm_resource_manager *man, + struct ttm_resource *mem); /** - * struct ttm_resource_manager member debug + * struct ttm_resource_manager_func member debug * * @man: Pointer to a memory type manager. * @printer: Prefix to be used in printout to identify the caller. -- cgit v1.2.3 From b2458726b38cb69f3da3677dbdf53e47af0e8792 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 3 Aug 2020 16:25:15 +0200 Subject: drm/ttm: give resource functions their own [ch] files MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a separate object we work within TTM. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/384338/?series=80346&rev=1 --- include/drm/ttm/ttm_bo_api.h | 70 ++--------- include/drm/ttm/ttm_bo_driver.h | 189 ----------------------------- include/drm/ttm/ttm_resource.h | 263 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 271 insertions(+), 251 deletions(-) create mode 100644 include/drm/ttm/ttm_resource.h (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 770ad2195875..dbb276abcf6a 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -42,6 +42,8 @@ #include #include +#include "ttm_resource.h" + struct ttm_bo_global; struct ttm_bo_device; @@ -54,57 +56,6 @@ struct ttm_place; struct ttm_lru_bulk_move; -struct ttm_resource_manager; - -/** - * struct ttm_bus_placement - * - * @addr: mapped virtual address - * @base: bus base address - * @is_iomem: is this io memory ? - * @size: size in byte - * @offset: offset from the base address - * @io_reserved_vm: The VM system has a refcount in @io_reserved_count - * @io_reserved_count: Refcounting the numbers of callers to ttm_mem_io_reserve - * - * Structure indicating the bus placement of an object. - */ -struct ttm_bus_placement { - void *addr; - phys_addr_t base; - unsigned long size; - unsigned long offset; - bool is_iomem; - bool io_reserved_vm; - uint64_t io_reserved_count; -}; - - -/** - * struct ttm_resource - * - * @mm_node: Memory manager node. - * @size: Requested size of memory region. - * @num_pages: Actual size of memory region in pages. - * @page_alignment: Page alignment. - * @placement: Placement flags. - * @bus: Placement on io bus accessible to the CPU - * - * Structure indicating the placement and space resources used by a - * buffer object. - */ - -struct ttm_resource { - void *mm_node; - unsigned long start; - unsigned long size; - unsigned long num_pages; - uint32_t page_alignment; - uint32_t mem_type; - uint32_t placement; - struct ttm_bus_placement bus; -}; - /** * enum ttm_bo_type * @@ -533,17 +484,6 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size, uint32_t page_alignment, bool interruptible, struct ttm_buffer_object **p_bo); -/** - * ttm_resource_manager_init - * - * @man: memory manager object to init - * @p_size: size managed area in pages. - * - * Initialise core parts of a manager object. - */ -void ttm_resource_manager_init(struct ttm_resource_manager *man, - unsigned long p_size); - /** * ttm_bo_evict_mm * @@ -680,6 +620,12 @@ static inline bool ttm_bo_uses_embedded_gem_object(struct ttm_buffer_object *bo) return bo->base.dev != NULL; } +int ttm_mem_evict_first(struct ttm_bo_device *bdev, + struct ttm_resource_manager *man, + const struct ttm_place *place, + struct ttm_operation_ctx *ctx, + struct ww_acquire_ctx *ticket); + /* Default number of pre-faulted pages in the TTM fault handler */ #define TTM_BO_VM_NUM_PREFAULT 16 diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index bfdda61edadb..27b4a1e92875 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -43,131 +43,6 @@ #include "ttm_placement.h" #include "ttm_tt.h" -#define TTM_MAX_BO_PRIORITY 4U - -struct ttm_resource_manager; - -struct ttm_resource_manager_func { - /** - * struct ttm_resource_manager_func member alloc - * - * @man: Pointer to a memory type manager. - * @bo: Pointer to the buffer object we're allocating space for. - * @placement: Placement details. - * @flags: Additional placement flags. - * @mem: Pointer to a struct ttm_resource to be filled in. - * - * This function should allocate space in the memory type managed - * by @man. Placement details if - * applicable are given by @placement. If successful, - * @mem::mm_node should be set to a non-null value, and - * @mem::start should be set to a value identifying the beginning - * of the range allocated, and the function should return zero. - * If the memory region accommodate the buffer object, @mem::mm_node - * should be set to NULL, and the function should return 0. - * If a system error occurred, preventing the request to be fulfilled, - * the function should return a negative error code. - * - * Note that @mem::mm_node will only be dereferenced by - * struct ttm_resource_manager functions and optionally by the driver, - * which has knowledge of the underlying type. - * - * This function may not be called from within atomic context, so - * an implementation can and must use either a mutex or a spinlock to - * protect any data structures managing the space. - */ - int (*alloc)(struct ttm_resource_manager *man, - struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource *mem); - - /** - * struct ttm_resource_manager_func member free - * - * @man: Pointer to a memory type manager. - * @mem: Pointer to a struct ttm_resource to be filled in. - * - * This function frees memory type resources previously allocated - * and that are identified by @mem::mm_node and @mem::start. May not - * be called from within atomic context. - */ - void (*free)(struct ttm_resource_manager *man, - struct ttm_resource *mem); - - /** - * struct ttm_resource_manager_func member debug - * - * @man: Pointer to a memory type manager. - * @printer: Prefix to be used in printout to identify the caller. - * - * This function is called to print out the state of the memory - * type manager to aid debugging of out-of-memory conditions. - * It may not be called from within atomic context. - */ - void (*debug)(struct ttm_resource_manager *man, - struct drm_printer *printer); -}; - -/** - * struct ttm_resource_manager - * - * @use_type: The memory type is enabled. - * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory - * managed by this memory type. - * @gpu_offset: If used, the GPU offset of the first managed page of - * fixed memory or the first managed location in an aperture. - * @size: Size of the managed region. - * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX, - * as defined in ttm_placement_common.h - * @default_caching: The default caching policy used for a buffer object - * placed in this memory type if the user doesn't provide one. - * @func: structure pointer implementing the range manager. See above - * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures - * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions - * reserved by the TTM vm system. - * @io_reserve_lru: Optional lru list for unreserving io mem regions. - * @move_lock: lock for move fence - * static information. bdev::driver::io_mem_free is never used. - * @lru: The lru list for this memory type. - * @move: The fence of the last pipelined move operation. - * - * This structure is used to identify and manage memory types for a device. - */ - - - -struct ttm_resource_manager { - /* - * No protection. Constant from start. - */ - bool use_type; - bool use_tt; - uint64_t size; - uint32_t available_caching; - uint32_t default_caching; - const struct ttm_resource_manager_func *func; - struct mutex io_reserve_mutex; - bool use_io_reserve_lru; - spinlock_t move_lock; - - /* - * Protected by @io_reserve_mutex: - */ - - struct list_head io_reserve_lru; - - /* - * Protected by the global->lru_lock. - */ - - struct list_head lru[TTM_MAX_BO_PRIORITY]; - - /* - * Protected by @move_lock. - */ - struct dma_fence *move; -}; - /** * struct ttm_bo_driver * @@ -537,8 +412,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, struct ttm_resource *mem, struct ttm_operation_ctx *ctx); -void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_resource *mem); - int ttm_bo_device_release(struct ttm_bo_device *bdev); /** @@ -675,59 +548,6 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo) dma_resv_unlock(bo->base.resv); } -/** - * ttm_resource_manager_set_used - * - * @man: A memory manager object. - * @used: usage state to set. - * - * Set the manager in use flag. If disabled the manager is no longer - * used for object placement. - */ -static inline void ttm_resource_manager_set_used(struct ttm_resource_manager *man, bool used) -{ - man->use_type = used; -} - -/** - * ttm_resource_manager_used - * - * @man: Manager to get used state for - * - * Get the in use flag for a manager. - * Returns: - * true is used, false if not. - */ -static inline bool ttm_resource_manager_used(struct ttm_resource_manager *man) -{ - return man->use_type; -} - -/** - * ttm_resource_manager_cleanup - * - * @man: A memory manager object. - * - * Cleanup the move fences from the memory manager object. - */ -static inline void ttm_resource_manager_cleanup(struct ttm_resource_manager *man) -{ - dma_fence_put(man->move); - man->move = NULL; -} - -/* - * ttm_resource_manager_force_list_clean - * - * @bdev - device to use - * @man - manager to use - * - * Force all the objects out of a memory manager until clean. - * Part of memory manager cleanup sequence. - */ -int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev, - struct ttm_resource_manager *man); - /* * ttm_bo_util.c */ @@ -874,13 +694,4 @@ int ttm_range_man_init(struct ttm_bo_device *bdev, int ttm_range_man_fini(struct ttm_bo_device *bdev, unsigned type); -/** - * ttm_resource_manager_debug - * - * @man: manager type to dump. - * @p: printer to use for debug. - */ -void ttm_resource_manager_debug(struct ttm_resource_manager *man, - struct drm_printer *p); - #endif diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h new file mode 100644 index 000000000000..bac22a56f6cd --- /dev/null +++ b/include/drm/ttm/ttm_resource.h @@ -0,0 +1,263 @@ +/* + * Copyright 2020 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Christian König + */ + +#ifndef _TTM_RESOURCE_H_ +#define _TTM_RESOURCE_H_ + +#include +#include +#include +#include + +#define TTM_MAX_BO_PRIORITY 4U + +struct ttm_bo_device; +struct ttm_resource_manager; +struct ttm_resource; +struct ttm_place; +struct ttm_buffer_object; + +struct ttm_resource_manager_func { + /** + * struct ttm_resource_manager_func member alloc + * + * @man: Pointer to a memory type manager. + * @bo: Pointer to the buffer object we're allocating space for. + * @placement: Placement details. + * @flags: Additional placement flags. + * @mem: Pointer to a struct ttm_resource to be filled in. + * + * This function should allocate space in the memory type managed + * by @man. Placement details if + * applicable are given by @placement. If successful, + * @mem::mm_node should be set to a non-null value, and + * @mem::start should be set to a value identifying the beginning + * of the range allocated, and the function should return zero. + * If the memory region accommodate the buffer object, @mem::mm_node + * should be set to NULL, and the function should return 0. + * If a system error occurred, preventing the request to be fulfilled, + * the function should return a negative error code. + * + * Note that @mem::mm_node will only be dereferenced by + * struct ttm_resource_manager functions and optionally by the driver, + * which has knowledge of the underlying type. + * + * This function may not be called from within atomic context, so + * an implementation can and must use either a mutex or a spinlock to + * protect any data structures managing the space. + */ + int (*alloc)(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource *mem); + + /** + * struct ttm_resource_manager_func member free + * + * @man: Pointer to a memory type manager. + * @mem: Pointer to a struct ttm_resource to be filled in. + * + * This function frees memory type resources previously allocated + * and that are identified by @mem::mm_node and @mem::start. May not + * be called from within atomic context. + */ + void (*free)(struct ttm_resource_manager *man, + struct ttm_resource *mem); + + /** + * struct ttm_resource_manager_func member debug + * + * @man: Pointer to a memory type manager. + * @printer: Prefix to be used in printout to identify the caller. + * + * This function is called to print out the state of the memory + * type manager to aid debugging of out-of-memory conditions. + * It may not be called from within atomic context. + */ + void (*debug)(struct ttm_resource_manager *man, + struct drm_printer *printer); +}; + +/** + * struct ttm_resource_manager + * + * @use_type: The memory type is enabled. + * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory + * managed by this memory type. + * @gpu_offset: If used, the GPU offset of the first managed page of + * fixed memory or the first managed location in an aperture. + * @size: Size of the managed region. + * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX, + * as defined in ttm_placement_common.h + * @default_caching: The default caching policy used for a buffer object + * placed in this memory type if the user doesn't provide one. + * @func: structure pointer implementing the range manager. See above + * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures + * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions + * reserved by the TTM vm system. + * @io_reserve_lru: Optional lru list for unreserving io mem regions. + * @move_lock: lock for move fence + * static information. bdev::driver::io_mem_free is never used. + * @lru: The lru list for this memory type. + * @move: The fence of the last pipelined move operation. + * + * This structure is used to identify and manage memory types for a device. + */ +struct ttm_resource_manager { + /* + * No protection. Constant from start. + */ + bool use_type; + bool use_tt; + uint64_t size; + uint32_t available_caching; + uint32_t default_caching; + const struct ttm_resource_manager_func *func; + struct mutex io_reserve_mutex; + bool use_io_reserve_lru; + spinlock_t move_lock; + + /* + * Protected by @io_reserve_mutex: + */ + + struct list_head io_reserve_lru; + + /* + * Protected by the global->lru_lock. + */ + + struct list_head lru[TTM_MAX_BO_PRIORITY]; + + /* + * Protected by @move_lock. + */ + struct dma_fence *move; +}; + +/** + * struct ttm_bus_placement + * + * @addr: mapped virtual address + * @base: bus base address + * @is_iomem: is this io memory ? + * @size: size in byte + * @offset: offset from the base address + * @io_reserved_vm: The VM system has a refcount in @io_reserved_count + * @io_reserved_count: Refcounting the numbers of callers to ttm_mem_io_reserve + * + * Structure indicating the bus placement of an object. + */ +struct ttm_bus_placement { + void *addr; + phys_addr_t base; + unsigned long size; + unsigned long offset; + bool is_iomem; + bool io_reserved_vm; + uint64_t io_reserved_count; +}; + +/** + * struct ttm_resource + * + * @mm_node: Memory manager node. + * @size: Requested size of memory region. + * @num_pages: Actual size of memory region in pages. + * @page_alignment: Page alignment. + * @placement: Placement flags. + * @bus: Placement on io bus accessible to the CPU + * + * Structure indicating the placement and space resources used by a + * buffer object. + */ +struct ttm_resource { + void *mm_node; + unsigned long start; + unsigned long size; + unsigned long num_pages; + uint32_t page_alignment; + uint32_t mem_type; + uint32_t placement; + struct ttm_bus_placement bus; +}; + +/** + * ttm_resource_manager_set_used + * + * @man: A memory manager object. + * @used: usage state to set. + * + * Set the manager in use flag. If disabled the manager is no longer + * used for object placement. + */ +static inline void +ttm_resource_manager_set_used(struct ttm_resource_manager *man, bool used) +{ + man->use_type = used; +} + +/** + * ttm_resource_manager_used + * + * @man: Manager to get used state for + * + * Get the in use flag for a manager. + * Returns: + * true is used, false if not. + */ +static inline bool ttm_resource_manager_used(struct ttm_resource_manager *man) +{ + return man->use_type; +} + +/** + * ttm_resource_manager_cleanup + * + * @man: A memory manager object. + * + * Cleanup the move fences from the memory manager object. + */ +static inline void +ttm_resource_manager_cleanup(struct ttm_resource_manager *man) +{ + dma_fence_put(man->move); + man->move = NULL; +} + +int ttm_resource_alloc(struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource *res); +void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource *res); + +void ttm_resource_manager_init(struct ttm_resource_manager *man, + unsigned long p_size); + +int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev, + struct ttm_resource_manager *man); + +void ttm_resource_manager_debug(struct ttm_resource_manager *man, + struct drm_printer *p); + +#endif -- cgit v1.2.3 From e544ea57ac0734bca752eb2d8635fecbe932c356 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 31 Jul 2020 16:07:46 -0700 Subject: x86/boot/compressed: Force hidden visibility for all symbol references Eliminate all GOT entries in the decompressor binary, by forcing hidden visibility for all symbol references, which informs the compiler that such references will be resolved at link time without the need for allocating GOT entries. To ensure that no GOT entries will creep back in, add an assertion to the decompressor linker script that will fire if the .got section has a non-zero size. [Arvind: move hidden.h to include/linux instead of making a copy] Signed-off-by: Ard Biesheuvel Signed-off-by: Arvind Sankar Signed-off-by: Kees Cook Signed-off-by: Ingo Molnar Tested-by: Nick Desaulniers Tested-by: Sedat Dilek Reviewed-by: Kees Cook Acked-by: Arvind Sankar Link: https://lore.kernel.org/r/20200731230820.1742553-3-keescook@chromium.org --- include/linux/hidden.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/hidden.h (limited to 'include') diff --git a/include/linux/hidden.h b/include/linux/hidden.h new file mode 100644 index 000000000000..49a17b6b5962 --- /dev/null +++ b/include/linux/hidden.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * When building position independent code with GCC using the -fPIC option, + * (or even the -fPIE one on older versions), it will assume that we are + * building a dynamic object (either a shared library or an executable) that + * may have symbol references that can only be resolved at load time. For a + * variety of reasons (ELF symbol preemption, the CoW footprint of the section + * that is modified by the loader), this results in all references to symbols + * with external linkage to go via entries in the Global Offset Table (GOT), + * which carries absolute addresses which need to be fixed up when the + * executable image is loaded at an offset which is different from its link + * time offset. + * + * Fortunately, there is a way to inform the compiler that such symbol + * references will be satisfied at link time rather than at load time, by + * giving them 'hidden' visibility. + */ + +#pragma GCC visibility push(hidden) -- cgit v1.2.3 From e1ac3e66d301e57472f31ebee81b916e9fa8b35b Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Sat, 15 Aug 2020 12:06:40 +0200 Subject: x86/paravirt: Remove set_pte_at() pv-op On x86 set_pte_at() is now always falling back to set_pte(). So instead of having this fallback after the paravirt maze just drop the set_pte_at paravirt operation and let set_pte_at() use the set_pte() function directly. Signed-off-by: Juergen Gross Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200815100641.26362-6-jgross@suse.com --- include/trace/events/xen.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index a5ccfa67bc5c..3b61b587e137 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -153,26 +153,6 @@ DECLARE_EVENT_CLASS(xen_mmu__set_pte, DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte); -TRACE_EVENT(xen_mmu_set_pte_at, - TP_PROTO(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval), - TP_ARGS(mm, addr, ptep, pteval), - TP_STRUCT__entry( - __field(struct mm_struct *, mm) - __field(unsigned long, addr) - __field(pte_t *, ptep) - __field(pteval_t, pteval) - ), - TP_fast_assign(__entry->mm = mm; - __entry->addr = addr; - __entry->ptep = ptep; - __entry->pteval = pteval.pte), - TP_printk("mm %p addr %lx ptep %p pteval %0*llx (raw %0*llx)", - __entry->mm, __entry->addr, __entry->ptep, - (int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)), - (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval) - ); - TRACE_DEFINE_SIZEOF(pmdval_t); TRACE_EVENT(xen_mmu_set_pmd, -- cgit v1.2.3 From 5f3e7503b97b3d068304ac8bb74faa10b804b24d Mon Sep 17 00:00:00 2001 From: Derek Basehore Date: Fri, 14 Aug 2020 00:56:06 +0300 Subject: drm/panel: Add helper for reading DT rotation This adds a helper function for reading the rotation (panel orientation) from the device tree. Reviewed-by: Sam Ravnborg Tested-by: Dmitry Osipenko Signed-off-by: Derek Basehore Signed-off-by: Dmitry Osipenko Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20200813215609.28643-2-digetx@gmail.com --- include/drm/drm_panel.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 45a1b5a2275d..33605c3f0eba 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -35,6 +35,8 @@ struct drm_device; struct drm_panel; struct display_timing; +enum drm_panel_orientation; + /** * struct drm_panel_funcs - perform operations on a given panel * @@ -188,11 +190,19 @@ int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector #if defined(CONFIG_OF) && defined(CONFIG_DRM_PANEL) struct drm_panel *of_drm_find_panel(const struct device_node *np); +int of_drm_get_panel_orientation(const struct device_node *np, + enum drm_panel_orientation *orientation); #else static inline struct drm_panel *of_drm_find_panel(const struct device_node *np) { return ERR_PTR(-ENODEV); } + +static inline int of_drm_get_panel_orientation(const struct device_node *np, + enum drm_panel_orientation *orientation) +{ + return -ENODEV; +} #endif #if IS_ENABLED(CONFIG_DRM_PANEL) && (IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ -- cgit v1.2.3 From e8ee6c8cb61b676f1a2d6b942329e98224bd8ee9 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 31 Jul 2020 23:08:26 +0300 Subject: dmaengine: dw: Add DMA-channels mask cell support DW DMA IP-core provides a way to synthesize the DMA controller with channels having different parameters like maximum burst-length, multi-block support, maximum data width, etc. Those parameters both explicitly and implicitly affect the channels performance. Since DMA slave devices might be very demanding to the DMA performance, let's provide a functionality for the slaves to be assigned with DW DMA channels, which performance according to the platform engineer fulfill their requirements. After this patch is applied it can be done by passing the mask of suitable DMA-channels either directly in the dw_dma_slave structure instance or as a fifth cell of the DMA DT-property. If mask is zero or not provided, then there is no limitation on the channels allocation. For instance Baikal-T1 SoC is equipped with a DW DMAC engine, which first two channels are synthesized with max burst length of 16, while the rest of the channels have been created with max-burst-len=4. It would seem that the first two channels must be faster than the others and should be more preferable for the time-critical DMA slave devices. In practice it turned out that the situation is quite the opposite. The channels with max-burst-len=4 demonstrated a better performance than the channels with max-burst-len=16 even when they both had been initialized with the same settings. The performance drop of the first two DMA-channels made them unsuitable for the DW APB SSI slave device. No matter what settings they are configured with, full-duplex SPI transfers occasionally experience the Rx FIFO overflow. It means that the DMA-engine doesn't keep up with incoming data pace even though the SPI-bus is enabled with speed of 25MHz while the DW DMA controller is clocked with 50MHz signal. There is no such problem has been noticed for the channels synthesized with max-burst-len=4. Signed-off-by: Serge Semin Link: https://lore.kernel.org/r/20200731200826.9292-6-Sergey.Semin@baikalelectronics.ru Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index fbbeb2f6189b..b34a094b2258 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -26,6 +26,7 @@ struct device; * @dst_id: dst request line * @m_master: memory master for transfers on allocated channel * @p_master: peripheral master for transfers on allocated channel + * @channels: mask of the channels permitted for allocation (zero value means any) * @hs_polarity:set active low polarity of handshake interface */ struct dw_dma_slave { @@ -34,6 +35,7 @@ struct dw_dma_slave { u8 dst_id; u8 m_master; u8 p_master; + u8 channels; bool hs_polarity; }; -- cgit v1.2.3 From d92aabca4df182763cd541d342f2d55f8c0a827c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 25 Jul 2020 21:15:20 -0700 Subject: firmware: bcm47xx_sprom: Fix -Wmissing-prototypes warnings bcm47xx_sprom.h did not include a prototype for bcm47xx_fill_sprom() therefore add one, and make sure we do include that header to fix -Wmissing-prototypes warnings. Reported-by: kernel test robot Signed-off-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer --- include/linux/bcm47xx_sprom.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/bcm47xx_sprom.h b/include/linux/bcm47xx_sprom.h index b0f4424f34fc..f8254fd53e15 100644 --- a/include/linux/bcm47xx_sprom.h +++ b/include/linux/bcm47xx_sprom.h @@ -9,9 +9,19 @@ #include #include +struct ssb_sprom; + #ifdef CONFIG_BCM47XX_SPROM +void bcm47xx_fill_sprom(struct ssb_sprom *sprom, const char *prefix, + bool fallback); int bcm47xx_sprom_register_fallbacks(void); #else +static inline void bcm47xx_fill_sprom(struct ssb_sprom *sprom, + const char *prefix, + bool fallback) +{ +} + static inline int bcm47xx_sprom_register_fallbacks(void) { return -ENOTSUPP; -- cgit v1.2.3 From 68d8904b25df28821425753eaebc8fe992dde236 Mon Sep 17 00:00:00 2001 From: Ajit Pandey Date: Fri, 14 Aug 2020 16:23:04 +0530 Subject: ASoC: Add sc7180-lpass bindings header Add header defining dai-id and mclk id for SC7180 lpass soc. Signed-off-by: Ajit Pandey Signed-off-by: Rohit kumar Acked-by: Rob Herring Link: https://lore.kernel.org/r/1597402388-14112-9-git-send-email-rohitkr@codeaurora.org Signed-off-by: Mark Brown --- include/dt-bindings/sound/sc7180-lpass.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/dt-bindings/sound/sc7180-lpass.h (limited to 'include') diff --git a/include/dt-bindings/sound/sc7180-lpass.h b/include/dt-bindings/sound/sc7180-lpass.h new file mode 100644 index 000000000000..7d988f6346a5 --- /dev/null +++ b/include/dt-bindings/sound/sc7180-lpass.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DT_SC7180_LPASS_H +#define __DT_SC7180_LPASS_H + +#define MI2S_PRIMARY 0 +#define MI2S_SECONDARY 1 + +#define LPASS_MCLK0 0 + +#endif /* __DT_APQ8016_LPASS_H */ -- cgit v1.2.3 From 5292481134b2c4d64e1279158917dc9b53713721 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Sat, 13 Jun 2020 10:21:33 +0200 Subject: MIPS: BMIPS: add BCM6328 power domain definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BCM6328 SoCs have a power domain controller to enable/disable certain components in order to save power. Signed-off-by: Álvaro Fernández Rojas Reviewed-by: Florian Fainelli Reviewed-by: Rob Herring Signed-off-by: Florian Fainelli --- include/dt-bindings/soc/bcm6328-pm.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/dt-bindings/soc/bcm6328-pm.h (limited to 'include') diff --git a/include/dt-bindings/soc/bcm6328-pm.h b/include/dt-bindings/soc/bcm6328-pm.h new file mode 100644 index 000000000000..557e1a69b7f7 --- /dev/null +++ b/include/dt-bindings/soc/bcm6328-pm.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef __DT_BINDINGS_BMIPS_BCM6328_PM_H +#define __DT_BINDINGS_BMIPS_BCM6328_PM_H + +#define BCM6328_POWER_DOMAIN_ADSL2_MIPS 0 +#define BCM6328_POWER_DOMAIN_ADSL2_PHY 1 +#define BCM6328_POWER_DOMAIN_ADSL2_AFE 2 +#define BCM6328_POWER_DOMAIN_SAR 3 +#define BCM6328_POWER_DOMAIN_PCM 4 +#define BCM6328_POWER_DOMAIN_USBD 5 +#define BCM6328_POWER_DOMAIN_USBH 6 +#define BCM6328_POWER_DOMAIN_PCIE 7 +#define BCM6328_POWER_DOMAIN_ROBOSW 8 +#define BCM6328_POWER_DOMAIN_EPHY 9 + +#endif /* __DT_BINDINGS_BMIPS_BCM6328_PM_H */ -- cgit v1.2.3 From 9f9fd9766a288e259ad7cefbf3e45e1ec117b50b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Sat, 13 Jun 2020 10:21:34 +0200 Subject: MIPS: BMIPS: add BCM6362 power domain definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BCM6362 SoCs have a power domain controller to enable/disable certain components in order to save power. Signed-off-by: Álvaro Fernández Rojas Reviewed-by: Florian Fainelli Reviewed-by: Rob Herring Signed-off-by: Florian Fainelli --- include/dt-bindings/soc/bcm6362-pm.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/dt-bindings/soc/bcm6362-pm.h (limited to 'include') diff --git a/include/dt-bindings/soc/bcm6362-pm.h b/include/dt-bindings/soc/bcm6362-pm.h new file mode 100644 index 000000000000..d087ba63c7a1 --- /dev/null +++ b/include/dt-bindings/soc/bcm6362-pm.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef __DT_BINDINGS_BMIPS_BCM6362_PM_H +#define __DT_BINDINGS_BMIPS_BCM6362_PM_H + +#define BCM6362_POWER_DOMAIN_SAR 0 +#define BCM6362_POWER_DOMAIN_IPSEC 1 +#define BCM6362_POWER_DOMAIN_MIPS 2 +#define BCM6362_POWER_DOMAIN_DECT 3 +#define BCM6362_POWER_DOMAIN_USBH 4 +#define BCM6362_POWER_DOMAIN_USBD 5 +#define BCM6362_POWER_DOMAIN_ROBOSW 6 +#define BCM6362_POWER_DOMAIN_PCM 7 +#define BCM6362_POWER_DOMAIN_PERIPH 8 +#define BCM6362_POWER_DOMAIN_ADSL_PHY 9 +#define BCM6362_POWER_DOMAIN_GMII_PADS 10 +#define BCM6362_POWER_DOMAIN_FAP 11 +#define BCM6362_POWER_DOMAIN_PCIE 12 +#define BCM6362_POWER_DOMAIN_WLAN_PADS 13 + +#endif /* __DT_BINDINGS_BMIPS_BCM6362_PM_H */ -- cgit v1.2.3 From 5a3be0d0ccfb21d1223f77746d260450d94df9e4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Sat, 13 Jun 2020 10:21:35 +0200 Subject: MIPS: BMIPS: add BCM63268 power domain definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BCM63268 SoCs have a power domain controller to enable/disable certain components in order to save power. Signed-off-by: Álvaro Fernández Rojas Reviewed-by: Florian Fainelli Reviewed-by: Rob Herring Signed-off-by: Florian Fainelli --- include/dt-bindings/soc/bcm63268-pm.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/dt-bindings/soc/bcm63268-pm.h (limited to 'include') diff --git a/include/dt-bindings/soc/bcm63268-pm.h b/include/dt-bindings/soc/bcm63268-pm.h new file mode 100644 index 000000000000..84ded53a732f --- /dev/null +++ b/include/dt-bindings/soc/bcm63268-pm.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef __DT_BINDINGS_BMIPS_BCM63268_PM_H +#define __DT_BINDINGS_BMIPS_BCM63268_PM_H + +#define BCM63268_POWER_DOMAIN_SAR 0 +#define BCM63268_POWER_DOMAIN_IPSEC 1 +#define BCM63268_POWER_DOMAIN_MIPS 2 +#define BCM63268_POWER_DOMAIN_DECT 3 +#define BCM63268_POWER_DOMAIN_USBH 4 +#define BCM63268_POWER_DOMAIN_USBD 5 +#define BCM63268_POWER_DOMAIN_ROBOSW 6 +#define BCM63268_POWER_DOMAIN_PCM 7 +#define BCM63268_POWER_DOMAIN_PERIPH 8 +#define BCM63268_POWER_DOMAIN_VDSL_PHY 9 +#define BCM63268_POWER_DOMAIN_VDSL_MIPS 10 +#define BCM63268_POWER_DOMAIN_FAP 11 +#define BCM63268_POWER_DOMAIN_PCIE 12 +#define BCM63268_POWER_DOMAIN_WLAN_PADS 13 + +#endif /* __DT_BINDINGS_BMIPS_BCM63268_PM_H */ -- cgit v1.2.3 From 8bf86a155688f3acbc5919cdf58c59378d62a663 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Sat, 13 Jun 2020 10:21:36 +0200 Subject: MIPS: BMIPS: add BCM6318 power domain definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BCM6318 SoCs have a power domain controller to enable/disable certain components in order to save power. Signed-off-by: Álvaro Fernández Rojas Reviewed-by: Florian Fainelli Reviewed-by: Rob Herring Signed-off-by: Florian Fainelli --- include/dt-bindings/soc/bcm6318-pm.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/dt-bindings/soc/bcm6318-pm.h (limited to 'include') diff --git a/include/dt-bindings/soc/bcm6318-pm.h b/include/dt-bindings/soc/bcm6318-pm.h new file mode 100644 index 000000000000..05931dce8333 --- /dev/null +++ b/include/dt-bindings/soc/bcm6318-pm.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef __DT_BINDINGS_BMIPS_BCM6318_PM_H +#define __DT_BINDINGS_BMIPS_BCM6318_PM_H + +#define BCM6318_POWER_DOMAIN_PCIE 0 +#define BCM6318_POWER_DOMAIN_USB 1 +#define BCM6318_POWER_DOMAIN_EPHY0 2 +#define BCM6318_POWER_DOMAIN_EPHY1 3 +#define BCM6318_POWER_DOMAIN_EPHY2 4 +#define BCM6318_POWER_DOMAIN_EPHY3 5 +#define BCM6318_POWER_DOMAIN_LDO2P5 6 +#define BCM6318_POWER_DOMAIN_LDO2P9 7 +#define BCM6318_POWER_DOMAIN_SW1P0 8 +#define BCM6318_POWER_DOMAIN_PAD 9 + +#endif /* __DT_BINDINGS_BMIPS_BCM6318_PM_H */ -- cgit v1.2.3 From c2fe8ebb332eefb3d0543b248e28dd2992c04793 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Aug 2020 21:26:42 +0200 Subject: clk: samsung: s3c64xx: declare s3c64xx_clk_init() in shared header The s3c64xx_clk_init() is defined and used by the clk-s3c64xx driver and also used in the mach-s3c64xx machine code. Move the declaration to a header to fix W=1 build warning: drivers/clk/samsung/clk-s3c64xx.c:391:13: warning: no previous prototype for 's3c64xx_clk_init' [-Wmissing-prototypes] 391 | void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f, Signed-off-by: Krzysztof Kozlowski Reviewed-by: Tomasz Figa Acked-by: Chanwoo Choi Reviewed-by: Stephen Boyd --- include/linux/clk/samsung.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 include/linux/clk/samsung.h (limited to 'include') diff --git a/include/linux/clk/samsung.h b/include/linux/clk/samsung.h new file mode 100644 index 000000000000..7a0824b22eed --- /dev/null +++ b/include/linux/clk/samsung.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Krzysztof Kozlowski + */ + +#ifndef __LINUX_CLK_SAMSUNG_H_ +#define __LINUX_CLK_SAMSUNG_H_ + +#include + +struct device_node; + +#ifdef CONFIG_ARCH_S3C64XX +void s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f, + unsigned long xusbxti_f, bool s3c6400, + void __iomem *base); +#else +static inline void s3c64xx_clk_init(struct device_node *np, + unsigned long xtal_f, + unsigned long xusbxti_f, + bool s3c6400, void __iomem *base) { } +#endif /* CONFIG_ARCH_S3C64XX */ + +#endif /* __LINUX_CLK_SAMSUNG_H_ */ -- cgit v1.2.3 From 16b17fcf77f2145b98cabbca6bfe6ea13c90bb08 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Aug 2020 21:26:43 +0200 Subject: clk: samsung: s3c24xx: declare s3c24xx_common_clk_init() in shared header The s3c2410_common_clk_init() and others are defined and used by the clk-s3c24xx driver and also used in the mach-s3c24xx machine code. Move the declaration to a header to fix W=1 build warnings: drivers/clk/samsung/clk-s3c2410.c:320:13: warning: no previous prototype for 's3c2410_common_clk_init' [-Wmissing-prototypes] 320 | void __init s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f, drivers/clk/samsung/clk-s3c2412.c:205:13: warning: no previous prototype for 's3c2412_common_clk_init' [-Wmissing-prototypes] 205 | void __init s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f, drivers/clk/samsung/clk-s3c2443.c:341:13: warning: no previous prototype for 's3c2443_common_clk_init' [-Wmissing-prototypes] 341 | void __init s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f, Signed-off-by: Krzysztof Kozlowski Acked-by: Chanwoo Choi Reviewed-by: Stephen Boyd --- include/linux/clk/samsung.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/clk/samsung.h b/include/linux/clk/samsung.h index 7a0824b22eed..79097e365f7f 100644 --- a/include/linux/clk/samsung.h +++ b/include/linux/clk/samsung.h @@ -21,4 +21,36 @@ static inline void s3c64xx_clk_init(struct device_node *np, bool s3c6400, void __iomem *base) { } #endif /* CONFIG_ARCH_S3C64XX */ +#ifdef CONFIG_S3C2410_COMMON_CLK +void s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f, + int current_soc, + void __iomem *reg_base); +#else +static inline void s3c2410_common_clk_init(struct device_node *np, + unsigned long xti_f, + int current_soc, + void __iomem *reg_base) { } +#endif /* CONFIG_S3C2410_COMMON_CLK */ + +#ifdef CONFIG_S3C2412_COMMON_CLK +void s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f, + unsigned long ext_f, void __iomem *reg_base); +#else +static inline void s3c2412_common_clk_init(struct device_node *np, + unsigned long xti_f, + unsigned long ext_f, + void __iomem *reg_base) { } +#endif /* CONFIG_S3C2412_COMMON_CLK */ + +#ifdef CONFIG_S3C2443_COMMON_CLK +void s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f, + int current_soc, + void __iomem *reg_base); +#else +static inline void s3c2443_common_clk_init(struct device_node *np, + unsigned long xti_f, + int current_soc, + void __iomem *reg_base) { } +#endif /* CONFIG_S3C2443_COMMON_CLK */ + #endif /* __LINUX_CLK_SAMSUNG_H_ */ -- cgit v1.2.3 From f2bde2546b81b64fb58aa04888fdd82a090b3908 Mon Sep 17 00:00:00 2001 From: Alexei Podtelezhnikov Date: Mon, 27 Apr 2020 23:47:52 -0400 Subject: drm/i915: Remove dubious Valleyview PCI IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 0x0155 is rather Ivy Bridge PCI-E Root Port. 0x0157 from the same commit ff049b6ce21d ("drm/i915: bind driver to ValleyView chipsets") is likely wrong too. Nowhere is it independetly confirmed or mentioned. Signed-off-by: Alexei Podtelezhnikov Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200428034752.3975-1-apodtele@gmail.com Signed-off-by: Rodrigo Vivi --- include/drm/i915_pciids.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 96e408b4bdc9..8e7ae30ebcbb 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -258,9 +258,7 @@ INTEL_VGA_DEVICE(0x0f30, info), \ INTEL_VGA_DEVICE(0x0f31, info), \ INTEL_VGA_DEVICE(0x0f32, info), \ - INTEL_VGA_DEVICE(0x0f33, info), \ - INTEL_VGA_DEVICE(0x0157, info), \ - INTEL_VGA_DEVICE(0x0155, info) + INTEL_VGA_DEVICE(0x0f33, info) #define INTEL_BDW_ULT_GT1_IDS(info) \ INTEL_VGA_DEVICE(0x1606, info), /* GT1 ULT */ \ -- cgit v1.2.3 From cda9edd02425d7902714c60a6f6e31881d2f2741 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Tue, 4 Aug 2020 11:59:53 +0300 Subject: drm/i915: introduce a mechanism to extend execbuf2 We're planning to use this for a couple of new feature where we need to provide additional parameters to execbuf. v2: Check for invalid flags in execbuffer2 (Lionel) v3: Rename I915_EXEC_EXT -> I915_EXEC_USE_EXTENSIONS (Chris) v4: Rebase Move array fence parsing in i915_gem_do_execbuffer() Signed-off-by: Lionel Landwerlin Reviewed-by: Daniel Vetter Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-2-lionel.g.landwerlin@intel.com Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901 Signed-off-by: Rodrigo Vivi --- include/uapi/drm/i915_drm.h | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 00546062e023..dcada8c3a693 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1046,6 +1046,10 @@ struct drm_i915_gem_exec_fence { __u32 flags; }; +enum drm_i915_gem_execbuffer_ext { + DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */ +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -1062,8 +1066,14 @@ struct drm_i915_gem_execbuffer2 { __u32 num_cliprects; /** * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY - * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a - * struct drm_i915_gem_exec_fence *fences. + * & I915_EXEC_USE_EXTENSIONS are not set. + * + * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array + * of struct drm_i915_gem_exec_fence and num_cliprects is the length + * of the array. + * + * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a + * single struct i915_user_extension and num_cliprects is 0. */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (0x3f) @@ -1181,7 +1191,16 @@ struct drm_i915_gem_execbuffer2 { */ #define I915_EXEC_FENCE_SUBMIT (1 << 20) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1)) +/* + * Setting I915_EXEC_USE_EXTENSIONS implies that + * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked + * list of i915_user_extension. Each i915_user_extension node is the base of a + * larger structure. The list of supported structures are listed in the + * drm_i915_gem_execbuffer_ext enum. + */ +#define I915_EXEC_USE_EXTENSIONS (1 << 21) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ -- cgit v1.2.3 From 13149e8bafc4657254831ba6c16ed8780aa64a06 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Tue, 4 Aug 2020 11:59:54 +0300 Subject: drm/i915: add syncobj timeline support Introduces a new parameters to execbuf so that we can specify syncobj handles as well as timeline points. v2: Reuse i915_user_extension_fn v3: Check that the chained extension is only present once (Chris) v4: Check that dma_fence_chain_find_seqno returns a non NULL fence (Lionel) v5: Use BIT_ULL (Chris) v6: Fix issue with already signaled timeline points, dma_fence_chain_find_seqno() setting fence to NULL (Chris) v7: Report ENOENT with invalid syncobj handle (Lionel) v8: Check for out of order timeline point insertion (Chris) v9: After explanations on https://lists.freedesktop.org/archives/dri-devel/2019-August/229287.html drop the ordering check from v8 (Lionel) v10: Set first extension enum item to 1 (Jason) v11: Rebase v12: Allow multiple extension nodes of timeline syncobj (Chris) Signed-off-by: Lionel Landwerlin Co-authored-by: Chris Wilson Reviewed-by: Daniel Vetter (v11) Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-3-lionel.g.landwerlin@intel.com Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901 Signed-off-by: Rodrigo Vivi --- include/uapi/drm/i915_drm.h | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index dcada8c3a693..fa1f3d62f9a6 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_PERF_REVISION 54 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See + * I915_EXEC_USE_EXTENSIONS. + */ +#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55 + /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1046,8 +1052,36 @@ struct drm_i915_gem_exec_fence { __u32 flags; }; -enum drm_i915_gem_execbuffer_ext { - DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */ +/** + * See drm_i915_gem_execbuffer_ext_timeline_fences. + */ +#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 + +/** + * This structure describes an array of drm_syncobj and associated points for + * timeline variants of drm_syncobj. It is invalid to append this structure to + * the execbuf if I915_EXEC_FENCE_ARRAY is set. + */ +struct drm_i915_gem_execbuffer_ext_timeline_fences { + struct i915_user_extension base; + + /** + * Number of element in the handles_ptr & value_ptr arrays. + */ + __u64 fence_count; + + /** + * Pointer to an array of struct drm_i915_gem_exec_fence of length + * fence_count. + */ + __u64 handles_ptr; + + /** + * Pointer to an array of u64 values of length fence_count. Values + * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline + * drm_syncobj is invalid as it turns a drm_syncobj into a binary one. + */ + __u64 values_ptr; }; struct drm_i915_gem_execbuffer2 { -- cgit v1.2.3 From a0308938ec81cd0dca9d75833ec0dd1b8708917e Mon Sep 17 00:00:00 2001 From: David Stevens Date: Tue, 18 Aug 2020 16:13:41 +0900 Subject: virtio: add dma-buf support for exported objects This change adds a new flavor of dma-bufs that can be used by virtio drivers to share exported objects. A virtio dma-buf can be queried by virtio drivers to obtain the UUID which identifies the underlying exported object. Signed-off-by: David Stevens Acked-by: Michael S. Tsirkin Link: http://patchwork.freedesktop.org/patch/msgid/20200818071343.3461203-2-stevensd@chromium.org Signed-off-by: Gerd Hoffmann --- include/linux/virtio.h | 1 + include/linux/virtio_dma_buf.h | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) create mode 100644 include/linux/virtio_dma_buf.h (limited to 'include') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index a493eac08393..55ea329fe72a 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -127,6 +127,7 @@ static inline struct virtio_device *dev_to_virtio(struct device *_dev) void virtio_add_status(struct virtio_device *dev, unsigned int status); int register_virtio_device(struct virtio_device *dev); void unregister_virtio_device(struct virtio_device *dev); +bool is_virtio_device(struct device *dev); void virtio_break_device(struct virtio_device *dev); diff --git a/include/linux/virtio_dma_buf.h b/include/linux/virtio_dma_buf.h new file mode 100644 index 000000000000..a2fdf217ac62 --- /dev/null +++ b/include/linux/virtio_dma_buf.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * dma-bufs for virtio exported objects + * + * Copyright (C) 2020 Google, Inc. + */ + +#ifndef _LINUX_VIRTIO_DMA_BUF_H +#define _LINUX_VIRTIO_DMA_BUF_H + +#include +#include +#include + +/** + * struct virtio_dma_buf_ops - operations possible on exported object dma-buf + * @ops: the base dma_buf_ops. ops.attach MUST be virtio_dma_buf_attach. + * @device_attach: [optional] callback invoked by virtio_dma_buf_attach during + * all attach operations. + * @get_uid: [required] callback to get the uuid of the exported object. + */ +struct virtio_dma_buf_ops { + struct dma_buf_ops ops; + int (*device_attach)(struct dma_buf *dma_buf, + struct dma_buf_attachment *attach); + int (*get_uuid)(struct dma_buf *dma_buf, uuid_t *uuid); +}; + +int virtio_dma_buf_attach(struct dma_buf *dma_buf, + struct dma_buf_attachment *attach); + +struct dma_buf *virtio_dma_buf_export + (const struct dma_buf_export_info *exp_info); +bool is_virtio_dma_buf(struct dma_buf *dma_buf); +int virtio_dma_buf_get_uuid(struct dma_buf *dma_buf, uuid_t *uuid); + +#endif /* _LINUX_VIRTIO_DMA_BUF_H */ -- cgit v1.2.3 From 592d9fba33c275b72cb4dae99c187444daafcd33 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Tue, 18 Aug 2020 16:13:42 +0900 Subject: virtio-gpu: add VIRTIO_GPU_F_RESOURCE_UUID feature This feature allows the guest to request a UUID from the host for a particular virtio_gpu resource. The UUID can then be shared with other virtio devices, to allow the other host devices to access the virtio_gpu's corresponding host resource. Signed-off-by: David Stevens Acked-by: Michael S. Tsirkin Link: http://patchwork.freedesktop.org/patch/msgid/20200818071343.3461203-3-stevensd@chromium.org Signed-off-by: Gerd Hoffmann --- include/uapi/linux/virtio_gpu.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 0c85914d9369..9721d58b4d58 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -50,6 +50,10 @@ * VIRTIO_GPU_CMD_GET_EDID */ #define VIRTIO_GPU_F_EDID 1 +/* + * VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID + */ +#define VIRTIO_GPU_F_RESOURCE_UUID 2 enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -66,6 +70,7 @@ enum virtio_gpu_ctrl_type { VIRTIO_GPU_CMD_GET_CAPSET_INFO, VIRTIO_GPU_CMD_GET_CAPSET, VIRTIO_GPU_CMD_GET_EDID, + VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID, /* 3d commands */ VIRTIO_GPU_CMD_CTX_CREATE = 0x0200, @@ -87,6 +92,7 @@ enum virtio_gpu_ctrl_type { VIRTIO_GPU_RESP_OK_CAPSET_INFO, VIRTIO_GPU_RESP_OK_CAPSET, VIRTIO_GPU_RESP_OK_EDID, + VIRTIO_GPU_RESP_OK_RESOURCE_UUID, /* error responses */ VIRTIO_GPU_RESP_ERR_UNSPEC = 0x1200, @@ -340,4 +346,17 @@ enum virtio_gpu_formats { VIRTIO_GPU_FORMAT_R8G8B8X8_UNORM = 134, }; +/* VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID */ +struct virtio_gpu_resource_assign_uuid { + struct virtio_gpu_ctrl_hdr hdr; + __le32 resource_id; + __le32 padding; +}; + +/* VIRTIO_GPU_RESP_OK_RESOURCE_UUID */ +struct virtio_gpu_resp_resource_uuid { + struct virtio_gpu_ctrl_hdr hdr; + __u8 uuid[16]; +}; + #endif -- cgit v1.2.3 From 242841992ae6f22bd761add2f380b2ef3271ba9a Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Mon, 29 Jun 2020 18:18:37 +0200 Subject: dt-bindings: reset: Add a binding for the RPi Firmware reset controller The firmware running on the RPi VideoCore can be used to reset and initialize HW controlled by the firmware. Reviewed-by: Florian Fainelli Signed-off-by: Nicolas Saenz Julienne Link: https://lore.kernel.org/r/20200629161845.6021-2-nsaenzjulienne@suse.de Signed-off-by: Greg Kroah-Hartman --- include/dt-bindings/reset/raspberrypi,firmware-reset.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/dt-bindings/reset/raspberrypi,firmware-reset.h (limited to 'include') diff --git a/include/dt-bindings/reset/raspberrypi,firmware-reset.h b/include/dt-bindings/reset/raspberrypi,firmware-reset.h new file mode 100644 index 000000000000..1a4f4c792723 --- /dev/null +++ b/include/dt-bindings/reset/raspberrypi,firmware-reset.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Nicolas Saenz Julienne + * Author: Nicolas Saenz Julienne + */ + +#ifndef _DT_BINDINGS_RASPBERRYPI_FIRMWARE_RESET_H +#define _DT_BINDINGS_RASPBERRYPI_FIRMWARE_RESET_H + +#define RASPBERRYPI_FIRMWARE_RESET_ID_USB 0 +#define RASPBERRYPI_FIRMWARE_RESET_NUM_IDS 1 + +#endif -- cgit v1.2.3 From 6b26057aab76b73c5b6a2d44a15b910845bd08cd Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Mon, 29 Jun 2020 18:18:44 +0200 Subject: Revert "firmware: raspberrypi: Introduce vl805 init routine" This reverts commit fbbc5ff3f7f9f4cad562e530ae2cf5d8964fe6d3. The vl805 init routine has moved into drivers/reset/reset-raspberrypi.c Reviewed-by: Florian Fainelli Signed-off-by: Nicolas Saenz Julienne Link: https://lore.kernel.org/r/20200629161845.6021-9-nsaenzjulienne@suse.de Signed-off-by: Greg Kroah-Hartman --- include/soc/bcm2835/raspberrypi-firmware.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h index 3025aca3c358..cc9cdbc66403 100644 --- a/include/soc/bcm2835/raspberrypi-firmware.h +++ b/include/soc/bcm2835/raspberrypi-firmware.h @@ -10,7 +10,6 @@ #include struct rpi_firmware; -struct pci_dev; enum rpi_firmware_property_status { RPI_FIRMWARE_STATUS_REQUEST = 0, @@ -142,7 +141,6 @@ int rpi_firmware_property(struct rpi_firmware *fw, int rpi_firmware_property_list(struct rpi_firmware *fw, void *data, size_t tag_size); struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node); -int rpi_firmware_init_vl805(struct pci_dev *pdev); #else static inline int rpi_firmware_property(struct rpi_firmware *fw, u32 tag, void *data, size_t len) @@ -160,11 +158,6 @@ static inline struct rpi_firmware *rpi_firmware_get(struct device_node *firmware { return NULL; } - -static inline int rpi_firmware_init_vl805(struct pci_dev *pdev) -{ - return 0; -} #endif #endif /* __SOC_RASPBERRY_FIRMWARE_H__ */ -- cgit v1.2.3 From d73568c4ccb01d01e20cd23fefbff8e4a05ddfac Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 18 Aug 2020 10:56:51 +0200 Subject: vt: make vc_data pointers const in selection.h There are many functions declared in selection.h which only read from struct vc_data passed as a parameter. Make all those uses const to hint the compiler a bit. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200818085706.12163-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 2 +- include/linux/consolemap.h | 3 ++- include/linux/selection.h | 14 ++++++++------ 3 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 0670d3491e0e..4b1e26c4cb42 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -74,7 +74,7 @@ struct consw { enum vc_intensity intensity, bool blink, bool underline, bool reverse, bool italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); - u16 *(*con_screen_pos)(struct vc_data *vc, int offset); + u16 *(*con_screen_pos)(const struct vc_data *vc, int offset); unsigned long (*con_getxy)(struct vc_data *vc, unsigned long position, int *px, int *py); /* diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h index 254246673390..bcfce748c9d8 100644 --- a/include/linux/consolemap.h +++ b/include/linux/consolemap.h @@ -17,7 +17,8 @@ #ifdef CONFIG_CONSOLE_TRANSLATIONS struct vc_data; -extern u16 inverse_translate(struct vc_data *conp, int glyph, int use_unicode); +extern u16 inverse_translate(const struct vc_data *conp, int glyph, + int use_unicode); extern unsigned short *set_translate(int m, struct vc_data *vc); extern int conv_uni_to_pc(struct vc_data *conp, long ucs); extern u32 conv_8bit_to_uni(unsigned char c); diff --git a/include/linux/selection.h b/include/linux/selection.h index 5b890ef5b59f..34404a019ebf 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -33,21 +33,23 @@ extern unsigned char default_red[]; extern unsigned char default_grn[]; extern unsigned char default_blu[]; -extern unsigned short *screen_pos(struct vc_data *vc, int w_offset, int viewed); -extern u16 screen_glyph(struct vc_data *vc, int offset); -extern u32 screen_glyph_unicode(struct vc_data *vc, int offset); +extern unsigned short *screen_pos(const struct vc_data *vc, int w_offset, + int viewed); +extern u16 screen_glyph(const struct vc_data *vc, int offset); +extern u32 screen_glyph_unicode(const struct vc_data *vc, int offset); extern void complement_pos(struct vc_data *vc, int offset); extern void invert_screen(struct vc_data *vc, int offset, int count, int shift); -extern void getconsxy(struct vc_data *vc, unsigned char *p); +extern void getconsxy(const struct vc_data *vc, unsigned char *p); extern void putconsxy(struct vc_data *vc, unsigned char *p); -extern u16 vcs_scr_readw(struct vc_data *vc, const u16 *org); +extern u16 vcs_scr_readw(const struct vc_data *vc, const u16 *org); extern void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org); extern void vcs_scr_updated(struct vc_data *vc); extern int vc_uniscr_check(struct vc_data *vc); -extern void vc_uniscr_copy_line(struct vc_data *vc, void *dest, int viewed, +extern void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, + int viewed, unsigned int row, unsigned int col, unsigned int nr); -- cgit v1.2.3 From a5c6bd806dd626103db38dee77796fe758c8df94 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 18 Aug 2020 10:56:52 +0200 Subject: vt: declare xy for get/putconsxy properly That is: 1) call the parameter 'xy' to denote what it really is, not generic 'p' 2) tell the compiler and users that we expect an array: * with at least 2 chars (static 2) * which we don't modify in putconsxy (const) Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200818085706.12163-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/selection.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/selection.h b/include/linux/selection.h index 34404a019ebf..15e36e7ef869 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -40,8 +40,8 @@ extern u32 screen_glyph_unicode(const struct vc_data *vc, int offset); extern void complement_pos(struct vc_data *vc, int offset); extern void invert_screen(struct vc_data *vc, int offset, int count, int shift); -extern void getconsxy(const struct vc_data *vc, unsigned char *p); -extern void putconsxy(struct vc_data *vc, unsigned char *p); +extern void getconsxy(const struct vc_data *vc, unsigned char xy[static 2]); +extern void putconsxy(struct vc_data *vc, unsigned char xy[static const 2]); extern u16 vcs_scr_readw(const struct vc_data *vc, const u16 *org); extern void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org); -- cgit v1.2.3 From b8209f694f7f4256181deea92d30eedb908d6788 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 18 Aug 2020 10:56:53 +0200 Subject: vc: propagate "viewed as bool" from screenpos up viewed is used as a flag, i.e. bool. So treat is as such in most of the places. vcs_vc is handled in the next patch. Note: the last parameter of invert_screen was misnamed in the declaration since 1.1.92. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200818085706.12163-3-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/selection.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/selection.h b/include/linux/selection.h index 15e36e7ef869..170ef28ff26b 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -34,11 +34,11 @@ extern unsigned char default_grn[]; extern unsigned char default_blu[]; extern unsigned short *screen_pos(const struct vc_data *vc, int w_offset, - int viewed); + bool viewed); extern u16 screen_glyph(const struct vc_data *vc, int offset); extern u32 screen_glyph_unicode(const struct vc_data *vc, int offset); extern void complement_pos(struct vc_data *vc, int offset); -extern void invert_screen(struct vc_data *vc, int offset, int count, int shift); +extern void invert_screen(struct vc_data *vc, int offset, int count, bool viewed); extern void getconsxy(const struct vc_data *vc, unsigned char xy[static 2]); extern void putconsxy(struct vc_data *vc, unsigned char xy[static const 2]); @@ -49,7 +49,7 @@ extern void vcs_scr_updated(struct vc_data *vc); extern int vc_uniscr_check(struct vc_data *vc); extern void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, - int viewed, + bool viewed, unsigned int row, unsigned int col, unsigned int nr); -- cgit v1.2.3 From 38df0b8506130c9d94178b2e7d48a21b26e8903b Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 17 Jul 2020 16:53:15 +0200 Subject: media: v4l2-subdev: Introduce [get|set]_mbus_config pad ops Introduce two new pad operations to allow retrieving and configuring the media bus parameters on a subdevice pad. The newly introduced operations aims to replace the s/g_mbus_config video operations, which have been on their way for deprecation since a long time. Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index d4e3b44cf14c..4d7e7e5cf96d 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -670,6 +670,30 @@ struct v4l2_subdev_pad_config { * * @set_frame_desc: set the low level media bus frame parameters, @fd array * may be adjusted by the subdev driver to device capabilities. + * + * @get_mbus_config: get the media bus configuration of a remote sub-device. + * The media bus configuration is usually retrieved from the + * firmware interface at sub-device probe time, immediately + * applied to the hardware and eventually adjusted by the + * driver. Remote sub-devices (usually video receivers) shall + * use this operation to query the transmitting end bus + * configuration in order to adjust their own one accordingly. + * Callers should make sure they get the most up-to-date as + * possible configuration from the remote end, likely calling + * this operation as close as possible to stream on time. The + * operation shall fail if the pad index it has been called on + * is not valid or in case of unrecoverable failures. + * + * @set_mbus_config: set the media bus configuration of a remote sub-device. + * This operations is intended to allow, in combination with + * the get_mbus_config operation, the negotiation of media bus + * configuration parameters between media sub-devices. The + * operation shall not fail if the requested configuration is + * not supported, but the driver shall update the content of + * the %config argument to reflect what has been actually + * applied to the hardware. The operation shall fail if the + * pad index it has been called on is not valid or in case of + * unrecoverable failures. */ struct v4l2_subdev_pad_ops { int (*init_cfg)(struct v4l2_subdev *sd, @@ -710,6 +734,10 @@ struct v4l2_subdev_pad_ops { struct v4l2_mbus_frame_desc *fd); int (*set_frame_desc)(struct v4l2_subdev *sd, unsigned int pad, struct v4l2_mbus_frame_desc *fd); + int (*get_mbus_config)(struct v4l2_subdev *sd, unsigned int pad, + struct v4l2_mbus_config *config); + int (*set_mbus_config)(struct v4l2_subdev *sd, unsigned int pad, + struct v4l2_mbus_config *config); }; /** -- cgit v1.2.3 From aa207a05f95abc3530b7415232f0f73278336bd3 Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Tue, 18 Aug 2020 14:51:45 +0300 Subject: mei: add connect with vtag ioctl This IOCTL is used to associate the current file descriptor with a FW Client (given by UUID), and virtual tag (vtag). The IOCTL opens a communication channel between a host client and a FW client on a tagged channel. From this point on, every reader and write will communicate with the associated FW client on the tagged channel. Upon close() the communication is terminated. The IOCTL argument is a struct with a union that contains the input parameter and the output parameter for this IOCTL. The input parameter is UUID of the FW Client, a vtag [0,255] The output parameter is the properties of the FW client Clients that do not support tagged connection will respond with -EOPNOTSUPP Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Link: https://lore.kernel.org/r/20200818115147.2567012-12-tomas.winkler@intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/mei.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h index c6aec86cc5de..4f3638489d01 100644 --- a/include/uapi/linux/mei.h +++ b/include/uapi/linux/mei.h @@ -66,4 +66,53 @@ struct mei_connect_client_data { */ #define IOCTL_MEI_NOTIFY_GET _IOR('H', 0x03, __u32) +/** + * struct mei_connect_client_vtag - mei client information struct with vtag + * + * @in_client_uuid: UUID of client to connect + * @vtag: virtual tag + * @reserved: reserved for future use + */ +struct mei_connect_client_vtag { + uuid_le in_client_uuid; + __u8 vtag; + __u8 reserved[3]; +}; + +/** + * struct mei_connect_client_data_vtag - IOCTL connect data union + * + * @connect: input connect data + * @out_client_properties: output client data + */ +struct mei_connect_client_data_vtag { + union { + struct mei_connect_client_vtag connect; + struct mei_client out_client_properties; + }; +}; + +/** + * DOC: + * This IOCTL is used to associate the current file descriptor with a + * FW Client (given by UUID), and virtual tag (vtag). + * The IOCTL opens a communication channel between a host client and + * a FW client on a tagged channel. From this point on, every read + * and write will communicate with the associated FW client with + * on the tagged channel. + * Upone close() the communication is terminated. + * + * The IOCTL argument is a struct with a union that contains + * the input parameter and the output parameter for this IOCTL. + * + * The input parameter is UUID of the FW Client, a vtag [0,255] + * The output parameter is the properties of the FW client + * (FW protocool version and max message size). + * + * Clients that do not support tagged connection + * will respond with -EOPNOTSUPP. + */ +#define IOCTL_MEI_CONNECT_CLIENT_VTAG \ + _IOWR('H', 0x04, struct mei_connect_client_data_vtag) + #endif /* _LINUX_MEI_H */ -- cgit v1.2.3 From d9857a6d81d327f39ef7a1ead50ebab458dd5564 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 17 Jul 2020 16:53:19 +0200 Subject: media: v4l2-subdev: Remove [s|g]_mbus_config video ops With all sensor and platform drivers now converted to use the new get_mbus_config and set_mbus_config pad operations, remove the deprecated video operations g_mbus_config and s_mbus_config. Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 4d7e7e5cf96d..6f6795bab737 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -402,12 +402,6 @@ struct v4l2_mbus_frame_desc { * * @query_dv_timings: callback for VIDIOC_QUERY_DV_TIMINGS() ioctl handler code. * - * @g_mbus_config: get supported mediabus configurations - * - * @s_mbus_config: set a certain mediabus configuration. This operation is added - * for compatibility with soc-camera drivers and should not be used by new - * software. - * * @s_rx_buffer: set a host allocated memory buffer for the subdev. The subdev * can adjust @size to a lower value and must not write more data to the * buffer starting at @data than the original value of @size. @@ -435,10 +429,6 @@ struct v4l2_subdev_video_ops { struct v4l2_dv_timings *timings); int (*query_dv_timings)(struct v4l2_subdev *sd, struct v4l2_dv_timings *timings); - int (*g_mbus_config)(struct v4l2_subdev *sd, - struct v4l2_mbus_config *cfg); - int (*s_mbus_config)(struct v4l2_subdev *sd, - const struct v4l2_mbus_config *cfg); int (*s_rx_buffer)(struct v4l2_subdev *sd, void *buf, unsigned int *size); }; -- cgit v1.2.3 From ddf5c927bd362b8b7c5e09e2e2271e4348e76b76 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 17 Jul 2020 16:53:20 +0200 Subject: media: v4l2- mediabus: Add usage note for V4L2_MBUS_* With the removal of the legacy g_mbus_config and s_mbus_config video operations, the sole users of V4L2_MBUS_* flags are now the newly introduced get_mbus_config and set_mbus_config pad operations. As the semantic of the new operations differs from the semantic of the legacy ones, add a usage note in the v4l2-mediabus.h header to specify how to use the flags. Also add a TODO note to record that we intend to replace the existing flags with fields, to prevent users from mixing conflicting values in a single operation call. Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mediabus.h | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 45f88f0248c4..59b1de197114 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -11,9 +11,34 @@ #include #include +/* + * How to use the V4L2_MBUS_* flags: + * Flags are defined for each of the possible states and values of a media + * bus configuration parameter. One and only one bit of each group of flags + * shall be set by the users of the v4l2_subdev_pad_ops.get_mbus_config and + * v4l2_subdev_pad_ops.set_mbus_config operations to ensure that no + * conflicting settings are specified when reporting and setting the media bus + * configuration with the two operations respectively. For example, it is + * invalid to set or clear both the V4L2_MBUS_HSYNC_ACTIVE_HIGH and the + * V4L2_MBUS_HSYNC_ACTIVE_LOW flag at the same time. Instead either flag + * V4L2_MBUS_HSYNC_ACTIVE_HIGH or flag V4L2_MBUS_HSYNC_ACTIVE_LOW shall be + * set. The same is true for the V4L2_MBUS_CSI2_1/2/3/4_LANE flags group: only + * one of these four bits shall be set. + * + * TODO: replace the existing V4L2_MBUS_* flags with structures of fields + * to avoid conflicting settings. + * + * In example: + * #define V4L2_MBUS_HSYNC_ACTIVE_HIGH BIT(2) + * #define V4L2_MBUS_HSYNC_ACTIVE_LOW BIT(3) + * will be replaced by a field whose value reports the intended active state of + * the signal: + * unsigned int v4l2_mbus_hsync_active : 1; + */ + /* Parallel flags */ /* - * Can the client run in master or in slave mode. By "Master mode" an operation + * The client runs in master or in slave mode. By "Master mode" an operation * mode is meant, when the client (e.g., a camera sensor) is producing * horizontal and vertical synchronisation. In "Slave mode" the host is * providing these signals to the slave. @@ -45,17 +70,17 @@ #define V4L2_MBUS_DATA_ENABLE_LOW BIT(15) /* Serial flags */ -/* How many lanes the client can use */ +/* CSI-2 D-PHY number of data lanes. */ #define V4L2_MBUS_CSI2_1_LANE BIT(0) #define V4L2_MBUS_CSI2_2_LANE BIT(1) #define V4L2_MBUS_CSI2_3_LANE BIT(2) #define V4L2_MBUS_CSI2_4_LANE BIT(3) -/* On which channels it can send video data */ +/* CSI-2 Virtual Channel identifiers. */ #define V4L2_MBUS_CSI2_CHANNEL_0 BIT(4) #define V4L2_MBUS_CSI2_CHANNEL_1 BIT(5) #define V4L2_MBUS_CSI2_CHANNEL_2 BIT(6) #define V4L2_MBUS_CSI2_CHANNEL_3 BIT(7) -/* Does it support only continuous or also non-continuous clock mode */ +/* Clock non-continuous mode support. */ #define V4L2_MBUS_CSI2_CONTINUOUS_CLOCK BIT(8) #define V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK BIT(9) -- cgit v1.2.3 From 1ae0965dc21698ba41638c95b5478779f3c4a9e4 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Sat, 1 Aug 2020 12:02:55 +0200 Subject: ASoC: core: Add common helper to parse aux devs from device tree simple-card.c and meson-card-utils.c use pretty much the same helper function to parse auxiliary devices from the device tree. Make it easier for other drivers to parse these from the device tree as well by adding a shared helper function to soc-core.c. snd_soc_of_parse_aux_devs() is pretty much a copy of meson_card_add_aux_devices() from meson-card-utils.c with two minor changes: - Make property name configurable as parameter - Change dev_err() message slightly for consistency with other error messages in soc-core.c Signed-off-by: Stephan Gerhold Reviewed-by: Jerome Brunet Link: https://lore.kernel.org/r/20200801100257.22658-1-stephan@gerhold.net Signed-off-by: Mark Brown --- include/sound/soc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 5e3919ffb00c..a0918d159fd3 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1331,6 +1331,7 @@ void snd_soc_of_parse_audio_prefix(struct snd_soc_card *card, int snd_soc_of_parse_audio_routing(struct snd_soc_card *card, const char *propname); +int snd_soc_of_parse_aux_devs(struct snd_soc_card *card, const char *propname); unsigned int snd_soc_of_parse_daifmt(struct device_node *np, const char *prefix, struct device_node **bitclkmaster, -- cgit v1.2.3 From 4524ac56cdcabf77b734ec8021089cba59cac1ac Mon Sep 17 00:00:00 2001 From: Mayulong Date: Mon, 17 Aug 2020 09:10:30 +0200 Subject: staging: mfd: add a PMIC driver for HiSilicon 6421 SPMI version Add the PMIC SPMI driver for the HiSilicon 6421v600. [mchehab+huawei@kernel.org: keep just the MFD driver on this patch, and renamed filenames to better match other upstream drivers] The compete patch is at: https://github.com/96boards-hikey/linux/commit/08464419fba2 Signed-off-by: Mayulong Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/4ffb2694244baa47387e39e2c5d71243242c1fc1.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 165 +++++++++++++++++++++++++++++++++++ 1 file changed, 165 insertions(+) create mode 100644 include/linux/mfd/hi6421-spmi-pmic.h (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h new file mode 100644 index 000000000000..939b36f617c1 --- /dev/null +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -0,0 +1,165 @@ +/* + * Header file for device driver Hi6421 PMIC + * + * Copyright (c) 2013 Linaro Ltd. + * Copyright (C) 2011 Hisilicon. + * + * Guodong Xu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#ifndef __HISI_PMIC_H +#define __HISI_PMIC_H + +#include + +#define HISI_REGS_ENA_PROTECT_TIME (0) /* in microseconds */ +#define HISI_ECO_MODE_ENABLE (1) +#define HISI_ECO_MODE_DISABLE (0) + +typedef int (*pmic_ocp_callback)(char *); +extern int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler); + +struct irq_mask_info { + int start_addr; + int array; +}; + +struct irq_info { + int start_addr; + int array; +}; + +struct bit_info { + int addr; + int bit; +}; + +struct write_lock { + int addr; + int val; +}; + +struct hisi_pmic { + struct resource *res; + struct device *dev; + void __iomem *regs; + spinlock_t lock; + struct irq_domain *domain; + int irq; + int gpio; + unsigned int *irqs; + int irqnum; + int irqarray; + struct irq_mask_info irq_mask_addr; + struct irq_info irq_addr; + int irqnum1; + int irqarray1; + struct irq_mask_info irq_mask_addr1; + struct irq_info irq_addr1; + struct write_lock normal_lock; + struct write_lock debug_lock; +}; + +/* 0:disable; 1:enable */ +unsigned int get_uv_mntn_status(void); +void clear_uv_mntn_resered_reg_bit(void); +void set_uv_mntn_resered_reg_bit(void); + +#if defined(CONFIG_HISI_PMIC) || defined(CONFIG_HISI_PMIC_PMU_SPMI) +/* Register Access Helpers */ +u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg); +void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val); +void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits); +unsigned int hisi_pmic_reg_read(int addr); +void hisi_pmic_reg_write(int addr, int val); +void hisi_pmic_reg_write_lock(int addr, int val); +int hisi_pmic_array_read(int addr, char *buff, unsigned int len); +int hisi_pmic_array_write(int addr, char *buff, unsigned int len); +extern int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list); +extern int hisi_pmic_get_vbus_status(void); +#if defined(CONFIG_HISI_DIEID) +u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg); +void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val); +#endif +#else +static inline u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg) { return 0; } +static inline void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val) {} +static inline void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits) {} +static inline unsigned int hisi_pmic_reg_read(int addr) { return 0; } +static inline void hisi_pmic_reg_write(int addr, int val) {} +static inline void hisi_pmic_reg_write_lock(int addr, int val) {} +static inline int hisi_pmic_array_read(int addr, char *buff, unsigned int len) { return 0; } +static inline int hisi_pmic_array_write(int addr, char *buff, unsigned int len) { return 0; } +static inline int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list) { return -1; } +static inline int hisi_pmic_get_vbus_status(void) { return 1; } +static inline u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg) { return 0; } +static inline void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val) {} +#endif + +#ifdef CONFIG_HISI_HI6421V500_PMU +enum pmic_irq_list { + POR_D45MR = 0, + VBUS_CONNECT, + VBUS_DISCONNECT, + ALARMON_R, + HOLD_6S, + HOLD_1S, + POWERKEY_UP, + POWERKEY_DOWN, + OCP_SCP_R, + COUL_R, + VSYS_OV, + VSYS_UV, + VSYS_PWROFF_ABS, + VSYS_PWROFF_DEB, + THSD_OTMP140, + THSD_OTMP125, + HRESETN, + SIM0_HPD_R = 24, + SIM0_HPD_F, + SIM0_HPD_H, + SIM0_HPD_L, + SIM1_HPD_R, + SIM1_HPD_F, + SIM1_HPD_H, + SIM1_HPD_L, + PMIC_IRQ_LIST_MAX, +}; +#else +enum pmic_irq_list { + OTMP = 0, + VBUS_CONNECT, + VBUS_DISCONNECT, + ALARMON_R, + HOLD_6S, + HOLD_1S, + POWERKEY_UP, + POWERKEY_DOWN, + OCP_SCP_R, + COUL_R, + SIM0_HPD_R, + SIM0_HPD_F, + SIM1_HPD_R, + SIM1_HPD_F, + PMIC_IRQ_LIST_MAX, +}; +#endif + +#ifdef CONFIG_HISI_SR_DEBUG +extern void get_ip_regulator_state(void); +#endif +#endif /* __HISI_PMIC_H */ + -- cgit v1.2.3 From 489b1a36b111b6a3a4ac1acf29de5cf154810887 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 17 Aug 2020 09:10:31 +0200 Subject: staging: mfd: hi6421-spmi-pmic: get rid of unused code There are some checks there which could make sense for downstream builds, but doesn't make much sense for upstream ones. They came from the official Hikey970 tree from Linaro, but even there, the commented-out code is not set via other Kconfig vars. So, let's just get rid of that. If needed later, this patch can be (partially?) reversed. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/ecbef801f6c32ba0850ad9e5c534a4304807df3b.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 42 ------------------------------------ 1 file changed, 42 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 939b36f617c1..5be9b4d3f207 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -78,7 +78,6 @@ unsigned int get_uv_mntn_status(void); void clear_uv_mntn_resered_reg_bit(void); void set_uv_mntn_resered_reg_bit(void); -#if defined(CONFIG_HISI_PMIC) || defined(CONFIG_HISI_PMIC_PMU_SPMI) /* Register Access Helpers */ u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg); void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val); @@ -90,11 +89,6 @@ int hisi_pmic_array_read(int addr, char *buff, unsigned int len); int hisi_pmic_array_write(int addr, char *buff, unsigned int len); extern int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list); extern int hisi_pmic_get_vbus_status(void); -#if defined(CONFIG_HISI_DIEID) -u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg); -void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val); -#endif -#else static inline u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg) { return 0; } static inline void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val) {} static inline void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits) {} @@ -107,38 +101,7 @@ static inline int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list) { return static inline int hisi_pmic_get_vbus_status(void) { return 1; } static inline u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg) { return 0; } static inline void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val) {} -#endif -#ifdef CONFIG_HISI_HI6421V500_PMU -enum pmic_irq_list { - POR_D45MR = 0, - VBUS_CONNECT, - VBUS_DISCONNECT, - ALARMON_R, - HOLD_6S, - HOLD_1S, - POWERKEY_UP, - POWERKEY_DOWN, - OCP_SCP_R, - COUL_R, - VSYS_OV, - VSYS_UV, - VSYS_PWROFF_ABS, - VSYS_PWROFF_DEB, - THSD_OTMP140, - THSD_OTMP125, - HRESETN, - SIM0_HPD_R = 24, - SIM0_HPD_F, - SIM0_HPD_H, - SIM0_HPD_L, - SIM1_HPD_R, - SIM1_HPD_F, - SIM1_HPD_H, - SIM1_HPD_L, - PMIC_IRQ_LIST_MAX, -}; -#else enum pmic_irq_list { OTMP = 0, VBUS_CONNECT, @@ -156,10 +119,5 @@ enum pmic_irq_list { SIM1_HPD_F, PMIC_IRQ_LIST_MAX, }; -#endif - -#ifdef CONFIG_HISI_SR_DEBUG -extern void get_ip_regulator_state(void); -#endif #endif /* __HISI_PMIC_H */ -- cgit v1.2.3 From 4b5e9b39e7dd9e6b980ad588f1f7a36fe7cda044 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 17 Aug 2020 09:10:33 +0200 Subject: staging: mfd: hi6421-spmi-pmic: get rid of the static vars There are several static vars inside this driver. Get rid of them. While here, add a SPDX header file. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/19c497fc2bb1d3a95863d92cac89869d5abe3f2e.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 5be9b4d3f207..e0a8b50f95fc 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Header file for device driver Hi6421 PMIC * @@ -5,19 +6,6 @@ * Copyright (C) 2011 Hisilicon. * * Guodong Xu - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ #ifndef __HISI_PMIC_H @@ -25,12 +13,12 @@ #include -#define HISI_REGS_ENA_PROTECT_TIME (0) /* in microseconds */ +#define HISI_REGS_ENA_PROTECT_TIME (0) /* in microseconds */ #define HISI_ECO_MODE_ENABLE (1) #define HISI_ECO_MODE_DISABLE (0) typedef int (*pmic_ocp_callback)(char *); -extern int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler); +int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler); struct irq_mask_info { int start_addr; @@ -71,6 +59,8 @@ struct hisi_pmic { struct irq_info irq_addr1; struct write_lock normal_lock; struct write_lock debug_lock; + + unsigned int g_extinterrupt_flag; }; /* 0:disable; 1:enable */ -- cgit v1.2.3 From 4860b39f545fd96805c6400bd185de4fb383a2c7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 17 Aug 2020 09:10:34 +0200 Subject: staging: mfd: hi6421-spmi-pmic: cleanup hi6421-spmi-pmic.h header There are several external vars that are defined there, which are not needed anymore. Get rid of them. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/3dbc3f3876275404153da52b84e5dcef09faf644.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index e0a8b50f95fc..1f986dd5f31c 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -63,34 +63,9 @@ struct hisi_pmic { unsigned int g_extinterrupt_flag; }; -/* 0:disable; 1:enable */ -unsigned int get_uv_mntn_status(void); -void clear_uv_mntn_resered_reg_bit(void); -void set_uv_mntn_resered_reg_bit(void); - -/* Register Access Helpers */ u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg); void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val); void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits); -unsigned int hisi_pmic_reg_read(int addr); -void hisi_pmic_reg_write(int addr, int val); -void hisi_pmic_reg_write_lock(int addr, int val); -int hisi_pmic_array_read(int addr, char *buff, unsigned int len); -int hisi_pmic_array_write(int addr, char *buff, unsigned int len); -extern int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list); -extern int hisi_pmic_get_vbus_status(void); -static inline u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg) { return 0; } -static inline void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val) {} -static inline void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits) {} -static inline unsigned int hisi_pmic_reg_read(int addr) { return 0; } -static inline void hisi_pmic_reg_write(int addr, int val) {} -static inline void hisi_pmic_reg_write_lock(int addr, int val) {} -static inline int hisi_pmic_array_read(int addr, char *buff, unsigned int len) { return 0; } -static inline int hisi_pmic_array_write(int addr, char *buff, unsigned int len) { return 0; } -static inline int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list) { return -1; } -static inline int hisi_pmic_get_vbus_status(void) { return 1; } -static inline u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg) { return 0; } -static inline void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val) {} enum pmic_irq_list { OTMP = 0, @@ -110,4 +85,3 @@ enum pmic_irq_list { PMIC_IRQ_LIST_MAX, }; #endif /* __HISI_PMIC_H */ - -- cgit v1.2.3 From bd07d62a47290ca3ceee58f373fa05464edc6eb5 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 17 Aug 2020 09:10:36 +0200 Subject: staging: mfd: hi6421-spmi-pmic: get rid of unused OF properties There are several OF properties that aren't used by Hikey 970, and some are not even used inside the driver. So, drop them, as as this makes easier to document what's actually used. If latter needed, those could be re-added later. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/332f96c178b81bf1e9908a1da2127f043909ae0c.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 1f986dd5f31c..41b61de48259 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -48,19 +48,11 @@ struct hisi_pmic { struct irq_domain *domain; int irq; int gpio; - unsigned int *irqs; + unsigned int *irqs; int irqnum; int irqarray; - struct irq_mask_info irq_mask_addr; - struct irq_info irq_addr; - int irqnum1; - int irqarray1; - struct irq_mask_info irq_mask_addr1; - struct irq_info irq_addr1; - struct write_lock normal_lock; - struct write_lock debug_lock; - - unsigned int g_extinterrupt_flag; + struct irq_mask_info irq_mask_addr; + struct irq_info irq_addr; }; u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg); -- cgit v1.2.3 From 1eb2784a90925d48500f6baac1fa1870085c4121 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 17 Aug 2020 09:10:38 +0200 Subject: staging: mfd: hi6421-spmi-pmic: change namespace on its functions Rename the functions used internally inside the driver in order for them to follow the driver's name. While here, get rid of some unused definitions at the header file. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/bfa8bf33f71612b1511d73269ca242d0d4e70940.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 51 ++++++++++++++---------------------- 1 file changed, 19 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 41b61de48259..d12ad7484018 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -17,49 +17,36 @@ #define HISI_ECO_MODE_ENABLE (1) #define HISI_ECO_MODE_DISABLE (0) -typedef int (*pmic_ocp_callback)(char *); -int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler); - -struct irq_mask_info { +struct hi6421_spmi_irq_mask_info { int start_addr; int array; }; -struct irq_info { +struct hi6421_spmi_irq_info { int start_addr; int array; }; -struct bit_info { - int addr; - int bit; -}; - -struct write_lock { - int addr; - int val; -}; - -struct hisi_pmic { - struct resource *res; - struct device *dev; - void __iomem *regs; - spinlock_t lock; - struct irq_domain *domain; - int irq; - int gpio; - unsigned int *irqs; - int irqnum; - int irqarray; - struct irq_mask_info irq_mask_addr; - struct irq_info irq_addr; +struct hi6421_spmi_pmic { + struct resource *res; + struct device *dev; + void __iomem *regs; + spinlock_t lock; + struct irq_domain *domain; + int irq; + int gpio; + unsigned int *irqs; + int irqnum; + int irqarray; + struct hi6421_spmi_irq_mask_info irq_mask_addr; + struct hi6421_spmi_irq_info irq_addr; }; -u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg); -void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val); -void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits); +u32 hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg); +void hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val); +void hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg, u32 mask, u32 bits); -enum pmic_irq_list { +enum hi6421_spmi_pmic_irq_list { OTMP = 0, VBUS_CONNECT, VBUS_DISCONNECT, -- cgit v1.2.3 From 4d70881afdeb261ee318447ed0232b96946ecabc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 17 Aug 2020 09:10:39 +0200 Subject: staging: mfd: hi6421-spmi-pmic: fix some coding style issues Checkpatch complains about some minor issues inside this driver that were not addressed by the previous patch. Address them. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/84b53d20632c84cc60b8dadfe937f3c54b355cef.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index d12ad7484018..403fd8bb45fa 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -38,7 +38,7 @@ struct hi6421_spmi_pmic { unsigned int *irqs; int irqnum; int irqarray; - struct hi6421_spmi_irq_mask_info irq_mask_addr; + struct hi6421_spmi_irq_mask_info irq_mask_addr; struct hi6421_spmi_irq_info irq_addr; }; -- cgit v1.2.3 From 6b946699252c68b0c792896eded217269c9aa286 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 17 Aug 2020 09:10:41 +0200 Subject: staging: mfd: hi6421-spmi-pmic: cleanup the code There are several small cleanups that can be done in order to make the code more prepared to be upstreamed. Suggested-by: Jonathan Cameron Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/823792ba2f69e613629ab52a33e5728d54e2288b.1597647359.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 403fd8bb45fa..ff3adfa7b3ec 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -36,15 +36,17 @@ struct hi6421_spmi_pmic { int irq; int gpio; unsigned int *irqs; + int irqnum; int irqarray; - struct hi6421_spmi_irq_mask_info irq_mask_addr; - struct hi6421_spmi_irq_info irq_addr; + int irq_mask_addr; + int irq_addr; }; -u32 hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg); -void hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val); -void hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg, u32 mask, u32 bits); +int hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg); +int hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val); +int hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg, + u32 mask, u32 bits); enum hi6421_spmi_pmic_irq_list { OTMP = 0, -- cgit v1.2.3 From 9f0c4fa111dc909ca545c45ea20ec84da555ce16 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 23 Jul 2020 10:11:10 -0700 Subject: perf/core: Add a new PERF_EV_CAP_SIBLING event capability Current perf assumes that events in a group are independent. Close an event doesn't impact the value of the other events in the same group. If the closed event is a member, after the event closure, other events are still running like a group. If the closed event is a leader, other events are running as singleton events. Add PERF_EV_CAP_SIBLING to allow events to indicate they require being part of a group, and when the leader dies they cannot exist independently. Suggested-by: Peter Zijlstra Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200723171117.9918-8-kan.liang@linux.intel.com --- include/linux/perf_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 04a49ccc7beb..6048650f8c1d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -576,9 +576,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. + * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and + * cannot be a group leader. If an event with this flag is detached from the + * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) +#define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) -- cgit v1.2.3 From 2cb5383b30d47c446ec7d884cd80f93ffcc31817 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 23 Jul 2020 10:11:14 -0700 Subject: perf/x86/intel: Support per-thread RDPMC TopDown metrics Starts from Ice Lake, the TopDown metrics are directly available as fixed counters and do not require generic counters. Also, the TopDown metrics can be collected per thread. Extend the RDPMC usage to support per-thread TopDown metrics. The RDPMC index of the PERF_METRICS will be output if RDPMC users ask for the RDPMC index of the metrics events. To support per thread RDPMC TopDown, the metrics and slots counters have to be saved/restored during the context switching. The last_period and period_left are not used in the counting mode. Use the fields for saved_metric and saved_slots. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200723171117.9918-12-kan.liang@linux.intel.com --- include/linux/perf_event.h | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6048650f8c1d..46a3974eb4fe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -212,17 +212,26 @@ struct hw_perf_event { */ u64 sample_period; - /* - * The period we started this sample with. - */ - u64 last_period; + union { + struct { /* Sampling */ + /* + * The period we started this sample with. + */ + u64 last_period; - /* - * However much is left of the current period; note that this is - * a full 64bit value and allows for generation of periods longer - * than hardware might allow. - */ - local64_t period_left; + /* + * However much is left of the current period; + * note that this is a full 64bit value and + * allows for generation of periods longer + * than hardware might allow. + */ + local64_t period_left; + }; + struct { /* Topdown events counting for context switch */ + u64 saved_metric; + u64 saved_slots; + }; + }; /* * State for throttling the event, see __perf_event_overflow() and -- cgit v1.2.3 From b240d0143bfbc96f610405f978e4753fd663cbfc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 18 Aug 2020 16:58:54 +0200 Subject: staging: mfd: hi6421-spmi-pmic: get rid of interrupt properties Both irqnum and irqarray properties reflect the same thing: the number of bits and bytes for interrupts at this chipset. E. g.: irqnum = 8 x irqarray This can be seen by the way pending interrupts are handled: /* During probe time */ pmic->irqs = devm_kzalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL); /* While handling IRQs */ for (i = 0; i < pmic->irqarray; i++) { pending = hi6421_spmi_pmic_read(pmic, (i + pmic->irq_addr)); pending &= 0xff; for_each_set_bit(offset, &pending, 8) generic_handle_irq(pmic->irqs[offset + i * 8]); } Going further, there are some logic at the driver which assumes that irqarray is 2: /* solve powerkey order */ if ((i == HISI_IRQ_KEY_NUM) && ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) { generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_DOWN]); generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_UP]); pending &= (~HISI_IRQ_KEY_VALUE); } As HISI_IRQ_KEY_DOWN and HISI_IRQ_KEY_UP are fixed values and don't depend on irqnum/irqarray. The IRQ addr and mask addr seem to be also fixed, based on some comments at the OF parsing code. So, get rid of them too, removing the of parsing function completely. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/e231244e42cb5b56240705cac2f987e11a078038.1597762400.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index ff3adfa7b3ec..2c8896fd852e 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -17,16 +17,6 @@ #define HISI_ECO_MODE_ENABLE (1) #define HISI_ECO_MODE_DISABLE (0) -struct hi6421_spmi_irq_mask_info { - int start_addr; - int array; -}; - -struct hi6421_spmi_irq_info { - int start_addr; - int array; -}; - struct hi6421_spmi_pmic { struct resource *res; struct device *dev; @@ -36,11 +26,6 @@ struct hi6421_spmi_pmic { int irq; int gpio; unsigned int *irqs; - - int irqnum; - int irqarray; - int irq_mask_addr; - int irq_addr; }; int hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg); -- cgit v1.2.3 From a21a4391f20c0ab45db452e22bc3e8afe8b36e46 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 8 Jul 2020 16:39:24 +0000 Subject: x86/resctrl: Include pid.h We are about to disturb the header soup. This header uses struct pid and struct pid_namespace. Include their header. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Reinette Chatre Link: https://lkml.kernel.org/r/20200708163929.2783-6-james.morse@arm.com --- include/linux/resctrl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index daf5cf64c6a6..9b05af9b3e28 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -2,6 +2,8 @@ #ifndef _RESCTRL_H #define _RESCTRL_H +#include + #ifdef CONFIG_PROC_CPU_RESCTRL int proc_resctrl_show(struct seq_file *m, -- cgit v1.2.3 From d6673746d69909f9ab52cf9fe1f9a21fca202e0c Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 30 Jul 2020 11:12:35 +0300 Subject: RDMA: Remove constant domain argument from flow creation call The "domain" argument is constant and modern device (mlx5) doesn't support anything except IB_FLOW_DOMAIN_USER, so delete this extra parameter and simplify code. Link: https://lore.kernel.org/r/20200730081235.1581127-4-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index c0b2fa7e9b95..55dfe0e9d1d6 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1863,17 +1863,6 @@ enum ib_flow_spec_type { #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 10 -/* Flow steering rule priority is set according to it's domain. - * Lower domain value means higher priority. - */ -enum ib_flow_domain { - IB_FLOW_DOMAIN_USER, - IB_FLOW_DOMAIN_ETHTOOL, - IB_FLOW_DOMAIN_RFS, - IB_FLOW_DOMAIN_NIC, - IB_FLOW_DOMAIN_NUM /* Must be last */ -}; - enum ib_flow_flags { IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */ @@ -2471,7 +2460,7 @@ struct ib_device_ops { void (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); struct ib_flow *(*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, - int domain, struct ib_udata *udata); + struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); struct ib_flow_action *(*create_flow_action_esp)( struct ib_device *device, -- cgit v1.2.3 From a4e6a1dd57469d6ecee084db1507d3e37908d1e2 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Fri, 31 Jul 2020 09:04:20 +0300 Subject: RDMA/efa: Introduce SRD RNR retry This patch introduces the ability to configure SRD QPs with the RNR retry parameter when issuing a modify QP command. In addition, a capability bit was added to report support to the userspace library. Link: https://lore.kernel.org/r/20200731060420.17053-5-galpress@amazon.com Reviewed-by: Firas JahJah Reviewed-by: Yossi Leybovich Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/efa-abi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h index 507a2862bedb..f89fbb5b1e8d 100644 --- a/include/uapi/rdma/efa-abi.h +++ b/include/uapi/rdma/efa-abi.h @@ -105,6 +105,7 @@ struct efa_ibv_create_ah_resp { enum { EFA_QUERY_DEVICE_CAPS_RDMA_READ = 1 << 0, + EFA_QUERY_DEVICE_CAPS_RNR_RETRY = 1 << 1, }; struct efa_ibv_ex_query_device_resp { -- cgit v1.2.3 From c0f4979e90eaa4cd4a63ae95fbf8e65a85150a5f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 5 Aug 2020 14:28:52 -0300 Subject: RDMA/cm: Remove unused cm_class Previous commits removed all references to the /sys/class/infiniband_cm/ directory represented by the cm_class symbol. Remove the directory and cm_class. Fixes: a1a8e4a85cf7 ("rdma: Delete the ib_ucm module") Link: https://lore.kernel.org/r/0-v1-90096a98c476+205-remove_cm_leftovers_jgg@nvidia.com Signed-off-by: Jason Gunthorpe --- include/rdma/ib_cm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h index 382427add677..e23eb357b761 100644 --- a/include/rdma/ib_cm.h +++ b/include/rdma/ib_cm.h @@ -14,9 +14,6 @@ #include #include -/* ib_cm and ib_user_cm modules share /sys/class/infiniband_cm */ -extern struct class cm_class; - enum ib_cm_state { IB_CM_IDLE, IB_CM_LISTEN, -- cgit v1.2.3 From 8aa26c575fb343ebde810b30dad0cba7d8121efb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 18 Aug 2020 10:17:33 +0200 Subject: netlink: make NLA_BINARY validation more flexible Add range validation for NLA_BINARY, allowing validation of any combination of combination minimum or maximum lengths, using the existing NLA_POLICY_RANGE()/NLA_POLICY_FULL_RANGE() macros, just like for integers where the value is checked. Also make NLA_POLICY_EXACT_LEN(), NLA_POLICY_EXACT_LEN_WARN() and NLA_POLICY_MIN_LEN() special cases of this, removing the old types NLA_EXACT_LEN and NLA_MIN_LEN. This allows us to save some code where both minimum and maximum lengths are requires, currently the policy only allows maximum (NLA_BINARY), minimum (NLA_MIN_LEN) or exact (NLA_EXACT_LEN), so a range of lengths cannot be accepted and must be checked by the code that consumes the attributes later. Also, this allows advertising the correct ranges in the policy export to userspace. Here, NLA_MIN_LEN and NLA_EXACT_LEN already were special cases of NLA_BINARY with min and min/max length respectively. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/netlink.h | 58 +++++++++++++++++++++++++++------------------------ 1 file changed, 31 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index c0411f14fb53..fdd317f8fde4 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -181,8 +181,6 @@ enum { NLA_S64, NLA_BITFIELD32, NLA_REJECT, - NLA_EXACT_LEN, - NLA_MIN_LEN, __NLA_TYPE_MAX, }; @@ -199,11 +197,11 @@ struct netlink_range_validation_signed { enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, + NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, - NLA_VALIDATE_WARN_TOO_LONG, }; /** @@ -222,7 +220,7 @@ enum nla_policy_validation { * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload - * NLA_MIN_LEN Minimum length of attribute payload + * (but see also below with the validation type) * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if @@ -237,11 +235,6 @@ enum nla_policy_validation { * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused - * NLA_EXACT_LEN Attribute should have exactly this length, otherwise - * it is rejected or warned about, the latter happening - * if and only if the `validation_type' is set to - * NLA_VALIDATE_WARN_TOO_LONG. - * NLA_MIN_LEN Minimum length of attribute payload * All other Minimum length of attribute payload * * Meaning of validation union: @@ -296,6 +289,11 @@ enum nla_policy_validation { * pointer to a struct netlink_range_validation_signed * that indicates the min/max values. * Use NLA_POLICY_FULL_RANGE_SIGNED(). + * + * NLA_BINARY If the validation type is like the ones for integers + * above, then the min/max length (not value like for + * integers) of the attribute is enforced. + * * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: @@ -309,7 +307,7 @@ enum nla_policy_validation { * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, - * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) }, + * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)), * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ @@ -335,9 +333,10 @@ struct nla_policy { * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT - * for any types >= this, so need to use NLA_MIN_LEN to get the - * previous pure { .len = xyz } behaviour. The advantage of this - * is that types not specified in the policy will be rejected. + * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to + * get the previous pure { .len = xyz } behaviour. The advantage + * of this is that types not specified in the policy will be + * rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones @@ -349,12 +348,6 @@ struct nla_policy { }; }; -#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } -#define NLA_POLICY_EXACT_LEN_WARN(_len) \ - { .type = NLA_EXACT_LEN, .len = _len, \ - .validation_type = NLA_VALIDATE_WARN_TOO_LONG, } -#define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len } - #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) @@ -370,19 +363,21 @@ struct nla_policy { { .type = NLA_BITFIELD32, .bitfield32_valid = valid } #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) -#define NLA_ENSURE_UINT_TYPE(tp) \ +#define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 || \ tp == NLA_U32 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16 || \ tp == NLA_S32 || tp == NLA_S64) + tp) -#define NLA_ENSURE_INT_TYPE(tp) \ +#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ tp == NLA_S16 || tp == NLA_U16 || \ tp == NLA_S32 || tp == NLA_U32 || \ tp == NLA_S64 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ @@ -390,14 +385,14 @@ struct nla_policy { tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_FULL_RANGE(tp, _range) { \ - .type = NLA_ENSURE_UINT_TYPE(tp), \ + .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range = _range, \ } @@ -409,13 +404,13 @@ struct nla_policy { } #define NLA_POLICY_MIN(tp, _min) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } @@ -427,6 +422,15 @@ struct nla_policy { .len = __VA_ARGS__ + 0, \ } +#define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len) +#define NLA_POLICY_EXACT_LEN_WARN(_len) { \ + .type = NLA_BINARY, \ + .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \ + .min = _len, \ + .max = _len \ +} +#define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) + /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request -- cgit v1.2.3 From e2d732fdb7a9e421720a644580cd6a9400f97f60 Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Tue, 11 Aug 2020 19:59:58 -0400 Subject: drm/scheduler: Scheduler priority fixes (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove DRM_SCHED_PRIORITY_LOW, as it was used in only one place. Rename and separate by a line DRM_SCHED_PRIORITY_MAX to DRM_SCHED_PRIORITY_COUNT as it represents a (total) count of said priorities and it is used as such in loops throughout the code. (0-based indexing is the the count number.) Remove redundant word HIGH in priority names, and rename *KERNEL* to *HIGH*, as it really means that, high. v2: Add back KERNEL and remove SW and HW, in lieu of a single HIGH between NORMAL and KERNEL. Signed-off-by: Luben Tuikov Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/drm/gpu_scheduler.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index a21b3b92135a..b30026ccd564 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -33,14 +33,16 @@ struct drm_gpu_scheduler; struct drm_sched_rq; +/* These are often used as an (initial) index + * to an array, and as such should start at 0. + */ enum drm_sched_priority { DRM_SCHED_PRIORITY_MIN, - DRM_SCHED_PRIORITY_LOW = DRM_SCHED_PRIORITY_MIN, DRM_SCHED_PRIORITY_NORMAL, - DRM_SCHED_PRIORITY_HIGH_SW, - DRM_SCHED_PRIORITY_HIGH_HW, + DRM_SCHED_PRIORITY_HIGH, DRM_SCHED_PRIORITY_KERNEL, - DRM_SCHED_PRIORITY_MAX, + + DRM_SCHED_PRIORITY_COUNT, DRM_SCHED_PRIORITY_INVALID = -1, DRM_SCHED_PRIORITY_UNSET = -2 }; @@ -274,7 +276,7 @@ struct drm_gpu_scheduler { uint32_t hw_submission_limit; long timeout; const char *name; - struct drm_sched_rq sched_rq[DRM_SCHED_PRIORITY_MAX]; + struct drm_sched_rq sched_rq[DRM_SCHED_PRIORITY_COUNT]; wait_queue_head_t wake_up_worker; wait_queue_head_t job_scheduled; atomic_t hw_rq_count; -- cgit v1.2.3 From 9af5e21dace795891544042abda877ada39abacc Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Tue, 11 Aug 2020 20:56:58 -0400 Subject: drm/scheduler: Remove priority macro INVALID (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove DRM_SCHED_PRIORITY_INVALID. We no longer carry around an invalid priority and cut it off at the source. Backwards compatibility behaviour of AMDGPU CTX IOCTL passing in garbage for context priority from user space and then mapping that to DRM_SCHED_PRIORITY_NORMAL is preserved. v2: Revert "res" --> "r" and "prio" --> "priority". Signed-off-by: Luben Tuikov Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/drm/gpu_scheduler.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index b30026ccd564..a33590e62108 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -43,7 +43,6 @@ enum drm_sched_priority { DRM_SCHED_PRIORITY_KERNEL, DRM_SCHED_PRIORITY_COUNT, - DRM_SCHED_PRIORITY_INVALID = -1, DRM_SCHED_PRIORITY_UNSET = -2 }; -- cgit v1.2.3 From cfe7ddcbd72dc67ce5749cc6f451a2b0c6aec5b5 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:47 +0100 Subject: ARM, sched/topology: Remove SD_SHARE_POWERDOMAIN This flag was introduced in 2014 by commit: d77b3ed5c9f8 ("sched: Add a new SD_SHARE_POWERDOMAIN for sched_domain") but AFAIA it was never leveraged by the scheduler. The closest thing I can think of is EAS caring about frequency domains, and it does that by leveraging performance domains. Remove the flag. No change in functionality is expected. Suggested-by: Morten Rasmussen Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Reviewed-by: Dietmar Eggemann Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-2-valentin.schneider@arm.com --- include/linux/sched/topology.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 820511289857..6ec7d7c1d1e3 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -18,13 +18,12 @@ #define SD_WAKE_AFFINE 0x0010 /* Wake task to waking CPU */ #define SD_ASYM_CPUCAPACITY 0x0020 /* Domain members have different CPU capacities */ #define SD_SHARE_CPUCAPACITY 0x0040 /* Domain members share CPU capacity */ -#define SD_SHARE_POWERDOMAIN 0x0080 /* Domain members share power domain */ -#define SD_SHARE_PKG_RESOURCES 0x0100 /* Domain members share CPU pkg resources */ -#define SD_SERIALIZE 0x0200 /* Only a single load balancing instance */ -#define SD_ASYM_PACKING 0x0400 /* Place busy groups earlier in the domain */ -#define SD_PREFER_SIBLING 0x0800 /* Prefer to place tasks in a sibling domain */ -#define SD_OVERLAP 0x1000 /* sched_domains of this level overlap */ -#define SD_NUMA 0x2000 /* cross-node balancing */ +#define SD_SHARE_PKG_RESOURCES 0x0080 /* Domain members share CPU pkg resources */ +#define SD_SERIALIZE 0x0100 /* Only a single load balancing instance */ +#define SD_ASYM_PACKING 0x0200 /* Place busy groups earlier in the domain */ +#define SD_PREFER_SIBLING 0x0400 /* Prefer to place tasks in a sibling domain */ +#define SD_OVERLAP 0x0800 /* sched_domains of this level overlap */ +#define SD_NUMA 0x1000 /* cross-node balancing */ #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) -- cgit v1.2.3 From d54a9658a75633b839af7a2c6c758807678b8064 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:49 +0100 Subject: sched/topology: Split out SD_* flags declaration to its own file To associate the SD flags with some metadata, we need some more structure in the way they are declared. Rather than shove that in a free-standing macro list, move the declaration in a separate file that can be re-imported with different SD_FLAG definitions. This is inspired by what is done with the syscall table (see uapi/asm/unistd.h and sys_call_table). The value assigned to a given SD flag now depends on the order it appears in sd_flags.h. No change in functionality. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Reviewed-by: Dietmar Eggemann Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-4-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/sched/topology.h | 26 +++++++++++++------------- 2 files changed, 48 insertions(+), 13 deletions(-) create mode 100644 include/linux/sched/sd_flags.h (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h new file mode 100644 index 000000000000..373dc45c024e --- /dev/null +++ b/include/linux/sched/sd_flags.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * sched-domains (multiprocessor balancing) flag declarations. + */ + +#ifndef SD_FLAG +# error "Incorrect import of SD flags definitions" +#endif + +/* Balance when about to become idle */ +SD_FLAG(SD_BALANCE_NEWIDLE) +/* Balance on exec */ +SD_FLAG(SD_BALANCE_EXEC) +/* Balance on fork, clone */ +SD_FLAG(SD_BALANCE_FORK) +/* Balance on wakeup */ +SD_FLAG(SD_BALANCE_WAKE) +/* Wake task to waking CPU */ +SD_FLAG(SD_WAKE_AFFINE) +/* Domain members have different CPU capacities */ +SD_FLAG(SD_ASYM_CPUCAPACITY) +/* Domain members share CPU capacity */ +SD_FLAG(SD_SHARE_CPUCAPACITY) +/* Domain members share CPU pkg resources */ +SD_FLAG(SD_SHARE_PKG_RESOURCES) +/* Only a single load balancing instance */ +SD_FLAG(SD_SERIALIZE) +/* Place busy groups earlier in the domain */ +SD_FLAG(SD_ASYM_PACKING) +/* Prefer to place tasks in a sibling domain */ +SD_FLAG(SD_PREFER_SIBLING) +/* sched_domains of this level overlap */ +SD_FLAG(SD_OVERLAP) +/* cross-node balancing */ +SD_FLAG(SD_NUMA) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 6ec7d7c1d1e3..3e41c0401b5f 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -11,19 +11,19 @@ */ #ifdef CONFIG_SMP -#define SD_BALANCE_NEWIDLE 0x0001 /* Balance when about to become idle */ -#define SD_BALANCE_EXEC 0x0002 /* Balance on exec */ -#define SD_BALANCE_FORK 0x0004 /* Balance on fork, clone */ -#define SD_BALANCE_WAKE 0x0008 /* Balance on wakeup */ -#define SD_WAKE_AFFINE 0x0010 /* Wake task to waking CPU */ -#define SD_ASYM_CPUCAPACITY 0x0020 /* Domain members have different CPU capacities */ -#define SD_SHARE_CPUCAPACITY 0x0040 /* Domain members share CPU capacity */ -#define SD_SHARE_PKG_RESOURCES 0x0080 /* Domain members share CPU pkg resources */ -#define SD_SERIALIZE 0x0100 /* Only a single load balancing instance */ -#define SD_ASYM_PACKING 0x0200 /* Place busy groups earlier in the domain */ -#define SD_PREFER_SIBLING 0x0400 /* Prefer to place tasks in a sibling domain */ -#define SD_OVERLAP 0x0800 /* sched_domains of this level overlap */ -#define SD_NUMA 0x1000 /* cross-node balancing */ +/* Generate SD flag indexes */ +#define SD_FLAG(name) __##name, +enum { + #include + __SD_FLAG_CNT, +}; +#undef SD_FLAG +/* Generate SD flag bits */ +#define SD_FLAG(name) name = 1 << __##name, +enum { + #include +}; +#undef SD_FLAG #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) -- cgit v1.2.3 From b6e862f386722e0de6c37f85f1cf438a0efa7f93 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:50 +0100 Subject: sched/topology: Define and assign sched_domain flag metadata There are some expectations regarding how sched domain flags should be laid out, but none of them are checked or asserted in sched_domain_debug_one(). After staring at said flags for a while, I've come to realize there's two repeating patterns: - Shared with children: those flags are set from the base CPU domain upwards. Any domain that has it set will have it set in its children. It hints at "some property holds true / some behaviour is enabled until this level". - Shared with parents: those flags are set from the topmost domain downwards. Any domain that has it set will have it set in its parents. It hints at "some property isn't visible / some behaviour is disabled until this level". There are two outliers that (currently) do not map to either of these: o SD_PREFER_SIBLING, which is cleared below levels with SD_ASYM_CPUCAPACITY. The change was introduced by commit: 9c63e84db29b ("sched/core: Disable SD_PREFER_SIBLING on asymmetric CPU capacity domains") as it could break misfit migration on some systems. In light of this, we might want to change it back to make it fit one of the two categories and fix the issue another way. o SD_ASYM_CPUCAPACITY, which gets set on a single level and isn't propagated up nor down. From a topology description point of view, it really wants to be SDF_SHARED_PARENT; this will be rectified in a later patch. Tweak the sched_domain flag declaration to assign each flag an expected layout, and include the rationale for each flag "meta type" assignment as a comment. Consolidate the flag metadata into an array; the index of a flag's metadata can easily be found with log2(flag), IOW __ffs(flag). Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Reviewed-by: Dietmar Eggemann Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-5-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 147 +++++++++++++++++++++++++++++++++-------- include/linux/sched/topology.h | 15 ++++- 2 files changed, 134 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 373dc45c024e..c24a45b05fbb 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -7,29 +7,124 @@ # error "Incorrect import of SD flags definitions" #endif -/* Balance when about to become idle */ -SD_FLAG(SD_BALANCE_NEWIDLE) -/* Balance on exec */ -SD_FLAG(SD_BALANCE_EXEC) -/* Balance on fork, clone */ -SD_FLAG(SD_BALANCE_FORK) -/* Balance on wakeup */ -SD_FLAG(SD_BALANCE_WAKE) -/* Wake task to waking CPU */ -SD_FLAG(SD_WAKE_AFFINE) -/* Domain members have different CPU capacities */ -SD_FLAG(SD_ASYM_CPUCAPACITY) -/* Domain members share CPU capacity */ -SD_FLAG(SD_SHARE_CPUCAPACITY) -/* Domain members share CPU pkg resources */ -SD_FLAG(SD_SHARE_PKG_RESOURCES) -/* Only a single load balancing instance */ -SD_FLAG(SD_SERIALIZE) -/* Place busy groups earlier in the domain */ -SD_FLAG(SD_ASYM_PACKING) -/* Prefer to place tasks in a sibling domain */ -SD_FLAG(SD_PREFER_SIBLING) -/* sched_domains of this level overlap */ -SD_FLAG(SD_OVERLAP) -/* cross-node balancing */ -SD_FLAG(SD_NUMA) +/* + * Expected flag uses + * + * SHARED_CHILD: These flags are meant to be set from the base domain upwards. + * If a domain has this flag set, all of its children should have it set. This + * is usually because the flag describes some shared resource (all CPUs in that + * domain share the same resource), or because they are tied to a scheduling + * behaviour that we want to disable at some point in the hierarchy for + * scalability reasons. + * + * In those cases it doesn't make sense to have the flag set for a domain but + * not have it in (some of) its children: sched domains ALWAYS span their child + * domains, so operations done with parent domains will cover CPUs in the lower + * child domains. + * + * + * SHARED_PARENT: These flags are meant to be set from the highest domain + * downwards. If a domain has this flag set, all of its parents should have it + * set. This is usually for topology properties that start to appear above a + * certain level (e.g. domain starts spanning CPUs outside of the base CPU's + * socket). + */ +#define SDF_SHARED_CHILD 0x1 +#define SDF_SHARED_PARENT 0x2 + +/* + * Balance when about to become idle + * + * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level. + */ +SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD) + +/* + * Balance on exec + * + * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + */ +SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD) + +/* + * Balance on fork, clone + * + * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + */ +SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD) + +/* + * Balance on wakeup + * + * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level. + */ +SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD) + +/* + * Consider waking task on waking CPU. + * + * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + */ +SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD) + +/* + * Domain members have different CPU capacities + */ +SD_FLAG(SD_ASYM_CPUCAPACITY, 0) + +/* + * Domain members share CPU capacity (i.e. SMT) + * + * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share + * CPU capacity. + */ +SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD) + +/* + * Domain members share CPU package resources (i.e. caches) + * + * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share + * the same cache(s). + */ +SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD) + +/* + * Only a single load balancing instance + * + * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a + * different level upwards, but it doesn't change that if a domain has this flag + * set, then all of its parents need to have it too (otherwise the serialization + * doesn't make sense). + */ +SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT) + +/* + * Place busy tasks earlier in the domain + * + * SHARED_CHILD: Usually set on the SMT level. Technically could be set further + * up, but currently assumed to be set from the base domain upwards (see + * update_top_cache_domain()). + */ +SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD) + +/* + * Prefer to place tasks in a sibling domain + * + * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD + * flag, but cleared below domains with SD_ASYM_CPUCAPACITY. + */ +SD_FLAG(SD_PREFER_SIBLING, 0) + +/* + * sched_groups of this level overlap + * + * SHARED_PARENT: Set for all NUMA levels above NODE. + */ +SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT) + +/* + * Cross-node balancing + * + * SHARED_PARENT: Set for all NUMA levels above NODE. + */ +SD_FLAG(SD_NUMA, SDF_SHARED_PARENT) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 3e41c0401b5f..32f602ff37a0 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -12,19 +12,30 @@ #ifdef CONFIG_SMP /* Generate SD flag indexes */ -#define SD_FLAG(name) __##name, +#define SD_FLAG(name, mflags) __##name, enum { #include __SD_FLAG_CNT, }; #undef SD_FLAG /* Generate SD flag bits */ -#define SD_FLAG(name) name = 1 << __##name, +#define SD_FLAG(name, mflags) name = 1 << __##name, enum { #include }; #undef SD_FLAG +#ifdef CONFIG_SCHED_DEBUG +#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name }, +static const struct { + unsigned int meta_flags; + char *name; +} sd_flag_debug[] = { +#include +}; +#undef SD_FLAG +#endif + #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) { -- cgit v1.2.3 From 4ee4ea443a5dc3fc4d8ae338199676eae9d8ef02 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:53 +0100 Subject: sched/topology: Introduce SD metaflag for flags needing > 1 groups In preparation of cleaning up the sd_degenerate*() functions, mark flags used in sd_degenerate() with the new SDF_NEEDS_GROUPS flag. With this, build a compile-time mask of those SD flags. Note that sd_parent_degenerate() uses an extra flag in its mask, SD_PREFER_SIBLING, which remains singled out for now. Suggested-by: Peter Zijlstra Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Reviewed-by: Dietmar Eggemann Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-8-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 39 ++++++++++++++++++++++++++++----------- include/linux/sched/topology.h | 7 +++++++ 2 files changed, 35 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index c24a45b05fbb..ee5cbfc7189f 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -8,7 +8,7 @@ #endif /* - * Expected flag uses + * Hierarchical metaflags * * SHARED_CHILD: These flags are meant to be set from the base domain upwards. * If a domain has this flag set, all of its children should have it set. This @@ -29,29 +29,42 @@ * certain level (e.g. domain starts spanning CPUs outside of the base CPU's * socket). */ -#define SDF_SHARED_CHILD 0x1 -#define SDF_SHARED_PARENT 0x2 +#define SDF_SHARED_CHILD 0x1 +#define SDF_SHARED_PARENT 0x2 + +/* + * Behavioural metaflags + * + * NEEDS_GROUPS: These flags are only relevant if the domain they are set on has + * more than one group. This is usually for balancing flags (load balancing + * involves equalizing a metric between groups), or for flags describing some + * shared resource (which would be shared between groups). + */ +#define SDF_NEEDS_GROUPS 0x4 /* * Balance when about to become idle * * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level. + * NEEDS_GROUPS: Load balancing flag. */ -SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD) +SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Balance on exec * * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + * NEEDS_GROUPS: Load balancing flag. */ -SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD) +SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Balance on fork, clone * * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + * NEEDS_GROUPS: Load balancing flag. */ -SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD) +SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Balance on wakeup @@ -69,24 +82,28 @@ SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD) /* * Domain members have different CPU capacities + * + * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups. */ -SD_FLAG(SD_ASYM_CPUCAPACITY, 0) +SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_NEEDS_GROUPS) /* * Domain members share CPU capacity (i.e. SMT) * * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share - * CPU capacity. + * CPU capacity. + * NEEDS_GROUPS: Capacity is shared between groups. */ -SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD) +SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Domain members share CPU package resources (i.e. caches) * * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share - * the same cache(s). + * the same cache(s). + * NEEDS_GROUPS: Caches are shared between groups. */ -SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD) +SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Only a single load balancing instance diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 32f602ff37a0..2d59ca77103e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -25,6 +25,13 @@ enum { }; #undef SD_FLAG +/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */ +#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) | +static const unsigned int SD_DEGENERATE_GROUPS_MASK = +#include +0; +#undef SD_FLAG + #ifdef CONFIG_SCHED_DEBUG #define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name }, static const struct { -- cgit v1.2.3 From c200191d4c2c1aa2ffb62a984b756ac1f02dc55c Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:56 +0100 Subject: sched/topology: Propagate SD_ASYM_CPUCAPACITY upwards We currently set this flag *only* on domains whose topology level exactly match the level where we detect asymmetry (as returned by asym_cpu_capacity_level()). This is rather problematic. Say there are two clusters in the system, one with a lone big CPU and the other with a mix of big and LITTLE CPUs (as is allowed by DynamIQ): DIE [ ] MC [ ][ ] 0 1 2 3 4 L L B B B asym_cpu_capacity_level() will figure out that the MC level is the one where all CPUs can see a CPU of max capacity, and we will thus set SD_ASYM_CPUCAPACITY at MC level for all CPUs. That lone big CPU will degenerate its MC domain, since it would be alone in there, and will end up with just a DIE domain. Since the flag was only set at MC, this CPU ends up not seeing any SD with the flag set, which is broken. Rather than clearing dflags at every topology level, clear it before entering the topology level loop. This will properly propagate upwards flags that are set starting from a certain level. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Reviewed-by: Quentin Perret Reviewed-by: Dietmar Eggemann Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-11-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index ee5cbfc7189f..40ad0d5c32e3 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -83,9 +83,11 @@ SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD) /* * Domain members have different CPU capacities * + * SHARED_PARENT: Set from the topmost domain down to the first domain where + * asymmetry is detected. * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups. */ -SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_NEEDS_GROUPS) +SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) /* * Domain members share CPU capacity (i.e. SMT) -- cgit v1.2.3 From 3a6712c7685352a5d71eaf459a4fddfc3589f018 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:57 +0100 Subject: sched/topology: Mark SD_PREFER_SIBLING as SDF_NEEDS_GROUPS SD_PREFER_SIBLING is currently considered in sd_parent_degenerate() but not in sd_degenerate(). It too hinges on load balancing, and thus won't have any effect when set on a domain with a single group. Add it to SD_DEGENERATE_GROUPS_MASK. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-12-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 40ad0d5c32e3..d28fe67c3098 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -131,8 +131,10 @@ SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD) * * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD * flag, but cleared below domains with SD_ASYM_CPUCAPACITY. + * + * NEEDS_GROUPS: Load balancing flag. */ -SD_FLAG(SD_PREFER_SIBLING, 0) +SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS) /* * sched_groups of this level overlap -- cgit v1.2.3 From 94b858fea1f2246a2fb7f7af21840fd14ced028f Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:58 +0100 Subject: sched/topology: Mark SD_BALANCE_WAKE as SDF_NEEDS_GROUPS Even if no mainline topology uses this flag, it is a load balancing flag just like SD_BALANCE_FORK and requires 2+ groups to have any effect. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-13-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index d28fe67c3098..729510a291b2 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -70,8 +70,9 @@ SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) * Balance on wakeup * * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level. + * NEEDS_GROUPS: Load balancing flag. */ -SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD) +SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Consider waking task on waking CPU. -- cgit v1.2.3 From bdb7c802cc0a7e21f5223dc3ce41b7ac220c576e Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:29:59 +0100 Subject: sched/topology: Mark SD_SERIALIZE as SDF_NEEDS_GROUPS There would be no point in preserving a sched_domain with a single group just because it has this flag set. Add it to SD_DEGENERATE_GROUPS_MASK. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-14-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 729510a291b2..b7f4d80e338e 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -112,11 +112,12 @@ SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) * Only a single load balancing instance * * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a - * different level upwards, but it doesn't change that if a domain has this flag - * set, then all of its parents need to have it too (otherwise the serialization - * doesn't make sense). + * different level upwards, but it doesn't change that if a + * domain has this flag set, then all of its parents need to have + * it too (otherwise the serialization doesn't make sense). + * NEEDS_GROUPS: No point in preserving domain if it has a single group. */ -SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT) +SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) /* * Place busy tasks earlier in the domain -- cgit v1.2.3 From 33199b0143daf4778d6301f966cb914d75f122eb Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:30:00 +0100 Subject: sched/topology: Mark SD_ASYM_PACKING as SDF_NEEDS_GROUPS Being a load-balancing flag, it requires 2+ groups to have any effect. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-15-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index b7f4d80e338e..2998ece2c18d 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -123,10 +123,11 @@ SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) * Place busy tasks earlier in the domain * * SHARED_CHILD: Usually set on the SMT level. Technically could be set further - * up, but currently assumed to be set from the base domain upwards (see - * update_top_cache_domain()). + * up, but currently assumed to be set from the base domain + * upwards (see update_top_cache_domain()). + * NEEDS_GROUPS: Load balancing flag. */ -SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD) +SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Prefer to place tasks in a sibling domain -- cgit v1.2.3 From 3551e954f5d95faf3dbc340d422da7624658c230 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:30:01 +0100 Subject: sched/topology: Mark SD_OVERLAP as SDF_NEEDS_GROUPS A sched_domain can only have overlapping sched_groups if it has more than one group. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-16-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 2998ece2c18d..29af5f032861 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -143,8 +143,9 @@ SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS) * sched_groups of this level overlap * * SHARED_PARENT: Set for all NUMA levels above NODE. + * NEEDS_GROUPS: Overlaps can only exist with more than one group. */ -SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT) +SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) /* * Cross-node balancing -- cgit v1.2.3 From 5f4a1c4ea44728aa80be21dbf3a0469b5ca81d88 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 17 Aug 2020 12:30:02 +0100 Subject: sched/topology: Mark SD_NUMA as SDF_NEEDS_GROUPS There would be no point in preserving a sched_domain with a single group just because it has this flag set. Add it to SD_DEGENERATE_GROUPS_MASK. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200817113003.20802-17-valentin.schneider@arm.com --- include/linux/sched/sd_flags.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 29af5f032861..34b21e971d77 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -151,5 +151,6 @@ SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) * Cross-node balancing * * SHARED_PARENT: Set for all NUMA levels above NODE. + * NEEDS_GROUPS: No point in preserving domain if it has a single group. */ -SD_FLAG(SD_NUMA, SDF_SHARED_PARENT) +SD_FLAG(SD_NUMA, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) -- cgit v1.2.3 From 709c4362725abb5fa1e36fd94893a9b0d049df82 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 8 Jul 2020 16:39:29 +0000 Subject: cacheinfo: Move resctrl's get_cache_id() to the cacheinfo header file resctrl/core.c defines get_cache_id() for use in its cpu-hotplug callbacks. This gets the id attribute of the cache at the corresponding level of a CPU. Later rework means this private function needs to be shared. Move it to the header file. The name conflicts with a different definition in intel_cacheinfo.c, name it get_cpu_cacheinfo_id() to show its relation with get_cpu_cacheinfo(). Now this is visible on other architectures, check the id attribute has actually been set. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Babu Moger Reviewed-by: Reinette Chatre Link: https://lkml.kernel.org/r/20200708163929.2783-11-james.morse@arm.com --- include/linux/cacheinfo.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 46b92cd61d0c..4f72b47973c3 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -3,6 +3,7 @@ #define _LINUX_CACHEINFO_H #include +#include #include #include @@ -119,4 +120,24 @@ int acpi_find_last_cache_level(unsigned int cpu); const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf); +/* + * Get the id of the cache associated with @cpu at level @level. + * cpuhp lock must be held. + */ +static inline int get_cpu_cacheinfo_id(int cpu, int level) +{ + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); + int i; + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == level) { + if (ci->info_list[i].attributes & CACHE_ID) + return ci->info_list[i].id; + return -1; + } + } + + return -1; +} + #endif /* _LINUX_CACHEINFO_H */ -- cgit v1.2.3 From 1dbb920e342cab987186ad8ed6eac9c1cf710db7 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 30 Jul 2020 22:39:13 +1000 Subject: crypto: algapi - Move crypto_yield into internal.h This patch moves crypto_yield into internal.h as it's only used by internal code such as skcipher. It also adds a missing inclusion of sched.h which is required for cond_resched. The header files in internal.h have been cleaned up to remove some ancient junk and add some more specific inclusions. Signed-off-by: Herbert Xu --- include/crypto/algapi.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 143d884d65c7..99fcb2d7a831 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -277,12 +277,6 @@ static inline int crypto_memneq(const void *a, const void *b, size_t size) return __crypto_memneq(a, b, size) != 0UL ? 1 : 0; } -static inline void crypto_yield(u32 flags) -{ - if (flags & CRYPTO_TFM_REQ_MAY_SLEEP) - cond_resched(); -} - int crypto_register_notifier(struct notifier_block *nb); int crypto_unregister_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 5b5858ef45906bbd71d8fc95e3bc30860b599620 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 17 Aug 2020 18:48:36 +0200 Subject: ARM: s3c24xx: drop s3c-camif setup platform code The s3c-camif driver setup platform code does not have any users so it can be safely removed. Along with the code W=1 compile warnings go away: arch/arm/mach-s3c24xx/setup-camif.c:28:5: warning: no previous prototype for 's3c_camif_gpio_get' [-Wmissing-prototypes] arch/arm/mach-s3c24xx/setup-camif.c:56:6: warning: no previous prototype for 's3c_camif_gpio_put' [-Wmissing-prototypes] Signed-off-by: Krzysztof Kozlowski --- include/media/drv-intf/s3c_camif.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/media/drv-intf/s3c_camif.h b/include/media/drv-intf/s3c_camif.h index d1200b40f53a..f746851a5ce6 100644 --- a/include/media/drv-intf/s3c_camif.h +++ b/include/media/drv-intf/s3c_camif.h @@ -35,8 +35,4 @@ struct s3c_camif_plat_data { int (*gpio_put)(void); }; -/* Platform default helper functions */ -int s3c_camif_gpio_get(void); -int s3c_camif_gpio_put(void); - #endif /* MEDIA_S3C_CAMIF_ */ -- cgit v1.2.3 From b84e23f5135103c45022b0e4a4ed2459d5398a7e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 6 Aug 2020 20:20:23 +0200 Subject: ARM: s3c24xx: pass pointer to clk driver via platform data Passing pointers directly as platform data is fragile and undocumented. Better to create a platform data structure which explicitly documents what is passed to the driver. Suggested-by: Tomasz Figa Signed-off-by: Krzysztof Kozlowski Acked-by: Arnd Bergmann Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20200806182059.2431-6-krzk@kernel.org --- include/linux/platform_data/clk-s3c2410.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/platform_data/clk-s3c2410.h (limited to 'include') diff --git a/include/linux/platform_data/clk-s3c2410.h b/include/linux/platform_data/clk-s3c2410.h new file mode 100644 index 000000000000..7eb1cfa5409b --- /dev/null +++ b/include/linux/platform_data/clk-s3c2410.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Krzysztof Kozlowski + */ + +#ifndef __LINUX_PLATFORM_DATA_CLK_S3C2410_H_ +#define __LINUX_PLATFORM_DATA_CLK_S3C2410_H_ + +/** + * struct s3c2410_clk_platform_data - platform data for S3C2410 clock driver + * + * @modify_misccr: Function to modify the MISCCR and return the new value + */ +struct s3c2410_clk_platform_data { + unsigned int (*modify_misccr)(unsigned int clr, unsigned int chg); +}; + +#endif /* __LINUX_PLATFORM_DATA_CLK_S3C2410_H_ */ + -- cgit v1.2.3 From 5f745424761a2a49762625e8616417a8e7694228 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:26 +0200 Subject: usb: gadget: s3c-hsudc: remove platform header dependency There is no real phy driver, so s3c-hsudc just pokes the registers itself. Improve this a little by making it a platform data callback like we do for gpios. There is only one board using this driver, and it's unlikely that another would be added, so this is a minimal workaround. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200806182059.2431-9-krzk@kernel.org [krzk: Include regs-s3c2443-clock.h in ifdef to fixup build on s3c6400] Signed-off-by: Krzysztof Kozlowski --- include/linux/platform_data/s3c-hsudc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/s3c-hsudc.h b/include/linux/platform_data/s3c-hsudc.h index 4dc9b8760166..a170939832d5 100644 --- a/include/linux/platform_data/s3c-hsudc.h +++ b/include/linux/platform_data/s3c-hsudc.h @@ -26,6 +26,8 @@ struct s3c24xx_hsudc_platdata { unsigned int epnum; void (*gpio_init)(void); void (*gpio_uninit)(void); + void (*phy_init)(void); + void (*phy_uninit)(void); }; #endif /* __LINUX_USB_S3C_HSUDC_H */ -- cgit v1.2.3 From 17132da70eb766785b9b4677bacce18cc11ea442 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:33 +0200 Subject: ARM: samsung: move pm check code to drivers/soc This is the only part of plat-samsung that is really shared between the s3c and s5p ports. Moving it to drivers/soc/ lets us make them completely independent. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200806182059.2431-16-krzk@kernel.org Signed-off-by: Krzysztof Kozlowski --- include/linux/soc/samsung/s3c-pm.h | 84 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 include/linux/soc/samsung/s3c-pm.h (limited to 'include') diff --git a/include/linux/soc/samsung/s3c-pm.h b/include/linux/soc/samsung/s3c-pm.h new file mode 100644 index 000000000000..730bd1d3d09a --- /dev/null +++ b/include/linux/soc/samsung/s3c-pm.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + * Tomasz Figa + * Copyright (c) 2004 Simtec Electronics + * http://armlinux.simtec.co.uk/ + * Written by Ben Dooks, + */ + +#ifndef __LINUX_SOC_SAMSUNG_S3C_PM_H +#define __LINUX_SOC_SAMSUNG_S3C_PM_H __FILE__ + +#include + +/* PM debug functions */ + +/** + * struct pm_uart_save - save block for core UART + * @ulcon: Save value for S3C2410_ULCON + * @ucon: Save value for S3C2410_UCON + * @ufcon: Save value for S3C2410_UFCON + * @umcon: Save value for S3C2410_UMCON + * @ubrdiv: Save value for S3C2410_UBRDIV + * + * Save block for UART registers to be held over sleep and restored if they + * are needed (say by debug). +*/ +struct pm_uart_save { + u32 ulcon; + u32 ucon; + u32 ufcon; + u32 umcon; + u32 ubrdiv; + u32 udivslot; +}; + +#ifdef CONFIG_SAMSUNG_PM_DEBUG +/** + * s3c_pm_dbg() - low level debug function for use in suspend/resume. + * @msg: The message to print. + * + * This function is used mainly to debug the resume process before the system + * can rely on printk/console output. It uses the low-level debugging output + * routine printascii() to do its work. + */ +extern void s3c_pm_dbg(const char *msg, ...); + +#define S3C_PMDBG(fmt...) s3c_pm_dbg(fmt) + +extern void s3c_pm_save_uarts(bool is_s3c24xx); +extern void s3c_pm_restore_uarts(bool is_s3c24xx); + +#ifdef CONFIG_ARCH_S3C64XX +extern void s3c_pm_arch_update_uart(void __iomem *regs, + struct pm_uart_save *save); +#else +static inline void +s3c_pm_arch_update_uart(void __iomem *regs, struct pm_uart_save *save) +{ +} +#endif + +#else +#define S3C_PMDBG(fmt...) pr_debug(fmt) + +static inline void s3c_pm_save_uarts(bool is_s3c24xx) { } +static inline void s3c_pm_restore_uarts(bool is_s3c24xx) { } +#endif + +/* suspend memory checking */ + +#ifdef CONFIG_SAMSUNG_PM_CHECK +extern void s3c_pm_check_prepare(void); +extern void s3c_pm_check_restore(void); +extern void s3c_pm_check_cleanup(void); +extern void s3c_pm_check_store(void); +#else +#define s3c_pm_check_prepare() do { } while (0) +#define s3c_pm_check_restore() do { } while (0) +#define s3c_pm_check_cleanup() do { } while (0) +#define s3c_pm_check_store() do { } while (0) +#endif + +#endif -- cgit v1.2.3 From 7dbad03ebcb924cde142f7477d65a54ffb1166a3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:39 +0200 Subject: ARM: s3c: adc: move header to linux/soc/samsung There are multiple drivers using the private adc interface. It seems unlikely that they would ever get converted to iio, so make the current state official by making the header file global. The s3c2410_ts driver needs a couple of register definitions as well. Signed-off-by: Arnd Bergmann Acked-by: Guenter Roeck Acked-by: Dmitry Torokhov Acked-by: Sebastian Reichel Link: https://lore.kernel.org/r/20200806182059.2431-22-krzk@kernel.org Signed-off-by: Krzysztof Kozlowski --- include/linux/soc/samsung/s3c-adc.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/soc/samsung/s3c-adc.h (limited to 'include') diff --git a/include/linux/soc/samsung/s3c-adc.h b/include/linux/soc/samsung/s3c-adc.h new file mode 100644 index 000000000000..591c94ef957d --- /dev/null +++ b/include/linux/soc/samsung/s3c-adc.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2008 Simtec Electronics + * http://armlinux.simtec.co.uk/ + * Ben Dooks + * + * S3C ADC driver information + */ + +#ifndef __LINUX_SOC_SAMSUNG_S3C_ADC_H +#define __LINUX_SOC_SAMSUNG_S3C_ADC_H __FILE__ + +struct s3c_adc_client; +struct platform_device; + +extern int s3c_adc_start(struct s3c_adc_client *client, + unsigned int channel, unsigned int nr_samples); + +extern int s3c_adc_read(struct s3c_adc_client *client, unsigned int ch); + +extern struct s3c_adc_client * + s3c_adc_register(struct platform_device *pdev, + void (*select)(struct s3c_adc_client *client, + unsigned selected), + void (*conv)(struct s3c_adc_client *client, + unsigned d0, unsigned d1, + unsigned *samples_left), + unsigned int is_ts); + +extern void s3c_adc_release(struct s3c_adc_client *client); + +#endif /* __LINUX_SOC_SAMSUNG_S3C_ADC_H */ -- cgit v1.2.3 From f131a4443ea468cd532410c271c229bb39caab08 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 3 Sep 2019 11:31:09 +0200 Subject: ARM: s3c24xx: move spi fiq handler into platform The fiq handler needs access to some register definitions that should not be used directly by device drivers. Since this is closely related to the irqchip driver anyway, move it into the same place. Signed-off-by: Arnd Bergmann [krzk: Add a header guard in include/linux/spi/s3c24xx-fiq.h, fix SPDX comment style, update maintainer's entry] Co-developed-by: Krzysztof Kozlowski Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200806182059.2431-23-krzk%40kernel.org Acked-by: Mark Brown --- include/linux/spi/s3c24xx-fiq.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 include/linux/spi/s3c24xx-fiq.h (limited to 'include') diff --git a/include/linux/spi/s3c24xx-fiq.h b/include/linux/spi/s3c24xx-fiq.h new file mode 100644 index 000000000000..d2842ac1de27 --- /dev/null +++ b/include/linux/spi/s3c24xx-fiq.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* linux/drivers/spi/spi_s3c24xx_fiq.h + * + * Copyright 2009 Simtec Electronics + * Ben Dooks + * + * S3C24XX SPI - FIQ pseudo-DMA transfer support +*/ + +#ifndef __LINUX_SPI_S3C24XX_FIQ_H +#define __LINUX_SPI_S3C24XX_FIQ_H __FILE__ + +/* We have R8 through R13 to play with */ + +#ifdef __ASSEMBLY__ +#define __REG_NR(x) r##x +#else + +extern struct spi_fiq_code s3c24xx_spi_fiq_txrx; +extern struct spi_fiq_code s3c24xx_spi_fiq_tx; +extern struct spi_fiq_code s3c24xx_spi_fiq_rx; + +#define __REG_NR(x) (x) +#endif + +#define fiq_rspi __REG_NR(8) +#define fiq_rtmp __REG_NR(9) +#define fiq_rrx __REG_NR(10) +#define fiq_rtx __REG_NR(11) +#define fiq_rcount __REG_NR(12) +#define fiq_rirq __REG_NR(13) + +#endif /* __LINUX_SPI_S3C24XX_FIQ_H */ -- cgit v1.2.3 From b558b6c24068d87ffcd95dad3bf0d9bd2ac290e9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Tue, 18 Aug 2020 18:07:09 -0700 Subject: net-tun: Add type safety to tun_xdp_to_ptr() and tun_ptr_to_xdp() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reduces likelihood of incorrect use. Test: builds Signed-off-by: Maciej Żenczykowski Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200819010710.3959310-1-zenczykowski@gmail.com --- include/linux/if_tun.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 5bda8cf457b6..6c37e1dbc5df 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -28,8 +28,8 @@ struct tun_xdp_hdr { struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); bool tun_is_xdp_frame(void *ptr); -void *tun_xdp_to_ptr(void *ptr); -void *tun_ptr_to_xdp(void *ptr); +void *tun_xdp_to_ptr(struct xdp_frame *xdp); +struct xdp_frame *tun_ptr_to_xdp(void *ptr); void tun_ptr_free(void *ptr); #else #include @@ -48,11 +48,11 @@ static inline bool tun_is_xdp_frame(void *ptr) { return false; } -static inline void *tun_xdp_to_ptr(void *ptr) +static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) { return NULL; } -static inline void *tun_ptr_to_xdp(void *ptr) +static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) { return NULL; } -- cgit v1.2.3 From 596b5ef458f903d4362fb3c69967b6d8a23334bd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Tue, 18 Aug 2020 18:07:10 -0700 Subject: net-tun: Eliminate two tun/xdp related function calls from vhost-net MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This provides a minor performance boost by virtue of inlining instead of cross module function calls. Test: builds Signed-off-by: Maciej Żenczykowski Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200819010710.3959310-2-zenczykowski@gmail.com --- include/linux/if_tun.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 6c37e1dbc5df..2a7660843444 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -27,9 +27,18 @@ struct tun_xdp_hdr { #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -bool tun_is_xdp_frame(void *ptr); -void *tun_xdp_to_ptr(struct xdp_frame *xdp); -struct xdp_frame *tun_ptr_to_xdp(void *ptr); +static inline bool tun_is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & TUN_XDP_FLAG; +} +static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) +{ + return (void *)((unsigned long)xdp | TUN_XDP_FLAG); +} +static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) +{ + return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG); +} void tun_ptr_free(void *ptr); #else #include -- cgit v1.2.3 From bdfbb63c314a6fb7d27dddd62f5a3e4f062b92bb Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Tue, 18 Aug 2020 12:32:43 +0200 Subject: ptp: Add generic ptp v2 header parsing function Reason: A lot of the ptp drivers - which implement hardware time stamping - need specific fields such as the sequence id from the ptp v2 header. Currently all drivers implement that themselves. Introduce a generic function to retrieve a pointer to the start of the ptp v2 header. Suggested-by: Russell King Signed-off-by: Kurt Kanzenbach Reviewed-by: Richard Cochran Reviewed-by: Florian Fainelli Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index dd00fa41f7e7..0a9cc0eb0801 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -44,6 +44,30 @@ #define OFF_IHL 14 #define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2) +struct clock_identity { + u8 id[8]; +} __packed; + +struct port_identity { + struct clock_identity clock_identity; + __be16 port_number; +} __packed; + +struct ptp_header { + u8 tsmt; /* transportSpecific | messageType */ + u8 ver; /* reserved | versionPTP */ + __be16 message_length; + u8 domain_number; + u8 reserved1; + u8 flag_field[2]; + __be64 correction; + __be32 reserved2; + struct port_identity source_port_identity; + __be16 sequence_id; + u8 control; + u8 log_message_interval; +} __packed; + #if defined(CONFIG_NET_PTP_CLASSIFY) /** * ptp_classify_raw - classify a PTP packet @@ -57,6 +81,21 @@ */ unsigned int ptp_classify_raw(const struct sk_buff *skb); +/** + * ptp_parse_header - Get pointer to the PTP v2 header + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * + * This function takes care of the VLAN, UDP, IPv4 and IPv6 headers. The length + * is checked. + * + * Note, internally skb_mac_header() is used. Make sure that the @skb is + * initialized accordingly. + * + * Return: Pointer to the ptp v2 header or NULL if not found + */ +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type); + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) @@ -66,5 +105,10 @@ static inline unsigned int ptp_classify_raw(struct sk_buff *skb) { return PTP_CLASS_NONE; } +static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb, + unsigned int type) +{ + return NULL; +} #endif #endif /* _PTP_CLASSIFY_H_ */ -- cgit v1.2.3 From 036c508ba95e573f53bd5bbb79b0c4d71003b319 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Tue, 18 Aug 2020 12:32:44 +0200 Subject: ptp: Add generic ptp message type function The message type is located at different offsets within the ptp header depending on the ptp version (v1 or v2). Therefore, drivers which also deal with ptp v1 have some code for it. Extract this into a helper function for drivers to be used. Signed-off-by: Kurt Kanzenbach Reviewed-by: Richard Cochran Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 0a9cc0eb0801..cfc6d9152f69 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -96,6 +96,31 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb); */ struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type); +/** + * ptp_get_msgtype - Extract ptp message type from given header + * @hdr: ptp header + * @type: type of the packet (see ptp_classify_raw()) + * + * This function returns the message type for a given ptp header. It takes care + * of the different ptp header versions (v1 or v2). + * + * Return: The message type + */ +static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, + unsigned int type) +{ + u8 msgtype; + + if (unlikely(type & PTP_CLASS_V1)) { + /* msg type is located at the control field for ptp v1 */ + msgtype = hdr->control; + } else { + msgtype = hdr->tsmt & 0x0f; + } + + return msgtype; +} + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) -- cgit v1.2.3 From 17060fb5069f2c73a566015ce6e019d5685680b5 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Tue, 18 Aug 2020 12:32:51 +0200 Subject: ptp: Remove unused macro The offset for the control field is not needed anymore. Remove it. Signed-off-by: Kurt Kanzenbach Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index cfc6d9152f69..8437307cca8c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -36,7 +36,6 @@ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 -#define OFF_PTP_CONTROL 32 /* PTPv1 only */ /* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 -- cgit v1.2.3 From 0c3dc787a62aef3ca7aedf3797ec42fff9b0a913 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 19 Aug 2020 21:58:20 +1000 Subject: crypto: algapi - Remove skbuff.h inclusion The header file algapi.h includes skbuff.h unnecessarily since all we need is a forward declaration for struct sk_buff. This patch removes that inclusion. Unfortunately skbuff.h pulls in a lot of things and drivers over the years have come to rely on it so this patch adds a lot of missing inclusions that result from this. Signed-off-by: Herbert Xu --- include/crypto/algapi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 99fcb2d7a831..18dd7a4aaf7d 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -10,7 +10,6 @@ #include #include #include -#include /* * Maximum values for blocksize and alignmask, used to allocate @@ -27,6 +26,7 @@ struct crypto_instance; struct module; struct rtattr; struct seq_file; +struct sk_buff; struct crypto_type { unsigned int (*ctxsize)(struct crypto_alg *alg, u32 type, u32 mask); -- cgit v1.2.3 From cad6967ac10843a70842cd39c7b53412901dd21f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 19 Aug 2020 12:46:45 +0200 Subject: fork: introduce kernel_clone() The old _do_fork() helper doesn't follow naming conventions of in-kernel helpers for syscalls. The process creation cleanup in [1] didn't change the name to something more reasonable mainly because _do_fork() was used in quite a few places. So sending this as a separate series seemed the better strategy. This commit does two things: 1. renames _do_fork() to kernel_clone() but keeps _do_fork() as a simple static inline wrapper around kernel_clone(). 2. Changes the return type from long to pid_t. This aligns kernel_thread() and kernel_clone(). Also, the return value from kernel_clone that is surfaced in fork(), vfork(), clone(), and clone3() is taken from pid_vrn() which returns a pid_t too. Follow-up patches will switch each caller of _do_fork() and each place where it is referenced over to kernel_clone(). After all these changes are done, we can remove _do_fork() completely and will only be left with kernel_clone(). [1]: 9ba27414f2ec ("Merge tag 'fork-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux") Signed-off-by: Christian Brauner Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: "Peter Zijlstra (Intel)" Link: https://lore.kernel.org/r/20200819104655.436656-2-christian.brauner@ubuntu.com --- include/linux/sched/task.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index a98965007eef..d4428039c3c1 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -83,7 +83,11 @@ extern void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); -extern long _do_fork(struct kernel_clone_args *kargs); +extern pid_t kernel_clone(struct kernel_clone_args *kargs); +static inline long _do_fork(struct kernel_clone_args *kargs) +{ + return kernel_clone(kargs); +} struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -- cgit v1.2.3 From 06fe45634942dc96c316bbb789049a4b0b692542 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 19 Aug 2020 12:46:55 +0200 Subject: sched: remove _do_fork() Now that all callers of _do_fork() have been switched to kernel_clone() remove the _do_fork() helper. Signed-off-by: Christian Brauner Link: https://lore.kernel.org/r/20200819104655.436656-12-christian.brauner@ubuntu.com --- include/linux/sched/task.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index d4428039c3c1..85fb2f34c59b 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -84,10 +84,6 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); -static inline long _do_fork(struct kernel_clone_args *kargs) -{ - return kernel_clone(kargs); -} struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -- cgit v1.2.3 From 005142b8a1f0f32d33fbe04b728464c1b7acfa0e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 18 Aug 2020 21:27:56 -0700 Subject: bpf: Factor out bpf_link_by_id() helper. Refactor the code a bit to extract bpf_link_by_id() helper. It's similar to existing bpf_prog_by_id(). Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200819042759.51280-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 55f694b63164..a9b7185a6b37 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1358,6 +1358,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); struct bpf_prog *bpf_prog_by_id(u32 id); +struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); #else /* !CONFIG_BPF_SYSCALL */ -- cgit v1.2.3 From f67f6c00c7f367fe90f2bc01b9a977aa13de870e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:46 +0200 Subject: ARM: s3c24xx: move s3cmci pinctrl handling into board files Rather than call the internal s3c_gpio_cfgall_range() function through a platform header, move the code into the set_power callback that is already exported by the board, and add a default implementation. In DT mode, the code already does not set the pin config, so nothing changes there. Signed-off-by: Arnd Bergmann Acked-by: Ulf Hansson Link: https://lore.kernel.org/r/20200806182059.2431-29-krzk@kernel.org [krzk: Rebase and correct set_power in mach-h1940.c] Signed-off-by: Krzysztof Kozlowski --- include/linux/platform_data/mmc-s3cmci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/mmc-s3cmci.h b/include/linux/platform_data/mmc-s3cmci.h index 33310b11cbdd..bacb86db3112 100644 --- a/include/linux/platform_data/mmc-s3cmci.h +++ b/include/linux/platform_data/mmc-s3cmci.h @@ -35,6 +35,7 @@ struct s3c24xx_mci_pdata { unsigned long ocr_avail; void (*set_power)(unsigned char power_mode, unsigned short vdd); + struct gpio_desc *bus[6]; }; /** @@ -44,6 +45,7 @@ struct s3c24xx_mci_pdata { * Copy the platform data supplied by @pdata so that this can be marked * __initdata. */ +extern void s3c24xx_mci_def_set_power(unsigned char power_mode, unsigned short vdd); extern void s3c24xx_mci_set_platdata(struct s3c24xx_mci_pdata *pdata); #endif /* _ARCH_NCI_H */ -- cgit v1.2.3 From cd4bd8f9435ddf08a8677f56abf418423f223959 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:48 +0200 Subject: ARM: s3c24xx: spi: avoid hardcoding fiq number in driver The IRQ_EINT0 constant is a platform detail that is defined in mach/irqs.h and not visible to drivers once that header is made private. Since the same calculation already happens in s3c24xx_set_fiq, just return the value from there. Signed-off-by: Arnd Bergmann Acked-by: Mark Brown Link: https://lore.kernel.org/r/20200806182059.2431-31-krzk@kernel.org Signed-off-by: Krzysztof Kozlowski --- include/linux/spi/s3c24xx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/s3c24xx.h b/include/linux/spi/s3c24xx.h index c91d10b82f08..440a71593162 100644 --- a/include/linux/spi/s3c24xx.h +++ b/include/linux/spi/s3c24xx.h @@ -20,6 +20,6 @@ struct s3c2410_spi_info { void (*set_cs)(struct s3c2410_spi_info *spi, int cs, int pol); }; -extern int s3c24xx_set_fiq(unsigned int irq, bool on); +extern int s3c24xx_set_fiq(unsigned int irq, u32 *ack_ptr, bool on); #endif /* __LINUX_SPI_S3C24XX_H */ -- cgit v1.2.3 From 81994e0ffc373e67ace4c98797c35f8213f07753 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Sep 2019 22:33:24 +0200 Subject: fbdev: s3c2410fb: remove mach header dependency The s3c2410fb driver is too deeply intertwined with the s3c24xx platform code. Change it in a way that avoids the use of platform header files but having all interface data in a platform_data header, and the private register definitions next to the driver itself. One ugly bit here is that the driver pokes directly into gpio registers, which are owned by another driver. Passing the mapped addresses in platform_data is somewhat suboptimal, but it is a small improvement over the previous version. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200806182059.2431-33-krzk@kernel.org Signed-off-by: Krzysztof Kozlowski --- include/linux/platform_data/fb-s3c2410.h | 99 ++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 include/linux/platform_data/fb-s3c2410.h (limited to 'include') diff --git a/include/linux/platform_data/fb-s3c2410.h b/include/linux/platform_data/fb-s3c2410.h new file mode 100644 index 000000000000..10c11e6316d6 --- /dev/null +++ b/include/linux/platform_data/fb-s3c2410.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2004 Arnaud Patard + * + * Inspired by pxafb.h +*/ + +#ifndef __ASM_PLAT_FB_S3C2410_H +#define __ASM_PLAT_FB_S3C2410_H __FILE__ + +#include + +struct s3c2410fb_hw { + unsigned long lcdcon1; + unsigned long lcdcon2; + unsigned long lcdcon3; + unsigned long lcdcon4; + unsigned long lcdcon5; +}; + +/* LCD description */ +struct s3c2410fb_display { + /* LCD type */ + unsigned type; +#define S3C2410_LCDCON1_DSCAN4 (0<<5) +#define S3C2410_LCDCON1_STN4 (1<<5) +#define S3C2410_LCDCON1_STN8 (2<<5) +#define S3C2410_LCDCON1_TFT (3<<5) + +#define S3C2410_LCDCON1_TFT1BPP (8<<1) +#define S3C2410_LCDCON1_TFT2BPP (9<<1) +#define S3C2410_LCDCON1_TFT4BPP (10<<1) +#define S3C2410_LCDCON1_TFT8BPP (11<<1) +#define S3C2410_LCDCON1_TFT16BPP (12<<1) +#define S3C2410_LCDCON1_TFT24BPP (13<<1) + + /* Screen size */ + unsigned short width; + unsigned short height; + + /* Screen info */ + unsigned short xres; + unsigned short yres; + unsigned short bpp; + + unsigned pixclock; /* pixclock in picoseconds */ + unsigned short left_margin; /* value in pixels (TFT) or HCLKs (STN) */ + unsigned short right_margin; /* value in pixels (TFT) or HCLKs (STN) */ + unsigned short hsync_len; /* value in pixels (TFT) or HCLKs (STN) */ + unsigned short upper_margin; /* value in lines (TFT) or 0 (STN) */ + unsigned short lower_margin; /* value in lines (TFT) or 0 (STN) */ + unsigned short vsync_len; /* value in lines (TFT) or 0 (STN) */ + + /* lcd configuration registers */ + unsigned long lcdcon5; +#define S3C2410_LCDCON5_BPP24BL (1<<12) +#define S3C2410_LCDCON5_FRM565 (1<<11) +#define S3C2410_LCDCON5_INVVCLK (1<<10) +#define S3C2410_LCDCON5_INVVLINE (1<<9) +#define S3C2410_LCDCON5_INVVFRAME (1<<8) +#define S3C2410_LCDCON5_INVVD (1<<7) +#define S3C2410_LCDCON5_INVVDEN (1<<6) +#define S3C2410_LCDCON5_INVPWREN (1<<5) +#define S3C2410_LCDCON5_INVLEND (1<<4) +#define S3C2410_LCDCON5_PWREN (1<<3) +#define S3C2410_LCDCON5_ENLEND (1<<2) +#define S3C2410_LCDCON5_BSWP (1<<1) +#define S3C2410_LCDCON5_HWSWP (1<<0) +}; + +struct s3c2410fb_mach_info { + + struct s3c2410fb_display *displays; /* attached displays info */ + unsigned num_displays; /* number of defined displays */ + unsigned default_display; + + /* GPIOs */ + + unsigned long gpcup; + unsigned long gpcup_mask; + unsigned long gpccon; + unsigned long gpccon_mask; + unsigned long gpdup; + unsigned long gpdup_mask; + unsigned long gpdcon; + unsigned long gpdcon_mask; + + void __iomem * gpccon_reg; + void __iomem * gpcup_reg; + void __iomem * gpdcon_reg; + void __iomem * gpdup_reg; + + /* lpc3600 control register */ + unsigned long lpcsel; +}; + +extern void s3c24xx_fb_set_platdata(struct s3c2410fb_mach_info *); + +#endif /* __ASM_PLAT_FB_S3C2410_H */ -- cgit v1.2.3 From 81b11a6a09964cfea4c525d22548790a1d92d38f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:52 +0200 Subject: ARM: s3c: remove cpufreq header dependencies The cpufreq drivers are split between the machine directory and the drivers/cpufreq directory. In order to share header files after we convert s3c to multiplatform, those headers have to live in a different global location. Move them to linux/soc/samsung/ in lack of a better place. Signed-off-by: Arnd Bergmann Acked-by: Viresh Kumar Link: https://lore.kernel.org/r/20200806182059.2431-35-krzk@kernel.org Signed-off-by: Krzysztof Kozlowski --- include/linux/soc/samsung/s3c-cpu-freq.h | 145 +++++++++++++ include/linux/soc/samsung/s3c-cpufreq-core.h | 291 +++++++++++++++++++++++++++ include/linux/soc/samsung/s3c-pm.h | 10 + 3 files changed, 446 insertions(+) create mode 100644 include/linux/soc/samsung/s3c-cpu-freq.h create mode 100644 include/linux/soc/samsung/s3c-cpufreq-core.h (limited to 'include') diff --git a/include/linux/soc/samsung/s3c-cpu-freq.h b/include/linux/soc/samsung/s3c-cpu-freq.h new file mode 100644 index 000000000000..63e88fd5dea2 --- /dev/null +++ b/include/linux/soc/samsung/s3c-cpu-freq.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2006-2007 Simtec Electronics + * http://armlinux.simtec.co.uk/ + * Ben Dooks + * + * S3C CPU frequency scaling support - driver and board + */ +#ifndef __LINUX_SOC_SAMSUNG_S3C_CPU_FREQ_H +#define __LINUX_SOC_SAMSUNG_S3C_CPU_FREQ_H + +#include + +struct s3c_cpufreq_info; +struct s3c_cpufreq_board; +struct s3c_iotimings; + +/** + * struct s3c_freq - frequency information (mainly for core drivers) + * @fclk: The FCLK frequency in Hz. + * @armclk: The ARMCLK frequency in Hz. + * @hclk_tns: HCLK cycle time in 10ths of nano-seconds. + * @hclk: The HCLK frequency in Hz. + * @pclk: The PCLK frequency in Hz. + * + * This contains the frequency information about the current configuration + * mainly for the core drivers to ensure we do not end up passing about + * a large number of parameters. + * + * The @hclk_tns field is a useful cache for the parts of the drivers that + * need to calculate IO timings and suchlike. + */ +struct s3c_freq { + unsigned long fclk; + unsigned long armclk; + unsigned long hclk_tns; /* in 10ths of ns */ + unsigned long hclk; + unsigned long pclk; +}; + +/** + * struct s3c_cpufreq_freqs - s3c cpufreq notification information. + * @freqs: The cpufreq setting information. + * @old: The old clock settings. + * @new: The new clock settings. + * @pll_changing: Set if the PLL is changing. + * + * Wrapper 'struct cpufreq_freqs' so that any drivers receiving the + * notification can use this information that is not provided by just + * having the core frequency alone. + * + * The pll_changing flag is used to indicate if the PLL itself is + * being set during this change. This is important as the clocks + * will temporarily be set to the XTAL clock during this time, so + * drivers may want to close down their output during this time. + * + * Note, this is not being used by any current drivers and therefore + * may be removed in the future. + */ +struct s3c_cpufreq_freqs { + struct cpufreq_freqs freqs; + struct s3c_freq old; + struct s3c_freq new; + + unsigned int pll_changing:1; +}; + +#define to_s3c_cpufreq(_cf) container_of(_cf, struct s3c_cpufreq_freqs, freqs) + +/** + * struct s3c_clkdivs - clock divisor information + * @p_divisor: Divisor from FCLK to PCLK. + * @h_divisor: Divisor from FCLK to HCLK. + * @arm_divisor: Divisor from FCLK to ARMCLK (not all CPUs). + * @dvs: Non-zero if using DVS mode for ARMCLK. + * + * Divisor settings for the core clocks. + */ +struct s3c_clkdivs { + int p_divisor; + int h_divisor; + int arm_divisor; + unsigned char dvs; +}; + +#define PLLVAL(_m, _p, _s) (((_m) << 12) | ((_p) << 4) | (_s)) + +/** + * struct s3c_pllval - PLL value entry. + * @freq: The frequency for this entry in Hz. + * @pll_reg: The PLL register setting for this PLL value. + */ +struct s3c_pllval { + unsigned long freq; + unsigned long pll_reg; +}; + +/** + * struct s3c_cpufreq_board - per-board cpu frequency informatin + * @refresh: The SDRAM refresh period in nanoseconds. + * @auto_io: Set if the IO timing settings should be generated from the + * initialisation time hardware registers. + * @need_io: Set if the board has external IO on any of the chipselect + * lines that will require the hardware timing registers to be + * updated on a clock change. + * @max: The maxium frequency limits for the system. Any field that + * is left at zero will use the CPU's settings. + * + * This contains the board specific settings that affect how the CPU + * drivers chose settings. These include the memory refresh and IO + * timing information. + * + * Registration depends on the driver being used, the ARMCLK only + * implementation does not currently need this but the older style + * driver requires this to be available. + */ +struct s3c_cpufreq_board { + unsigned int refresh; + unsigned int auto_io:1; /* automatically init io timings. */ + unsigned int need_io:1; /* set if needs io timing support. */ + + /* any non-zero field in here is taken as an upper limit. */ + struct s3c_freq max; /* frequency limits */ +}; + +/* Things depending on frequency scaling. */ +#ifdef CONFIG_ARM_S3C_CPUFREQ +#define __init_or_cpufreq +#else +#define __init_or_cpufreq __init +#endif + +/* Board functions */ + +#ifdef CONFIG_ARM_S3C_CPUFREQ +extern int s3c_cpufreq_setboard(struct s3c_cpufreq_board *board); +#else + +static inline int s3c_cpufreq_setboard(struct s3c_cpufreq_board *board) +{ + return 0; +} +#endif /* CONFIG_ARM_S3C_CPUFREQ */ + +#endif diff --git a/include/linux/soc/samsung/s3c-cpufreq-core.h b/include/linux/soc/samsung/s3c-cpufreq-core.h new file mode 100644 index 000000000000..c578b07ccd5d --- /dev/null +++ b/include/linux/soc/samsung/s3c-cpufreq-core.h @@ -0,0 +1,291 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2006-2009 Simtec Electronics + * http://armlinux.simtec.co.uk/ + * Ben Dooks + * + * S3C CPU frequency scaling support - core support + */ +#ifndef __LINUX_SOC_SAMSUNG_S3C_CPUFREQ_CORE_H +#define __LINUX_SOC_SAMSUNG_S3C_CPUFREQ_CORE_H + +#include + +struct seq_file; + +#define MAX_BANKS (8) +#define S3C2412_MAX_IO (8) + +/** + * struct s3c2410_iobank_timing - IO bank timings for S3C2410 style timings + * @bankcon: The cached version of settings in this structure. + * @tacp: + * @tacs: Time from address valid to nCS asserted. + * @tcos: Time from nCS asserted to nOE or nWE asserted. + * @tacc: Time that nOE or nWE is asserted. + * @tcoh: Time nCS is held after nOE or nWE are released. + * @tcah: Time address is held for after + * @nwait_en: Whether nWAIT is enabled for this bank. + * + * This structure represents the IO timings for a S3C2410 style IO bank + * used by the CPU frequency support if it needs to change the settings + * of the IO. + */ +struct s3c2410_iobank_timing { + unsigned long bankcon; + unsigned int tacp; + unsigned int tacs; + unsigned int tcos; + unsigned int tacc; + unsigned int tcoh; /* nCS hold after nOE/nWE */ + unsigned int tcah; /* Address hold after nCS */ + unsigned char nwait_en; /* nWait enabled for bank. */ +}; + +/** + * struct s3c2412_iobank_timing - io timings for PL092 (S3C2412) style IO + * @idcy: The idle cycle time between transactions. + * @wstrd: nCS release to end of read cycle. + * @wstwr: nCS release to end of write cycle. + * @wstoen: nCS assertion to nOE assertion time. + * @wstwen: nCS assertion to nWE assertion time. + * @wstbrd: Burst ready delay. + * @smbidcyr: Register cache for smbidcyr value. + * @smbwstrd: Register cache for smbwstrd value. + * @smbwstwr: Register cache for smbwstwr value. + * @smbwstoen: Register cache for smbwstoen value. + * @smbwstwen: Register cache for smbwstwen value. + * @smbwstbrd: Register cache for smbwstbrd value. + * + * Timing information for a IO bank on an S3C2412 or similar system which + * uses a PL093 block. + */ +struct s3c2412_iobank_timing { + unsigned int idcy; + unsigned int wstrd; + unsigned int wstwr; + unsigned int wstoen; + unsigned int wstwen; + unsigned int wstbrd; + + /* register cache */ + unsigned char smbidcyr; + unsigned char smbwstrd; + unsigned char smbwstwr; + unsigned char smbwstoen; + unsigned char smbwstwen; + unsigned char smbwstbrd; +}; + +union s3c_iobank { + struct s3c2410_iobank_timing *io_2410; + struct s3c2412_iobank_timing *io_2412; +}; + +/** + * struct s3c_iotimings - Chip IO timings holder + * @bank: The timings for each IO bank. + */ +struct s3c_iotimings { + union s3c_iobank bank[MAX_BANKS]; +}; + +/** + * struct s3c_plltab - PLL table information. + * @vals: List of PLL values. + * @size: Size of the PLL table @vals. + */ +struct s3c_plltab { + struct s3c_pllval *vals; + int size; +}; + +/** + * struct s3c_cpufreq_config - current cpu frequency configuration + * @freq: The current settings for the core clocks. + * @max: Maxium settings, derived from core, board and user settings. + * @pll: The PLL table entry for the current PLL settings. + * @divs: The divisor settings for the core clocks. + * @info: The current core driver information. + * @board: The information for the board we are running on. + * @lock_pll: Set if the PLL settings cannot be changed. + * + * This is for the core drivers that need to know information about + * the current settings and values. It should not be needed by any + * device drivers. +*/ +struct s3c_cpufreq_config { + struct s3c_freq freq; + struct s3c_freq max; + struct clk *mpll; + struct cpufreq_frequency_table pll; + struct s3c_clkdivs divs; + struct s3c_cpufreq_info *info; /* for core, not drivers */ + struct s3c_cpufreq_board *board; + + unsigned int lock_pll:1; +}; + +/** + * struct s3c_cpufreq_info - Information for the CPU frequency driver. + * @name: The name of this implementation. + * @max: The maximum frequencies for the system. + * @latency: Transition latency to give to cpufreq. + * @locktime_m: The lock-time in uS for the MPLL. + * @locktime_u: The lock-time in uS for the UPLL. + * @locttime_bits: The number of bits each LOCKTIME field. + * @need_pll: Set if this driver needs to change the PLL values to achieve + * any frequency changes. This is really only need by devices like the + * S3C2410 where there is no or limited divider between the PLL and the + * ARMCLK. + * @get_iotiming: Get the current IO timing data, mainly for use at start. + * @set_iotiming: Update the IO timings from the cached copies calculated + * from the @calc_iotiming entry when changing the frequency. + * @calc_iotiming: Calculate and update the cached copies of the IO timings + * from the newly calculated frequencies. + * @calc_freqtable: Calculate (fill in) the given frequency table from the + * current frequency configuration. If the table passed in is NULL, + * then the return is the number of elements to be filled for allocation + * of the table. + * @set_refresh: Set the memory refresh configuration. + * @set_fvco: Set the PLL frequencies. + * @set_divs: Update the clock divisors. + * @calc_divs: Calculate the clock divisors. + */ +struct s3c_cpufreq_info { + const char *name; + struct s3c_freq max; + + unsigned int latency; + + unsigned int locktime_m; + unsigned int locktime_u; + unsigned char locktime_bits; + + unsigned int need_pll:1; + + /* driver routines */ + + int (*get_iotiming)(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *timings); + + void (*set_iotiming)(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *timings); + + int (*calc_iotiming)(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *timings); + + int (*calc_freqtable)(struct s3c_cpufreq_config *cfg, + struct cpufreq_frequency_table *t, + size_t table_size); + + void (*debug_io_show)(struct seq_file *seq, + struct s3c_cpufreq_config *cfg, + union s3c_iobank *iob); + + void (*set_refresh)(struct s3c_cpufreq_config *cfg); + void (*set_fvco)(struct s3c_cpufreq_config *cfg); + void (*set_divs)(struct s3c_cpufreq_config *cfg); + int (*calc_divs)(struct s3c_cpufreq_config *cfg); +}; + +extern int s3c_cpufreq_register(struct s3c_cpufreq_info *info); + +extern int s3c_plltab_register(struct cpufreq_frequency_table *plls, + unsigned int plls_no); + +/* exports and utilities for debugfs */ +extern struct s3c_cpufreq_config *s3c_cpufreq_getconfig(void); +extern struct s3c_iotimings *s3c_cpufreq_getiotimings(void); + +#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_DEBUGFS +#define s3c_cpufreq_debugfs_call(x) x +#else +#define s3c_cpufreq_debugfs_call(x) NULL +#endif + +/* Useful utility functions. */ + +extern struct clk *s3c_cpufreq_clk_get(struct device *, const char *); + +/* S3C2410 and compatible exported functions */ + +extern void s3c2410_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg); +extern void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg); + +#ifdef CONFIG_S3C2410_IOTIMING +extern void s3c2410_iotiming_debugfs(struct seq_file *seq, + struct s3c_cpufreq_config *cfg, + union s3c_iobank *iob); + +extern int s3c2410_iotiming_calc(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *iot); + +extern int s3c2410_iotiming_get(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *timings); + +extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *iot); +#else +#define s3c2410_iotiming_debugfs NULL +#define s3c2410_iotiming_calc NULL +#define s3c2410_iotiming_get NULL +#define s3c2410_iotiming_set NULL +#endif /* CONFIG_S3C2410_IOTIMING */ + +/* S3C2412 compatible routines */ + +#ifdef CONFIG_S3C2412_IOTIMING +extern void s3c2412_iotiming_debugfs(struct seq_file *seq, + struct s3c_cpufreq_config *cfg, + union s3c_iobank *iob); + +extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *timings); + +extern int s3c2412_iotiming_calc(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *iot); + +extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg, + struct s3c_iotimings *iot); +#else +#define s3c2412_iotiming_debugfs NULL +#define s3c2412_iotiming_calc NULL +#define s3c2412_iotiming_get NULL +#define s3c2412_iotiming_set NULL +#endif /* CONFIG_S3C2412_IOTIMING */ + +#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_DEBUG +#define s3c_freq_dbg(x...) printk(KERN_INFO x) +#else +#define s3c_freq_dbg(x...) do { if (0) printk(x); } while (0) +#endif /* CONFIG_ARM_S3C24XX_CPUFREQ_DEBUG */ + +#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_IODEBUG +#define s3c_freq_iodbg(x...) printk(KERN_INFO x) +#else +#define s3c_freq_iodbg(x...) do { if (0) printk(x); } while (0) +#endif /* CONFIG_ARM_S3C24XX_CPUFREQ_IODEBUG */ + +static inline int s3c_cpufreq_addfreq(struct cpufreq_frequency_table *table, + int index, size_t table_size, + unsigned int freq) +{ + if (index < 0) + return index; + + if (table) { + if (index >= table_size) + return -ENOMEM; + + s3c_freq_dbg("%s: { %d = %u kHz }\n", + __func__, index, freq); + + table[index].driver_data = index; + table[index].frequency = freq; + } + + return index + 1; +} + +#endif diff --git a/include/linux/soc/samsung/s3c-pm.h b/include/linux/soc/samsung/s3c-pm.h index 730bd1d3d09a..f9164559c99f 100644 --- a/include/linux/soc/samsung/s3c-pm.h +++ b/include/linux/soc/samsung/s3c-pm.h @@ -81,4 +81,14 @@ extern void s3c_pm_check_store(void); #define s3c_pm_check_store() do { } while (0) #endif +/* system device subsystems */ + +extern struct bus_type s3c2410_subsys; +extern struct bus_type s3c2410a_subsys; +extern struct bus_type s3c2412_subsys; +extern struct bus_type s3c2416_subsys; +extern struct bus_type s3c2440_subsys; +extern struct bus_type s3c2442_subsys; +extern struct bus_type s3c2443_subsys; + #endif -- cgit v1.2.3 From 44c01f5ce1c7518886a87d5522528e30e0b4d9f8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:53 +0200 Subject: cpufreq: s3c2412: use global s3c2412_cpufreq_setrefresh There are two identical copies of the s3c2412_cpufreq_setrefresh function: a static one in the cpufreq driver and a global version in iotiming-s3c2412.c. As the function requires the use of a hardcoded register address from a header that we want to not be visible to drivers, just move the existing global function and add a declaration in one of the cpufreq header files. Signed-off-by: Arnd Bergmann Acked-by: Viresh Kumar Link: https://lore.kernel.org/r/20200806182059.2431-36-krzk@kernel.org Signed-off-by: Krzysztof Kozlowski --- include/linux/soc/samsung/s3c-cpufreq-core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/soc/samsung/s3c-cpufreq-core.h b/include/linux/soc/samsung/s3c-cpufreq-core.h index c578b07ccd5d..e0c7217a0f53 100644 --- a/include/linux/soc/samsung/s3c-cpufreq-core.h +++ b/include/linux/soc/samsung/s3c-cpufreq-core.h @@ -248,6 +248,7 @@ extern int s3c2412_iotiming_calc(struct s3c_cpufreq_config *cfg, extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg, struct s3c_iotimings *iot); +extern void s3c2412_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg); #else #define s3c2412_iotiming_debugfs NULL #define s3c2412_iotiming_calc NULL -- cgit v1.2.3 From c38758e3d574380ccfa583793be14c1cc8a322ff Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 6 Aug 2020 20:20:54 +0200 Subject: cpufreq: s3c24xx: move low-level clk reg access into platform code Rather than have the cpufreq drivers touch include the common headers to get the constants, add a small indirection. This is still not the proper way that would do this through the common clk API, but it lets us kill off the header file usage. Signed-off-by: Arnd Bergmann Acked-by: Viresh Kumar Link: https://lore.kernel.org/r/20200806182059.2431-37-krzk@kernel.org [krzk: Rebase and fix -Wold-style-definition] Signed-off-by: Krzysztof Kozlowski --- include/linux/soc/samsung/s3c-cpufreq-core.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/soc/samsung/s3c-cpufreq-core.h b/include/linux/soc/samsung/s3c-cpufreq-core.h index e0c7217a0f53..3b278afb769b 100644 --- a/include/linux/soc/samsung/s3c-cpufreq-core.h +++ b/include/linux/soc/samsung/s3c-cpufreq-core.h @@ -289,4 +289,11 @@ static inline int s3c_cpufreq_addfreq(struct cpufreq_frequency_table *table, return index + 1; } +u32 s3c2440_read_camdivn(void); +void s3c2440_write_camdivn(u32 camdiv); +u32 s3c24xx_read_clkdivn(void); +void s3c24xx_write_clkdivn(u32 clkdiv); +u32 s3c24xx_read_mpllcon(void); +void s3c24xx_write_locktime(u32 locktime); + #endif -- cgit v1.2.3 From 8d5930dfb7edbf136f2d9900be34ca7af4ba38c1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 10 Jul 2020 20:07:10 -0400 Subject: skb_copy_and_csum_bits(): don't bother with the last argument it's always 0 Signed-off-by: Al Viro --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46881d902124..31a6d2fce071 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3535,7 +3535,7 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, - int len, __wsum csum); + int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); -- cgit v1.2.3 From 6e41c585e38ff696de3a11509a0ad0a11150b0c3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 22 Jul 2020 22:14:36 -0400 Subject: unify generic instances of csum_partial_copy_nocheck() quite a few architectures have the same csum_partial_copy_nocheck() - simply memcpy() the data and then return the csum of the copy. hexagon, parisc, ia64, s390, um: explicitly spelled out that way. arc, arm64, csky, h8300, m68k/nommu, microblaze, mips/GENERIC_CSUM, nds32, nios2, openrisc, riscv, unicore32: end up picking the same thing spelled out in lib/checksum.h (with varying amounts of perversions along the way). everybody else (alpha, arm, c6x, m68k/mmu, mips/!GENERIC_CSUM, powerpc, sh, sparc, x86, xtensa) have non-generic variants. For all except c6x the declaration is in their asm/checksum.h. c6x uses the wrapper from asm-generic/checksum.h that would normally lead to the lib/checksum.h instance, but in case of c6x we end up using an asm function from arch/c6x instead. Screw that mess - have architectures with private instances define _HAVE_ARCH_CSUM_AND_COPY in their asm/checksum.h and have the default one right in net/checksum.h conditional on _HAVE_ARCH_CSUM_AND_COPY *not* defined. Signed-off-by: Al Viro --- include/asm-generic/checksum.h | 12 ------------ include/net/checksum.h | 9 +++++++++ 2 files changed, 9 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h index cd8b75aa770d..43e18db89c14 100644 --- a/include/asm-generic/checksum.h +++ b/include/asm-generic/checksum.h @@ -16,18 +16,6 @@ */ extern __wsum csum_partial(const void *buff, int len, __wsum sum); -/* - * the same as csum_partial, but copies from src while it - * checksums - * - * here even more important to align src and dst on a 32-bit (or even - * better 64-bit) boundary - */ -#ifndef csum_partial_copy_nocheck -__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, - __wsum sum); -#endif - #ifndef ip_fast_csum /* * This is a version of ip_compute_csum() optimized for IP headers, diff --git a/include/net/checksum.h b/include/net/checksum.h index 46754ba9d7b7..db9d02b5f88a 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -47,6 +47,15 @@ static __inline__ __wsum csum_and_copy_to_user } #endif +#ifndef _HAVE_ARCH_CSUM_AND_COPY +static inline __wsum +csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum) +{ + memcpy(dst, src, len); + return csum_partial(dst, len, sum); +} +#endif + #ifndef HAVE_ARCH_CSUM_ADD static inline __wsum csum_add(__wsum csum, __wsum addend) { -- cgit v1.2.3 From cc44c17baf7f3f833d36b2f2a1edb1cc0b6f2cc4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 11 Jul 2020 00:12:07 -0400 Subject: csum_partial_copy_nocheck(): drop the last argument It's always 0. Note that we theoretically could use ~0U as well - result will be the same modulo 0xffff, _if_ the damn thing did the right thing for any value of initial sum; later we'll make use of that when convenient. However, unlike csum_and_copy_..._user(), there are instances that did not work for arbitrary initial sums; c6x is one such. Signed-off-by: Al Viro --- include/net/checksum.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/checksum.h b/include/net/checksum.h index db9d02b5f88a..1029191986e3 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -49,10 +49,10 @@ static __inline__ __wsum csum_and_copy_to_user #ifndef _HAVE_ARCH_CSUM_AND_COPY static inline __wsum -csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum) +csum_partial_copy_nocheck(const void *src, void *dst, int len) { memcpy(dst, src, len); - return csum_partial(dst, len, sum); + return csum_partial(dst, len, 0); } #endif -- cgit v1.2.3 From c693cc4676a055c4126e487b30b0a96ea7ec9936 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 11 Jul 2020 00:27:49 -0400 Subject: saner calling conventions for csum_and_copy_..._user() All callers of these primitives will * discard anything we might've copied in case of error * ignore the csum value in case of error * always pass 0xffffffff as the initial sum, so the resulting csum value (in case of success, that is) will never be 0. That suggest the following calling conventions: * don't pass err_ptr - just return 0 on error. * don't bother with zeroing destination, etc. in case of error * don't pass the initial sum - just use 0xffffffff. This commit does the minimal conversion in the instances of csum_and_copy_...(); the changes of actual asm code behind them are done later in the series. Note that this asm code is often shared with csum_partial_copy_nocheck(); the difference is that csum_partial_copy_nocheck() passes 0 for initial sum while csum_and_copy_..._user() pass 0xffffffff. Fortunately, we are free to pass 0xffffffff in all cases and subsequent patches will use that freedom without any special comments. A part that could be split off: parisc and uml/i386 claimed to have csum_and_copy_to_user() instances of their own, but those were identical to the generic one, so we simply drop them. Not sure if it's worth a separate commit... Signed-off-by: Al Viro --- include/net/checksum.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/checksum.h b/include/net/checksum.h index 1029191986e3..0d05b9e8690b 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -24,26 +24,23 @@ #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER static inline __wsum csum_and_copy_from_user (const void __user *src, void *dst, - int len, __wsum sum, int *err_ptr) + int len) { if (copy_from_user(dst, src, len)) - *err_ptr = -EFAULT; - return csum_partial(dst, len, sum); + return 0; + return csum_partial(dst, len, ~0U); } #endif #ifndef HAVE_CSUM_COPY_USER static __inline__ __wsum csum_and_copy_to_user -(const void *src, void __user *dst, int len, __wsum sum, int *err_ptr) +(const void *src, void __user *dst, int len) { - sum = csum_partial(src, len, sum); + __wsum sum = csum_partial(src, len, ~0U); if (copy_to_user(dst, src, len) == 0) return sum; - if (len) - *err_ptr = -EFAULT; - - return (__force __wsum)-1; /* invalid checksum */ + return 0; } #endif -- cgit v1.2.3 From 8afa25aa833fbd4f3aa701cb42ebd52b1deef1d3 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Mon, 10 Aug 2020 17:40:15 -0700 Subject: crypto: hash - Remove unused async iterators Revert "crypto: hash - Add real ahash walk interface" This reverts commit 75ecb231ff45b54afa9f4ec9137965c3c00868f4. The callers of the functions in this commit were removed in ab8085c130ed Remove these unused calls. Fixes: ab8085c130ed ("crypto: x86 - remove SHA multibuffer routines and mcryptd") Cc: Ard Biesheuvel Signed-off-by: Ira Weiny Signed-off-by: Herbert Xu --- include/crypto/internal/hash.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 89f6f46ab2b8..6d3ad5ac4d28 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -62,25 +62,12 @@ struct crypto_shash_spawn { int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err); int crypto_hash_walk_first(struct ahash_request *req, struct crypto_hash_walk *walk); -int crypto_ahash_walk_first(struct ahash_request *req, - struct crypto_hash_walk *walk); - -static inline int crypto_ahash_walk_done(struct crypto_hash_walk *walk, - int err) -{ - return crypto_hash_walk_done(walk, err); -} static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) { return !(walk->entrylen | walk->total); } -static inline int crypto_ahash_walk_last(struct crypto_hash_walk *walk) -{ - return crypto_hash_walk_last(walk); -} - int crypto_register_ahash(struct ahash_alg *alg); void crypto_unregister_ahash(struct ahash_alg *alg); int crypto_register_ahashes(struct ahash_alg *algs, int count); -- cgit v1.2.3 From ba171d3f0850003216fd1a85190d17b1feddb961 Mon Sep 17 00:00:00 2001 From: Cedric Neveux Date: Mon, 4 Mar 2019 08:54:23 +0100 Subject: driver: tee: Handle NULL pointer indication from client TEE Client introduce a new capability "TEE_GEN_CAP_MEMREF_NULL" to handle the support of the shared memory buffer with a NULL pointer. This capability depends on TEE Capabilities and driver support. Driver and TEE exchange capabilities at driver initialization. Signed-off-by: Michael Whitfield Signed-off-by: Cedric Neveux Reviewed-by: Joakim Bech Tested-by: Joakim Bech (QEMU) Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 3 +++ include/uapi/linux/tee.h | 13 +++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index d074302989dd..cdd049a724b1 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -47,6 +47,8 @@ struct tee_shm_pool; * and just return with an error code. It is needed for requests * that arises from TEE based kernel drivers that should be * non-blocking in nature. + * @cap_memref_null: flag indicating if the TEE Client support shared + * memory buffer with a NULL pointer. */ struct tee_context { struct tee_device *teedev; @@ -54,6 +56,7 @@ struct tee_context { struct kref refcount; bool releasing; bool supp_nowait; + bool cap_memref_null; }; struct tee_param_memref { diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index b619f37ee03e..d67cadf221fc 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -51,6 +51,9 @@ #define TEE_GEN_CAP_GP (1 << 0)/* GlobalPlatform compliant TEE */ #define TEE_GEN_CAP_PRIVILEGED (1 << 1)/* Privileged device (for supplicant) */ #define TEE_GEN_CAP_REG_MEM (1 << 2)/* Supports registering shared memory */ +#define TEE_GEN_CAP_MEMREF_NULL (1 << 3)/* NULL MemRef support */ + +#define TEE_MEMREF_NULL (__u64)(-1) /* NULL MemRef Buffer */ /* * TEE Implementation ID @@ -200,6 +203,16 @@ struct tee_ioctl_buf_data { * a part of a shared memory by specifying an offset (@a) and size (@b) of * the object. To supply the entire shared memory object set the offset * (@a) to 0 and size (@b) to the previously returned size of the object. + * + * A client may need to present a NULL pointer in the argument + * passed to a trusted application in the TEE. + * This is also a requirement in GlobalPlatform Client API v1.0c + * (section 3.2.5 memory references), which can be found at + * http://www.globalplatform.org/specificationsdevice.asp + * + * If a NULL pointer is passed to a TA in the TEE, the (@c) + * IOCTL parameters value must be set to TEE_MEMREF_NULL indicating a NULL + * memory reference. */ struct tee_ioctl_param { __u64 attr; -- cgit v1.2.3 From 6b0a249a301e2af9adda84adbced3a2988248b95 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Fri, 21 Aug 2020 11:44:18 -0700 Subject: bpf: Implement link_query for bpf iterators This patch implemented bpf_link callback functions show_fdinfo and fill_link_info to support link_query interface. The general interface for show_fdinfo and fill_link_info will print/fill the target_name. Each targets can register show_fdinfo and fill_link_info callbacks to print/fill more target specific information. For example, the below is a fdinfo result for a bpf task iterator. $ cat /proc/1749/fdinfo/7 pos: 0 flags: 02000000 mnt_id: 14 link_type: iter link_id: 11 prog_tag: 990e1f8152f7e54f prog_id: 59 target_name: task Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200821184418.574122-1-yhs@fb.com --- include/linux/bpf.h | 6 ++++++ include/uapi/linux/bpf.h | 7 +++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a9b7185a6b37..529e9b183eeb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1218,12 +1218,18 @@ typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); +typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, + struct seq_file *seq); +typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info); #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; + bpf_iter_show_fdinfo_t show_fdinfo; + bpf_iter_fill_link_info_t fill_link_info; u32 ctx_arg_info_size; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0480f893facd..a1bbaff7a0af 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4071,6 +4071,13 @@ struct bpf_link_info { __u64 cgroup_id; __u32 attach_type; } cgroup; + struct { + __aligned_u64 target_name; /* in/out: target_name buffer ptr */ + __u32 target_name_len; /* in/out: target_name buffer len */ + union { + __u32 map_id; + } map; + } iter; struct { __u32 netns_ino; __u32 attach_type; -- cgit v1.2.3 From b76f22269028fb252727a696084c70494d80a52c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Fri, 21 Aug 2020 11:44:19 -0700 Subject: bpf: Implement link_query callbacks in map element iterators For bpf_map_elem and bpf_sk_local_storage bpf iterators, additional map_id should be shown for fdinfo and userspace query. For example, the following is for a bpf_map_elem iterator. $ cat /proc/1753/fdinfo/9 pos: 0 flags: 02000000 mnt_id: 14 link_type: iter link_id: 34 prog_tag: 104be6d3fe45e6aa prog_id: 173 target_name: bpf_map_elem map_id: 127 Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200821184419.574240-1-yhs@fb.com --- include/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 529e9b183eeb..30c144af894a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1256,6 +1256,10 @@ int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); +void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq); +int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From dd8166212d9a2eca3181567c953d5687aea4d7dc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thi=C3=A9baud=20Weksteen?= Date: Fri, 21 Aug 2020 16:08:21 +0200 Subject: selinux: add tracepoint on audited events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The audit data currently captures which process and which target is responsible for a denial. There is no data on where exactly in the process that call occurred. Debugging can be made easier by being able to reconstruct the unified kernel and userland stack traces [1]. Add a tracepoint on the SELinux denials which can then be used by userland (i.e. perf). Although this patch could manually be added by each OS developer to trouble shoot a denial, adding it to the kernel streamlines the developers workflow. It is possible to use perf for monitoring the event: # perf record -e avc:selinux_audited -g -a ^C # perf report -g [...] 6.40% 6.40% audited=800000 tclass=4 | __libc_start_main | |--4.60%--__GI___ioctl | entry_SYSCALL_64 | do_syscall_64 | __x64_sys_ioctl | ksys_ioctl | binder_ioctl | binder_set_nice | can_nice | capable | security_capable | cred_has_capability.isra.0 | slow_avc_audit | common_lsm_audit | avc_audit_post_callback | avc_audit_post_callback | It is also possible to use the ftrace interface: # echo 1 > /sys/kernel/debug/tracing/events/avc/selinux_audited/enable # cat /sys/kernel/debug/tracing/trace tracer: nop entries-in-buffer/entries-written: 1/1 #P:8 [...] dmesg-3624 [001] 13072.325358: selinux_denied: audited=800000 tclass=4 The tclass value can be mapped to a class by searching security/selinux/flask.h. The audited value is a bit field of the permissions described in security/selinux/av_permissions.h for the corresponding class. [1] https://source.android.com/devices/tech/debug/native_stack_dump Signed-off-by: Thiébaud Weksteen Suggested-by: Joel Fernandes Reviewed-by: Peter Enderborg Acked-by: Stephen Smalley Signed-off-by: Paul Moore --- include/trace/events/avc.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/trace/events/avc.h (limited to 'include') diff --git a/include/trace/events/avc.h b/include/trace/events/avc.h new file mode 100644 index 000000000000..07c058a9bbcd --- /dev/null +++ b/include/trace/events/avc.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Author: Thiébaud Weksteen + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM avc + +#if !defined(_TRACE_SELINUX_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_SELINUX_H + +#include + +TRACE_EVENT(selinux_audited, + + TP_PROTO(struct selinux_audit_data *sad), + + TP_ARGS(sad), + + TP_STRUCT__entry( + __field(unsigned int, tclass) + __field(unsigned int, audited) + ), + + TP_fast_assign( + __entry->tclass = sad->tclass; + __entry->audited = sad->audited; + ), + + TP_printk("tclass=%u audited=%x", + __entry->tclass, + __entry->audited) +); + +#endif + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 30969bc8e0751a5e5d44896c0632bc688abfa86f Mon Sep 17 00:00:00 2001 From: Peter Enderborg Date: Fri, 21 Aug 2020 16:08:22 +0200 Subject: selinux: add basic filtering for audit trace events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds further attributes to the event. These attributes are helpful to understand the context of the message and can be used to filter the events. There are three common items. Source context, target context and tclass. There are also items from the outcome of operation performed. An event is similar to: <...>-1309 [002] .... 6346.691689: selinux_audited: requested=0x4000000 denied=0x4000000 audited=0x4000000 result=-13 scontext=system_u:system_r:cupsd_t:s0-s0:c0.c1023 tcontext=system_u:object_r:bin_t:s0 tclass=file With systems where many denials are occurring, it is useful to apply a filter. The filtering is a set of logic that is inserted with the filter file. Example: echo "tclass==\"file\" " > events/avc/selinux_audited/filter This adds that we only get tclass=file. The trace can also have extra properties. Adding the user stack can be done with echo 1 > options/userstacktrace Now the output will be runcon-1365 [003] .... 6960.955530: selinux_audited: requested=0x4000000 denied=0x4000000 audited=0x4000000 result=-13 scontext=system_u:system_r:cupsd_t:s0-s0:c0.c1023 tcontext=system_u:object_r:bin_t:s0 tclass=file runcon-1365 [003] .... 6960.955560: => <00007f325b4ce45b> => <00005607093efa57> Signed-off-by: Peter Enderborg Reviewed-by: Thiébaud Weksteen Acked-by: Stephen Smalley Signed-off-by: Paul Moore --- include/trace/events/avc.h | 36 ++++++++++++++++++++++++++---------- 1 file changed, 26 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/trace/events/avc.h b/include/trace/events/avc.h index 07c058a9bbcd..b55fda2e0773 100644 --- a/include/trace/events/avc.h +++ b/include/trace/events/avc.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Author: Thiébaud Weksteen + * Authors: Thiébaud Weksteen + * Peter Enderborg */ #undef TRACE_SYSTEM #define TRACE_SYSTEM avc @@ -12,23 +13,38 @@ TRACE_EVENT(selinux_audited, - TP_PROTO(struct selinux_audit_data *sad), + TP_PROTO(struct selinux_audit_data *sad, + char *scontext, + char *tcontext, + const char *tclass + ), - TP_ARGS(sad), + TP_ARGS(sad, scontext, tcontext, tclass), TP_STRUCT__entry( - __field(unsigned int, tclass) - __field(unsigned int, audited) + __field(u32, requested) + __field(u32, denied) + __field(u32, audited) + __field(int, result) + __string(scontext, scontext) + __string(tcontext, tcontext) + __string(tclass, tclass) ), TP_fast_assign( - __entry->tclass = sad->tclass; - __entry->audited = sad->audited; + __entry->requested = sad->requested; + __entry->denied = sad->denied; + __entry->audited = sad->audited; + __entry->result = sad->result; + __assign_str(tcontext, tcontext); + __assign_str(scontext, scontext); + __assign_str(tclass, tclass); ), - TP_printk("tclass=%u audited=%x", - __entry->tclass, - __entry->audited) + TP_printk("requested=0x%x denied=0x%x audited=0x%x result=%d scontext=%s tcontext=%s tclass=%s", + __entry->requested, __entry->denied, __entry->audited, __entry->result, + __get_str(scontext), __get_str(tcontext), __get_str(tclass) + ) ); #endif -- cgit v1.2.3 From 7b219da43f94a3b4d5a8aa4cc52b75b34f0301ec Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Fri, 21 Aug 2020 11:29:43 +0100 Subject: net: sk_msg: Simplify sk_psock initialization Initializing psock->sk_proto and other saved callbacks is only done in sk_psock_update_proto, after sk_psock_init has returned. The logic for this is difficult to follow, and needlessly complex. Instead, initialize psock->sk_proto whenever we allocate a new psock. Additionally, assert the following invariants: * The SK has no ULP: ULP does it's own finagling of sk->sk_prot * sk_user_data is unused: we need it to store sk_psock Protect our access to sk_user_data with sk_callback_lock, which is what other users like reuseport arrays, etc. do. The result is that an sk_psock is always fully initialized, and that psock->sk_proto is always the "original" struct proto. The latter allows us to use psock->sk_proto when initializing IPv6 TCP / UDP callbacks for sockmap. Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com --- include/linux/skmsg.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 1e9ed840b9fc..3119928fc103 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -340,23 +340,6 @@ static inline void sk_psock_update_proto(struct sock *sk, struct sk_psock *psock, struct proto *ops) { - /* Initialize saved callbacks and original proto only once, since this - * function may be called multiple times for a psock, e.g. when - * psock->progs.msg_parser is updated. - * - * Since we've not installed the new proto, psock is not yet in use and - * we can initialize it without synchronization. - */ - if (!psock->sk_proto) { - struct proto *orig = READ_ONCE(sk->sk_prot); - - psock->saved_unhash = orig->unhash; - psock->saved_close = orig->close; - psock->saved_write_space = sk->sk_write_space; - - psock->sk_proto = orig; - } - /* Pairs with lockless read in sk_clone_lock() */ WRITE_ONCE(sk->sk_prot, ops); } -- cgit v1.2.3 From 13b79d3ffbb8add9e2a6d604db2b49f241b97303 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Fri, 21 Aug 2020 11:29:45 +0100 Subject: bpf: sockmap: Call sock_map_update_elem directly Don't go via map->ops to call sock_map_update_elem, since we know what function to call in bpf_map_update_value. Since we currently don't allow calling map_update_elem from BPF context, we can remove ops->map_update_elem and rename the function to sock_map_update_elem_sys. Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200821102948.21918-4-lmb@cloudflare.com --- include/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 30c144af894a..81f38e2fda78 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1648,6 +1648,7 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -1669,6 +1670,12 @@ static inline int sock_map_prog_detach(const union bpf_attr *attr, { return -EOPNOTSUPP; } + +static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, + u64 flags) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) -- cgit v1.2.3 From 4ffa22fd22a7cbde1a1394b2707ea73593dc0fda Mon Sep 17 00:00:00 2001 From: Matt Ranostay Date: Thu, 23 Jul 2020 09:29:43 +0300 Subject: iio: add IIO_MOD_O2 modifier Add modifier IIO_MOD_O2 for O2 concentration reporting Signed-off-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- include/uapi/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index fdd81affca4b..48c13147c0a8 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -94,6 +94,7 @@ enum iio_modifier { IIO_MOD_PM10, IIO_MOD_ETHANOL, IIO_MOD_H2, + IIO_MOD_O2, }; enum iio_event_type { -- cgit v1.2.3 From 781cb90b0529b5bb84c63691fe42a7c26d197aec Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:30:40 -0700 Subject: platform_data: ad7793.h: drop a duplicated word Drop the repeated word "and" in a comment. Signed-off-by: Randy Dunlap Cc: Lars-Peter Clausen Cc: Jonathan Cameron Signed-off-by: Jonathan Cameron --- include/linux/platform_data/ad7793.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/ad7793.h b/include/linux/platform_data/ad7793.h index 576c7f962c4e..7c697e58f02a 100644 --- a/include/linux/platform_data/ad7793.h +++ b/include/linux/platform_data/ad7793.h @@ -40,7 +40,7 @@ enum ad7793_bias_voltage { * enum ad7793_refsel - AD7793 reference voltage selection * @AD7793_REFSEL_REFIN1: External reference applied between REFIN1(+) * and REFIN1(-). - * @AD7793_REFSEL_REFIN2: External reference applied between REFIN2(+) and + * @AD7793_REFSEL_REFIN2: External reference applied between REFIN2(+) * and REFIN1(-). Only valid for AD7795/AD7796. * @AD7793_REFSEL_INTERNAL: Internal 1.17 V reference. */ -- cgit v1.2.3 From eee049c0ef5b5b433f36841801e34c21c9f82a23 Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Sat, 22 Aug 2020 15:59:08 +0100 Subject: l2tp: remove tunnel and session debug flags field The l2tp subsystem now uses standard kernel logging APIs for informational and warning messages, and tracepoints for debug information. Now that the tunnel and session debug flags are unused, remove the field from the core structures. Various system calls (in the case of l2tp_ppp) and netlink messages handle the getting and setting of debug flags. To avoid userspace breakage don't modify the API of these calls; simply ignore set requests, and send dummy data for get requests. Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- include/uapi/linux/if_pppol2tp.h | 2 +- include/uapi/linux/l2tp.h | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 060b4d1f3129..a91044328bc9 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -75,7 +75,7 @@ struct pppol2tpv3in6_addr { }; /* Socket options: - * DEBUG - bitmask of debug message categories + * DEBUG - bitmask of debug message categories (not used) * SENDSEQ - 0 => don't send packets with sequence numbers * 1 => send packets with sequence numbers * RECVSEQ - 0 => receive packet sequence numbers are optional diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 61158f5a1a5b..88a0d32b8c07 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -108,7 +108,7 @@ enum { L2TP_ATTR_VLAN_ID, /* u16 (not used) */ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ - L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */ + L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags (not used) */ L2TP_ATTR_RECV_SEQ, /* u8 */ L2TP_ATTR_SEND_SEQ, /* u8 */ L2TP_ATTR_LNS_MODE, /* u8 */ @@ -177,7 +177,9 @@ enum l2tp_seqmode { }; /** - * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions + * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions. + * + * Unused. * * @L2TP_MSG_DEBUG: verbose debug (if compiled in) * @L2TP_MSG_CONTROL: userspace - kernel interface -- cgit v1.2.3 From 0b8056106c02bef72b9d47524dc3c59ccf99124d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 17 Aug 2020 17:12:54 +0200 Subject: clk: imx: vf610: Add CRC clock Add the clock for CRC block allowing it to be enabled by consumers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Shawn Guo --- include/dt-bindings/clock/vf610-clock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/vf610-clock.h b/include/dt-bindings/clock/vf610-clock.h index 0f2d60e884dc..373644e46747 100644 --- a/include/dt-bindings/clock/vf610-clock.h +++ b/include/dt-bindings/clock/vf610-clock.h @@ -196,6 +196,7 @@ #define VF610_CLK_TCON0 187 #define VF610_CLK_TCON1 188 #define VF610_CLK_CAAM 189 -#define VF610_CLK_END 190 +#define VF610_CLK_CRC 190 +#define VF610_CLK_END 191 #endif /* __DT_BINDINGS_CLOCK_VF610_H */ -- cgit v1.2.3 From e2d977c9f1abd1d199b412f8f83c1727808b794d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 14 Aug 2020 12:19:35 +0200 Subject: timekeeping: Provide multi-timestamp accessor to NMI safe timekeeper printk wants to store various timestamps (MONOTONIC, REALTIME, BOOTTIME) to make correlation of dmesg from several systems easier. Provide an interface to retrieve all three timestamps in one go. There are some caveats: 1) Boot time and late sleep time injection Boot time is a racy access on 32bit systems if the sleep time injection happens late during resume and not in timekeeping_resume(). That could be avoided by expanding struct tk_read_base with boot offset for 32bit and adding more overhead to the update. As this is a hard to observe once per resume event which can be filtered with reasonable effort using the accurate mono/real timestamps, it's probably not worth the trouble. Aside of that it might be possible on 32 and 64 bit to observe the following when the sleep time injection happens late: CPU 0 CPU 1 timekeeping_resume() ktime_get_fast_timestamps() mono, real = __ktime_get_real_fast() inject_sleep_time() update boot offset boot = mono + bootoffset; That means that boot time already has the sleep time adjustment, but real time does not. On the next readout both are in sync again. Preventing this for 64bit is not really feasible without destroying the careful cache layout of the timekeeper because the sequence count and struct tk_read_base would then need two cache lines instead of one. 2) Suspend/resume timestamps Access to the time keeper clock source is disabled accross the innermost steps of suspend/resume. The accessors still work, but the timestamps are frozen until time keeping is resumed which happens very early. For regular suspend/resume there is no observable difference vs. sched clock, but it might affect some of the nasty low level debug printks. OTOH, access to sched clock is not guaranteed accross suspend/resume on all systems either so it depends on the hardware in use. If that turns out to be a real problem then this could be mitigated by using sched clock in a similar way as during early boot. But it's not as trivial as on early boot because it needs some careful protection against the clock monotonic timestamp jumping backwards on resume. Signed-off-by: Thomas Gleixner Tested-by: Petr Mladek Link: https://lore.kernel.org/r/20200814115512.159981360@linutronix.de --- include/linux/timekeeping.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index d5471d6fa778..7f7e4a3f4394 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -222,6 +222,18 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); +/* + * struct ktime_timestanps - Simultaneous mono/boot/real timestamps + * @mono: Monotonic timestamp + * @boot: Boottime timestamp + * @real: Realtime timestamp + */ +struct ktime_timestamps { + u64 mono; + u64 boot; + u64 real; +}; + /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value @@ -280,6 +292,9 @@ extern int get_device_system_crosststamp( */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); +/* NMI safe mono/boot/realtime timestamps */ +extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); + /* * Persistent clock related interfaces */ -- cgit v1.2.3 From 2152fbbd47c06c4f50ad265ec1b0c43673bee3e8 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 3 Jul 2020 09:07:29 -0700 Subject: soc: ti: pm33xx: Simplify RTC usage to prepare to drop platform data We must re-enable the RTC module clock enabled in RTC+DDR suspend, and pm33xx has been using platform data callbacks for that. Looks like for retention suspend the RTC module clock must not be re-enabled. To remove the legacy platform data callbacks, and eventually be able to drop the RTC legacy platform data, let's manage the RTC module clock and register range directly in pm33xx. Acked-by: Santosh Shilimkar Signed-off-by: Tony Lindgren --- include/linux/platform_data/pm33xx.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/pm33xx.h b/include/linux/platform_data/pm33xx.h index 644af1d89cfa..7037ba7a53ca 100644 --- a/include/linux/platform_data/pm33xx.h +++ b/include/linux/platform_data/pm33xx.h @@ -54,11 +54,8 @@ struct am33xx_pm_platform_data { void (*begin_suspend)(void); void (*finish_suspend)(void); struct am33xx_pm_sram_addr *(*get_sram_addrs)(void); - void __iomem *(*get_rtc_base_addr)(void); void (*save_context)(void); void (*restore_context)(void); - void (*prepare_rtc_suspend)(void); - void (*prepare_rtc_resume)(void); int (*check_off_mode_enable)(void); }; -- cgit v1.2.3 From ebb21aa1882f418b436ee23463683790c553a447 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 11 Aug 2020 17:46:58 +1000 Subject: drm/ttm: drop bus.size from bus placement. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is always calculated the same, and only used in a couple of places. Signed-off-by: Dave Airlie Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20200811074658.58309-2-airlied@gmail.com --- include/drm/ttm/ttm_resource.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index bac22a56f6cd..6d4226190480 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -162,7 +162,6 @@ struct ttm_resource_manager { * @addr: mapped virtual address * @base: bus base address * @is_iomem: is this io memory ? - * @size: size in byte * @offset: offset from the base address * @io_reserved_vm: The VM system has a refcount in @io_reserved_count * @io_reserved_count: Refcounting the numbers of callers to ttm_mem_io_reserve @@ -172,7 +171,6 @@ struct ttm_resource_manager { struct ttm_bus_placement { void *addr; phys_addr_t base; - unsigned long size; unsigned long offset; bool is_iomem; bool io_reserved_vm; -- cgit v1.2.3 From dde6f18a8779dcd88d9fd5d6336032fee7e07fcd Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Fri, 3 Apr 2020 17:38:37 +0200 Subject: ocxl: Don't return trigger page when allocating an interrupt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Existing users of ocxl_link_irq_alloc() have been converted to obtain the trigger page of an interrupt through xive directly, we therefore have no need to return the trigger page when allocating an interrupt. It also allows ocxl to use the xive native interface to allocate interrupts, instead of its custom service. Signed-off-by: Frederic Barrat Reviewed-by: Cédric Le Goater Reviewed-by: Greg Kurz Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200403153838.29224-4-fbarrat@linux.ibm.com --- include/misc/ocxl.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h index 357ef1aadbc0..e013736e275d 100644 --- a/include/misc/ocxl.h +++ b/include/misc/ocxl.h @@ -460,14 +460,8 @@ int ocxl_link_remove_pe(void *link_handle, int pasid); * Allocate an AFU interrupt associated to the link. * * 'hw_irq' is the hardware interrupt number - * 'obj_handle' is the 64-bit object handle to be passed to the AFU to - * trigger the interrupt. - * On P9, 'obj_handle' is an address, which, if written, triggers the - * interrupt. It is an MMIO address which needs to be remapped (one - * page). - */ -int ocxl_link_irq_alloc(void *link_handle, int *hw_irq, - u64 *obj_handle); + */ +int ocxl_link_irq_alloc(void *link_handle, int *hw_irq); /* * Free a previously allocated AFU interrupt -- cgit v1.2.3 From b3d03daa7cd19a91266dc2cea3587dcf60e7a1f0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 17 Aug 2020 09:53:11 -0400 Subject: RDMA/core: Move the rdma_show_ib_cm_event() macro Refactor: Make it globally available in the utilities header. Link: https://lore.kernel.org/r/159767239131.2968.9520990257041764685.stgit@klimt.1015granger.net Signed-off-by: Chuck Lever Signed-off-by: Jason Gunthorpe --- include/trace/events/rdma.h | 41 ++++++++++++++++++++++++++++++++++++++++- include/trace/events/rpcrdma.h | 1 + 2 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rdma.h b/include/trace/events/rdma.h index aa19afc73a4e..81bb454fc288 100644 --- a/include/trace/events/rdma.h +++ b/include/trace/events/rdma.h @@ -6,7 +6,6 @@ /* * enum ib_event_type, from include/rdma/ib_verbs.h */ - #define IB_EVENT_LIST \ ib_event(CQ_ERR) \ ib_event(QP_FATAL) \ @@ -90,6 +89,46 @@ IB_WC_STATUS_LIST #define rdma_show_wc_status(x) \ __print_symbolic(x, IB_WC_STATUS_LIST) +/* + * enum ib_cm_event_type, from include/rdma/ib_cm.h + */ +#define IB_CM_EVENT_LIST \ + ib_cm_event(REQ_ERROR) \ + ib_cm_event(REQ_RECEIVED) \ + ib_cm_event(REP_ERROR) \ + ib_cm_event(REP_RECEIVED) \ + ib_cm_event(RTU_RECEIVED) \ + ib_cm_event(USER_ESTABLISHED) \ + ib_cm_event(DREQ_ERROR) \ + ib_cm_event(DREQ_RECEIVED) \ + ib_cm_event(DREP_RECEIVED) \ + ib_cm_event(TIMEWAIT_EXIT) \ + ib_cm_event(MRA_RECEIVED) \ + ib_cm_event(REJ_RECEIVED) \ + ib_cm_event(LAP_ERROR) \ + ib_cm_event(LAP_RECEIVED) \ + ib_cm_event(APR_RECEIVED) \ + ib_cm_event(SIDR_REQ_ERROR) \ + ib_cm_event(SIDR_REQ_RECEIVED) \ + ib_cm_event_end(SIDR_REP_RECEIVED) + +#undef ib_cm_event +#undef ib_cm_event_end + +#define ib_cm_event(x) TRACE_DEFINE_ENUM(IB_CM_##x); +#define ib_cm_event_end(x) TRACE_DEFINE_ENUM(IB_CM_##x); + +IB_CM_EVENT_LIST + +#undef ib_cm_event +#undef ib_cm_event_end + +#define ib_cm_event(x) { IB_CM_##x, #x }, +#define ib_cm_event_end(x) { IB_CM_##x, #x } + +#define rdma_show_ib_cm_event(x) \ + __print_symbolic(x, IB_CM_EVENT_LIST) + /* * enum rdma_cm_event_type, from include/rdma/rdma_cm.h */ diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index abe942225637..b6aad52beb62 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -13,6 +13,7 @@ #include #include #include +#include #include /** -- cgit v1.2.3 From 70a217f1976f75a6cfe8223e5669ad7b405daaad Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:14 -0700 Subject: tcp: Use a struct to represent a saved_syn The TCP_SAVE_SYN has both the network header and tcp header. The total length of the saved syn packet is currently stored in the first 4 bytes (u32) of an array and the actual packet data is stored after that. A later patch will add a bpf helper that allows to get the tcp header alone from the saved syn without the network header. It will be more convenient to have a direct offset to a specific header instead of re-parsing it. This requires to separately store the network hdrlen. The total header length (i.e. network + tcp) is still needed for the current usage in getsockopt. Although this total length can be obtained by looking into the tcphdr and then get the (th->doff << 2), this patch chooses to directly store the tcp hdrlen in the second four bytes of this newly created "struct saved_syn". By using a new struct, it can give a readable name to each individual header length. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190014.2883694-1-kafai@fb.com --- include/linux/tcp.h | 7 ++++++- include/net/request_sock.h | 8 +++++++- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 14b62d7df942..2088d5a079af 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -406,7 +406,7 @@ struct tcp_sock { * socket. Used to retransmit SYNACKs etc. */ struct request_sock __rcu *fastopen_rsk; - u32 *saved_syn; + struct saved_syn *saved_syn; }; enum tsq_enum { @@ -484,6 +484,11 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } +static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) +{ + return saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; +} + struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b2eb8b4ba697..7d9ed99a77bd 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -41,6 +41,12 @@ struct request_sock_ops { int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); +struct saved_syn { + u32 network_hdrlen; + u32 tcp_hdrlen; + u8 data[]; +}; + /* struct request_sock - mini sock to represent a connection request */ struct request_sock { @@ -60,7 +66,7 @@ struct request_sock { struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; - u32 *saved_syn; + struct saved_syn *saved_syn; u32 secid; u32 peer_secid; }; -- cgit v1.2.3 From 2b8ee4f05d4f6a6c427ad30dd6c1bb49eb2efd3b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:21 -0700 Subject: tcp: bpf: Add TCP_BPF_DELACK_MAX setsockopt This change is mostly from an internal patch and adapts it from sysctl config to the bpf_setsockopt setup. The bpf_prog can set the max delay ack by using bpf_setsockopt(TCP_BPF_DELACK_MAX). This max delay ack can be communicated to its peer through bpf header option. The receiving peer can then use this max delay ack and set a potentially lower rto by using bpf_setsockopt(TCP_BPF_RTO_MIN) which will be introduced in the next patch. Another later selftest patch will also use it like the above to show how to write and parse bpf tcp header option. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190021.2884000-1-kafai@fb.com --- include/net/inet_connection_sock.h | 1 + include/uapi/linux/bpf.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index aa8893c68c50..da7264a1ebfc 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,7 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a1bbaff7a0af..7b905cb0213e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4257,6 +4257,7 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ }; struct bpf_perf_event_value { -- cgit v1.2.3 From ca584ba070864c606f3a54faaafe774726d5b4a1 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:27 -0700 Subject: tcp: bpf: Add TCP_BPF_RTO_MIN for bpf_setsockopt This patch adds bpf_setsockopt(TCP_BPF_RTO_MIN) to allow bpf prog to set the min rto of a connection. It could be used together with the earlier patch which has added bpf_setsockopt(TCP_BPF_DELACK_MAX). A later selftest patch will communicate the max delay ack in a bpf tcp header option and then the receiving side can use bpf_setsockopt(TCP_BPF_RTO_MIN) to set a shorter rto. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190027.2884170-1-kafai@fb.com --- include/net/inet_connection_sock.h | 1 + include/net/tcp.h | 2 +- include/uapi/linux/bpf.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index da7264a1ebfc..c738abeb3265 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,7 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_rto_min; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; diff --git a/include/net/tcp.h b/include/net/tcp.h index eab6c7510b5b..dda778c782fe 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -699,7 +699,7 @@ static inline void tcp_fast_path_check(struct sock *sk) static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = TCP_RTO_MIN; + u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7b905cb0213e..1ae20058b574 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4258,6 +4258,7 @@ enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ }; struct bpf_perf_event_value { -- cgit v1.2.3 From 7656d68455891f7fc6689f95415fd59e7a1d629b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:33 -0700 Subject: tcp: Add saw_unknown to struct tcp_options_received In a later patch, the bpf prog only wants to be called to handle a header option if that particular header option cannot be handled by the kernel. This unknown option could be written by the peer's bpf-prog. It could also be a new standard option that the running kernel does not support it while a bpf-prog can handle it. This patch adds a "saw_unknown" bit to "struct tcp_options_received" and it uses an existing one byte hole to do that. "saw_unknown" will be set in tcp_parse_options() if it sees an option that the kernel cannot handle. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190033.2884430-1-kafai@fb.com --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2088d5a079af..29d166263ae7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -92,6 +92,8 @@ struct tcp_options_received { smc_ok : 1, /* SMC seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ + u8 saw_unknown:1, /* Received unknown option */ + unused:7; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ -- cgit v1.2.3 From 72be0fe6ba76282704cb84952bd5a1eb47910290 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:39 -0700 Subject: bpf: tcp: Add bpf_skops_established() In tcp_init_transfer(), it currently calls the bpf prog to give it a chance to handle the just "ESTABLISHED" event (e.g. do setsockopt on the newly established sk). Right now, it is done by calling the general purpose tcp_call_bpf(). In the later patch, it also needs to pass the just-received skb which concludes the 3 way handshake. E.g. the SYNACK received at the active side. The bpf prog can then learn some specific header options written by the peer's bpf-prog and potentially do setsockopt on the newly established sk. Thus, instead of reusing the general purpose tcp_call_bpf(), a new function bpf_skops_established() is added to allow passing the "skb" to the bpf prog. The actual skb passing from bpf_skops_established() to the bpf prog will happen together in a later patch which has the necessary bpf pieces. A "skb" arg is also added to tcp_init_transfer() such that it can then be passed to bpf_skops_established(). Calling the new bpf_skops_established() instead of tcp_call_bpf() should be a noop in this patch. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200820190039.2884750-1-kafai@fb.com --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index dda778c782fe..c186dbf731e1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -394,7 +394,7 @@ void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); -void tcp_init_transfer(struct sock *sk, int bpf_op); +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, -- cgit v1.2.3 From 00d211a4ea6f48e8e3b758813fe23ad28193d3bf Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:46 -0700 Subject: bpf: tcp: Add bpf_skops_parse_hdr() The patch adds a function bpf_skops_parse_hdr(). It will call the bpf prog to parse the TCP header received at a tcp_sock that has at least reached the ESTABLISHED state. For the packets received during the 3WHS (SYN, SYNACK and ACK), the received skb will be available to the bpf prog during the callback in bpf_skops_established() introduced in the previous patch and in the bpf_skops_write_hdr_opt() that will be added in the next patch. Calling bpf prog to parse header is controlled by two new flags in tp->bpf_sock_ops_cb_flags: BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG and BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG. When BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG is set, the bpf prog will only be called when there is unknown option in the TCP header. When BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG is set, the bpf prog will be called on all received TCP header. This function is half implemented to highlight the changes in TCP stack. The actual codes preparing the bpf running context and invoking the bpf prog will be added in the later patch with other necessary bpf pieces. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/bpf/20200820190046.2885054-1-kafai@fb.com --- include/uapi/linux/bpf.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1ae20058b574..010ed2abcb66 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4173,8 +4173,10 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), /* Mask of all currently supported cb flags */ - BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF, + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x3F, }; /* List of known BPF sock_ops operators. -- cgit v1.2.3 From 331fca4315efa3bbd258fbdf8209d59d253c0480 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:52 -0700 Subject: bpf: tcp: Add bpf_skops_hdr_opt_len() and bpf_skops_write_hdr_opt() The bpf prog needs to parse the SYN header to learn what options have been sent by the peer's bpf-prog before writing its options into SYNACK. This patch adds a "syn_skb" arg to tcp_make_synack() and send_synack(). This syn_skb will eventually be made available (as read-only) to the bpf prog. This will be the only SYN packet available to the bpf prog during syncookie. For other regular cases, the bpf prog can also use the saved_syn. When writing options, the bpf prog will first be called to tell the kernel its required number of bytes. It is done by the new bpf_skops_hdr_opt_len(). The bpf prog will only be called when the new BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG is set in tp->bpf_sock_ops_cb_flags. When the bpf prog returns, the kernel will know how many bytes are needed and then update the "*remaining" arg accordingly. 4 byte alignment will be included in the "*remaining" before this function returns. The 4 byte aligned number of bytes will also be stored into the opts->bpf_opt_len. "bpf_opt_len" is a newly added member to the struct tcp_out_options. Then the new bpf_skops_write_hdr_opt() will call the bpf prog to write the header options. The bpf prog is only called if it has reserved spaces before (opts->bpf_opt_len > 0). The bpf prog is the last one getting a chance to reserve header space and writing the header option. These two functions are half implemented to highlight the changes in TCP stack. The actual codes preparing the bpf running context and invoking the bpf prog will be added in the later patch with other necessary bpf pieces. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/bpf/20200820190052.2885316-1-kafai@fb.com --- include/net/tcp.h | 6 ++++-- include/uapi/linux/bpf.h | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index c186dbf731e1..3e768a6b8264 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -455,7 +455,8 @@ enum tcp_synack_type { struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -2035,7 +2036,8 @@ struct tcp_request_sock_ops { int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 010ed2abcb66..18d0e128bc3c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4175,8 +4175,9 @@ enum { BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ - BPF_SOCK_OPS_ALL_CB_FLAGS = 0x3F, + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; /* List of known BPF sock_ops operators. -- cgit v1.2.3 From c9985d09e18965131958102f4b67fa1e742df335 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:00:58 -0700 Subject: bpf: sock_ops: Change some members of sock_ops_kern from u32 to u8 A later patch needs to add a few pointers and a few u8 to sock_ops_kern. Hence, this patch saves some spaces by moving some of the existing members from u32 to u8 so that the later patch can still fit everything in a cacheline. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200820190058.2885640-1-kafai@fb.com --- include/linux/filter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 0a355b005bf4..c427dfa5f908 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1236,13 +1236,13 @@ struct bpf_sock_addr_kern { struct bpf_sock_ops_kern { struct sock *sk; - u32 op; union { u32 args[4]; u32 reply; u32 replylong[4]; }; - u32 is_fullsock; + u8 op; + u8 is_fullsock; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that -- cgit v1.2.3 From 0813a841566f0962a5551be7749b43c45f0022a0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:01:04 -0700 Subject: bpf: tcp: Allow bpf prog to write and parse TCP header option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Note: The TCP changes here is mainly to implement the bpf pieces into the bpf_skops_*() functions introduced in the earlier patches. ] The earlier effort in BPF-TCP-CC allows the TCP Congestion Control algorithm to be written in BPF. It opens up opportunities to allow a faster turnaround time in testing/releasing new congestion control ideas to production environment. The same flexibility can be extended to writing TCP header option. It is not uncommon that people want to test new TCP header option to improve the TCP performance. Another use case is for data-center that has a more controlled environment and has more flexibility in putting header options for internal only use. For example, we want to test the idea in putting maximum delay ACK in TCP header option which is similar to a draft RFC proposal [1]. This patch introduces the necessary BPF API and use them in the TCP stack to allow BPF_PROG_TYPE_SOCK_OPS program to parse and write TCP header options. It currently supports most of the TCP packet except RST. Supported TCP header option: ─────────────────────────── This patch allows the bpf-prog to write any option kind. Different bpf-progs can write its own option by calling the new helper bpf_store_hdr_opt(). The helper will ensure there is no duplicated option in the header. By allowing bpf-prog to write any option kind, this gives a lot of flexibility to the bpf-prog. Different bpf-prog can write its own option kind. It could also allow the bpf-prog to support a recently standardized option on an older kernel. Sockops Callback Flags: ────────────────────── The bpf program will only be called to parse/write tcp header option if the following newly added callback flags are enabled in tp->bpf_sock_ops_cb_flags: BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG A few words on the PARSE CB flags. When the above PARSE CB flags are turned on, the bpf-prog will be called on packets received at a sk that has at least reached the ESTABLISHED state. The parsing of the SYN-SYNACK-ACK will be discussed in the "3 Way HandShake" section. The default is off for all of the above new CB flags, i.e. the bpf prog will not be called to parse or write bpf hdr option. There are details comment on these new cb flags in the UAPI bpf.h. sock_ops->skb_data and bpf_load_hdr_opt() ───────────────────────────────────────── sock_ops->skb_data and sock_ops->skb_data_end covers the whole TCP header and its options. They are read only. The new bpf_load_hdr_opt() helps to read a particular option "kind" from the skb_data. Please refer to the comment in UAPI bpf.h. It has details on what skb_data contains under different sock_ops->op. 3 Way HandShake ─────────────── The bpf-prog can learn if it is sending SYN or SYNACK by reading the sock_ops->skb_tcp_flags. * Passive side When writing SYNACK (i.e. sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB), the received SYN skb will be available to the bpf prog. The bpf prog can use the SYN skb (which may carry the header option sent from the remote bpf prog) to decide what bpf header option should be written to the outgoing SYNACK skb. The SYN packet can be obtained by getsockopt(TCP_BPF_SYN*). More on this later. Also, the bpf prog can learn if it is in syncookie mode (by checking sock_ops->args[0] == BPF_WRITE_HDR_TCP_SYNACK_COOKIE). The bpf prog can store the received SYN pkt by using the existing bpf_setsockopt(TCP_SAVE_SYN). The example in a later patch does it. [ Note that the fullsock here is a listen sk, bpf_sk_storage is not very useful here since the listen sk will be shared by many concurrent connection requests. Extending bpf_sk_storage support to request_sock will add weight to the minisock and it is not necessary better than storing the whole ~100 bytes SYN pkt. ] When the connection is established, the bpf prog will be called in the existing PASSIVE_ESTABLISHED_CB callback. At that time, the bpf prog can get the header option from the saved syn and then apply the needed operation to the newly established socket. The later patch will use the max delay ack specified in the SYN header and set the RTO of this newly established connection as an example. The received ACK (that concludes the 3WHS) will also be available to the bpf prog during PASSIVE_ESTABLISHED_CB through the sock_ops->skb_data. It could be useful in syncookie scenario. More on this later. There is an existing getsockopt "TCP_SAVED_SYN" to return the whole saved syn pkt which includes the IP[46] header and the TCP header. A few "TCP_BPF_SYN*" getsockopt has been added to allow specifying where to start getting from, e.g. starting from TCP header, or from IP[46] header. The new getsockopt(TCP_BPF_SYN*) will also know where it can get the SYN's packet from: - (a) the just received syn (available when the bpf prog is writing SYNACK) and it is the only way to get SYN during syncookie mode. or - (b) the saved syn (available in PASSIVE_ESTABLISHED_CB and also other existing CB). The bpf prog does not need to know where the SYN pkt is coming from. The getsockopt(TCP_BPF_SYN*) will hide this details. Similarly, a flags "BPF_LOAD_HDR_OPT_TCP_SYN" is also added to bpf_load_hdr_opt() to read a particular header option from the SYN packet. * Fastopen Fastopen should work the same as the regular non fastopen case. This is a test in a later patch. * Syncookie For syncookie, the later example patch asks the active side's bpf prog to resend the header options in ACK. The server can use bpf_load_hdr_opt() to look at the options in this received ACK during PASSIVE_ESTABLISHED_CB. * Active side The bpf prog will get a chance to write the bpf header option in the SYN packet during WRITE_HDR_OPT_CB. The received SYNACK pkt will also be available to the bpf prog during the existing ACTIVE_ESTABLISHED_CB callback through the sock_ops->skb_data and bpf_load_hdr_opt(). * Turn off header CB flags after 3WHS If the bpf prog does not need to write/parse header options beyond the 3WHS, the bpf prog can clear the bpf_sock_ops_cb_flags to avoid being called for header options. Or the bpf-prog can select to leave the UNKNOWN_HDR_OPT_CB_FLAG on so that the kernel will only call it when there is option that the kernel cannot handle. [1]: draft-wang-tcpm-low-latency-opt-00 https://tools.ietf.org/html/draft-wang-tcpm-low-latency-opt-00 Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200820190104.2885895-1-kafai@fb.com --- include/linux/bpf-cgroup.h | 25 ++++ include/linux/filter.h | 4 + include/net/tcp.h | 49 ++++++++ include/uapi/linux/bpf.h | 300 ++++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 377 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 64f367044e25..2f98d2fce62e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -279,6 +279,31 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL) +/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a + * fullsock and its parent fullsock cannot be traced by + * sk_to_full_sk(). + * + * e.g. sock_ops->sk is a request_sock and it is under syncookie mode. + * Its listener-sk is not attached to the rsk_listener. + * In this case, the caller holds the listener-sk (unlocked), + * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with + * the listener-sk such that the cgroup-bpf-progs of the + * listener-sk will be run. + * + * Regardless of syncookie mode or not, + * calling bpf_setsockopt on listener-sk will not make sense anyway, + * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. + */ +#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + __ret; \ +}) + #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ diff --git a/include/linux/filter.h b/include/linux/filter.h index c427dfa5f908..995625950cc1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1241,8 +1241,12 @@ struct bpf_sock_ops_kern { u32 reply; u32 replylong[4]; }; + struct sk_buff *syn_skb; + struct sk_buff *skb; + void *skb_data_end; u8 op; u8 is_fullsock; + u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that diff --git a/include/net/tcp.h b/include/net/tcp.h index 3e768a6b8264..1f967b4e22f6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2235,6 +2235,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#ifdef CONFIG_CGROUP_BPF +/* Copy the listen sk's HDR_OPT_CB flags to its child. + * + * During 3-Way-HandShake, the synack is usually sent from + * the listen sk with the HDR_OPT_CB flags set so that + * bpf-prog will be called to write the BPF hdr option. + * + * In fastopen, the child sk is used to send synack instead + * of the listen sk. Thus, inheriting the HDR_OPT_CB flags + * from the listen sk gives the bpf-prog a chance to write + * BPF hdr option in the synack pkt during fastopen. + * + * Both fastopen and non-fastopen child will inherit the + * HDR_OPT_CB flags to keep the bpf-prog having a consistent + * behavior when deciding to clear this cb flags (or not) + * during the PASSIVE_ESTABLISHED_CB. + * + * In the future, other cb flags could be inherited here also. + */ +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ + tcp_sk(child)->bpf_sock_ops_cb_flags = + tcp_sk(sk)->bpf_sock_ops_cb_flags & + (BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ + skops->skb = skb; + skops->skb_data_end = skb->data + end_offset; +} +#else +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ +} +#endif + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 18d0e128bc3c..f67ec5d9e57d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3395,6 +3395,120 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (BPF_PROG_TYPE_SOCK_OPS). + * + * If *flags* is 0, it will search the option from the + * sock_ops->skb_data. The comment in "struct bpf_sock_ops" + * has details on what skb_data contains under different + * sock_ops->op. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the searchby_res should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * >0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. + * + * **-EINVAL** If param is invalid + * + * **-ENOMSG** The option is not found + * + * **-ENOENT** No syn packet available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used + * + * **-ENOSPC** Not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** Cannot parse the header options in the packet + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid + * + * **-ENOSPC** Not enough space in the header. + * Nothing has been written + * + * **-EEXIST** The option has already existed + * + * **-EFAULT** Cannot parse the existing header options + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by bpf_store_hdr_opt() later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * If bpf_reserve_hdr_opt() is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * BPF_SOCK_OPS_HDR_OPT_LEN_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if param is invalid + * + * **-ENOSPC** Not enough space in the header. + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3539,6 +3653,9 @@ union bpf_attr { FN(skc_to_tcp_request_sock), \ FN(skc_to_udp6_sock), \ FN(get_task_stack), \ + FN(load_hdr_opt), \ + FN(store_hdr_opt), \ + FN(reserve_hdr_opt), /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4165,6 +4282,36 @@ struct bpf_sock_ops { __u64 bytes_received; __u64 bytes_acked; __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4173,8 +4320,48 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), - BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, @@ -4233,6 +4420,63 @@ enum { */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -4262,6 +4506,60 @@ enum { TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ }; struct bpf_perf_event_value { -- cgit v1.2.3 From 267cf9fa43d1c9d525d5d818a8651f2900e3aa9e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 20 Aug 2020 12:01:23 -0700 Subject: tcp: bpf: Optionally store mac header in TCP_SAVE_SYN This patch is adapted from Eric's patch in an earlier discussion [1]. The TCP_SAVE_SYN currently only stores the network header and tcp header. This patch allows it to optionally store the mac header also if the setsockopt's optval is 2. It requires one more bit for the "save_syn" bit field in tcp_sock. This patch achieves this by moving the syn_smc bit next to the is_mptcp. The syn_smc is currently used with the TCP experimental option. Since syn_smc is only used when CONFIG_SMC is enabled, this patch also puts the "IS_ENABLED(CONFIG_SMC)" around it like the is_mptcp did with "IS_ENABLED(CONFIG_MPTCP)". The mac_hdrlen is also stored in the "struct saved_syn" to allow a quick offset from the bpf prog if it chooses to start getting from the network header or the tcp header. [1]: https://lore.kernel.org/netdev/CANn89iLJNWh6bkH7DNhy_kmcAexuUCccqERqe7z2QsvPhGrYPQ@mail.gmail.com/ Suggested-by: Eric Dumazet Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/bpf/20200820190123.2886935-1-kafai@fb.com --- include/linux/tcp.h | 13 ++++++++----- include/net/request_sock.h | 1 + include/uapi/linux/bpf.h | 1 + 3 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 29d166263ae7..56ff2952edaf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -239,14 +239,13 @@ struct tcp_sock { repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; - u8 syn_data:1, /* SYN includes data */ + u8 save_syn:2, /* Save headers of SYN packet */ + syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ - save_syn:1, /* Save headers of SYN packet */ - is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ - syn_smc:1; /* SYN includes SMC */ + is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ @@ -393,6 +392,9 @@ struct tcp_sock { #if IS_ENABLED(CONFIG_MPTCP) bool is_mptcp; #endif +#if IS_ENABLED(CONFIG_SMC) + bool syn_smc; /* SYN includes SMC */ +#endif #ifdef CONFIG_TCP_MD5SIG /* TCP AF-Specific parts; only used by MD5 Signature support so far */ @@ -488,7 +490,8 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) { - return saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; + return saved_syn->mac_hdrlen + saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 7d9ed99a77bd..29e41ff3ec93 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -42,6 +42,7 @@ struct request_sock_ops { int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); struct saved_syn { + u32 mac_hdrlen; u32 network_hdrlen; u32 tcp_hdrlen; u8 data[]; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f67ec5d9e57d..544b89a64918 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4540,6 +4540,7 @@ enum { */ TCP_BPF_SYN = 1005, /* Copy the TCP header */ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ + TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ }; enum { -- cgit v1.2.3 From 14e2ac8de0f91f12122a49f09897b0cd05256460 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 24 Jul 2020 09:00:01 +0200 Subject: kcsan: Support compounded read-write instrumentation Add support for compounded read-write instrumentation if supported by the compiler. Adds the necessary instrumentation functions, and a new type which is used to generate a more descriptive report. Furthermore, such compounded memory access instrumentation is excluded from the "assume aligned writes up to word size are atomic" rule, because we cannot assume that the compiler emits code that is atomic for compound ops. LLVM/Clang added support for the feature in: https://github.com/llvm/llvm-project/commit/785d41a261d136b64ab6c15c5d35f2adc5ad53e3 The new instrumentation is emitted for sets of memory accesses in the same basic block to the same address with at least one read appearing before a write. These typically result from compound operations such as ++, --, +=, -=, |=, &=, etc. but also equivalent forms such as "var = var + 1". Where the compiler determines that it is equivalent to emit a call to a single __tsan_read_write instead of separate __tsan_read and __tsan_write, we can then benefit from improved performance and better reporting for such access patterns. The new reports now show that the ops are both reads and writes, for example: read-write to 0xffffffff90548a38 of 8 bytes by task 143 on cpu 3: test_kernel_rmw_array+0x45/0xa0 access_thread+0x71/0xb0 kthread+0x21e/0x240 ret_from_fork+0x22/0x30 read-write to 0xffffffff90548a38 of 8 bytes by task 144 on cpu 2: test_kernel_rmw_array+0x45/0xa0 access_thread+0x71/0xb0 kthread+0x21e/0x240 ret_from_fork+0x22/0x30 Acked-by: Peter Zijlstra (Intel) Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 45 +++++++++++++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index c5f6c1dcf7e3..cf14840609ce 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -7,19 +7,13 @@ #include #include -/* - * ACCESS TYPE MODIFIERS - * - * : normal read access; - * WRITE : write access; - * ATOMIC: access is atomic; - * ASSERT: access is not a regular access, but an assertion; - * SCOPED: access is a scoped access; - */ -#define KCSAN_ACCESS_WRITE 0x1 -#define KCSAN_ACCESS_ATOMIC 0x2 -#define KCSAN_ACCESS_ASSERT 0x4 -#define KCSAN_ACCESS_SCOPED 0x8 +/* Access types -- if KCSAN_ACCESS_WRITE is not set, the access is a read. */ +#define KCSAN_ACCESS_WRITE (1 << 0) /* Access is a write. */ +#define KCSAN_ACCESS_COMPOUND (1 << 1) /* Compounded read-write instrumentation. */ +#define KCSAN_ACCESS_ATOMIC (1 << 2) /* Access is atomic. */ +/* The following are special, and never due to compiler instrumentation. */ +#define KCSAN_ACCESS_ASSERT (1 << 3) /* Access is an assertion. */ +#define KCSAN_ACCESS_SCOPED (1 << 4) /* Access is a scoped access. */ /* * __kcsan_*: Always calls into the runtime when KCSAN is enabled. This may be used @@ -204,6 +198,15 @@ static inline void __kcsan_disable_current(void) { } #define __kcsan_check_write(ptr, size) \ __kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) +/** + * __kcsan_check_read_write - check regular read-write access for races + * + * @ptr: address of access + * @size: size of access + */ +#define __kcsan_check_read_write(ptr, size) \ + __kcsan_check_access(ptr, size, KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE) + /** * kcsan_check_read - check regular read access for races * @@ -221,18 +224,30 @@ static inline void __kcsan_disable_current(void) { } #define kcsan_check_write(ptr, size) \ kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) +/** + * kcsan_check_read_write - check regular read-write access for races + * + * @ptr: address of access + * @size: size of access + */ +#define kcsan_check_read_write(ptr, size) \ + kcsan_check_access(ptr, size, KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE) + /* * Check for atomic accesses: if atomic accesses are not ignored, this simply * aliases to kcsan_check_access(), otherwise becomes a no-op. */ #ifdef CONFIG_KCSAN_IGNORE_ATOMICS -#define kcsan_check_atomic_read(...) do { } while (0) -#define kcsan_check_atomic_write(...) do { } while (0) +#define kcsan_check_atomic_read(...) do { } while (0) +#define kcsan_check_atomic_write(...) do { } while (0) +#define kcsan_check_atomic_read_write(...) do { } while (0) #else #define kcsan_check_atomic_read(ptr, size) \ kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC) #define kcsan_check_atomic_write(ptr, size) \ kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE) +#define kcsan_check_atomic_read_write(ptr, size) \ + kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND) #endif /** -- cgit v1.2.3 From 00047c2e6d7c576c1a847f7db07ef0fc58085f22 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 24 Jul 2020 09:00:06 +0200 Subject: instrumented.h: Introduce read-write instrumentation hooks Introduce read-write instrumentation hooks, to more precisely denote an operation's behaviour. KCSAN is able to distinguish compound instrumentation, and with the new instrumentation we then benefit from improved reporting. More importantly, read-write compound operations should not implicitly be treated as atomic, if they aren't actually atomic. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/instrumented.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 43e6ea591975..42faebbaa202 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -42,6 +42,21 @@ static __always_inline void instrument_write(const volatile void *v, size_t size kcsan_check_write(v, size); } +/** + * instrument_read_write - instrument regular read-write access + * + * Instrument a regular write access. The instrumentation should be inserted + * before the actual write happens. + * + * @ptr address of access + * @size size of access + */ +static __always_inline void instrument_read_write(const volatile void *v, size_t size) +{ + kasan_check_write(v, size); + kcsan_check_read_write(v, size); +} + /** * instrument_atomic_read - instrument atomic read access * @@ -72,6 +87,21 @@ static __always_inline void instrument_atomic_write(const volatile void *v, size kcsan_check_atomic_write(v, size); } +/** + * instrument_atomic_read_write - instrument atomic read-write access + * + * Instrument an atomic read-write access. The instrumentation should be + * inserted before the actual write happens. + * + * @ptr address of access + * @size size of access + */ +static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) +{ + kasan_check_write(v, size); + kcsan_check_atomic_read_write(v, size); +} + /** * instrument_copy_to_user - instrument reads of copy_to_user * -- cgit v1.2.3 From b159eeccb75a7916278d95e2ff5540e670682748 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 24 Jul 2020 09:00:07 +0200 Subject: asm-generic/bitops: Use instrument_read_write() where appropriate Use the new instrument_read_write() where appropriate. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/asm-generic/bitops/instrumented-atomic.h | 6 +++--- include/asm-generic/bitops/instrumented-lock.h | 2 +- include/asm-generic/bitops/instrumented-non-atomic.h | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h index fb2cb33a4013..81915dcd4b4e 100644 --- a/include/asm-generic/bitops/instrumented-atomic.h +++ b/include/asm-generic/bitops/instrumented-atomic.h @@ -67,7 +67,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr) */ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { - instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); + instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit(nr, addr); } @@ -80,7 +80,7 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) */ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { - instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); + instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_clear_bit(nr, addr); } @@ -93,7 +93,7 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) */ static inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { - instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); + instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_change_bit(nr, addr); } diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h index b9bec468ae03..75ef606f7145 100644 --- a/include/asm-generic/bitops/instrumented-lock.h +++ b/include/asm-generic/bitops/instrumented-lock.h @@ -52,7 +52,7 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) */ static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr) { - instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); + instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit_lock(nr, addr); } diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 20f788a25ef9..f86234c7c10c 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -68,7 +68,7 @@ static inline void __change_bit(long nr, volatile unsigned long *addr) */ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) { - instrument_write(addr + BIT_WORD(nr), sizeof(long)); + instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch___test_and_set_bit(nr, addr); } @@ -82,7 +82,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) */ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) { - instrument_write(addr + BIT_WORD(nr), sizeof(long)); + instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch___test_and_clear_bit(nr, addr); } @@ -96,7 +96,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) */ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) { - instrument_write(addr + BIT_WORD(nr), sizeof(long)); + instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch___test_and_change_bit(nr, addr); } -- cgit v1.2.3 From 3570a1bcf45e9a7ddf9ba0e8d6d57cc67675cfef Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 24 Jul 2020 09:00:08 +0200 Subject: locking/atomics: Use read-write instrumentation for atomic RMWs Use instrument_atomic_read_write() for atomic RMW ops. Cc: Will Deacon Cc: Boqun Feng Cc: Arnd Bergmann Cc: Acked-by: Peter Zijlstra (Intel) Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/asm-generic/atomic-instrumented.h | 330 +++++++++++++++--------------- 1 file changed, 165 insertions(+), 165 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 379986e40159..cd223b68b69d 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -60,7 +60,7 @@ atomic_set_release(atomic_t *v, int i) static __always_inline void atomic_add(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_add(i, v); } #define atomic_add atomic_add @@ -69,7 +69,7 @@ atomic_add(int i, atomic_t *v) static __always_inline int atomic_add_return(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return(i, v); } #define atomic_add_return atomic_add_return @@ -79,7 +79,7 @@ atomic_add_return(int i, atomic_t *v) static __always_inline int atomic_add_return_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return_acquire(i, v); } #define atomic_add_return_acquire atomic_add_return_acquire @@ -89,7 +89,7 @@ atomic_add_return_acquire(int i, atomic_t *v) static __always_inline int atomic_add_return_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return_release(i, v); } #define atomic_add_return_release atomic_add_return_release @@ -99,7 +99,7 @@ atomic_add_return_release(int i, atomic_t *v) static __always_inline int atomic_add_return_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return_relaxed(i, v); } #define atomic_add_return_relaxed atomic_add_return_relaxed @@ -109,7 +109,7 @@ atomic_add_return_relaxed(int i, atomic_t *v) static __always_inline int atomic_fetch_add(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add(i, v); } #define atomic_fetch_add atomic_fetch_add @@ -119,7 +119,7 @@ atomic_fetch_add(int i, atomic_t *v) static __always_inline int atomic_fetch_add_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_acquire(i, v); } #define atomic_fetch_add_acquire atomic_fetch_add_acquire @@ -129,7 +129,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_release(i, v); } #define atomic_fetch_add_release atomic_fetch_add_release @@ -139,7 +139,7 @@ atomic_fetch_add_release(int i, atomic_t *v) static __always_inline int atomic_fetch_add_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_relaxed(i, v); } #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed @@ -148,7 +148,7 @@ atomic_fetch_add_relaxed(int i, atomic_t *v) static __always_inline void atomic_sub(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_sub(i, v); } #define atomic_sub atomic_sub @@ -157,7 +157,7 @@ atomic_sub(int i, atomic_t *v) static __always_inline int atomic_sub_return(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return(i, v); } #define atomic_sub_return atomic_sub_return @@ -167,7 +167,7 @@ atomic_sub_return(int i, atomic_t *v) static __always_inline int atomic_sub_return_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return_acquire(i, v); } #define atomic_sub_return_acquire atomic_sub_return_acquire @@ -177,7 +177,7 @@ atomic_sub_return_acquire(int i, atomic_t *v) static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return_release(i, v); } #define atomic_sub_return_release atomic_sub_return_release @@ -187,7 +187,7 @@ atomic_sub_return_release(int i, atomic_t *v) static __always_inline int atomic_sub_return_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return_relaxed(i, v); } #define atomic_sub_return_relaxed atomic_sub_return_relaxed @@ -197,7 +197,7 @@ atomic_sub_return_relaxed(int i, atomic_t *v) static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub(i, v); } #define atomic_fetch_sub atomic_fetch_sub @@ -207,7 +207,7 @@ atomic_fetch_sub(int i, atomic_t *v) static __always_inline int atomic_fetch_sub_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub_acquire(i, v); } #define atomic_fetch_sub_acquire atomic_fetch_sub_acquire @@ -217,7 +217,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub_release(i, v); } #define atomic_fetch_sub_release atomic_fetch_sub_release @@ -227,7 +227,7 @@ atomic_fetch_sub_release(int i, atomic_t *v) static __always_inline int atomic_fetch_sub_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub_relaxed(i, v); } #define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed @@ -237,7 +237,7 @@ atomic_fetch_sub_relaxed(int i, atomic_t *v) static __always_inline void atomic_inc(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_inc(v); } #define atomic_inc atomic_inc @@ -247,7 +247,7 @@ atomic_inc(atomic_t *v) static __always_inline int atomic_inc_return(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return(v); } #define atomic_inc_return atomic_inc_return @@ -257,7 +257,7 @@ atomic_inc_return(atomic_t *v) static __always_inline int atomic_inc_return_acquire(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return_acquire(v); } #define atomic_inc_return_acquire atomic_inc_return_acquire @@ -267,7 +267,7 @@ atomic_inc_return_acquire(atomic_t *v) static __always_inline int atomic_inc_return_release(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return_release(v); } #define atomic_inc_return_release atomic_inc_return_release @@ -277,7 +277,7 @@ atomic_inc_return_release(atomic_t *v) static __always_inline int atomic_inc_return_relaxed(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return_relaxed(v); } #define atomic_inc_return_relaxed atomic_inc_return_relaxed @@ -287,7 +287,7 @@ atomic_inc_return_relaxed(atomic_t *v) static __always_inline int atomic_fetch_inc(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc(v); } #define atomic_fetch_inc atomic_fetch_inc @@ -297,7 +297,7 @@ atomic_fetch_inc(atomic_t *v) static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc_acquire(v); } #define atomic_fetch_inc_acquire atomic_fetch_inc_acquire @@ -307,7 +307,7 @@ atomic_fetch_inc_acquire(atomic_t *v) static __always_inline int atomic_fetch_inc_release(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc_release(v); } #define atomic_fetch_inc_release atomic_fetch_inc_release @@ -317,7 +317,7 @@ atomic_fetch_inc_release(atomic_t *v) static __always_inline int atomic_fetch_inc_relaxed(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc_relaxed(v); } #define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed @@ -327,7 +327,7 @@ atomic_fetch_inc_relaxed(atomic_t *v) static __always_inline void atomic_dec(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_dec(v); } #define atomic_dec atomic_dec @@ -337,7 +337,7 @@ atomic_dec(atomic_t *v) static __always_inline int atomic_dec_return(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return(v); } #define atomic_dec_return atomic_dec_return @@ -347,7 +347,7 @@ atomic_dec_return(atomic_t *v) static __always_inline int atomic_dec_return_acquire(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return_acquire(v); } #define atomic_dec_return_acquire atomic_dec_return_acquire @@ -357,7 +357,7 @@ atomic_dec_return_acquire(atomic_t *v) static __always_inline int atomic_dec_return_release(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return_release(v); } #define atomic_dec_return_release atomic_dec_return_release @@ -367,7 +367,7 @@ atomic_dec_return_release(atomic_t *v) static __always_inline int atomic_dec_return_relaxed(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return_relaxed(v); } #define atomic_dec_return_relaxed atomic_dec_return_relaxed @@ -377,7 +377,7 @@ atomic_dec_return_relaxed(atomic_t *v) static __always_inline int atomic_fetch_dec(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec(v); } #define atomic_fetch_dec atomic_fetch_dec @@ -387,7 +387,7 @@ atomic_fetch_dec(atomic_t *v) static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec_acquire(v); } #define atomic_fetch_dec_acquire atomic_fetch_dec_acquire @@ -397,7 +397,7 @@ atomic_fetch_dec_acquire(atomic_t *v) static __always_inline int atomic_fetch_dec_release(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec_release(v); } #define atomic_fetch_dec_release atomic_fetch_dec_release @@ -407,7 +407,7 @@ atomic_fetch_dec_release(atomic_t *v) static __always_inline int atomic_fetch_dec_relaxed(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec_relaxed(v); } #define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed @@ -416,7 +416,7 @@ atomic_fetch_dec_relaxed(atomic_t *v) static __always_inline void atomic_and(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_and(i, v); } #define atomic_and atomic_and @@ -425,7 +425,7 @@ atomic_and(int i, atomic_t *v) static __always_inline int atomic_fetch_and(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and(i, v); } #define atomic_fetch_and atomic_fetch_and @@ -435,7 +435,7 @@ atomic_fetch_and(int i, atomic_t *v) static __always_inline int atomic_fetch_and_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and_acquire(i, v); } #define atomic_fetch_and_acquire atomic_fetch_and_acquire @@ -445,7 +445,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and_release(i, v); } #define atomic_fetch_and_release atomic_fetch_and_release @@ -455,7 +455,7 @@ atomic_fetch_and_release(int i, atomic_t *v) static __always_inline int atomic_fetch_and_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and_relaxed(i, v); } #define atomic_fetch_and_relaxed atomic_fetch_and_relaxed @@ -465,7 +465,7 @@ atomic_fetch_and_relaxed(int i, atomic_t *v) static __always_inline void atomic_andnot(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_andnot(i, v); } #define atomic_andnot atomic_andnot @@ -475,7 +475,7 @@ atomic_andnot(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot(i, v); } #define atomic_fetch_andnot atomic_fetch_andnot @@ -485,7 +485,7 @@ atomic_fetch_andnot(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot_acquire(i, v); } #define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire @@ -495,7 +495,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot_release(i, v); } #define atomic_fetch_andnot_release atomic_fetch_andnot_release @@ -505,7 +505,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot_relaxed(i, v); } #define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed @@ -514,7 +514,7 @@ atomic_fetch_andnot_relaxed(int i, atomic_t *v) static __always_inline void atomic_or(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_or(i, v); } #define atomic_or atomic_or @@ -523,7 +523,7 @@ atomic_or(int i, atomic_t *v) static __always_inline int atomic_fetch_or(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or(i, v); } #define atomic_fetch_or atomic_fetch_or @@ -533,7 +533,7 @@ atomic_fetch_or(int i, atomic_t *v) static __always_inline int atomic_fetch_or_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or_acquire(i, v); } #define atomic_fetch_or_acquire atomic_fetch_or_acquire @@ -543,7 +543,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or_release(i, v); } #define atomic_fetch_or_release atomic_fetch_or_release @@ -553,7 +553,7 @@ atomic_fetch_or_release(int i, atomic_t *v) static __always_inline int atomic_fetch_or_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or_relaxed(i, v); } #define atomic_fetch_or_relaxed atomic_fetch_or_relaxed @@ -562,7 +562,7 @@ atomic_fetch_or_relaxed(int i, atomic_t *v) static __always_inline void atomic_xor(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic_xor(i, v); } #define atomic_xor atomic_xor @@ -571,7 +571,7 @@ atomic_xor(int i, atomic_t *v) static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor(i, v); } #define atomic_fetch_xor atomic_fetch_xor @@ -581,7 +581,7 @@ atomic_fetch_xor(int i, atomic_t *v) static __always_inline int atomic_fetch_xor_acquire(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor_acquire(i, v); } #define atomic_fetch_xor_acquire atomic_fetch_xor_acquire @@ -591,7 +591,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor_release(i, v); } #define atomic_fetch_xor_release atomic_fetch_xor_release @@ -601,7 +601,7 @@ atomic_fetch_xor_release(int i, atomic_t *v) static __always_inline int atomic_fetch_xor_relaxed(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor_relaxed(i, v); } #define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed @@ -611,7 +611,7 @@ atomic_fetch_xor_relaxed(int i, atomic_t *v) static __always_inline int atomic_xchg(atomic_t *v, int i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg(v, i); } #define atomic_xchg atomic_xchg @@ -621,7 +621,7 @@ atomic_xchg(atomic_t *v, int i) static __always_inline int atomic_xchg_acquire(atomic_t *v, int i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg_acquire(v, i); } #define atomic_xchg_acquire atomic_xchg_acquire @@ -631,7 +631,7 @@ atomic_xchg_acquire(atomic_t *v, int i) static __always_inline int atomic_xchg_release(atomic_t *v, int i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg_release(v, i); } #define atomic_xchg_release atomic_xchg_release @@ -641,7 +641,7 @@ atomic_xchg_release(atomic_t *v, int i) static __always_inline int atomic_xchg_relaxed(atomic_t *v, int i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg_relaxed(v, i); } #define atomic_xchg_relaxed atomic_xchg_relaxed @@ -651,7 +651,7 @@ atomic_xchg_relaxed(atomic_t *v, int i) static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg(v, old, new); } #define atomic_cmpxchg atomic_cmpxchg @@ -661,7 +661,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new) static __always_inline int atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg_acquire(v, old, new); } #define atomic_cmpxchg_acquire atomic_cmpxchg_acquire @@ -671,7 +671,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg_release(v, old, new); } #define atomic_cmpxchg_release atomic_cmpxchg_release @@ -681,7 +681,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new) static __always_inline int atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg_relaxed(v, old, new); } #define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed @@ -691,8 +691,8 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg(v, old, new); } #define atomic_try_cmpxchg atomic_try_cmpxchg @@ -702,8 +702,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg_acquire(v, old, new); } #define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire @@ -713,8 +713,8 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg_release(v, old, new); } #define atomic_try_cmpxchg_release atomic_try_cmpxchg_release @@ -724,8 +724,8 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg_relaxed(v, old, new); } #define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed @@ -735,7 +735,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_and_test(i, v); } #define atomic_sub_and_test atomic_sub_and_test @@ -745,7 +745,7 @@ atomic_sub_and_test(int i, atomic_t *v) static __always_inline bool atomic_dec_and_test(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_and_test(v); } #define atomic_dec_and_test atomic_dec_and_test @@ -755,7 +755,7 @@ atomic_dec_and_test(atomic_t *v) static __always_inline bool atomic_inc_and_test(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_and_test(v); } #define atomic_inc_and_test atomic_inc_and_test @@ -765,7 +765,7 @@ atomic_inc_and_test(atomic_t *v) static __always_inline bool atomic_add_negative(int i, atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_negative(i, v); } #define atomic_add_negative atomic_add_negative @@ -775,7 +775,7 @@ atomic_add_negative(int i, atomic_t *v) static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_unless(v, a, u); } #define atomic_fetch_add_unless atomic_fetch_add_unless @@ -785,7 +785,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_unless(v, a, u); } #define atomic_add_unless atomic_add_unless @@ -795,7 +795,7 @@ atomic_add_unless(atomic_t *v, int a, int u) static __always_inline bool atomic_inc_not_zero(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_not_zero(v); } #define atomic_inc_not_zero atomic_inc_not_zero @@ -805,7 +805,7 @@ atomic_inc_not_zero(atomic_t *v) static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_unless_negative(v); } #define atomic_inc_unless_negative atomic_inc_unless_negative @@ -815,7 +815,7 @@ atomic_inc_unless_negative(atomic_t *v) static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_unless_positive(v); } #define atomic_dec_unless_positive atomic_dec_unless_positive @@ -825,7 +825,7 @@ atomic_dec_unless_positive(atomic_t *v) static __always_inline int atomic_dec_if_positive(atomic_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_if_positive(v); } #define atomic_dec_if_positive atomic_dec_if_positive @@ -870,7 +870,7 @@ atomic64_set_release(atomic64_t *v, s64 i) static __always_inline void atomic64_add(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_add(i, v); } #define atomic64_add atomic64_add @@ -879,7 +879,7 @@ atomic64_add(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return(i, v); } #define atomic64_add_return atomic64_add_return @@ -889,7 +889,7 @@ atomic64_add_return(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return_acquire(i, v); } #define atomic64_add_return_acquire atomic64_add_return_acquire @@ -899,7 +899,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return_release(i, v); } #define atomic64_add_return_release atomic64_add_return_release @@ -909,7 +909,7 @@ atomic64_add_return_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return_relaxed(i, v); } #define atomic64_add_return_relaxed atomic64_add_return_relaxed @@ -919,7 +919,7 @@ atomic64_add_return_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add(i, v); } #define atomic64_fetch_add atomic64_fetch_add @@ -929,7 +929,7 @@ atomic64_fetch_add(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_acquire(i, v); } #define atomic64_fetch_add_acquire atomic64_fetch_add_acquire @@ -939,7 +939,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_release(i, v); } #define atomic64_fetch_add_release atomic64_fetch_add_release @@ -949,7 +949,7 @@ atomic64_fetch_add_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_relaxed(i, v); } #define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed @@ -958,7 +958,7 @@ atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) static __always_inline void atomic64_sub(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_sub(i, v); } #define atomic64_sub atomic64_sub @@ -967,7 +967,7 @@ atomic64_sub(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return(i, v); } #define atomic64_sub_return atomic64_sub_return @@ -977,7 +977,7 @@ atomic64_sub_return(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return_acquire(i, v); } #define atomic64_sub_return_acquire atomic64_sub_return_acquire @@ -987,7 +987,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return_release(i, v); } #define atomic64_sub_return_release atomic64_sub_return_release @@ -997,7 +997,7 @@ atomic64_sub_return_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return_relaxed(i, v); } #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed @@ -1007,7 +1007,7 @@ atomic64_sub_return_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub(i, v); } #define atomic64_fetch_sub atomic64_fetch_sub @@ -1017,7 +1017,7 @@ atomic64_fetch_sub(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub_acquire(i, v); } #define atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire @@ -1027,7 +1027,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub_release(i, v); } #define atomic64_fetch_sub_release atomic64_fetch_sub_release @@ -1037,7 +1037,7 @@ atomic64_fetch_sub_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub_relaxed(i, v); } #define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed @@ -1047,7 +1047,7 @@ atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) static __always_inline void atomic64_inc(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_inc(v); } #define atomic64_inc atomic64_inc @@ -1057,7 +1057,7 @@ atomic64_inc(atomic64_t *v) static __always_inline s64 atomic64_inc_return(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return(v); } #define atomic64_inc_return atomic64_inc_return @@ -1067,7 +1067,7 @@ atomic64_inc_return(atomic64_t *v) static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return_acquire(v); } #define atomic64_inc_return_acquire atomic64_inc_return_acquire @@ -1077,7 +1077,7 @@ atomic64_inc_return_acquire(atomic64_t *v) static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return_release(v); } #define atomic64_inc_return_release atomic64_inc_return_release @@ -1087,7 +1087,7 @@ atomic64_inc_return_release(atomic64_t *v) static __always_inline s64 atomic64_inc_return_relaxed(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return_relaxed(v); } #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed @@ -1097,7 +1097,7 @@ atomic64_inc_return_relaxed(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc(v); } #define atomic64_fetch_inc atomic64_fetch_inc @@ -1107,7 +1107,7 @@ atomic64_fetch_inc(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc_acquire(v); } #define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire @@ -1117,7 +1117,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc_release(v); } #define atomic64_fetch_inc_release atomic64_fetch_inc_release @@ -1127,7 +1127,7 @@ atomic64_fetch_inc_release(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc_relaxed(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc_relaxed(v); } #define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed @@ -1137,7 +1137,7 @@ atomic64_fetch_inc_relaxed(atomic64_t *v) static __always_inline void atomic64_dec(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_dec(v); } #define atomic64_dec atomic64_dec @@ -1147,7 +1147,7 @@ atomic64_dec(atomic64_t *v) static __always_inline s64 atomic64_dec_return(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return(v); } #define atomic64_dec_return atomic64_dec_return @@ -1157,7 +1157,7 @@ atomic64_dec_return(atomic64_t *v) static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return_acquire(v); } #define atomic64_dec_return_acquire atomic64_dec_return_acquire @@ -1167,7 +1167,7 @@ atomic64_dec_return_acquire(atomic64_t *v) static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return_release(v); } #define atomic64_dec_return_release atomic64_dec_return_release @@ -1177,7 +1177,7 @@ atomic64_dec_return_release(atomic64_t *v) static __always_inline s64 atomic64_dec_return_relaxed(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return_relaxed(v); } #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed @@ -1187,7 +1187,7 @@ atomic64_dec_return_relaxed(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec(v); } #define atomic64_fetch_dec atomic64_fetch_dec @@ -1197,7 +1197,7 @@ atomic64_fetch_dec(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec_acquire(v); } #define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire @@ -1207,7 +1207,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec_release(v); } #define atomic64_fetch_dec_release atomic64_fetch_dec_release @@ -1217,7 +1217,7 @@ atomic64_fetch_dec_release(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec_relaxed(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec_relaxed(v); } #define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed @@ -1226,7 +1226,7 @@ atomic64_fetch_dec_relaxed(atomic64_t *v) static __always_inline void atomic64_and(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_and(i, v); } #define atomic64_and atomic64_and @@ -1235,7 +1235,7 @@ atomic64_and(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and(i, v); } #define atomic64_fetch_and atomic64_fetch_and @@ -1245,7 +1245,7 @@ atomic64_fetch_and(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and_acquire(i, v); } #define atomic64_fetch_and_acquire atomic64_fetch_and_acquire @@ -1255,7 +1255,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and_release(i, v); } #define atomic64_fetch_and_release atomic64_fetch_and_release @@ -1265,7 +1265,7 @@ atomic64_fetch_and_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and_relaxed(i, v); } #define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed @@ -1275,7 +1275,7 @@ atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_andnot(i, v); } #define atomic64_andnot atomic64_andnot @@ -1285,7 +1285,7 @@ atomic64_andnot(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot(i, v); } #define atomic64_fetch_andnot atomic64_fetch_andnot @@ -1295,7 +1295,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot_acquire(i, v); } #define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire @@ -1305,7 +1305,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot_release(i, v); } #define atomic64_fetch_andnot_release atomic64_fetch_andnot_release @@ -1315,7 +1315,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot_relaxed(i, v); } #define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed @@ -1324,7 +1324,7 @@ atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) static __always_inline void atomic64_or(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_or(i, v); } #define atomic64_or atomic64_or @@ -1333,7 +1333,7 @@ atomic64_or(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or(i, v); } #define atomic64_fetch_or atomic64_fetch_or @@ -1343,7 +1343,7 @@ atomic64_fetch_or(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or_acquire(i, v); } #define atomic64_fetch_or_acquire atomic64_fetch_or_acquire @@ -1353,7 +1353,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or_release(i, v); } #define atomic64_fetch_or_release atomic64_fetch_or_release @@ -1363,7 +1363,7 @@ atomic64_fetch_or_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or_relaxed(i, v); } #define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed @@ -1372,7 +1372,7 @@ atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) static __always_inline void atomic64_xor(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); arch_atomic64_xor(i, v); } #define atomic64_xor atomic64_xor @@ -1381,7 +1381,7 @@ atomic64_xor(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor(i, v); } #define atomic64_fetch_xor atomic64_fetch_xor @@ -1391,7 +1391,7 @@ atomic64_fetch_xor(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor_acquire(i, v); } #define atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire @@ -1401,7 +1401,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor_release(i, v); } #define atomic64_fetch_xor_release atomic64_fetch_xor_release @@ -1411,7 +1411,7 @@ atomic64_fetch_xor_release(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor_relaxed(i, v); } #define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed @@ -1421,7 +1421,7 @@ atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg(v, i); } #define atomic64_xchg atomic64_xchg @@ -1431,7 +1431,7 @@ atomic64_xchg(atomic64_t *v, s64 i) static __always_inline s64 atomic64_xchg_acquire(atomic64_t *v, s64 i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg_acquire(v, i); } #define atomic64_xchg_acquire atomic64_xchg_acquire @@ -1441,7 +1441,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i) static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg_release(v, i); } #define atomic64_xchg_release atomic64_xchg_release @@ -1451,7 +1451,7 @@ atomic64_xchg_release(atomic64_t *v, s64 i) static __always_inline s64 atomic64_xchg_relaxed(atomic64_t *v, s64 i) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg_relaxed(v, i); } #define atomic64_xchg_relaxed atomic64_xchg_relaxed @@ -1461,7 +1461,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 i) static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg(v, old, new); } #define atomic64_cmpxchg atomic64_cmpxchg @@ -1471,7 +1471,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) static __always_inline s64 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg_acquire(v, old, new); } #define atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire @@ -1481,7 +1481,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg_release(v, old, new); } #define atomic64_cmpxchg_release atomic64_cmpxchg_release @@ -1491,7 +1491,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) static __always_inline s64 atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg_relaxed(v, old, new); } #define atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed @@ -1501,8 +1501,8 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg(v, old, new); } #define atomic64_try_cmpxchg atomic64_try_cmpxchg @@ -1512,8 +1512,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg_acquire(v, old, new); } #define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire @@ -1523,8 +1523,8 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg_release(v, old, new); } #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release @@ -1534,8 +1534,8 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { - instrument_atomic_write(v, sizeof(*v)); - instrument_atomic_write(old, sizeof(*old)); + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg_relaxed(v, old, new); } #define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed @@ -1545,7 +1545,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_and_test(i, v); } #define atomic64_sub_and_test atomic64_sub_and_test @@ -1555,7 +1555,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_and_test(v); } #define atomic64_dec_and_test atomic64_dec_and_test @@ -1565,7 +1565,7 @@ atomic64_dec_and_test(atomic64_t *v) static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_and_test(v); } #define atomic64_inc_and_test atomic64_inc_and_test @@ -1575,7 +1575,7 @@ atomic64_inc_and_test(atomic64_t *v) static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_negative(i, v); } #define atomic64_add_negative atomic64_add_negative @@ -1585,7 +1585,7 @@ atomic64_add_negative(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_unless(v, a, u); } #define atomic64_fetch_add_unless atomic64_fetch_add_unless @@ -1595,7 +1595,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_unless(v, a, u); } #define atomic64_add_unless atomic64_add_unless @@ -1605,7 +1605,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_not_zero(v); } #define atomic64_inc_not_zero atomic64_inc_not_zero @@ -1615,7 +1615,7 @@ atomic64_inc_not_zero(atomic64_t *v) static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_unless_negative(v); } #define atomic64_inc_unless_negative atomic64_inc_unless_negative @@ -1625,7 +1625,7 @@ atomic64_inc_unless_negative(atomic64_t *v) static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_unless_positive(v); } #define atomic64_dec_unless_positive atomic64_dec_unless_positive @@ -1635,7 +1635,7 @@ atomic64_dec_unless_positive(atomic64_t *v) static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { - instrument_atomic_write(v, sizeof(*v)); + instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_if_positive(v); } #define atomic64_dec_if_positive atomic64_dec_if_positive @@ -1786,4 +1786,4 @@ atomic64_dec_if_positive(atomic64_t *v) }) #endif /* _ASM_GENERIC_ATOMIC_INSTRUMENTED_H */ -// 89bf97f3a7509b740845e51ddf31055b48a81f40 +// 9d5e6a315fb1335d02f0ccd3655a91c3dafcc63e -- cgit v1.2.3 From 068df05363b79f54241bd6bd612055b8c16c5964 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 13 Aug 2020 18:38:59 +0200 Subject: bitops, kcsan: Partially revert instrumentation for non-atomic bitops Previous to the change to distinguish read-write accesses, when CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=y is set, KCSAN would consider the non-atomic bitops as atomic. We want to partially revert to this behaviour, but with one important distinction: report racing modifications, since lost bits due to non-atomicity are certainly possible. Given the operations here only modify a single bit, assuming non-atomicity of the writer is sufficient may be reasonable for certain usage (and follows the permissible nature of the "assume plain writes atomic" rule). In other words: 1. We want non-atomic read-modify-write races to be reported; this is accomplished by kcsan_check_read(), where any concurrent write (atomic or not) will generate a report. 2. We do not want to report races with marked readers, but -do- want to report races with unmarked readers; this is accomplished by the instrument_write() ("assume atomic write" with Kconfig option set). With the above rules, when KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected, it is hoped that KCSAN's reporting behaviour is better aligned with current expected permissible usage for non-atomic bitops. Note that, a side-effect of not telling KCSAN that the accesses are read-writes, is that this information is not displayed in the access summary in the report. It is, however, visible in inline-expanded stack traces. For now, it does not make sense to introduce yet another special case to KCSAN's runtime, only to cater to the case here. Cc: Dmitry Vyukov Cc: Paul E. McKenney Cc: Will Deacon Cc: Arnd Bergmann Cc: Daniel Axtens Cc: Michael Ellerman Cc: Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- .../asm-generic/bitops/instrumented-non-atomic.h | 30 +++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index f86234c7c10c..37363d570b9b 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -58,6 +58,30 @@ static inline void __change_bit(long nr, volatile unsigned long *addr) arch___change_bit(nr, addr); } +static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) +{ + if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { + /* + * We treat non-atomic read-write bitops a little more special. + * Given the operations here only modify a single bit, assuming + * non-atomicity of the writer is sufficient may be reasonable + * for certain usage (and follows the permissible nature of the + * assume-plain-writes-atomic rule): + * 1. report read-modify-write races -> check read; + * 2. do not report races with marked readers, but do report + * races with unmarked readers -> check "atomic" write. + */ + kcsan_check_read(addr + BIT_WORD(nr), sizeof(long)); + /* + * Use generic write instrumentation, in case other sanitizers + * or tools are enabled alongside KCSAN. + */ + instrument_write(addr + BIT_WORD(nr), sizeof(long)); + } else { + instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); + } +} + /** * __test_and_set_bit - Set a bit and return its old value * @nr: Bit to set @@ -68,7 +92,7 @@ static inline void __change_bit(long nr, volatile unsigned long *addr) */ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) { - instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); + __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); } @@ -82,7 +106,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) */ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) { - instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); + __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); } @@ -96,7 +120,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) */ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) { - instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); + __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); } -- cgit v1.2.3 From 583bbf0624dfd8fc45f1049be1d4980be59451ff Mon Sep 17 00:00:00 2001 From: Luke Hsiao Date: Fri, 21 Aug 2020 21:41:04 -0700 Subject: io_uring: allow tcp ancillary data for __sys_recvmsg_sock() For TCP tx zero-copy, the kernel notifies the process of completions by queuing completion notifications on the socket error queue. This patch allows reading these notifications via recvmsg to support TCP tx zero-copy. Ancillary data was originally disallowed due to privilege escalation via io_uring's offloading of sendmsg() onto a kernel thread with kernel credentials (https://crbug.com/project-zero/1975). So, we must ensure that the socket type is one where the ancillary data types that are delivered on recvmsg are plain data (no file descriptors or values that are translated based on the identity of the calling process). This was tested by using io_uring to call recvmsg on the MSG_ERRQUEUE with tx zero-copy enabled. Before this patch, we received -EINVALID from this specific code path. After this patch, we could read tcp tx zero-copy completion notifications from the MSG_ERRQUEUE. Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Arjun Roy Acked-by: Eric Dumazet Reviewed-by: Jann Horn Reviewed-by: Jens Axboe Signed-off-by: Luke Hsiao Signed-off-by: David S. Miller --- include/linux/net.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..7657c6432a69 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,8 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define PROTO_CMSG_DATA_ONLY 0x0001 + #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -135,6 +137,7 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; + unsigned int flags; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, -- cgit v1.2.3 From 755f982bb1ff469a181df3eaf8dd5d769267ab8e Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Sun, 23 Aug 2020 14:19:26 +0300 Subject: qed/qede: make devlink survive recovery Devlink instance lifecycle was linked to qed_dev object, that caused devlink to be recreated on each recovery. Changing it by making higher level driver (qede) responsible for its life. This way devlink now survives recoveries. qede now stores devlink structure pointer as a part of its device object, devlink private data contains a linkage structure, qed_devlink. Signed-off-by: Igor Russkikh Signed-off-by: Alexander Lobakin Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..d8368e1770df 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -21,6 +21,7 @@ #include #include #include +#include enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, @@ -779,6 +780,10 @@ enum qed_nvm_flash_cmd { QED_NVM_FLASH_CMD_NVM_MAX, }; +struct qed_devlink { + struct qed_dev *cdev; +}; + struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); @@ -1137,6 +1142,10 @@ struct qed_common_ops { * */ int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val); + + struct devlink* (*devlink_register)(struct qed_dev *cdev); + + void (*devlink_unregister)(struct devlink *devlink); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From 9524067b9a91dce2a096a0de7727c217495e3d2e Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Sun, 23 Aug 2020 14:19:29 +0300 Subject: qed: health reporter init deinit seq Here we declare health reporter ops (empty for now) and register these in qed probe and remove callbacks. This way we get devlink attached to all kind of qed* PCI device entities: networking or storage offload entity. Signed-off-by: Igor Russkikh Signed-off-by: Alexander Lobakin Signed-off-by: Michal Kalderon Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index d8368e1770df..30fe06fe06a0 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -782,6 +782,7 @@ enum qed_nvm_flash_cmd { struct qed_devlink { struct qed_dev *cdev; + struct devlink_health_reporter *fw_reporter; }; struct qed_common_cb_ops { -- cgit v1.2.3 From 4f5a8db27eb926616500f827d9b81dc40595b0ef Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Sun, 23 Aug 2020 14:19:30 +0300 Subject: qed: use devlink logic to report errors Use devlink_health_report to push error indications. We implement this in qede via callback function to make it possible to reuse the same for other drivers sitting on top of qed in future. Signed-off-by: Igor Russkikh Signed-off-by: Alexander Lobakin Signed-off-by: Michal Kalderon Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 30fe06fe06a0..a75533de9186 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -906,6 +906,9 @@ struct qed_common_ops { int (*dbg_all_data_size) (struct qed_dev *cdev); + int (*report_fatal_error)(struct devlink *devlink, + enum qed_hw_err_type err_type); + /** * @brief can_link_change - can the instance change the link or not * -- cgit v1.2.3 From c5c642c55e2fd43fcf42262fd1e87271d413fb42 Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Sun, 23 Aug 2020 14:19:33 +0300 Subject: qed: align adjacent indent Remove extra indent on some of adjacent declarations. Signed-off-by: Igor Russkikh Signed-off-by: Alexander Lobakin Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 69 ++++++++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index a75533de9186..56fa55841d39 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -850,10 +850,9 @@ struct qed_common_ops { struct qed_dev* (*probe)(struct pci_dev *dev, struct qed_probe_params *params); - void (*remove)(struct qed_dev *cdev); + void (*remove)(struct qed_dev *cdev); - int (*set_power_state)(struct qed_dev *cdev, - pci_power_t state); + int (*set_power_state)(struct qed_dev *cdev, pci_power_t state); void (*set_name) (struct qed_dev *cdev, char name[]); @@ -861,50 +860,48 @@ struct qed_common_ops { * PF params required for the call before slowpath_start is * documented within the qed_pf_params structure definition. */ - void (*update_pf_params)(struct qed_dev *cdev, - struct qed_pf_params *params); - int (*slowpath_start)(struct qed_dev *cdev, - struct qed_slowpath_params *params); + void (*update_pf_params)(struct qed_dev *cdev, + struct qed_pf_params *params); - int (*slowpath_stop)(struct qed_dev *cdev); + int (*slowpath_start)(struct qed_dev *cdev, + struct qed_slowpath_params *params); + + int (*slowpath_stop)(struct qed_dev *cdev); /* Requests to use `cnt' interrupts for fastpath. * upon success, returns number of interrupts allocated for fastpath. */ - int (*set_fp_int)(struct qed_dev *cdev, - u16 cnt); + int (*set_fp_int)(struct qed_dev *cdev, u16 cnt); /* Fills `info' with pointers required for utilizing interrupts */ - int (*get_fp_int)(struct qed_dev *cdev, - struct qed_int_info *info); - - u32 (*sb_init)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - void *sb_virt_addr, - dma_addr_t sb_phy_addr, - u16 sb_id, - enum qed_sb_type type); - - u32 (*sb_release)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - u16 sb_id, - enum qed_sb_type type); - - void (*simd_handler_config)(struct qed_dev *cdev, - void *token, - int index, - void (*handler)(void *)); - - void (*simd_handler_clean)(struct qed_dev *cdev, - int index); - int (*dbg_grc)(struct qed_dev *cdev, - void *buffer, u32 *num_dumped_bytes); + int (*get_fp_int)(struct qed_dev *cdev, struct qed_int_info *info); + + u32 (*sb_init)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + void *sb_virt_addr, + dma_addr_t sb_phy_addr, + u16 sb_id, + enum qed_sb_type type); + + u32 (*sb_release)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + u16 sb_id, + enum qed_sb_type type); + + void (*simd_handler_config)(struct qed_dev *cdev, + void *token, + int index, + void (*handler)(void *)); + + void (*simd_handler_clean)(struct qed_dev *cdev, int index); + + int (*dbg_grc)(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes); int (*dbg_grc_size)(struct qed_dev *cdev); - int (*dbg_all_data) (struct qed_dev *cdev, void *buffer); + int (*dbg_all_data)(struct qed_dev *cdev, void *buffer); - int (*dbg_all_data_size) (struct qed_dev *cdev); + int (*dbg_all_data_size)(struct qed_dev *cdev); int (*report_fatal_error)(struct devlink *devlink, enum qed_hw_err_type err_type); -- cgit v1.2.3 From c30068f41a0e899f870e0158a2c69c68d738bf96 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Thu, 18 Jun 2020 21:36:39 -0400 Subject: rcu/trace: Print negative GP numbers correctly GP numbers start from -300 and gp_seq numbers start of -1200 (for a shift of 2). These negative numbers are printed as unsigned long which not only takes up more text space, but is rather confusing to the reader as they have to constantly expend energy to truncate the number. Just print the negative numbering directly. Cc: Uladzislau Rezki (Sony) Signed-off-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 54 +++++++++++++++++++++++----------------------- 1 file changed, 27 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index ced71237b7e4..155b5cb43cfd 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -74,17 +74,17 @@ TRACE_EVENT_RCU(rcu_grace_period, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gp_seq) + __field(long, gp_seq) __field(const char *, gpevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gp_seq = gp_seq; + __entry->gp_seq = (long)gp_seq; __entry->gpevent = gpevent; ), - TP_printk("%s %lu %s", + TP_printk("%s %ld %s", __entry->rcuname, __entry->gp_seq, __entry->gpevent) ); @@ -114,8 +114,8 @@ TRACE_EVENT_RCU(rcu_future_grace_period, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gp_seq) - __field(unsigned long, gp_seq_req) + __field(long, gp_seq) + __field(long, gp_seq_req) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -124,16 +124,16 @@ TRACE_EVENT_RCU(rcu_future_grace_period, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gp_seq = gp_seq; - __entry->gp_seq_req = gp_seq_req; + __entry->gp_seq = (long)gp_seq; + __entry->gp_seq_req = (long)gp_seq_req; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; __entry->gpevent = gpevent; ), - TP_printk("%s %lu %lu %u %d %d %s", - __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level, + TP_printk("%s %ld %ld %u %d %d %s", + __entry->rcuname, (long)__entry->gp_seq, (long)__entry->gp_seq_req, __entry->level, __entry->grplo, __entry->grphi, __entry->gpevent) ); @@ -153,7 +153,7 @@ TRACE_EVENT_RCU(rcu_grace_period_init, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gp_seq) + __field(long, gp_seq) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -162,14 +162,14 @@ TRACE_EVENT_RCU(rcu_grace_period_init, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gp_seq = gp_seq; + __entry->gp_seq = (long)gp_seq; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; __entry->qsmask = qsmask; ), - TP_printk("%s %lu %u %d %d %lx", + TP_printk("%s %ld %u %d %d %lx", __entry->rcuname, __entry->gp_seq, __entry->level, __entry->grplo, __entry->grphi, __entry->qsmask) ); @@ -197,17 +197,17 @@ TRACE_EVENT_RCU(rcu_exp_grace_period, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpseq) + __field(long, gpseq) __field(const char *, gpevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpseq = gpseq; + __entry->gpseq = (long)gpseq; __entry->gpevent = gpevent; ), - TP_printk("%s %lu %s", + TP_printk("%s %ld %s", __entry->rcuname, __entry->gpseq, __entry->gpevent) ); @@ -316,17 +316,17 @@ TRACE_EVENT_RCU(rcu_preempt_task, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gp_seq) + __field(long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gp_seq = gp_seq; + __entry->gp_seq = (long)gp_seq; __entry->pid = pid; ), - TP_printk("%s %lu %d", + TP_printk("%s %ld %d", __entry->rcuname, __entry->gp_seq, __entry->pid) ); @@ -343,17 +343,17 @@ TRACE_EVENT_RCU(rcu_unlock_preempted_task, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gp_seq) + __field(long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gp_seq = gp_seq; + __entry->gp_seq = (long)gp_seq; __entry->pid = pid; ), - TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid) + TP_printk("%s %ld %d", __entry->rcuname, __entry->gp_seq, __entry->pid) ); /* @@ -374,7 +374,7 @@ TRACE_EVENT_RCU(rcu_quiescent_state_report, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gp_seq) + __field(long, gp_seq) __field(unsigned long, mask) __field(unsigned long, qsmask) __field(u8, level) @@ -385,7 +385,7 @@ TRACE_EVENT_RCU(rcu_quiescent_state_report, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gp_seq = gp_seq; + __entry->gp_seq = (long)gp_seq; __entry->mask = mask; __entry->qsmask = qsmask; __entry->level = level; @@ -394,7 +394,7 @@ TRACE_EVENT_RCU(rcu_quiescent_state_report, __entry->gp_tasks = gp_tasks; ), - TP_printk("%s %lu %lx>%lx %u %d %d %u", + TP_printk("%s %ld %lx>%lx %u %d %d %u", __entry->rcuname, __entry->gp_seq, __entry->mask, __entry->qsmask, __entry->level, __entry->grplo, __entry->grphi, __entry->gp_tasks) @@ -415,19 +415,19 @@ TRACE_EVENT_RCU(rcu_fqs, TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gp_seq) + __field(long, gp_seq) __field(int, cpu) __field(const char *, qsevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gp_seq = gp_seq; + __entry->gp_seq = (long)gp_seq; __entry->cpu = cpu; __entry->qsevent = qsevent; ), - TP_printk("%s %lu %d %s", + TP_printk("%s %ld %d %s", __entry->rcuname, __entry->gp_seq, __entry->cpu, __entry->qsevent) ); -- cgit v1.2.3 From 000601bb62330f18dc8f5d2d0b82e9aec3e207c4 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Thu, 9 Jul 2020 15:05:59 +0200 Subject: rcu: Fix kerneldoc comments in rcupdate.h This commit fixes the kerneldoc comments for rcu_read_unlock_bh(), rcu_read_unlock_sched() and rcu_head_after_call_rcu() so they e.g. get properly linked in the API documentation. Also add parenthesis after function names to match the notation used in other kerneldoc comments in the same file. Signed-off-by: Tobias Klauser Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d15d46db61f7..b47d6b66665e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -709,8 +709,8 @@ static inline void rcu_read_lock_bh(void) "rcu_read_lock_bh() used illegally while idle"); } -/* - * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section +/** + * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ @@ -751,10 +751,10 @@ static inline notrace void rcu_read_lock_sched_notrace(void) __acquire(RCU_SCHED); } -/* - * rcu_read_unlock_sched - marks the end of a RCU-classic critical section +/** + * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * - * See rcu_read_lock_sched for more information. + * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { @@ -945,7 +945,7 @@ static inline void rcu_head_init(struct rcu_head *rhp) } /** - * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()? + * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * -- cgit v1.2.3 From ae2212a7216b674633bdc3bd2e24947a0665efb8 Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Sun, 12 Jul 2020 18:40:02 +0530 Subject: rculist: Introduce list/hlist_for_each_entry_srcu() macros list/hlist_for_each_entry_rcu() provides an optional cond argument to specify the lock held in the updater side. However for SRCU read side, not providing the cond argument results into false positive as whether srcu_read_lock is held or not is not checked implicitly. Therefore, on read side the lockdep expression srcu_read_lock_held(srcu struct) can solve this issue. However, the function still fails to check the cases where srcu protected list is traversed with rcu_read_lock() instead of srcu_read_lock(). Therefore, to remove the false negative, this patch introduces two new list traversal primitives : list_for_each_entry_srcu() and hlist_for_each_entry_srcu(). Both of the functions have non-optional cond argument as it is required for both read and update side, and simply checks if the cond is true. For regular read side the lockdep expression srcu_read_lock_head() can be passed as the cond argument to list/hlist_for_each_entry_srcu(). Suggested-by: Paolo Bonzini Tested-by: Suraj Upadhyay Tested-by: Naresh Kamboju [ paulmck: Add "true" per kbuild test robot feedback. ] Signed-off-by: Madhuparna Bhowmik Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 7a6fc9956510..f8633d37e358 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -63,9 +63,17 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) + +#define __list_check_srcu(cond) \ + ({ \ + RCU_LOCKDEP_WARN(!(cond), \ + "RCU-list traversed without holding the required lock!");\ + }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) + +#define __list_check_srcu(cond) ({ }) #endif /* @@ -385,6 +393,25 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) +/** + * list_for_each_entry_srcu - iterate over rcu list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * @cond: lockdep expression for the lock required to traverse the list. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as list_add_rcu() + * as long as the traversal is guarded by srcu_read_lock(). + * The lockdep expression srcu_read_lock_held() can be passed as the + * cond argument from read side. + */ +#define list_for_each_entry_srcu(pos, head, member, cond) \ + for (__list_check_srcu(cond), \ + pos = list_entry_rcu((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) + /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. @@ -683,6 +710,27 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) +/** + * hlist_for_each_entry_srcu - iterate over rcu list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + * @cond: lockdep expression for the lock required to traverse the list. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as hlist_add_head_rcu() + * as long as the traversal is guarded by srcu_read_lock(). + * The lockdep expression srcu_read_lock_held() can be passed as the + * cond argument from read side. + */ +#define hlist_for_each_entry_srcu(pos, head, member, cond) \ + for (__list_check_srcu(cond), \ + pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ + &(pos)->member)), typeof(*(pos)), member)) + /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. -- cgit v1.2.3 From 7f2a53c231fe5d9522c3b695ab454203904031ac Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 17 Aug 2020 10:37:22 -0700 Subject: rcu: Remove unused __rcu_is_watching() function The x86/entry work removed all uses of __rcu_is_watching(), therefore this commit removes it entirely. Cc: Andy Lutomirski Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 1 - include/linux/rcutree.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 5cc9637cac16..7c1ecdb356d8 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -103,7 +103,6 @@ static inline void rcu_scheduler_starting(void) { } static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } -static inline bool __rcu_is_watching(void) { return true; } static inline void rcu_momentary_dyntick_idle(void) { } static inline void kfree_rcu_scheduler_running(void) { } static inline bool rcu_gp_might_be_stalled(void) { return false; } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d2f4064ebd1d..59eb5cd567d7 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -64,7 +64,6 @@ extern int rcu_scheduler_active __read_mostly; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); -bool __rcu_is_watching(void); #ifndef CONFIG_PREEMPTION void rcu_all_qs(void); #endif -- cgit v1.2.3 From aa40c138cc8f36e2f5c721fd1bdb823a1ef1a237 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 10 Aug 2020 09:58:03 -0700 Subject: rcu: Report QS for outermost PREEMPT=n rcu_read_unlock() for strict GPs The CONFIG_PREEMPT=n instance of rcu_read_unlock is even more aggressively than that of CONFIG_PREEMPT=y in deferring reporting quiescent states to the RCU core. This is just what is wanted in normal use because it reduces overhead, but the resulting delay is not what is wanted for kernels built with CONFIG_RCU_STRICT_GRACE_PERIOD=y. This commit therefore adds an rcu_read_unlock_strict() function that checks for exceptional conditions, and reports the newly started quiescent state if it is safe to do so, also doing a spin-delay if requested via rcutree.rcu_unlock_delay. This commit also adds a call to rcu_read_unlock_strict() from the CONFIG_PREEMPT=n instance of __rcu_read_unlock(). [ paulmck: Fixed bug located by kernel test robot ] Reported-by Jann Horn Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d15d46db61f7..522529a13786 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -55,6 +55,12 @@ void __rcu_read_unlock(void); #else /* #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_TINY_RCU +#define rcu_read_unlock_strict() do { } while (0) +#else +void rcu_read_unlock_strict(void); +#endif + static inline void __rcu_read_lock(void) { preempt_disable(); @@ -63,6 +69,7 @@ static inline void __rcu_read_lock(void) static inline void __rcu_read_unlock(void) { preempt_enable(); + rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) -- cgit v1.2.3 From fb038ce4db55cf2c911b6b221d10f06afe5f25af Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Fri, 24 Jul 2020 14:58:43 +0800 Subject: clk: sunxi-ng: add support for the Allwinner A100 CCU Add support for a100 in the sunxi-ng CCU framework. Signed-off-by: Yangtao Li Signed-off-by: Maxime Ripard Acked-by: Rob Herring Link: https://lore.kernel.org/r/1eb41bf6c966a0e54820200650d27a5d4f2ac160.1595572867.git.frank@allwinnertech.com --- include/dt-bindings/clock/sun50i-a100-ccu.h | 116 ++++++++++++++++++++++++++ include/dt-bindings/clock/sun50i-a100-r-ccu.h | 23 +++++ include/dt-bindings/reset/sun50i-a100-ccu.h | 68 +++++++++++++++ include/dt-bindings/reset/sun50i-a100-r-ccu.h | 18 ++++ 4 files changed, 225 insertions(+) create mode 100644 include/dt-bindings/clock/sun50i-a100-ccu.h create mode 100644 include/dt-bindings/clock/sun50i-a100-r-ccu.h create mode 100644 include/dt-bindings/reset/sun50i-a100-ccu.h create mode 100644 include/dt-bindings/reset/sun50i-a100-r-ccu.h (limited to 'include') diff --git a/include/dt-bindings/clock/sun50i-a100-ccu.h b/include/dt-bindings/clock/sun50i-a100-ccu.h new file mode 100644 index 000000000000..28dc36e1a232 --- /dev/null +++ b/include/dt-bindings/clock/sun50i-a100-ccu.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ +/* + * Copyright (c) 2020 Yangtao Li + */ + +#ifndef _DT_BINDINGS_CLK_SUN50I_A100_H_ +#define _DT_BINDINGS_CLK_SUN50I_A100_H_ + +#define CLK_PLL_PERIPH0 3 + +#define CLK_CPUX 24 + +#define CLK_APB1 29 + +#define CLK_MBUS 31 +#define CLK_DE 32 +#define CLK_BUS_DE 33 +#define CLK_G2D 34 +#define CLK_BUS_G2D 35 +#define CLK_GPU 36 +#define CLK_BUS_GPU 37 +#define CLK_CE 38 +#define CLK_BUS_CE 39 +#define CLK_VE 40 +#define CLK_BUS_VE 41 +#define CLK_BUS_DMA 42 +#define CLK_BUS_MSGBOX 43 +#define CLK_BUS_SPINLOCK 44 +#define CLK_BUS_HSTIMER 45 +#define CLK_AVS 46 +#define CLK_BUS_DBG 47 +#define CLK_BUS_PSI 48 +#define CLK_BUS_PWM 49 +#define CLK_BUS_IOMMU 50 +#define CLK_MBUS_DMA 51 +#define CLK_MBUS_VE 52 +#define CLK_MBUS_CE 53 +#define CLK_MBUS_NAND 54 +#define CLK_MBUS_CSI 55 +#define CLK_MBUS_ISP 56 +#define CLK_MBUS_G2D 57 + +#define CLK_NAND0 59 +#define CLK_NAND1 60 +#define CLK_BUS_NAND 61 +#define CLK_MMC0 62 +#define CLK_MMC1 63 +#define CLK_MMC2 64 +#define CLK_MMC3 65 +#define CLK_BUS_MMC0 66 +#define CLK_BUS_MMC1 67 +#define CLK_BUS_MMC2 68 +#define CLK_BUS_UART0 69 +#define CLK_BUS_UART1 70 +#define CLK_BUS_UART2 71 +#define CLK_BUS_UART3 72 +#define CLK_BUS_UART4 73 +#define CLK_BUS_I2C0 74 +#define CLK_BUS_I2C1 75 +#define CLK_BUS_I2C2 76 +#define CLK_BUS_I2C3 77 +#define CLK_SPI0 78 +#define CLK_SPI1 79 +#define CLK_SPI2 80 +#define CLK_BUS_SPI0 81 +#define CLK_BUS_SPI1 82 +#define CLK_BUS_SPI2 83 +#define CLK_EMAC_25M 84 +#define CLK_BUS_EMAC 85 +#define CLK_IR_RX 86 +#define CLK_BUS_IR_RX 87 +#define CLK_IR_TX 88 +#define CLK_BUS_IR_TX 89 +#define CLK_BUS_GPADC 90 +#define CLK_BUS_THS 91 +#define CLK_I2S0 92 +#define CLK_I2S1 93 +#define CLK_I2S2 94 +#define CLK_I2S3 95 +#define CLK_BUS_I2S0 96 +#define CLK_BUS_I2S1 97 +#define CLK_BUS_I2S2 98 +#define CLK_BUS_I2S3 99 +#define CLK_SPDIF 100 +#define CLK_BUS_SPDIF 101 +#define CLK_DMIC 102 +#define CLK_BUS_DMIC 103 +#define CLK_AUDIO_DAC 104 +#define CLK_AUDIO_ADC 105 +#define CLK_AUDIO_4X 106 +#define CLK_BUS_AUDIO_CODEC 107 +#define CLK_USB_OHCI0 108 +#define CLK_USB_PHY0 109 +#define CLK_USB_OHCI1 110 +#define CLK_USB_PHY1 111 +#define CLK_BUS_OHCI0 112 +#define CLK_BUS_OHCI1 113 +#define CLK_BUS_EHCI0 114 +#define CLK_BUS_EHCI1 115 +#define CLK_BUS_OTG 116 +#define CLK_BUS_LRADC 117 +#define CLK_BUS_DPSS_TOP0 118 +#define CLK_BUS_DPSS_TOP1 119 +#define CLK_MIPI_DSI 120 +#define CLK_BUS_MIPI_DSI 121 +#define CLK_TCON_LCD 122 +#define CLK_BUS_TCON_LCD 123 +#define CLK_LEDC 124 +#define CLK_BUS_LEDC 125 +#define CLK_CSI_TOP 126 +#define CLK_CSI0_MCLK 127 +#define CLK_CSI1_MCLK 128 +#define CLK_BUS_CSI 129 +#define CLK_CSI_ISP 130 + +#endif /* _DT_BINDINGS_CLK_SUN50I_A100_H_ */ diff --git a/include/dt-bindings/clock/sun50i-a100-r-ccu.h b/include/dt-bindings/clock/sun50i-a100-r-ccu.h new file mode 100644 index 000000000000..07312e7264fb --- /dev/null +++ b/include/dt-bindings/clock/sun50i-a100-r-ccu.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Yangtao Li + */ + +#ifndef _DT_BINDINGS_CLK_SUN50I_A100_R_CCU_H_ +#define _DT_BINDINGS_CLK_SUN50I_A100_R_CCU_H_ + +#define CLK_R_APB1 2 + +#define CLK_R_APB1_TIMER 4 +#define CLK_R_APB1_TWD 5 +#define CLK_R_APB1_PWM 6 +#define CLK_R_APB1_BUS_PWM 7 +#define CLK_R_APB1_PPU 8 +#define CLK_R_APB2_UART 9 +#define CLK_R_APB2_I2C0 10 +#define CLK_R_APB2_I2C1 11 +#define CLK_R_APB1_IR 12 +#define CLK_R_APB1_BUS_IR 13 +#define CLK_R_AHB_BUS_RTC 14 + +#endif /* _DT_BINDINGS_CLK_SUN50I_A100_R_CCU_H_ */ diff --git a/include/dt-bindings/reset/sun50i-a100-ccu.h b/include/dt-bindings/reset/sun50i-a100-ccu.h new file mode 100644 index 000000000000..55c0ada99885 --- /dev/null +++ b/include/dt-bindings/reset/sun50i-a100-ccu.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ +/* + * Copyright (c) 2020 Yangtao Li + */ + +#ifndef _DT_BINDINGS_RESET_SUN50I_A100_H_ +#define _DT_BINDINGS_RESET_SUN50I_A100_H_ + +#define RST_MBUS 0 +#define RST_BUS_DE 1 +#define RST_BUS_G2D 2 +#define RST_BUS_GPU 3 +#define RST_BUS_CE 4 +#define RST_BUS_VE 5 +#define RST_BUS_DMA 6 +#define RST_BUS_MSGBOX 7 +#define RST_BUS_SPINLOCK 8 +#define RST_BUS_HSTIMER 9 +#define RST_BUS_DBG 10 +#define RST_BUS_PSI 11 +#define RST_BUS_PWM 12 +#define RST_BUS_DRAM 13 +#define RST_BUS_NAND 14 +#define RST_BUS_MMC0 15 +#define RST_BUS_MMC1 16 +#define RST_BUS_MMC2 17 +#define RST_BUS_UART0 18 +#define RST_BUS_UART1 19 +#define RST_BUS_UART2 20 +#define RST_BUS_UART3 21 +#define RST_BUS_UART4 22 +#define RST_BUS_I2C0 23 +#define RST_BUS_I2C1 24 +#define RST_BUS_I2C2 25 +#define RST_BUS_I2C3 26 +#define RST_BUS_SPI0 27 +#define RST_BUS_SPI1 28 +#define RST_BUS_SPI2 29 +#define RST_BUS_EMAC 30 +#define RST_BUS_IR_RX 31 +#define RST_BUS_IR_TX 32 +#define RST_BUS_GPADC 33 +#define RST_BUS_THS 34 +#define RST_BUS_I2S0 35 +#define RST_BUS_I2S1 36 +#define RST_BUS_I2S2 37 +#define RST_BUS_I2S3 38 +#define RST_BUS_SPDIF 39 +#define RST_BUS_DMIC 40 +#define RST_BUS_AUDIO_CODEC 41 +#define RST_USB_PHY0 42 +#define RST_USB_PHY1 43 +#define RST_BUS_OHCI0 44 +#define RST_BUS_OHCI1 45 +#define RST_BUS_EHCI0 46 +#define RST_BUS_EHCI1 47 +#define RST_BUS_OTG 48 +#define RST_BUS_LRADC 49 +#define RST_BUS_DPSS_TOP0 50 +#define RST_BUS_DPSS_TOP1 51 +#define RST_BUS_MIPI_DSI 52 +#define RST_BUS_TCON_LCD 53 +#define RST_BUS_LVDS 54 +#define RST_BUS_LEDC 55 +#define RST_BUS_CSI 56 +#define RST_BUS_CSI_ISP 57 + +#endif /* _DT_BINDINGS_RESET_SUN50I_A100_H_ */ diff --git a/include/dt-bindings/reset/sun50i-a100-r-ccu.h b/include/dt-bindings/reset/sun50i-a100-r-ccu.h new file mode 100644 index 000000000000..737bf6f66626 --- /dev/null +++ b/include/dt-bindings/reset/sun50i-a100-r-ccu.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ +/* + * Copyright (c) 2020 Yangtao Li + */ + +#ifndef _DT_BINDINGS_RST_SUN50I_A100_R_CCU_H_ +#define _DT_BINDINGS_RST_SUN50I_A100_R_CCU_H_ + +#define RST_R_APB1_TIMER 0 +#define RST_R_APB1_BUS_PWM 1 +#define RST_R_APB1_PPU 2 +#define RST_R_APB2_UART 3 +#define RST_R_APB2_I2C0 4 +#define RST_R_APB2_I2C1 5 +#define RST_R_APB1_BUS_IR 6 +#define RST_R_AHB_BUS_RTC 7 + +#endif /* _DT_BINDINGS_RST_SUN50I_A100_R_CCU_H_ */ -- cgit v1.2.3 From c1f90759b3d536f9b1b047484d08dfd04af3c4b1 Mon Sep 17 00:00:00 2001 From: David Heidelberg Date: Fri, 14 Aug 2020 00:34:01 +0300 Subject: dt-bindings: power: supply: Add device-tree binding for Summit SMB3xx Summit SMB3xx series is a Programmable Switching Li+ Battery Charger. This patch adds device-tree binding for Summit SMB345, SMB347 and SMB358 chargers. Signed-off-by: David Heidelberg Signed-off-by: Dmitry Osipenko Reviewed-by: Rob Herring Signed-off-by: Sebastian Reichel --- include/dt-bindings/power/summit,smb347-charger.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/dt-bindings/power/summit,smb347-charger.h (limited to 'include') diff --git a/include/dt-bindings/power/summit,smb347-charger.h b/include/dt-bindings/power/summit,smb347-charger.h new file mode 100644 index 000000000000..d918bf321a71 --- /dev/null +++ b/include/dt-bindings/power/summit,smb347-charger.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0-or-later or MIT) */ +/* + * Author: David Heidelberg + */ + +#ifndef _DT_BINDINGS_SMB347_CHARGER_H +#define _DT_BINDINGS_SMB347_CHARGER_H + +/* Charging compensation method */ +#define SMB3XX_SOFT_TEMP_COMPENSATE_NONE 0 +#define SMB3XX_SOFT_TEMP_COMPENSATE_CURRENT 1 +#define SMB3XX_SOFT_TEMP_COMPENSATE_VOLTAGE 2 + +/* Charging enable control */ +#define SMB3XX_CHG_ENABLE_SW 0 +#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_LOW 1 +#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH 2 + +#endif -- cgit v1.2.3 From 00cda13e339c9f4956a6f036675df2ca5b5a552e Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 14 Aug 2020 00:34:02 +0300 Subject: power: supply: Support battery temperature device-tree properties The generic battery temperature properties are already supported by the power-supply core. Let's support parsing of the common battery temperature properties from a device-tree. Signed-off-by: Dmitry Osipenko Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 97cc4b85bf61..d0684362a392 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -365,6 +365,12 @@ struct power_supply_battery_info { int constant_charge_voltage_max_uv; /* microVolts */ int factory_internal_resistance_uohm; /* microOhms */ int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX];/* celsius */ + int temp_ambient_alert_min; /* celsius */ + int temp_ambient_alert_max; /* celsius */ + int temp_alert_min; /* celsius */ + int temp_alert_max; /* celsius */ + int temp_min; /* celsius */ + int temp_max; /* celsius */ struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX]; int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; struct power_supply_resistance_temp_table *resist_table; -- cgit v1.2.3 From 135ab457e776d042c481d70d8954f6775ce35958 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 24 Aug 2020 15:09:12 -0500 Subject: ASoC: Intel: use consistent HDAudio spelling in comments/docs We use HDaudio and HDAudio, pick one to make searches easier. No functionality change Reported-by: Guennadi Liakhovetski Reviewed-by: Bard Liao Reviewed-by: Guennadi Liakhovetski Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20200824200912.46852-9-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index d2e9e3b4d7ea..b77b05c413a3 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -58,7 +58,7 @@ static inline struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg) * snd_soc_acpi_mach_params: interface for machine driver configuration * * @acpi_ipc_irq_index: used for BYT-CR detection - * @platform: string used for HDaudio codec support + * @platform: string used for HDAudio codec support * @codec_mask: used for HDAudio support * @common_hdmi_codec_drv: use commom HDAudio HDMI codec driver * @link_mask: links enabled on the board -- cgit v1.2.3 From 1f00d375af84fbcdb6dd6c79fd7c3d02d2390338 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:13 +0200 Subject: bpf: Renames in preparation for bpf_local_storage A purely mechanical change to split the renaming from the actual generalization. Flags/consts: SK_STORAGE_CREATE_FLAG_MASK BPF_LOCAL_STORAGE_CREATE_FLAG_MASK BPF_SK_STORAGE_CACHE_SIZE BPF_LOCAL_STORAGE_CACHE_SIZE MAX_VALUE_SIZE BPF_LOCAL_STORAGE_MAX_VALUE_SIZE Structs: bucket bpf_local_storage_map_bucket bpf_sk_storage_map bpf_local_storage_map bpf_sk_storage_data bpf_local_storage_data bpf_sk_storage_elem bpf_local_storage_elem bpf_sk_storage bpf_local_storage The "sk" member in bpf_local_storage is also updated to "owner" in preparation for changing the type to void * in a subsequent patch. Functions: selem_linked_to_sk selem_linked_to_storage selem_alloc bpf_selem_alloc __selem_unlink_sk bpf_selem_unlink_storage_nolock __selem_link_sk bpf_selem_link_storage_nolock selem_unlink_sk __bpf_selem_unlink_storage sk_storage_update bpf_local_storage_update __sk_storage_lookup bpf_local_storage_lookup bpf_sk_storage_map_free bpf_local_storage_map_free bpf_sk_storage_map_alloc bpf_local_storage_map_alloc bpf_sk_storage_map_alloc_check bpf_local_storage_map_alloc_check bpf_sk_storage_map_check_btf bpf_local_storage_map_check_btf Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-2-kpsingh@chromium.org --- include/net/sock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 064637d1ddf6..18423cc9cde8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -246,7 +246,7 @@ struct sock_common { /* public: */ }; -struct bpf_sk_storage; +struct bpf_local_storage; /** * struct sock - network layer representation of sockets @@ -517,7 +517,7 @@ struct sock { void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL - struct bpf_sk_storage __rcu *sk_bpf_storage; + struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; }; -- cgit v1.2.3 From 4cc9ce4e739961a7b9e6b2f3b27a72124d356373 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:14 +0200 Subject: bpf: Generalize caching for sk_storage. Provide the a ability to define local storage caches on a per-object type basis. The caches and caching indices for different objects should not be inter-mixed as suggested in: https://lore.kernel.org/bpf/20200630193441.kdwnkestulg5erii@kafai-mbp.dhcp.thefacebook.com/ "Caching a sk-storage at idx=0 of a sk should not stop an inode-storage to be cached at the same idx of a inode." Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-3-kpsingh@chromium.org --- include/net/bpf_sk_storage.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 5036c94c0503..950c5aaba15e 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -3,6 +3,9 @@ #ifndef _BPF_SK_STORAGE_H #define _BPF_SK_STORAGE_H +#include +#include + struct sock; void bpf_sk_storage_free(struct sock *sk); @@ -15,6 +18,22 @@ struct sk_buff; struct nlattr; struct sock; +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_cache { + spinlock_t idx_lock; + u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; +}; + +#define DEFINE_BPF_STORAGE_CACHE(name) \ +static struct bpf_local_storage_cache name = { \ + .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx); + #ifdef CONFIG_BPF_SYSCALL int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk); struct bpf_sk_storage_diag * -- cgit v1.2.3 From f836a56e84ffc9f1a1cd73f77e10404ca46a4616 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:15 +0200 Subject: bpf: Generalize bpf_sk_storage Refactor the functionality in bpf_sk_storage.c so that concept of storage linked to kernel objects can be extended to other objects like inode, task_struct etc. Each new local storage will still be a separate map and provide its own set of helpers. This allows for future object specific extensions and still share a lot of the underlying implementation. This includes the changes suggested by Martin in: https://lore.kernel.org/bpf/20200725013047.4006241-1-kafai@fb.com/ adding new map operations to support bpf_local_storage maps: * storages for different kernel objects to optionally have different memory charging strategy (map_local_storage_charge, map_local_storage_uncharge) * Functionality to extract the storage pointer from a pointer to the owning object (map_owner_storage_ptr) Co-developed-by: Martin KaFai Lau Signed-off-by: Martin KaFai Lau Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200825182919.1118197-4-kpsingh@chromium.org --- include/linux/bpf.h | 8 +++++++ include/net/bpf_sk_storage.h | 52 ++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/bpf.h | 8 +++++-- 3 files changed, 66 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 81f38e2fda78..8c443b93ac11 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -34,6 +34,8 @@ struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; +struct bpf_local_storage; +struct bpf_local_storage_map; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -104,6 +106,12 @@ struct bpf_map_ops { __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + /* Functions called by bpf_local_storage maps */ + int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 950c5aaba15e..9e631b5466e3 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -3,8 +3,15 @@ #ifndef _BPF_SK_STORAGE_H #define _BPF_SK_STORAGE_H +#include +#include +#include #include #include +#include +#include +#include +#include struct sock; @@ -13,6 +20,7 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +struct bpf_local_storage_elem; struct bpf_sk_storage_diag; struct sk_buff; struct nlattr; @@ -34,6 +42,50 @@ u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, u16 idx); +/* Helper functions for bpf_local_storage */ +int bpf_local_storage_map_alloc_check(union bpf_attr *attr); + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit); + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type); + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem); + +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_omem); + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem); + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem); + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, + bool charge_mem); + +int +bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem); + +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags); + #ifdef CONFIG_BPF_SYSCALL int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk); struct bpf_sk_storage_diag * diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 544b89a64918..2cbd137eed86 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3765,9 +3765,13 @@ enum { BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), }; -/* BPF_FUNC_sk_storage_get flags */ +/* BPF_FUNC__storage_get flags */ enum { - BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), + BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0), + /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility + * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead. + */ + BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE, }; /* BPF_FUNC_read_branch_records flags. */ -- cgit v1.2.3 From 450af8d0f6be2e7dd2a528a3fb054bb726bf1747 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:16 +0200 Subject: bpf: Split bpf_local_storage to bpf_sk_storage A purely mechanical change: bpf_sk_storage.c = bpf_sk_storage.c + bpf_local_storage.c bpf_sk_storage.h = bpf_sk_storage.h + bpf_local_storage.h Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-5-kpsingh@chromium.org --- include/linux/bpf_local_storage.h | 163 ++++++++++++++++++++++++++++++++++++++ include/net/bpf_sk_storage.h | 61 +------------- 2 files changed, 164 insertions(+), 60 deletions(-) create mode 100644 include/linux/bpf_local_storage.h (limited to 'include') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h new file mode 100644 index 000000000000..b2c9463f36a1 --- /dev/null +++ b/include/linux/bpf_local_storage.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2019 Facebook + * Copyright 2020 Google LLC. + */ + +#ifndef _BPF_LOCAL_STORAGE_H +#define _BPF_LOCAL_STORAGE_H + +#include +#include +#include +#include +#include +#include + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_map_bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* Thp map is not the primary owner of a bpf_local_storage_elem. + * Instead, the container object (eg. sk->sk_bpf_storage) is. + * + * The map (bpf_local_storage_map) is for two purposes + * 1. Define the size of the "local storage". It is + * the map's value_size. + * + * 2. Maintain a list to keep track of all elems such + * that they can be cleaned up during the map destruction. + * + * When a bpf local storage is being looked up for a + * particular object, the "bpf_map" pointer is actually used + * as the "key" to search in the list of elem in + * the respective bpf_local_storage owned by the object. + * + * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer + * as the searching key. + */ +struct bpf_local_storage_map { + struct bpf_map map; + /* Lookup elem does not require accessing the map. + * + * Updating/Deleting requires a bucket lock to + * link/unlink the elem from the map. Having + * multiple buckets to improve contention. + */ + struct bpf_local_storage_map_bucket *buckets; + u32 bucket_log; + u16 elem_size; + u16 cache_idx; +}; + +struct bpf_local_storage_data { + /* smap is used as the searching key when looking up + * from the object's bpf_local_storage. + * + * Put it in the same cacheline as the data to minimize + * the number of cachelines access during the cache hit case. + */ + struct bpf_local_storage_map __rcu *smap; + u8 data[] __aligned(8); +}; + +/* Linked to bpf_local_storage and bpf_local_storage_map */ +struct bpf_local_storage_elem { + struct hlist_node map_node; /* Linked to bpf_local_storage_map */ + struct hlist_node snode; /* Linked to bpf_local_storage */ + struct bpf_local_storage __rcu *local_storage; + struct rcu_head rcu; + /* 8 bytes hole */ + /* The data is stored in aother cacheline to minimize + * the number of cachelines access during a cache hit. + */ + struct bpf_local_storage_data sdata ____cacheline_aligned; +}; + +struct bpf_local_storage { + struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_local_storage_elem */ + void *owner; /* The object that owns the above "list" of + * bpf_local_storage_elem. + */ + struct rcu_head rcu; + raw_spinlock_t lock; /* Protect adding/removing from the "list" */ +}; + +/* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ +#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \ + min_t(u32, \ + (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \ + sizeof(struct bpf_local_storage_elem)), \ + (U16_MAX - sizeof(struct bpf_local_storage_elem))) + +#define SELEM(_SDATA) \ + container_of((_SDATA), struct bpf_local_storage_elem, sdata) +#define SDATA(_SELEM) (&(_SELEM)->sdata) + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_cache { + spinlock_t idx_lock; + u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; +}; + +#define DEFINE_BPF_STORAGE_CACHE(name) \ +static struct bpf_local_storage_cache name = { \ + .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx); + +/* Helper functions for bpf_local_storage */ +int bpf_local_storage_map_alloc_check(union bpf_attr *attr); + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit); + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type); + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem); + +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_omem); + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem); + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem); + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, + bool charge_mem); + +int +bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem); + +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags); + +#endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 9e631b5466e3..3c516dd07caf 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -12,6 +12,7 @@ #include #include #include +#include struct sock; @@ -26,66 +27,6 @@ struct sk_buff; struct nlattr; struct sock; -#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 - -struct bpf_local_storage_cache { - spinlock_t idx_lock; - u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; -}; - -#define DEFINE_BPF_STORAGE_CACHE(name) \ -static struct bpf_local_storage_cache name = { \ - .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ -} - -u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); -void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, - u16 idx); - -/* Helper functions for bpf_local_storage */ -int bpf_local_storage_map_alloc_check(union bpf_attr *attr); - -struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); - -struct bpf_local_storage_data * -bpf_local_storage_lookup(struct bpf_local_storage *local_storage, - struct bpf_local_storage_map *smap, - bool cacheit_lockit); - -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); - -int bpf_local_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type); - -void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem); - -bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_omem); - -void bpf_selem_unlink(struct bpf_local_storage_elem *selem); - -void bpf_selem_link_map(struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *selem); - -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); - -struct bpf_local_storage_elem * -bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem); - -int -bpf_local_storage_alloc(void *owner, - struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *first_selem); - -struct bpf_local_storage_data * -bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags); - #ifdef CONFIG_BPF_SYSCALL int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk); struct bpf_sk_storage_diag * -- cgit v1.2.3 From 8ea636848aca35b9f97c5b5dee30225cf2dd0fe6 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:17 +0200 Subject: bpf: Implement bpf_local_storage for inodes Similar to bpf_local_storage for sockets, add local storage for inodes. The life-cycle of storage is managed with the life-cycle of the inode. i.e. the storage is destroyed along with the owning inode. The BPF LSM allocates an __rcu pointer to the bpf_local_storage in the security blob which are now stackable and can co-exist with other LSMs. Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200825182919.1118197-6-kpsingh@chromium.org --- include/linux/bpf_lsm.h | 29 +++++++++++++++++++++++++++++ include/linux/bpf_types.h | 3 +++ include/uapi/linux/bpf.h | 40 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 71 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index af74712af585..aaacb6aafc87 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -17,9 +17,28 @@ #include #undef LSM_HOOK +struct bpf_storage_blob { + struct bpf_local_storage __rcu *storage; +}; + +extern struct lsm_blob_sizes bpf_lsm_blob_sizes; + int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog); +static inline struct bpf_storage_blob *bpf_inode( + const struct inode *inode) +{ + if (unlikely(!inode->i_security)) + return NULL; + + return inode->i_security + bpf_lsm_blob_sizes.lbs_inode; +} + +extern const struct bpf_func_proto bpf_inode_storage_get_proto; +extern const struct bpf_func_proto bpf_inode_storage_delete_proto; +void bpf_inode_storage_free(struct inode *inode); + #else /* !CONFIG_BPF_LSM */ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, @@ -28,6 +47,16 @@ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return -EOPNOTSUPP; } +static inline struct bpf_storage_blob *bpf_inode( + const struct inode *inode) +{ + return NULL; +} + +static inline void bpf_inode_storage_free(struct inode *inode) +{ +} + #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a52a5688418e..2e6f568377f1 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -107,6 +107,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif +#ifdef CONFIG_BPF_LSM +BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2cbd137eed86..b6bfcd085a76 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -155,6 +155,7 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP_HASH, BPF_MAP_TYPE_STRUCT_OPS, BPF_MAP_TYPE_RINGBUF, + BPF_MAP_TYPE_INODE_STORAGE, }; /* Note that tracing related programs such as @@ -3509,6 +3510,41 @@ union bpf_attr { * * **-EPERM** This helper cannot be used under the * current sock_ops->op. + * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) + * Description + * Get a bpf_local_storage from an *inode*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *inode* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this + * helper enforces the key must be an inode and the map must also + * be a **BPF_MAP_TYPE_INODE_STORAGE**. + * + * Underneath, the value is stored locally at *inode* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *inode*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * int bpf_inode_storage_delete(struct bpf_map *map, void *inode) + * Description + * Delete a bpf_local_storage from an *inode*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3655,7 +3691,9 @@ union bpf_attr { FN(get_task_stack), \ FN(load_hdr_opt), \ FN(store_hdr_opt), \ - FN(reserve_hdr_opt), + FN(reserve_hdr_opt), \ + FN(inode_storage_get), \ + FN(inode_storage_delete), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 30897832d8b97e93833fb52c0a02951db3692ed2 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 25 Aug 2020 20:29:18 +0200 Subject: bpf: Allow local storage to be used from LSM programs Adds support for both bpf_{sk, inode}_storage_{get, delete} to be used in LSM programs. These helpers are not used for tracing programs (currently) as their usage is tied to the life-cycle of the object and should only be used where the owning object won't be freed (when the owning object is passed as an argument to the LSM hook). Thus, they are safer to use in LSM hooks than tracing. Usage of local storage in tracing programs will probably follow a per function based whitelist approach. Since the UAPI helper signature for bpf_sk_storage expect a bpf_sock, it, leads to a compilation warning for LSM programs, it's also updated to accept a void * pointer instead. Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200825182919.1118197-7-kpsingh@chromium.org --- include/net/bpf_sk_storage.h | 2 ++ include/uapi/linux/bpf.h | 7 +++++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 3c516dd07caf..119f4c9c3a9c 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -20,6 +20,8 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +extern const struct bpf_func_proto sk_storage_get_btf_proto; +extern const struct bpf_func_proto sk_storage_delete_btf_proto; struct bpf_local_storage_elem; struct bpf_sk_storage_diag; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b6bfcd085a76..0e1cdf806fe1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2808,7 +2808,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags) * Description * Get a bpf-local-storage from a *sk*. * @@ -2824,6 +2824,9 @@ union bpf_attr { * "type". The bpf-local-storage "type" (i.e. the *map*) is * searched against all bpf-local-storages residing at *sk*. * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be * used such that a new bpf-local-storage will be * created if one does not exist. *value* can be used @@ -2836,7 +2839,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, void *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return -- cgit v1.2.3 From 6298399bfc101f8e8cf35a916f26aa32bdf04278 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Aug 2020 21:21:13 +0200 Subject: bpf: Move btf_resolve_size into __btf_resolve_size Moving btf_resolve_size into __btf_resolve_size and keeping btf_resolve_size public with just first 3 arguments, because the rest of the arguments are not used by outside callers. Following changes are adding more arguments, which are not useful to outside callers. They will be added to the __btf_resolve_size function. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200825192124.710397-4-jolsa@kernel.org --- include/linux/btf.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 8b81fbb4497c..a9af5e7a7ece 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -64,8 +64,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, - u32 *type_size, const struct btf_type **elem_type, - u32 *total_nelems); + u32 *type_size); #define for_each_member(i, struct_type, member) \ for (i = 0, member = btf_type_member(struct_type); \ -- cgit v1.2.3 From faaf4a790d93794b46d67e2fd69b8e5c8cae2d41 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Aug 2020 21:21:18 +0200 Subject: bpf: Add btf_struct_ids_match function Adding btf_struct_ids_match function to check if given address provided by BTF object + offset is also address of another nested BTF object. This allows to pass an argument to helper, which is defined via parent BTF object + offset, like for bpf_d_path (added in following changes): SEC("fentry/filp_close") int BPF_PROG(prog_close, struct file *file, void *id) { ... ret = bpf_d_path(&file->f_path, ... The first bpf_d_path argument is hold by verifier as BTF file object plus offset of f_path member. The btf_struct_ids_match function will walk the struct file object and check if there's nested struct path object on the given offset. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200825192124.710397-9-jolsa@kernel.org --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8c443b93ac11..540f5e6c3788 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1358,6 +1358,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); +bool btf_struct_ids_match(struct bpf_verifier_log *log, + int off, u32 id, u32 need_type_id); int btf_resolve_helper_id(struct bpf_verifier_log *log, const struct bpf_func_proto *fn, int); -- cgit v1.2.3 From eae2e83e62633a2659e3bc690facba1c2fc9c45b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Aug 2020 21:21:19 +0200 Subject: bpf: Add BTF_SET_START/END macros Adding support to define sorted set of BTF ID values. Following defines sorted set of BTF ID values: BTF_SET_START(btf_allowlist_d_path) BTF_ID(func, vfs_truncate) BTF_ID(func, vfs_fallocate) BTF_ID(func, dentry_open) BTF_ID(func, vfs_getattr) BTF_ID(func, filp_close) BTF_SET_END(btf_allowlist_d_path) It defines following 'struct btf_id_set' variable to access values and count: struct btf_id_set btf_allowlist_d_path; Adding 'allowed' callback to struct bpf_func_proto, to allow verifier the check on allowed callers. Adding btf_id_set_contains function, which will be used by allowed callbacks to verify the caller's BTF ID value is within allowed set. Also removing extra '\' in __BTF_ID_LIST macro. Added BTF_SET_START_GLOBAL macro for global sets. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200825192124.710397-10-jolsa@kernel.org --- include/linux/bpf.h | 4 ++++ include/linux/btf_ids.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 54 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 540f5e6c3788..a6131d95e31e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -317,6 +317,7 @@ struct bpf_func_proto { * for this argument. */ int *ret_btf_id; /* return value btf_id */ + bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -1878,4 +1879,7 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +struct btf_id_set; +bool btf_id_set_contains(struct btf_id_set *set, u32 id); + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 4867d549e3c1..210b086188a3 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,11 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +struct btf_id_set { + u32 cnt; + u32 ids[]; +}; + #ifdef CONFIG_DEBUG_INFO_BTF #include /* for __PASTE */ @@ -62,7 +67,7 @@ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ "." #scope " " #name "; \n" \ #name ":; \n" \ -".popsection; \n"); \ +".popsection; \n"); #define BTF_ID_LIST(name) \ __BTF_ID_LIST(name, local) \ @@ -88,12 +93,56 @@ asm( \ ".zero 4 \n" \ ".popsection; \n"); +/* + * The BTF_SET_START/END macros pair defines sorted list of + * BTF IDs plus its members count, with following layout: + * + * BTF_SET_START(list) + * BTF_ID(type1, name1) + * BTF_ID(type2, name2) + * BTF_SET_END(list) + * + * __BTF_ID__set__list: + * .zero 4 + * list: + * __BTF_ID__type1__name1__3: + * .zero 4 + * __BTF_ID__type2__name2__4: + * .zero 4 + * + */ +#define __BTF_SET_START(name, scope) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +"." #scope " __BTF_ID__set__" #name "; \n" \ +"__BTF_ID__set__" #name ":; \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#define BTF_SET_START(name) \ +__BTF_ID_LIST(name, local) \ +__BTF_SET_START(name, local) + +#define BTF_SET_START_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) \ +__BTF_SET_START(name, globl) + +#define BTF_SET_END(name) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".size __BTF_ID__set__" #name ", .-" #name " \n" \ +".popsection; \n"); \ +extern struct btf_id_set name; + #else #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED #define BTF_ID_LIST_GLOBAL(name) u32 name[1]; +#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ -- cgit v1.2.3 From 6e22ab9da79343532cd3cde39df25e5a5478c692 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Aug 2020 21:21:20 +0200 Subject: bpf: Add d_path helper Adding d_path helper function that returns full path for given 'struct path' object, which needs to be the kernel BTF 'path' object. The path is returned in buffer provided 'buf' of size 'sz' and is zero terminated. bpf_d_path(&file->f_path, buf, size); The helper calls directly d_path function, so there's only limited set of function it can be called from. Adding just very modest set for the start. Updating also bpf.h tools uapi header and adding 'path' to bpf_helpers_doc.py script. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20200825192124.710397-11-jolsa@kernel.org --- include/uapi/linux/bpf.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0e1cdf806fe1..0388bc0200b0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3513,6 +3513,7 @@ union bpf_attr { * * **-EPERM** This helper cannot be used under the * current sock_ops->op. + * * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) * Description * Get a bpf_local_storage from an *inode*. @@ -3548,6 +3549,18 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf_local_storage cannot be found. + * + * long bpf_d_path(struct path *path, char *buf, u32 sz) + * Description + * Return full path for given 'struct path' object, which + * needs to be the kernel BTF 'path' object. The path is + * returned in the provided buffer 'buf' of size 'sz' and + * is zero terminated. + * + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3697,6 +3710,7 @@ union bpf_attr { FN(reserve_hdr_opt), \ FN(inode_storage_get), \ FN(inode_storage_delete), \ + FN(d_path), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 01ccf592362a984534371b3596d4c953da6a7bb2 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 19 Aug 2020 21:55:05 +0200 Subject: sched: Bring the PF_IO_WORKER and PF_WQ_WORKER bits closer together The bits PF_IO_WORKER and PF_WQ_WORKER are tested together in sched_submit_work() which is considered to be a hot path. If the two bits cross the 8 or 16 bit boundary then most architecture require multiple load instructions in order to create the constant value. Also, such a value can not be encoded within the compare opcode. By moving the bit definition within the same block, the compiler can create/use one immediate value. For some reason gcc-10 on ARM64 requires both bits to be next to each other in order to issue "tst reg, val; bne label". Otherwise the result is "mov reg1, val; tst reg, reg1; bne label". Move PF_VCPU out of the way so that PF_IO_WORKER can be next to PF_WQ_WORKER. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200819195505.y3fxk72sotnrkczi@linutronix.de --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 93ecd930efd3..2bf0af19a62a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1489,9 +1489,10 @@ extern struct pid *cad_pid; /* * Per process flags */ +#define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ -#define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +#define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ @@ -1515,7 +1516,6 @@ extern struct pid *cad_pid; #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ -#define PF_IO_WORKER 0x20000000 /* Task is an IO worker */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ -- cgit v1.2.3 From 8fca9494d4b4d6b57b1398cd473feb308df656db Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 25 Aug 2020 14:32:15 +0100 Subject: sched/topology: Move sd_flag_debug out of linux/sched/topology.h Defining an array in a header imported all over the place clearly is a daft idea, that still didn't stop me from doing it. Leave a declaration of sd_flag_debug in topology.h and move its definition to sched/debug.c. Fixes: b6e862f38672 ("sched/topology: Define and assign sched_domain flag metadata") Reported-by: Andy Shevchenko Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200825133216.9163-1-valentin.schneider@arm.com --- include/linux/sched/topology.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 2d59ca77103e..b9b0dab4d067 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -33,14 +33,13 @@ static const unsigned int SD_DEGENERATE_GROUPS_MASK = #undef SD_FLAG #ifdef CONFIG_SCHED_DEBUG -#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name }, -static const struct { + +struct sd_flag_debug { unsigned int meta_flags; char *name; -} sd_flag_debug[] = { -#include }; -#undef SD_FLAG +extern const struct sd_flag_debug sd_flag_debug[]; + #endif #ifdef CONFIG_SCHED_SMT -- cgit v1.2.3 From 4fc472f1214ef75e5450f207e23ff13af6eecad4 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 25 Aug 2020 14:32:16 +0100 Subject: sched/topology: Move SD_DEGENERATE_GROUPS_MASK out of linux/sched/topology.h SD_DEGENERATE_GROUPS_MASK is only useful for sched/topology.c, but still gets defined for anyone who imports topology.h, leading to a flurry of unused variable warnings. Move it out of the header and place it next to the SD degeneration functions in sched/topology.c. Fixes: 4ee4ea443a5d ("sched/topology: Introduce SD metaflag for flags needing > 1 groups") Reported-by: Andy Shevchenko Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200825133216.9163-2-valentin.schneider@arm.com --- include/linux/sched/topology.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index b9b0dab4d067..9ef7bf686a9f 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -25,13 +25,6 @@ enum { }; #undef SD_FLAG -/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */ -#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) | -static const unsigned int SD_DEGENERATE_GROUPS_MASK = -#include -0; -#undef SD_FLAG - #ifdef CONFIG_SCHED_DEBUG struct sd_flag_debug { -- cgit v1.2.3 From a435b9a14356587cf512ea6473368a579373c74c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Jul 2020 13:00:57 +0200 Subject: locking/refcount: Provide __refcount API to obtain the old value David requested means to obtain the old/previous value from the refcount API for tracing purposes. Duplicate (most of) the API as __refcount*() with an additional 'int *' argument into which, if !NULL, the old value will be stored. Requested-by: David Howells Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200729111120.GA2638@hirez.programming.kicks-ass.net --- include/linux/refcount.h | 65 ++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 57 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 0e3ee25eb156..7fabb1af18e0 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -165,7 +165,7 @@ static inline unsigned int refcount_read(const refcount_t *r) * * Return: false if the passed refcount is 0, true otherwise */ -static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) +static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); @@ -174,12 +174,20 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); + if (oldp) + *oldp = old; + if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } +static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) +{ + return __refcount_add_not_zero(i, r, NULL); +} + /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount @@ -196,16 +204,24 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ -static inline void refcount_add(int i, refcount_t *r) +static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); + if (oldp) + *oldp = old; + if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } +static inline void refcount_add(int i, refcount_t *r) +{ + __refcount_add(i, r, NULL); +} + /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment @@ -219,9 +235,14 @@ static inline void refcount_add(int i, refcount_t *r) * * Return: true if the increment was successful, false otherwise */ +static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) +{ + return __refcount_add_not_zero(1, r, oldp); +} + static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { - return refcount_add_not_zero(1, r); + return __refcount_inc_not_zero(r, NULL); } /** @@ -236,9 +257,14 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ +static inline void __refcount_inc(refcount_t *r, int *oldp) +{ + __refcount_add(1, r, oldp); +} + static inline void refcount_inc(refcount_t *r) { - refcount_add(1, r); + __refcount_inc(r, NULL); } /** @@ -261,10 +287,13 @@ static inline void refcount_inc(refcount_t *r) * * Return: true if the resulting refcount is 0, false otherwise */ -static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) +static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); + if (oldp) + *oldp = old; + if (old == i) { smp_acquire__after_ctrl_dep(); return true; @@ -276,6 +305,11 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) return false; } +static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) +{ + return __refcount_sub_and_test(i, r, NULL); +} + /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount @@ -289,9 +323,14 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) * * Return: true if the resulting refcount is 0, false otherwise */ +static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) +{ + return __refcount_sub_and_test(1, r, oldp); +} + static inline __must_check bool refcount_dec_and_test(refcount_t *r) { - return refcount_sub_and_test(1, r); + return __refcount_dec_and_test(r, NULL); } /** @@ -304,12 +343,22 @@ static inline __must_check bool refcount_dec_and_test(refcount_t *r) * Provides release memory ordering, such that prior loads and stores are done * before. */ -static inline void refcount_dec(refcount_t *r) +static inline void __refcount_dec(refcount_t *r, int *oldp) { - if (unlikely(atomic_fetch_sub_release(1, &r->refs) <= 1)) + int old = atomic_fetch_sub_release(1, &r->refs); + + if (oldp) + *oldp = old; + + if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } +static inline void refcount_dec(refcount_t *r) +{ + __refcount_dec(r, NULL); +} + extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); -- cgit v1.2.3 From a28e884b966e713da29caefbb347efea77367d22 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 16 Aug 2020 17:02:00 -0700 Subject: seqlock: Fix multiple kernel-doc warnings Fix kernel-doc warnings in . ../include/linux/seqlock.h:152: warning: Incorrect use of kernel-doc format: * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t ../include/linux/seqlock.h:164: warning: Incorrect use of kernel-doc format: * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers ../include/linux/seqlock.h:229: warning: Function parameter or member 'seq_name' not described in 'SEQCOUNT_LOCKTYPE_ZERO' ../include/linux/seqlock.h:229: warning: Function parameter or member 'assoc_lock' not described in 'SEQCOUNT_LOCKTYPE_ZERO' ../include/linux/seqlock.h:229: warning: Excess function parameter 'name' description in 'SEQCOUNT_LOCKTYPE_ZERO' ../include/linux/seqlock.h:229: warning: Excess function parameter 'lock' description in 'SEQCOUNT_LOCKTYPE_ZERO' ../include/linux/seqlock.h:695: warning: duplicate section name 'NOTE' Demote kernel-doc notation for the macros "seqcount_LOCKNAME_init()" and "SEQCOUNT_LOCKTYPE()"; scripts/kernel-doc does not handle them correctly. Rename function parameters in SEQCNT_LOCKNAME_ZERO() documentation to match the macro's argument names. Change the macro name in the documentation to SEQCOUNT_LOCKTYPE_ZERO() to match the macro's name. For raw_write_seqcount_latch(), rename the second NOTE: to NOTE2: to prevent a kernel-doc warning. However, the generated output is not quite as nice as it could be for this. Fix a typo: s/LOCKTYPR/LOCKTYPE/ Fixes: 0efc94c5d15c ("seqcount: Compress SEQCNT_LOCKNAME_ZERO()") Fixes: e4e9ab3f9f91 ("seqlock: Fold seqcount_LOCKNAME_init() definition") Fixes: a8772dccb2ec ("seqlock: Fold seqcount_LOCKNAME_t definition") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200817000200.20993-1-rdunlap@infradead.org --- include/linux/seqlock.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 962d9768945f..300cbf312546 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -138,7 +138,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #endif /** - * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated + * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPE associated * @seqcount: The real sequence counter * @lock: Pointer to the associated spinlock * @@ -148,7 +148,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * that the write side critical section is properly serialized. */ -/** +/* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKTYPE @@ -217,7 +217,7 @@ SEQCOUNT_LOCKTYPE(rwlock_t, rwlock, false, s->lock) SEQCOUNT_LOCKTYPE(struct mutex, mutex, true, s->lock) SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base) -/** +/* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKTYPE @@ -688,7 +688,7 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s) * to miss an entire modification sequence, once it resumes it might * observe the new entry. * - * NOTE: + * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. -- cgit v1.2.3 From e918188611f073063415f40fae568fa4d86d9044 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 7 Aug 2020 15:42:20 +0800 Subject: locking: More accurate annotations for read_lock() On the archs using QUEUED_RWLOCKS, read_lock() is not always a recursive read lock, actually it's only recursive if in_interrupt() is true. So change the annotation accordingly to catch more deadlocks. Note we used to treat read_lock() as pure recursive read locks in lib/locking-seftest.c, and this is useful, especially for the lockdep development selftest, so we keep this via a variable to force switching lock annotation for read_lock(). Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200807074238.1632519-2-boqun.feng@gmail.com --- include/linux/lockdep.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 6a584b3e5c74..7cae5ea00d59 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -469,6 +469,20 @@ static inline void print_irqtrace_events(struct task_struct *curr) } #endif +/* Variable used to make lockdep treat read_lock() as recursive in selftests */ +#ifdef CONFIG_DEBUG_LOCKING_API_SELFTESTS +extern unsigned int force_read_lock_recursive; +#else /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ +#define force_read_lock_recursive 0 +#endif /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ + +#ifdef CONFIG_LOCKDEP +extern bool read_lock_is_recursive(void); +#else /* CONFIG_LOCKDEP */ +/* If !LOCKDEP, the value is meaningless */ +#define read_lock_is_recursive() 0 +#endif + /* * For trivial one-depth nesting of a lock-class, the following * global define can be used. (Subsystems with multiple levels @@ -490,7 +504,14 @@ static inline void print_irqtrace_events(struct task_struct *curr) #define spin_release(l, i) lock_release(l, i) #define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) -#define rwlock_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) +#define rwlock_acquire_read(l, s, t, i) \ +do { \ + if (read_lock_is_recursive()) \ + lock_acquire_shared_recursive(l, s, t, NULL, i); \ + else \ + lock_acquire_shared(l, s, t, NULL, i); \ +} while (0) + #define rwlock_release(l, i) lock_release(l, i) #define seqcount_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) -- cgit v1.2.3 From bd76eca10de2eb9998d5125b08e8997cbf5508d5 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 7 Aug 2020 15:42:24 +0800 Subject: lockdep: Reduce the size of lock_list::distance lock_list::distance is always not greater than MAX_LOCK_DEPTH (which is 48 right now), so a u16 will fit. This patch reduces the size of lock_list::distance to save space, so that we can introduce other fields to help detect recursive read lock deadlocks without increasing the size of lock_list structure. Suggested-by: Peter Zijlstra Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200807074238.1632519-6-boqun.feng@gmail.com --- include/linux/lockdep.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 7cae5ea00d59..22750102b5fe 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -54,7 +54,7 @@ struct lock_list { struct lock_class *class; struct lock_class *links_to; const struct lock_trace *trace; - int distance; + u16 distance; /* * The parent field is used to implement breadth-first search, and the -- cgit v1.2.3 From 3454a36d6a39186de508dd43df590a6363364176 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 7 Aug 2020 15:42:25 +0800 Subject: lockdep: Introduce lock_list::dep To add recursive read locks into the dependency graph, we need to store the types of dependencies for the BFS later. There are four types of dependencies: * Exclusive -> Non-recursive dependencies: EN e.g. write_lock(prev) held and try to acquire write_lock(next) or non-recursive read_lock(next), which can be represented as "prev -(EN)-> next" * Shared -> Non-recursive dependencies: SN e.g. read_lock(prev) held and try to acquire write_lock(next) or non-recursive read_lock(next), which can be represented as "prev -(SN)-> next" * Exclusive -> Recursive dependencies: ER e.g. write_lock(prev) held and try to acquire recursive read_lock(next), which can be represented as "prev -(ER)-> next" * Shared -> Recursive dependencies: SR e.g. read_lock(prev) held and try to acquire recursive read_lock(next), which can be represented as "prev -(SR)-> next" So we use 4 bits for the presence of each type in lock_list::dep. Helper functions and macros are also introduced to convert a pair of locks into lock_list::dep bit and maintain the addition of different types of dependencies. Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200807074238.1632519-7-boqun.feng@gmail.com --- include/linux/lockdep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 22750102b5fe..35c8bb0108dd 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -55,6 +55,8 @@ struct lock_list { struct lock_class *links_to; const struct lock_trace *trace; u16 distance; + /* bitmap of different dependencies from head to this */ + u8 dep; /* * The parent field is used to implement breadth-first search, and the -- cgit v1.2.3 From 6971c0f345620aae5e6172207a57b7524603a34e Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 7 Aug 2020 15:42:26 +0800 Subject: lockdep: Extend __bfs() to work with multiple types of dependencies Now we have four types of dependencies in the dependency graph, and not all the pathes carry real dependencies (the dependencies that may cause a deadlock), for example: Given lock A and B, if we have: CPU1 CPU2 ============= ============== write_lock(A); read_lock(B); read_lock(B); write_lock(A); (assuming read_lock(B) is a recursive reader) then we have dependencies A -(ER)-> B, and B -(SN)-> A, and a dependency path A -(ER)-> B -(SN)-> A. In lockdep w/o recursive locks, a dependency path from A to A means a deadlock. However, the above case is obviously not a deadlock, because no one holds B exclusively, therefore no one waits for the other to release B, so who get A first in CPU1 and CPU2 will run non-blockingly. As a result, dependency path A -(ER)-> B -(SN)-> A is not a real/strong dependency that could cause a deadlock. From the observation above, we know that for a dependency path to be real/strong, no two adjacent dependencies can be as -(*R)-> -(S*)->. Now our mission is to make __bfs() traverse only the strong dependency paths, which is simple: we record whether we only have -(*R)-> for the previous lock_list of the path in lock_list::only_xr, and when we pick a dependency in the traverse, we 1) filter out -(S*)-> dependency if the previous lock_list only has -(*R)-> dependency (i.e. ->only_xr is true) and 2) set the next lock_list::only_xr to true if we only have -(*R)-> left after we filter out dependencies based on 1), otherwise, set it to false. With this extension for __bfs(), we now need to initialize the root of __bfs() properly (with a correct ->only_xr), to do so, we introduce some helper functions, which also cleans up a little bit for the __bfs() root initialization code. Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200807074238.1632519-8-boqun.feng@gmail.com --- include/linux/lockdep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 35c8bb0108dd..57d642d378c7 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -57,6 +57,8 @@ struct lock_list { u16 distance; /* bitmap of different dependencies from head to this */ u8 dep; + /* used by BFS to record whether "prev -> this" only has -(*R)-> */ + u8 only_xr; /* * The parent field is used to implement breadth-first search, and the -- cgit v1.2.3 From 76ab546cd8f0c64d4603b2faad4558c5b670561e Mon Sep 17 00:00:00 2001 From: Karol Trzcinski Date: Tue, 25 Aug 2020 16:58:51 -0700 Subject: ASoC: SOF: IPC: make sof_ipc_window monosized This step is needed to add possibility to pack sof_ipc_window inside another one in used FW build tools - for example in extended manifest. Structure reusability leads to easy parsing function reuse, so source code is shorter and easier to maintain. Using structures with constant size is less tricky and properly supported by each toolchain by contrast to variable size elements. This is minor ABI change - backward compatibility is kept. Signed-off-by: Karol Trzcinski Reviewed-by: Guennadi Liakhovetski Reviewed-by: Kai Vehmanen Reviewed-by: Pierre-Louis Bossart Signed-off-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20200825235854.1588034-2-ranjani.sridharan@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/info.h | 2 +- include/uapi/sound/sof/abi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h index 5a55ba8b7e56..313e3e70c630 100644 --- a/include/sound/sof/info.h +++ b/include/sound/sof/info.h @@ -99,7 +99,7 @@ struct sof_ipc_window_elem { struct sof_ipc_window { struct sof_ipc_ext_data_hdr ext_hdr; uint32_t num_windows; - struct sof_ipc_window_elem window[]; + struct sof_ipc_window_elem window[SOF_IPC_MAX_ELEMS]; } __packed; struct sof_ipc_cc_version { diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index d54be303090f..6af32f82fb99 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -26,7 +26,7 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 -#define SOF_ABI_MINOR 16 +#define SOF_ABI_MINOR 17 #define SOF_ABI_PATCH 0 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ -- cgit v1.2.3 From 60b7c1ba289b8ebe4f275b0b381f711e5b60184b Mon Sep 17 00:00:00 2001 From: Karol Trzcinski Date: Tue, 25 Aug 2020 16:58:53 -0700 Subject: ASoC: SOF: ext_manifest: Parse debug ABI version The debug ABI can be extracted from the extended manifest content. This information known at build time does not need to be provided in a mailbox. Signed-off-by: Karol Trzcinski Reviewed-by: Kai Vehmanen Reviewed-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Signed-off-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20200825235854.1588034-4-ranjani.sridharan@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/ext_manifest.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/sound/sof/ext_manifest.h b/include/sound/sof/ext_manifest.h index 04359cda92dc..342e86e54db5 100644 --- a/include/sound/sof/ext_manifest.h +++ b/include/sound/sof/ext_manifest.h @@ -60,6 +60,7 @@ enum sof_ext_man_elem_type { SOF_EXT_MAN_ELEM_FW_VERSION = 0, SOF_EXT_MAN_ELEM_WINDOW = SOF_IPC_EXT_WINDOW, SOF_EXT_MAN_ELEM_CC_VERSION = SOF_IPC_EXT_CC_INFO, + SOF_EXT_MAN_ELEM_DBG_ABI = SOF_IPC_EXT_USER_ABI_INFO, }; /* extended manifest element header */ @@ -92,4 +93,10 @@ struct sof_ext_man_cc_version { struct sof_ipc_cc_version cc_version; } __packed; +struct ext_man_dbg_abi { + struct sof_ext_man_elem_header hdr; + /* use sof_ipc struct because of code re-use */ + struct sof_ipc_user_abi_version dbg_abi; +} __packed; + #endif /* __SOF_FIRMWARE_EXT_MANIFEST_H__ */ -- cgit v1.2.3 From d321571d5e4c2d5511b75e6cf1a910e0a0c2a2e9 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Wed, 26 Aug 2020 18:49:17 +0800 Subject: regulator: mt6360: Add support for MT6360 regulator Add MT6360 regulator driver that contains two BUCKs and six LDOs Signed-off-by: Gene Chen Link: https://lore.kernel.org/r/1598438958-26802-2-git-send-email-gene.chen.richtek@gmail.com Signed-off-by: Mark Brown --- .../dt-bindings/regulator/mediatek,mt6360-regulator.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/dt-bindings/regulator/mediatek,mt6360-regulator.h (limited to 'include') diff --git a/include/dt-bindings/regulator/mediatek,mt6360-regulator.h b/include/dt-bindings/regulator/mediatek,mt6360-regulator.h new file mode 100644 index 000000000000..21c75de700c0 --- /dev/null +++ b/include/dt-bindings/regulator/mediatek,mt6360-regulator.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __DT_BINDINGS_MEDIATEK_MT6360_REGULATOR_H__ +#define __DT_BINDINGS_MEDIATEK_MT6360_REGULATOR_H__ + +/* + * BUCK/LDO mode constants which may be used in devicetree properties + * (eg. regulator-allowed-modes). + * See the manufacturer's datasheet for more information on these modes. + */ + +#define MT6360_OPMODE_LP 2 +#define MT6360_OPMODE_ULP 3 +#define MT6360_OPMODE_NORMAL 0 + +#endif -- cgit v1.2.3 From a2bee00cccf4f2a80412d38328b92f448fd66935 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Tue, 25 Aug 2020 22:17:43 +0200 Subject: spi: pxa2xx: Add SSC2 and SSPSP2 SSP registers Update list of SSP registers with SSC2 and SSPSP2. These registers are utilized by LPT/WPT AudioDSP architecture. While SSC2 shares the same offset (0x40) as SSACDD, description of this register for SSP device present on mentioned AudioDSP is different so define separate constant to avoid any ambiguity. Cc: Andy Shevchenko Signed-off-by: Cezary Rojewski Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200825201743.4926-1-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 6facf27865f9..1608c760fe91 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -186,6 +186,10 @@ #define SSIRF 0x48 /* RX FIFO trigger level */ #define SSIRF_RxThresh(x) ((x) - 1) +/* LPT/WPT SSP */ +#define SSCR2 (0x40) /* SSP Command / Status 2 */ +#define SSPSP2 (0x44) /* SSP Programmable Serial Protocol 2 */ + enum pxa_ssp_type { SSP_UNDEFINED = 0, PXA25x_SSP, /* pxa 210, 250, 255, 26x */ -- cgit v1.2.3 From 24da79902efc4a8443fae09e6c8e25b515bd8db2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Aug 2020 06:50:16 -0700 Subject: inet: remove inet_sk_copy_descendant() This is no longer used, SCTP now uses a private helper. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 11 ----------- include/net/inet_sock.h | 7 ------- 2 files changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a44789d027cc..bac8f4fffbd6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -345,17 +345,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return (struct raw6_sock *)sk; } -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - int ancestor_size = sizeof(struct inet_sock); - - if (sk_from->sk_family == PF_INET6) - ancestor_size += sizeof(struct ipv6_pinfo); - - __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); -} - #define __ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_only_sock(sk) (__ipv6_only_sock(sk)) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a3702d1d4875..89163ef8cf4b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -296,13 +296,6 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to, memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } -#if !(IS_ENABLED(CONFIG_IPV6)) -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - __inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock)); -} -#endif int inet_sk_rebuild_header(struct sock *sk); -- cgit v1.2.3 From b305dfe2e93434b12d438434461b709641f62af4 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 20 Aug 2020 12:47:16 +0200 Subject: media: videodev2.h: RGB BT2020 and HSV are always full range The default RGB quantization range for BT.2020 is full range (just as for all the other RGB pixel encodings), not limited range. Update the V4L2_MAP_QUANTIZATION_DEFAULT macro and documentation accordingly. Also mention that HSV is always full range and cannot be limited range. When RGB BT2020 was introduced in V4L2 it was not clear whether it should be limited or full range, but full range is the right (and consistent) choice. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c7b70ff53bc1..4769628790da 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -375,9 +375,9 @@ enum v4l2_hsv_encoding { enum v4l2_quantization { /* - * The default for R'G'B' quantization is always full range, except - * for the BT2020 colorspace. For Y'CbCr the quantization is always - * limited range, except for COLORSPACE_JPEG: this is full range. + * The default for R'G'B' quantization is always full range. + * For Y'CbCr the quantization is always limited range, except + * for COLORSPACE_JPEG: this is full range. */ V4L2_QUANTIZATION_DEFAULT = 0, V4L2_QUANTIZATION_FULL_RANGE = 1, @@ -386,14 +386,13 @@ enum v4l2_quantization { /* * Determine how QUANTIZATION_DEFAULT should map to a proper quantization. - * This depends on whether the image is RGB or not, the colorspace and the - * Y'CbCr encoding. + * This depends on whether the image is RGB or not, the colorspace. + * The Y'CbCr encoding is not used anymore, but is still there for backwards + * compatibility. */ #define V4L2_MAP_QUANTIZATION_DEFAULT(is_rgb_or_hsv, colsp, ycbcr_enc) \ - (((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \ - V4L2_QUANTIZATION_LIM_RANGE : \ - (((is_rgb_or_hsv) || (colsp) == V4L2_COLORSPACE_JPEG) ? \ - V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE)) + (((is_rgb_or_hsv) || (colsp) == V4L2_COLORSPACE_JPEG) ? \ + V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE) /* * Deprecated names for opRGB colorspace (IEC 61966-2-5) -- cgit v1.2.3 From 5ca937fb5d6870735341d8fdacdd2b49618c35dc Mon Sep 17 00:00:00 2001 From: Subbaraman Narayanamurthy Date: Thu, 13 Aug 2020 11:34:08 -0700 Subject: power: supply: add wireless type Currently, power_supply framework supports only Battery, UPS, Mains and USB power_supply_type. Add wireless power_supply_type so that the drivers which supports wireless can register a power supply class device with POWER_SUPPLY_TYPE_WIRELESS. Signed-off-by: Subbaraman Narayanamurthy Signed-off-by: Guru Das Srinagesh Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index d0684362a392..81a55e974feb 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -186,6 +186,7 @@ enum power_supply_type { POWER_SUPPLY_TYPE_USB_PD, /* Power Delivery Port */ POWER_SUPPLY_TYPE_USB_PD_DRP, /* PD Dual Role Port */ POWER_SUPPLY_TYPE_APPLE_BRICK_ID, /* Apple Charging Method */ + POWER_SUPPLY_TYPE_WIRELESS, /* Wireless */ }; enum power_supply_usb_type { -- cgit v1.2.3 From 45c2044ccbedd48bc2a8cddde9ce7e82f03d588c Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Fri, 21 Aug 2020 17:13:43 +0200 Subject: media: v4l2-tpg: Clamp hue in tpg_s_hue() Setting `hue` by calling tpg_s_hue() directly is risky, since it does not perform range check. Clamp `hue` to the valid range in tpg_s_hue(). Suggested-by: Hans Verkuil Signed-off-by: Peilin Ye Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/tpg/v4l2-tpg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/tpg/v4l2-tpg.h b/include/media/tpg/v4l2-tpg.h index 0b0ddb87380e..181dcbe777f3 100644 --- a/include/media/tpg/v4l2-tpg.h +++ b/include/media/tpg/v4l2-tpg.h @@ -325,6 +325,7 @@ static inline void tpg_s_saturation(struct tpg_data *tpg, static inline void tpg_s_hue(struct tpg_data *tpg, s16 hue) { + hue = clamp_t(s16, hue, -128, 128); if (tpg->hue == hue) return; tpg->hue = hue; -- cgit v1.2.3 From 7f9fb67358a2bcaacbdfeee12e0f19e98c8bdf55 Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Wed, 19 Aug 2020 15:34:56 +0800 Subject: regmap: add Intel SPI Slave to AVMM Bus Bridge support This patch add support for regmap APIs that are intended to be used by the drivers of some SPI slave chips which integrate the "SPI slave to Avalon Master Bridge" (spi-avmm) IP. The spi-avmm IP acts as a bridge to convert encoded streams of bytes from the host to the chip's internal register read/write on Avalon bus. The driver implements the register read/write operations for a generic SPI master to access the sub devices behind spi-avmm bridge. Signed-off-by: Xu Yilun Signed-off-by: Wu Hao Signed-off-by: Matthew Gerlach Signed-off-by: Russ Weight Reviewed-by: Tom Rix Reviewed-by: Luis Claudio R. Goncalves Link: https://lore.kernel.org/r/1597822497-25107-2-git-send-email-yilun.xu@intel.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 1970ed59d49f..d865d8fea535 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -567,6 +567,10 @@ struct regmap *__regmap_init_sdw(struct sdw_slave *sdw, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__regmap_init_spi_avmm(struct spi_device *spi, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__devm_regmap_init(struct device *dev, const struct regmap_bus *bus, @@ -620,6 +624,10 @@ struct regmap *__devm_regmap_init_i3c(struct i3c_device *i3c, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__devm_regmap_init_spi_avmm(struct spi_device *spi, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); /* * Wrapper for regmap_init macros to include a unique lockdep key and name * for each call. No-op if CONFIG_LOCKDEP is not set. @@ -806,6 +814,19 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); __regmap_lockdep_wrapper(__regmap_init_sdw, #config, \ sdw, config) +/** + * regmap_init_spi_avmm() - Initialize register map for Intel SPI Slave + * to AVMM Bus Bridge + * + * @spi: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. + */ +#define regmap_init_spi_avmm(spi, config) \ + __regmap_lockdep_wrapper(__regmap_init_spi_avmm, #config, \ + spi, config) /** * devm_regmap_init() - Initialise managed register map @@ -993,6 +1014,21 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); __regmap_lockdep_wrapper(__devm_regmap_init_i3c, #config, \ i3c, config) +/** + * devm_regmap_init_spi_avmm() - Initialize register map for Intel SPI Slave + * to AVMM Bus Bridge + * + * @spi: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The map will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_spi_avmm(spi, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_spi_avmm, #config, \ + spi, config) + int regmap_mmio_attach_clk(struct regmap *map, struct clk *clk); void regmap_mmio_detach_clk(struct regmap *map); void regmap_exit(struct regmap *map); -- cgit v1.2.3 From e7aaf8748897d88fd1d17bfa461df84cf233d5a9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 26 Aug 2020 18:14:53 +0300 Subject: spi: pxa2xx: Update header block in pxa2xx_ssp.h We have direct users of some headers that are missed and have header included when forward declarations are enough. Update header block in pxa2xx_ssp.h to align with actual usage. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200826151455.55970-1-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 1608c760fe91..ae65fe635934 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -16,10 +16,15 @@ #ifndef __LINUX_SSP_H #define __LINUX_SSP_H -#include +#include #include -#include +#include +#include +#include +struct clk; +struct device; +struct device_node; /* * SSP Serial Port Registers -- cgit v1.2.3 From 410f4cf79f64b1831e207b89f3c7ab08e36aa646 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 26 Aug 2020 18:14:54 +0300 Subject: spi: pxa2xx: Switch to use BIT() and GENMASK() in pxa2xx_ssp.h Switch pxa2xx_ssp.h header to use BIT() and GENMASK(). It's better to read and understand. While here, correct ordering of some definitions. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200826151455.55970-2-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 150 ++++++++++++++++++++++----------------------- 1 file changed, 75 insertions(+), 75 deletions(-) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index ae65fe635934..3f0f275bd630 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -16,6 +16,7 @@ #ifndef __LINUX_SSP_H #define __LINUX_SSP_H +#include #include #include #include @@ -48,130 +49,127 @@ struct device_node; #define SSACDD (0x40) /* SSP Audio Clock Dither Divider */ /* Common PXA2xx bits first */ -#define SSCR0_DSS (0x0000000f) /* Data Size Select (mask) */ +#define SSCR0_DSS GENMASK(3, 0) /* Data Size Select (mask) */ #define SSCR0_DataSize(x) ((x) - 1) /* Data Size Select [4..16] */ -#define SSCR0_FRF (0x00000030) /* FRame Format (mask) */ +#define SSCR0_FRF GENMASK(5, 4) /* FRame Format (mask) */ #define SSCR0_Motorola (0x0 << 4) /* Motorola's Serial Peripheral Interface (SPI) */ #define SSCR0_TI (0x1 << 4) /* Texas Instruments' Synchronous Serial Protocol (SSP) */ #define SSCR0_National (0x2 << 4) /* National Microwire */ -#define SSCR0_ECS (1 << 6) /* External clock select */ -#define SSCR0_SSE (1 << 7) /* Synchronous Serial Port Enable */ +#define SSCR0_ECS BIT(6) /* External clock select */ +#define SSCR0_SSE BIT(7) /* Synchronous Serial Port Enable */ #define SSCR0_SCR(x) ((x) << 8) /* Serial Clock Rate (mask) */ /* PXA27x, PXA3xx */ -#define SSCR0_EDSS (1 << 20) /* Extended data size select */ -#define SSCR0_NCS (1 << 21) /* Network clock select */ -#define SSCR0_RIM (1 << 22) /* Receive FIFO overrrun interrupt mask */ -#define SSCR0_TUM (1 << 23) /* Transmit FIFO underrun interrupt mask */ -#define SSCR0_FRDC (0x07000000) /* Frame rate divider control (mask) */ +#define SSCR0_EDSS BIT(20) /* Extended data size select */ +#define SSCR0_NCS BIT(21) /* Network clock select */ +#define SSCR0_RIM BIT(22) /* Receive FIFO overrrun interrupt mask */ +#define SSCR0_TUM BIT(23) /* Transmit FIFO underrun interrupt mask */ +#define SSCR0_FRDC GENMASK(26, 24) /* Frame rate divider control (mask) */ #define SSCR0_SlotsPerFrm(x) (((x) - 1) << 24) /* Time slots per frame [1..8] */ -#define SSCR0_FPCKE (1 << 29) /* FIFO packing enable */ -#define SSCR0_ACS (1 << 30) /* Audio clock select */ -#define SSCR0_MOD (1 << 31) /* Mode (normal or network) */ - - -#define SSCR1_RIE (1 << 0) /* Receive FIFO Interrupt Enable */ -#define SSCR1_TIE (1 << 1) /* Transmit FIFO Interrupt Enable */ -#define SSCR1_LBM (1 << 2) /* Loop-Back Mode */ -#define SSCR1_SPO (1 << 3) /* Motorola SPI SSPSCLK polarity setting */ -#define SSCR1_SPH (1 << 4) /* Motorola SPI SSPSCLK phase setting */ -#define SSCR1_MWDS (1 << 5) /* Microwire Transmit Data Size */ - -#define SSSR_ALT_FRM_MASK 3 /* Masks the SFRM signal number */ -#define SSSR_TNF (1 << 2) /* Transmit FIFO Not Full */ -#define SSSR_RNE (1 << 3) /* Receive FIFO Not Empty */ -#define SSSR_BSY (1 << 4) /* SSP Busy */ -#define SSSR_TFS (1 << 5) /* Transmit FIFO Service Request */ -#define SSSR_RFS (1 << 6) /* Receive FIFO Service Request */ -#define SSSR_ROR (1 << 7) /* Receive FIFO Overrun */ +#define SSCR0_FPCKE BIT(29) /* FIFO packing enable */ +#define SSCR0_ACS BIT(30) /* Audio clock select */ +#define SSCR0_MOD BIT(31) /* Mode (normal or network) */ + +#define SSCR1_RIE BIT(0) /* Receive FIFO Interrupt Enable */ +#define SSCR1_TIE BIT(1) /* Transmit FIFO Interrupt Enable */ +#define SSCR1_LBM BIT(2) /* Loop-Back Mode */ +#define SSCR1_SPO BIT(3) /* Motorola SPI SSPSCLK polarity setting */ +#define SSCR1_SPH BIT(4) /* Motorola SPI SSPSCLK phase setting */ +#define SSCR1_MWDS BIT(5) /* Microwire Transmit Data Size */ + +#define SSSR_ALT_FRM_MASK GENMASK(1, 0) /* Masks the SFRM signal number */ +#define SSSR_TNF BIT(2) /* Transmit FIFO Not Full */ +#define SSSR_RNE BIT(3) /* Receive FIFO Not Empty */ +#define SSSR_BSY BIT(4) /* SSP Busy */ +#define SSSR_TFS BIT(5) /* Transmit FIFO Service Request */ +#define SSSR_RFS BIT(6) /* Receive FIFO Service Request */ +#define SSSR_ROR BIT(7) /* Receive FIFO Overrun */ #define RX_THRESH_DFLT 8 #define TX_THRESH_DFLT 8 -#define SSSR_TFL_MASK (0xf << 8) /* Transmit FIFO Level mask */ -#define SSSR_RFL_MASK (0xf << 12) /* Receive FIFO Level mask */ +#define SSSR_TFL_MASK GENMASK(11, 8) /* Transmit FIFO Level mask */ +#define SSSR_RFL_MASK GENMASK(15, 12) /* Receive FIFO Level mask */ -#define SSCR1_TFT (0x000003c0) /* Transmit FIFO Threshold (mask) */ +#define SSCR1_TFT GENMASK(9, 6) /* Transmit FIFO Threshold (mask) */ #define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..16] */ -#define SSCR1_RFT (0x00003c00) /* Receive FIFO Threshold (mask) */ +#define SSCR1_RFT GENMASK(13, 10) /* Receive FIFO Threshold (mask) */ #define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..16] */ #define RX_THRESH_CE4100_DFLT 2 #define TX_THRESH_CE4100_DFLT 2 -#define CE4100_SSSR_TFL_MASK (0x3 << 8) /* Transmit FIFO Level mask */ -#define CE4100_SSSR_RFL_MASK (0x3 << 12) /* Receive FIFO Level mask */ +#define CE4100_SSSR_TFL_MASK GENMASK(9, 8) /* Transmit FIFO Level mask */ +#define CE4100_SSSR_RFL_MASK GENMASK(13, 12) /* Receive FIFO Level mask */ -#define CE4100_SSCR1_TFT (0x000000c0) /* Transmit FIFO Threshold (mask) */ +#define CE4100_SSCR1_TFT GENMASK(7, 6) /* Transmit FIFO Threshold (mask) */ #define CE4100_SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..4] */ -#define CE4100_SSCR1_RFT (0x00000c00) /* Receive FIFO Threshold (mask) */ +#define CE4100_SSCR1_RFT GENMASK(11, 10) /* Receive FIFO Threshold (mask) */ #define CE4100_SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..4] */ /* QUARK_X1000 SSCR0 bit definition */ -#define QUARK_X1000_SSCR0_DSS (0x1F << 0) /* Data Size Select (mask) */ +#define QUARK_X1000_SSCR0_DSS GENMASK(4, 0) /* Data Size Select (mask) */ #define QUARK_X1000_SSCR0_DataSize(x) ((x) - 1) /* Data Size Select [4..32] */ -#define QUARK_X1000_SSCR0_FRF (0x3 << 5) /* FRame Format (mask) */ +#define QUARK_X1000_SSCR0_FRF GENMASK(6, 5) /* FRame Format (mask) */ #define QUARK_X1000_SSCR0_Motorola (0x0 << 5) /* Motorola's Serial Peripheral Interface (SPI) */ #define RX_THRESH_QUARK_X1000_DFLT 1 #define TX_THRESH_QUARK_X1000_DFLT 16 -#define QUARK_X1000_SSSR_TFL_MASK (0x1F << 8) /* Transmit FIFO Level mask */ -#define QUARK_X1000_SSSR_RFL_MASK (0x1F << 13) /* Receive FIFO Level mask */ +#define QUARK_X1000_SSSR_TFL_MASK GENMASK(12, 8) /* Transmit FIFO Level mask */ +#define QUARK_X1000_SSSR_RFL_MASK GENMASK(17, 13) /* Receive FIFO Level mask */ -#define QUARK_X1000_SSCR1_TFT (0x1F << 6) /* Transmit FIFO Threshold (mask) */ +#define QUARK_X1000_SSCR1_TFT GENMASK(10, 6) /* Transmit FIFO Threshold (mask) */ #define QUARK_X1000_SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..32] */ -#define QUARK_X1000_SSCR1_RFT (0x1F << 11) /* Receive FIFO Threshold (mask) */ +#define QUARK_X1000_SSCR1_RFT GENMASK(15, 11) /* Receive FIFO Threshold (mask) */ #define QUARK_X1000_SSCR1_RxTresh(x) (((x) - 1) << 11) /* level [1..32] */ -#define QUARK_X1000_SSCR1_STRF (1 << 17) /* Select FIFO or EFWR */ -#define QUARK_X1000_SSCR1_EFWR (1 << 16) /* Enable FIFO Write/Read */ +#define QUARK_X1000_SSCR1_EFWR BIT(16) /* Enable FIFO Write/Read */ +#define QUARK_X1000_SSCR1_STRF BIT(17) /* Select FIFO or EFWR */ /* extra bits in PXA255, PXA26x and PXA27x SSP ports */ #define SSCR0_TISSP (1 << 4) /* TI Sync Serial Protocol */ #define SSCR0_PSP (3 << 4) /* PSP - Programmable Serial Protocol */ -#define SSCR1_TTELP (1 << 31) /* TXD Tristate Enable Last Phase */ -#define SSCR1_TTE (1 << 30) /* TXD Tristate Enable */ -#define SSCR1_EBCEI (1 << 29) /* Enable Bit Count Error interrupt */ -#define SSCR1_SCFR (1 << 28) /* Slave Clock free Running */ -#define SSCR1_ECRA (1 << 27) /* Enable Clock Request A */ -#define SSCR1_ECRB (1 << 26) /* Enable Clock request B */ -#define SSCR1_SCLKDIR (1 << 25) /* Serial Bit Rate Clock Direction */ -#define SSCR1_SFRMDIR (1 << 24) /* Frame Direction */ -#define SSCR1_RWOT (1 << 23) /* Receive Without Transmit */ -#define SSCR1_TRAIL (1 << 22) /* Trailing Byte */ -#define SSCR1_TSRE (1 << 21) /* Transmit Service Request Enable */ -#define SSCR1_RSRE (1 << 20) /* Receive Service Request Enable */ -#define SSCR1_TINTE (1 << 19) /* Receiver Time-out Interrupt enable */ -#define SSCR1_PINTE (1 << 18) /* Peripheral Trailing Byte Interrupt Enable */ -#define SSCR1_IFS (1 << 16) /* Invert Frame Signal */ -#define SSCR1_STRF (1 << 15) /* Select FIFO or EFWR */ -#define SSCR1_EFWR (1 << 14) /* Enable FIFO Write/Read */ - -#define SSSR_BCE (1 << 23) /* Bit Count Error */ -#define SSSR_CSS (1 << 22) /* Clock Synchronisation Status */ -#define SSSR_TUR (1 << 21) /* Transmit FIFO Under Run */ -#define SSSR_EOC (1 << 20) /* End Of Chain */ -#define SSSR_TINT (1 << 19) /* Receiver Time-out Interrupt */ -#define SSSR_PINT (1 << 18) /* Peripheral Trailing Byte Interrupt */ +#define SSCR1_EFWR BIT(14) /* Enable FIFO Write/Read */ +#define SSCR1_STRF BIT(15) /* Select FIFO or EFWR */ +#define SSCR1_IFS BIT(16) /* Invert Frame Signal */ +#define SSCR1_PINTE BIT(18) /* Peripheral Trailing Byte Interrupt Enable */ +#define SSCR1_TINTE BIT(19) /* Receiver Time-out Interrupt enable */ +#define SSCR1_RSRE BIT(20) /* Receive Service Request Enable */ +#define SSCR1_TSRE BIT(21) /* Transmit Service Request Enable */ +#define SSCR1_TRAIL BIT(22) /* Trailing Byte */ +#define SSCR1_RWOT BIT(23) /* Receive Without Transmit */ +#define SSCR1_SFRMDIR BIT(24) /* Frame Direction */ +#define SSCR1_SCLKDIR BIT(25) /* Serial Bit Rate Clock Direction */ +#define SSCR1_ECRB BIT(26) /* Enable Clock request B */ +#define SSCR1_ECRA BIT(27) /* Enable Clock Request A */ +#define SSCR1_SCFR BIT(28) /* Slave Clock free Running */ +#define SSCR1_EBCEI BIT(29) /* Enable Bit Count Error interrupt */ +#define SSCR1_TTE BIT(30) /* TXD Tristate Enable */ +#define SSCR1_TTELP BIT(31) /* TXD Tristate Enable Last Phase */ + +#define SSSR_PINT BIT(18) /* Peripheral Trailing Byte Interrupt */ +#define SSSR_TINT BIT(19) /* Receiver Time-out Interrupt */ +#define SSSR_EOC BIT(20) /* End Of Chain */ +#define SSSR_TUR BIT(21) /* Transmit FIFO Under Run */ +#define SSSR_CSS BIT(22) /* Clock Synchronisation Status */ +#define SSSR_BCE BIT(23) /* Bit Count Error */ #define SSPSP_SCMODE(x) ((x) << 0) /* Serial Bit Rate Clock Mode */ -#define SSPSP_SFRMP (1 << 2) /* Serial Frame Polarity */ -#define SSPSP_ETDS (1 << 3) /* End of Transfer data State */ +#define SSPSP_SFRMP BIT(2) /* Serial Frame Polarity */ +#define SSPSP_ETDS BIT(3) /* End of Transfer data State */ #define SSPSP_STRTDLY(x) ((x) << 4) /* Start Delay */ #define SSPSP_DMYSTRT(x) ((x) << 7) /* Dummy Start */ #define SSPSP_SFRMDLY(x) ((x) << 9) /* Serial Frame Delay */ #define SSPSP_SFRMWDTH(x) ((x) << 16) /* Serial Frame Width */ #define SSPSP_DMYSTOP(x) ((x) << 23) /* Dummy Stop */ -#define SSPSP_FSRT (1 << 25) /* Frame Sync Relative Timing */ +#define SSPSP_FSRT BIT(25) /* Frame Sync Relative Timing */ /* PXA3xx */ #define SSPSP_EDMYSTRT(x) ((x) << 26) /* Extended Dummy Start */ #define SSPSP_EDMYSTOP(x) ((x) << 28) /* Extended Dummy Stop */ #define SSPSP_TIMING_MASK (0x7f8001f0) -#define SSACD_SCDB (1 << 3) /* SSPSYSCLK Divider Bypass */ -#define SSACD_ACPS(x) ((x) << 4) /* Audio clock PLL select */ #define SSACD_ACDS(x) ((x) << 0) /* Audio clock divider select */ #define SSACD_ACDS_1 (0) #define SSACD_ACDS_2 (1) @@ -179,14 +177,16 @@ struct device_node; #define SSACD_ACDS_8 (3) #define SSACD_ACDS_16 (4) #define SSACD_ACDS_32 (5) +#define SSACD_SCDB BIT(3) /* SSPSYSCLK Divider Bypass */ #define SSACD_SCDB_4X (0) #define SSACD_SCDB_1X (1) -#define SSACD_SCDX8 (1 << 7) /* SYSCLK division ratio select */ +#define SSACD_ACPS(x) ((x) << 4) /* Audio clock PLL select */ +#define SSACD_SCDX8 BIT(7) /* SYSCLK division ratio select */ /* LPSS SSP */ #define SSITF 0x44 /* TX FIFO trigger level */ +#define SSITF_TxHiThresh(x) (((x) - 1) << 0) #define SSITF_TxLoThresh(x) (((x) - 1) << 8) -#define SSITF_TxHiThresh(x) ((x) - 1) #define SSIRF 0x48 /* RX FIFO trigger level */ #define SSIRF_RxThresh(x) ((x) - 1) -- cgit v1.2.3 From 3a2fd4011a1ecec361498301a27d79d5fef255de Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 26 Aug 2020 18:14:55 +0300 Subject: spi: pxa2xx: Drop useless comment in the pxa2xx_ssp.h No need to have file name inside file. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200826151455.55970-3-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 3f0f275bd630..7f73b26ed22e 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * pxa2xx_ssp.h - * * Copyright (C) 2003 Russell King, All Rights Reserved. * * This driver supports the following PXA CPU/SSP ports:- -- cgit v1.2.3 From f468f21b7af0fa472ff8ff70f10b9b4995ef7eb3 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 26 Aug 2020 15:54:16 +0300 Subject: net: Take common prefetch code structure into a function Many device drivers use the same prefetch code structure to deal with small L1 cacheline size. Take this code into a function and call it from the drivers. Suggested-by: Jakub Kicinski Signed-off-by: Tariq Toukan Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/netdevice.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..b8abe1d7aa0b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2193,6 +2193,22 @@ int netdev_get_num_tc(struct net_device *dev) return dev->num_tc; } +static inline void net_prefetch(void *p) +{ + prefetch(p); +#if L1_CACHE_BYTES < 128 + prefetch((u8 *)p + L1_CACHE_BYTES); +#endif +} + +static inline void net_prefetchw(void *p) +{ + prefetchw(p); +#if L1_CACHE_BYTES < 128 + prefetchw((u8 *)p + L1_CACHE_BYTES); +#endif +} + void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev); int netdev_bind_sb_channel_queue(struct net_device *dev, -- cgit v1.2.3 From f9f890ba2b13ea9ccfffd0e7354c7b64d9109790 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Thu, 30 Jul 2020 18:28:01 +0300 Subject: gpio: dwapb: Add max GPIOs macro Add a new macro DWAPB_MAX_GPIOS which defines the maximum possible number of GPIO lines corresponding to the maximum DW APB GPIO controller port width. Use the new macro instead of number literal 32 where it's applicable. Suggested-by: Andy Shevchenko Signed-off-by: Serge Semin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200730152808.2955-5-Sergey.Semin@baikalelectronics.ru Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-dwapb.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h index ff1be737bad6..0aa5c6720259 100644 --- a/include/linux/platform_data/gpio-dwapb.h +++ b/include/linux/platform_data/gpio-dwapb.h @@ -6,12 +6,14 @@ #ifndef GPIO_DW_APB_H #define GPIO_DW_APB_H +#define DWAPB_MAX_GPIOS 32 + struct dwapb_port_property { struct fwnode_handle *fwnode; unsigned int idx; unsigned int ngpio; unsigned int gpio_base; - int irq[32]; + int irq[DWAPB_MAX_GPIOS]; bool irq_shared; }; -- cgit v1.2.3 From 7c81b7199b79e053db7b909e667f2a88e6c437b0 Mon Sep 17 00:00:00 2001 From: Zhiyong Tao Date: Mon, 17 Aug 2020 08:17:00 +0800 Subject: dt-bindings: pinctrl: mt8192: add pinctrl file This patch adds pinctrl file for mt8192. Signed-off-by: Zhiyong Tao Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20200817001702.1646-2-zhiyong.tao@mediatek.com Signed-off-by: Linus Walleij --- include/dt-bindings/pinctrl/mt8192-pinfunc.h | 1344 ++++++++++++++++++++++++++ 1 file changed, 1344 insertions(+) create mode 100644 include/dt-bindings/pinctrl/mt8192-pinfunc.h (limited to 'include') diff --git a/include/dt-bindings/pinctrl/mt8192-pinfunc.h b/include/dt-bindings/pinctrl/mt8192-pinfunc.h new file mode 100644 index 000000000000..71ffe3a52578 --- /dev/null +++ b/include/dt-bindings/pinctrl/mt8192-pinfunc.h @@ -0,0 +1,1344 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 MediaTek Inc. + * Author: Zhiyong Tao + * + */ + +#ifndef __MT8192_PINFUNC_H +#define __MT8192_PINFUNC_H + +#include "mt65xx.h" + +#define PINMUX_GPIO0__FUNC_GPIO0 (MTK_PIN_NO(0) | 0) +#define PINMUX_GPIO0__FUNC_SPI6_CLK (MTK_PIN_NO(0) | 1) +#define PINMUX_GPIO0__FUNC_I2S5_MCK (MTK_PIN_NO(0) | 2) +#define PINMUX_GPIO0__FUNC_PWM_0 (MTK_PIN_NO(0) | 3) +#define PINMUX_GPIO0__FUNC_TDM_LRCK (MTK_PIN_NO(0) | 4) +#define PINMUX_GPIO0__FUNC_TP_GPIO0_AO (MTK_PIN_NO(0) | 5) +#define PINMUX_GPIO0__FUNC_MD_INT0 (MTK_PIN_NO(0) | 6) + +#define PINMUX_GPIO1__FUNC_GPIO1 (MTK_PIN_NO(1) | 0) +#define PINMUX_GPIO1__FUNC_SPI6_CSB (MTK_PIN_NO(1) | 1) +#define PINMUX_GPIO1__FUNC_I2S5_BCK (MTK_PIN_NO(1) | 2) +#define PINMUX_GPIO1__FUNC_PWM_1 (MTK_PIN_NO(1) | 3) +#define PINMUX_GPIO1__FUNC_TDM_BCK (MTK_PIN_NO(1) | 4) +#define PINMUX_GPIO1__FUNC_TP_GPIO1_AO (MTK_PIN_NO(1) | 5) +#define PINMUX_GPIO1__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(1) | 6) +#define PINMUX_GPIO1__FUNC_DBG_MON_A9 (MTK_PIN_NO(1) | 7) + +#define PINMUX_GPIO2__FUNC_GPIO2 (MTK_PIN_NO(2) | 0) +#define PINMUX_GPIO2__FUNC_SPI6_MI (MTK_PIN_NO(2) | 1) +#define PINMUX_GPIO2__FUNC_I2S5_LRCK (MTK_PIN_NO(2) | 2) +#define PINMUX_GPIO2__FUNC_PWM_2 (MTK_PIN_NO(2) | 3) +#define PINMUX_GPIO2__FUNC_TDM_MCK (MTK_PIN_NO(2) | 4) +#define PINMUX_GPIO2__FUNC_TP_GPIO2_AO (MTK_PIN_NO(2) | 5) +#define PINMUX_GPIO2__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(2) | 6) +#define PINMUX_GPIO2__FUNC_DBG_MON_A10 (MTK_PIN_NO(2) | 7) + +#define PINMUX_GPIO3__FUNC_GPIO3 (MTK_PIN_NO(3) | 0) +#define PINMUX_GPIO3__FUNC_SPI6_MO (MTK_PIN_NO(3) | 1) +#define PINMUX_GPIO3__FUNC_I2S5_DO (MTK_PIN_NO(3) | 2) +#define PINMUX_GPIO3__FUNC_PWM_3 (MTK_PIN_NO(3) | 3) +#define PINMUX_GPIO3__FUNC_TDM_DATA0 (MTK_PIN_NO(3) | 4) +#define PINMUX_GPIO3__FUNC_TP_GPIO3_AO (MTK_PIN_NO(3) | 5) +#define PINMUX_GPIO3__FUNC_CLKM0 (MTK_PIN_NO(3) | 6) +#define PINMUX_GPIO3__FUNC_DBG_MON_A11 (MTK_PIN_NO(3) | 7) + +#define PINMUX_GPIO4__FUNC_GPIO4 (MTK_PIN_NO(4) | 0) +#define PINMUX_GPIO4__FUNC_SPI4_A_CLK (MTK_PIN_NO(4) | 1) +#define PINMUX_GPIO4__FUNC_I2S2_MCK (MTK_PIN_NO(4) | 2) +#define PINMUX_GPIO4__FUNC_DMIC1_CLK (MTK_PIN_NO(4) | 3) +#define PINMUX_GPIO4__FUNC_TDM_DATA1 (MTK_PIN_NO(4) | 4) +#define PINMUX_GPIO4__FUNC_TP_GPIO4_AO (MTK_PIN_NO(4) | 5) +#define PINMUX_GPIO4__FUNC_PCM1_DI (MTK_PIN_NO(4) | 6) +#define PINMUX_GPIO4__FUNC_IDDIG (MTK_PIN_NO(4) | 7) + +#define PINMUX_GPIO5__FUNC_GPIO5 (MTK_PIN_NO(5) | 0) +#define PINMUX_GPIO5__FUNC_SPI4_A_CSB (MTK_PIN_NO(5) | 1) +#define PINMUX_GPIO5__FUNC_I2S2_BCK (MTK_PIN_NO(5) | 2) +#define PINMUX_GPIO5__FUNC_DMIC1_DAT (MTK_PIN_NO(5) | 3) +#define PINMUX_GPIO5__FUNC_TDM_DATA2 (MTK_PIN_NO(5) | 4) +#define PINMUX_GPIO5__FUNC_TP_GPIO5_AO (MTK_PIN_NO(5) | 5) +#define PINMUX_GPIO5__FUNC_PCM1_CLK (MTK_PIN_NO(5) | 6) +#define PINMUX_GPIO5__FUNC_USB_DRVVBUS (MTK_PIN_NO(5) | 7) + +#define PINMUX_GPIO6__FUNC_GPIO6 (MTK_PIN_NO(6) | 0) +#define PINMUX_GPIO6__FUNC_SPI4_A_MI (MTK_PIN_NO(6) | 1) +#define PINMUX_GPIO6__FUNC_I2S2_LRCK (MTK_PIN_NO(6) | 2) +#define PINMUX_GPIO6__FUNC_DMIC_CLK (MTK_PIN_NO(6) | 3) +#define PINMUX_GPIO6__FUNC_TDM_DATA3 (MTK_PIN_NO(6) | 4) +#define PINMUX_GPIO6__FUNC_TP_GPIO6_AO (MTK_PIN_NO(6) | 5) +#define PINMUX_GPIO6__FUNC_PCM1_SYNC (MTK_PIN_NO(6) | 6) + +#define PINMUX_GPIO7__FUNC_GPIO7 (MTK_PIN_NO(7) | 0) +#define PINMUX_GPIO7__FUNC_SPI4_A_MO (MTK_PIN_NO(7) | 1) +#define PINMUX_GPIO7__FUNC_I2S2_DI (MTK_PIN_NO(7) | 2) +#define PINMUX_GPIO7__FUNC_DMIC_DAT (MTK_PIN_NO(7) | 3) +#define PINMUX_GPIO7__FUNC_WIFI_TXD (MTK_PIN_NO(7) | 4) +#define PINMUX_GPIO7__FUNC_TP_GPIO7_AO (MTK_PIN_NO(7) | 5) +#define PINMUX_GPIO7__FUNC_PCM1_DO0 (MTK_PIN_NO(7) | 6) + +#define PINMUX_GPIO8__FUNC_GPIO8 (MTK_PIN_NO(8) | 0) +#define PINMUX_GPIO8__FUNC_SRCLKENAI1 (MTK_PIN_NO(8) | 1) +#define PINMUX_GPIO8__FUNC_I2S2_DI2 (MTK_PIN_NO(8) | 2) +#define PINMUX_GPIO8__FUNC_KPCOL2 (MTK_PIN_NO(8) | 3) +#define PINMUX_GPIO8__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(8) | 4) +#define PINMUX_GPIO8__FUNC_CLKM1 (MTK_PIN_NO(8) | 5) +#define PINMUX_GPIO8__FUNC_PCM1_DO1 (MTK_PIN_NO(8) | 6) +#define PINMUX_GPIO8__FUNC_DBG_MON_A12 (MTK_PIN_NO(8) | 7) + +#define PINMUX_GPIO9__FUNC_GPIO9 (MTK_PIN_NO(9) | 0) +#define PINMUX_GPIO9__FUNC_SRCLKENAI0 (MTK_PIN_NO(9) | 1) +#define PINMUX_GPIO9__FUNC_DVFSRC_EXT_REQ (MTK_PIN_NO(9) | 2) +#define PINMUX_GPIO9__FUNC_KPROW2 (MTK_PIN_NO(9) | 3) +#define PINMUX_GPIO9__FUNC_CMMCLK4 (MTK_PIN_NO(9) | 4) +#define PINMUX_GPIO9__FUNC_CLKM3 (MTK_PIN_NO(9) | 5) +#define PINMUX_GPIO9__FUNC_PCM1_DO2 (MTK_PIN_NO(9) | 6) +#define PINMUX_GPIO9__FUNC_DBG_MON_A13 (MTK_PIN_NO(9) | 7) + +#define PINMUX_GPIO10__FUNC_GPIO10 (MTK_PIN_NO(10) | 0) +#define PINMUX_GPIO10__FUNC_MSDC2_CLK (MTK_PIN_NO(10) | 1) +#define PINMUX_GPIO10__FUNC_SPI4_B_CLK (MTK_PIN_NO(10) | 2) +#define PINMUX_GPIO10__FUNC_I2S8_MCK (MTK_PIN_NO(10) | 3) +#define PINMUX_GPIO10__FUNC_MD_INT0 (MTK_PIN_NO(10) | 5) +#define PINMUX_GPIO10__FUNC_TP_GPIO8_AO (MTK_PIN_NO(10) | 6) + +#define PINMUX_GPIO11__FUNC_GPIO11 (MTK_PIN_NO(11) | 0) +#define PINMUX_GPIO11__FUNC_MSDC2_CMD (MTK_PIN_NO(11) | 1) +#define PINMUX_GPIO11__FUNC_SPI4_B_CSB (MTK_PIN_NO(11) | 2) +#define PINMUX_GPIO11__FUNC_I2S8_BCK (MTK_PIN_NO(11) | 3) +#define PINMUX_GPIO11__FUNC_PCIE_CLKREQ_N (MTK_PIN_NO(11) | 4) +#define PINMUX_GPIO11__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(11) | 5) +#define PINMUX_GPIO11__FUNC_TP_GPIO9_AO (MTK_PIN_NO(11) | 6) + +#define PINMUX_GPIO12__FUNC_GPIO12 (MTK_PIN_NO(12) | 0) +#define PINMUX_GPIO12__FUNC_MSDC2_DAT3 (MTK_PIN_NO(12) | 1) +#define PINMUX_GPIO12__FUNC_SPI4_B_MI (MTK_PIN_NO(12) | 2) +#define PINMUX_GPIO12__FUNC_I2S8_LRCK (MTK_PIN_NO(12) | 3) +#define PINMUX_GPIO12__FUNC_DMIC1_CLK (MTK_PIN_NO(12) | 4) +#define PINMUX_GPIO12__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(12) | 5) +#define PINMUX_GPIO12__FUNC_TP_GPIO10_AO (MTK_PIN_NO(12) | 6) + +#define PINMUX_GPIO13__FUNC_GPIO13 (MTK_PIN_NO(13) | 0) +#define PINMUX_GPIO13__FUNC_MSDC2_DAT0 (MTK_PIN_NO(13) | 1) +#define PINMUX_GPIO13__FUNC_SPI4_B_MO (MTK_PIN_NO(13) | 2) +#define PINMUX_GPIO13__FUNC_I2S8_DI (MTK_PIN_NO(13) | 3) +#define PINMUX_GPIO13__FUNC_DMIC1_DAT (MTK_PIN_NO(13) | 4) +#define PINMUX_GPIO13__FUNC_ANT_SEL10 (MTK_PIN_NO(13) | 5) +#define PINMUX_GPIO13__FUNC_TP_GPIO11_AO (MTK_PIN_NO(13) | 6) + +#define PINMUX_GPIO14__FUNC_GPIO14 (MTK_PIN_NO(14) | 0) +#define PINMUX_GPIO14__FUNC_MSDC2_DAT2 (MTK_PIN_NO(14) | 1) +#define PINMUX_GPIO14__FUNC_IDDIG (MTK_PIN_NO(14) | 2) +#define PINMUX_GPIO14__FUNC_SCL_6306 (MTK_PIN_NO(14) | 3) +#define PINMUX_GPIO14__FUNC_PCIE_PERESET_N (MTK_PIN_NO(14) | 4) +#define PINMUX_GPIO14__FUNC_ANT_SEL11 (MTK_PIN_NO(14) | 5) +#define PINMUX_GPIO14__FUNC_TP_GPIO12_AO (MTK_PIN_NO(14) | 6) + +#define PINMUX_GPIO15__FUNC_GPIO15 (MTK_PIN_NO(15) | 0) +#define PINMUX_GPIO15__FUNC_MSDC2_DAT1 (MTK_PIN_NO(15) | 1) +#define PINMUX_GPIO15__FUNC_USB_DRVVBUS (MTK_PIN_NO(15) | 2) +#define PINMUX_GPIO15__FUNC_SDA_6306 (MTK_PIN_NO(15) | 3) +#define PINMUX_GPIO15__FUNC_PCIE_WAKE_N (MTK_PIN_NO(15) | 4) +#define PINMUX_GPIO15__FUNC_ANT_SEL12 (MTK_PIN_NO(15) | 5) +#define PINMUX_GPIO15__FUNC_TP_GPIO13_AO (MTK_PIN_NO(15) | 6) + +#define PINMUX_GPIO16__FUNC_GPIO16 (MTK_PIN_NO(16) | 0) +#define PINMUX_GPIO16__FUNC_SRCLKENAI1 (MTK_PIN_NO(16) | 1) +#define PINMUX_GPIO16__FUNC_IDDIG (MTK_PIN_NO(16) | 2) +#define PINMUX_GPIO16__FUNC_TP_GPIO14_AO (MTK_PIN_NO(16) | 3) +#define PINMUX_GPIO16__FUNC_KPCOL2 (MTK_PIN_NO(16) | 4) +#define PINMUX_GPIO16__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(16) | 5) +#define PINMUX_GPIO16__FUNC_SPI7_A_MI (MTK_PIN_NO(16) | 6) +#define PINMUX_GPIO16__FUNC_DBG_MON_A0 (MTK_PIN_NO(16) | 7) + +#define PINMUX_GPIO17__FUNC_GPIO17 (MTK_PIN_NO(17) | 0) +#define PINMUX_GPIO17__FUNC_SRCLKENAI0 (MTK_PIN_NO(17) | 1) +#define PINMUX_GPIO17__FUNC_USB_DRVVBUS (MTK_PIN_NO(17) | 2) +#define PINMUX_GPIO17__FUNC_TP_GPIO15_AO (MTK_PIN_NO(17) | 3) +#define PINMUX_GPIO17__FUNC_KPROW2 (MTK_PIN_NO(17) | 4) +#define PINMUX_GPIO17__FUNC_SPI7_A_MO (MTK_PIN_NO(17) | 6) +#define PINMUX_GPIO17__FUNC_DBG_MON_A1 (MTK_PIN_NO(17) | 7) + +#define PINMUX_GPIO18__FUNC_GPIO18 (MTK_PIN_NO(18) | 0) +#define PINMUX_GPIO18__FUNC_SRCLKENAI0 (MTK_PIN_NO(18) | 1) +#define PINMUX_GPIO18__FUNC_SPI4_C_MI (MTK_PIN_NO(18) | 2) +#define PINMUX_GPIO18__FUNC_SPI1_B_MI (MTK_PIN_NO(18) | 3) +#define PINMUX_GPIO18__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(18) | 4) +#define PINMUX_GPIO18__FUNC_ANT_SEL10 (MTK_PIN_NO(18) | 5) +#define PINMUX_GPIO18__FUNC_MD_INT0 (MTK_PIN_NO(18) | 6) +#define PINMUX_GPIO18__FUNC_DBG_MON_B2 (MTK_PIN_NO(18) | 7) + +#define PINMUX_GPIO19__FUNC_GPIO19 (MTK_PIN_NO(19) | 0) +#define PINMUX_GPIO19__FUNC_SRCLKENAI1 (MTK_PIN_NO(19) | 1) +#define PINMUX_GPIO19__FUNC_SPI4_C_MO (MTK_PIN_NO(19) | 2) +#define PINMUX_GPIO19__FUNC_SPI1_B_MO (MTK_PIN_NO(19) | 3) +#define PINMUX_GPIO19__FUNC_ANT_SEL11 (MTK_PIN_NO(19) | 5) +#define PINMUX_GPIO19__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(19) | 6) +#define PINMUX_GPIO19__FUNC_DBG_MON_B3 (MTK_PIN_NO(19) | 7) + +#define PINMUX_GPIO20__FUNC_GPIO20 (MTK_PIN_NO(20) | 0) +#define PINMUX_GPIO20__FUNC_SRCLKENAI0 (MTK_PIN_NO(20) | 1) +#define PINMUX_GPIO20__FUNC_SPI4_C_CLK (MTK_PIN_NO(20) | 2) +#define PINMUX_GPIO20__FUNC_SPI1_B_CLK (MTK_PIN_NO(20) | 3) +#define PINMUX_GPIO20__FUNC_PWM_3 (MTK_PIN_NO(20) | 4) +#define PINMUX_GPIO20__FUNC_ANT_SEL12 (MTK_PIN_NO(20) | 5) +#define PINMUX_GPIO20__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(20) | 6) +#define PINMUX_GPIO20__FUNC_DBG_MON_B4 (MTK_PIN_NO(20) | 7) + +#define PINMUX_GPIO21__FUNC_GPIO21 (MTK_PIN_NO(21) | 0) +#define PINMUX_GPIO21__FUNC_SPI4_C_CSB (MTK_PIN_NO(21) | 2) +#define PINMUX_GPIO21__FUNC_SPI1_B_CSB (MTK_PIN_NO(21) | 3) +#define PINMUX_GPIO21__FUNC_IDDIG (MTK_PIN_NO(21) | 6) +#define PINMUX_GPIO21__FUNC_DBG_MON_B5 (MTK_PIN_NO(21) | 7) + +#define PINMUX_GPIO22__FUNC_GPIO22 (MTK_PIN_NO(22) | 0) +#define PINMUX_GPIO22__FUNC_SPI0_C_CLK (MTK_PIN_NO(22) | 2) +#define PINMUX_GPIO22__FUNC_SPI7_B_CLK (MTK_PIN_NO(22) | 3) +#define PINMUX_GPIO22__FUNC_I2S7_BCK (MTK_PIN_NO(22) | 4) +#define PINMUX_GPIO22__FUNC_I2S9_BCK (MTK_PIN_NO(22) | 5) +#define PINMUX_GPIO22__FUNC_SCL_6306 (MTK_PIN_NO(22) | 6) + +#define PINMUX_GPIO23__FUNC_GPIO23 (MTK_PIN_NO(23) | 0) +#define PINMUX_GPIO23__FUNC_SPI0_C_CSB (MTK_PIN_NO(23) | 2) +#define PINMUX_GPIO23__FUNC_SPI7_B_CSB (MTK_PIN_NO(23) | 3) +#define PINMUX_GPIO23__FUNC_I2S7_LRCK (MTK_PIN_NO(23) | 4) +#define PINMUX_GPIO23__FUNC_I2S9_LRCK (MTK_PIN_NO(23) | 5) +#define PINMUX_GPIO23__FUNC_SDA_6306 (MTK_PIN_NO(23) | 6) + +#define PINMUX_GPIO24__FUNC_GPIO24 (MTK_PIN_NO(24) | 0) +#define PINMUX_GPIO24__FUNC_SRCLKENAI1 (MTK_PIN_NO(24) | 1) +#define PINMUX_GPIO24__FUNC_SPI0_C_MI (MTK_PIN_NO(24) | 2) +#define PINMUX_GPIO24__FUNC_SPI7_B_MI (MTK_PIN_NO(24) | 3) +#define PINMUX_GPIO24__FUNC_I2S6_DI (MTK_PIN_NO(24) | 4) +#define PINMUX_GPIO24__FUNC_I2S8_DI (MTK_PIN_NO(24) | 5) +#define PINMUX_GPIO24__FUNC_SPINOR_CS (MTK_PIN_NO(24) | 6) + +#define PINMUX_GPIO25__FUNC_GPIO25 (MTK_PIN_NO(25) | 0) +#define PINMUX_GPIO25__FUNC_SRCLKENAI0 (MTK_PIN_NO(25) | 1) +#define PINMUX_GPIO25__FUNC_SPI0_C_MO (MTK_PIN_NO(25) | 2) +#define PINMUX_GPIO25__FUNC_SPI7_B_MO (MTK_PIN_NO(25) | 3) +#define PINMUX_GPIO25__FUNC_I2S7_DO (MTK_PIN_NO(25) | 4) +#define PINMUX_GPIO25__FUNC_I2S9_DO (MTK_PIN_NO(25) | 5) +#define PINMUX_GPIO25__FUNC_SPINOR_CK (MTK_PIN_NO(25) | 6) + +#define PINMUX_GPIO26__FUNC_GPIO26 (MTK_PIN_NO(26) | 0) +#define PINMUX_GPIO26__FUNC_PWM_2 (MTK_PIN_NO(26) | 1) +#define PINMUX_GPIO26__FUNC_CLKM0 (MTK_PIN_NO(26) | 2) +#define PINMUX_GPIO26__FUNC_USB_DRVVBUS (MTK_PIN_NO(26) | 3) +#define PINMUX_GPIO26__FUNC_SPI5_C_MI (MTK_PIN_NO(26) | 4) +#define PINMUX_GPIO26__FUNC_I2S9_BCK (MTK_PIN_NO(26) | 5) + +#define PINMUX_GPIO27__FUNC_GPIO27 (MTK_PIN_NO(27) | 0) +#define PINMUX_GPIO27__FUNC_PWM_3 (MTK_PIN_NO(27) | 1) +#define PINMUX_GPIO27__FUNC_CLKM1 (MTK_PIN_NO(27) | 2) +#define PINMUX_GPIO27__FUNC_SPI5_C_MO (MTK_PIN_NO(27) | 4) +#define PINMUX_GPIO27__FUNC_I2S9_LRCK (MTK_PIN_NO(27) | 5) +#define PINMUX_GPIO27__FUNC_SPINOR_IO0 (MTK_PIN_NO(27) | 6) + +#define PINMUX_GPIO28__FUNC_GPIO28 (MTK_PIN_NO(28) | 0) +#define PINMUX_GPIO28__FUNC_PWM_0 (MTK_PIN_NO(28) | 1) +#define PINMUX_GPIO28__FUNC_CLKM2 (MTK_PIN_NO(28) | 2) +#define PINMUX_GPIO28__FUNC_SPI5_C_CSB (MTK_PIN_NO(28) | 4) +#define PINMUX_GPIO28__FUNC_I2S9_MCK (MTK_PIN_NO(28) | 5) +#define PINMUX_GPIO28__FUNC_SPINOR_IO1 (MTK_PIN_NO(28) | 6) + +#define PINMUX_GPIO29__FUNC_GPIO29 (MTK_PIN_NO(29) | 0) +#define PINMUX_GPIO29__FUNC_PWM_1 (MTK_PIN_NO(29) | 1) +#define PINMUX_GPIO29__FUNC_CLKM3 (MTK_PIN_NO(29) | 2) +#define PINMUX_GPIO29__FUNC_SPI5_C_CLK (MTK_PIN_NO(29) | 4) +#define PINMUX_GPIO29__FUNC_I2S9_DO (MTK_PIN_NO(29) | 5) +#define PINMUX_GPIO29__FUNC_SPINOR_IO2 (MTK_PIN_NO(29) | 6) + +#define PINMUX_GPIO30__FUNC_GPIO30 (MTK_PIN_NO(30) | 0) +#define PINMUX_GPIO30__FUNC_PWM_2 (MTK_PIN_NO(30) | 1) +#define PINMUX_GPIO30__FUNC_CLKM0 (MTK_PIN_NO(30) | 2) +#define PINMUX_GPIO30__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(30) | 3) +#define PINMUX_GPIO30__FUNC_I2S7_MCK (MTK_PIN_NO(30) | 4) +#define PINMUX_GPIO30__FUNC_I2S9_MCK (MTK_PIN_NO(30) | 5) +#define PINMUX_GPIO30__FUNC_SPINOR_IO3 (MTK_PIN_NO(30) | 6) + +#define PINMUX_GPIO31__FUNC_GPIO31 (MTK_PIN_NO(31) | 0) +#define PINMUX_GPIO31__FUNC_I2S3_MCK (MTK_PIN_NO(31) | 1) +#define PINMUX_GPIO31__FUNC_I2S1_MCK (MTK_PIN_NO(31) | 2) +#define PINMUX_GPIO31__FUNC_I2S5_MCK (MTK_PIN_NO(31) | 3) +#define PINMUX_GPIO31__FUNC_SRCLKENAI0 (MTK_PIN_NO(31) | 4) +#define PINMUX_GPIO31__FUNC_I2S0_MCK (MTK_PIN_NO(31) | 5) + +#define PINMUX_GPIO32__FUNC_GPIO32 (MTK_PIN_NO(32) | 0) +#define PINMUX_GPIO32__FUNC_I2S3_BCK (MTK_PIN_NO(32) | 1) +#define PINMUX_GPIO32__FUNC_I2S1_BCK (MTK_PIN_NO(32) | 2) +#define PINMUX_GPIO32__FUNC_I2S5_BCK (MTK_PIN_NO(32) | 3) +#define PINMUX_GPIO32__FUNC_PCM0_CLK (MTK_PIN_NO(32) | 4) +#define PINMUX_GPIO32__FUNC_I2S0_BCK (MTK_PIN_NO(32) | 5) + +#define PINMUX_GPIO33__FUNC_GPIO33 (MTK_PIN_NO(33) | 0) +#define PINMUX_GPIO33__FUNC_I2S3_LRCK (MTK_PIN_NO(33) | 1) +#define PINMUX_GPIO33__FUNC_I2S1_LRCK (MTK_PIN_NO(33) | 2) +#define PINMUX_GPIO33__FUNC_I2S5_LRCK (MTK_PIN_NO(33) | 3) +#define PINMUX_GPIO33__FUNC_PCM0_SYNC (MTK_PIN_NO(33) | 4) +#define PINMUX_GPIO33__FUNC_I2S0_LRCK (MTK_PIN_NO(33) | 5) + +#define PINMUX_GPIO34__FUNC_GPIO34 (MTK_PIN_NO(34) | 0) +#define PINMUX_GPIO34__FUNC_I2S0_DI (MTK_PIN_NO(34) | 1) +#define PINMUX_GPIO34__FUNC_I2S2_DI (MTK_PIN_NO(34) | 2) +#define PINMUX_GPIO34__FUNC_I2S2_DI2 (MTK_PIN_NO(34) | 3) +#define PINMUX_GPIO34__FUNC_PCM0_DI (MTK_PIN_NO(34) | 4) +#define PINMUX_GPIO34__FUNC_I2S0_DI_A (MTK_PIN_NO(34) | 5) + +#define PINMUX_GPIO35__FUNC_GPIO35 (MTK_PIN_NO(35) | 0) +#define PINMUX_GPIO35__FUNC_I2S3_DO (MTK_PIN_NO(35) | 1) +#define PINMUX_GPIO35__FUNC_I2S1_DO (MTK_PIN_NO(35) | 2) +#define PINMUX_GPIO35__FUNC_I2S5_DO (MTK_PIN_NO(35) | 3) +#define PINMUX_GPIO35__FUNC_PCM0_DO (MTK_PIN_NO(35) | 4) + +#define PINMUX_GPIO36__FUNC_GPIO36 (MTK_PIN_NO(36) | 0) +#define PINMUX_GPIO36__FUNC_SPI5_A_CLK (MTK_PIN_NO(36) | 1) +#define PINMUX_GPIO36__FUNC_DMIC1_CLK (MTK_PIN_NO(36) | 2) +#define PINMUX_GPIO36__FUNC_MD_URXD0 (MTK_PIN_NO(36) | 4) +#define PINMUX_GPIO36__FUNC_UCTS0 (MTK_PIN_NO(36) | 5) +#define PINMUX_GPIO36__FUNC_URXD1 (MTK_PIN_NO(36) | 6) + +#define PINMUX_GPIO37__FUNC_GPIO37 (MTK_PIN_NO(37) | 0) +#define PINMUX_GPIO37__FUNC_SPI5_A_CSB (MTK_PIN_NO(37) | 1) +#define PINMUX_GPIO37__FUNC_DMIC1_DAT (MTK_PIN_NO(37) | 2) +#define PINMUX_GPIO37__FUNC_MD_UTXD0 (MTK_PIN_NO(37) | 4) +#define PINMUX_GPIO37__FUNC_URTS0 (MTK_PIN_NO(37) | 5) +#define PINMUX_GPIO37__FUNC_UTXD1 (MTK_PIN_NO(37) | 6) + +#define PINMUX_GPIO38__FUNC_GPIO38 (MTK_PIN_NO(38) | 0) +#define PINMUX_GPIO38__FUNC_SPI5_A_MI (MTK_PIN_NO(38) | 1) +#define PINMUX_GPIO38__FUNC_DMIC_CLK (MTK_PIN_NO(38) | 2) +#define PINMUX_GPIO38__FUNC_MD_URXD1 (MTK_PIN_NO(38) | 4) +#define PINMUX_GPIO38__FUNC_URXD0 (MTK_PIN_NO(38) | 5) +#define PINMUX_GPIO38__FUNC_UCTS1 (MTK_PIN_NO(38) | 6) + +#define PINMUX_GPIO39__FUNC_GPIO39 (MTK_PIN_NO(39) | 0) +#define PINMUX_GPIO39__FUNC_SPI5_A_MO (MTK_PIN_NO(39) | 1) +#define PINMUX_GPIO39__FUNC_DMIC_DAT (MTK_PIN_NO(39) | 2) +#define PINMUX_GPIO39__FUNC_MD_UTXD1 (MTK_PIN_NO(39) | 4) +#define PINMUX_GPIO39__FUNC_UTXD0 (MTK_PIN_NO(39) | 5) +#define PINMUX_GPIO39__FUNC_URTS1 (MTK_PIN_NO(39) | 6) + +#define PINMUX_GPIO40__FUNC_GPIO40 (MTK_PIN_NO(40) | 0) +#define PINMUX_GPIO40__FUNC_DISP_PWM (MTK_PIN_NO(40) | 1) +#define PINMUX_GPIO40__FUNC_DBG_MON_A6 (MTK_PIN_NO(40) | 7) + +#define PINMUX_GPIO41__FUNC_GPIO41 (MTK_PIN_NO(41) | 0) +#define PINMUX_GPIO41__FUNC_DSI_TE (MTK_PIN_NO(41) | 1) +#define PINMUX_GPIO41__FUNC_DBG_MON_A7 (MTK_PIN_NO(41) | 7) + +#define PINMUX_GPIO42__FUNC_GPIO42 (MTK_PIN_NO(42) | 0) +#define PINMUX_GPIO42__FUNC_LCM_RST (MTK_PIN_NO(42) | 1) +#define PINMUX_GPIO42__FUNC_DBG_MON_A8 (MTK_PIN_NO(42) | 7) + +#define PINMUX_GPIO43__FUNC_GPIO43 (MTK_PIN_NO(43) | 0) +#define PINMUX_GPIO43__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(43) | 1) +#define PINMUX_GPIO43__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(43) | 2) +#define PINMUX_GPIO43__FUNC_SCL_6306 (MTK_PIN_NO(43) | 3) +#define PINMUX_GPIO43__FUNC_ADSP_URXD0 (MTK_PIN_NO(43) | 4) +#define PINMUX_GPIO43__FUNC_PTA_RXD (MTK_PIN_NO(43) | 5) +#define PINMUX_GPIO43__FUNC_SSPM_URXD_AO (MTK_PIN_NO(43) | 6) +#define PINMUX_GPIO43__FUNC_DBG_MON_B0 (MTK_PIN_NO(43) | 7) + +#define PINMUX_GPIO44__FUNC_GPIO44 (MTK_PIN_NO(44) | 0) +#define PINMUX_GPIO44__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(44) | 1) +#define PINMUX_GPIO44__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(44) | 2) +#define PINMUX_GPIO44__FUNC_SDA_6306 (MTK_PIN_NO(44) | 3) +#define PINMUX_GPIO44__FUNC_ADSP_UTXD0 (MTK_PIN_NO(44) | 4) +#define PINMUX_GPIO44__FUNC_PTA_TXD (MTK_PIN_NO(44) | 5) +#define PINMUX_GPIO44__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(44) | 6) +#define PINMUX_GPIO44__FUNC_DBG_MON_B1 (MTK_PIN_NO(44) | 7) + +#define PINMUX_GPIO45__FUNC_GPIO45 (MTK_PIN_NO(45) | 0) +#define PINMUX_GPIO45__FUNC_MD1_SIM2_SCLK (MTK_PIN_NO(45) | 1) +#define PINMUX_GPIO45__FUNC_MD1_SIM1_SCLK (MTK_PIN_NO(45) | 2) +#define PINMUX_GPIO45__FUNC_MCUPM_JTAG_TDI (MTK_PIN_NO(45) | 3) +#define PINMUX_GPIO45__FUNC_APU_JTAG_TDI (MTK_PIN_NO(45) | 4) +#define PINMUX_GPIO45__FUNC_CCU_JTAG_TDI (MTK_PIN_NO(45) | 5) +#define PINMUX_GPIO45__FUNC_LVTS_SCK (MTK_PIN_NO(45) | 6) +#define PINMUX_GPIO45__FUNC_CONN_DSP_JDI (MTK_PIN_NO(45) | 7) + +#define PINMUX_GPIO46__FUNC_GPIO46 (MTK_PIN_NO(46) | 0) +#define PINMUX_GPIO46__FUNC_MD1_SIM2_SRST (MTK_PIN_NO(46) | 1) +#define PINMUX_GPIO46__FUNC_MD1_SIM1_SRST (MTK_PIN_NO(46) | 2) +#define PINMUX_GPIO46__FUNC_MCUPM_JTAG_TMS (MTK_PIN_NO(46) | 3) +#define PINMUX_GPIO46__FUNC_APU_JTAG_TMS (MTK_PIN_NO(46) | 4) +#define PINMUX_GPIO46__FUNC_CCU_JTAG_TMS (MTK_PIN_NO(46) | 5) +#define PINMUX_GPIO46__FUNC_LVTS_SDI (MTK_PIN_NO(46) | 6) +#define PINMUX_GPIO46__FUNC_CONN_DSP_JMS (MTK_PIN_NO(46) | 7) + +#define PINMUX_GPIO47__FUNC_GPIO47 (MTK_PIN_NO(47) | 0) +#define PINMUX_GPIO47__FUNC_MD1_SIM2_SIO (MTK_PIN_NO(47) | 1) +#define PINMUX_GPIO47__FUNC_MD1_SIM1_SIO (MTK_PIN_NO(47) | 2) +#define PINMUX_GPIO47__FUNC_MCUPM_JTAG_TDO (MTK_PIN_NO(47) | 3) +#define PINMUX_GPIO47__FUNC_APU_JTAG_TDO (MTK_PIN_NO(47) | 4) +#define PINMUX_GPIO47__FUNC_CCU_JTAG_TDO (MTK_PIN_NO(47) | 5) +#define PINMUX_GPIO47__FUNC_LVTS_SCF (MTK_PIN_NO(47) | 6) +#define PINMUX_GPIO47__FUNC_CONN_DSP_JDO (MTK_PIN_NO(47) | 7) + +#define PINMUX_GPIO48__FUNC_GPIO48 (MTK_PIN_NO(48) | 0) +#define PINMUX_GPIO48__FUNC_MD1_SIM1_SIO (MTK_PIN_NO(48) | 1) +#define PINMUX_GPIO48__FUNC_MD1_SIM2_SIO (MTK_PIN_NO(48) | 2) +#define PINMUX_GPIO48__FUNC_MCUPM_JTAG_TRSTN (MTK_PIN_NO(48) | 3) +#define PINMUX_GPIO48__FUNC_APU_JTAG_TRST (MTK_PIN_NO(48) | 4) +#define PINMUX_GPIO48__FUNC_CCU_JTAG_TRST (MTK_PIN_NO(48) | 5) +#define PINMUX_GPIO48__FUNC_LVTS_FOUT (MTK_PIN_NO(48) | 6) +#define PINMUX_GPIO48__FUNC_CONN_DSP_JINTP (MTK_PIN_NO(48) | 7) + +#define PINMUX_GPIO49__FUNC_GPIO49 (MTK_PIN_NO(49) | 0) +#define PINMUX_GPIO49__FUNC_MD1_SIM1_SRST (MTK_PIN_NO(49) | 1) +#define PINMUX_GPIO49__FUNC_MD1_SIM2_SRST (MTK_PIN_NO(49) | 2) +#define PINMUX_GPIO49__FUNC_MCUPM_JTAG_TCK (MTK_PIN_NO(49) | 3) +#define PINMUX_GPIO49__FUNC_APU_JTAG_TCK (MTK_PIN_NO(49) | 4) +#define PINMUX_GPIO49__FUNC_CCU_JTAG_TCK (MTK_PIN_NO(49) | 5) +#define PINMUX_GPIO49__FUNC_LVTS_SDO (MTK_PIN_NO(49) | 6) +#define PINMUX_GPIO49__FUNC_CONN_DSP_JCK (MTK_PIN_NO(49) | 7) + +#define PINMUX_GPIO50__FUNC_GPIO50 (MTK_PIN_NO(50) | 0) +#define PINMUX_GPIO50__FUNC_MD1_SIM1_SCLK (MTK_PIN_NO(50) | 1) +#define PINMUX_GPIO50__FUNC_MD1_SIM2_SCLK (MTK_PIN_NO(50) | 2) +#define PINMUX_GPIO50__FUNC_LVTS_26M (MTK_PIN_NO(50) | 6) + +#define PINMUX_GPIO51__FUNC_GPIO51 (MTK_PIN_NO(51) | 0) +#define PINMUX_GPIO51__FUNC_MSDC1_CLK (MTK_PIN_NO(51) | 1) +#define PINMUX_GPIO51__FUNC_PCM1_CLK (MTK_PIN_NO(51) | 2) +#define PINMUX_GPIO51__FUNC_CONN_DSP_JCK (MTK_PIN_NO(51) | 3) +#define PINMUX_GPIO51__FUNC_UDI_TCK (MTK_PIN_NO(51) | 4) +#define PINMUX_GPIO51__FUNC_IPU_JTAG_TCK (MTK_PIN_NO(51) | 5) +#define PINMUX_GPIO51__FUNC_SSPM_JTAG_TCK (MTK_PIN_NO(51) | 6) +#define PINMUX_GPIO51__FUNC_JTCK_SEL3 (MTK_PIN_NO(51) | 7) + +#define PINMUX_GPIO52__FUNC_GPIO52 (MTK_PIN_NO(52) | 0) +#define PINMUX_GPIO52__FUNC_MSDC1_CMD (MTK_PIN_NO(52) | 1) +#define PINMUX_GPIO52__FUNC_PCM1_SYNC (MTK_PIN_NO(52) | 2) +#define PINMUX_GPIO52__FUNC_CONN_DSP_JMS (MTK_PIN_NO(52) | 3) +#define PINMUX_GPIO52__FUNC_UDI_TMS (MTK_PIN_NO(52) | 4) +#define PINMUX_GPIO52__FUNC_IPU_JTAG_TMS (MTK_PIN_NO(52) | 5) +#define PINMUX_GPIO52__FUNC_SSPM_JTAG_TMS (MTK_PIN_NO(52) | 6) +#define PINMUX_GPIO52__FUNC_JTMS_SEL3 (MTK_PIN_NO(52) | 7) + +#define PINMUX_GPIO53__FUNC_GPIO53 (MTK_PIN_NO(53) | 0) +#define PINMUX_GPIO53__FUNC_MSDC1_DAT3 (MTK_PIN_NO(53) | 1) +#define PINMUX_GPIO53__FUNC_PCM1_DI (MTK_PIN_NO(53) | 2) +#define PINMUX_GPIO53__FUNC_CONN_DSP_JINTP (MTK_PIN_NO(53) | 3) +#define PINMUX_GPIO53__FUNC_CONN_MCU_AICE_TMSC (MTK_PIN_NO(53) | 4) + +#define PINMUX_GPIO54__FUNC_GPIO54 (MTK_PIN_NO(54) | 0) +#define PINMUX_GPIO54__FUNC_MSDC1_DAT0 (MTK_PIN_NO(54) | 1) +#define PINMUX_GPIO54__FUNC_PCM1_DO0 (MTK_PIN_NO(54) | 2) +#define PINMUX_GPIO54__FUNC_CONN_DSP_JDI (MTK_PIN_NO(54) | 3) +#define PINMUX_GPIO54__FUNC_UDI_TDI (MTK_PIN_NO(54) | 4) +#define PINMUX_GPIO54__FUNC_IPU_JTAG_TDI (MTK_PIN_NO(54) | 5) +#define PINMUX_GPIO54__FUNC_SSPM_JTAG_TDI (MTK_PIN_NO(54) | 6) +#define PINMUX_GPIO54__FUNC_JTDI_SEL3 (MTK_PIN_NO(54) | 7) + +#define PINMUX_GPIO55__FUNC_GPIO55 (MTK_PIN_NO(55) | 0) +#define PINMUX_GPIO55__FUNC_MSDC1_DAT2 (MTK_PIN_NO(55) | 1) +#define PINMUX_GPIO55__FUNC_PCM1_DO2 (MTK_PIN_NO(55) | 2) +#define PINMUX_GPIO55__FUNC_CONN_MCU_AICE_TCKC (MTK_PIN_NO(55) | 3) +#define PINMUX_GPIO55__FUNC_UDI_NTRST (MTK_PIN_NO(55) | 4) +#define PINMUX_GPIO55__FUNC_IPU_JTAG_TRST (MTK_PIN_NO(55) | 5) +#define PINMUX_GPIO55__FUNC_SSPM_JTAG_TRSTN (MTK_PIN_NO(55) | 6) +#define PINMUX_GPIO55__FUNC_JTRSTN_SEL3 (MTK_PIN_NO(55) | 7) + +#define PINMUX_GPIO56__FUNC_GPIO56 (MTK_PIN_NO(56) | 0) +#define PINMUX_GPIO56__FUNC_MSDC1_DAT1 (MTK_PIN_NO(56) | 1) +#define PINMUX_GPIO56__FUNC_PCM1_DO1 (MTK_PIN_NO(56) | 2) +#define PINMUX_GPIO56__FUNC_CONN_DSP_JDO (MTK_PIN_NO(56) | 3) +#define PINMUX_GPIO56__FUNC_UDI_TDO (MTK_PIN_NO(56) | 4) +#define PINMUX_GPIO56__FUNC_IPU_JTAG_TDO (MTK_PIN_NO(56) | 5) +#define PINMUX_GPIO56__FUNC_SSPM_JTAG_TDO (MTK_PIN_NO(56) | 6) +#define PINMUX_GPIO56__FUNC_JTDO_SEL3 (MTK_PIN_NO(56) | 7) + +#define PINMUX_GPIO57__FUNC_GPIO57 (MTK_PIN_NO(57) | 0) +#define PINMUX_GPIO57__FUNC_MIPI2_D_SCLK (MTK_PIN_NO(57) | 1) + +#define PINMUX_GPIO58__FUNC_GPIO58 (MTK_PIN_NO(58) | 0) +#define PINMUX_GPIO58__FUNC_MIPI2_D_SDATA (MTK_PIN_NO(58) | 1) + +#define PINMUX_GPIO59__FUNC_GPIO59 (MTK_PIN_NO(59) | 0) +#define PINMUX_GPIO59__FUNC_MIPI_M_SCLK (MTK_PIN_NO(59) | 1) + +#define PINMUX_GPIO60__FUNC_GPIO60 (MTK_PIN_NO(60) | 0) +#define PINMUX_GPIO60__FUNC_MIPI_M_SDATA (MTK_PIN_NO(60) | 1) + +#define PINMUX_GPIO61__FUNC_GPIO61 (MTK_PIN_NO(61) | 0) +#define PINMUX_GPIO61__FUNC_MD_UCNT_A_TGL (MTK_PIN_NO(61) | 1) + +#define PINMUX_GPIO62__FUNC_GPIO62 (MTK_PIN_NO(62) | 0) +#define PINMUX_GPIO62__FUNC_DIGRF_IRQ (MTK_PIN_NO(62) | 1) + +#define PINMUX_GPIO63__FUNC_GPIO63 (MTK_PIN_NO(63) | 0) +#define PINMUX_GPIO63__FUNC_BPI_BUS0 (MTK_PIN_NO(63) | 1) +#define PINMUX_GPIO63__FUNC_PCIE_WAKE_N (MTK_PIN_NO(63) | 3) + +#define PINMUX_GPIO64__FUNC_GPIO64 (MTK_PIN_NO(64) | 0) +#define PINMUX_GPIO64__FUNC_BPI_BUS1 (MTK_PIN_NO(64) | 1) +#define PINMUX_GPIO64__FUNC_PCIE_PERESET_N (MTK_PIN_NO(64) | 3) + +#define PINMUX_GPIO65__FUNC_GPIO65 (MTK_PIN_NO(65) | 0) +#define PINMUX_GPIO65__FUNC_BPI_BUS2 (MTK_PIN_NO(65) | 1) +#define PINMUX_GPIO65__FUNC_PCIE_CLKREQ_N (MTK_PIN_NO(65) | 3) + +#define PINMUX_GPIO66__FUNC_GPIO66 (MTK_PIN_NO(66) | 0) +#define PINMUX_GPIO66__FUNC_BPI_BUS3 (MTK_PIN_NO(66) | 1) + +#define PINMUX_GPIO67__FUNC_GPIO67 (MTK_PIN_NO(67) | 0) +#define PINMUX_GPIO67__FUNC_BPI_BUS4 (MTK_PIN_NO(67) | 1) + +#define PINMUX_GPIO68__FUNC_GPIO68 (MTK_PIN_NO(68) | 0) +#define PINMUX_GPIO68__FUNC_BPI_BUS5 (MTK_PIN_NO(68) | 1) + +#define PINMUX_GPIO69__FUNC_GPIO69 (MTK_PIN_NO(69) | 0) +#define PINMUX_GPIO69__FUNC_BPI_BUS6 (MTK_PIN_NO(69) | 1) +#define PINMUX_GPIO69__FUNC_CONN_BPI_BUS6 (MTK_PIN_NO(69) | 2) + +#define PINMUX_GPIO70__FUNC_GPIO70 (MTK_PIN_NO(70) | 0) +#define PINMUX_GPIO70__FUNC_BPI_BUS7 (MTK_PIN_NO(70) | 1) +#define PINMUX_GPIO70__FUNC_CONN_BPI_BUS7 (MTK_PIN_NO(70) | 2) + +#define PINMUX_GPIO71__FUNC_GPIO71 (MTK_PIN_NO(71) | 0) +#define PINMUX_GPIO71__FUNC_BPI_BUS8 (MTK_PIN_NO(71) | 1) +#define PINMUX_GPIO71__FUNC_CONN_BPI_BUS8 (MTK_PIN_NO(71) | 2) + +#define PINMUX_GPIO72__FUNC_GPIO72 (MTK_PIN_NO(72) | 0) +#define PINMUX_GPIO72__FUNC_BPI_BUS9 (MTK_PIN_NO(72) | 1) +#define PINMUX_GPIO72__FUNC_CONN_BPI_BUS9 (MTK_PIN_NO(72) | 2) + +#define PINMUX_GPIO73__FUNC_GPIO73 (MTK_PIN_NO(73) | 0) +#define PINMUX_GPIO73__FUNC_BPI_BUS10 (MTK_PIN_NO(73) | 1) +#define PINMUX_GPIO73__FUNC_CONN_BPI_BUS10 (MTK_PIN_NO(73) | 2) + +#define PINMUX_GPIO74__FUNC_GPIO74 (MTK_PIN_NO(74) | 0) +#define PINMUX_GPIO74__FUNC_BPI_BUS11_OLAT0 (MTK_PIN_NO(74) | 1) +#define PINMUX_GPIO74__FUNC_CONN_BPI_BUS11_OLAT0 (MTK_PIN_NO(74) | 2) + +#define PINMUX_GPIO75__FUNC_GPIO75 (MTK_PIN_NO(75) | 0) +#define PINMUX_GPIO75__FUNC_BPI_BUS12_OLAT1 (MTK_PIN_NO(75) | 1) +#define PINMUX_GPIO75__FUNC_CONN_BPI_BUS12_OLAT1 (MTK_PIN_NO(75) | 2) + +#define PINMUX_GPIO76__FUNC_GPIO76 (MTK_PIN_NO(76) | 0) +#define PINMUX_GPIO76__FUNC_BPI_BUS13_OLAT2 (MTK_PIN_NO(76) | 1) +#define PINMUX_GPIO76__FUNC_CONN_BPI_BUS13_OLAT2 (MTK_PIN_NO(76) | 2) + +#define PINMUX_GPIO77__FUNC_GPIO77 (MTK_PIN_NO(77) | 0) +#define PINMUX_GPIO77__FUNC_BPI_BUS14_OLAT3 (MTK_PIN_NO(77) | 1) +#define PINMUX_GPIO77__FUNC_CONN_BPI_BUS14_OLAT3 (MTK_PIN_NO(77) | 2) + +#define PINMUX_GPIO78__FUNC_GPIO78 (MTK_PIN_NO(78) | 0) +#define PINMUX_GPIO78__FUNC_BPI_BUS15_OLAT4 (MTK_PIN_NO(78) | 1) +#define PINMUX_GPIO78__FUNC_CONN_BPI_BUS15_OLAT4 (MTK_PIN_NO(78) | 2) + +#define PINMUX_GPIO79__FUNC_GPIO79 (MTK_PIN_NO(79) | 0) +#define PINMUX_GPIO79__FUNC_BPI_BUS16_OLAT5 (MTK_PIN_NO(79) | 1) +#define PINMUX_GPIO79__FUNC_CONN_BPI_BUS16_OLAT5 (MTK_PIN_NO(79) | 2) + +#define PINMUX_GPIO80__FUNC_GPIO80 (MTK_PIN_NO(80) | 0) +#define PINMUX_GPIO80__FUNC_BPI_BUS17_ANT0 (MTK_PIN_NO(80) | 1) +#define PINMUX_GPIO80__FUNC_CONN_BPI_BUS17_ANT0 (MTK_PIN_NO(80) | 2) +#define PINMUX_GPIO80__FUNC_PCIE_WAKE_N (MTK_PIN_NO(80) | 3) + +#define PINMUX_GPIO81__FUNC_GPIO81 (MTK_PIN_NO(81) | 0) +#define PINMUX_GPIO81__FUNC_BPI_BUS18_ANT1 (MTK_PIN_NO(81) | 1) +#define PINMUX_GPIO81__FUNC_CONN_BPI_BUS18_ANT1 (MTK_PIN_NO(81) | 2) +#define PINMUX_GPIO81__FUNC_PCIE_PERESET_N (MTK_PIN_NO(81) | 3) + +#define PINMUX_GPIO82__FUNC_GPIO82 (MTK_PIN_NO(82) | 0) +#define PINMUX_GPIO82__FUNC_BPI_BUS19_ANT2 (MTK_PIN_NO(82) | 1) +#define PINMUX_GPIO82__FUNC_CONN_BPI_BUS19_ANT2 (MTK_PIN_NO(82) | 2) +#define PINMUX_GPIO82__FUNC_PCIE_CLKREQ_N (MTK_PIN_NO(82) | 3) + +#define PINMUX_GPIO83__FUNC_GPIO83 (MTK_PIN_NO(83) | 0) +#define PINMUX_GPIO83__FUNC_BPI_BUS20_ANT3 (MTK_PIN_NO(83) | 1) +#define PINMUX_GPIO83__FUNC_CONN_BPI_BUS20_ANT3 (MTK_PIN_NO(83) | 2) + +#define PINMUX_GPIO84__FUNC_GPIO84 (MTK_PIN_NO(84) | 0) +#define PINMUX_GPIO84__FUNC_BPI_BUS21_ANT4 (MTK_PIN_NO(84) | 1) +#define PINMUX_GPIO84__FUNC_CONN_BPI_BUS21_ANT4 (MTK_PIN_NO(84) | 2) + +#define PINMUX_GPIO85__FUNC_GPIO85 (MTK_PIN_NO(85) | 0) +#define PINMUX_GPIO85__FUNC_MIPI1_D_SCLK (MTK_PIN_NO(85) | 1) +#define PINMUX_GPIO85__FUNC_CONN_MIPI1_SCLK (MTK_PIN_NO(85) | 2) + +#define PINMUX_GPIO86__FUNC_GPIO86 (MTK_PIN_NO(86) | 0) +#define PINMUX_GPIO86__FUNC_MIPI1_D_SDATA (MTK_PIN_NO(86) | 1) +#define PINMUX_GPIO86__FUNC_CONN_MIPI1_SDATA (MTK_PIN_NO(86) | 2) + +#define PINMUX_GPIO87__FUNC_GPIO87 (MTK_PIN_NO(87) | 0) +#define PINMUX_GPIO87__FUNC_MIPI0_D_SCLK (MTK_PIN_NO(87) | 1) +#define PINMUX_GPIO87__FUNC_CONN_MIPI0_SCLK (MTK_PIN_NO(87) | 2) + +#define PINMUX_GPIO88__FUNC_GPIO88 (MTK_PIN_NO(88) | 0) +#define PINMUX_GPIO88__FUNC_MIPI0_D_SDATA (MTK_PIN_NO(88) | 1) +#define PINMUX_GPIO88__FUNC_CONN_MIPI0_SDATA (MTK_PIN_NO(88) | 2) + +#define PINMUX_GPIO89__FUNC_GPIO89 (MTK_PIN_NO(89) | 0) +#define PINMUX_GPIO89__FUNC_SPMI_SCL (MTK_PIN_NO(89) | 1) +#define PINMUX_GPIO89__FUNC_SCL10 (MTK_PIN_NO(89) | 2) + +#define PINMUX_GPIO90__FUNC_GPIO90 (MTK_PIN_NO(90) | 0) +#define PINMUX_GPIO90__FUNC_SPMI_SDA (MTK_PIN_NO(90) | 1) +#define PINMUX_GPIO90__FUNC_SDA10 (MTK_PIN_NO(90) | 2) + +#define PINMUX_GPIO91__FUNC_GPIO91 (MTK_PIN_NO(91) | 0) +#define PINMUX_GPIO91__FUNC_AP_GOOD (MTK_PIN_NO(91) | 1) + +#define PINMUX_GPIO92__FUNC_GPIO92 (MTK_PIN_NO(92) | 0) +#define PINMUX_GPIO92__FUNC_URXD0 (MTK_PIN_NO(92) | 1) +#define PINMUX_GPIO92__FUNC_MD_URXD0 (MTK_PIN_NO(92) | 2) +#define PINMUX_GPIO92__FUNC_MD_URXD1 (MTK_PIN_NO(92) | 3) +#define PINMUX_GPIO92__FUNC_SSPM_URXD_AO (MTK_PIN_NO(92) | 4) +#define PINMUX_GPIO92__FUNC_CONN_UART0_RXD (MTK_PIN_NO(92) | 5) + +#define PINMUX_GPIO93__FUNC_GPIO93 (MTK_PIN_NO(93) | 0) +#define PINMUX_GPIO93__FUNC_UTXD0 (MTK_PIN_NO(93) | 1) +#define PINMUX_GPIO93__FUNC_MD_UTXD0 (MTK_PIN_NO(93) | 2) +#define PINMUX_GPIO93__FUNC_MD_UTXD1 (MTK_PIN_NO(93) | 3) +#define PINMUX_GPIO93__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(93) | 4) +#define PINMUX_GPIO93__FUNC_CONN_UART0_TXD (MTK_PIN_NO(93) | 5) +#define PINMUX_GPIO93__FUNC_WIFI_TXD (MTK_PIN_NO(93) | 6) + +#define PINMUX_GPIO94__FUNC_GPIO94 (MTK_PIN_NO(94) | 0) +#define PINMUX_GPIO94__FUNC_URXD1 (MTK_PIN_NO(94) | 1) +#define PINMUX_GPIO94__FUNC_ADSP_URXD0 (MTK_PIN_NO(94) | 2) +#define PINMUX_GPIO94__FUNC_MD32_0_RXD (MTK_PIN_NO(94) | 3) +#define PINMUX_GPIO94__FUNC_SSPM_URXD_AO (MTK_PIN_NO(94) | 4) +#define PINMUX_GPIO94__FUNC_TP_URXD1_AO (MTK_PIN_NO(94) | 5) +#define PINMUX_GPIO94__FUNC_TP_URXD2_AO (MTK_PIN_NO(94) | 6) +#define PINMUX_GPIO94__FUNC_MBISTREADEN_TRIGGER (MTK_PIN_NO(94) | 7) + +#define PINMUX_GPIO95__FUNC_GPIO95 (MTK_PIN_NO(95) | 0) +#define PINMUX_GPIO95__FUNC_UTXD1 (MTK_PIN_NO(95) | 1) +#define PINMUX_GPIO95__FUNC_ADSP_UTXD0 (MTK_PIN_NO(95) | 2) +#define PINMUX_GPIO95__FUNC_MD32_0_TXD (MTK_PIN_NO(95) | 3) +#define PINMUX_GPIO95__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(95) | 4) +#define PINMUX_GPIO95__FUNC_TP_UTXD1_AO (MTK_PIN_NO(95) | 5) +#define PINMUX_GPIO95__FUNC_TP_UTXD2_AO (MTK_PIN_NO(95) | 6) +#define PINMUX_GPIO95__FUNC_MBISTWRITEEN_TRIGGER (MTK_PIN_NO(95) | 7) + +#define PINMUX_GPIO96__FUNC_GPIO96 (MTK_PIN_NO(96) | 0) +#define PINMUX_GPIO96__FUNC_TDM_LRCK (MTK_PIN_NO(96) | 1) +#define PINMUX_GPIO96__FUNC_I2S7_LRCK (MTK_PIN_NO(96) | 2) +#define PINMUX_GPIO96__FUNC_I2S9_LRCK (MTK_PIN_NO(96) | 3) +#define PINMUX_GPIO96__FUNC_DPI_D0 (MTK_PIN_NO(96) | 4) +#define PINMUX_GPIO96__FUNC_ADSP_JTAG0_TDI (MTK_PIN_NO(96) | 5) +#define PINMUX_GPIO96__FUNC_IO_JTAG_TDI (MTK_PIN_NO(96) | 7) + +#define PINMUX_GPIO97__FUNC_GPIO97 (MTK_PIN_NO(97) | 0) +#define PINMUX_GPIO97__FUNC_TDM_BCK (MTK_PIN_NO(97) | 1) +#define PINMUX_GPIO97__FUNC_I2S7_BCK (MTK_PIN_NO(97) | 2) +#define PINMUX_GPIO97__FUNC_I2S9_BCK (MTK_PIN_NO(97) | 3) +#define PINMUX_GPIO97__FUNC_DPI_D1 (MTK_PIN_NO(97) | 4) +#define PINMUX_GPIO97__FUNC_ADSP_JTAG0_TRSTN (MTK_PIN_NO(97) | 5) +#define PINMUX_GPIO97__FUNC_IO_JTAG_TRSTN (MTK_PIN_NO(97) | 7) + +#define PINMUX_GPIO98__FUNC_GPIO98 (MTK_PIN_NO(98) | 0) +#define PINMUX_GPIO98__FUNC_TDM_MCK (MTK_PIN_NO(98) | 1) +#define PINMUX_GPIO98__FUNC_I2S7_MCK (MTK_PIN_NO(98) | 2) +#define PINMUX_GPIO98__FUNC_I2S9_MCK (MTK_PIN_NO(98) | 3) +#define PINMUX_GPIO98__FUNC_DPI_D2 (MTK_PIN_NO(98) | 4) +#define PINMUX_GPIO98__FUNC_ADSP_JTAG0_TCK (MTK_PIN_NO(98) | 5) +#define PINMUX_GPIO98__FUNC_IO_JTAG_TCK (MTK_PIN_NO(98) | 7) + +#define PINMUX_GPIO99__FUNC_GPIO99 (MTK_PIN_NO(99) | 0) +#define PINMUX_GPIO99__FUNC_TDM_DATA0 (MTK_PIN_NO(99) | 1) +#define PINMUX_GPIO99__FUNC_I2S6_DI (MTK_PIN_NO(99) | 2) +#define PINMUX_GPIO99__FUNC_I2S8_DI (MTK_PIN_NO(99) | 3) +#define PINMUX_GPIO99__FUNC_DPI_D3 (MTK_PIN_NO(99) | 4) +#define PINMUX_GPIO99__FUNC_ADSP_JTAG0_TDO (MTK_PIN_NO(99) | 5) +#define PINMUX_GPIO99__FUNC_IO_JTAG_TDO (MTK_PIN_NO(99) | 7) + +#define PINMUX_GPIO100__FUNC_GPIO100 (MTK_PIN_NO(100) | 0) +#define PINMUX_GPIO100__FUNC_TDM_DATA1 (MTK_PIN_NO(100) | 1) +#define PINMUX_GPIO100__FUNC_I2S7_DO (MTK_PIN_NO(100) | 2) +#define PINMUX_GPIO100__FUNC_I2S9_DO (MTK_PIN_NO(100) | 3) +#define PINMUX_GPIO100__FUNC_DPI_D4 (MTK_PIN_NO(100) | 4) +#define PINMUX_GPIO100__FUNC_ADSP_JTAG0_TMS (MTK_PIN_NO(100) | 5) +#define PINMUX_GPIO100__FUNC_IO_JTAG_TMS (MTK_PIN_NO(100) | 7) + +#define PINMUX_GPIO101__FUNC_GPIO101 (MTK_PIN_NO(101) | 0) +#define PINMUX_GPIO101__FUNC_TDM_DATA2 (MTK_PIN_NO(101) | 1) +#define PINMUX_GPIO101__FUNC_DMIC1_CLK (MTK_PIN_NO(101) | 2) +#define PINMUX_GPIO101__FUNC_SRCLKENAI0 (MTK_PIN_NO(101) | 3) +#define PINMUX_GPIO101__FUNC_DPI_D5 (MTK_PIN_NO(101) | 4) +#define PINMUX_GPIO101__FUNC_CLKM0 (MTK_PIN_NO(101) | 5) +#define PINMUX_GPIO101__FUNC_DAP_MD32_SWD (MTK_PIN_NO(101) | 7) + +#define PINMUX_GPIO102__FUNC_GPIO102 (MTK_PIN_NO(102) | 0) +#define PINMUX_GPIO102__FUNC_TDM_DATA3 (MTK_PIN_NO(102) | 1) +#define PINMUX_GPIO102__FUNC_DMIC1_DAT (MTK_PIN_NO(102) | 2) +#define PINMUX_GPIO102__FUNC_SRCLKENAI1 (MTK_PIN_NO(102) | 3) +#define PINMUX_GPIO102__FUNC_DPI_D6 (MTK_PIN_NO(102) | 4) +#define PINMUX_GPIO102__FUNC_DVFSRC_EXT_REQ (MTK_PIN_NO(102) | 6) +#define PINMUX_GPIO102__FUNC_DAP_MD32_SWCK (MTK_PIN_NO(102) | 7) + +#define PINMUX_GPIO103__FUNC_GPIO103 (MTK_PIN_NO(103) | 0) +#define PINMUX_GPIO103__FUNC_SPI0_A_MI (MTK_PIN_NO(103) | 1) +#define PINMUX_GPIO103__FUNC_SCP_SPI0_MI (MTK_PIN_NO(103) | 2) +#define PINMUX_GPIO103__FUNC_DPI_D7 (MTK_PIN_NO(103) | 4) +#define PINMUX_GPIO103__FUNC_DFD_TDO (MTK_PIN_NO(103) | 5) +#define PINMUX_GPIO103__FUNC_SPM_JTAG_TDO (MTK_PIN_NO(103) | 6) +#define PINMUX_GPIO103__FUNC_JTDO_SEL1 (MTK_PIN_NO(103) | 7) + +#define PINMUX_GPIO104__FUNC_GPIO104 (MTK_PIN_NO(104) | 0) +#define PINMUX_GPIO104__FUNC_SPI0_A_CSB (MTK_PIN_NO(104) | 1) +#define PINMUX_GPIO104__FUNC_SCP_SPI0_CS (MTK_PIN_NO(104) | 2) +#define PINMUX_GPIO104__FUNC_DPI_D8 (MTK_PIN_NO(104) | 4) +#define PINMUX_GPIO104__FUNC_DFD_TMS (MTK_PIN_NO(104) | 5) +#define PINMUX_GPIO104__FUNC_SPM_JTAG_TMS (MTK_PIN_NO(104) | 6) +#define PINMUX_GPIO104__FUNC_JTMS_SEL1 (MTK_PIN_NO(104) | 7) + +#define PINMUX_GPIO105__FUNC_GPIO105 (MTK_PIN_NO(105) | 0) +#define PINMUX_GPIO105__FUNC_SPI0_A_MO (MTK_PIN_NO(105) | 1) +#define PINMUX_GPIO105__FUNC_SCP_SPI0_MO (MTK_PIN_NO(105) | 2) +#define PINMUX_GPIO105__FUNC_SCP_SDA0 (MTK_PIN_NO(105) | 3) +#define PINMUX_GPIO105__FUNC_DPI_D9 (MTK_PIN_NO(105) | 4) +#define PINMUX_GPIO105__FUNC_DFD_TDI (MTK_PIN_NO(105) | 5) +#define PINMUX_GPIO105__FUNC_SPM_JTAG_TDI (MTK_PIN_NO(105) | 6) +#define PINMUX_GPIO105__FUNC_JTDI_SEL1 (MTK_PIN_NO(105) | 7) + +#define PINMUX_GPIO106__FUNC_GPIO106 (MTK_PIN_NO(106) | 0) +#define PINMUX_GPIO106__FUNC_SPI0_A_CLK (MTK_PIN_NO(106) | 1) +#define PINMUX_GPIO106__FUNC_SCP_SPI0_CK (MTK_PIN_NO(106) | 2) +#define PINMUX_GPIO106__FUNC_SCP_SCL0 (MTK_PIN_NO(106) | 3) +#define PINMUX_GPIO106__FUNC_DPI_D10 (MTK_PIN_NO(106) | 4) +#define PINMUX_GPIO106__FUNC_DFD_TCK_XI (MTK_PIN_NO(106) | 5) +#define PINMUX_GPIO106__FUNC_SPM_JTAG_TCK (MTK_PIN_NO(106) | 6) +#define PINMUX_GPIO106__FUNC_JTCK_SEL1 (MTK_PIN_NO(106) | 7) + +#define PINMUX_GPIO107__FUNC_GPIO107 (MTK_PIN_NO(107) | 0) +#define PINMUX_GPIO107__FUNC_DMIC_CLK (MTK_PIN_NO(107) | 1) +#define PINMUX_GPIO107__FUNC_PWM_0 (MTK_PIN_NO(107) | 2) +#define PINMUX_GPIO107__FUNC_CLKM2 (MTK_PIN_NO(107) | 3) +#define PINMUX_GPIO107__FUNC_SPM_JTAG_TRSTN (MTK_PIN_NO(107) | 6) +#define PINMUX_GPIO107__FUNC_JTRSTN_SEL1 (MTK_PIN_NO(107) | 7) + +#define PINMUX_GPIO108__FUNC_GPIO108 (MTK_PIN_NO(108) | 0) +#define PINMUX_GPIO108__FUNC_DMIC_DAT (MTK_PIN_NO(108) | 1) +#define PINMUX_GPIO108__FUNC_PWM_1 (MTK_PIN_NO(108) | 2) +#define PINMUX_GPIO108__FUNC_CLKM3 (MTK_PIN_NO(108) | 3) +#define PINMUX_GPIO108__FUNC_DAP_SONIC_SWD (MTK_PIN_NO(108) | 7) + +#define PINMUX_GPIO109__FUNC_GPIO109 (MTK_PIN_NO(109) | 0) +#define PINMUX_GPIO109__FUNC_I2S1_MCK (MTK_PIN_NO(109) | 1) +#define PINMUX_GPIO109__FUNC_I2S3_MCK (MTK_PIN_NO(109) | 2) +#define PINMUX_GPIO109__FUNC_I2S2_MCK (MTK_PIN_NO(109) | 3) +#define PINMUX_GPIO109__FUNC_DPI_DE (MTK_PIN_NO(109) | 4) +#define PINMUX_GPIO109__FUNC_I2S2_MCK_A (MTK_PIN_NO(109) | 5) +#define PINMUX_GPIO109__FUNC_SRCLKENAI0 (MTK_PIN_NO(109) | 6) +#define PINMUX_GPIO109__FUNC_DAP_SONIC_SWCK (MTK_PIN_NO(109) | 7) + +#define PINMUX_GPIO110__FUNC_GPIO110 (MTK_PIN_NO(110) | 0) +#define PINMUX_GPIO110__FUNC_I2S1_BCK (MTK_PIN_NO(110) | 1) +#define PINMUX_GPIO110__FUNC_I2S3_BCK (MTK_PIN_NO(110) | 2) +#define PINMUX_GPIO110__FUNC_I2S2_BCK (MTK_PIN_NO(110) | 3) +#define PINMUX_GPIO110__FUNC_DPI_D11 (MTK_PIN_NO(110) | 4) +#define PINMUX_GPIO110__FUNC_I2S2_BCK_A (MTK_PIN_NO(110) | 5) +#define PINMUX_GPIO110__FUNC_CONN_MCU_TDO (MTK_PIN_NO(110) | 6) + +#define PINMUX_GPIO111__FUNC_GPIO111 (MTK_PIN_NO(111) | 0) +#define PINMUX_GPIO111__FUNC_I2S1_LRCK (MTK_PIN_NO(111) | 1) +#define PINMUX_GPIO111__FUNC_I2S3_LRCK (MTK_PIN_NO(111) | 2) +#define PINMUX_GPIO111__FUNC_I2S2_LRCK (MTK_PIN_NO(111) | 3) +#define PINMUX_GPIO111__FUNC_DPI_VSYNC (MTK_PIN_NO(111) | 4) +#define PINMUX_GPIO111__FUNC_I2S2_LRCK_A (MTK_PIN_NO(111) | 5) +#define PINMUX_GPIO111__FUNC_CONN_MCU_TDI (MTK_PIN_NO(111) | 6) + +#define PINMUX_GPIO112__FUNC_GPIO112 (MTK_PIN_NO(112) | 0) +#define PINMUX_GPIO112__FUNC_I2S2_DI (MTK_PIN_NO(112) | 1) +#define PINMUX_GPIO112__FUNC_I2S0_DI (MTK_PIN_NO(112) | 2) +#define PINMUX_GPIO112__FUNC_I2S2_DI2 (MTK_PIN_NO(112) | 3) +#define PINMUX_GPIO112__FUNC_DPI_CK (MTK_PIN_NO(112) | 4) +#define PINMUX_GPIO112__FUNC_I2S2_DI_A (MTK_PIN_NO(112) | 5) +#define PINMUX_GPIO112__FUNC_CONN_MCU_TMS (MTK_PIN_NO(112) | 6) + +#define PINMUX_GPIO113__FUNC_GPIO113 (MTK_PIN_NO(113) | 0) +#define PINMUX_GPIO113__FUNC_I2S1_DO (MTK_PIN_NO(113) | 1) +#define PINMUX_GPIO113__FUNC_I2S3_DO (MTK_PIN_NO(113) | 2) +#define PINMUX_GPIO113__FUNC_I2S5_DO (MTK_PIN_NO(113) | 3) +#define PINMUX_GPIO113__FUNC_DPI_HSYNC (MTK_PIN_NO(113) | 4) +#define PINMUX_GPIO113__FUNC_I2S2_DI2 (MTK_PIN_NO(113) | 5) +#define PINMUX_GPIO113__FUNC_CONN_MCU_TCK (MTK_PIN_NO(113) | 6) + +#define PINMUX_GPIO114__FUNC_GPIO114 (MTK_PIN_NO(114) | 0) +#define PINMUX_GPIO114__FUNC_SPI2_MI (MTK_PIN_NO(114) | 1) +#define PINMUX_GPIO114__FUNC_SCP_SPI2_MI (MTK_PIN_NO(114) | 2) +#define PINMUX_GPIO114__FUNC_PCM0_DI (MTK_PIN_NO(114) | 4) +#define PINMUX_GPIO114__FUNC_CONN_MCU_TRST_B (MTK_PIN_NO(114) | 6) + +#define PINMUX_GPIO115__FUNC_GPIO115 (MTK_PIN_NO(115) | 0) +#define PINMUX_GPIO115__FUNC_SPI2_CSB (MTK_PIN_NO(115) | 1) +#define PINMUX_GPIO115__FUNC_SCP_SPI2_CS (MTK_PIN_NO(115) | 2) +#define PINMUX_GPIO115__FUNC_PCM0_SYNC (MTK_PIN_NO(115) | 4) +#define PINMUX_GPIO115__FUNC_CONN_MCU_DBGI_N (MTK_PIN_NO(115) | 6) + +#define PINMUX_GPIO116__FUNC_GPIO116 (MTK_PIN_NO(116) | 0) +#define PINMUX_GPIO116__FUNC_SPI2_MO (MTK_PIN_NO(116) | 1) +#define PINMUX_GPIO116__FUNC_SCP_SPI2_MO (MTK_PIN_NO(116) | 2) +#define PINMUX_GPIO116__FUNC_SCP_SDA1 (MTK_PIN_NO(116) | 3) +#define PINMUX_GPIO116__FUNC_PCM0_DO (MTK_PIN_NO(116) | 4) +#define PINMUX_GPIO116__FUNC_CONN_MCU_DBGACK_N (MTK_PIN_NO(116) | 6) + +#define PINMUX_GPIO117__FUNC_GPIO117 (MTK_PIN_NO(117) | 0) +#define PINMUX_GPIO117__FUNC_SPI2_CLK (MTK_PIN_NO(117) | 1) +#define PINMUX_GPIO117__FUNC_SCP_SPI2_CK (MTK_PIN_NO(117) | 2) +#define PINMUX_GPIO117__FUNC_SCP_SCL1 (MTK_PIN_NO(117) | 3) +#define PINMUX_GPIO117__FUNC_PCM0_CLK (MTK_PIN_NO(117) | 4) + +#define PINMUX_GPIO118__FUNC_GPIO118 (MTK_PIN_NO(118) | 0) +#define PINMUX_GPIO118__FUNC_SCL1 (MTK_PIN_NO(118) | 1) +#define PINMUX_GPIO118__FUNC_SCP_SCL0 (MTK_PIN_NO(118) | 2) +#define PINMUX_GPIO118__FUNC_SCP_SCL1 (MTK_PIN_NO(118) | 3) + +#define PINMUX_GPIO119__FUNC_GPIO119 (MTK_PIN_NO(119) | 0) +#define PINMUX_GPIO119__FUNC_SDA1 (MTK_PIN_NO(119) | 1) +#define PINMUX_GPIO119__FUNC_SCP_SDA0 (MTK_PIN_NO(119) | 2) +#define PINMUX_GPIO119__FUNC_SCP_SDA1 (MTK_PIN_NO(119) | 3) + +#define PINMUX_GPIO120__FUNC_GPIO120 (MTK_PIN_NO(120) | 0) +#define PINMUX_GPIO120__FUNC_SCL9 (MTK_PIN_NO(120) | 1) +#define PINMUX_GPIO120__FUNC_SCP_SCL0 (MTK_PIN_NO(120) | 2) + +#define PINMUX_GPIO121__FUNC_GPIO121 (MTK_PIN_NO(121) | 0) +#define PINMUX_GPIO121__FUNC_SDA9 (MTK_PIN_NO(121) | 1) +#define PINMUX_GPIO121__FUNC_SCP_SDA0 (MTK_PIN_NO(121) | 2) + +#define PINMUX_GPIO122__FUNC_GPIO122 (MTK_PIN_NO(122) | 0) +#define PINMUX_GPIO122__FUNC_SCL8 (MTK_PIN_NO(122) | 1) +#define PINMUX_GPIO122__FUNC_SCP_SDA0 (MTK_PIN_NO(122) | 2) + +#define PINMUX_GPIO123__FUNC_GPIO123 (MTK_PIN_NO(123) | 0) +#define PINMUX_GPIO123__FUNC_SDA8 (MTK_PIN_NO(123) | 1) +#define PINMUX_GPIO123__FUNC_SCP_SCL0 (MTK_PIN_NO(123) | 2) + +#define PINMUX_GPIO124__FUNC_GPIO124 (MTK_PIN_NO(124) | 0) +#define PINMUX_GPIO124__FUNC_SCL7 (MTK_PIN_NO(124) | 1) +#define PINMUX_GPIO124__FUNC_DMIC1_CLK (MTK_PIN_NO(124) | 2) + +#define PINMUX_GPIO125__FUNC_GPIO125 (MTK_PIN_NO(125) | 0) +#define PINMUX_GPIO125__FUNC_SDA7 (MTK_PIN_NO(125) | 1) +#define PINMUX_GPIO125__FUNC_DMIC1_DAT (MTK_PIN_NO(125) | 2) + +#define PINMUX_GPIO126__FUNC_GPIO126 (MTK_PIN_NO(126) | 0) +#define PINMUX_GPIO126__FUNC_CMFLASH0 (MTK_PIN_NO(126) | 1) +#define PINMUX_GPIO126__FUNC_PWM_2 (MTK_PIN_NO(126) | 2) +#define PINMUX_GPIO126__FUNC_TP_UCTS1_AO (MTK_PIN_NO(126) | 3) +#define PINMUX_GPIO126__FUNC_UCTS0 (MTK_PIN_NO(126) | 4) +#define PINMUX_GPIO126__FUNC_SCL11 (MTK_PIN_NO(126) | 5) +#define PINMUX_GPIO126__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(126) | 6) +#define PINMUX_GPIO126__FUNC_DBG_MON_A14 (MTK_PIN_NO(126) | 7) + +#define PINMUX_GPIO127__FUNC_GPIO127 (MTK_PIN_NO(127) | 0) +#define PINMUX_GPIO127__FUNC_CMFLASH1 (MTK_PIN_NO(127) | 1) +#define PINMUX_GPIO127__FUNC_PWM_3 (MTK_PIN_NO(127) | 2) +#define PINMUX_GPIO127__FUNC_TP_URTS1_AO (MTK_PIN_NO(127) | 3) +#define PINMUX_GPIO127__FUNC_URTS0 (MTK_PIN_NO(127) | 4) +#define PINMUX_GPIO127__FUNC_SDA11 (MTK_PIN_NO(127) | 5) +#define PINMUX_GPIO127__FUNC_DBG_MON_A15 (MTK_PIN_NO(127) | 7) + +#define PINMUX_GPIO128__FUNC_GPIO128 (MTK_PIN_NO(128) | 0) +#define PINMUX_GPIO128__FUNC_CMFLASH2 (MTK_PIN_NO(128) | 1) +#define PINMUX_GPIO128__FUNC_PWM_0 (MTK_PIN_NO(128) | 2) +#define PINMUX_GPIO128__FUNC_TP_UCTS2_AO (MTK_PIN_NO(128) | 3) +#define PINMUX_GPIO128__FUNC_UCTS1 (MTK_PIN_NO(128) | 4) +#define PINMUX_GPIO128__FUNC_SCL_6306 (MTK_PIN_NO(128) | 5) +#define PINMUX_GPIO128__FUNC_DBG_MON_A16 (MTK_PIN_NO(128) | 7) + +#define PINMUX_GPIO129__FUNC_GPIO129 (MTK_PIN_NO(129) | 0) +#define PINMUX_GPIO129__FUNC_CMFLASH3 (MTK_PIN_NO(129) | 1) +#define PINMUX_GPIO129__FUNC_PWM_1 (MTK_PIN_NO(129) | 2) +#define PINMUX_GPIO129__FUNC_TP_URTS2_AO (MTK_PIN_NO(129) | 3) +#define PINMUX_GPIO129__FUNC_URTS1 (MTK_PIN_NO(129) | 4) +#define PINMUX_GPIO129__FUNC_SDA_6306 (MTK_PIN_NO(129) | 5) +#define PINMUX_GPIO129__FUNC_DBG_MON_A17 (MTK_PIN_NO(129) | 7) + +#define PINMUX_GPIO130__FUNC_GPIO130 (MTK_PIN_NO(130) | 0) +#define PINMUX_GPIO130__FUNC_CMVREF0 (MTK_PIN_NO(130) | 1) +#define PINMUX_GPIO130__FUNC_ANT_SEL10 (MTK_PIN_NO(130) | 2) +#define PINMUX_GPIO130__FUNC_SCP_JTAG0_TDO (MTK_PIN_NO(130) | 3) +#define PINMUX_GPIO130__FUNC_MD32_0_JTAG_TDO (MTK_PIN_NO(130) | 4) +#define PINMUX_GPIO130__FUNC_SCL11 (MTK_PIN_NO(130) | 5) +#define PINMUX_GPIO130__FUNC_SPI5_B_CLK (MTK_PIN_NO(130) | 6) +#define PINMUX_GPIO130__FUNC_DBG_MON_A22 (MTK_PIN_NO(130) | 7) + +#define PINMUX_GPIO131__FUNC_GPIO131 (MTK_PIN_NO(131) | 0) +#define PINMUX_GPIO131__FUNC_CMVREF1 (MTK_PIN_NO(131) | 1) +#define PINMUX_GPIO131__FUNC_ANT_SEL11 (MTK_PIN_NO(131) | 2) +#define PINMUX_GPIO131__FUNC_SCP_JTAG0_TDI (MTK_PIN_NO(131) | 3) +#define PINMUX_GPIO131__FUNC_MD32_0_JTAG_TDI (MTK_PIN_NO(131) | 4) +#define PINMUX_GPIO131__FUNC_SDA11 (MTK_PIN_NO(131) | 5) +#define PINMUX_GPIO131__FUNC_SPI5_B_MO (MTK_PIN_NO(131) | 6) +#define PINMUX_GPIO131__FUNC_DBG_MON_A25 (MTK_PIN_NO(131) | 7) + +#define PINMUX_GPIO132__FUNC_GPIO132 (MTK_PIN_NO(132) | 0) +#define PINMUX_GPIO132__FUNC_CMVREF2 (MTK_PIN_NO(132) | 1) +#define PINMUX_GPIO132__FUNC_ANT_SEL12 (MTK_PIN_NO(132) | 2) +#define PINMUX_GPIO132__FUNC_SCP_JTAG0_TMS (MTK_PIN_NO(132) | 3) +#define PINMUX_GPIO132__FUNC_MD32_0_JTAG_TMS (MTK_PIN_NO(132) | 4) +#define PINMUX_GPIO132__FUNC_DBG_MON_A28 (MTK_PIN_NO(132) | 7) + +#define PINMUX_GPIO133__FUNC_GPIO133 (MTK_PIN_NO(133) | 0) +#define PINMUX_GPIO133__FUNC_CMVREF3 (MTK_PIN_NO(133) | 1) +#define PINMUX_GPIO133__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(133) | 2) +#define PINMUX_GPIO133__FUNC_SCP_JTAG0_TCK (MTK_PIN_NO(133) | 3) +#define PINMUX_GPIO133__FUNC_MD32_0_JTAG_TCK (MTK_PIN_NO(133) | 4) +#define PINMUX_GPIO133__FUNC_SPI5_B_CSB (MTK_PIN_NO(133) | 6) +#define PINMUX_GPIO133__FUNC_DBG_MON_A23 (MTK_PIN_NO(133) | 7) + +#define PINMUX_GPIO134__FUNC_GPIO134 (MTK_PIN_NO(134) | 0) +#define PINMUX_GPIO134__FUNC_CMVREF4 (MTK_PIN_NO(134) | 1) +#define PINMUX_GPIO134__FUNC_SCP_JTAG0_TRSTN (MTK_PIN_NO(134) | 3) +#define PINMUX_GPIO134__FUNC_MD32_0_JTAG_TRST (MTK_PIN_NO(134) | 4) +#define PINMUX_GPIO134__FUNC_DBG_MON_A26 (MTK_PIN_NO(134) | 7) + +#define PINMUX_GPIO135__FUNC_GPIO135 (MTK_PIN_NO(135) | 0) +#define PINMUX_GPIO135__FUNC_PWM_0 (MTK_PIN_NO(135) | 1) +#define PINMUX_GPIO135__FUNC_SRCLKENAI1 (MTK_PIN_NO(135) | 2) +#define PINMUX_GPIO135__FUNC_MD_URXD0 (MTK_PIN_NO(135) | 3) +#define PINMUX_GPIO135__FUNC_MD32_0_RXD (MTK_PIN_NO(135) | 4) +#define PINMUX_GPIO135__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(135) | 5) +#define PINMUX_GPIO135__FUNC_DBG_MON_A29 (MTK_PIN_NO(135) | 7) + +#define PINMUX_GPIO136__FUNC_GPIO136 (MTK_PIN_NO(136) | 0) +#define PINMUX_GPIO136__FUNC_CMMCLK3 (MTK_PIN_NO(136) | 1) +#define PINMUX_GPIO136__FUNC_CLKM1 (MTK_PIN_NO(136) | 2) +#define PINMUX_GPIO136__FUNC_MD_UTXD0 (MTK_PIN_NO(136) | 3) +#define PINMUX_GPIO136__FUNC_MD32_0_TXD (MTK_PIN_NO(136) | 4) +#define PINMUX_GPIO136__FUNC_SPI5_B_MI (MTK_PIN_NO(136) | 6) +#define PINMUX_GPIO136__FUNC_DBG_MON_A24 (MTK_PIN_NO(136) | 7) + +#define PINMUX_GPIO137__FUNC_GPIO137 (MTK_PIN_NO(137) | 0) +#define PINMUX_GPIO137__FUNC_CMMCLK4 (MTK_PIN_NO(137) | 1) +#define PINMUX_GPIO137__FUNC_CLKM2 (MTK_PIN_NO(137) | 2) +#define PINMUX_GPIO137__FUNC_MD_URXD1 (MTK_PIN_NO(137) | 3) +#define PINMUX_GPIO137__FUNC_CONN_UART0_RXD (MTK_PIN_NO(137) | 6) +#define PINMUX_GPIO137__FUNC_DBG_MON_A27 (MTK_PIN_NO(137) | 7) + +#define PINMUX_GPIO138__FUNC_GPIO138 (MTK_PIN_NO(138) | 0) +#define PINMUX_GPIO138__FUNC_CMMCLK5 (MTK_PIN_NO(138) | 1) +#define PINMUX_GPIO138__FUNC_CLKM3 (MTK_PIN_NO(138) | 2) +#define PINMUX_GPIO138__FUNC_MD_UTXD1 (MTK_PIN_NO(138) | 3) +#define PINMUX_GPIO138__FUNC_CONN_UART0_TXD (MTK_PIN_NO(138) | 6) +#define PINMUX_GPIO138__FUNC_DBG_MON_A30 (MTK_PIN_NO(138) | 7) + +#define PINMUX_GPIO139__FUNC_GPIO139 (MTK_PIN_NO(139) | 0) +#define PINMUX_GPIO139__FUNC_SCL4 (MTK_PIN_NO(139) | 1) +#define PINMUX_GPIO139__FUNC_DBG_MON_A21 (MTK_PIN_NO(139) | 7) + +#define PINMUX_GPIO140__FUNC_GPIO140 (MTK_PIN_NO(140) | 0) +#define PINMUX_GPIO140__FUNC_SDA4 (MTK_PIN_NO(140) | 1) +#define PINMUX_GPIO140__FUNC_DBG_MON_A20 (MTK_PIN_NO(140) | 7) + +#define PINMUX_GPIO141__FUNC_GPIO141 (MTK_PIN_NO(141) | 0) +#define PINMUX_GPIO141__FUNC_SCL2 (MTK_PIN_NO(141) | 1) +#define PINMUX_GPIO141__FUNC_DBG_MON_A18 (MTK_PIN_NO(141) | 7) + +#define PINMUX_GPIO142__FUNC_GPIO142 (MTK_PIN_NO(142) | 0) +#define PINMUX_GPIO142__FUNC_SDA2 (MTK_PIN_NO(142) | 1) +#define PINMUX_GPIO142__FUNC_DBG_MON_A19 (MTK_PIN_NO(142) | 7) + +#define PINMUX_GPIO143__FUNC_GPIO143 (MTK_PIN_NO(143) | 0) +#define PINMUX_GPIO143__FUNC_CMVREF0 (MTK_PIN_NO(143) | 1) +#define PINMUX_GPIO143__FUNC_SPI3_CLK (MTK_PIN_NO(143) | 2) +#define PINMUX_GPIO143__FUNC_ADSP_JTAG1_TDO (MTK_PIN_NO(143) | 3) +#define PINMUX_GPIO143__FUNC_SCP_JTAG1_TDO (MTK_PIN_NO(143) | 4) +#define PINMUX_GPIO143__FUNC_DBG_MON_A31 (MTK_PIN_NO(143) | 7) + +#define PINMUX_GPIO144__FUNC_GPIO144 (MTK_PIN_NO(144) | 0) +#define PINMUX_GPIO144__FUNC_CMVREF1 (MTK_PIN_NO(144) | 1) +#define PINMUX_GPIO144__FUNC_SPI3_CSB (MTK_PIN_NO(144) | 2) +#define PINMUX_GPIO144__FUNC_ADSP_JTAG1_TDI (MTK_PIN_NO(144) | 3) +#define PINMUX_GPIO144__FUNC_SCP_JTAG1_TDI (MTK_PIN_NO(144) | 4) + +#define PINMUX_GPIO145__FUNC_GPIO145 (MTK_PIN_NO(145) | 0) +#define PINMUX_GPIO145__FUNC_CMVREF2 (MTK_PIN_NO(145) | 1) +#define PINMUX_GPIO145__FUNC_SPI3_MI (MTK_PIN_NO(145) | 2) +#define PINMUX_GPIO145__FUNC_ADSP_JTAG1_TMS (MTK_PIN_NO(145) | 3) +#define PINMUX_GPIO145__FUNC_SCP_JTAG1_TMS (MTK_PIN_NO(145) | 4) + +#define PINMUX_GPIO146__FUNC_GPIO146 (MTK_PIN_NO(146) | 0) +#define PINMUX_GPIO146__FUNC_CMVREF3 (MTK_PIN_NO(146) | 1) +#define PINMUX_GPIO146__FUNC_SPI3_MO (MTK_PIN_NO(146) | 2) +#define PINMUX_GPIO146__FUNC_ADSP_JTAG1_TCK (MTK_PIN_NO(146) | 3) +#define PINMUX_GPIO146__FUNC_SCP_JTAG1_TCK (MTK_PIN_NO(146) | 4) +#define PINMUX_GPIO146__FUNC_DBG_MON_A32 (MTK_PIN_NO(146) | 7) + +#define PINMUX_GPIO147__FUNC_GPIO147 (MTK_PIN_NO(147) | 0) +#define PINMUX_GPIO147__FUNC_CMVREF4 (MTK_PIN_NO(147) | 1) +#define PINMUX_GPIO147__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(147) | 2) +#define PINMUX_GPIO147__FUNC_ADSP_JTAG1_TRSTN (MTK_PIN_NO(147) | 3) +#define PINMUX_GPIO147__FUNC_SCP_JTAG1_TRSTN (MTK_PIN_NO(147) | 4) + +#define PINMUX_GPIO148__FUNC_GPIO148 (MTK_PIN_NO(148) | 0) +#define PINMUX_GPIO148__FUNC_PWM_1 (MTK_PIN_NO(148) | 1) +#define PINMUX_GPIO148__FUNC_AGPS_SYNC (MTK_PIN_NO(148) | 2) +#define PINMUX_GPIO148__FUNC_CMMCLK5 (MTK_PIN_NO(148) | 3) + +#define PINMUX_GPIO149__FUNC_GPIO149 (MTK_PIN_NO(149) | 0) +#define PINMUX_GPIO149__FUNC_CMMCLK0 (MTK_PIN_NO(149) | 1) +#define PINMUX_GPIO149__FUNC_CLKM0 (MTK_PIN_NO(149) | 2) +#define PINMUX_GPIO149__FUNC_MD32_0_GPIO0 (MTK_PIN_NO(149) | 3) + +#define PINMUX_GPIO150__FUNC_GPIO150 (MTK_PIN_NO(150) | 0) +#define PINMUX_GPIO150__FUNC_CMMCLK1 (MTK_PIN_NO(150) | 1) +#define PINMUX_GPIO150__FUNC_CLKM1 (MTK_PIN_NO(150) | 2) +#define PINMUX_GPIO150__FUNC_MD32_0_GPIO1 (MTK_PIN_NO(150) | 3) +#define PINMUX_GPIO150__FUNC_CONN_MCU_AICE_TMSC (MTK_PIN_NO(150) | 7) + +#define PINMUX_GPIO151__FUNC_GPIO151 (MTK_PIN_NO(151) | 0) +#define PINMUX_GPIO151__FUNC_CMMCLK2 (MTK_PIN_NO(151) | 1) +#define PINMUX_GPIO151__FUNC_CLKM2 (MTK_PIN_NO(151) | 2) +#define PINMUX_GPIO151__FUNC_MD32_0_GPIO2 (MTK_PIN_NO(151) | 3) +#define PINMUX_GPIO151__FUNC_CONN_MCU_AICE_TCKC (MTK_PIN_NO(151) | 7) + +#define PINMUX_GPIO152__FUNC_GPIO152 (MTK_PIN_NO(152) | 0) +#define PINMUX_GPIO152__FUNC_KPROW1 (MTK_PIN_NO(152) | 1) +#define PINMUX_GPIO152__FUNC_PWM_2 (MTK_PIN_NO(152) | 2) +#define PINMUX_GPIO152__FUNC_IDDIG (MTK_PIN_NO(152) | 3) +#define PINMUX_GPIO152__FUNC_MBISTREADEN_TRIGGER (MTK_PIN_NO(152) | 6) +#define PINMUX_GPIO152__FUNC_DBG_MON_B9 (MTK_PIN_NO(152) | 7) + +#define PINMUX_GPIO153__FUNC_GPIO153 (MTK_PIN_NO(153) | 0) +#define PINMUX_GPIO153__FUNC_KPROW0 (MTK_PIN_NO(153) | 1) +#define PINMUX_GPIO153__FUNC_DBG_MON_B8 (MTK_PIN_NO(153) | 7) + +#define PINMUX_GPIO154__FUNC_GPIO154 (MTK_PIN_NO(154) | 0) +#define PINMUX_GPIO154__FUNC_KPCOL0 (MTK_PIN_NO(154) | 1) +#define PINMUX_GPIO154__FUNC_DBG_MON_B6 (MTK_PIN_NO(154) | 7) + +#define PINMUX_GPIO155__FUNC_GPIO155 (MTK_PIN_NO(155) | 0) +#define PINMUX_GPIO155__FUNC_KPCOL1 (MTK_PIN_NO(155) | 1) +#define PINMUX_GPIO155__FUNC_PWM_3 (MTK_PIN_NO(155) | 2) +#define PINMUX_GPIO155__FUNC_USB_DRVVBUS (MTK_PIN_NO(155) | 3) +#define PINMUX_GPIO155__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(155) | 4) +#define PINMUX_GPIO155__FUNC_MBISTWRITEEN_TRIGGER (MTK_PIN_NO(155) | 6) +#define PINMUX_GPIO155__FUNC_DBG_MON_B7 (MTK_PIN_NO(155) | 7) + +#define PINMUX_GPIO156__FUNC_GPIO156 (MTK_PIN_NO(156) | 0) +#define PINMUX_GPIO156__FUNC_SPI1_A_CLK (MTK_PIN_NO(156) | 1) +#define PINMUX_GPIO156__FUNC_SCP_SPI1_A_CK (MTK_PIN_NO(156) | 2) +#define PINMUX_GPIO156__FUNC_MRG_CLK (MTK_PIN_NO(156) | 3) +#define PINMUX_GPIO156__FUNC_AGPS_SYNC (MTK_PIN_NO(156) | 4) +#define PINMUX_GPIO156__FUNC_MD_URXD0 (MTK_PIN_NO(156) | 5) +#define PINMUX_GPIO156__FUNC_UDI_TMS (MTK_PIN_NO(156) | 6) +#define PINMUX_GPIO156__FUNC_DBG_MON_B10 (MTK_PIN_NO(156) | 7) + +#define PINMUX_GPIO157__FUNC_GPIO157 (MTK_PIN_NO(157) | 0) +#define PINMUX_GPIO157__FUNC_SPI1_A_CSB (MTK_PIN_NO(157) | 1) +#define PINMUX_GPIO157__FUNC_SCP_SPI1_A_CS (MTK_PIN_NO(157) | 2) +#define PINMUX_GPIO157__FUNC_MRG_SYNC (MTK_PIN_NO(157) | 3) +#define PINMUX_GPIO157__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(157) | 4) +#define PINMUX_GPIO157__FUNC_MD_UTXD0 (MTK_PIN_NO(157) | 5) +#define PINMUX_GPIO157__FUNC_UDI_TCK (MTK_PIN_NO(157) | 6) +#define PINMUX_GPIO157__FUNC_DBG_MON_B11 (MTK_PIN_NO(157) | 7) + +#define PINMUX_GPIO158__FUNC_GPIO158 (MTK_PIN_NO(158) | 0) +#define PINMUX_GPIO158__FUNC_SPI1_A_MI (MTK_PIN_NO(158) | 1) +#define PINMUX_GPIO158__FUNC_SCP_SPI1_A_MI (MTK_PIN_NO(158) | 2) +#define PINMUX_GPIO158__FUNC_MRG_DI (MTK_PIN_NO(158) | 3) +#define PINMUX_GPIO158__FUNC_PTA_RXD (MTK_PIN_NO(158) | 4) +#define PINMUX_GPIO158__FUNC_MD_URXD1 (MTK_PIN_NO(158) | 5) +#define PINMUX_GPIO158__FUNC_UDI_TDO (MTK_PIN_NO(158) | 6) +#define PINMUX_GPIO158__FUNC_DBG_MON_B12 (MTK_PIN_NO(158) | 7) + +#define PINMUX_GPIO159__FUNC_GPIO159 (MTK_PIN_NO(159) | 0) +#define PINMUX_GPIO159__FUNC_SPI1_A_MO (MTK_PIN_NO(159) | 1) +#define PINMUX_GPIO159__FUNC_SCP_SPI1_A_MO (MTK_PIN_NO(159) | 2) +#define PINMUX_GPIO159__FUNC_MRG_DO (MTK_PIN_NO(159) | 3) +#define PINMUX_GPIO159__FUNC_PTA_TXD (MTK_PIN_NO(159) | 4) +#define PINMUX_GPIO159__FUNC_MD_UTXD1 (MTK_PIN_NO(159) | 5) +#define PINMUX_GPIO159__FUNC_UDI_NTRST (MTK_PIN_NO(159) | 6) +#define PINMUX_GPIO159__FUNC_DBG_MON_B13 (MTK_PIN_NO(159) | 7) + +#define PINMUX_GPIO160__FUNC_GPIO160 (MTK_PIN_NO(160) | 0) +#define PINMUX_GPIO160__FUNC_SCL3 (MTK_PIN_NO(160) | 1) +#define PINMUX_GPIO160__FUNC_SCP_SCL1 (MTK_PIN_NO(160) | 3) +#define PINMUX_GPIO160__FUNC_DBG_MON_B14 (MTK_PIN_NO(160) | 7) + +#define PINMUX_GPIO161__FUNC_GPIO161 (MTK_PIN_NO(161) | 0) +#define PINMUX_GPIO161__FUNC_SDA3 (MTK_PIN_NO(161) | 1) +#define PINMUX_GPIO161__FUNC_SCP_SDA1 (MTK_PIN_NO(161) | 3) +#define PINMUX_GPIO161__FUNC_DBG_MON_B15 (MTK_PIN_NO(161) | 7) + +#define PINMUX_GPIO162__FUNC_GPIO162 (MTK_PIN_NO(162) | 0) +#define PINMUX_GPIO162__FUNC_ANT_SEL0 (MTK_PIN_NO(162) | 1) +#define PINMUX_GPIO162__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(162) | 2) +#define PINMUX_GPIO162__FUNC_UDI_TDI (MTK_PIN_NO(162) | 6) +#define PINMUX_GPIO162__FUNC_DBG_MON_B16 (MTK_PIN_NO(162) | 7) + +#define PINMUX_GPIO163__FUNC_GPIO163 (MTK_PIN_NO(163) | 0) +#define PINMUX_GPIO163__FUNC_ANT_SEL1 (MTK_PIN_NO(163) | 1) +#define PINMUX_GPIO163__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(163) | 2) +#define PINMUX_GPIO163__FUNC_DBG_MON_B17 (MTK_PIN_NO(163) | 7) + +#define PINMUX_GPIO164__FUNC_GPIO164 (MTK_PIN_NO(164) | 0) +#define PINMUX_GPIO164__FUNC_ANT_SEL2 (MTK_PIN_NO(164) | 1) +#define PINMUX_GPIO164__FUNC_SCP_SPI1_B_CK (MTK_PIN_NO(164) | 2) +#define PINMUX_GPIO164__FUNC_TP_URXD1_AO (MTK_PIN_NO(164) | 3) +#define PINMUX_GPIO164__FUNC_UCTS0 (MTK_PIN_NO(164) | 5) +#define PINMUX_GPIO164__FUNC_DBG_MON_B18 (MTK_PIN_NO(164) | 7) + +#define PINMUX_GPIO165__FUNC_GPIO165 (MTK_PIN_NO(165) | 0) +#define PINMUX_GPIO165__FUNC_ANT_SEL3 (MTK_PIN_NO(165) | 1) +#define PINMUX_GPIO165__FUNC_SCP_SPI1_B_CS (MTK_PIN_NO(165) | 2) +#define PINMUX_GPIO165__FUNC_TP_UTXD1_AO (MTK_PIN_NO(165) | 3) +#define PINMUX_GPIO165__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(165) | 4) +#define PINMUX_GPIO165__FUNC_URTS0 (MTK_PIN_NO(165) | 5) +#define PINMUX_GPIO165__FUNC_DBG_MON_B19 (MTK_PIN_NO(165) | 7) + +#define PINMUX_GPIO166__FUNC_GPIO166 (MTK_PIN_NO(166) | 0) +#define PINMUX_GPIO166__FUNC_ANT_SEL4 (MTK_PIN_NO(166) | 1) +#define PINMUX_GPIO166__FUNC_SCP_SPI1_B_MI (MTK_PIN_NO(166) | 2) +#define PINMUX_GPIO166__FUNC_TP_URXD2_AO (MTK_PIN_NO(166) | 3) +#define PINMUX_GPIO166__FUNC_SRCLKENAI1 (MTK_PIN_NO(166) | 4) +#define PINMUX_GPIO166__FUNC_UCTS1 (MTK_PIN_NO(166) | 5) +#define PINMUX_GPIO166__FUNC_DBG_MON_B20 (MTK_PIN_NO(166) | 7) + +#define PINMUX_GPIO167__FUNC_GPIO167 (MTK_PIN_NO(167) | 0) +#define PINMUX_GPIO167__FUNC_ANT_SEL5 (MTK_PIN_NO(167) | 1) +#define PINMUX_GPIO167__FUNC_SCP_SPI1_B_MO (MTK_PIN_NO(167) | 2) +#define PINMUX_GPIO167__FUNC_TP_UTXD2_AO (MTK_PIN_NO(167) | 3) +#define PINMUX_GPIO167__FUNC_SRCLKENAI0 (MTK_PIN_NO(167) | 4) +#define PINMUX_GPIO167__FUNC_URTS1 (MTK_PIN_NO(167) | 5) +#define PINMUX_GPIO167__FUNC_DBG_MON_B21 (MTK_PIN_NO(167) | 7) + +#define PINMUX_GPIO168__FUNC_GPIO168 (MTK_PIN_NO(168) | 0) +#define PINMUX_GPIO168__FUNC_ANT_SEL6 (MTK_PIN_NO(168) | 1) +#define PINMUX_GPIO168__FUNC_SPI0_B_CLK (MTK_PIN_NO(168) | 2) +#define PINMUX_GPIO168__FUNC_TP_UCTS1_AO (MTK_PIN_NO(168) | 3) +#define PINMUX_GPIO168__FUNC_KPCOL2 (MTK_PIN_NO(168) | 4) +#define PINMUX_GPIO168__FUNC_MD_UCTS0 (MTK_PIN_NO(168) | 5) +#define PINMUX_GPIO168__FUNC_SCL11 (MTK_PIN_NO(168) | 6) +#define PINMUX_GPIO168__FUNC_DBG_MON_B22 (MTK_PIN_NO(168) | 7) + +#define PINMUX_GPIO169__FUNC_GPIO169 (MTK_PIN_NO(169) | 0) +#define PINMUX_GPIO169__FUNC_ANT_SEL7 (MTK_PIN_NO(169) | 1) +#define PINMUX_GPIO169__FUNC_SPI0_B_CSB (MTK_PIN_NO(169) | 2) +#define PINMUX_GPIO169__FUNC_TP_URTS1_AO (MTK_PIN_NO(169) | 3) +#define PINMUX_GPIO169__FUNC_KPROW2 (MTK_PIN_NO(169) | 4) +#define PINMUX_GPIO169__FUNC_MD_URTS0 (MTK_PIN_NO(169) | 5) +#define PINMUX_GPIO169__FUNC_SDA11 (MTK_PIN_NO(169) | 6) +#define PINMUX_GPIO169__FUNC_DBG_MON_B23 (MTK_PIN_NO(169) | 7) + +#define PINMUX_GPIO170__FUNC_GPIO170 (MTK_PIN_NO(170) | 0) +#define PINMUX_GPIO170__FUNC_ANT_SEL8 (MTK_PIN_NO(170) | 1) +#define PINMUX_GPIO170__FUNC_SPI0_B_MI (MTK_PIN_NO(170) | 2) +#define PINMUX_GPIO170__FUNC_TP_UCTS2_AO (MTK_PIN_NO(170) | 3) +#define PINMUX_GPIO170__FUNC_SRCLKENAI1 (MTK_PIN_NO(170) | 4) +#define PINMUX_GPIO170__FUNC_MD_UCTS1 (MTK_PIN_NO(170) | 5) +#define PINMUX_GPIO170__FUNC_DBG_MON_B24 (MTK_PIN_NO(170) | 7) + +#define PINMUX_GPIO171__FUNC_GPIO171 (MTK_PIN_NO(171) | 0) +#define PINMUX_GPIO171__FUNC_ANT_SEL9 (MTK_PIN_NO(171) | 1) +#define PINMUX_GPIO171__FUNC_SPI0_B_MO (MTK_PIN_NO(171) | 2) +#define PINMUX_GPIO171__FUNC_TP_URTS2_AO (MTK_PIN_NO(171) | 3) +#define PINMUX_GPIO171__FUNC_SRCLKENAI0 (MTK_PIN_NO(171) | 4) +#define PINMUX_GPIO171__FUNC_MD_URTS1 (MTK_PIN_NO(171) | 5) +#define PINMUX_GPIO171__FUNC_DBG_MON_B25 (MTK_PIN_NO(171) | 7) + +#define PINMUX_GPIO172__FUNC_GPIO172 (MTK_PIN_NO(172) | 0) +#define PINMUX_GPIO172__FUNC_CONN_TOP_CLK (MTK_PIN_NO(172) | 1) +#define PINMUX_GPIO172__FUNC_AUXIF_CLK0 (MTK_PIN_NO(172) | 2) +#define PINMUX_GPIO172__FUNC_DBG_MON_B29 (MTK_PIN_NO(172) | 7) + +#define PINMUX_GPIO173__FUNC_GPIO173 (MTK_PIN_NO(173) | 0) +#define PINMUX_GPIO173__FUNC_CONN_TOP_DATA (MTK_PIN_NO(173) | 1) +#define PINMUX_GPIO173__FUNC_AUXIF_ST0 (MTK_PIN_NO(173) | 2) +#define PINMUX_GPIO173__FUNC_DBG_MON_B30 (MTK_PIN_NO(173) | 7) + +#define PINMUX_GPIO174__FUNC_GPIO174 (MTK_PIN_NO(174) | 0) +#define PINMUX_GPIO174__FUNC_CONN_HRST_B (MTK_PIN_NO(174) | 1) +#define PINMUX_GPIO174__FUNC_DBG_MON_B28 (MTK_PIN_NO(174) | 7) + +#define PINMUX_GPIO175__FUNC_GPIO175 (MTK_PIN_NO(175) | 0) +#define PINMUX_GPIO175__FUNC_CONN_WB_PTA (MTK_PIN_NO(175) | 1) +#define PINMUX_GPIO175__FUNC_DBG_MON_B31 (MTK_PIN_NO(175) | 7) + +#define PINMUX_GPIO176__FUNC_GPIO176 (MTK_PIN_NO(176) | 0) +#define PINMUX_GPIO176__FUNC_CONN_BT_CLK (MTK_PIN_NO(176) | 1) +#define PINMUX_GPIO176__FUNC_AUXIF_CLK1 (MTK_PIN_NO(176) | 2) +#define PINMUX_GPIO176__FUNC_DBG_MON_B26 (MTK_PIN_NO(176) | 7) + +#define PINMUX_GPIO177__FUNC_GPIO177 (MTK_PIN_NO(177) | 0) +#define PINMUX_GPIO177__FUNC_CONN_BT_DATA (MTK_PIN_NO(177) | 1) +#define PINMUX_GPIO177__FUNC_AUXIF_ST1 (MTK_PIN_NO(177) | 2) +#define PINMUX_GPIO177__FUNC_DBG_MON_B27 (MTK_PIN_NO(177) | 7) + +#define PINMUX_GPIO178__FUNC_GPIO178 (MTK_PIN_NO(178) | 0) +#define PINMUX_GPIO178__FUNC_CONN_WF_CTRL0 (MTK_PIN_NO(178) | 1) + +#define PINMUX_GPIO179__FUNC_GPIO179 (MTK_PIN_NO(179) | 0) +#define PINMUX_GPIO179__FUNC_CONN_WF_CTRL1 (MTK_PIN_NO(179) | 1) +#define PINMUX_GPIO179__FUNC_UFS_MPHY_SCL (MTK_PIN_NO(179) | 2) + +#define PINMUX_GPIO180__FUNC_GPIO180 (MTK_PIN_NO(180) | 0) +#define PINMUX_GPIO180__FUNC_CONN_WF_CTRL2 (MTK_PIN_NO(180) | 1) +#define PINMUX_GPIO180__FUNC_UFS_MPHY_SDA (MTK_PIN_NO(180) | 2) + +#define PINMUX_GPIO181__FUNC_GPIO181 (MTK_PIN_NO(181) | 0) +#define PINMUX_GPIO181__FUNC_CONN_WF_CTRL3 (MTK_PIN_NO(181) | 1) + +#define PINMUX_GPIO182__FUNC_GPIO182 (MTK_PIN_NO(182) | 0) +#define PINMUX_GPIO182__FUNC_CONN_WF_CTRL4 (MTK_PIN_NO(182) | 1) + +#define PINMUX_GPIO183__FUNC_GPIO183 (MTK_PIN_NO(183) | 0) +#define PINMUX_GPIO183__FUNC_MSDC0_CMD (MTK_PIN_NO(183) | 1) + +#define PINMUX_GPIO184__FUNC_GPIO184 (MTK_PIN_NO(184) | 0) +#define PINMUX_GPIO184__FUNC_MSDC0_DAT0 (MTK_PIN_NO(184) | 1) + +#define PINMUX_GPIO185__FUNC_GPIO185 (MTK_PIN_NO(185) | 0) +#define PINMUX_GPIO185__FUNC_MSDC0_DAT2 (MTK_PIN_NO(185) | 1) + +#define PINMUX_GPIO186__FUNC_GPIO186 (MTK_PIN_NO(186) | 0) +#define PINMUX_GPIO186__FUNC_MSDC0_DAT4 (MTK_PIN_NO(186) | 1) + +#define PINMUX_GPIO187__FUNC_GPIO187 (MTK_PIN_NO(187) | 0) +#define PINMUX_GPIO187__FUNC_MSDC0_DAT6 (MTK_PIN_NO(187) | 1) + +#define PINMUX_GPIO188__FUNC_GPIO188 (MTK_PIN_NO(188) | 0) +#define PINMUX_GPIO188__FUNC_MSDC0_DAT1 (MTK_PIN_NO(188) | 1) + +#define PINMUX_GPIO189__FUNC_GPIO189 (MTK_PIN_NO(189) | 0) +#define PINMUX_GPIO189__FUNC_MSDC0_DAT5 (MTK_PIN_NO(189) | 1) + +#define PINMUX_GPIO190__FUNC_GPIO190 (MTK_PIN_NO(190) | 0) +#define PINMUX_GPIO190__FUNC_MSDC0_DAT7 (MTK_PIN_NO(190) | 1) + +#define PINMUX_GPIO191__FUNC_GPIO191 (MTK_PIN_NO(191) | 0) +#define PINMUX_GPIO191__FUNC_MSDC0_DSL (MTK_PIN_NO(191) | 1) +#define PINMUX_GPIO191__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(191) | 2) +#define PINMUX_GPIO191__FUNC_IDDIG (MTK_PIN_NO(191) | 3) +#define PINMUX_GPIO191__FUNC_DMIC_CLK (MTK_PIN_NO(191) | 4) + +#define PINMUX_GPIO192__FUNC_GPIO192 (MTK_PIN_NO(192) | 0) +#define PINMUX_GPIO192__FUNC_MSDC0_CLK (MTK_PIN_NO(192) | 1) +#define PINMUX_GPIO192__FUNC_USB_DRVVBUS (MTK_PIN_NO(192) | 3) +#define PINMUX_GPIO192__FUNC_DMIC_DAT (MTK_PIN_NO(192) | 4) + +#define PINMUX_GPIO193__FUNC_GPIO193 (MTK_PIN_NO(193) | 0) +#define PINMUX_GPIO193__FUNC_MSDC0_DAT3 (MTK_PIN_NO(193) | 1) + +#define PINMUX_GPIO194__FUNC_GPIO194 (MTK_PIN_NO(194) | 0) +#define PINMUX_GPIO194__FUNC_MSDC0_RSTB (MTK_PIN_NO(194) | 1) + +#define PINMUX_GPIO195__FUNC_GPIO195 (MTK_PIN_NO(195) | 0) +#define PINMUX_GPIO195__FUNC_SCP_VREQ_VAO (MTK_PIN_NO(195) | 1) +#define PINMUX_GPIO195__FUNC_DVFSRC_EXT_REQ (MTK_PIN_NO(195) | 2) + +#define PINMUX_GPIO196__FUNC_GPIO196 (MTK_PIN_NO(196) | 0) +#define PINMUX_GPIO196__FUNC_AUD_DAT_MOSI2 (MTK_PIN_NO(196) | 1) + +#define PINMUX_GPIO197__FUNC_GPIO197 (MTK_PIN_NO(197) | 0) +#define PINMUX_GPIO197__FUNC_AUD_NLE_MOSI1 (MTK_PIN_NO(197) | 1) +#define PINMUX_GPIO197__FUNC_AUD_CLK_MISO (MTK_PIN_NO(197) | 2) +#define PINMUX_GPIO197__FUNC_I2S2_MCK (MTK_PIN_NO(197) | 3) +#define PINMUX_GPIO197__FUNC_I2S6_MCK (MTK_PIN_NO(197) | 4) +#define PINMUX_GPIO197__FUNC_I2S8_MCK (MTK_PIN_NO(197) | 5) + +#define PINMUX_GPIO198__FUNC_GPIO198 (MTK_PIN_NO(198) | 0) +#define PINMUX_GPIO198__FUNC_AUD_NLE_MOSI0 (MTK_PIN_NO(198) | 1) +#define PINMUX_GPIO198__FUNC_AUD_SYNC_MISO (MTK_PIN_NO(198) | 2) +#define PINMUX_GPIO198__FUNC_I2S2_BCK (MTK_PIN_NO(198) | 3) +#define PINMUX_GPIO198__FUNC_I2S6_BCK (MTK_PIN_NO(198) | 4) +#define PINMUX_GPIO198__FUNC_I2S8_BCK (MTK_PIN_NO(198) | 5) + +#define PINMUX_GPIO199__FUNC_GPIO199 (MTK_PIN_NO(199) | 0) +#define PINMUX_GPIO199__FUNC_AUD_DAT_MISO2 (MTK_PIN_NO(199) | 1) +#define PINMUX_GPIO199__FUNC_I2S2_DI2 (MTK_PIN_NO(199) | 3) + +#define PINMUX_GPIO200__FUNC_GPIO200 (MTK_PIN_NO(200) | 0) +#define PINMUX_GPIO200__FUNC_SCL6 (MTK_PIN_NO(200) | 1) +#define PINMUX_GPIO200__FUNC_SCP_SCL1 (MTK_PIN_NO(200) | 3) +#define PINMUX_GPIO200__FUNC_SCL_6306 (MTK_PIN_NO(200) | 4) +#define PINMUX_GPIO200__FUNC_DBG_MON_A4 (MTK_PIN_NO(200) | 7) + +#define PINMUX_GPIO201__FUNC_GPIO201 (MTK_PIN_NO(201) | 0) +#define PINMUX_GPIO201__FUNC_SDA6 (MTK_PIN_NO(201) | 1) +#define PINMUX_GPIO201__FUNC_SCP_SDA1 (MTK_PIN_NO(201) | 3) +#define PINMUX_GPIO201__FUNC_SDA_6306 (MTK_PIN_NO(201) | 4) +#define PINMUX_GPIO201__FUNC_DBG_MON_A5 (MTK_PIN_NO(201) | 7) + +#define PINMUX_GPIO202__FUNC_GPIO202 (MTK_PIN_NO(202) | 0) +#define PINMUX_GPIO202__FUNC_SCL5 (MTK_PIN_NO(202) | 1) + +#define PINMUX_GPIO203__FUNC_GPIO203 (MTK_PIN_NO(203) | 0) +#define PINMUX_GPIO203__FUNC_SDA5 (MTK_PIN_NO(203) | 1) + +#define PINMUX_GPIO204__FUNC_GPIO204 (MTK_PIN_NO(204) | 0) +#define PINMUX_GPIO204__FUNC_SCL0 (MTK_PIN_NO(204) | 1) +#define PINMUX_GPIO204__FUNC_SPI7_A_CLK (MTK_PIN_NO(204) | 6) +#define PINMUX_GPIO204__FUNC_DBG_MON_A2 (MTK_PIN_NO(204) | 7) + +#define PINMUX_GPIO205__FUNC_GPIO205 (MTK_PIN_NO(205) | 0) +#define PINMUX_GPIO205__FUNC_SDA0 (MTK_PIN_NO(205) | 1) +#define PINMUX_GPIO205__FUNC_SPI7_A_CSB (MTK_PIN_NO(205) | 6) +#define PINMUX_GPIO205__FUNC_DBG_MON_A3 (MTK_PIN_NO(205) | 7) + +#define PINMUX_GPIO206__FUNC_GPIO206 (MTK_PIN_NO(206) | 0) +#define PINMUX_GPIO206__FUNC_SRCLKENA0 (MTK_PIN_NO(206) | 1) + +#define PINMUX_GPIO207__FUNC_GPIO207 (MTK_PIN_NO(207) | 0) +#define PINMUX_GPIO207__FUNC_SRCLKENA1 (MTK_PIN_NO(207) | 1) + +#define PINMUX_GPIO208__FUNC_GPIO208 (MTK_PIN_NO(208) | 0) +#define PINMUX_GPIO208__FUNC_WATCHDOG (MTK_PIN_NO(208) | 1) + +#define PINMUX_GPIO209__FUNC_GPIO209 (MTK_PIN_NO(209) | 0) +#define PINMUX_GPIO209__FUNC_PWRAP_SPI0_MI (MTK_PIN_NO(209) | 1) +#define PINMUX_GPIO209__FUNC_PWRAP_SPI0_MO (MTK_PIN_NO(209) | 2) + +#define PINMUX_GPIO210__FUNC_GPIO210 (MTK_PIN_NO(210) | 0) +#define PINMUX_GPIO210__FUNC_PWRAP_SPI0_CSN (MTK_PIN_NO(210) | 1) + +#define PINMUX_GPIO211__FUNC_GPIO211 (MTK_PIN_NO(211) | 0) +#define PINMUX_GPIO211__FUNC_PWRAP_SPI0_MO (MTK_PIN_NO(211) | 1) +#define PINMUX_GPIO211__FUNC_PWRAP_SPI0_MI (MTK_PIN_NO(211) | 2) + +#define PINMUX_GPIO212__FUNC_GPIO212 (MTK_PIN_NO(212) | 0) +#define PINMUX_GPIO212__FUNC_PWRAP_SPI0_CK (MTK_PIN_NO(212) | 1) + +#define PINMUX_GPIO213__FUNC_GPIO213 (MTK_PIN_NO(213) | 0) +#define PINMUX_GPIO213__FUNC_RTC32K_CK (MTK_PIN_NO(213) | 1) + +#define PINMUX_GPIO214__FUNC_GPIO214 (MTK_PIN_NO(214) | 0) +#define PINMUX_GPIO214__FUNC_AUD_CLK_MOSI (MTK_PIN_NO(214) | 1) +#define PINMUX_GPIO214__FUNC_I2S1_MCK (MTK_PIN_NO(214) | 3) +#define PINMUX_GPIO214__FUNC_I2S7_MCK (MTK_PIN_NO(214) | 4) +#define PINMUX_GPIO214__FUNC_I2S9_MCK (MTK_PIN_NO(214) | 5) + +#define PINMUX_GPIO215__FUNC_GPIO215 (MTK_PIN_NO(215) | 0) +#define PINMUX_GPIO215__FUNC_AUD_SYNC_MOSI (MTK_PIN_NO(215) | 1) +#define PINMUX_GPIO215__FUNC_I2S1_BCK (MTK_PIN_NO(215) | 3) +#define PINMUX_GPIO215__FUNC_I2S7_BCK (MTK_PIN_NO(215) | 4) +#define PINMUX_GPIO215__FUNC_I2S9_BCK (MTK_PIN_NO(215) | 5) + +#define PINMUX_GPIO216__FUNC_GPIO216 (MTK_PIN_NO(216) | 0) +#define PINMUX_GPIO216__FUNC_AUD_DAT_MOSI0 (MTK_PIN_NO(216) | 1) +#define PINMUX_GPIO216__FUNC_I2S1_LRCK (MTK_PIN_NO(216) | 3) +#define PINMUX_GPIO216__FUNC_I2S7_LRCK (MTK_PIN_NO(216) | 4) +#define PINMUX_GPIO216__FUNC_I2S9_LRCK (MTK_PIN_NO(216) | 5) + +#define PINMUX_GPIO217__FUNC_GPIO217 (MTK_PIN_NO(217) | 0) +#define PINMUX_GPIO217__FUNC_AUD_DAT_MOSI1 (MTK_PIN_NO(217) | 1) +#define PINMUX_GPIO217__FUNC_I2S1_DO (MTK_PIN_NO(217) | 3) +#define PINMUX_GPIO217__FUNC_I2S7_DO (MTK_PIN_NO(217) | 4) +#define PINMUX_GPIO217__FUNC_I2S9_DO (MTK_PIN_NO(217) | 5) + +#define PINMUX_GPIO218__FUNC_GPIO218 (MTK_PIN_NO(218) | 0) +#define PINMUX_GPIO218__FUNC_AUD_DAT_MISO0 (MTK_PIN_NO(218) | 1) +#define PINMUX_GPIO218__FUNC_VOW_DAT_MISO (MTK_PIN_NO(218) | 2) +#define PINMUX_GPIO218__FUNC_I2S2_LRCK (MTK_PIN_NO(218) | 3) +#define PINMUX_GPIO218__FUNC_I2S6_LRCK (MTK_PIN_NO(218) | 4) +#define PINMUX_GPIO218__FUNC_I2S8_LRCK (MTK_PIN_NO(218) | 5) + +#define PINMUX_GPIO219__FUNC_GPIO219 (MTK_PIN_NO(219) | 0) +#define PINMUX_GPIO219__FUNC_AUD_DAT_MISO1 (MTK_PIN_NO(219) | 1) +#define PINMUX_GPIO219__FUNC_VOW_CLK_MISO (MTK_PIN_NO(219) | 2) +#define PINMUX_GPIO219__FUNC_I2S2_DI (MTK_PIN_NO(219) | 3) +#define PINMUX_GPIO219__FUNC_I2S6_DI (MTK_PIN_NO(219) | 4) +#define PINMUX_GPIO219__FUNC_I2S8_DI (MTK_PIN_NO(219) | 5) + +#endif /* __MT8192_PINFUNC_H */ -- cgit v1.2.3 From 2da45b8f069644604e8e05ccb03b2b66ada611d5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:49 +0200 Subject: mtd: rawnand: Add a kernel doc to the ECC algorithm enumeration Before moving it to the generic raw NAND core, ensure the enumeration is properly described. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a725b620aca2..1495f22b60cb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -92,6 +92,13 @@ enum nand_ecc_mode { NAND_ECC_ON_DIE, }; +/** + * enum nand_ecc_algo - NAND ECC algorithm + * @NAND_ECC_UNKNOWN: Unknown algorithm + * @NAND_ECC_HAMMING: Hamming algorithm + * @NAND_ECC_BCH: Bose-Chaudhuri-Hocquenghem algorithm + * @NAND_ECC_RS: Reed-Solomon algorithm + */ enum nand_ecc_algo { NAND_ECC_UNKNOWN, NAND_ECC_HAMMING, -- cgit v1.2.3 From e0a564ae0a4bc1bcf156d468955b27d3606e8253 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:50 +0200 Subject: mtd: rawnand: Rename the ECC algorithm enumeration items NAND_ECC_ is not a meaningful prefix, use NAND_ECC_ALGO_ instead. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-3-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 1495f22b60cb..8174c0c331a1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -94,16 +94,16 @@ enum nand_ecc_mode { /** * enum nand_ecc_algo - NAND ECC algorithm - * @NAND_ECC_UNKNOWN: Unknown algorithm - * @NAND_ECC_HAMMING: Hamming algorithm - * @NAND_ECC_BCH: Bose-Chaudhuri-Hocquenghem algorithm - * @NAND_ECC_RS: Reed-Solomon algorithm + * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm + * @NAND_ECC_ALGO_HAMMING: Hamming algorithm + * @NAND_ECC_ALGO_BCH: Bose-Chaudhuri-Hocquenghem algorithm + * @NAND_ECC_ALGO_RS: Reed-Solomon algorithm */ enum nand_ecc_algo { - NAND_ECC_UNKNOWN, - NAND_ECC_HAMMING, - NAND_ECC_BCH, - NAND_ECC_RS, + NAND_ECC_ALGO_UNKNOWN, + NAND_ECC_ALGO_HAMMING, + NAND_ECC_ALGO_BCH, + NAND_ECC_ALGO_RS, }; /* -- cgit v1.2.3 From f2f64c1e924131878179da64794d9cb18ee5c827 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:51 +0200 Subject: mtd: rawnand: Move the nand_ecc_algo enum to the generic NAND layer This enumeration is generic and will be reused NAND-wide. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-4-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 14 ++++++++++++++ include/linux/mtd/rawnand.h | 14 -------------- 2 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index af99041ceaa9..986c7de83326 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -115,6 +115,20 @@ struct nand_page_io_req { int mode; }; +/** + * enum nand_ecc_algo - NAND ECC algorithm + * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm + * @NAND_ECC_ALGO_HAMMING: Hamming algorithm + * @NAND_ECC_ALGO_BCH: Bose-Chaudhuri-Hocquenghem algorithm + * @NAND_ECC_ALGO_RS: Reed-Solomon algorithm + */ +enum nand_ecc_algo { + NAND_ECC_ALGO_UNKNOWN, + NAND_ECC_ALGO_HAMMING, + NAND_ECC_ALGO_BCH, + NAND_ECC_ALGO_RS, +}; + /** * struct nand_ecc_props - NAND ECC properties * @strength: ECC strength diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8174c0c331a1..10bbfbf4ad7f 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -92,20 +92,6 @@ enum nand_ecc_mode { NAND_ECC_ON_DIE, }; -/** - * enum nand_ecc_algo - NAND ECC algorithm - * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm - * @NAND_ECC_ALGO_HAMMING: Hamming algorithm - * @NAND_ECC_ALGO_BCH: Bose-Chaudhuri-Hocquenghem algorithm - * @NAND_ECC_ALGO_RS: Reed-Solomon algorithm - */ -enum nand_ecc_algo { - NAND_ECC_ALGO_UNKNOWN, - NAND_ECC_ALGO_HAMMING, - NAND_ECC_ALGO_BCH, - NAND_ECC_ALGO_RS, -}; - /* * Constants for Hardware ECC */ -- cgit v1.2.3 From 701981cab01696584a12e5f0e7c2ad931a326059 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:52 +0200 Subject: mtd: nand: Add a NAND page I/O request type Use an enum to differentiate the type of I/O (reading or writing a page). Also update the request iterator. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-5-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 986c7de83326..e754a6fc8a4b 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -82,8 +82,19 @@ struct nand_pos { unsigned int page; }; +/** + * enum nand_page_io_req_type - Direction of an I/O request + * @NAND_PAGE_READ: from the chip, to the controller + * @NAND_PAGE_WRITE: from the controller, to the chip + */ +enum nand_page_io_req_type { + NAND_PAGE_READ = 0, + NAND_PAGE_WRITE, +}; + /** * struct nand_page_io_req - NAND I/O request object + * @type: the type of page I/O: read or write * @pos: the position this I/O request is targeting * @dataoffs: the offset within the page * @datalen: number of data bytes to read from/write to this page @@ -99,6 +110,7 @@ struct nand_pos { * specific commands/operations. */ struct nand_page_io_req { + enum nand_page_io_req_type type; struct nand_pos pos; unsigned int dataoffs; unsigned int datalen; @@ -638,11 +650,13 @@ static inline void nanddev_pos_next_page(struct nand_device *nand, * layer. */ static inline void nanddev_io_iter_init(struct nand_device *nand, + enum nand_page_io_req_type reqtype, loff_t offs, struct mtd_oob_ops *req, struct nand_io_iter *iter) { struct mtd_info *mtd = nanddev_to_mtd(nand); + iter->req.type = reqtype; iter->req.mode = req->mode; iter->req.dataoffs = nanddev_offs_to_pos(nand, offs, &iter->req.pos); iter->req.ooboffs = req->ooboffs; @@ -712,8 +726,8 @@ static inline bool nanddev_io_iter_end(struct nand_device *nand, * * Should be used for iterate over pages that are contained in an MTD request. */ -#define nanddev_io_for_each_page(nand, start, req, iter) \ - for (nanddev_io_iter_init(nand, start, req, iter); \ +#define nanddev_io_for_each_page(nand, type, start, req, iter) \ + for (nanddev_io_iter_init(nand, type, start, req, iter); \ !nanddev_io_iter_end(nand, iter); \ nanddev_io_iter_next_page(nand, iter)) -- cgit v1.2.3 From 493a0ebd804c986e6bd207603c5e1ca748470d3d Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 13 Apr 2020 09:20:53 -0700 Subject: nl80211: fix PORT_AUTHORIZED wording to reflect behavior The CMD_PORT_AUTHORIZED event was described as an event which indicated a successfully completed 4-way handshake. But the behavior was not as advertized. The only driver which uses this is brcmfmac, and this driver only sends the event after a successful 802.1X-FT roam. This prevents userspace applications from knowing if the 4-way completed on: 1. Normal 802.1X connects 2. Normal PSK connections 3. FT-PSK roams wpa_supplicant handles this incorrect behavior by just completing the connection after association, before the 4-way has completed. If the 4-way ends up failing it disconnects at that point. Since this behavior appears to be expected (wpa_s handles it this way) I have changed the wording in the API description to reflect the actual behavior. Signed-off-by: James Prestwood Link: https://lore.kernel.org/r/20200413162053.3711-1-prestwoj@gmail.com [fix spelling of 802.1X throughout ...] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 631f3a997b3c..8cc2b825e4e4 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -647,13 +647,9 @@ * authentication/association or not receiving a response from the AP. * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as * well to remain backwards compatible. - * When establishing a security association, drivers that support 4 way - * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when - * the 4 way handshake is completed successfully. * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself. - * When a security association was established with the new AP (e.g. if - * the FT protocol was used for roaming or the driver completed the 4 way - * handshake), this event should be followed by an + * When a security association was established on an 802.1X network using + * fast transition, this event should be followed by an * %NL80211_CMD_PORT_AUTHORIZED event. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other @@ -1067,13 +1063,11 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * %NL80211_ATTR_MAC. - * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way - * handshake was completed successfully by the driver. The BSSID is - * specified with %NL80211_ATTR_MAC. Drivers that support 4 way handshake - * offload should send this event after indicating 802.11 association with - * %NL80211_CMD_CONNECT or %NL80211_CMD_ROAM. If the 4 way handshake failed - * %NL80211_CMD_DISCONNECT should be indicated instead. - * + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was + * completed successfully. Drivers that support 4 way handshake offload + * should send this event after indicating 802.1X FT assocation with + * %NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT + * should be indicated instead. * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request * and RX notification. This command is used both as a request to transmit * a control port frame and as a notification that a control port frame -- cgit v1.2.3 From 7c4b1ab9f16732fb921b3f11cd127fa65f26ad5c Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Tue, 18 Aug 2020 14:52:45 +0300 Subject: IB/mlx5: Add DCT RoCE LAG support When DCT QPs work in RoCE LAG mode: 1. DCT creation is allowed only when it is supported 2. The "port" of a DCT QP is assigned in a round-robin way Link: https://lore.kernel.org/r/20200818115245.700581-3-leon@kernel.org Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index de1ffb4804d6..aee25e4fb2cc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1430,7 +1430,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_bf_reg_size[0x5]; - u8 reserved_at_270[0x8]; + u8 reserved_at_270[0x6]; + u8 lag_dct[0x2]; u8 lag_tx_port_affinity[0x1]; u8 reserved_at_279[0x2]; u8 lag_master[0x1]; -- cgit v1.2.3 From d114c6feedfe0600c19b9f9479a4026354d1f7fd Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 18 Aug 2020 15:05:18 +0300 Subject: RDMA/cma: Add missing locking to rdma_accept() In almost all cases rdma_accept() is called under the handler_mutex by ULPs from their handler callbacks. The one exception was ucma which did not get the handler_mutex. To improve the understand-ability of the locking scheme obtain the mutex for ucma as well. This improves how ucma works by allowing it to directly use handler_mutex for some of its internal locking against the handler callbacks intead of the global file->mut lock. There does not seem to be a serious bug here, other than a DISCONNECT event can be delivered concurrently with accept succeeding. Link: https://lore.kernel.org/r/20200818120526.702120-7-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/rdma_cm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index cf5da2ae49bf..c1334c9a7aa8 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -253,6 +253,8 @@ int rdma_listen(struct rdma_cm_id *id, int backlog); int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, const char *caller); +void rdma_lock_handler(struct rdma_cm_id *id); +void rdma_unlock_handler(struct rdma_cm_id *id); int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, const char *caller, struct rdma_ucm_ece *ece); @@ -270,6 +272,9 @@ int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, * In the case of error, a reject message is sent to the remote side and the * state of the qp associated with the id is modified to error, such that any * previously posted receive buffers would be flushed. + * + * This function is for use by kernel ULPs and must be called from under the + * handler callback. */ #define rdma_accept(id, conn_param) \ __rdma_accept((id), (conn_param), KBUILD_MODNAME) -- cgit v1.2.3 From eb89a6a6b7a1af2d9c8d83ee44fa67700d6337e7 Mon Sep 17 00:00:00 2001 From: Miles Hu Date: Tue, 4 Aug 2020 10:16:29 +0200 Subject: nl80211: add support for setting fixed HE rate/gi/ltf This patch adds the nl80211 structs, definitions, policies and parsing code required to pass fixed HE rate, GI and LTF settings. Signed-off-by: Miles Hu Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20200804081630.2013619-1-john@phrozen.org [fix comment] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 3 +++ include/uapi/linux/nl80211.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d9e6b9fbd95b..c9bce9bba511 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -678,7 +678,10 @@ struct cfg80211_bitrate_mask { u32 legacy; u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mcs[NL80211_VHT_NSS_MAX]; + u16 he_mcs[NL80211_HE_NSS_MAX]; enum nl80211_txrate_gi gi; + enum nl80211_he_gi he_gi; + enum nl80211_he_ltf he_ltf; } control[NUM_NL80211_BANDS]; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8cc2b825e4e4..1a4b922f489f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3180,6 +3180,18 @@ enum nl80211_he_gi { NL80211_RATE_INFO_HE_GI_3_2, }; +/** + * enum nl80211_he_ltf - HE long training field + * @NL80211_RATE_INFO_HE_1xLTF: 3.2 usec + * @NL80211_RATE_INFO_HE_2xLTF: 6.4 usec + * @NL80211_RATE_INFO_HE_4xLTF: 12.8 usec + */ +enum nl80211_he_ltf { + NL80211_RATE_INFO_HE_1XLTF, + NL80211_RATE_INFO_HE_2XLTF, + NL80211_RATE_INFO_HE_4XLTF, +}; + /** * enum nl80211_he_ru_alloc - HE RU allocation values * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation @@ -4735,6 +4747,10 @@ enum nl80211_key_attributes { * @NL80211_TXRATE_VHT: VHT rates allowed for TX rate selection, * see &struct nl80211_txrate_vht * @NL80211_TXRATE_GI: configure GI, see &enum nl80211_txrate_gi + * @NL80211_TXRATE_HE: HE rates allowed for TX rate selection, + * see &struct nl80211_txrate_he + * @NL80211_TXRATE_HE_GI: configure HE GI, 0.8us, 1.6us and 3.2us. + * @NL80211_TXRATE_HE_LTF: configure HE LTF, 1XLTF, 2XLTF and 4XLTF. * @__NL80211_TXRATE_AFTER_LAST: internal * @NL80211_TXRATE_MAX: highest TX rate attribute */ @@ -4744,6 +4760,9 @@ enum nl80211_tx_rate_attributes { NL80211_TXRATE_HT, NL80211_TXRATE_VHT, NL80211_TXRATE_GI, + NL80211_TXRATE_HE, + NL80211_TXRATE_HE_GI, + NL80211_TXRATE_HE_LTF, /* keep last */ __NL80211_TXRATE_AFTER_LAST, @@ -4761,6 +4780,15 @@ struct nl80211_txrate_vht { __u16 mcs[NL80211_VHT_NSS_MAX]; }; +#define NL80211_HE_NSS_MAX 8 +/** + * struct nl80211_txrate_he - HE MCS/NSS txrate bitmap + * @mcs: MCS bitmap table for each NSS (array index 0 for 1 stream, etc.) + */ +struct nl80211_txrate_he { + __u16 mcs[NL80211_HE_NSS_MAX]; +}; + enum nl80211_txrate_gi { NL80211_TXRATE_DEFAULT_GI, NL80211_TXRATE_FORCE_SGI, -- cgit v1.2.3 From 00c207edfb2bff9cf03a8f21e57c9c752a1d9f16 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Tue, 11 Aug 2020 10:01:03 +0200 Subject: nl80211: rename csa counter attributes countdown counters We want to reuse the attributes for other counters such as BSS color change. Rename them to more generic names. Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20200811080107.3615705-1-john@phrozen.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1a4b922f489f..ec96d5fe0e05 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2076,10 +2076,10 @@ enum nl80211_commands { * operation). * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information * for the time while performing a channel switch. - * @NL80211_ATTR_CSA_C_OFF_BEACON: An array of offsets (u16) to the channel - * switch counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). - * @NL80211_ATTR_CSA_C_OFF_PRESP: An array of offsets (u16) to the channel - * switch counters in the probe response (%NL80211_ATTR_PROBE_RESP). + * @NL80211_ATTR_CNTDWN_OFFS_BEACON: An array of offsets (u16) to the channel + * switch or color change counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). + * @NL80211_ATTR_CNTDWN_OFFS_PRESP: An array of offsets (u16) to the channel + * switch or color change counters in the probe response (%NL80211_ATTR_PROBE_RESP). * * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32. * As specified in the &enum nl80211_rxmgmt_flags. @@ -2815,8 +2815,8 @@ enum nl80211_attrs { NL80211_ATTR_CH_SWITCH_COUNT, NL80211_ATTR_CH_SWITCH_BLOCK_TX, NL80211_ATTR_CSA_IES, - NL80211_ATTR_CSA_C_OFF_BEACON, - NL80211_ATTR_CSA_C_OFF_PRESP, + NL80211_ATTR_CNTDWN_OFFS_BEACON, + NL80211_ATTR_CNTDWN_OFFS_PRESP, NL80211_ATTR_RXMGMT_FLAGS, @@ -3003,6 +3003,8 @@ enum nl80211_attrs { #define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG #define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER #define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA +#define NL80211_ATTR_CSA_C_OFF_BEACON NL80211_ATTR_CNTDWN_OFFS_BEACON +#define NL80211_ATTR_CSA_C_OFF_PRESP NL80211_ATTR_CNTDWN_OFFS_PRESP /* * Allow user space programs to use #ifdef on new attributes by defining them -- cgit v1.2.3 From 8552a434b6a05cc38006733afe6a239ad4d600a2 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Tue, 11 Aug 2020 10:01:04 +0200 Subject: mac80211: rename csa counters to countdown counters We want to reuse the functions and structs for other counters such as BSS color change. Rename them to more generic names. Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20200811080107.3615705-2-john@phrozen.org Signed-off-by: Johannes Berg --- include/net/mac80211.h | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 66e2bfd165e8..ec148b3e9c41 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3736,7 +3736,7 @@ enum ieee80211_reconfig_type { * decremented, and when they reach 1 the driver must call * ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get() * get the csa counter decremented by mac80211, but must check if it is - * 1 using ieee80211_csa_is_complete() after the beacon has been + * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been * transmitted and then call ieee80211_csa_finish(). * If the CSA count starts as zero or 1, this function will not be called, * since there won't be any time to beacon before the switch anyway. @@ -4763,21 +4763,21 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, */ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets); -#define IEEE80211_MAX_CSA_COUNTERS_NUM 2 +#define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2 /** * struct ieee80211_mutable_offsets - mutable beacon offsets * @tim_offset: position of TIM element * @tim_length: size of TIM element - * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets - * to CSA counters. This array can contain zero values which + * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets + * to countdown counters. This array can contain zero values which * should be ignored. */ struct ieee80211_mutable_offsets { u16 tim_offset; u16 tim_length; - u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; }; /** @@ -4846,31 +4846,31 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, } /** - * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter + * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * The csa counter should be updated after each beacon transmission. + * The beacon counter should be updated after each beacon transmission. * This function is called implicitly when * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the * beacon frames are generated by the device, the driver should call this - * function after each beacon transmission to sync mac80211's csa counters. + * function after each beacon transmission to sync mac80211's beacon countdown. * - * Return: new csa counter value + * Return: new countdown value */ -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif); +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif); /** - * ieee80211_csa_set_counter - request mac80211 to set csa counter + * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @counter: the new value for the counter * - * The csa counter can be changed by the device, this API should be + * The beacon countdown can be changed by the device, this API should be * used by the device driver to update csa counter in mac80211. * - * It should never be used together with ieee80211_csa_update_counter(), + * It should never be used together with ieee80211_beacon_update_cntdwn(), * as it will cause a race condition around the counter value. */ -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter); /** * ieee80211_csa_finish - notify mac80211 about channel switch @@ -4883,13 +4883,12 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); void ieee80211_csa_finish(struct ieee80211_vif *vif); /** - * ieee80211_csa_is_complete - find out if counters reached 1 + * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1 * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * This function returns whether the channel switch counters reached zero. + * This function returns whether the countdown reached zero. */ -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif); - +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif); /** * ieee80211_proberesp_get - retrieve a Probe Response template -- cgit v1.2.3 From 1c9c02bb22684f6949d2e7ddc0a3ff364fd5a6fc Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 27 Apr 2020 14:50:37 -0500 Subject: mtd: lpddr: Fix bad logic in print_drs_error Update logic for broken test. Use a more common logging style. It appears the logic in this function is broken for the consecutive tests of if (prog_status & 0x3) ... else if (prog_status & 0x2) ... else (prog_status & 0x1) ... Likely the first test should be if ((prog_status & 0x3) == 0x3) Found by inspection of include files using printk. Fixes: eb3db27507f7 ("[MTD] LPDDR PFOW definition") Cc: stable@vger.kernel.org Reported-by: Joe Perches Signed-off-by: Gustavo A. R. Silva Acked-by: Miquel Raynal Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/3fb0e29f5b601db8be2938a01d974b00c8788501.1588016644.git.gustavo@embeddedor.com --- include/linux/mtd/pfow.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h index 6166e7c60869..b8da6f8e854b 100644 --- a/include/linux/mtd/pfow.h +++ b/include/linux/mtd/pfow.h @@ -128,7 +128,7 @@ static inline void print_drs_error(unsigned dsr) if (!(dsr & DSR_AVAILABLE)) printk(KERN_NOTICE"DSR.15: (0) Device not Available\n"); - if (prog_status & 0x03) + if ((prog_status & 0x03) == 0x03) printk(KERN_NOTICE"DSR.9,8: (11) Attempt to program invalid " "half with 41h command\n"); else if (prog_status & 0x02) -- cgit v1.2.3 From 518693abe6e3f57606ec18892e9135abbc04b361 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 27 Apr 2020 14:54:13 -0500 Subject: mtd: lpddr: Replace printk with pr_notice pr_notice is preferred over printk. Also, coalesce formats as coalescing is part of coding-style: "never break user-visible strings such as printk messages" Suggested-by: Joe Perches Signed-off-by: Gustavo A. R. Silva Reviewed-by: Miquel Raynal Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/ff48ce07ef208ba65b858f09279a3b36031d64d2.1588016644.git.gustavo@embeddedor.com --- include/linux/mtd/pfow.h | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h index b8da6f8e854b..1c0f6113f230 100644 --- a/include/linux/mtd/pfow.h +++ b/include/linux/mtd/pfow.h @@ -127,31 +127,26 @@ static inline void print_drs_error(unsigned dsr) int prog_status = (dsr & DSR_RPS) >> 8; if (!(dsr & DSR_AVAILABLE)) - printk(KERN_NOTICE"DSR.15: (0) Device not Available\n"); + pr_notice("DSR.15: (0) Device not Available\n"); if ((prog_status & 0x03) == 0x03) - printk(KERN_NOTICE"DSR.9,8: (11) Attempt to program invalid " - "half with 41h command\n"); + pr_notice("DSR.9,8: (11) Attempt to program invalid half with 41h command\n"); else if (prog_status & 0x02) - printk(KERN_NOTICE"DSR.9,8: (10) Object Mode Program attempt " - "in region with Control Mode data\n"); + pr_notice("DSR.9,8: (10) Object Mode Program attempt in region with Control Mode data\n"); else if (prog_status & 0x01) - printk(KERN_NOTICE"DSR.9,8: (01) Program attempt in region " - "with Object Mode data\n"); + pr_notice("DSR.9,8: (01) Program attempt in region with Object Mode data\n"); if (!(dsr & DSR_READY_STATUS)) - printk(KERN_NOTICE"DSR.7: (0) Device is Busy\n"); + pr_notice("DSR.7: (0) Device is Busy\n"); if (dsr & DSR_ESS) - printk(KERN_NOTICE"DSR.6: (1) Erase Suspended\n"); + pr_notice("DSR.6: (1) Erase Suspended\n"); if (dsr & DSR_ERASE_STATUS) - printk(KERN_NOTICE"DSR.5: (1) Erase/Blank check error\n"); + pr_notice("DSR.5: (1) Erase/Blank check error\n"); if (dsr & DSR_PROGRAM_STATUS) - printk(KERN_NOTICE"DSR.4: (1) Program Error\n"); + pr_notice("DSR.4: (1) Program Error\n"); if (dsr & DSR_VPPS) - printk(KERN_NOTICE"DSR.3: (1) Vpp low detect, operation " - "aborted\n"); + pr_notice("DSR.3: (1) Vpp low detect, operation aborted\n"); if (dsr & DSR_PSS) - printk(KERN_NOTICE"DSR.2: (1) Program suspended\n"); + pr_notice("DSR.2: (1) Program suspended\n"); if (dsr & DSR_DPS) - printk(KERN_NOTICE"DSR.1: (1) Aborted Erase/Program attempt " - "on locked block\n"); + pr_notice("DSR.1: (1) Aborted Erase/Program attempt on locked block\n"); } #endif /* __LINUX_MTD_PFOW_H */ -- cgit v1.2.3 From 1a64026eda1642c81425e48550fd4bd3f73d0ab5 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 27 Apr 2020 14:56:08 -0500 Subject: mtd: lpddr: Move function print_drs_error to lpddr_cmds.c Function print_drs_error is only used in drivers/mtd/lpddr/lpddr_cmds.c so, better to move it there. Also, notice that there's no need for inline as the function is used once. Lastly, fix the following checkpatch warning: WARNING: Prefer 'unsigned int' to bare use of 'unsigned' +static void print_drs_error(unsigned dsr) Suggested-by: Joe Perches Signed-off-by: Gustavo A. R. Silva Reviewed-by: Miquel Raynal Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/e0063cbd65f3b47be1db34efc494ea3047634d88.1588016644.git.gustavo@embeddedor.com --- include/linux/mtd/pfow.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h index 1c0f6113f230..146413d4bdb7 100644 --- a/include/linux/mtd/pfow.h +++ b/include/linux/mtd/pfow.h @@ -121,32 +121,4 @@ static inline void send_pfow_command(struct map_info *map, map_write(map, CMD(LPDDR_START_EXECUTION), map->pfow_base + PFOW_COMMAND_EXECUTE); } - -static inline void print_drs_error(unsigned dsr) -{ - int prog_status = (dsr & DSR_RPS) >> 8; - - if (!(dsr & DSR_AVAILABLE)) - pr_notice("DSR.15: (0) Device not Available\n"); - if ((prog_status & 0x03) == 0x03) - pr_notice("DSR.9,8: (11) Attempt to program invalid half with 41h command\n"); - else if (prog_status & 0x02) - pr_notice("DSR.9,8: (10) Object Mode Program attempt in region with Control Mode data\n"); - else if (prog_status & 0x01) - pr_notice("DSR.9,8: (01) Program attempt in region with Object Mode data\n"); - if (!(dsr & DSR_READY_STATUS)) - pr_notice("DSR.7: (0) Device is Busy\n"); - if (dsr & DSR_ESS) - pr_notice("DSR.6: (1) Erase Suspended\n"); - if (dsr & DSR_ERASE_STATUS) - pr_notice("DSR.5: (1) Erase/Blank check error\n"); - if (dsr & DSR_PROGRAM_STATUS) - pr_notice("DSR.4: (1) Program Error\n"); - if (dsr & DSR_VPPS) - pr_notice("DSR.3: (1) Vpp low detect, operation aborted\n"); - if (dsr & DSR_PSS) - pr_notice("DSR.2: (1) Program suspended\n"); - if (dsr & DSR_DPS) - pr_notice("DSR.1: (1) Aborted Erase/Program attempt on locked block\n"); -} #endif /* __LINUX_MTD_PFOW_H */ -- cgit v1.2.3 From 5f9e2822d12fe5050da5db0e65924d5ddc86bf29 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Thu, 20 Aug 2020 17:46:23 -0500 Subject: RDMA/rxe: Fix style warnings Fixed several minor checkpatch warnings in existing rxe source. Link: https://lore.kernel.org/r/20200820224638.3212-3-rpearson@hpe.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/rdma_user_rxe.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index aae2e696bb38..d8f2e0e46dab 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -99,8 +99,8 @@ struct rxe_send_wr { struct ib_mr *mr; __aligned_u64 reserved; }; - __u32 key; - __u32 access; + __u32 key; + __u32 access; } reg; } wr; }; @@ -112,7 +112,7 @@ struct rxe_sge { }; struct mminfo { - __aligned_u64 offset; + __aligned_u64 offset; __u32 size; __u32 pad; }; -- cgit v1.2.3 From 2831a631022eed6e3f800f08892132c6edde652c Mon Sep 17 00:00:00 2001 From: Chung-Hsien Hsu Date: Mon, 17 Aug 2020 02:33:15 -0500 Subject: nl80211: support SAE authentication offload in AP mode Let drivers advertise support for AP-mode SAE authentication offload with a new NL80211_EXT_FEATURE_SAE_OFFLOAD_AP flag. Signed-off-by: Chung-Hsien Hsu Signed-off-by: Chi-Hsien Lin Link: https://lore.kernel.org/r/20200817073316.33402-4-stanley.hsu@cypress.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ec96d5fe0e05..0584e0d349f0 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -252,9 +252,13 @@ * DOC: SAE authentication offload * * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they - * support offloading SAE authentication for WPA3-Personal networks. In - * %NL80211_CMD_CONNECT the password for SAE should be specified using - * %NL80211_ATTR_SAE_PASSWORD. + * support offloading SAE authentication for WPA3-Personal networks in station + * mode. Similarly @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP flag can be set by + * drivers indicating the offload support in AP mode. + * + * The password for SAE should be specified using %NL80211_ATTR_SAE_PASSWORD in + * %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP for station and AP mode + * respectively. */ /** @@ -5845,6 +5849,9 @@ enum nl80211_feature_flags { * handshake with PSK in AP mode (PSK is passed as part of the start AP * command). * + * @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP: Device wants to do SAE authentication + * in AP mode (SAE password is passed as part of the start AP command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5902,6 +5909,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From c242766f286aa5a54cc3d987e71b8c952059132d Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Wed, 26 Aug 2020 11:45:25 -0700 Subject: ALSA: hda: fix VS_LTRC register name It should be called VS_LTRP instead. Reviewed-by: Guennadi Liakhovetski Reviewed-by: Pierre-Louis Bossart Signed-off-by: Ranjani Sridharan Reviewed-by: Takashi Iwai Link: https://lore.kernel.org/r/20200826184532.1612070-2-ranjani.sridharan@linux.intel.com Signed-off-by: Mark Brown --- include/sound/hda_register.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h index 057d2a2d0bd0..4f987b1f32f7 100644 --- a/include/sound/hda_register.h +++ b/include/sound/hda_register.h @@ -119,7 +119,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; #define AZX_REG_VS_EM3U 0x103C #define AZX_REG_VS_EM4L 0x1040 #define AZX_REG_VS_EM4U 0x1044 -#define AZX_REG_VS_LTRC 0x1048 +#define AZX_REG_VS_LTRP 0x1048 #define AZX_REG_VS_D0I3C 0x104A #define AZX_REG_VS_PCE 0x104B #define AZX_REG_VS_L2MAGC 0x1050 -- cgit v1.2.3 From c1c277b2c425f69b9b4f4258d9db18562d9be041 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 27 Aug 2020 08:55:39 +0900 Subject: ASoC: soc-core: add snd_soc_find_dai_with_mutex() commit 25612477d20b52 ("ASoC: soc-dai: set dai_link dpcm_ flags with a helper") added snd_soc_dai_link_set_capabilities(). But it is using snd_soc_find_dai() (A) which is required client_mutex (B). And client_mutex is soc-core.c local. struct snd_soc_dai *snd_soc_find_dai(xxx) { ... (B) lockdep_assert_held(&client_mutex); ... } void snd_soc_dai_link_set_capabilities(xxx) { ... for_each_pcm_streams(direction) { ... for_each_link_cpus(dai_link, i, cpu) { (A) dai = snd_soc_find_dai(cpu); ... } ... for_each_link_codecs(dai_link, i, codec) { (A) dai = snd_soc_find_dai(codec); ... } } ... } Because of these background, we will get WARNING if .config has CONFIG_LOCKDEP. WARNING: CPU: 2 PID: 53 at sound/soc/soc-core.c:814 snd_soc_find_dai+0xf8/0x100 CPU: 2 PID: 53 Comm: kworker/2:1 Not tainted 5.7.0-rc1+ #328 Hardware name: Renesas H3ULCB Kingfisher board based on r8a77951 (DT) Workqueue: events deferred_probe_work_func pstate: 60000005 (nZCv daif -PAN -UAO) pc : snd_soc_find_dai+0xf8/0x100 lr : snd_soc_find_dai+0xf4/0x100 ... Call trace: snd_soc_find_dai+0xf8/0x100 snd_soc_dai_link_set_capabilities+0xa0/0x16c graph_dai_link_of_dpcm+0x390/0x3c0 graph_for_each_link+0x134/0x200 graph_probe+0x144/0x230 platform_drv_probe+0x5c/0xb0 really_probe+0xe4/0x430 driver_probe_device+0x60/0xf4 snd_soc_find_dai() will be used from (X) CPU/Codec/Platform driver with mutex lock, and (Y) Card driver without mutex lock. This snd_soc_dai_link_set_capabilities() is for Card driver, this means called without mutex. This patch adds snd_soc_find_dai_with_mutex() to solve it. Fixes: 25612477d20b52 ("ASoC: soc-dai: set dai_link dpcm_ flags with a helper") Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87blixvuab.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index a0918d159fd3..b94ebff12350 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1362,6 +1362,8 @@ void snd_soc_unregister_dai(struct snd_soc_dai *dai); struct snd_soc_dai *snd_soc_find_dai( const struct snd_soc_dai_link_component *dlc); +struct snd_soc_dai *snd_soc_find_dai_with_mutex( + const struct snd_soc_dai_link_component *dlc); #include -- cgit v1.2.3 From 2fa4e4b799e191530edbae4b96b85d4486e55053 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 27 Aug 2020 04:00:28 +0200 Subject: net: pcs: Move XPCS into new PCS subdirectory Create drivers/net/pcs and move the Synopsys DesignWare XPCS into the new directory. Move the header file into a subdirectory include/linux/pcs Start a naming convention of all PCS files use the prefix pcs-, and rename the XPCS files to fit. v2: Add include/linux/pcs v4: Fix include path in stmmac. Remove PCS_DEVICES to avoid new prompts Cc: Jose Abreu Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mdio-xpcs.h | 41 ----------------------------------------- include/linux/pcs/pcs-xpcs.h | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+), 41 deletions(-) delete mode 100644 include/linux/mdio-xpcs.h create mode 100644 include/linux/pcs/pcs-xpcs.h (limited to 'include') diff --git a/include/linux/mdio-xpcs.h b/include/linux/mdio-xpcs.h deleted file mode 100644 index 9a841aa5982d..000000000000 --- a/include/linux/mdio-xpcs.h +++ /dev/null @@ -1,41 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates. - * Synopsys DesignWare XPCS helpers - */ - -#ifndef __LINUX_MDIO_XPCS_H -#define __LINUX_MDIO_XPCS_H - -#include -#include - -struct mdio_xpcs_args { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); - struct mii_bus *bus; - int addr; -}; - -struct mdio_xpcs_ops { - int (*validate)(struct mdio_xpcs_args *xpcs, - unsigned long *supported, - struct phylink_link_state *state); - int (*config)(struct mdio_xpcs_args *xpcs, - const struct phylink_link_state *state); - int (*get_state)(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state); - int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, - phy_interface_t interface); - int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); -}; - -#if IS_ENABLED(CONFIG_MDIO_XPCS) -struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); -#else -static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) -{ - return NULL; -} -#endif - -#endif /* __LINUX_MDIO_XPCS_H */ diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h new file mode 100644 index 000000000000..351c1c9aedc5 --- /dev/null +++ b/include/linux/pcs/pcs-xpcs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates. + * Synopsys DesignWare XPCS helpers + */ + +#ifndef __LINUX_PCS_XPCS_H +#define __LINUX_PCS_XPCS_H + +#include +#include + +struct mdio_xpcs_args { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + struct mii_bus *bus; + int addr; +}; + +struct mdio_xpcs_ops { + int (*validate)(struct mdio_xpcs_args *xpcs, + unsigned long *supported, + struct phylink_link_state *state); + int (*config)(struct mdio_xpcs_args *xpcs, + const struct phylink_link_state *state); + int (*get_state)(struct mdio_xpcs_args *xpcs, + struct phylink_link_state *state); + int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, + phy_interface_t interface); + int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); +}; + +#if IS_ENABLED(CONFIG_PCS_XPCS) +struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); +#else +static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) +{ + return NULL; +} +#endif + +#endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From fcba68bd75bb1d42b3aec7f471d382a9e639a672 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 27 Aug 2020 04:00:29 +0200 Subject: net/phy/mdio-i2c: Move header file to include/linux/mdio In preparation for moving all MDIO drivers into drivers/net/mdio, move the mdio-i2c header file into include/linux/mdio so it can be used by both the MDIO driver and the SFP code which instantiates I2C MDIO busses. v2: Add include/linux/mdio Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mdio/mdio-i2c.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/mdio/mdio-i2c.h (limited to 'include') diff --git a/include/linux/mdio/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h new file mode 100644 index 000000000000..b1d27f7cd23f --- /dev/null +++ b/include/linux/mdio/mdio-i2c.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * MDIO I2C bridge + * + * Copyright (C) 2015 Russell King + */ +#ifndef MDIO_I2C_H +#define MDIO_I2C_H + +struct device; +struct i2c_adapter; +struct mii_bus; + +struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c); + +#endif -- cgit v1.2.3 From 232e15e1d7ddb191c28248cb681f4544c0ff1c54 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 27 Aug 2020 04:00:30 +0200 Subject: net: xgene: Move shared header file into include/linux This header file is currently included into the ethernet driver via a relative path into the PHY subsystem. This is bad practice, and causes issues for the upcoming move of the MDIO driver. Move the header file into include/linux to clean this up. v2: Move header to include/linux/mdio Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mdio/mdio-xgene.h | 130 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 130 insertions(+) create mode 100644 include/linux/mdio/mdio-xgene.h (limited to 'include') diff --git a/include/linux/mdio/mdio-xgene.h b/include/linux/mdio/mdio-xgene.h new file mode 100644 index 000000000000..8af93ada8b64 --- /dev/null +++ b/include/linux/mdio/mdio-xgene.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Applied Micro X-Gene SoC MDIO Driver + * + * Copyright (c) 2016, Applied Micro Circuits Corporation + * Author: Iyappan Subramanian + */ + +#ifndef __MDIO_XGENE_H__ +#define __MDIO_XGENE_H__ + +#define BLOCK_XG_MDIO_CSR_OFFSET 0x5000 +#define BLOCK_DIAG_CSR_OFFSET 0xd000 +#define XGENET_CONFIG_REG_ADDR 0x20 + +#define MAC_ADDR_REG_OFFSET 0x00 +#define MAC_COMMAND_REG_OFFSET 0x04 +#define MAC_WRITE_REG_OFFSET 0x08 +#define MAC_READ_REG_OFFSET 0x0c +#define MAC_COMMAND_DONE_REG_OFFSET 0x10 + +#define CLKEN_OFFSET 0x08 +#define SRST_OFFSET 0x00 + +#define MENET_CFG_MEM_RAM_SHUTDOWN_ADDR 0x70 +#define MENET_BLOCK_MEM_RDY_ADDR 0x74 + +#define MAC_CONFIG_1_ADDR 0x00 +#define MII_MGMT_COMMAND_ADDR 0x24 +#define MII_MGMT_ADDRESS_ADDR 0x28 +#define MII_MGMT_CONTROL_ADDR 0x2c +#define MII_MGMT_STATUS_ADDR 0x30 +#define MII_MGMT_INDICATORS_ADDR 0x34 +#define SOFT_RESET BIT(31) + +#define MII_MGMT_CONFIG_ADDR 0x20 +#define MII_MGMT_COMMAND_ADDR 0x24 +#define MII_MGMT_ADDRESS_ADDR 0x28 +#define MII_MGMT_CONTROL_ADDR 0x2c +#define MII_MGMT_STATUS_ADDR 0x30 +#define MII_MGMT_INDICATORS_ADDR 0x34 + +#define MIIM_COMMAND_ADDR 0x20 +#define MIIM_FIELD_ADDR 0x24 +#define MIIM_CONFIGURATION_ADDR 0x28 +#define MIIM_LINKFAILVECTOR_ADDR 0x2c +#define MIIM_INDICATOR_ADDR 0x30 +#define MIIMRD_FIELD_ADDR 0x34 + +#define MDIO_CSR_OFFSET 0x5000 + +#define REG_ADDR_POS 0 +#define REG_ADDR_LEN 5 +#define PHY_ADDR_POS 8 +#define PHY_ADDR_LEN 5 + +#define HSTMIIMWRDAT_POS 0 +#define HSTMIIMWRDAT_LEN 16 +#define HSTPHYADX_POS 23 +#define HSTPHYADX_LEN 5 +#define HSTREGADX_POS 18 +#define HSTREGADX_LEN 5 +#define HSTLDCMD BIT(3) +#define HSTMIIMCMD_POS 0 +#define HSTMIIMCMD_LEN 3 + +#define BUSY_MASK BIT(0) +#define READ_CYCLE_MASK BIT(0) + +enum xgene_enet_cmd { + XGENE_ENET_WR_CMD = BIT(31), + XGENE_ENET_RD_CMD = BIT(30) +}; + +enum { + MIIM_CMD_IDLE, + MIIM_CMD_LEGACY_WRITE, + MIIM_CMD_LEGACY_READ, +}; + +enum xgene_mdio_id { + XGENE_MDIO_RGMII = 1, + XGENE_MDIO_XFI +}; + +struct xgene_mdio_pdata { + struct clk *clk; + struct device *dev; + void __iomem *mac_csr_addr; + void __iomem *diag_csr_addr; + void __iomem *mdio_csr_addr; + struct mii_bus *mdio_bus; + int mdio_id; + spinlock_t mac_lock; /* mac lock */ +}; + +/* Set the specified value into a bit-field defined by its starting position + * and length within a single u64. + */ +static inline u64 xgene_enet_set_field_value(int pos, int len, u64 val) +{ + return (val & ((1ULL << len) - 1)) << pos; +} + +#define SET_VAL(field, val) \ + xgene_enet_set_field_value(field ## _POS, field ## _LEN, val) + +#define SET_BIT(field) \ + xgene_enet_set_field_value(field ## _POS, 1, 1) + +/* Get the value from a bit-field defined by its starting position + * and length within the specified u64. + */ +static inline u64 xgene_enet_get_field_value(int pos, int len, u64 src) +{ + return (src >> pos) & ((1ULL << len) - 1); +} + +#define GET_VAL(field, src) \ + xgene_enet_get_field_value(field ## _POS, field ## _LEN, src) + +#define GET_BIT(field, src) \ + xgene_enet_get_field_value(field ## _POS, 1, src) + +u32 xgene_mdio_rd_mac(struct xgene_mdio_pdata *pdata, u32 rd_addr); +void xgene_mdio_wr_mac(struct xgene_mdio_pdata *pdata, u32 wr_addr, u32 data); +int xgene_mdio_rgmii_read(struct mii_bus *bus, int phy_id, int reg); +int xgene_mdio_rgmii_write(struct mii_bus *bus, int phy_id, int reg, u16 data); +struct phy_device *xgene_enet_phy_register(struct mii_bus *bus, int phy_addr); + +#endif /* __MDIO_XGENE_H__ */ -- cgit v1.2.3 From 17529bcf0ae20f1ac6d7846762bf0c6ad91dbb7f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 27 Aug 2020 10:48:28 +0200 Subject: power: supply: gpio-charger: Convert to GPIO descriptors This converts the GPIO charger to use exclusively GPIO descriptors, moving the two remaining platforms passing global GPIO numbers over to using a GPIO descriptor table. Signed-off-by: Linus Walleij Cc: Robert Jarzmik Cc: Dmitry Eremin-Solenikov Signed-off-by: Sebastian Reichel --- include/linux/power/gpio-charger.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/power/gpio-charger.h b/include/linux/power/gpio-charger.h index 5a5a8de98181..c0b7657ac1df 100644 --- a/include/linux/power/gpio-charger.h +++ b/include/linux/power/gpio-charger.h @@ -13,18 +13,12 @@ * struct gpio_charger_platform_data - platform_data for gpio_charger devices * @name: Name for the chargers power_supply device * @type: Type of the charger - * @gpio: GPIO which is used to indicate the chargers status - * @gpio_active_low: Should be set to 1 if the GPIO is active low otherwise 0 * @supplied_to: Array of battery names to which this chargers supplies power * @num_supplicants: Number of entries in the supplied_to array */ struct gpio_charger_platform_data { const char *name; enum power_supply_type type; - - int gpio; - int gpio_active_low; - char **supplied_to; size_t num_supplicants; }; -- cgit v1.2.3 From 50aba46c234ea6ab3134cebb5ab27885f33a3e5d Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 27 Aug 2020 14:19:23 +0200 Subject: gtp: add notification mechanism Like all other network functions, let's notify gtp context on creation and deletion. Signed-off-by: Nicolas Dichtel Tested-by: Gabriel Ganne Acked-by: Harald Welte Signed-off-by: David S. Miller --- include/uapi/linux/gtp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index c7d66755d212..79f9191bbb24 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ +#define GTP_GENL_MCGRP_NAME "gtp" + enum gtp_genl_cmds { GTP_CMD_NEWPDP, GTP_CMD_DELPDP, -- cgit v1.2.3 From dab741e0e02bd3c4f5e2e97be74b39df2523fc6e Mon Sep 17 00:00:00 2001 From: Mattias Nissler Date: Thu, 27 Aug 2020 11:09:46 -0600 Subject: Add a "nosymfollow" mount option. For mounts that have the new "nosymfollow" option, don't follow symlinks when resolving paths. The new option is similar in spirit to the existing "nodev", "noexec", and "nosuid" options, as well as to the LOOKUP_NO_SYMLINKS resolve flag in the openat2(2) syscall. Various BSD variants have been supporting the "nosymfollow" mount option for a long time with equivalent implementations. Note that symlinks may still be created on file systems mounted with the "nosymfollow" option present. readlink() remains functional, so user space code that is aware of symlinks can still choose to follow them explicitly. Setting the "nosymfollow" mount option helps prevent privileged writers from modifying files unintentionally in case there is an unexpected link along the accessed path. The "nosymfollow" option is thus useful as a defensive measure for systems that need to deal with untrusted file systems in privileged contexts. More information on the history and motivation for this patch can be found here: https://sites.google.com/a/chromium.org/dev/chromium-os/chromiumos-design-docs/hardening-against-malicious-stateful-data#TOC-Restricting-symlink-traversal Signed-off-by: Mattias Nissler Signed-off-by: Ross Zwisler Reviewed-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/mount.h | 3 ++- include/linux/statfs.h | 1 + include/uapi/linux/mount.h | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mount.h b/include/linux/mount.h index de657bd211fa..aaf343b38671 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -30,6 +30,7 @@ struct fs_context; #define MNT_NODIRATIME 0x10 #define MNT_RELATIME 0x20 #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ +#define MNT_NOSYMFOLLOW 0x80 #define MNT_SHRINKABLE 0x100 #define MNT_WRITE_HOLD 0x200 @@ -46,7 +47,7 @@ struct fs_context; #define MNT_SHARED_MASK (MNT_UNBINDABLE) #define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ - | MNT_READONLY) + | MNT_READONLY | MNT_NOSYMFOLLOW) #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ diff --git a/include/linux/statfs.h b/include/linux/statfs.h index 9bc69edb8f18..fac4356ea1bf 100644 --- a/include/linux/statfs.h +++ b/include/linux/statfs.h @@ -40,6 +40,7 @@ struct kstatfs { #define ST_NOATIME 0x0400 /* do not update access times */ #define ST_NODIRATIME 0x0800 /* do not update directory access times */ #define ST_RELATIME 0x1000 /* update atime relative to mtime/ctime */ +#define ST_NOSYMFOLLOW 0x2000 /* do not follow symlinks */ struct dentry; extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid); diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 96a0240f23fe..dd8306ea336c 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -16,6 +16,7 @@ #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ #define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ #define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ #define MS_NOATIME 1024 /* Do not update access times. */ #define MS_NODIRATIME 2048 /* Do not update directory access times */ #define MS_BIND 4096 -- cgit v1.2.3 From e73d340db6448013ac219d105654d2b9868a8dd2 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 18 Aug 2020 18:25:34 +1000 Subject: crypto: ahash - Add init_tfm/exit_tfm This patch adds the type-safe init_tfm/exit_tfm functions to the ahash interface. This is meant to replace the unsafe cra_init and cra_exit interface. Signed-off-by: Herbert Xu --- include/crypto/hash.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 0d1b403888c9..a2563a59fadd 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -123,6 +123,17 @@ struct ahash_request { * data so the transformation can continue from this point onward. No * data processing happens at this point. Driver must not use * req->result. + * @init_tfm: Initialize the cryptographic transformation object. + * This function is called only once at the instantiation + * time, right after the transformation context was + * allocated. In case the cryptographic hardware has + * some special requirements which need to be handled + * by software, this function shall check for the precise + * requirement of the transformation and put any software + * fallbacks in place. + * @exit_tfm: Deinitialize the cryptographic transformation object. + * This is a counterpart to @init_tfm, used to remove + * various changes set in @init_tfm. * @halg: see struct hash_alg_common */ struct ahash_alg { @@ -135,6 +146,8 @@ struct ahash_alg { int (*import)(struct ahash_request *req, const void *in); int (*setkey)(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); + int (*init_tfm)(struct crypto_ahash *tfm); + void (*exit_tfm)(struct crypto_ahash *tfm); struct hash_alg_common halg; }; -- cgit v1.2.3 From b00ba76a03a02c23494644d2ccd389fdc411f9e9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 18 Aug 2020 18:25:36 +1000 Subject: crypto: ahash - Add ahash_alg_instance This patch adds the helper ahash_alg_instance which is used to convert a crypto_ahash object into its corresponding ahash_instance. Signed-off-by: Herbert Xu --- include/crypto/internal/hash.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 6d3ad5ac4d28..0a288dddcf5b 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -164,6 +164,12 @@ static inline struct ahash_instance *ahash_instance( return container_of(inst, struct ahash_instance, s.base); } +static inline struct ahash_instance *ahash_alg_instance( + struct crypto_ahash *ahash) +{ + return ahash_instance(crypto_tfm_alg_instance(&ahash->base)); +} + static inline void *ahash_instance_ctx(struct ahash_instance *inst) { return crypto_instance_ctx(ahash_crypto_instance(inst)); -- cgit v1.2.3 From f858ddef5a57fb0597bb23f69edda3477d47e30a Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 18 Aug 2020 18:25:38 +1000 Subject: crypto: ahash - Remove AHASH_REQUEST_ON_STACK This patch removes AHASH_REQUEST_ON_STACK which is unused. Signed-off-by: Herbert Xu Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/hash.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/crypto/hash.h b/include/crypto/hash.h index a2563a59fadd..af2ff31ff619 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -59,11 +59,6 @@ struct ahash_request { void *__ctx[] CRYPTO_MINALIGN_ATTR; }; -#define AHASH_REQUEST_ON_STACK(name, ahash) \ - char __##name##_desc[sizeof(struct ahash_request) + \ - crypto_ahash_reqsize(ahash)] CRYPTO_MINALIGN_ATTR; \ - struct ahash_request *name = (void *)__##name##_desc - /** * struct ahash_alg - asynchronous message digest definition * @init: **[mandatory]** Initialize the transformation context. Intended only to initialize the -- cgit v1.2.3 From 6bbe2a90a0bb4af8dd99c3565e907fe9b5e7fd88 Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 17 Aug 2020 11:38:27 -0700 Subject: usb: typec: tcpm: During PR_SWAP, source caps should be sent only after tSwapSourceStart The patch addresses the compliance test failures while running TD.PD.CP.E3, TD.PD.CP.E4, TD.PD.CP.E5 of the "Deterministic PD Compliance MOI" test plan published in https://www.usb.org/usbc. For a product to be Type-C compliant, it's expected that these tests are run on usb.org certified Type-C compliance tester as mentioned in https://www.usb.org/usbc. The purpose of the tests TD.PD.CP.E3, TD.PD.CP.E4, TD.PD.CP.E5 is to verify the PR_SWAP response of the device. While doing so, the test asserts that Source Capabilities message is NOT received from the test device within tSwapSourceStart min (20 ms) from the time the last bit of GoodCRC corresponding to the RS_RDY message sent by the UUT was sent. If it does then the test fails. This is in line with the requirements from the USB Power Delivery Specification Revision 3.0, Version 1.2: "6.6.8.1 SwapSourceStartTimer The SwapSourceStartTimer Shall be used by the new Source, after a Power Role Swap or Fast Role Swap, to ensure that it does not send Source_Capabilities Message before the new Sink is ready to receive the Source_Capabilities Message. The new Source Shall Not send the Source_Capabilities Message earlier than tSwapSourceStart after the last bit of the EOP of GoodCRC Message sent in response to the PS_RDY Message sent by the new Source indicating that its power supply is ready." The patch makes sure that TCPM does not send the Source_Capabilities Message within tSwapSourceStart(20ms) by transitioning into SRC_STARTUP only after tSwapSourceStart(20ms). Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Guenter Roeck Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200817183828.1895015-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index b6c233e79bd4..1df895e4680b 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -473,6 +473,7 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_ERROR_RECOVERY 100 /* minimum 25 is insufficient */ #define PD_T_SRCSWAPSTDBY 625 /* Maximum of 650ms */ #define PD_T_NEWSRC 250 /* Maximum of 275ms */ +#define PD_T_SWAP_SRC_START 20 /* Minimum of 20ms */ #define PD_T_DRP_TRY 100 /* 75 - 150 ms */ #define PD_T_DRP_TRYWAIT 600 /* 400 - 800 ms */ -- cgit v1.2.3 From aefc66afe42bcae01743c0b3c5addd089263801b Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 17 Aug 2020 11:38:28 -0700 Subject: usb: typec: pd: Fix formatting in pd.h header Replacing spaces with tabs for PD_T_* constants. Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Guenter Roeck Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200817183828.1895015-2-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index 1df895e4680b..f842e4589bd2 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -471,9 +471,10 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_VCONN_SOURCE_ON 100 #define PD_T_SINK_REQUEST 100 /* 100 ms minimum */ #define PD_T_ERROR_RECOVERY 100 /* minimum 25 is insufficient */ -#define PD_T_SRCSWAPSTDBY 625 /* Maximum of 650ms */ -#define PD_T_NEWSRC 250 /* Maximum of 275ms */ +#define PD_T_SRCSWAPSTDBY 625 /* Maximum of 650ms */ +#define PD_T_NEWSRC 250 /* Maximum of 275ms */ #define PD_T_SWAP_SRC_START 20 /* Minimum of 20ms */ +#define PD_T_BIST_CONT_MODE 50 /* 30 - 60 ms */ #define PD_T_DRP_TRY 100 /* 75 - 150 ms */ #define PD_T_DRP_TRYWAIT 600 /* 400 - 800 ms */ @@ -484,5 +485,4 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_N_CAPS_COUNT (PD_T_NO_RESPONSE / PD_T_SEND_SOURCE_CAP) #define PD_N_HARD_RESET_COUNT 2 -#define PD_T_BIST_CONT_MODE 50 /* 30 - 60 ms */ #endif /* __LINUX_USB_PD_H */ -- cgit v1.2.3 From d3cd0071a89a085a2d578b6a9e31db10469501c6 Mon Sep 17 00:00:00 2001 From: Christian Eggers Date: Mon, 27 Jul 2020 13:12:18 +0200 Subject: eeprom: at25: allow page sizes greater than 16 bit Storage technologies like FRAM have no "write pages", the whole chip can be written within one SPI transfer. For these chips, the page size can be set equal to the device size. Currently available devices are already bigger than 64 kiB. Signed-off-by: Christian Eggers Link: https://lore.kernel.org/r/20200727111218.26926-1-ceggers@arri.de Signed-off-by: Greg Kroah-Hartman --- include/linux/spi/eeprom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/eeprom.h b/include/linux/spi/eeprom.h index aceccf9c71fb..1cca3dd5a748 100644 --- a/include/linux/spi/eeprom.h +++ b/include/linux/spi/eeprom.h @@ -14,7 +14,7 @@ struct spi_eeprom { u32 byte_len; char name[10]; - u16 page_size; /* for writes */ + u32 page_size; /* for writes */ u16 flags; #define EE_ADDR1 0x0001 /* 8 bit addrs */ #define EE_ADDR2 0x0002 /* 16 bit addrs */ -- cgit v1.2.3 From 145fbd1e82e6654398ace321432e3a803b8a2be4 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 28 Aug 2020 11:41:41 +0300 Subject: dmaengine: Remove unused define for dma_request_slave_channel_reason() No users left in the kernel, it can be removed. Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20200828084141.14902-1-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 6fbd5c99e30c..011371b7f081 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1527,8 +1527,6 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, } #endif -#define dma_request_slave_channel_reason(dev, name) dma_request_chan(dev, name) - static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx) { struct dma_slave_caps caps; -- cgit v1.2.3 From 31b4b3bff2c217c61bb99db76f24c4886e74a1a5 Mon Sep 17 00:00:00 2001 From: Sebastian Fricke Date: Mon, 3 Aug 2020 07:43:45 +0200 Subject: include/linux/miscdevice.h - Fix typo/grammar Improve the clarity and grammar of descriptive comment on top of the minor number assignments. Fix a typo within 2 comments for macros. s/This helps in eleminating of boilerplate code. /This helps to eliminate boilerplate code./ Signed-off-by: Sebastian Fricke Link: https://lore.kernel.org/r/20200803054346.4285-1-sebastian.fricke.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/miscdevice.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index c7a93002a3c1..0676f18093f9 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -7,9 +7,9 @@ #include /* - * These allocations are managed by device@lanana.org. If you use an - * entry that is not in assigned your entry may well be moved and - * reassigned, or set dynamic if a fixed value is not justified. + * These allocations are managed by device@lanana.org. If you need + * an entry that is not assigned here, it can be moved and + * reassigned or dynamically set if a fixed value is not justified. */ #define PSMOUSE_MINOR 1 @@ -93,14 +93,14 @@ extern void misc_deregister(struct miscdevice *misc); /* * Helper macro for drivers that don't do anything special in the initcall. - * This helps in eleminating of boilerplate code. + * This helps to eliminate boilerplate code. */ #define builtin_misc_device(__misc_device) \ builtin_driver(__misc_device, misc_register) /* * Helper macro for drivers that don't do anything special in module init / exit - * call. This helps in eleminating of boilerplate code. + * call. This helps to eliminate boilerplate code. */ #define module_misc_device(__misc_device) \ module_driver(__misc_device, misc_register, misc_deregister) -- cgit v1.2.3 From 20d9fdee72dfaa1fa7588c7a846283bd740e7157 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 27 Aug 2020 08:55:39 +0900 Subject: ASoC: soc-core: add snd_soc_find_dai_with_mutex() commit 25612477d20b52 ("ASoC: soc-dai: set dai_link dpcm_ flags with a helper") added snd_soc_dai_link_set_capabilities(). But it is using snd_soc_find_dai() (A) which is required client_mutex (B). And client_mutex is soc-core.c local. struct snd_soc_dai *snd_soc_find_dai(xxx) { ... (B) lockdep_assert_held(&client_mutex); ... } void snd_soc_dai_link_set_capabilities(xxx) { ... for_each_pcm_streams(direction) { ... for_each_link_cpus(dai_link, i, cpu) { (A) dai = snd_soc_find_dai(cpu); ... } ... for_each_link_codecs(dai_link, i, codec) { (A) dai = snd_soc_find_dai(codec); ... } } ... } Because of these background, we will get WARNING if .config has CONFIG_LOCKDEP. WARNING: CPU: 2 PID: 53 at sound/soc/soc-core.c:814 snd_soc_find_dai+0xf8/0x100 CPU: 2 PID: 53 Comm: kworker/2:1 Not tainted 5.7.0-rc1+ #328 Hardware name: Renesas H3ULCB Kingfisher board based on r8a77951 (DT) Workqueue: events deferred_probe_work_func pstate: 60000005 (nZCv daif -PAN -UAO) pc : snd_soc_find_dai+0xf8/0x100 lr : snd_soc_find_dai+0xf4/0x100 ... Call trace: snd_soc_find_dai+0xf8/0x100 snd_soc_dai_link_set_capabilities+0xa0/0x16c graph_dai_link_of_dpcm+0x390/0x3c0 graph_for_each_link+0x134/0x200 graph_probe+0x144/0x230 platform_drv_probe+0x5c/0xb0 really_probe+0xe4/0x430 driver_probe_device+0x60/0xf4 snd_soc_find_dai() will be used from (X) CPU/Codec/Platform driver with mutex lock, and (Y) Card driver without mutex lock. This snd_soc_dai_link_set_capabilities() is for Card driver, this means called without mutex. This patch adds snd_soc_find_dai_with_mutex() to solve it. Fixes: 25612477d20b52 ("ASoC: soc-dai: set dai_link dpcm_ flags with a helper") Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87blixvuab.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 5e3919ffb00c..4176071f61bf 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1361,6 +1361,8 @@ void snd_soc_unregister_dai(struct snd_soc_dai *dai); struct snd_soc_dai *snd_soc_find_dai( const struct snd_soc_dai_link_component *dlc); +struct snd_soc_dai *snd_soc_find_dai_with_mutex( + const struct snd_soc_dai_link_component *dlc); #include -- cgit v1.2.3 From b0c9eb37817943840a1a82dbc998c491609a0afd Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 27 Aug 2020 22:19:22 -0700 Subject: bpf: Make bpf_link_info.iter similar to bpf_iter_link_info bpf_link_info.iter is used by link_query to return bpf_iter_link_info to user space. Fields may be different, e.g., map_fd vs. map_id, so we cannot reuse the exact structure. But make them similar, e.g., struct bpf_link_info { /* common fields */ union { struct { ... } raw_tracepoint; struct { ... } tracing; ... struct { /* common fields for iter */ union { struct { __u32 map_id; } map; /* other structs for other targets */ }; }; }; }; so the structure is extensible the same way as bpf_iter_link_info. Fixes: 6b0a249a301e ("bpf: Implement link_query for bpf iterators") Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200828051922.758950-1-yhs@fb.com --- include/uapi/linux/bpf.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0388bc0200b0..ef7af384f5ee 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4251,8 +4251,10 @@ struct bpf_link_info { __aligned_u64 target_name; /* in/out: target_name buffer ptr */ __u32 target_name_len; /* in/out: target_name buffer len */ union { - __u32 map_id; - } map; + struct { + __u32 map_id; + } map; + }; } iter; struct { __u32 netns_ino; -- cgit v1.2.3 From f729ef5796d82a95758d9edc7eea5879a3a12b25 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 13 Jul 2020 13:30:42 +0200 Subject: media: videobuf2-v4l2.c: add vb2_video_unregister_device helper function If a driver calls (_)vb2_fop_release(), then such a driver should also call vb2_video_unregister_device() instead of video_unregister_device(). This helper will call vb2_queue_release() if a filehandle is marked as owner of the queue. This ensures that at unregister time any streaming is cancelled and all buffers are returned to userspace. This is very useful for complex drivers since this stops all streaming in all subdevs in the pipeline controlled by this video device. Otherwise this would be delayed until the owner filehandle is closed, which can be quite some time later. Bonus points for ordering the includes :-) Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf2-v4l2.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h index b7b5a9cb5a28..c203047eb834 100644 --- a/include/media/videobuf2-v4l2.h +++ b/include/media/videobuf2-v4l2.h @@ -23,6 +23,8 @@ #error VB2_MAX_PLANES != VIDEO_MAX_PLANES #endif +struct video_device; + /** * struct vb2_v4l2_buffer - video buffer information for v4l2. * @@ -319,6 +321,21 @@ unsigned long vb2_fop_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif +/** + * vb2_video_unregister_device - unregister the video device and release queue + * + * @vdev: pointer to &struct video_device + * + * If the driver uses vb2_fop_release()/_vb2_fop_release(), then it should use + * vb2_video_unregister_device() instead of video_unregister_device(). + * + * This function will call video_unregister_device() and then release the + * vb2_queue if streaming is in progress. This will stop streaming and + * this will simplify the unbind sequence since after this call all subdevs + * will have stopped streaming as well. + */ +void vb2_video_unregister_device(struct video_device *vdev); + /** * vb2_ops_wait_prepare - helper function to lock a struct &vb2_queue * -- cgit v1.2.3 From cf5153e4338c4cca655a4a4eff6d54c6a0adcdb7 Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Wed, 12 Aug 2020 02:27:19 +0200 Subject: media: gpu: host1x: mipi: Keep MIPI clock enabled and mutex locked till calibration done With the split of MIPI calibration into tegra_mipi_calibrate() and tegra_mipi_wait(), MIPI clock is not kept enabled and mutex is not locked till the calibration is done. So, this patch keeps MIPI clock enabled and mutex locked after triggering start of calibration till its done. To let calibration process go through its finite sequence codes before calibration logic waiting for pads idle state added wait time of 75usec to make sure it sees idle state to apply the results. This patch renames tegra_mipi_calibrate() as tegra_mipi_start_calibration() and tegra_mipi_wait() as tegra_mipi_finish_calibration() to be inline with their usage. Reviewed-by: Dmitry Osipenko Signed-off-by: Sowjanya Komatineni Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/host1x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 20c885d0bddc..ce59a6a6a008 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -333,7 +333,7 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device, void tegra_mipi_free(struct tegra_mipi_device *device); int tegra_mipi_enable(struct tegra_mipi_device *device); int tegra_mipi_disable(struct tegra_mipi_device *device); -int tegra_mipi_calibrate(struct tegra_mipi_device *device); -int tegra_mipi_wait(struct tegra_mipi_device *device); +int tegra_mipi_start_calibration(struct tegra_mipi_device *device); +int tegra_mipi_finish_calibration(struct tegra_mipi_device *device); #endif -- cgit v1.2.3 From 911ea8ec42dea0e28083a6e92b1b4a5a0ad5acca Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Fri, 14 Aug 2020 09:11:40 +0200 Subject: media: v4l2-mem2mem: add v4l2_m2m_suspend, v4l2_m2m_resume Add two functions that can be used to stop new jobs from being queued / continue running queued job. This can be used while a driver using m2m helper is going to suspend / wake up from resume, and can ensure that there's no job running in suspend process. Signed-off-by: Pi-Hsun Shih Signed-off-by: Jerry-ch Chen Reviewed-by: Tomasz Figa Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mem2mem.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index 98753f00df7e..5a91b548ecc0 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -304,6 +304,28 @@ v4l2_m2m_is_last_draining_src_buf(struct v4l2_m2m_ctx *m2m_ctx, void v4l2_m2m_last_buffer_done(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_v4l2_buffer *vbuf); +/** + * v4l2_m2m_suspend() - stop new jobs from being run and wait for current job + * to finish + * + * @m2m_dev: opaque pointer to the internal data to handle M2M context + * + * Called by a driver in the suspend hook. Stop new jobs from being run, and + * wait for current running job to finish. + */ +void v4l2_m2m_suspend(struct v4l2_m2m_dev *m2m_dev); + +/** + * v4l2_m2m_resume() - resume job running and try to run a queued job + * + * @m2m_dev: opaque pointer to the internal data to handle M2M context + * + * Called by a driver in the resume hook. This reverts the operation of + * v4l2_m2m_suspend() and allows job to be run. Also try to run a queued job if + * there is any. + */ +void v4l2_m2m_resume(struct v4l2_m2m_dev *m2m_dev); + /** * v4l2_m2m_reqbufs() - multi-queue-aware REQBUFS multiplexer * -- cgit v1.2.3 From b6f3e21b928a8ae7959a0d79203b80bd70120768 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 26 Aug 2020 16:41:58 +0200 Subject: power: supply: smb347-charger: Drop pdata support There are no platforms using the pdata support, so let's drop it to simplify the driver. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Sebastian Reichel --- include/linux/power/smb347-charger.h | 114 ----------------------------------- 1 file changed, 114 deletions(-) delete mode 100644 include/linux/power/smb347-charger.h (limited to 'include') diff --git a/include/linux/power/smb347-charger.h b/include/linux/power/smb347-charger.h deleted file mode 100644 index e0b687a4d20c..000000000000 --- a/include/linux/power/smb347-charger.h +++ /dev/null @@ -1,114 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Summit Microelectronics SMB347 Battery Charger Driver - * - * Copyright (C) 2011, Intel Corporation - * - * Authors: Bruce E. Robertson - * Mika Westerberg - */ - -#ifndef SMB347_CHARGER_H -#define SMB347_CHARGER_H - -#include -#include - -enum { - /* use the default compensation method */ - SMB347_SOFT_TEMP_COMPENSATE_DEFAULT = -1, - - SMB347_SOFT_TEMP_COMPENSATE_NONE, - SMB347_SOFT_TEMP_COMPENSATE_CURRENT, - SMB347_SOFT_TEMP_COMPENSATE_VOLTAGE, -}; - -/* Use default factory programmed value for hard/soft temperature limit */ -#define SMB347_TEMP_USE_DEFAULT -273 - -/* - * Charging enable can be controlled by software (via i2c) by - * smb347-charger driver or by EN pin (active low/high). - */ -enum smb347_chg_enable { - SMB347_CHG_ENABLE_SW, - SMB347_CHG_ENABLE_PIN_ACTIVE_LOW, - SMB347_CHG_ENABLE_PIN_ACTIVE_HIGH, -}; - -/** - * struct smb347_charger_platform_data - platform data for SMB347 charger - * @battery_info: Information about the battery - * @max_charge_current: maximum current (in uA) the battery can be charged - * @max_charge_voltage: maximum voltage (in uV) the battery can be charged - * @pre_charge_current: current (in uA) to use in pre-charging phase - * @termination_current: current (in uA) used to determine when the - * charging cycle terminates - * @pre_to_fast_voltage: voltage (in uV) treshold used for transitioning to - * pre-charge to fast charge mode - * @mains_current_limit: maximum input current drawn from AC/DC input (in uA) - * @usb_hc_current_limit: maximum input high current (in uA) drawn from USB - * input - * @chip_temp_threshold: die temperature where device starts limiting charge - * current [%100 - %130] (in degree C) - * @soft_cold_temp_limit: soft cold temperature limit [%0 - %15] (in degree C), - * granularity is 5 deg C. - * @soft_hot_temp_limit: soft hot temperature limit [%40 - %55] (in degree C), - * granularity is 5 deg C. - * @hard_cold_temp_limit: hard cold temperature limit [%-5 - %10] (in degree C), - * granularity is 5 deg C. - * @hard_hot_temp_limit: hard hot temperature limit [%50 - %65] (in degree C), - * granularity is 5 deg C. - * @suspend_on_hard_temp_limit: suspend charging when hard limit is hit - * @soft_temp_limit_compensation: compensation method when soft temperature - * limit is hit - * @charge_current_compensation: current (in uA) for charging compensation - * current when temperature hits soft limits - * @use_mains: AC/DC input can be used - * @use_usb: USB input can be used - * @use_usb_otg: USB OTG output can be used (not implemented yet) - * @irq_gpio: GPIO number used for interrupts (%-1 if not used) - * @enable_control: how charging enable/disable is controlled - * (driver/pin controls) - * - * @use_main, @use_usb, and @use_usb_otg are means to enable/disable - * hardware support for these. This is useful when we want to have for - * example OTG charging controlled via OTG transceiver driver and not by - * the SMB347 hardware. - * - * Hard and soft temperature limit values are given as described in the - * device data sheet and assuming NTC beta value is %3750. Even if this is - * not the case, these values should be used. They can be mapped to the - * corresponding NTC beta values with the help of table %2 in the data - * sheet. So for example if NTC beta is %3375 and we want to program hard - * hot limit to be %53 deg C, @hard_hot_temp_limit should be set to %50. - * - * If zero value is given in any of the current and voltage values, the - * factory programmed default will be used. For soft/hard temperature - * values, pass in %SMB347_TEMP_USE_DEFAULT instead. - */ -struct smb347_charger_platform_data { - struct power_supply_info battery_info; - unsigned int max_charge_current; - unsigned int max_charge_voltage; - unsigned int pre_charge_current; - unsigned int termination_current; - unsigned int pre_to_fast_voltage; - unsigned int mains_current_limit; - unsigned int usb_hc_current_limit; - unsigned int chip_temp_threshold; - int soft_cold_temp_limit; - int soft_hot_temp_limit; - int hard_cold_temp_limit; - int hard_hot_temp_limit; - bool suspend_on_hard_temp_limit; - unsigned int soft_temp_limit_compensation; - unsigned int charge_current_compensation; - bool use_mains; - bool use_usb; - bool use_usb_otg; - int irq_gpio; - enum smb347_chg_enable enable_control; -}; - -#endif /* SMB347_CHARGER_H */ -- cgit v1.2.3 From f4d05259213ff1e91f767c91dcab455f68308fac Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 27 Aug 2020 18:18:06 -0700 Subject: bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com --- include/linux/bpf.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a6131d95e31e..dbba82a80087 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -112,6 +112,19 @@ struct bpf_map_ops { void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); + + /* map_meta_equal must be implemented for maps that can be + * used as an inner map. It is a runtime check to ensure + * an inner map can be inserted to an outer map. + * + * Some properties of the inner map has been used during the + * verification time. When inserting an inner map at the runtime, + * map_meta_equal has to ensure the inserting map has the same + * properties that the verifier has used earlier. + */ + bool (*map_meta_equal)(const struct bpf_map *meta0, + const struct bpf_map *meta1); + /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; @@ -235,6 +248,9 @@ int map_check_no_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type); +bool bpf_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1); + extern const struct bpf_map_ops bpf_map_offload_ops; /* function argument constraints */ -- cgit v1.2.3 From 316cdaa1158af17250397054f92bb339fbd8e282 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 26 Aug 2020 09:05:35 -0700 Subject: net: add option to not create fall-back tunnels in root-ns as well The sysctl that was added earlier by commit 79134e6ce2c ("net: do not create fallback tunnels for non-default namespaces") to create fall-back only in root-ns. This patch enhances that behavior to provide option not to create fallback tunnels in root-ns as well. Since modules that create fallback tunnels could be built-in and setting the sysctl value after booting is pointless, so added a kernel cmdline options to change this default. The default setting is preseved for backward compatibility. The kernel command line option of fb_tunnels=initns will set the sysctl value to 1 and will create fallback tunnels only in initns while kernel cmdline fb_tunnels=none will set the sysctl value to 2 and fallback tunnels are skipped in every netns. Signed-off-by: Mahesh Bandewar Cc: Eric Dumazet Cc: Maciej Zenczykowski Cc: Jian Yang Cc: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b8abe1d7aa0b..c0b512e6a02b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -640,10 +640,14 @@ struct netdev_queue { extern int sysctl_fb_tunnels_only_for_init_net; extern int sysctl_devconf_inherit_init_net; +/* + * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns + * == 1 : For initns only + * == 2 : For none. + */ static inline bool net_has_fallback_tunnels(const struct net *net) { - return net == &init_net || - !IS_ENABLED(CONFIG_SYSCTL) || + return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) || !sysctl_fb_tunnels_only_for_init_net; } -- cgit v1.2.3 From 9584051f3cf3af181e577960956bb7c085879b67 Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Thu, 14 May 2020 16:04:27 -0700 Subject: power: supply: charger-manager: Remove cm_notify_event function cm_notify_event() was introduced to get an event associated with the battery status externally (ie in board files), but no one ever used it. Moreover it makes charger manager driver more complicated. Drop the function and all data related to it to simplify the driver. Signed-off-by: Jonghwa Lee Signed-off-by: Krzysztof Kozlowski Signed-off-by: Jonathan Bakker Signed-off-by: Sebastian Reichel --- include/linux/power/charger-manager.h | 33 ++++++--------------------------- 1 file changed, 6 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index ae94dcebd936..3a98837684e3 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -31,16 +31,10 @@ enum polling_modes { CM_POLL_CHARGING_ONLY, }; -enum cm_event_types { - CM_EVENT_UNKNOWN = 0, - CM_EVENT_BATT_FULL, - CM_EVENT_BATT_IN, - CM_EVENT_BATT_OUT, - CM_EVENT_BATT_OVERHEAT, - CM_EVENT_BATT_COLD, - CM_EVENT_EXT_PWR_IN_OUT, - CM_EVENT_CHG_START_STOP, - CM_EVENT_OTHERS, +enum cm_batt_temp { + CM_BATT_OK = 0, + CM_BATT_OVERHEAT, + CM_BATT_COLD, }; /** @@ -131,11 +125,10 @@ struct charger_regulator { * @psy_name: the name of power-supply-class for charger manager * @polling_mode: * Determine which polling mode will be used - * @fullbatt_vchkdrop_ms: * @fullbatt_vchkdrop_uV: * Check voltage drop after the battery is fully charged. - * If it has dropped more than fullbatt_vchkdrop_uV after - * fullbatt_vchkdrop_ms, CM will restart charging. + * If it has dropped more than fullbatt_vchkdrop_uV + * CM will restart charging. * @fullbatt_uV: voltage in microvolt * If VBATT >= fullbatt_uV, it is assumed to be full. * @fullbatt_soc: state of Charge in % @@ -172,7 +165,6 @@ struct charger_desc { enum polling_modes polling_mode; unsigned int polling_interval_ms; - unsigned int fullbatt_vchkdrop_ms; unsigned int fullbatt_vchkdrop_uV; unsigned int fullbatt_uV; unsigned int fullbatt_soc; @@ -211,9 +203,6 @@ struct charger_desc { * @charger_stat: array of power_supply for chargers * @tzd_batt : thermal zone device for battery * @charger_enabled: the state of charger - * @fullbatt_vchk_jiffies_at: - * jiffies at the time full battery check will occur. - * @fullbatt_vchk_work: work queue for full battery check * @emergency_stop: * When setting true, stop charging * @psy_name_buf: the name of power-supply-class for charger manager @@ -235,9 +224,6 @@ struct charger_manager { #endif bool charger_enabled; - unsigned long fullbatt_vchk_jiffies_at; - struct delayed_work fullbatt_vchk_work; - int emergency_stop; char psy_name_buf[PSY_NAME_MAX + 1]; @@ -248,11 +234,4 @@ struct charger_manager { u64 charging_end_time; }; -#if IS_ENABLED(CONFIG_CHARGER_MANAGER) -extern void cm_notify_event(struct power_supply *psy, - enum cm_event_types type, char *msg); -#else -static inline void cm_notify_event(struct power_supply *psy, - enum cm_event_types type, char *msg) { } -#endif #endif /* _CHARGER_MANAGER_H */ -- cgit v1.2.3 From 7a81575b806e5dab214025e6757362c62d946405 Mon Sep 17 00:00:00 2001 From: "Jose M. Guisado Gomez" Date: Thu, 20 Aug 2020 10:19:01 +0200 Subject: netfilter: nf_tables: add userdata attributes to nft_table Enables storing userdata for nft_table. Field udata points to user data and udlen store its length. Adds new attribute flag NFTA_TABLE_USERDATA Signed-off-by: Jose M. Guisado Gomez Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ include/uapi/linux/netfilter/nf_tables.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index bf9491b77d16..97a7e147a59a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1080,6 +1080,8 @@ struct nft_table { flags:8, genmask:2; char *name; + u16 udlen; + u8 *udata; }; void nft_register_chain_type(const struct nft_chain_type *); diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 42f351c1f5c5..aeb88cbd303e 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -172,6 +172,7 @@ enum nft_table_flags { * @NFTA_TABLE_NAME: name of the table (NLA_STRING) * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32) * @NFTA_TABLE_USE: number of chains in this table (NLA_U32) + * @NFTA_TABLE_USERDATA: user data (NLA_BINARY) */ enum nft_table_attributes { NFTA_TABLE_UNSPEC, @@ -180,6 +181,7 @@ enum nft_table_attributes { NFTA_TABLE_USE, NFTA_TABLE_HANDLE, NFTA_TABLE_PAD, + NFTA_TABLE_USERDATA, __NFTA_TABLE_MAX }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) -- cgit v1.2.3 From e132fc6bb89bd307cfcdb8ba24afcd1985261485 Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Thu, 14 May 2020 16:04:31 -0700 Subject: power: supply: charger-manager: Make decisions focussed on battery status cm_monitor(), where charging management starts, checks various charging condition sequentially to decide next charging operation. However, as it follows sequential process, cascaded if statements, it does some jobs which have already done in the previous stage. This results in a delay in decision making. Moreover, starting point of charging is spread all around which makes maintain code and debugging difficult. Both of the problems mentioned above become clean if it manages battery charging focusing on battery status not following sequential condition checking. Now, cm_monitor() moves battery state diagram and does the optimal operation for current state. As a result, it reduces whole monitoring time almost in half. Signed-off-by: Jonghwa Lee Signed-off-by: Krzysztof Kozlowski Signed-off-by: Jonathan Bakker Signed-off-by: Sebastian Reichel --- include/linux/power/charger-manager.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index 3a98837684e3..c127dbe31e49 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -213,6 +213,7 @@ struct charger_desc { * saved status of battery before entering suspend-to-RAM * @charging_start_time: saved start time of enabling charging * @charging_end_time: saved end time of disabling charging + * @battery_status: Current battery status */ struct charger_manager { struct list_head entry; @@ -232,6 +233,8 @@ struct charger_manager { u64 charging_start_time; u64 charging_end_time; + + int battery_status; }; #endif /* _CHARGER_MANAGER_H */ -- cgit v1.2.3 From c1f73028f75df43689feda4bc70573b7d18a618e Mon Sep 17 00:00:00 2001 From: Jonathan Bakker Date: Thu, 14 May 2020 16:04:33 -0700 Subject: power: supply: charger-manager: Update extcon functions In commit 830ae442202e ("extcon: Remove the deprecated extcon functions") the function extcon_register_interest became a no-op returning an error, leading to non-functional behaviour in charger-manager. Additionally, a translation table is needed between the text representation of the extcon cable names and their IDs is needed. In order to retain DT compatibility, TA and CHARGE-DOWNSTREAM are added as they were present up until commit 11eecf910bd8 ("extcon: Modify the id and name of external connector") Signed-off-by: Jonathan Bakker Signed-off-by: Sebastian Reichel --- include/linux/power/charger-manager.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index c127dbe31e49..45e228b353ea 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -40,7 +40,7 @@ enum cm_batt_temp { /** * struct charger_cable * @extcon_name: the name of extcon device. - * @name: the name of charger cable(external connector). + * @name: the name of the cable connector * @extcon_dev: the extcon device. * @wq: the workqueue to control charger according to the state of * charger cable. If charger cable is attached, enable charger. @@ -56,9 +56,10 @@ enum cm_batt_temp { struct charger_cable { const char *extcon_name; const char *name; + struct extcon_dev *extcon_dev; + u64 extcon_type; /* The charger-manager use Extcon framework */ - struct extcon_specific_cable_nb extcon_dev; struct work_struct wq; struct notifier_block nb; -- cgit v1.2.3 From 4afc41dfa5a716e9e7a90c22972583f337c0bcbf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 26 Aug 2020 00:52:43 +0200 Subject: netfilter: conntrack: remove ignore stats This counter increments when nf_conntrack_in sees a packet that already has a conntrack attached or when the packet is marked as UNTRACKED. Neither is an error. The former is normal for loopback traffic. The second happens for certain ICMPv6 packets or when nftables/ip(6)tables rules are in place. In case someone needs to count UNTRACKED packets, or packets that are marked as untracked before conntrack_in this can be done with both nftables and ip(6)tables rules. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 1 - include/uapi/linux/netfilter/nfnetlink_conntrack.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 1db83c931d9c..96b90d7e361f 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -8,7 +8,6 @@ struct ip_conntrack_stat { unsigned int found; unsigned int invalid; - unsigned int ignore; unsigned int insert; unsigned int insert_failed; unsigned int drop; diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 262881792671..3e471558da82 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -247,7 +247,7 @@ enum ctattr_stats_cpu { CTA_STATS_FOUND, CTA_STATS_NEW, /* no longer used */ CTA_STATS_INVALID, - CTA_STATS_IGNORE, + CTA_STATS_IGNORE, /* no longer used */ CTA_STATS_DELETE, /* no longer used */ CTA_STATS_DELETE_LIST, /* no longer used */ CTA_STATS_INSERT, -- cgit v1.2.3 From bc92470413f3af152db0d8f90ef3eb13f8cc417a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 26 Aug 2020 00:52:44 +0200 Subject: netfilter: conntrack: add clash resolution stat counter There is a misconception about what "insert_failed" means. We increment this even when a clash got resolved, so it might not indicate a problem. Add a dedicated counter for clash resolution and only increment insert_failed if a clash cannot be resolved. For the old /proc interface, export this in place of an older stat that got removed a while back. For ctnetlink, export this with a new attribute. Also correct an outdated comment that implies we add a duplicate tuple -- we only add the (unique) reply direction. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 1 + include/uapi/linux/netfilter/nfnetlink_conntrack.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 96b90d7e361f..0c7d8d1e945d 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -10,6 +10,7 @@ struct ip_conntrack_stat { unsigned int invalid; unsigned int insert; unsigned int insert_failed; + unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 3e471558da82..d8484be72fdc 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -256,6 +256,7 @@ enum ctattr_stats_cpu { CTA_STATS_EARLY_DROP, CTA_STATS_ERROR, CTA_STATS_SEARCH_RESTART, + CTA_STATS_CLASH_RESOLVE, __CTA_STATS_MAX, }; #define CTA_STATS_MAX (__CTA_STATS_MAX - 1) -- cgit v1.2.3 From 1e6c62a8821557720a9b2ea9617359b264f2f67c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 27 Aug 2020 15:01:11 -0700 Subject: bpf: Introduce sleepable BPF programs Introduce sleepable BPF programs that can request such property for themselves via BPF_F_SLEEPABLE flag at program load time. In such case they will be able to use helpers like bpf_copy_from_user() that might sleep. At present only fentry/fexit/fmod_ret and lsm programs can request to be sleepable and only when they are attached to kernel functions that are known to allow sleeping. The non-sleepable programs are relying on implicit rcu_read_lock() and migrate_disable() to protect life time of programs, maps that they use and per-cpu kernel structures used to pass info between bpf programs and the kernel. The sleepable programs cannot be enclosed into rcu_read_lock(). migrate_disable() maps to preempt_disable() in non-RT kernels, so the progs should not be enclosed in migrate_disable() as well. Therefore rcu_read_lock_trace is used to protect the life time of sleepable progs. There are many networking and tracing program types. In many cases the 'struct bpf_prog *' pointer itself is rcu protected within some other kernel data structure and the kernel code is using rcu_dereference() to load that program pointer and call BPF_PROG_RUN() on it. All these cases are not touched. Instead sleepable bpf programs are allowed with bpf trampoline only. The program pointers are hard-coded into generated assembly of bpf trampoline and synchronize_rcu_tasks_trace() is used to protect the life time of the program. The same trampoline can hold both sleepable and non-sleepable progs. When rcu_read_lock_trace is held it means that some sleepable bpf program is running from bpf trampoline. Those programs can use bpf arrays and preallocated hash/lru maps. These map types are waiting on programs to complete via synchronize_rcu_tasks_trace(); Updates to trampoline now has to do synchronize_rcu_tasks_trace() and synchronize_rcu_tasks() to wait for sleepable progs to finish and for trampoline assembly to finish. This is the first step of introducing sleepable progs. Eventually dynamically allocated hash maps can be allowed and networking program types can become sleepable too. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Reviewed-by: Josef Bacik Acked-by: Andrii Nakryiko Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20200827220114.69225-3-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 8 ++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index dbba82a80087..4dd7e927621d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -539,6 +539,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); +void notrace __bpf_prog_enter_sleepable(void); +void notrace __bpf_prog_exit_sleepable(void); struct bpf_ksym { unsigned long start; @@ -734,6 +736,7 @@ struct bpf_prog_aux { bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; + bool sleepable; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ef7af384f5ee..6e8b706aeb05 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -346,6 +346,14 @@ enum bpf_link_type { /* The verifier internal test flag. Behavior is undefined */ #define BPF_F_TEST_STATE_FREQ (1U << 3) +/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will + * restrict map and helper usage for such programs. Sleepable BPF programs can + * only be attached to hooks where kernel execution context allows sleeping. + * Such programs are allowed to use helpers that may sleep like + * bpf_copy_from_user(). + */ +#define BPF_F_SLEEPABLE (1U << 4) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * -- cgit v1.2.3 From 07be4c4a3e7a0db148e44b16c5190e753d1c8569 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 27 Aug 2020 15:01:12 -0700 Subject: bpf: Add bpf_copy_from_user() helper. Sleepable BPF programs can now use copy_from_user() to access user memory. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20200827220114.69225-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4dd7e927621d..c6d9f2c444f4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1784,6 +1784,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; +extern const struct bpf_func_proto bpf_copy_from_user_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6e8b706aeb05..a613750d5515 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3569,6 +3569,13 @@ union bpf_attr { * On success, the strictly positive length of the string, * including the trailing NUL character. On error, a negative * value. + * + * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) + * Description + * Read *size* bytes from user space address *user_ptr* and store + * the data in *dst*. This is a wrapper of copy_from_user(). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3719,6 +3726,7 @@ union bpf_attr { FN(inode_storage_get), \ FN(inode_storage_delete), \ FN(d_path), \ + FN(copy_from_user), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 67407a406db337acdaabecd3747d160d89a929e4 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Sat, 29 Aug 2020 08:19:15 +0200 Subject: netfilter: nft_socket: add wildcard support Add NFT_SOCKET_WILDCARD to match to wildcard socket listener. Signed-off-by: Balazs Scheidler Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index aeb88cbd303e..543dc697b796 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1010,10 +1010,12 @@ enum nft_socket_attributes { * * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option * @NFT_SOCKET_MARK: Value of the socket mark + * @NFT_SOCKET_WILDCARD: Whether the socket is zero-bound (e.g. 0.0.0.0 or ::0) */ enum nft_socket_keys { NFT_SOCKET_TRANSPARENT, NFT_SOCKET_MARK, + NFT_SOCKET_WILDCARD, __NFT_SOCKET_MAX }; #define NFT_SOCKET_MAX (__NFT_SOCKET_MAX - 1) -- cgit v1.2.3 From afff77ce882dbd1a5fe0047df49b68a96cfe6d9b Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Mon, 24 Aug 2020 15:37:01 +0800 Subject: clk: imx: Correct the root clk of media ldb on imx8mp The root clock slice at 0xbf00 is media_ldb clock, not csi_phy2_ref, so correct it. Signed-off-by: Jacky Bai Signed-off-by: Shawn Guo --- include/dt-bindings/clock/imx8mp-clock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index 7a23f289b27f..e8d68fbb6e3f 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -180,7 +180,7 @@ #define IMX8MP_CLK_MEDIA_MIPI_PHY1_REF 171 #define IMX8MP_CLK_MEDIA_DISP1_PIX 172 #define IMX8MP_CLK_MEDIA_CAM2_PIX 173 -#define IMX8MP_CLK_MEDIA_MIPI_PHY2_REF 174 +#define IMX8MP_CLK_MEDIA_LDB 174 #define IMX8MP_CLK_MEDIA_MIPI_CSI2_ESC 175 #define IMX8MP_CLK_PCIE2_CTRL 176 #define IMX8MP_CLK_PCIE2_PHY 177 -- cgit v1.2.3 From d452bd091e168f75ec2807c30eec1f7be918c737 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Fri, 28 Aug 2020 16:31:25 +0300 Subject: drm/i915: break TGL pci-ids in GT 1 & 2 I'll need this in IGT to identify the different kind of GTs and apply the right performance query configuration. Signed-off-by: Lionel Landwerlin Reviewed-by: Ashutosh Dixit Link: https://patchwork.freedesktop.org/patch/msgid/20200828133125.157171-1-lionel.g.landwerlin@intel.com --- include/drm/i915_pciids.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 8e7ae30ebcbb..7eeecb07c9a1 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -594,19 +594,25 @@ INTEL_VGA_DEVICE(0x4E51, info) /* TGL */ -#define INTEL_TGL_12_IDS(info) \ +#define INTEL_TGL_12_GT1_IDS(info) \ + INTEL_VGA_DEVICE(0x9A60, info), \ + INTEL_VGA_DEVICE(0x9A68, info), \ + INTEL_VGA_DEVICE(0x9A70, info) + +#define INTEL_TGL_12_GT2_IDS(info) \ INTEL_VGA_DEVICE(0x9A40, info), \ INTEL_VGA_DEVICE(0x9A49, info), \ INTEL_VGA_DEVICE(0x9A59, info), \ - INTEL_VGA_DEVICE(0x9A60, info), \ - INTEL_VGA_DEVICE(0x9A68, info), \ - INTEL_VGA_DEVICE(0x9A70, info), \ INTEL_VGA_DEVICE(0x9A78, info), \ INTEL_VGA_DEVICE(0x9AC0, info), \ INTEL_VGA_DEVICE(0x9AC9, info), \ INTEL_VGA_DEVICE(0x9AD9, info), \ INTEL_VGA_DEVICE(0x9AF8, info) +#define INTEL_TGL_12_IDS(info) \ + INTEL_TGL_12_GT1_IDS(info), \ + INTEL_TGL_12_GT2_IDS(info) + /* RKL */ #define INTEL_RKL_IDS(info) \ INTEL_VGA_DEVICE(0x4C80, info), \ -- cgit v1.2.3 From 074bf2c2c7a1f5722eabccee7d919fe20ada0cda Mon Sep 17 00:00:00 2001 From: Weihang Li Date: Fri, 21 Aug 2020 17:31:29 +0800 Subject: RDMA/hns: Get udp sport num dynamically instead of using a fixed value The UDP source port number in RoCE v2 is used to create entropy for network routers (ECMP), load balancers and 802.3ad link aggregation switching that are not aware of RoCE IB headers. Considering that the IB core has achieved a new interface to get a hashed value of it, the fixed value of it in QPC and UD WQE in hns driver could be fixed and the port number is to be set dynamically now. For QPC of RC, the value could be hashed from flow_lable if the user pass it in or from remote qpn and local qpn. For WQE of UD, it is set according to fl or as a random value. Link: https://lore.kernel.org/r/1598002289-8611-1-git-send-email-liweihang@huawei.com Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 55dfe0e9d1d6..c868609a4ffa 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4706,6 +4706,7 @@ bool rdma_dev_access_netns(const struct ib_device *device, const struct net *net); #define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000) +#define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF) #define IB_GRH_FLOWLABEL_MASK (0x000FFFFF) /** -- cgit v1.2.3 From 61690d01db32eb1f94adc9ac2b8bb741d34e4671 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 25 Aug 2020 15:17:08 -0300 Subject: RDMA/umem: Fix signature of stub ib_umem_find_best_pgsz() The original function returns unsigned long and 0 on failure. Fixes: 4a35339958f1 ("RDMA/umem: Add API to find best driver supported page size in an MR") Link: https://lore.kernel.org/r/0-v1-982a13cc5c6d+501ae-fix_best_pgsz_stub_jgg@nvidia.com Reviewed-by: Gal Pressman Acked-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- include/rdma/ib_umem.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 71f573a418bf..07a764eb692e 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -68,10 +68,11 @@ static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offs size_t length) { return -EINVAL; } -static inline int ib_umem_find_best_pgsz(struct ib_umem *umem, - unsigned long pgsz_bitmap, - unsigned long virt) { - return -EINVAL; +static inline unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, + unsigned long pgsz_bitmap, + unsigned long virt) +{ + return 0; } #endif /* CONFIG_INFINIBAND_USER_MEM */ -- cgit v1.2.3 From 55977744f9d862512a524fea93fc5226b09e76a9 Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Fri, 28 Aug 2020 18:50:42 -0400 Subject: drm/amdkfd: Add GPU reset SMI event Add support for reporting GPU reset events through SMI. KFD would report both pre and post GPU reset events. Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index cb1f963a84e0..8b7368bfbd84 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -453,6 +453,8 @@ enum kfd_smi_event { KFD_SMI_EVENT_NONE = 0, /* not used */ KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ KFD_SMI_EVENT_THERMAL_THROTTLE = 2, + KFD_SMI_EVENT_GPU_PRE_RESET = 3, + KFD_SMI_EVENT_GPU_POST_RESET = 4, }; #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1)) -- cgit v1.2.3 From 5dc1a0bcb758c343b873e8330ee986417f5a1727 Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Fri, 28 Aug 2020 19:53:08 -0400 Subject: include/uapi/linux: Fix indentation in kfd_smi_event enum Replace spaces with Tabs to fix indentation in kfd_smi_event enum. Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 8b7368bfbd84..695b606da4b1 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -450,9 +450,9 @@ struct kfd_ioctl_import_dmabuf_args { * KFD SMI(System Management Interface) events */ enum kfd_smi_event { - KFD_SMI_EVENT_NONE = 0, /* not used */ - KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ - KFD_SMI_EVENT_THERMAL_THROTTLE = 2, + KFD_SMI_EVENT_NONE = 0, /* not used */ + KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ + KFD_SMI_EVENT_THERMAL_THROTTLE = 2, KFD_SMI_EVENT_GPU_PRE_RESET = 3, KFD_SMI_EVENT_GPU_POST_RESET = 4, }; -- cgit v1.2.3 From 9667305c6374df8672be46bc496f52f040999531 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 31 Aug 2020 08:51:55 -0700 Subject: bpf: Fix build without BPF_SYSCALL, but with BPF_JIT. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When CONFIG_BPF_SYSCALL is not set, but CONFIG_BPF_JIT=y the kernel build fails: In file included from ../kernel/bpf/trampoline.c:11: ../kernel/bpf/trampoline.c: In function ‘bpf_trampoline_update’: ../kernel/bpf/trampoline.c:220:39: error: ‘call_rcu_tasks_trace’ undeclared ../kernel/bpf/trampoline.c: In function ‘__bpf_prog_enter_sleepable’: ../kernel/bpf/trampoline.c:411:2: error: implicit declaration of function ‘rcu_read_lock_trace’ ../kernel/bpf/trampoline.c: In function ‘__bpf_prog_exit_sleepable’: ../kernel/bpf/trampoline.c:416:2: error: implicit declaration of function ‘rcu_read_unlock_trace’ This is due to: obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_JIT) += dispatcher.o There is a number of functions that arch/x86/net/bpf_jit_comp.c is using from these two files, but none of them will be used when only cBPF is on (which is the case for BPF_SYSCALL=n BPF_JIT=y). Add rcu_trace functions to rcupdate_trace.h. The JITed code won't execute them and BPF trampoline logic won't be used without BPF_SYSCALL. Fixes: 1e6c62a88215 ("bpf: Introduce sleepable BPF programs") Reported-by: kernel test robot Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Paul E. McKenney Link: https://lore.kernel.org/bpf/20200831155155.62754-1-alexei.starovoitov@gmail.com --- include/linux/rcupdate_trace.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index d9015aac78c6..aaaac8ac927c 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -82,7 +82,14 @@ static inline void rcu_read_unlock_trace(void) void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); void synchronize_rcu_tasks_trace(void); void rcu_barrier_tasks_trace(void); - +#else +/* + * The BPF JIT forms these addresses even when it doesn't call these + * functions, so provide definitions that result in runtime errors. + */ +static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { BUG(); } +static inline void rcu_read_lock_trace(void) { BUG(); } +static inline void rcu_read_unlock_trace(void) { BUG(); } #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ #endif /* __LINUX_RCUPDATE_TRACE_H */ -- cgit v1.2.3 From 1742b3d528690ae7773cf7bf2f01a90ee1de2fe0 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:15 +0200 Subject: xsk: i40e: ice: ixgbe: mlx5: Pass buffer pool to driver instead of umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the explicit umem reference passed to the driver in AF_XDP zero-copy mode with the buffer pool instead. This in preparation for extending the functionality of the zero-copy mode so that umems can be shared between queues on the same netdev and also between netdevs. In this commit, only an umem reference has been added to the buffer pool struct. But later commits will add other entities to it. These are going to be entities that are different between different queue ids and netdevs even though the umem is shared between them. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-2-git-send-email-magnus.karlsson@intel.com --- include/linux/netdevice.h | 10 +++++----- include/net/xdp_sock_drv.h | 7 ++++--- include/net/xsk_buff_pool.h | 4 +++- 3 files changed, 12 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..d088dd866825 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -618,7 +618,7 @@ struct netdev_queue { /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif /* * write-mostly part @@ -751,7 +751,7 @@ struct netdev_rx_queue { struct net_device *dev; struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif } ____cacheline_aligned_in_smp; @@ -879,7 +879,7 @@ enum bpf_netdev_command { /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, - XDP_SETUP_XSK_UMEM, + XDP_SETUP_XSK_POOL, }; struct bpf_prog_offload_ops; @@ -913,9 +913,9 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_SETUP_XSK_UMEM */ + /* XDP_SETUP_XSK_POOL */ struct { - struct xdp_umem *umem; + struct xsk_buff_pool *pool; u16 queue_id; } xsk; }; diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index ccf848f7efa4..5dc8d3c0dcd4 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -14,7 +14,8 @@ void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); +struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev, + u16 queue_id); void xsk_set_rx_need_wakeup(struct xdp_umem *umem); void xsk_set_tx_need_wakeup(struct xdp_umem *umem); void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); @@ -125,8 +126,8 @@ static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) { } -static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) +static inline struct xsk_buff_pool * +xdp_get_xsk_pool_from_qid(struct net_device *dev, u16 queue_id) { return NULL; } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 6842990e2712..f851b0a68324 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -13,6 +13,7 @@ struct xsk_buff_pool; struct xdp_rxq_info; struct xsk_queue; struct xdp_desc; +struct xdp_umem; struct device; struct page; @@ -42,13 +43,14 @@ struct xsk_buff_pool { u32 frame_len; bool dma_need_sync; bool unaligned; + struct xdp_umem *umem; void *addrs; struct device *dev; struct xdp_buff_xsk *free_heads[]; }; /* AF_XDP core. */ -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, +struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks, u32 chunk_size, u32 headroom, u64 size, bool unaligned); void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); -- cgit v1.2.3 From c4655761d3cf62bf5f86650e79349c1bfa5c6285 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:16 +0200 Subject: xsk: i40e: ice: ixgbe: mlx5: Rename xsk zero-copy driver interfaces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename the AF_XDP zero-copy driver interface functions to better reflect what they do after the replacement of umems with buffer pools in the previous commit. Mostly it is about replacing the umem name from the function names with xsk_buff and also have them take the a buffer pool pointer instead of a umem. The various ring functions have also been renamed in the process so that they have the same naming convention as the internal functions in xsk_queue.h. This so that it will be clearer what they do and also for consistency. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-3-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 1 + include/net/xdp_sock_drv.h | 114 +++++++++++++++++++++++---------------------- 2 files changed, 60 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index c9d87cc40c11..ccf6cb54f9a6 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -52,6 +52,7 @@ struct xdp_sock { struct net_device *dev; struct xdp_umem *umem; struct list_head flush_node; + struct xsk_buff_pool *pool; u16 queue_id; bool zc; enum { diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 5dc8d3c0dcd4..a7c7d2eff860 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -11,48 +11,50 @@ #ifdef CONFIG_XDP_SOCKETS -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); -void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev, - u16 queue_id); -void xsk_set_rx_need_wakeup(struct xdp_umem *umem); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem); +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); +void xsk_tx_release(struct xsk_buff_pool *pool); +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id); +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool); +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool); -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { - return XDP_PACKET_HEADROOM + umem->headroom; + return XDP_PACKET_HEADROOM + pool->headroom; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { - return umem->chunk_size; + return pool->chunk_size; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { - return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem); + return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { - xp_set_rxq_info(umem->pool, rxq); + xp_set_rxq_info(pool, rxq); } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { - xp_dma_unmap(umem->pool, attrs); + xp_dma_unmap(pool, attrs); } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { - return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs); + struct xdp_umem *umem = pool->umem; + + return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs); } static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp) @@ -69,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return xp_get_frame_dma(xskb); } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { - return xp_alloc(umem->pool); + return xp_alloc(pool); } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { - return xp_can_alloc(umem->pool, count); + return xp_can_alloc(pool, count); } static inline void xsk_buff_free(struct xdp_buff *xdp) @@ -86,14 +88,15 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { - return xp_raw_get_dma(umem->pool, addr); + return xp_raw_get_dma(pool, addr); } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { - return xp_raw_get_data(umem->pool, addr); + return xp_raw_get_data(pool, addr); } static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) @@ -103,83 +106,83 @@ static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) xp_dma_sync_for_cpu(xskb); } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - xp_dma_sync_for_device(umem->pool, dma, size); + xp_dma_sync_for_device(pool, dma, size); } #else -static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, - struct xdp_desc *desc) +static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, + struct xdp_desc *desc) { return false; } -static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +static inline void xsk_tx_release(struct xsk_buff_pool *pool) { } static inline struct xsk_buff_pool * -xdp_get_xsk_pool_from_qid(struct net_device *dev, u16 queue_id) +xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) { return NULL; } -static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { return false; } -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { return 0; } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { return 0; } @@ -194,12 +197,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return 0; } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { return NULL; } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return false; } @@ -208,12 +211,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { return 0; } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { return NULL; } @@ -222,7 +226,7 @@ static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) { } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { -- cgit v1.2.3 From 1c1efc2af158869795d3334a12fed2afd9c51539 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:17 +0200 Subject: xsk: Create and free buffer pool independently from umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Create and free the buffer pool independently from the umem. Move these operations that are performed on the buffer pool from the umem create and destroy functions to new create and destroy functions just for the buffer pool. This so that in later commits we can instantiate multiple buffer pools per umem when sharing a umem between HW queues and/or devices. We also erradicate the back pointer from the umem to the buffer pool as this will not work when we introduce the possibility to have multiple buffer pools per umem. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-4-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 3 +-- include/net/xsk_buff_pool.h | 13 ++++++++++--- 2 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index ccf6cb54f9a6..ea2b020c4fbc 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -20,13 +20,12 @@ struct xdp_buff; struct xdp_umem { struct xsk_queue *fq; struct xsk_queue *cq; - struct xsk_buff_pool *pool; u64 size; u32 headroom; u32 chunk_size; + u32 chunks; struct user_struct *user; refcount_t users; - struct work_struct work; struct page **pgs; u32 npgs; u16 queue_id; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index f851b0a68324..4025486cc057 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -14,6 +14,7 @@ struct xdp_rxq_info; struct xsk_queue; struct xdp_desc; struct xdp_umem; +struct xdp_sock; struct device; struct page; @@ -46,16 +47,22 @@ struct xsk_buff_pool { struct xdp_umem *umem; void *addrs; struct device *dev; + refcount_t users; + struct work_struct work; struct xdp_buff_xsk *free_heads[]; }; /* AF_XDP core. */ -struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned); +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem); +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags); void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); +void xp_get_pool(struct xsk_buff_pool *pool); +void xp_put_pool(struct xsk_buff_pool *pool); +void xp_clear_dev(struct xsk_buff_pool *pool); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); -- cgit v1.2.3 From 7361f9c3d71955c624fdad5676c99fc88a8249e9 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:18 +0200 Subject: xsk: Move fill and completion rings to buffer pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the fill and completion rings from the umem to the buffer pool. This so that we in a later commit can share the umem between multiple HW queue ids. In this case, we need one fill and completion ring per queue id. As the buffer pool is per queue id and napi id this is a natural place for it and one umem struture can be shared between these buffer pools. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-5-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 4 ++-- include/net/xsk_buff_pool.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index ea2b020c4fbc..2a284e137e9a 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -18,8 +18,6 @@ struct xsk_queue; struct xdp_buff; struct xdp_umem { - struct xsk_queue *fq; - struct xsk_queue *cq; u64 size; u32 headroom; u32 chunk_size; @@ -77,6 +75,8 @@ struct xdp_sock { struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; + struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */ + struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; #ifdef CONFIG_XDP_SOCKETS diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 4025486cc057..380d9aeedbea 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -30,6 +30,7 @@ struct xdp_buff_xsk { struct xsk_buff_pool { struct xsk_queue *fq; + struct xsk_queue *cq; struct list_head free_list; dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; @@ -57,7 +58,6 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); -- cgit v1.2.3 From c2d3d6a474629e30428b1622af3d551f560cd1d8 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:19 +0200 Subject: xsk: Move queue_id, dev and need_wakeup to buffer pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move queue_id, dev, and need_wakeup from the umem to the buffer pool. This so that we in a later commit can share the umem between multiple HW queues. There is one buffer pool per dev and queue id, so these variables should belong to the buffer pool, not the umem. Need_wakeup is also something that is set on a per napi level, so there is usually one per device and queue id. So move this to the buffer pool too. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-6-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 3 --- include/net/xsk_buff_pool.h | 4 ++++ 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 2a284e137e9a..b052f1c005a9 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -26,11 +26,8 @@ struct xdp_umem { refcount_t users; struct page **pgs; u32 npgs; - u16 queue_id; - u8 need_wakeup; u8 flags; int id; - struct net_device *dev; bool zc; spinlock_t xsk_tx_list_lock; struct list_head xsk_tx_list; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 380d9aeedbea..2d948905f05f 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -43,11 +43,15 @@ struct xsk_buff_pool { u32 headroom; u32 chunk_size; u32 frame_len; + u16 queue_id; + u8 cached_need_wakeup; + bool uses_need_wakeup; bool dma_need_sync; bool unaligned; struct xdp_umem *umem; void *addrs; struct device *dev; + struct net_device *netdev; refcount_t users; struct work_struct work; struct xdp_buff_xsk *free_heads[]; -- cgit v1.2.3 From a5aa8e529e3667eb377ec132d4b4926dee065a45 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:20 +0200 Subject: xsk: Move xsk_tx_list and its lock to buffer pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the xsk_tx_list and the xsk_tx_list_lock from the umem to the buffer pool. This so that we in a later commit can share the umem between multiple HW queues. There is one xsk_tx_list per device and queue id, so it should be located in the buffer pool. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-7-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 4 +--- include/net/xsk_buff_pool.h | 5 +++++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index b052f1c005a9..9a61d05ec132 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -29,8 +29,6 @@ struct xdp_umem { u8 flags; int id; bool zc; - spinlock_t xsk_tx_list_lock; - struct list_head xsk_tx_list; }; struct xsk_map { @@ -57,7 +55,7 @@ struct xdp_sock { /* Protects multiple processes in the control path */ struct mutex mutex; struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; + struct list_head tx_list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 2d948905f05f..83f100c6d440 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -52,6 +52,9 @@ struct xsk_buff_pool { void *addrs; struct device *dev; struct net_device *netdev; + struct list_head xsk_tx_list; + /* Protects modifications to the xsk_tx_list */ + spinlock_t xsk_tx_list_lock; refcount_t users; struct work_struct work; struct xdp_buff_xsk *free_heads[]; @@ -67,6 +70,8 @@ void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); void xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); -- cgit v1.2.3 From 7f7ffa4e9c38f01d380ed9df6adb238fd5e6eea5 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:21 +0200 Subject: xsk: Move addrs from buffer pool to umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replicate the addrs pointer in the buffer pool to the umem. This mapping will be the same for all buffer pools sharing the same umem. In the buffer pool we leave the addrs pointer for performance reasons. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-8-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 9a61d05ec132..126d24364b5a 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -18,6 +18,7 @@ struct xsk_queue; struct xdp_buff; struct xdp_umem { + void *addrs; u64 size; u32 headroom; u32 chunk_size; -- cgit v1.2.3 From 921b68692abb4fd02237b6875b2056bc59435116 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:22 +0200 Subject: xsk: Enable sharing of dma mappings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enable the sharing of dma mappings by moving them out from the buffer pool. Instead we put each dma mapped umem region in a list in the umem structure. If dma has already been mapped for this umem and device, it is not mapped again and the existing dma mappings are reused. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-9-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 1 + include/net/xsk_buff_pool.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 126d24364b5a..282aeba0d20f 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -30,6 +30,7 @@ struct xdp_umem { u8 flags; int id; bool zc; + struct list_head xsk_dma_list; }; struct xsk_map { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 83f100c6d440..356d0ac74eba 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -28,10 +28,23 @@ struct xdp_buff_xsk { struct list_head free_list_node; }; +struct xsk_dma_map { + dma_addr_t *dma_pages; + struct device *dev; + struct net_device *netdev; + refcount_t users; + struct list_head list; /* Protected by the RTNL_LOCK */ + u32 dma_pages_cnt; + bool dma_need_sync; +}; + struct xsk_buff_pool { struct xsk_queue *fq; struct xsk_queue *cq; struct list_head free_list; + /* For performance reasons, each buff pool has its own array of dma_pages + * even when they are identical. + */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; u64 chunk_mask; -- cgit v1.2.3 From 8ef4e27eb3f03edfbfbe5657b8061f2a47757037 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:23 +0200 Subject: xsk: Rearrange internal structs for better performance MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rearrange the xdp_sock, xdp_umem and xsk_buff_pool structures so that they get smaller and align better to the cache lines. In the previous commits of this patch set, these structs have been reordered with the focus on functionality and simplicity, not performance. This patch improves throughput performance by around 3%. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-10-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock.h | 13 +++++++------ include/net/xsk_buff_pool.h | 27 +++++++++++++++------------ 2 files changed, 22 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 282aeba0d20f..1a9559c0cbdd 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -23,13 +23,13 @@ struct xdp_umem { u32 headroom; u32 chunk_size; u32 chunks; + u32 npgs; struct user_struct *user; refcount_t users; - struct page **pgs; - u32 npgs; u8 flags; - int id; bool zc; + struct page **pgs; + int id; struct list_head xsk_dma_list; }; @@ -42,7 +42,7 @@ struct xsk_map { struct xdp_sock { /* struct sock must be the first member of struct xdp_sock */ struct sock sk; - struct xsk_queue *rx; + struct xsk_queue *rx ____cacheline_aligned_in_smp; struct net_device *dev; struct xdp_umem *umem; struct list_head flush_node; @@ -54,8 +54,7 @@ struct xdp_sock { XSK_BOUND, XSK_UNBOUND, } state; - /* Protects multiple processes in the control path */ - struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; struct list_head tx_list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths @@ -72,6 +71,8 @@ struct xdp_sock { struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; + /* Protects multiple processes in the control path */ + struct mutex mutex; struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */ struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 356d0ac74eba..38d03a64c9ea 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -39,9 +39,22 @@ struct xsk_dma_map { }; struct xsk_buff_pool { - struct xsk_queue *fq; - struct xsk_queue *cq; + /* Members only used in the control path first. */ + struct device *dev; + struct net_device *netdev; + struct list_head xsk_tx_list; + /* Protects modifications to the xsk_tx_list */ + spinlock_t xsk_tx_list_lock; + refcount_t users; + struct xdp_umem *umem; + struct work_struct work; struct list_head free_list; + u32 heads_cnt; + u16 queue_id; + + /* Data path members as close to free_heads at the end as possible. */ + struct xsk_queue *fq ____cacheline_aligned_in_smp; + struct xsk_queue *cq; /* For performance reasons, each buff pool has its own array of dma_pages * even when they are identical. */ @@ -51,25 +64,15 @@ struct xsk_buff_pool { u64 addrs_cnt; u32 free_list_cnt; u32 dma_pages_cnt; - u32 heads_cnt; u32 free_heads_cnt; u32 headroom; u32 chunk_size; u32 frame_len; - u16 queue_id; u8 cached_need_wakeup; bool uses_need_wakeup; bool dma_need_sync; bool unaligned; - struct xdp_umem *umem; void *addrs; - struct device *dev; - struct net_device *netdev; - struct list_head xsk_tx_list; - /* Protects modifications to the xsk_tx_list */ - spinlock_t xsk_tx_list_lock; - refcount_t users; - struct work_struct work; struct xdp_buff_xsk *free_heads[]; }; -- cgit v1.2.3 From 9647c57b11e563f5b33a49ef72b347753917c21c Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:24 +0200 Subject: xsk: i40e: ice: ixgbe: mlx5: Test for dma_need_sync earlier for better performance MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Test for dma_need_sync earlier to increase performance. xsk_buff_dma_sync_for_cpu() takes an xdp_buff as parameter and from that the xsk_buff_pool reference is dug out. Perf shows that this dereference causes a lot of cache misses. But as the buffer pool is now sent down to the driver at zero-copy initialization time, we might as well use this pointer directly, instead of going via the xsk_buff and we can do so already in xsk_buff_dma_sync_for_cpu() instead of in xp_dma_sync_for_cpu. This gets rid of these cache misses. Throughput increases with 3% for the xdpsock l2fwd sample application on my machine. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-11-git-send-email-magnus.karlsson@intel.com --- include/net/xdp_sock_drv.h | 7 +++++-- include/net/xsk_buff_pool.h | 3 --- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index a7c7d2eff860..5b1ee8a9976d 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -99,10 +99,13 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return xp_raw_get_data(pool, addr); } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + if (!pool->dma_need_sync) + return; + xp_dma_sync_for_cpu(xskb); } @@ -222,7 +225,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return NULL; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 38d03a64c9ea..907537dddcac 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -114,9 +114,6 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - if (!xskb->pool->dma_need_sync) - return; - xp_dma_sync_for_cpu_slow(xskb); } -- cgit v1.2.3 From b5aea28dca13456c1a08b9b2ef8a8b92598ac426 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 28 Aug 2020 10:26:25 +0200 Subject: xsk: Add shared umem support between queue ids MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support to share a umem between queue ids on the same device. This mode can be invoked with the XDP_SHARED_UMEM bind flag. Previously, sharing was only supported within the same queue id and device, and you shared one set of fill and completion rings. However, note that when sharing a umem between queue ids, you need to create a fill ring and a completion ring and tie them to the socket before you do the bind with the XDP_SHARED_UMEM flag. This so that the single-producer single-consumer semantics can be upheld. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/1598603189-32145-12-git-send-email-magnus.karlsson@intel.com --- include/net/xsk_buff_pool.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 907537dddcac..0140d086dc84 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -81,6 +81,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); -- cgit v1.2.3 From 1d97898b36bab91e8ffb38a660cc40eaba613f88 Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 28 Aug 2020 23:14:31 +0800 Subject: ipv6: add ipv6_fragment hook in ipv6_stub Add ipv6_fragment to ipv6_stub to avoid calling netfilter when access ip6_fragment. Signed-off-by: wenxu Signed-off-by: David S. Miller --- include/net/ipv6_stubs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index d7a7f7c81e7b..8fce558b5fea 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -63,6 +63,9 @@ struct ipv6_stub { int encap_type); #endif struct neigh_table *nd_tbl; + + int (*ipv6_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; -- cgit v1.2.3 From 5af68891dc16e1c8216705034a5e0144fd47779a Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Sat, 29 Aug 2020 05:21:30 -0400 Subject: net: clean up codestyle This is a pure codestyle cleanup patch. No functional change intended. Signed-off-by: Miaohe Lin Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- include/net/sock.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 6ae2e625050d..8ea8812b0b41 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -214,7 +214,7 @@ dst_allfrag(const struct dst_entry *dst) static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { - return dst_metric(dst, RTAX_LOCK) & (1<sk_forward_alloc || + return size <= sk->sk_forward_alloc || __sk_mem_schedule(sk, size, SK_MEM_RECV) || skb_pfmemalloc(skb); } -- cgit v1.2.3 From afd6220999d4932616322f8a893371f8d0567a2a Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Sun, 30 Aug 2020 11:33:58 +0300 Subject: net: phylink: add helper function to decode USXGMII word With the new addition of the USXGMII link partner ability constants we can now introduce a phylink helper that decodes the USXGMII word and populates the appropriate fields in the phylink_link_state structure based on them. Signed-off-by: Ioana Ciornei Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c36fb41a7d90..d81a714cfbbd 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -490,4 +490,7 @@ void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); + +void phylink_decode_usxgmii_word(struct phylink_link_state *state, + uint16_t lpa); #endif -- cgit v1.2.3 From 2dab432c5ae4f9c8eab3132ac0e9facf498ead92 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Sun, 30 Aug 2020 11:34:00 +0300 Subject: net: mdiobus: add clause 45 mdiobus write accessor Add the locked variant of the clause 45 mdiobus write accessor - mdiobus_c45_write(). Signed-off-by: Ioana Ciornei Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/linux/mdio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 898cbf00332a..3a88b699b758 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -358,6 +358,12 @@ static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); } +static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, + u16 regnum, u16 val) +{ + return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); -- cgit v1.2.3 From 0da4c3d393e40e41e3c6b9f1cebaa498512c2abb Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Sun, 30 Aug 2020 11:34:01 +0300 Subject: net: phy: add Lynx PCS module Add a Lynx PCS module which exposes the necessary operations to drive the PCS using phylink. The majority of the code is extracted from the Felix DSA driver, which will be also modified in a later patch, and exposed as a separate module for code reusability purposes. As such, this aims at feature and bug parity with the existing Felix DSA driver, and thus USXGMII, SGMII, QSGMII and 2500Base-X (only w/o in-band AN) are supported by the Lynx PCS module since these were also supported by Felix. The module can only be enabled by the drivers in need and not user selectable. Signed-off-by: Ioana Ciornei Signed-off-by: David S. Miller --- include/linux/pcs-lynx.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/pcs-lynx.h (limited to 'include') diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h new file mode 100644 index 000000000000..a6440d6ebe95 --- /dev/null +++ b/include/linux/pcs-lynx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2020 NXP + * Lynx PCS helpers + */ + +#ifndef __LINUX_PCS_LYNX_H +#define __LINUX_PCS_LYNX_H + +#include +#include + +struct lynx_pcs { + struct phylink_pcs pcs; + struct mdio_device *mdio; +}; + +struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio); + +void lynx_pcs_destroy(struct lynx_pcs *pcs); + +#endif /* __LINUX_PCS_LYNX_H */ -- cgit v1.2.3 From 3f7d820bad6cace3ecb859bf3fa5bc56fe8bb1c6 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 31 Aug 2020 02:26:10 -0400 Subject: net: ipv6: remove unused arg exact_dif in compute_score The arg exact_dif is not used anymore, remove it. inet6_exact_dif_match() is no longer needed after the above is removed, remove it too. Signed-off-by: Miaohe Lin Signed-off-by: David S. Miller --- include/linux/ipv6.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index bac8f4fffbd6..dda61d150a13 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -177,17 +177,6 @@ static inline int inet6_sdif(const struct sk_buff *skb) return 0; } -/* can not be used in TCP layer after tcp_v6_fill_cb */ -static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if defined(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) - return true; -#endif - return false; -} - struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; -- cgit v1.2.3 From 34e1ec319e99322bfed02767d51f4998a961d205 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 31 Aug 2020 02:26:34 -0400 Subject: net: ipv4: remove unused arg exact_dif in compute_score The arg exact_dif is not used anymore, remove it. inet_exact_dif_match() is no longer needed after the above is removed, so remove it too. Signed-off-by: Miaohe Lin Signed-off-by: David S. Miller --- include/net/tcp.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index eab6c7510b5b..0d11db6436c8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -941,16 +941,6 @@ INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); #endif -static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) - return true; -#endif - return false; -} - /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { -- cgit v1.2.3 From 144b0a0e608690d46e9a77819249bdd8d23bdcb6 Mon Sep 17 00:00:00 2001 From: Yaroslav Bolyukin Date: Sat, 29 Aug 2020 18:59:53 +0500 Subject: ipvs: remove dependency on ip6_tables This dependency was added because ipv6_find_hdr was in iptables specific code but is no longer required Fixes: f8f626754ebe ("ipv6: Move ipv6_find_hdr() out of Netfilter code.") Fixes: 63dca2c0b0e7 ("ipvs: Fix faulty IPv6 extension header handling in IPVS") Signed-off-by: Yaroslav Bolyukin Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9a59a33787cb..d609e957a3ec 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,9 +25,6 @@ #include #include /* for struct ipv6hdr */ #include -#if IS_ENABLED(CONFIG_IP_VS_IPV6) -#include -#endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif -- cgit v1.2.3 From 4b4659128e634ce65dc02acf297d623f5bc97497 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Wed, 26 Aug 2020 14:24:45 -0400 Subject: drm/i915/dp: Extract drm_dp_read_mst_cap() Just a tiny drive-by cleanup, we can consolidate i915's code for checking for MST support into a helper to be shared across drivers. v5: * Drop !!() * Move drm_dp_has_mst() out of header * Change name from drm_dp_has_mst() to drm_dp_read_mst_cap() Signed-off-by: Lyude Paul Reviewed-by: Sean Paul Reviewed-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-10-lyude@redhat.com --- include/drm/drm_dp_mst_helper.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index 8b9eb4db3381..6ae5860d8644 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -728,10 +728,9 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr); - +bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]); int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state); - int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled); -- cgit v1.2.3 From 3d3721ccb18a3dcec874c44120e2df7ec1c1db99 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Wed, 26 Aug 2020 14:24:49 -0400 Subject: drm/i915/dp: Extract drm_dp_read_downstream_info() We're going to be doing the same probing process in nouveau for determining downstream DP port capabilities, so let's deduplicate the work by moving i915's code for handling this into a shared helper: drm_dp_read_downstream_info(). Note that when we do this, we also do make some functional changes while we're at it: * We always clear the downstream port info before trying to read it, just to make things easier for the caller * We skip reading downstream port info if the DPCD indicates that we don't support downstream port info * We only read as many bytes as needed for the reported number of downstream ports, no sense in reading the whole thing every time v2: * Fixup logic for calculating the downstream port length to account for the fact that downstream port caps can be either 1 byte or 4 bytes long. We can actually skip fixing the max_clock/max_bpc helpers here since they all check for DP_DETAILED_CAP_INFO_AVAILABLE anyway. * Fix ret code check for drm_dp_dpcd_read v5: * Change name from drm_dp_downstream_read_info() to drm_dp_read_downstream_info() * Also, add "See Also" sections for the various downstream info functions (drm_dp_read_downstream_info(), drm_dp_downstream_max_clock(), drm_dp_downstream_max_bpc()) Reviewed-by: Sean Paul Signed-off-by: Lyude Paul Reviewed-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-14-lyude@redhat.com --- include/drm/drm_dp_helper.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 5c2819924862..b8716b200666 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1613,6 +1613,9 @@ int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, u8 real_edid_checksum); +int drm_dp_read_downstream_info(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]); int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4]); int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], -- cgit v1.2.3 From 693c3ec5976eb4b66cbd4f3f1c701a6f0ae1c9b9 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Wed, 26 Aug 2020 14:24:51 -0400 Subject: drm/i915/dp: Extract drm_dp_read_sink_count_cap() Since other drivers are also going to need to be aware of the sink count in order to do proper dongle detection, we might as well steal i915's DP_SINK_COUNT helpers and move them into DRM helpers so that other dirvers can use them as well. Note that this also starts using intel_dp_has_sink_count() in intel_dp_detect_dpcd(), which is a functional change. v5: * Change name from drm_dp_has_sink_count() to drm_dp_read_sink_count_cap() Signed-off-by: Lyude Paul Reviewed-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-16-lyude@redhat.com --- include/drm/drm_dp_helper.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index b8716b200666..4c56ce4dc54f 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1631,6 +1631,11 @@ void drm_dp_set_subconnector_property(struct drm_connector *connector, const u8 *dpcd, const u8 port_cap[4]); +struct drm_dp_desc; +bool drm_dp_read_sink_count_cap(struct drm_connector *connector, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const struct drm_dp_desc *desc); + void drm_dp_remote_aux_init(struct drm_dp_aux *aux); void drm_dp_aux_init(struct drm_dp_aux *aux); int drm_dp_aux_register(struct drm_dp_aux *aux); @@ -1689,7 +1694,8 @@ enum drm_dp_quirk { * @DP_DPCD_QUIRK_NO_SINK_COUNT: * * The device does not set SINK_COUNT to a non-zero value. - * The driver should ignore SINK_COUNT during detection. + * The driver should ignore SINK_COUNT during detection. Note that + * drm_dp_read_sink_count_cap() automatically checks for this quirk. */ DP_DPCD_QUIRK_NO_SINK_COUNT, /** -- cgit v1.2.3 From 4778ff052812029bc076f5e78eff3ba1851cbea7 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Wed, 26 Aug 2020 14:24:52 -0400 Subject: drm/i915/dp: Extract drm_dp_read_sink_count() And of course, we'll also need to read the sink count from other drivers as well if we're checking whether or not it's supported. So, let's extract the code for this into another helper. v2: * Fix drm_dp_dpcd_readb() ret check * Add back comment and move back sink_count assignment in intel_dp_get_dpcd() v5: * Change name from drm_dp_get_sink_count() to drm_dp_read_sink_count() * Also, add "See also:" section to kdocs Signed-off-by: Lyude Paul Reviewed-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-17-lyude@redhat.com --- include/drm/drm_dp_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 4c56ce4dc54f..bc5cb8c503fb 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1635,6 +1635,7 @@ struct drm_dp_desc; bool drm_dp_read_sink_count_cap(struct drm_connector *connector, const u8 dpcd[DP_RECEIVER_CAP_SIZE], const struct drm_dp_desc *desc); +int drm_dp_read_sink_count(struct drm_dp_aux *aux); void drm_dp_remote_aux_init(struct drm_dp_aux *aux); void drm_dp_aux_init(struct drm_dp_aux *aux); -- cgit v1.2.3 From b9936121d95b0127d34fa6c25678994582d1b17c Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Wed, 26 Aug 2020 14:24:55 -0400 Subject: drm/i915/dp: Extract drm_dp_read_dpcd_caps() Since DP 1.3, it's been possible for DP receivers to specify an additional set of DPCD capabilities, which can take precedence over the capabilities reported at DP_DPCD_REV. Basically any device supporting DP is going to need to read these in an identical manner, in particular nouveau, so let's go ahead and just move this code out of i915 into a shared DRM DP helper that we can use in other drivers. v2: * Remove redundant dpcd[DP_DPCD_REV] == 0 check * Fix drm_dp_dpcd_read() ret checks Signed-off-by: Lyude Paul Reviewed-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-20-lyude@redhat.com --- include/drm/drm_dp_helper.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index bc5cb8c503fb..85513eeb2196 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1607,6 +1607,9 @@ static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux, return drm_dp_dpcd_write(aux, offset, &value, 1); } +int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux, + u8 dpcd[DP_RECEIVER_CAP_SIZE]); + int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, u8 status[DP_LINK_STATUS_SIZE]); -- cgit v1.2.3 From b7176c261cdbced87bed9562577333150ed05b01 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Mon, 24 Aug 2020 11:03:07 +1200 Subject: dma-contiguous: provide the ability to reserve per-numa CMA Right now, drivers like ARM SMMU are using dma_alloc_coherent() to get coherent DMA buffers to save their command queues and page tables. As there is only one default CMA in the whole system, SMMUs on nodes other than node0 will get remote memory. This leads to significant latency. This patch provides per-numa CMA so that drivers like SMMU can get local memory. Tests show localizing CMA can decrease dma_unmap latency much. For instance, before this patch, SMMU on node2 has to wait for more than 560ns for the completion of CMD_SYNC in an empty command queue; with this patch, it needs 240ns only. A positive side effect of this patch would be improving performance even further for those users who are worried about performance more than DMA security and use iommu.passthrough=1 to skip IOMMU. With local CMA, all drivers can get local coherent DMA buffers. Also, this patch changes the default CONFIG_CMA_AREAS to 19 in NUMA. As 1+CONFIG_CMA_AREAS should be quite enough for most servers on the market even they enable both hugetlb_cma and pernuma_cma. 2 numa nodes: 2(hugetlb) + 2(pernuma) + 1(default global cma) = 5 4 numa nodes: 4(hugetlb) + 4(pernuma) + 1(default global cma) = 9 8 numa nodes: 8(hugetlb) + 8(pernuma) + 1(default global cma) = 17 Signed-off-by: Barry Song Signed-off-by: Christoph Hellwig --- include/linux/dma-contiguous.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 03f8e98e3bcc..fe55e004f1f4 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -171,6 +171,12 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page, #endif +#ifdef CONFIG_DMA_PERNUMA_CMA +void dma_pernuma_cma_reserve(void); +#else +static inline void dma_pernuma_cma_reserve(void) { } +#endif + #endif #endif -- cgit v1.2.3 From 2281f797f5524abb8fff66bf8540b4f4687332a2 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Mon, 24 Aug 2020 11:03:09 +1200 Subject: mm: cma: use CMA_MAX_NAME to define the length of cma name array CMA_MAX_NAME should be visible to CMA's users as they might need it to set the name of CMA areas and avoid hardcoding the size locally. So this patch moves CMA_MAX_NAME from local header file to include/linux header file and removes the hardcode in both hugetlb.c and contiguous.c. Signed-off-by: Barry Song Signed-off-by: Christoph Hellwig --- include/linux/cma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cma.h b/include/linux/cma.h index 6ff79fefd01f..217999c8a762 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -18,6 +18,8 @@ #endif +#define CMA_MAX_NAME 64 + struct cma; extern unsigned long totalcma_pages; -- cgit v1.2.3 From 1f0882214fd0037b74f245d9be75c31516fed040 Mon Sep 17 00:00:00 2001 From: Sean Paul Date: Tue, 18 Aug 2020 11:38:49 -0400 Subject: drm/i915: Fix sha_text population code This patch fixes a few bugs: 1- We weren't taking into account sha_leftovers when adding multiple ksvs to sha_text. As such, we were or'ing the end of ksv[j - 1] with the beginning of ksv[j] 2- In the sha_leftovers == 2 and sha_leftovers == 3 case, bstatus was being placed on the wrong half of sha_text, overlapping the leftover ksv value 3- In the sha_leftovers == 2 case, we need to manually terminate the byte stream with 0x80 since the hardware doesn't have enough room to add it after writing M0 The upside is that all of the HDCP supported HDMI repeaters I could find on Amazon just strip HDCP anyways, so it turns out to be _really_ hard to hit any of these cases without an MST hub, which is not (yet) supported. Oh, and the sha_leftovers == 1 case works perfectly! Fixes: ee5e5e7a5e0f ("drm/i915: Add HDCP framework + base implementation") Cc: Chris Wilson Cc: Ramalingam C Cc: Daniel Vetter Cc: Sean Paul Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: intel-gfx@lists.freedesktop.org Cc: # v4.17+ Reviewed-by: Ramalingam C Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20191203173638.94919-2-sean@poorly.run #v1 Link: https://patchwork.freedesktop.org/patch/msgid/20191212190230.188505-2-sean@poorly.run #v2 Link: https://patchwork.freedesktop.org/patch/msgid/20200117193103.156821-2-sean@poorly.run #v3 Link: https://patchwork.freedesktop.org/patch/msgid/20200218220242.107265-2-sean@poorly.run #v4 Link: https://patchwork.freedesktop.org/patch/msgid/20200305201236.152307-2-sean@poorly.run #v5 Link: https://patchwork.freedesktop.org/patch/msgid/20200429195502.39919-2-sean@poorly.run #v6 Link: https://patchwork.freedesktop.org/patch/msgid/20200623155907.22961-2-sean@poorly.run #v7 Changes in v2: -None Changes in v3: -None Changes in v4: -Rebased on intel_de_write changes Changes in v5: -None Changes in v6: -None Changes in v7: -None Changes in v8: -None Signed-off-by: Ramalingam C Link: https://patchwork.freedesktop.org/patch/msgid/20200818153910.27894-2-sean@poorly.run --- include/drm/drm_hdcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h index c6bab4986a65..fe58dbb46962 100644 --- a/include/drm/drm_hdcp.h +++ b/include/drm/drm_hdcp.h @@ -29,6 +29,9 @@ /* Slave address for the HDCP registers in the receiver */ #define DRM_HDCP_DDC_ADDR 0x3A +/* Value to use at the end of the SHA-1 bytestream used for repeaters */ +#define DRM_HDCP_SHA1_TERMINATOR 0x80 + /* HDCP register offsets for HDMI/DVI devices */ #define DRM_HDCP_DDC_BKSV 0x00 #define DRM_HDCP_DDC_RI_PRIME 0x08 -- cgit v1.2.3 From e38c298fcd19149d337f91640f037a9265bd8c3f Mon Sep 17 00:00:00 2001 From: Sean Paul Date: Wed, 19 Aug 2020 10:31:24 -0400 Subject: drm/mst: Add support for QUERY_STREAM_ENCRYPTION_STATUS MST sideband message Used to query whether an MST stream is encrypted or not. Cc: Lyude Paul Reviewed-by: Anshuman Gupta Reviewed-by: Lyude Paul Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200218220242.107265-14-sean@poorly.run #v4 Link: https://patchwork.freedesktop.org/patch/msgid/20200305201236.152307-15-sean@poorly.run #v5 Link: https://patchwork.freedesktop.org/patch/msgid/20200429195502.39919-15-sean@poorly.run #v6 Link: https://patchwork.freedesktop.org/patch/msgid/20200623155907.22961-16-sean@poorly.run #v7 Link: https://patchwork.freedesktop.org/patch/msgid/20200818153910.27894-16-sean@poorly.run #v8 Changes in v4: -Added to the set Changes in v5: -None Changes in v6: -Use FIELD_PREP to generate request buffer bitfields (Lyude) -Add mst selftest and dump/decode_sideband_req for QSES (Lyude) Changes in v7: -None Changes in v8: -Reverse the parsing on the hdcp_*x_device_present bits and leave breadcrumb in case this is incorrect (Anshuman) Changes in v8.5: -s/DRM_DEBUG_KMS/drm_dbg_kms/ (Lyude) Signed-off-by: Ramalingam C Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200819143133.46232-1-sean@poorly.run --- include/drm/drm_dp_helper.h | 3 +++ include/drm/drm_dp_mst_helper.h | 44 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index e47dc22ebf50..e2d2df5e869e 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1108,6 +1108,9 @@ #define DP_POWER_DOWN_PHY 0x25 #define DP_SINK_EVENT_NOTIFY 0x30 #define DP_QUERY_STREAM_ENC_STATUS 0x38 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST 0 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE 1 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE 2 /* DP 1.2 MST sideband reply types */ #define DP_SIDEBAND_REPLY_ACK 0x00 diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index 8b9eb4db3381..371eef8798ad 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -313,6 +313,34 @@ struct drm_dp_remote_i2c_write_ack_reply { u8 port_number; }; +struct drm_dp_query_stream_enc_status_ack_reply { + /* Bit[23:16]- Stream Id */ + u8 stream_id; + + /* Bit[15]- Signed */ + bool reply_signed; + + /* Bit[10:8]- Stream Output Sink Type */ + bool unauthorizable_device_present; + bool legacy_device_present; + bool query_capable_device_present; + + /* Bit[12:11]- Stream Output CP Type */ + bool hdcp_1x_device_present; + bool hdcp_2x_device_present; + + /* Bit[4]- Stream Authentication */ + bool auth_completed; + + /* Bit[3]- Stream Encryption */ + bool encryption_enabled; + + /* Bit[2]- Stream Repeater Function Present */ + bool repeater_present; + + /* Bit[1:0]- Stream State */ + u8 state; +}; #define DRM_DP_MAX_SDP_STREAMS 16 struct drm_dp_allocate_payload { @@ -374,6 +402,15 @@ struct drm_dp_remote_i2c_write { u8 *bytes; }; +struct drm_dp_query_stream_enc_status { + u8 stream_id; + u8 client_id[7]; /* 56-bit nonce */ + u8 stream_event; + bool valid_stream_event; + u8 stream_behavior; + u8 valid_stream_behavior; +}; + /* this covers ENUM_RESOURCES, POWER_DOWN_PHY, POWER_UP_PHY */ struct drm_dp_port_number_req { u8 port_number; @@ -422,6 +459,8 @@ struct drm_dp_sideband_msg_req_body { struct drm_dp_remote_i2c_read i2c_read; struct drm_dp_remote_i2c_write i2c_write; + + struct drm_dp_query_stream_enc_status enc_status; } u; }; @@ -444,6 +483,8 @@ struct drm_dp_sideband_msg_reply_body { struct drm_dp_remote_i2c_read_ack_reply remote_i2c_read_ack; struct drm_dp_remote_i2c_read_nak_reply remote_i2c_read_nack; struct drm_dp_remote_i2c_write_ack_reply remote_i2c_write_ack; + + struct drm_dp_query_stream_enc_status_ack_reply enc_status; } u; }; @@ -808,6 +849,9 @@ drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, struct drm_dp_mst_port *port); int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, bool power_up); +int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, + struct drm_dp_query_stream_enc_status_ack_reply *status); int __must_check drm_dp_mst_atomic_check(struct drm_atomic_state *state); void drm_dp_mst_get_port_malloc(struct drm_dp_mst_port *port); -- cgit v1.2.3 From 03c2b85cb7f13e9bd82cbe4201ede52177d433f5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 21 Aug 2020 12:42:42 -0700 Subject: vmlinux.lds.h: Create COMMON_DISCARDS Collect the common DISCARD sections for architectures that need more specialized discard control than what the standard DISCARDS section provides. Signed-off-by: Kees Cook Signed-off-by: Ingo Molnar Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/r/20200821194310.3089815-2-keescook@chromium.org --- include/asm-generic/vmlinux.lds.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 7616ff0b96ec..184b23d62784 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -954,13 +954,16 @@ EXIT_DATA #endif +#define COMMON_DISCARDS \ + *(.discard) \ + *(.discard.*) \ + *(.modinfo) + #define DISCARDS \ /DISCARD/ : { \ EXIT_DISCARDS \ EXIT_CALL \ - *(.discard) \ - *(.discard.*) \ - *(.modinfo) \ + COMMON_DISCARDS \ } /** -- cgit v1.2.3 From dfbe69689b4dee19021d8c315a5137b4790b5634 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 21 Aug 2020 12:42:43 -0700 Subject: vmlinux.lds.h: Add .gnu.version* to COMMON_DISCARDS For vmlinux linking, no architecture uses the .gnu.version* sections, so remove it via the COMMON_DISCARDS macro in preparation for adding --orphan-handling=warn more widely. This is a work-around for what appears to be a bug[1] in ld.bfd which warns for this synthetic section even when none is found in input objects, and even when no section is emitted for an output object[2]. [1] https://sourceware.org/bugzilla/show_bug.cgi?id=26153 [2] https://lore.kernel.org/lkml/202006221524.CEB86E036B@keescook/ Signed-off-by: Kees Cook Signed-off-by: Ingo Molnar Reviewed-by: Fangrui Song Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/r/20200821194310.3089815-3-keescook@chromium.org --- include/asm-generic/vmlinux.lds.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 184b23d62784..f1f02a2f71b7 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -957,7 +957,9 @@ #define COMMON_DISCARDS \ *(.discard) \ *(.discard.*) \ - *(.modinfo) + *(.modinfo) \ + /* ld.bfd warns about .gnu.version* even when not emitted */ \ + *(.gnu.version*) \ #define DISCARDS \ /DISCARD/ : { \ -- cgit v1.2.3 From d812db78288d76d1e8c6df3a840c41a8875f6468 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 21 Aug 2020 12:42:44 -0700 Subject: vmlinux.lds.h: Avoid KASAN and KCSAN's unwanted sections KASAN (-fsanitize=kernel-address) and KCSAN (-fsanitize=thread) produce unwanted[1] .eh_frame and .init_array.* sections. Add them to COMMON_DISCARDS, except with CONFIG_CONSTRUCTORS, which wants to keep .init_array.* sections. [1] https://bugs.llvm.org/show_bug.cgi?id=46478 Signed-off-by: Kees Cook Signed-off-by: Ingo Molnar Tested-by: Marco Elver Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/r/20200821194310.3089815-4-keescook@chromium.org --- include/asm-generic/vmlinux.lds.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index f1f02a2f71b7..6b89a03e636e 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -954,7 +954,27 @@ EXIT_DATA #endif +/* + * Clang's -fsanitize=kernel-address and -fsanitize=thread produce + * unwanted sections (.eh_frame and .init_array.*), but + * CONFIG_CONSTRUCTORS wants to keep any .init_array.* sections. + * https://bugs.llvm.org/show_bug.cgi?id=46478 + */ +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) +# ifdef CONFIG_CONSTRUCTORS +# define SANITIZER_DISCARDS \ + *(.eh_frame) +# else +# define SANITIZER_DISCARDS \ + *(.init_array) *(.init_array.*) \ + *(.eh_frame) +# endif +#else +# define SANITIZER_DISCARDS +#endif + #define COMMON_DISCARDS \ + SANITIZER_DISCARDS \ *(.discard) \ *(.discard.*) \ *(.modinfo) \ -- cgit v1.2.3 From c604abc3f6e3030f3a3022b184ed7d3780c34d30 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 21 Aug 2020 12:42:45 -0700 Subject: vmlinux.lds.h: Split ELF_DETAILS from STABS_DEBUG The .comment section doesn't belong in STABS_DEBUG. Split it out into a new macro named ELF_DETAILS. This will gain other non-debug sections that need to be accounted for when linking with --orphan-handling=warn. Signed-off-by: Kees Cook Signed-off-by: Ingo Molnar Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/r/20200821194310.3089815-5-keescook@chromium.org --- include/asm-generic/vmlinux.lds.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6b89a03e636e..cadcbc3cdabd 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -34,6 +34,7 @@ * * STABS_DEBUG * DWARF_DEBUG + * ELF_DETAILS * * DISCARDS // must be the last * } @@ -811,14 +812,17 @@ .debug_macro 0 : { *(.debug_macro) } \ .debug_addr 0 : { *(.debug_addr) } - /* Stabs debugging sections. */ +/* Stabs debugging sections. */ #define STABS_DEBUG \ .stab 0 : { *(.stab) } \ .stabstr 0 : { *(.stabstr) } \ .stab.excl 0 : { *(.stab.excl) } \ .stab.exclstr 0 : { *(.stab.exclstr) } \ .stab.index 0 : { *(.stab.index) } \ - .stab.indexstr 0 : { *(.stab.indexstr) } \ + .stab.indexstr 0 : { *(.stab.indexstr) } + +/* Required sections not related to debugging. */ +#define ELF_DETAILS \ .comment 0 : { *(.comment) } #ifdef CONFIG_GENERIC_BUG -- cgit v1.2.3 From a840c4de569f610bc5ee043b613c35b779d23186 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 21 Aug 2020 12:42:46 -0700 Subject: vmlinux.lds.h: Add .symtab, .strtab, and .shstrtab to ELF_DETAILS When linking vmlinux with LLD, the synthetic sections .symtab, .strtab, and .shstrtab are listed as orphaned. Add them to the ELF_DETAILS section so there will be no warnings when --orphan-handling=warn is used more widely. (They are added above comment as it is the more common order[1].) ld.lld: warning: :(.symtab) is being placed in '.symtab' ld.lld: warning: :(.shstrtab) is being placed in '.shstrtab' ld.lld: warning: :(.strtab) is being placed in '.strtab' [1] https://lore.kernel.org/lkml/20200622224928.o2a7jkq33guxfci4@google.com/ Reported-by: Fangrui Song Signed-off-by: Kees Cook Signed-off-by: Ingo Molnar Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/r/20200821194310.3089815-6-keescook@chromium.org --- include/asm-generic/vmlinux.lds.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index cadcbc3cdabd..98d013dcc11a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -823,7 +823,10 @@ /* Required sections not related to debugging. */ #define ELF_DETAILS \ - .comment 0 : { *(.comment) } + .comment 0 : { *(.comment) } \ + .symtab 0 : { *(.symtab) } \ + .strtab 0 : { *(.strtab) } \ + .shstrtab 0 : { *(.shstrtab) } #ifdef CONFIG_GENERIC_BUG #define BUG_TABLE \ -- cgit v1.2.3 From eff8728fe69880d3f7983bec3fb6cea4c306261f Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 21 Aug 2020 12:42:47 -0700 Subject: vmlinux.lds.h: Add PGO and AutoFDO input sections MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Basically, consider .text.{hot|unlikely|unknown}.* part of .text, too. When compiling with profiling information (collected via PGO instrumentations or AutoFDO sampling), Clang will separate code into .text.hot, .text.unlikely, or .text.unknown sections based on profiling information. After D79600 (clang-11), these sections will have a trailing `.` suffix, ie. .text.hot., .text.unlikely., .text.unknown.. When using -ffunction-sections together with profiling infomation, either explicitly (FGKASLR) or implicitly (LTO), code may be placed in sections following the convention: .text.hot., .text.unlikely., .text.unknown. where , , and are functions. (This produces one section per function; we generally try to merge these all back via linker script so that we don't have 50k sections). For the above cases, we need to teach our linker scripts that such sections might exist and that we'd explicitly like them grouped together, otherwise we can wind up with code outside of the _stext/_etext boundaries that might not be mapped properly for some architectures, resulting in boot failures. If the linker script is not told about possible input sections, then where the section is placed as output is a heuristic-laiden mess that's non-portable between linkers (ie. BFD and LLD), and has resulted in many hard to debug bugs. Kees Cook is working on cleaning this up by adding --orphan-handling=warn linker flag used in ARCH=powerpc to additional architectures. In the case of linker scripts, borrowing from the Zen of Python: explicit is better than implicit. Also, ld.bfd's internal linker script considers .text.hot AND .text.hot.* to be part of .text, as well as .text.unlikely and .text.unlikely.*. I didn't see support for .text.unknown.*, and didn't see Clang producing such code in our kernel builds, but I see code in LLVM that can produce such section names if profiling information is missing. That may point to a larger issue with generating or collecting profiles, but I would much rather be safe and explicit than have to debug yet another issue related to orphan section placement. Reported-by: Jian Cai Suggested-by: Fāng-ruì Sòng Signed-off-by: Nick Desaulniers Signed-off-by: Kees Cook Signed-off-by: Ingo Molnar Tested-by: Luis Lozano Tested-by: Manoj Gupta Acked-by: Kees Cook Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commitdiff;h=add44f8d5c5c05e08b11e033127a744d61c26aee Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commitdiff;h=1de778ed23ce7492c523d5850c6c6dbb34152655 Link: https://reviews.llvm.org/D79600 Link: https://bugs.chromium.org/p/chromium/issues/detail?id=1084760 Link: https://lore.kernel.org/r/20200821194310.3089815-7-keescook@chromium.org Debugged-by: Luis Lozano --- include/asm-generic/vmlinux.lds.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 98d013dcc11a..91dcfb91ac45 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -581,7 +581,10 @@ */ #define TEXT_TEXT \ ALIGN_FUNCTION(); \ - *(.text.hot TEXT_MAIN .text.fixup .text.unlikely) \ + *(.text.hot .text.hot.*) \ + *(TEXT_MAIN .text.fixup) \ + *(.text.unlikely .text.unlikely.*) \ + *(.text.unknown .text.unknown.*) \ NOINSTR_TEXT \ *(.text..refcount) \ *(.ref.text) \ -- cgit v1.2.3 From 70d932985757fbe978024db313001218e9f8fe5c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 Aug 2020 15:57:36 +0200 Subject: notifier: Fix broken error handling pattern The current notifiers have the following error handling pattern all over the place: int err, nr; err = __foo_notifier_call_chain(&chain, val_up, v, -1, &nr); if (err & NOTIFIER_STOP_MASK) __foo_notifier_call_chain(&chain, val_down, v, nr-1, NULL) And aside from the endless repetition thereof, it is broken. Consider blocking notifiers; both calls take and drop the rwsem, this means that the notifier list can change in between the two calls, making @nr meaningless. Fix this by replacing all the __foo_notifier_call_chain() functions with foo_notifier_call_chain_robust() that embeds the above pattern, but ensures it is inside a single lock region. Note: I switched atomic_notifier_call_chain_robust() to use the spinlock, since RCU cannot provide the guarantee required for the recovery. Note: software_resume() error handling was broken afaict. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20200818135804.325626653@infradead.org --- include/linux/notifier.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 018947611483..2fb373a5c1ed 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -161,20 +161,19 @@ extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v); -extern int __atomic_notifier_call_chain(struct atomic_notifier_head *nh, - unsigned long val, void *v, int nr_to_call, int *nr_calls); extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v); -extern int __blocking_notifier_call_chain(struct blocking_notifier_head *nh, - unsigned long val, void *v, int nr_to_call, int *nr_calls); extern int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v); -extern int __raw_notifier_call_chain(struct raw_notifier_head *nh, - unsigned long val, void *v, int nr_to_call, int *nr_calls); extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); -extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh, - unsigned long val, void *v, int nr_to_call, int *nr_calls); + +extern int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh, + unsigned long val_up, unsigned long val_down, void *v); +extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, + unsigned long val_up, unsigned long val_down, void *v); +extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, + unsigned long val_up, unsigned long val_down, void *v); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ -- cgit v1.2.3 From 563a02b0c9704f69c0364befedd451f57fe88092 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 18 Aug 2020 15:57:40 +0200 Subject: compiler.h: Make __ADDRESSABLE() symbol truly unique The __ADDRESSABLE() macro uses the __LINE__ macro to create a temporary symbol which has a unique name. However, if the macro is used multiple times from within another macro, the line number will always be the same, resulting in duplicate symbols. Make the temporary symbols truly unique by using __UNIQUE_ID instead of __LINE__. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20200818135804.564436253@infradead.org --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6810d80acb0b..92ef163a7479 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -207,7 +207,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define __ADDRESSABLE(sym) \ static void * __section(.discard.addressable) __used \ - __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; + __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym; /** * offset_to_ptr - convert a relative memory offset to an absolute pointer -- cgit v1.2.3 From 115284d89a436e9b66da0c6c4f6efded806874b2 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 18 Aug 2020 15:57:41 +0200 Subject: static_call: Add basic static call infrastructure Static calls are a replacement for global function pointers. They use code patching to allow direct calls to be used instead of indirect calls. They give the flexibility of function pointers, but with improved performance. This is especially important for cases where retpolines would otherwise be used, as retpolines can significantly impact performance. The concept and code are an extension of previous work done by Ard Biesheuvel and Steven Rostedt: https://lkml.kernel.org/r/20181005081333.15018-1-ard.biesheuvel@linaro.org https://lkml.kernel.org/r/20181006015110.653946300@goodmis.org There are two implementations, depending on arch support: 1) out-of-line: patched trampolines (CONFIG_HAVE_STATIC_CALL) 2) basic function pointers For more details, see the comments in include/linux/static_call.h. [peterz: simplified interface] Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Steven Rostedt (VMware) Cc: Linus Torvalds Link: https://lore.kernel.org/r/20200818135804.623259796@infradead.org --- include/linux/static_call.h | 156 ++++++++++++++++++++++++++++++++++++++ include/linux/static_call_types.h | 15 ++++ 2 files changed, 171 insertions(+) create mode 100644 include/linux/static_call.h create mode 100644 include/linux/static_call_types.h (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h new file mode 100644 index 000000000000..d8892dff2e91 --- /dev/null +++ b/include/linux/static_call.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_STATIC_CALL_H +#define _LINUX_STATIC_CALL_H + +/* + * Static call support + * + * Static calls use code patching to hard-code function pointers into direct + * branch instructions. They give the flexibility of function pointers, but + * with improved performance. This is especially important for cases where + * retpolines would otherwise be used, as retpolines can significantly impact + * performance. + * + * + * API overview: + * + * DECLARE_STATIC_CALL(name, func); + * DEFINE_STATIC_CALL(name, func); + * static_call(name)(args...); + * static_call_update(name, func); + * + * Usage example: + * + * # Start with the following functions (with identical prototypes): + * int func_a(int arg1, int arg2); + * int func_b(int arg1, int arg2); + * + * # Define a 'my_name' reference, associated with func_a() by default + * DEFINE_STATIC_CALL(my_name, func_a); + * + * # Call func_a() + * static_call(my_name)(arg1, arg2); + * + * # Update 'my_name' to point to func_b() + * static_call_update(my_name, &func_b); + * + * # Call func_b() + * static_call(my_name)(arg1, arg2); + * + * + * Implementation details: + * + * This requires some arch-specific code (CONFIG_HAVE_STATIC_CALL). + * Otherwise basic indirect calls are used (with function pointers). + * + * Each static_call() site calls into a trampoline associated with the name. + * The trampoline has a direct branch to the default function. Updates to a + * name will modify the trampoline's branch destination. + * + * If the arch has CONFIG_HAVE_STATIC_CALL_INLINE, then the call sites + * themselves will be patched at runtime to call the functions directly, + * rather than calling through the trampoline. This requires objtool or a + * compiler plugin to detect all the static_call() sites and annotate them + * in the .static_call_sites section. + */ + +#include +#include +#include + +#ifdef CONFIG_HAVE_STATIC_CALL +#include + +/* + * Either @site or @tramp can be NULL. + */ +extern void arch_static_call_transform(void *site, void *tramp, void *func); + +#define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name) + +/* + * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from + * the symbol table so that objtool can reference it when it generates the + * .static_call_sites section. + */ +#define __static_call(name) \ +({ \ + __ADDRESSABLE(STATIC_CALL_KEY(name)); \ + &STATIC_CALL_TRAMP(name); \ +}) + +#else +#define STATIC_CALL_TRAMP_ADDR(name) NULL +#endif + + +#define DECLARE_STATIC_CALL(name, func) \ + extern struct static_call_key STATIC_CALL_KEY(name); \ + extern typeof(func) STATIC_CALL_TRAMP(name); + +#define static_call_update(name, func) \ +({ \ + BUILD_BUG_ON(!__same_type(*(func), STATIC_CALL_TRAMP(name))); \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), func); \ +}) + +#if defined(CONFIG_HAVE_STATIC_CALL) + +struct static_call_key { + void *func; +}; + +#define DEFINE_STATIC_CALL(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = _func, \ + }; \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) + +#define static_call(name) __static_call(name) + +static inline +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + cpus_read_lock(); + WRITE_ONCE(key->func, func); + arch_static_call_transform(NULL, tramp, func); + cpus_read_unlock(); +} + +#define EXPORT_STATIC_CALL(name) \ + EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ + EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)) + +#define EXPORT_STATIC_CALL_GPL(name) \ + EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name)); \ + EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name)) + +#else /* Generic implementation */ + +struct static_call_key { + void *func; +}; + +#define DEFINE_STATIC_CALL(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = _func, \ + } + +#define static_call(name) \ + ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) + +static inline +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + WRITE_ONCE(key->func, func); +} + +#define EXPORT_STATIC_CALL(name) EXPORT_SYMBOL(STATIC_CALL_KEY(name)) +#define EXPORT_STATIC_CALL_GPL(name) EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name)) + +#endif /* CONFIG_HAVE_STATIC_CALL */ + +#endif /* _LINUX_STATIC_CALL_H */ diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h new file mode 100644 index 000000000000..5ed249dc47d3 --- /dev/null +++ b/include/linux/static_call_types.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _STATIC_CALL_TYPES_H +#define _STATIC_CALL_TYPES_H + +#include + +#define STATIC_CALL_KEY_PREFIX __SCK__ +#define STATIC_CALL_KEY(name) __PASTE(STATIC_CALL_KEY_PREFIX, name) + +#define STATIC_CALL_TRAMP_PREFIX __SCT__ +#define STATIC_CALL_TRAMP_PREFIX_STR __stringify(STATIC_CALL_TRAMP_PREFIX) +#define STATIC_CALL_TRAMP(name) __PASTE(STATIC_CALL_TRAMP_PREFIX, name) +#define STATIC_CALL_TRAMP_STR(name) __stringify(STATIC_CALL_TRAMP(name)) + +#endif /* _STATIC_CALL_TYPES_H */ -- cgit v1.2.3 From 9183c3f9ed710a8edf1a61e8a96d497258d26e08 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 18 Aug 2020 15:57:42 +0200 Subject: static_call: Add inline static call infrastructure Add infrastructure for an arch-specific CONFIG_HAVE_STATIC_CALL_INLINE option, which is a faster version of CONFIG_HAVE_STATIC_CALL. At runtime, the static call sites are patched directly, rather than using the out-of-line trampolines. Compared to out-of-line static calls, the performance benefits are more modest, but still measurable. Steven Rostedt did some tracepoint measurements: https://lkml.kernel.org/r/20181126155405.72b4f718@gandalf.local.home This code is heavily inspired by the jump label code (aka "static jumps"), as some of the concepts are very similar. For more details, see the comments in include/linux/static_call.h. [peterz: simplified interface; merged trampolines] Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Steven Rostedt (VMware) Cc: Linus Torvalds Link: https://lore.kernel.org/r/20200818135804.684334440@infradead.org --- include/asm-generic/vmlinux.lds.h | 7 +++++++ include/linux/module.h | 5 +++++ include/linux/static_call.h | 36 +++++++++++++++++++++++++++++++++++- include/linux/static_call_types.h | 13 +++++++++++++ 4 files changed, 60 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 5430febd34be..0088a5cd6a40 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -388,6 +388,12 @@ KEEP(*(__jump_table)) \ __stop___jump_table = .; +#define STATIC_CALL_DATA \ + . = ALIGN(8); \ + __start_static_call_sites = .; \ + KEEP(*(.static_call_sites)) \ + __stop_static_call_sites = .; + /* * Allow architectures to handle ro_after_init data on their * own by defining an empty RO_AFTER_INIT_DATA. @@ -398,6 +404,7 @@ __start_ro_after_init = .; \ *(.data..ro_after_init) \ JUMP_TABLE_DATA \ + STATIC_CALL_DATA \ __end_ro_after_init = .; #endif diff --git a/include/linux/module.h b/include/linux/module.h index e30ed5fa33a7..a29187f7c360 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -498,6 +499,10 @@ struct module { unsigned long *kprobe_blacklist; unsigned int num_kprobe_blacklist; #endif +#ifdef CONFIG_HAVE_STATIC_CALL_INLINE + int num_static_call_sites; + struct static_call_site *static_call_sites; +#endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ diff --git a/include/linux/static_call.h b/include/linux/static_call.h index d8892dff2e91..0d7f9efaa3b2 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -95,7 +95,41 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func); STATIC_CALL_TRAMP_ADDR(name), func); \ }) -#if defined(CONFIG_HAVE_STATIC_CALL) +#ifdef CONFIG_HAVE_STATIC_CALL_INLINE + +struct static_call_mod { + struct static_call_mod *next; + struct module *mod; /* for vmlinux, mod == NULL */ + struct static_call_site *sites; +}; + +struct static_call_key { + void *func; + struct static_call_mod *mods; +}; + +extern void __static_call_update(struct static_call_key *key, void *tramp, void *func); +extern int static_call_mod_init(struct module *mod); + +#define DEFINE_STATIC_CALL(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = _func, \ + .mods = NULL, \ + }; \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) + +#define static_call(name) __static_call(name) + +#define EXPORT_STATIC_CALL(name) \ + EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ + EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)) + +#define EXPORT_STATIC_CALL_GPL(name) \ + EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name)); \ + EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name)) + +#elif defined(CONFIG_HAVE_STATIC_CALL) struct static_call_key { void *func; diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index 5ed249dc47d3..408d345d83e1 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -2,14 +2,27 @@ #ifndef _STATIC_CALL_TYPES_H #define _STATIC_CALL_TYPES_H +#include #include #define STATIC_CALL_KEY_PREFIX __SCK__ +#define STATIC_CALL_KEY_PREFIX_STR __stringify(STATIC_CALL_KEY_PREFIX) +#define STATIC_CALL_KEY_PREFIX_LEN (sizeof(STATIC_CALL_KEY_PREFIX_STR) - 1) #define STATIC_CALL_KEY(name) __PASTE(STATIC_CALL_KEY_PREFIX, name) #define STATIC_CALL_TRAMP_PREFIX __SCT__ #define STATIC_CALL_TRAMP_PREFIX_STR __stringify(STATIC_CALL_TRAMP_PREFIX) +#define STATIC_CALL_TRAMP_PREFIX_LEN (sizeof(STATIC_CALL_TRAMP_PREFIX_STR) - 1) #define STATIC_CALL_TRAMP(name) __PASTE(STATIC_CALL_TRAMP_PREFIX, name) #define STATIC_CALL_TRAMP_STR(name) __stringify(STATIC_CALL_TRAMP(name)) +/* + * The static call site table needs to be created by external tooling (objtool + * or a compiler plugin). + */ +struct static_call_site { + s32 addr; + s32 key; +}; + #endif /* _STATIC_CALL_TYPES_H */ -- cgit v1.2.3 From 6333e8f73b834f54e395a056e6002403f0862c51 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 Aug 2020 15:57:43 +0200 Subject: static_call: Avoid kprobes on inline static_call()s Similar to how we disallow kprobes on any other dynamic text (ftrace/jump_label) also disallow kprobes on inline static_call()s. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200818135804.744920586@infradead.org --- include/linux/static_call.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 0d7f9efaa3b2..6f62ceda7dd9 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -110,6 +110,7 @@ struct static_call_key { extern void __static_call_update(struct static_call_key *key, void *tramp, void *func); extern int static_call_mod_init(struct module *mod); +extern int static_call_text_reserved(void *start, void *end); #define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -153,6 +154,11 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) cpus_read_unlock(); } +static inline int static_call_text_reserved(void *start, void *end) +{ + return 0; +} + #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)) @@ -182,6 +188,11 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) WRITE_ONCE(key->func, func); } +static inline int static_call_text_reserved(void *start, void *end) +{ + return 0; +} + #define EXPORT_STATIC_CALL(name) EXPORT_SYMBOL(STATIC_CALL_KEY(name)) #define EXPORT_STATIC_CALL_GPL(name) EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name)) -- cgit v1.2.3 From 1e7e47883830aae5e8246a22ca2fc6883c61acdf Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 18 Aug 2020 15:57:45 +0200 Subject: x86/static_call: Add inline static call implementation for x86-64 Add the inline static call implementation for x86-64. The generated code is identical to the out-of-line case, except we move the trampoline into it's own section. Objtool uses the trampoline naming convention to detect all the call sites. It then annotates those call sites in the .static_call_sites section. During boot (and module init), the call sites are patched to call directly into the destination function. The temporary trampoline is then no longer used. [peterz: merged trampolines, put trampoline in section] Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Cc: Linus Torvalds Link: https://lore.kernel.org/r/20200818135804.864271425@infradead.org --- include/asm-generic/vmlinux.lds.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 0088a5cd6a40..0502087654d7 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -642,6 +642,12 @@ *(.softirqentry.text) \ __softirqentry_text_end = .; +#define STATIC_CALL_TEXT \ + ALIGN_FUNCTION(); \ + __static_call_text_start = .; \ + *(.static_call.text) \ + __static_call_text_end = .; + /* Section used for early init (in .S files) */ #define HEAD_TEXT KEEP(*(.head.text)) -- cgit v1.2.3 From 452cddbff74b6a15b9354505671011700fe03710 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 Aug 2020 15:57:48 +0200 Subject: static_call: Add static_call_cond() Extend the static_call infrastructure to optimize the following common pattern: if (func_ptr) func_ptr(args...) For the trampoline (which is in effect a tail-call), we patch the JMP.d32 into a RET, which then directly consumes the trampoline call. For the in-line sites we replace the CALL with a NOP5. NOTE: this is 'obviously' limited to functions with a 'void' return type. NOTE: DEFINE_STATIC_COND_CALL() only requires a typename, as opposed to a full function. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Cc: Linus Torvalds Link: https://lore.kernel.org/r/20200818135805.042977182@infradead.org --- include/linux/static_call.h | 86 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 6f62ceda7dd9..0f74581e0e2f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -16,7 +16,9 @@ * * DECLARE_STATIC_CALL(name, func); * DEFINE_STATIC_CALL(name, func); + * DEFINE_STATIC_CALL_NULL(name, typename); * static_call(name)(args...); + * static_call_cond(name)(args...); * static_call_update(name, func); * * Usage example: @@ -52,6 +54,43 @@ * rather than calling through the trampoline. This requires objtool or a * compiler plugin to detect all the static_call() sites and annotate them * in the .static_call_sites section. + * + * + * Notes on NULL function pointers: + * + * Static_call()s support NULL functions, with many of the caveats that + * regular function pointers have. + * + * Clearly calling a NULL function pointer is 'BAD', so too for + * static_call()s (although when HAVE_STATIC_CALL it might not be immediately + * fatal). A NULL static_call can be the result of: + * + * DECLARE_STATIC_CALL_NULL(my_static_call, void (*)(int)); + * + * which is equivalent to declaring a NULL function pointer with just a + * typename: + * + * void (*my_func_ptr)(int arg1) = NULL; + * + * or using static_call_update() with a NULL function. In both cases the + * HAVE_STATIC_CALL implementation will patch the trampoline with a RET + * instruction, instead of an immediate tail-call JMP. HAVE_STATIC_CALL_INLINE + * architectures can patch the trampoline call to a NOP. + * + * In all cases, any argument evaluation is unconditional. Unlike a regular + * conditional function pointer call: + * + * if (my_func_ptr) + * my_func_ptr(arg1) + * + * where the argument evaludation also depends on the pointer value. + * + * When calling a static_call that can be NULL, use: + * + * static_call_cond(name)(arg1); + * + * which will include the required value tests to avoid NULL-pointer + * dereferences. */ #include @@ -120,7 +159,16 @@ extern int static_call_text_reserved(void *start, void *end); }; \ ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) +#define DEFINE_STATIC_CALL_NULL(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = NULL, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) + #define static_call(name) __static_call(name) +#define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ @@ -143,7 +191,15 @@ struct static_call_key { }; \ ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) +#define DEFINE_STATIC_CALL_NULL(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = NULL, \ + }; \ + ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) + #define static_call(name) __static_call(name) +#define static_call_cond(name) (void)__static_call(name) static inline void __static_call_update(struct static_call_key *key, void *tramp, void *func) @@ -179,9 +235,39 @@ struct static_call_key { .func = _func, \ } +#define DEFINE_STATIC_CALL_NULL(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = NULL, \ + } + #define static_call(name) \ ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) +static inline void __static_call_nop(void) { } + +/* + * This horrific hack takes care of two things: + * + * - it ensures the compiler will only load the function pointer ONCE, + * which avoids a reload race. + * + * - it ensures the argument evaluation is unconditional, similar + * to the HAVE_STATIC_CALL variant. + * + * Sadly current GCC/Clang (10 for both) do not optimize this properly + * and will emit an indirect call for the NULL case :-( + */ +#define __static_call_cond(name) \ +({ \ + void *func = READ_ONCE(STATIC_CALL_KEY(name).func); \ + if (!func) \ + func = &__static_call_nop; \ + (typeof(STATIC_CALL_TRAMP(name))*)func; \ +}) + +#define static_call_cond(name) (void)__static_call_cond(name) + static inline void __static_call_update(struct static_call_key *key, void *tramp, void *func) { -- cgit v1.2.3 From 5b06fd3bb9cdce4f3e731c48eb5b74c4acc47997 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 Aug 2020 15:57:49 +0200 Subject: static_call: Handle tail-calls GCC can turn our static_call(name)(args...) into a tail call, in which case we get a JMP.d32 into the trampoline (which then does a further tail-call). Teach objtool to recognise and mark these in .static_call_sites and adjust the code patching to deal with this. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Cc: Linus Torvalds Link: https://lore.kernel.org/r/20200818135805.101186767@infradead.org --- include/linux/static_call.h | 4 ++-- include/linux/static_call_types.h | 7 +++++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 0f74581e0e2f..519bd666e096 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -103,7 +103,7 @@ /* * Either @site or @tramp can be NULL. */ -extern void arch_static_call_transform(void *site, void *tramp, void *func); +extern void arch_static_call_transform(void *site, void *tramp, void *func, bool tail); #define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name) @@ -206,7 +206,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) { cpus_read_lock(); WRITE_ONCE(key->func, func); - arch_static_call_transform(NULL, tramp, func); + arch_static_call_transform(NULL, tramp, func, false); cpus_read_unlock(); } diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index 408d345d83e1..89135bb35bf7 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -16,6 +16,13 @@ #define STATIC_CALL_TRAMP(name) __PASTE(STATIC_CALL_TRAMP_PREFIX, name) #define STATIC_CALL_TRAMP_STR(name) __stringify(STATIC_CALL_TRAMP(name)) +/* + * Flags in the low bits of static_call_site::key. + */ +#define STATIC_CALL_SITE_TAIL 1UL /* tail call */ +#define STATIC_CALL_SITE_INIT 2UL /* init section */ +#define STATIC_CALL_SITE_FLAGS 3UL + /* * The static call site table needs to be created by external tooling (objtool * or a compiler plugin). -- cgit v1.2.3 From a945c8345ec0decb2f1a7f19a8c5e60bcb1dd1eb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 Aug 2020 15:57:51 +0200 Subject: static_call: Allow early init In order to use static_call() to wire up x86_pmu, we need to initialize earlier, specifically before memory allocation works; copy some of the tricks from jump_label to enable this. Primarily we overload key->next to store a sites pointer when there are no modules, this avoids having to use kmalloc() to initialize the sites and allows us to run much earlier. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Steven Rostedt (VMware) Link: https://lore.kernel.org/r/20200818135805.220737930@infradead.org --- include/linux/static_call.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 519bd666e096..bfa2ba39be57 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -136,6 +136,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern void __init static_call_init(void); + struct static_call_mod { struct static_call_mod *next; struct module *mod; /* for vmlinux, mod == NULL */ @@ -144,7 +146,12 @@ struct static_call_mod { struct static_call_key { void *func; - struct static_call_mod *mods; + union { + /* bit 0: 0 = mods, 1 = sites */ + unsigned long type; + struct static_call_mod *mods; + struct static_call_site *sites; + }; }; extern void __static_call_update(struct static_call_key *key, void *tramp, void *func); @@ -155,7 +162,7 @@ extern int static_call_text_reserved(void *start, void *end); DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ .func = _func, \ - .mods = NULL, \ + .type = 1, \ }; \ ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) @@ -180,6 +187,8 @@ extern int static_call_text_reserved(void *start, void *end); #elif defined(CONFIG_HAVE_STATIC_CALL) +static inline void static_call_init(void) { } + struct static_call_key { void *func; }; @@ -225,6 +234,8 @@ static inline int static_call_text_reserved(void *start, void *end) #else /* Generic implementation */ +static inline void static_call_init(void) { } + struct static_call_key { void *func; }; -- cgit v1.2.3 From d25e37d89dd2f41d7acae0429039d2f0ae8b4a07 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 18 Aug 2020 15:57:52 +0200 Subject: tracepoint: Optimize using static_call() Currently the tracepoint site will iterate a vector and issue indirect calls to however many handlers are registered (ie. the vector is long). Using static_call() it is possible to optimize this for the common case of only having a single handler registered. In this case the static_call() can directly call this handler. Otherwise, if the vector is longer than 1, call a function that iterates the whole vector like the current code. [peterz: updated to new interface] Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Cc: Linus Torvalds Link: https://lore.kernel.org/r/20200818135805.279421092@infradead.org --- include/linux/tracepoint-defs.h | 5 +++ include/linux/tracepoint.h | 86 +++++++++++++++++++++++++++++------------ include/trace/define_trace.h | 14 +++---- 3 files changed, 73 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index b29950a19205..de97450cf190 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -11,6 +11,8 @@ #include #include +struct static_call_key; + struct trace_print_flags { unsigned long mask; const char *name; @@ -30,6 +32,9 @@ struct tracepoint_func { struct tracepoint { const char *name; /* Tracepoint name */ struct static_key key; + struct static_call_key *static_call_key; + void *static_call_tramp; + void *iterator; int (*regfunc)(void); void (*unregfunc)(void); struct tracepoint_func __rcu *funcs; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 598fec9f9dbf..3722a10fc46d 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -19,6 +19,7 @@ #include #include #include +#include struct module; struct tracepoint; @@ -92,7 +93,9 @@ extern int syscall_regfunc(void); extern void syscall_unregfunc(void); #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */ +#ifndef PARAMS #define PARAMS(args...) args +#endif #define TRACE_DEFINE_ENUM(x) #define TRACE_DEFINE_SIZEOF(x) @@ -148,6 +151,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #ifdef TRACEPOINTS_ENABLED +#ifdef CONFIG_HAVE_STATIC_CALL +#define __DO_TRACE_CALL(name) static_call(tp_func_##name) +#else +#define __DO_TRACE_CALL(name) __tracepoint_iter_##name +#endif /* CONFIG_HAVE_STATIC_CALL */ + /* * it_func[0] is never NULL because there is at least one element in the array * when the array itself is non NULL. @@ -157,12 +166,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * has a "void" prototype, then it is invalid to declare a function * as "(void *, void)". */ -#define __DO_TRACE(tp, proto, args, cond, rcuidle) \ +#define __DO_TRACE(name, proto, args, cond, rcuidle) \ do { \ struct tracepoint_func *it_func_ptr; \ - void *it_func; \ - void *__data; \ int __maybe_unused __idx = 0; \ + void *__data; \ \ if (!(cond)) \ return; \ @@ -182,14 +190,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) rcu_irq_enter_irqson(); \ } \ \ - it_func_ptr = rcu_dereference_raw((tp)->funcs); \ - \ + it_func_ptr = \ + rcu_dereference_raw((&__tracepoint_##name)->funcs); \ if (it_func_ptr) { \ - do { \ - it_func = (it_func_ptr)->func; \ - __data = (it_func_ptr)->data; \ - ((void(*)(proto))(it_func))(args); \ - } while ((++it_func_ptr)->func); \ + __data = (it_func_ptr)->data; \ + __DO_TRACE_CALL(name)(args); \ } \ \ if (rcuidle) { \ @@ -205,7 +210,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static inline void trace_##name##_rcuidle(proto) \ { \ if (static_key_false(&__tracepoint_##name.key)) \ - __DO_TRACE(&__tracepoint_##name, \ + __DO_TRACE(name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond), 1); \ @@ -227,11 +232,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * poking RCU a bit. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ + extern int __tracepoint_iter_##name(data_proto); \ + DECLARE_STATIC_CALL(tp_func_##name, __tracepoint_iter_##name); \ extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ if (static_key_false(&__tracepoint_##name.key)) \ - __DO_TRACE(&__tracepoint_##name, \ + __DO_TRACE(name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond), 0); \ @@ -277,21 +284,50 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * structures, so we create an array of pointers that will be used for iteration * on the tracepoints. */ -#define DEFINE_TRACE_FN(name, reg, unreg) \ - static const char __tpstrtab_##name[] \ - __section(__tracepoints_strings) = #name; \ - struct tracepoint __tracepoint_##name __used \ - __section(__tracepoints) = \ - { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\ - __TRACEPOINT_ENTRY(name); +#define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args) \ + static const char __tpstrtab_##_name[] \ + __section(__tracepoints_strings) = #_name; \ + extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name); \ + int __tracepoint_iter_##_name(void *__data, proto); \ + struct tracepoint __tracepoint_##_name __used \ + __section(__tracepoints) = { \ + .name = __tpstrtab_##_name, \ + .key = STATIC_KEY_INIT_FALSE, \ + .static_call_key = &STATIC_CALL_KEY(tp_func_##_name), \ + .static_call_tramp = STATIC_CALL_TRAMP_ADDR(tp_func_##_name), \ + .iterator = &__tracepoint_iter_##_name, \ + .regfunc = _reg, \ + .unregfunc = _unreg, \ + .funcs = NULL }; \ + __TRACEPOINT_ENTRY(_name); \ + int __tracepoint_iter_##_name(void *__data, proto) \ + { \ + struct tracepoint_func *it_func_ptr; \ + void *it_func; \ + \ + it_func_ptr = \ + rcu_dereference_raw((&__tracepoint_##_name)->funcs); \ + do { \ + it_func = (it_func_ptr)->func; \ + __data = (it_func_ptr)->data; \ + ((void(*)(void *, proto))(it_func))(__data, args); \ + } while ((++it_func_ptr)->func); \ + return 0; \ + } \ + DEFINE_STATIC_CALL(tp_func_##_name, __tracepoint_iter_##_name); -#define DEFINE_TRACE(name) \ - DEFINE_TRACE_FN(name, NULL, NULL); +#define DEFINE_TRACE(name, proto, args) \ + DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args)); #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \ - EXPORT_SYMBOL_GPL(__tracepoint_##name) + EXPORT_SYMBOL_GPL(__tracepoint_##name); \ + EXPORT_SYMBOL_GPL(__tracepoint_iter_##name); \ + EXPORT_STATIC_CALL_GPL(tp_func_##name) #define EXPORT_TRACEPOINT_SYMBOL(name) \ - EXPORT_SYMBOL(__tracepoint_##name) + EXPORT_SYMBOL(__tracepoint_##name); \ + EXPORT_SYMBOL(__tracepoint_iter_##name); \ + EXPORT_STATIC_CALL(tp_func_##name) + #else /* !TRACEPOINTS_ENABLED */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ @@ -320,8 +356,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) return false; \ } -#define DEFINE_TRACE_FN(name, reg, unreg) -#define DEFINE_TRACE(name) +#define DEFINE_TRACE_FN(name, reg, unreg, proto, args) +#define DEFINE_TRACE(name, proto, args) #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) #define EXPORT_TRACEPOINT_SYMBOL(name) diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index bd75f97867b9..00723935dcc7 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -25,7 +25,7 @@ #undef TRACE_EVENT #define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ - DEFINE_TRACE(name) + DEFINE_TRACE(name, PARAMS(proto), PARAMS(args)) #undef TRACE_EVENT_CONDITION #define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \ @@ -39,12 +39,12 @@ #undef TRACE_EVENT_FN #define TRACE_EVENT_FN(name, proto, args, tstruct, \ assign, print, reg, unreg) \ - DEFINE_TRACE_FN(name, reg, unreg) + DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args)) #undef TRACE_EVENT_FN_COND #define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct, \ assign, print, reg, unreg) \ - DEFINE_TRACE_FN(name, reg, unreg) + DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args)) #undef TRACE_EVENT_NOP #define TRACE_EVENT_NOP(name, proto, args, struct, assign, print) @@ -54,15 +54,15 @@ #undef DEFINE_EVENT #define DEFINE_EVENT(template, name, proto, args) \ - DEFINE_TRACE(name) + DEFINE_TRACE(name, PARAMS(proto), PARAMS(args)) #undef DEFINE_EVENT_FN #define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \ - DEFINE_TRACE_FN(name, reg, unreg) + DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args)) #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ - DEFINE_TRACE(name) + DEFINE_TRACE(name, PARAMS(proto), PARAMS(args)) #undef DEFINE_EVENT_CONDITION #define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \ @@ -70,7 +70,7 @@ #undef DECLARE_TRACE #define DECLARE_TRACE(name, proto, args) \ - DEFINE_TRACE(name) + DEFINE_TRACE(name, PARAMS(proto), PARAMS(args)) #undef TRACE_INCLUDE #undef __TRACE_INCLUDE -- cgit v1.2.3 From 0e09c4fa72f9837ea8d78cb40ab0b52ff3252ea2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 28 Apr 2020 20:19:39 +0300 Subject: drm: Nuke mode->private_flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The last two uses of mode->private_flags (in i915 and gma500) are now gone. So let's remove mode->private_flags entirely. v2: Drop the earlier int->u8 conversion CC: Sam Ravnborg Cc: Daniel Vetter Cc: Emil Velikov Reviewed-by: Sam Ravnborg Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200428171940.19552-16-ville.syrjala@linux.intel.com Reviewed-by: Emil Velikov --- include/drm/drm_modes.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index eee3c9de6c4f..7d686f9a29bf 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -349,16 +349,6 @@ struct drm_display_mode { */ u8 type; - /** - * @private_flags: - * - * Driver private flags. private_flags can only be used for mode - * objects passed to drivers in modeset operations. It shouldn't be used - * by atomic drivers since they can store any additional data by - * subclassing state structures. - */ - int private_flags; - /** * @head: * -- cgit v1.2.3 From 8445e2c54c257e92084a451a0f20d6a7f3f9fa34 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 28 Apr 2020 20:19:40 +0300 Subject: drm: Replace mode->export_head with a boolean MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to shrink drm_display_mode below the magic two cacheline mark in 64bit we need to shrink it by another 8 bytes. The easiest thing to eliminate is the 'export_head' list head which is only used during the getconnector ioctl to temporarly track which modes on the connector's mode list are to be exposed and which are to remain hidden. We can simply replace the list head with a boolean which we use to tag the modes that are to be exposed. If we make sure to clear the tags after we're done with them we don't even need an extra loop over the modes to reset the tags at the start of the getconnector ioctl. Conveniently we already have a hole for the boolean left behind by the removal of mode->private_flags. The final size of the struct is now 112 bytes on 32bit and 120 bytes on 64bit. Another alternative would be a temp bitmask so we wouldn't have to have anything in the mode struct itself. The main issue is how large of a bitmask do we need? I guess we could allocate it dynamically but that means an extra kcalloc() and an extra loop through the modes to count them first (or grow the bitmask with krealloc() as needed). CC: Sam Ravnborg Cc: Daniel Vetter Cc: Emil Velikov Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200428171940.19552-17-ville.syrjala@linux.intel.com Reviewed-by: Emil Velikov --- include/drm/drm_modes.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index 7d686f9a29bf..cdf2a299ccd4 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -350,24 +350,22 @@ struct drm_display_mode { u8 type; /** - * @head: + * @expose_to_userspace: * - * struct list_head for mode lists. + * Indicates whether the mode is to be exposed to the userspace. + * This is to maintain a set of exposed modes while preparing + * user-mode's list in drm_mode_getconnector ioctl. The purpose of + * this only lies in the ioctl function, and is not to be used + * outside the function. */ - struct list_head head; + bool expose_to_userspace; /** - * @export_head: + * @head: * - * struct list_head for modes to be exposed to the userspace. - * This is to maintain a list of exposed modes while preparing - * user-mode's list in drm_mode_getconnector ioctl. The purpose of this - * list_head only lies in the ioctl function, and is not expected to be - * used outside the function. - * Once used, the stale pointers are not reset, but left as it is, to - * avoid overhead of protecting it by mode_config.mutex. + * struct list_head for mode lists. */ - struct list_head export_head; + struct list_head head; /** * @name: -- cgit v1.2.3 From 5d0d7b9009feb3b411814b9c1b7dddabbb10a5fb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 18 Aug 2020 15:36:02 +0200 Subject: media: cec: no need to check return value of debugfs_create functions When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by: Greg Kroah-Hartman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index c48b5f2e4b50..cd35ae6b7560 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -248,8 +248,6 @@ struct cec_adapter { #endif struct dentry *cec_dir; - struct dentry *status_file; - struct dentry *error_inj_file; u32 sequence; -- cgit v1.2.3 From e000e1fa4bdbd783149e7f97cf3be61e1c0bab8c Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Tue, 25 Aug 2020 05:52:27 +0200 Subject: media: uapi: h264: Update reference lists When dealing with interlaced frames, reference lists must tell if each particular reference is meant for top or bottom field. This info is currently not provided at all in the H264 related controls. Change reference lists to hold a structure, which specifies an index into the DPB array and the field/frame specification for the picture. Currently the only user of these lists is Cedrus which is just compile fixed here. Actual usage of will come in a following commit. Signed-off-by: Jernej Skrabec Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 080fd1293c42..3c613b84e5ae 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -19,6 +19,8 @@ */ #define V4L2_H264_NUM_DPB_ENTRIES 16 +#define V4L2_H264_REF_LIST_LEN (2 * V4L2_H264_NUM_DPB_ENTRIES) + /* Our pixel format isn't stable at the moment */ #define V4L2_PIX_FMT_H264_SLICE v4l2_fourcc('S', '2', '6', '4') /* H264 parsed slices */ @@ -140,6 +142,17 @@ struct v4l2_h264_pred_weight_table { #define V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED 0x04 #define V4L2_H264_SLICE_FLAG_SP_FOR_SWITCH 0x08 +#define V4L2_H264_TOP_FIELD_REF 0x1 +#define V4L2_H264_BOTTOM_FIELD_REF 0x2 +#define V4L2_H264_FRAME_REF 0x3 + +struct v4l2_h264_reference { + __u8 fields; + + /* Index into v4l2_ctrl_h264_decode_params.dpb[] */ + __u8 index; +}; + struct v4l2_ctrl_h264_slice_params { /* Size in bytes, including header */ __u32 size; @@ -178,12 +191,8 @@ struct v4l2_ctrl_h264_slice_params { __u8 num_ref_idx_l1_active_minus1; __u32 slice_group_change_cycle; - /* - * Entries on each list are indices into - * v4l2_ctrl_h264_decode_params.dpb[]. - */ - __u8 ref_pic_list0[32]; - __u8 ref_pic_list1[32]; + struct v4l2_h264_reference ref_pic_list0[V4L2_H264_REF_LIST_LEN]; + struct v4l2_h264_reference ref_pic_list1[V4L2_H264_REF_LIST_LEN]; __u32 flags; }; -- cgit v1.2.3 From eb44c6c9c236b1568985816254faf520fde21776 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:29 +0200 Subject: media: uapi: h264: Split prediction weight parameters The prediction weight parameters are only required under certain conditions, which depend on slice header parameters. As specified in section 7.3.3 Slice header syntax, the prediction weight table is present if: ((weighted_pred_flag && (slice_type == P || slice_type == SP)) || \ (weighted_bipred_idc == 1 && slice_type == B)) Given its size, it makes sense to move this table to its control, so applications can avoid passing it if the slice doesn't specify it. Before this change struct v4l2_ctrl_h264_slice_params was 960 bytes. With this change, it's 188 bytes and struct v4l2_ctrl_h264_pred_weight is 772 bytes. Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 12 ++++++++++-- include/media/v4l2-ctrls.h | 2 ++ 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 3c613b84e5ae..31c6f4c5963b 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -36,6 +36,7 @@ #define V4L2_CID_MPEG_VIDEO_H264_DECODE_PARAMS (V4L2_CID_MPEG_BASE+1004) #define V4L2_CID_MPEG_VIDEO_H264_DECODE_MODE (V4L2_CID_MPEG_BASE+1005) #define V4L2_CID_MPEG_VIDEO_H264_START_CODE (V4L2_CID_MPEG_BASE+1006) +#define V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS (V4L2_CID_MPEG_BASE+1007) /* enum v4l2_ctrl_type type values */ #define V4L2_CTRL_TYPE_H264_SPS 0x0110 @@ -43,6 +44,7 @@ #define V4L2_CTRL_TYPE_H264_SCALING_MATRIX 0x0112 #define V4L2_CTRL_TYPE_H264_SLICE_PARAMS 0x0113 #define V4L2_CTRL_TYPE_H264_DECODE_PARAMS 0x0114 +#define V4L2_CTRL_TYPE_H264_PRED_WEIGHTS 0x0115 enum v4l2_mpeg_video_h264_decode_mode { V4L2_MPEG_VIDEO_H264_DECODE_MODE_SLICE_BASED, @@ -125,7 +127,14 @@ struct v4l2_h264_weight_factors { __s16 chroma_offset[32][2]; }; -struct v4l2_h264_pred_weight_table { +#define V4L2_H264_CTRL_PRED_WEIGHTS_REQUIRED(pps, slice) \ + ((((pps)->flags & V4L2_H264_PPS_FLAG_WEIGHTED_PRED) && \ + ((slice)->slice_type == V4L2_H264_SLICE_TYPE_P || \ + (slice)->slice_type == V4L2_H264_SLICE_TYPE_SP)) || \ + ((pps)->weighted_bipred_idc == 1 && \ + (slice)->slice_type == V4L2_H264_SLICE_TYPE_B)) + +struct v4l2_ctrl_h264_pred_weights { __u16 luma_log2_weight_denom; __u16 chroma_log2_weight_denom; struct v4l2_h264_weight_factors weight_factors[2]; @@ -175,7 +184,6 @@ struct v4l2_ctrl_h264_slice_params { __s32 delta_pic_order_cnt0; __s32 delta_pic_order_cnt1; - struct v4l2_h264_pred_weight_table pred_weight_table; /* Size in bits of dec_ref_pic_marking() syntax element. */ __u32 dec_ref_pic_marking_bit_size; /* Size in bits of pic order count syntax. */ diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index f40e2cbb21d3..cb25f345e9ad 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -51,6 +51,7 @@ struct video_device; * @p_h264_scaling_matrix: Pointer to a struct v4l2_ctrl_h264_scaling_matrix. * @p_h264_slice_params: Pointer to a struct v4l2_ctrl_h264_slice_params. * @p_h264_decode_params: Pointer to a struct v4l2_ctrl_h264_decode_params. + * @p_h264_pred_weights: Pointer to a struct v4l2_ctrl_h264_pred_weights. * @p_vp8_frame_header: Pointer to a VP8 frame header structure. * @p_hevc_sps: Pointer to an HEVC sequence parameter set structure. * @p_hevc_pps: Pointer to an HEVC picture parameter set structure. @@ -74,6 +75,7 @@ union v4l2_ctrl_ptr { struct v4l2_ctrl_h264_scaling_matrix *p_h264_scaling_matrix; struct v4l2_ctrl_h264_slice_params *p_h264_slice_params; struct v4l2_ctrl_h264_decode_params *p_h264_decode_params; + struct v4l2_ctrl_h264_pred_weights *p_h264_pred_weights; struct v4l2_ctrl_vp8_frame_header *p_vp8_frame_header; struct v4l2_ctrl_hevc_sps *p_hevc_sps; struct v4l2_ctrl_hevc_pps *p_hevc_pps; -- cgit v1.2.3 From 4245232fa6ca58f79710732bd16cefe78b8b8bc4 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:31 +0200 Subject: media: uapi: h264: Increase size of 'first_mb_in_slice' field Slice header syntax element 'first_mb_in_slice' can point to the last macroblock, currently the field can only reference 65536 macroblocks which is insufficient for 8K videos. Although unlikely, a 8192x4320 video (where macroblocks are 16x16), would contain 138240 macroblocks on a frame. As per the H264 specification, 'first_mb_in_slice' can be up to PicSizeInMbs - 1, so increase the size of the field to 32-bits. Note that v4l2_ctrl_h264_slice_params struct will be modified in a follow-up commit, and so we defer its 64-bit padding. Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 31c6f4c5963b..9a6722edf004 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -172,7 +172,8 @@ struct v4l2_ctrl_h264_slice_params { /* Offset in bits to slice_data() from the beginning of this slice. */ __u32 header_bit_size; - __u16 first_mb_in_slice; + __u32 first_mb_in_slice; + __u8 slice_type; __u8 pic_parameter_set_id; __u8 colour_plane_id; -- cgit v1.2.3 From c02ff21952a6a19ca375b9dc4f9a5609616a82b8 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:32 +0200 Subject: media: uapi: h264: Clean DPB entry interface As discussed recently, the current interface for the Decoded Picture Buffer is not enough to properly support field coding. This commit introduces enough semantics to support frame and field coding, and to signal how DPB entries are "used for reference". Reserved fields will be added by a follow-up commit. Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 9a6722edf004..0529e75cce5f 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -210,12 +210,12 @@ struct v4l2_ctrl_h264_slice_params { #define V4L2_H264_DPB_ENTRY_FLAG_ACTIVE 0x02 #define V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM 0x04 #define V4L2_H264_DPB_ENTRY_FLAG_FIELD 0x08 -#define V4L2_H264_DPB_ENTRY_FLAG_BOTTOM_FIELD 0x10 struct v4l2_h264_dpb_entry { __u64 reference_ts; __u16 frame_num; __u16 pic_num; + __u8 fields; /* Note that field is indicated by v4l2_buffer.field */ __s32 top_field_order_cnt; __s32 bottom_field_order_cnt; -- cgit v1.2.3 From f9879eb378295e8a912d2d10c872c45f3e19421b Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:33 +0200 Subject: media: uapi: h264: Increase size of DPB entry pic_num DPB entry PicNum maximum value is 2*MaxFrameNum for interlaced content (field_pic_flag=1). As specified, MaxFrameNum is 2^(log2_max_frame_num_minus4 + 4) and log2_max_frame_num_minus4 is in the range of 0 to 12, which means pic_num should be a 32-bit field. The v4l2_h264_dpb_entry struct needs to be padded to avoid a hole, which might be also useful to allow future uAPI extensions. Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 3 ++- include/media/v4l2-h264.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 0529e75cce5f..91f6f0d43e11 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -213,9 +213,10 @@ struct v4l2_ctrl_h264_slice_params { struct v4l2_h264_dpb_entry { __u64 reference_ts; + __u32 pic_num; __u16 frame_num; - __u16 pic_num; __u8 fields; + __u8 reserved[5]; /* Note that field is indicated by v4l2_buffer.field */ __s32 top_field_order_cnt; __s32 bottom_field_order_cnt; diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index bc9ebb560ccf..1a5f26fc2a9a 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -33,7 +33,7 @@ struct v4l2_h264_reflist_builder { struct { s32 pic_order_count; int frame_num; - u16 pic_num; + u32 pic_num; u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; s32 cur_pic_order_count; -- cgit v1.2.3 From f6f0d58edfa77d18c41777740958f467de615728 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:34 +0200 Subject: media: uapi: h264: Drop SLICE_PARAMS 'size' field The SLICE_PARAMS control is intended for slice-based devices. In this mode, the OUTPUT buffer contains a single slice, and so the buffer's plane payload size can be used to query the slice size. To reduce the API surface drop the size from the SLICE_PARAMS control. A follow-up change will remove other members in SLICE_PARAMS so we don't need to add padding fields here. Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 91f6f0d43e11..77d0ec51ae43 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -163,9 +163,6 @@ struct v4l2_h264_reference { }; struct v4l2_ctrl_h264_slice_params { - /* Size in bytes, including header */ - __u32 size; - /* Offset in bytes to the start of slice in the OUTPUT buffer. */ __u32 start_byte_offset; -- cgit v1.2.3 From 2287c5e65cbcc99633c412dbfe1d39bd9f7bf1ce Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:35 +0200 Subject: media: uapi: h264: Clarify SLICE_BASED mode Currently, the SLICE_BASED and FRAME_BASED modes documentation is misleading and not matching the intended use-cases. Drop non-required fields SLICE_PARAMS 'start_byte_offset' and DECODE_PARAMS 'num_slices' and clarify the decoding modes in the documentation. On SLICE_BASED mode, a single slice is expected per OUTPUT buffer, and therefore 'start_byte_offset' is not needed (since the offset to the slice is the start of the buffer). This mode requires the use of CAPTURE buffer holding, and so the number of slices shall not be required. On FRAME_BASED mode, the devices are expected to take care of slice parsing. Neither SLICE_PARAMS are required (and shouldn't be exposed by frame-based drivers), nor the number of slices. Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 77d0ec51ae43..e4cae02a765f 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -163,9 +163,6 @@ struct v4l2_h264_reference { }; struct v4l2_ctrl_h264_slice_params { - /* Offset in bytes to the start of slice in the OUTPUT buffer. */ - __u32 start_byte_offset; - /* Offset in bits to slice_data() from the beginning of this slice. */ __u32 header_bit_size; @@ -224,7 +221,6 @@ struct v4l2_h264_dpb_entry { struct v4l2_ctrl_h264_decode_params { struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]; - __u16 num_slices; __u16 nal_ref_idc; __s32 top_field_order_cnt; __s32 bottom_field_order_cnt; -- cgit v1.2.3 From d9358563179a7f01f9020ebbe201c7e54ba3af48 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:36 +0200 Subject: media: uapi: h264: Clean slice invariants syntax elements The H.264 specification requires in section 7.4.3 "Slice header semantics", that the following values shall be the same in all slice headers: pic_parameter_set_id frame_num field_pic_flag bottom_field_flag idr_pic_id pic_order_cnt_lsb delta_pic_order_cnt_bottom delta_pic_order_cnt[ 0 ] delta_pic_order_cnt[ 1 ] sp_for_switch_flag slice_group_change_cycle These bitstream fields are part of the slice header, and therefore passed redundantly on each slice. The purpose of the redundancy is to make the codec fault-tolerant in network scenarios. This is of course not needed to be reflected in the V4L2 controls, given the bitstream has already been parsed by applications. Therefore, move the redundant fields to the per-frame decode parameters control (DECODE_PARAMS). Field 'pic_parameter_set_id' is simply removed in this case, because the PPS control must currently contain the active PPS. Syntax elements dec_ref_pic_marking() and those related to pic order count, remain invariant as well, and therefore, the fields dec_ref_pic_marking_bit_size and pic_order_cnt_bit_size are also common to all slices. Signed-off-by: Ezequiel Garcia Reviewed-by: Nicolas Dufresne Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 39 ++++++++++++++++++++------------------- include/media/v4l2-h264.h | 1 - 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index e4cae02a765f..0c15ff938873 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -146,10 +146,8 @@ struct v4l2_ctrl_h264_pred_weights { #define V4L2_H264_SLICE_TYPE_SP 3 #define V4L2_H264_SLICE_TYPE_SI 4 -#define V4L2_H264_SLICE_FLAG_FIELD_PIC 0x01 -#define V4L2_H264_SLICE_FLAG_BOTTOM_FIELD 0x02 -#define V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED 0x04 -#define V4L2_H264_SLICE_FLAG_SP_FOR_SWITCH 0x08 +#define V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED 0x01 +#define V4L2_H264_SLICE_FLAG_SP_FOR_SWITCH 0x02 #define V4L2_H264_TOP_FIELD_REF 0x1 #define V4L2_H264_BOTTOM_FIELD_REF 0x2 @@ -169,21 +167,8 @@ struct v4l2_ctrl_h264_slice_params { __u32 first_mb_in_slice; __u8 slice_type; - __u8 pic_parameter_set_id; __u8 colour_plane_id; __u8 redundant_pic_cnt; - __u16 frame_num; - __u16 idr_pic_id; - __u16 pic_order_cnt_lsb; - __s32 delta_pic_order_cnt_bottom; - __s32 delta_pic_order_cnt0; - __s32 delta_pic_order_cnt1; - - /* Size in bits of dec_ref_pic_marking() syntax element. */ - __u32 dec_ref_pic_marking_bit_size; - /* Size in bits of pic order count syntax. */ - __u32 pic_order_cnt_bit_size; - __u8 cabac_init_idc; __s8 slice_qp_delta; __s8 slice_qs_delta; @@ -192,7 +177,8 @@ struct v4l2_ctrl_h264_slice_params { __s8 slice_beta_offset_div2; __u8 num_ref_idx_l0_active_minus1; __u8 num_ref_idx_l1_active_minus1; - __u32 slice_group_change_cycle; + + __u8 reserved; struct v4l2_h264_reference ref_pic_list0[V4L2_H264_REF_LIST_LEN]; struct v4l2_h264_reference ref_pic_list1[V4L2_H264_REF_LIST_LEN]; @@ -217,13 +203,28 @@ struct v4l2_h264_dpb_entry { __u32 flags; /* V4L2_H264_DPB_ENTRY_FLAG_* */ }; -#define V4L2_H264_DECODE_PARAM_FLAG_IDR_PIC 0x01 +#define V4L2_H264_DECODE_PARAM_FLAG_IDR_PIC 0x01 +#define V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC 0x02 +#define V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD 0x04 struct v4l2_ctrl_h264_decode_params { struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]; __u16 nal_ref_idc; + __u16 frame_num; __s32 top_field_order_cnt; __s32 bottom_field_order_cnt; + __u16 idr_pic_id; + __u16 pic_order_cnt_lsb; + __s32 delta_pic_order_cnt_bottom; + __s32 delta_pic_order_cnt0; + __s32 delta_pic_order_cnt1; + /* Size in bits of dec_ref_pic_marking() syntax element. */ + __u32 dec_ref_pic_marking_bit_size; + /* Size in bits of pic order count syntax. */ + __u32 pic_order_cnt_bit_size; + __u32 slice_group_change_cycle; + + __u32 reserved; __u32 flags; /* V4L2_H264_DECODE_PARAM_FLAG_* */ }; diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index 1a5f26fc2a9a..f08ba181263d 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -44,7 +44,6 @@ struct v4l2_h264_reflist_builder { void v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, const struct v4l2_ctrl_h264_decode_params *dec_params, - const struct v4l2_ctrl_h264_slice_params *slice_params, const struct v4l2_ctrl_h264_sps *sps, const struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]); -- cgit v1.2.3 From 54889c51b833d236228f983be16212fbe806bb89 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 25 Aug 2020 05:52:37 +0200 Subject: media: uapi: h264: Rename and clarify PPS_FLAG_SCALING_MATRIX_PRESENT Applications are expected to fill V4L2_CID_MPEG_VIDEO_H264_SCALING_MATRIX if a non-flat scaling matrix applies to the picture. This is the case if SPS scaling_matrix_present_flag or PPS pic_scaling_matrix_present_flag are set, and should be handled by applications. On one hand, the PPS bitstream syntax element signals the presence of a Picture scaling matrix modifying the Sequence (SPS) scaling matrix. On the other hand, our flag should indicate if the scaling matrix V4L2 control is applicable to this request. Rename the flag from PPS_FLAG_PIC_SCALING_MATRIX_PRESENT to PPS_FLAG_SCALING_MATRIX_PRESENT, to avoid mixing this flag with bitstream syntax element pic_scaling_matrix_present_flag, and clarify the meaning of our flag. Signed-off-by: Ezequiel Garcia Tested-by: Jonas Karlman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/h264-ctrls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h index 0c15ff938873..ec4799154438 100644 --- a/include/media/h264-ctrls.h +++ b/include/media/h264-ctrls.h @@ -99,7 +99,7 @@ struct v4l2_ctrl_h264_sps { #define V4L2_H264_PPS_FLAG_CONSTRAINED_INTRA_PRED 0x0010 #define V4L2_H264_PPS_FLAG_REDUNDANT_PIC_CNT_PRESENT 0x0020 #define V4L2_H264_PPS_FLAG_TRANSFORM_8X8_MODE 0x0040 -#define V4L2_H264_PPS_FLAG_PIC_SCALING_MATRIX_PRESENT 0x0080 +#define V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT 0x0080 struct v4l2_ctrl_h264_pps { __u8 pic_parameter_set_id; -- cgit v1.2.3 From 4ad1b0d410c88c7c8e8fd1298c9d2293b651e35c Mon Sep 17 00:00:00 2001 From: Maheshwar Ajja Date: Sat, 23 May 2020 03:05:26 +0200 Subject: media: v4l2-ctrls: Add encoder constant quality control When V4L2_CID_MPEG_VIDEO_BITRATE_MODE value is V4L2_MPEG_VIDEO_BITRATE_MODE_CQ, encoder will produce constant quality output indicated by V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY control value. Encoder will choose appropriate quantization parameter and bitrate to produce requested frame quality level. Signed-off-by: Maheshwar Ajja Reviewed-by: Hans Verkuil Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 62271418c1be..0f7e4388dcce 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -375,6 +375,7 @@ enum v4l2_mpeg_video_aspect { enum v4l2_mpeg_video_bitrate_mode { V4L2_MPEG_VIDEO_BITRATE_MODE_VBR = 0, V4L2_MPEG_VIDEO_BITRATE_MODE_CBR = 1, + V4L2_MPEG_VIDEO_BITRATE_MODE_CQ = 2, }; #define V4L2_CID_MPEG_VIDEO_BITRATE (V4L2_CID_MPEG_BASE+207) #define V4L2_CID_MPEG_VIDEO_BITRATE_PEAK (V4L2_CID_MPEG_BASE+208) @@ -742,6 +743,7 @@ enum v4l2_cid_mpeg_video_hevc_size_of_length_field { #define V4L2_CID_MPEG_VIDEO_HEVC_HIER_CODING_L6_BR (V4L2_CID_MPEG_BASE + 642) #define V4L2_CID_MPEG_VIDEO_REF_NUMBER_FOR_PFRAMES (V4L2_CID_MPEG_BASE + 643) #define V4L2_CID_MPEG_VIDEO_PREPEND_SPSPPS_TO_IDR (V4L2_CID_MPEG_BASE + 644) +#define V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY (V4L2_CID_MPEG_BASE + 645) /* MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */ #define V4L2_CID_MPEG_CX2341X_BASE (V4L2_CTRL_CLASS_MPEG | 0x1000) -- cgit v1.2.3 From 44f5b2fffc3213c919f53adddadb1a05519bdc0e Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Sun, 5 Jul 2020 01:41:00 +0200 Subject: media: v4l2-ctrl: Add frame-skip std encoder control Adds encoders standard v4l2 control for frame-skip. The control is a copy of a custom encoder control so that other v4l2 encoder drivers can use it. Signed-off-by: Stanimir Varbanov Reviewed-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 0f7e4388dcce..053827cda8e6 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -744,6 +744,12 @@ enum v4l2_cid_mpeg_video_hevc_size_of_length_field { #define V4L2_CID_MPEG_VIDEO_REF_NUMBER_FOR_PFRAMES (V4L2_CID_MPEG_BASE + 643) #define V4L2_CID_MPEG_VIDEO_PREPEND_SPSPPS_TO_IDR (V4L2_CID_MPEG_BASE + 644) #define V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY (V4L2_CID_MPEG_BASE + 645) +#define V4L2_CID_MPEG_VIDEO_FRAME_SKIP_MODE (V4L2_CID_MPEG_BASE + 646) +enum v4l2_mpeg_video_frame_skip_mode { + V4L2_MPEG_VIDEO_FRAME_SKIP_MODE_DISABLED = 0, + V4L2_MPEG_VIDEO_FRAME_SKIP_MODE_LEVEL_LIMIT = 1, + V4L2_MPEG_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT = 2, +}; /* MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */ #define V4L2_CID_MPEG_CX2341X_BASE (V4L2_CTRL_CLASS_MPEG | 0x1000) -- cgit v1.2.3 From f53fa968a7344970b8f8a5707c39cdcf17a6f367 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 5 May 2020 15:42:35 +0200 Subject: scif: Fix spelling of EACCES As per POSIX, the correct spelling is EACCES: include/uapi/asm-generic/errno-base.h:#define EACCES 13 /* Permission denied */ Signed-off-by: Geert Uytterhoeven Signed-off-by: Jiri Kosina --- include/linux/scif.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/scif.h b/include/linux/scif.h index eeb250b73c4b..329e695b8fe5 100644 --- a/include/linux/scif.h +++ b/include/linux/scif.h @@ -657,7 +657,7 @@ int scif_unregister(scif_epd_t epd, off_t offset, size_t len); * the negative of one of the following errors is returned. * * Errors: - * EACCESS - Attempt to write to a read-only range + * EACCES - Attempt to write to a read-only range * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer * EINVAL - rma_flags is invalid @@ -733,7 +733,7 @@ int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t * the negative of one of the following errors is returned. * * Errors: - * EACCESS - Attempt to write to a read-only range + * EACCES - Attempt to write to a read-only range * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer * EINVAL - rma_flags is invalid @@ -815,7 +815,7 @@ int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t * the negative of one of the following errors is returned. * * Errors: - * EACCESS - Attempt to write to a read-only range + * EACCES - Attempt to write to a read-only range * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer * EINVAL - rma_flags is invalid @@ -895,7 +895,7 @@ int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset, * the negative of one of the following errors is returned. * * Errors: - * EACCESS - Attempt to write to a read-only range + * EACCES - Attempt to write to a read-only range * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer * EINVAL - rma_flags is invalid -- cgit v1.2.3 From 1ad5f100e3ba73fe75615f720fa721f039759ee6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 31 Aug 2020 13:54:24 -0400 Subject: locks: Remove extra "0x" in tracepoint format specifier Clean up: %p adds its own 0x already. Signed-off-by: Chuck Lever Signed-off-by: Jeff Layton --- include/trace/events/filelock.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h index c705e4944a50..1646dadd7f37 100644 --- a/include/trace/events/filelock.h +++ b/include/trace/events/filelock.h @@ -92,7 +92,7 @@ DECLARE_EVENT_CLASS(filelock_lock, __entry->ret = ret; ), - TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_blocker=0x%p fl_owner=0x%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d", + TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->fl_blocker, __entry->fl_owner, __entry->fl_pid, show_fl_flags(__entry->fl_flags), @@ -145,7 +145,7 @@ DECLARE_EVENT_CLASS(filelock_lease, __entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0; ), - TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_blocker=0x%p fl_owner=0x%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu", + TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->fl_blocker, __entry->fl_owner, show_fl_flags(__entry->fl_flags), @@ -195,7 +195,7 @@ TRACE_EVENT(generic_add_lease, __entry->fl_type = fl->fl_type; ), - TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=0x%p fl_flags=%s fl_type=%s", + TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->wcount, __entry->rcount, __entry->icount, __entry->fl_owner, @@ -228,7 +228,7 @@ TRACE_EVENT(leases_conflict, __entry->conflict = conflict; ), - TP_printk("conflict %d: lease=0x%p fl_flags=%s fl_type=%s; breaker=0x%p fl_flags=%s fl_type=%s", + TP_printk("conflict %d: lease=%p fl_flags=%s fl_type=%s; breaker=%p fl_flags=%s fl_type=%s", __entry->conflict, __entry->lease, show_fl_flags(__entry->l_fl_flags), -- cgit v1.2.3 From db04e18dbb0146d3c753dc05f7233350375bbc48 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 19 Aug 2020 14:34:03 +0200 Subject: block: Make request_queue.rpm_status an enum request_queue.rpm_status is assigned values of the rpm_status enum only, so reflect that in its type. Note that including is (currently) a no-op, as it is already included through and , but it is better to play it safe. Signed-off-by: Geert Uytterhoeven Acked-by: Rafael J. Wysocki Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..0a1730b30ad2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -458,7 +459,7 @@ struct request_queue { #ifdef CONFIG_PM struct device *dev; - int rpm_status; + enum rpm_status rpm_status; unsigned int nr_pending; #endif -- cgit v1.2.3 From 611bee526b4a89d49f1b9914a770bfdc101d5fb5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 23 Aug 2020 11:10:41 +0200 Subject: block: replace bd_set_size with bd_set_nr_sectors Replace bd_set_size with a version that takes the number of sectors instead, as that fits most of the current and future callers much better. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 4ab853461dff..39025dc0397c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -375,7 +375,7 @@ void unregister_blkdev(unsigned int major, const char *name); int revalidate_disk(struct gendisk *disk); int check_disk_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); -void bd_set_size(struct block_device *bdev, loff_t size); +void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); /* for drivers/char/raw.c: */ int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -- cgit v1.2.3 From c2b4bb8cb3741c0bacf3683e4c1ecd04c977ada3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 23 Aug 2020 11:10:42 +0200 Subject: block: fix locking for struct block_device size updates Two different callers use two different mutexes for updating the block device size, which obviously doesn't help to actually protect against concurrent updates from the different callers. In addition one of the locks, bd_mutex is rather prone to deadlocks with other parts of the block stack that use it for high level synchronization. Switch to using a new spinlock protecting just the size updates, as that is all we need, and make sure everyone does the update through the proper helper. This fixes a bug reported with the nvme revalidating disks during a hot removal operation, which can currently deadlock on bd_mutex. Reported-by: Xianting Tian Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4ecf4fed171f..5accc2549d22 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -38,6 +38,7 @@ struct block_device { /* number of times partitions within this device have been opened. */ unsigned bd_part_count; int bd_invalidated; + spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; -- cgit v1.2.3 From f3256075ba49d80835b601bfbff350a2140b2924 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2020 17:37:45 +0200 Subject: block: remove the BIO_NULL_MAPPED flag We can simply use a boolean flag in the bio_map_data data structure instead. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5accc2549d22..78b073956884 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -257,7 +257,6 @@ enum { BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ BIO_USER_MAPPED, /* contains user pages */ - BIO_NULL_MAPPED, /* contains invalid user pages */ BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ -- cgit v1.2.3 From 3310eebafe6f9a872c1f757b3d822dafae9c0cd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2020 17:37:48 +0200 Subject: block: remove the BIO_USER_MAPPED flag Just check if there is private data, in which case the bio must have originated from bio_copy_user_iov. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 78b073956884..63a39e47fc60 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -256,7 +256,6 @@ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ - BIO_USER_MAPPED, /* contains user pages */ BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ -- cgit v1.2.3 From bdc6a287bc98e8f32bf52c9cb2d1bdf75975f5a0 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 28 Aug 2020 10:52:55 +0800 Subject: block: Move blk_mq_bio_list_merge() into blk-merge.c Move the blk_mq_bio_list_merge() into blk-merge.c and rename it as a generic name. Reviewed-by: Christoph Hellwig Signed-off-by: Baolin Wang Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9d2d5ad367a4..21a02e0577dd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -489,8 +489,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); -bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, - struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); -- cgit v1.2.3 From 7b8917f5e29c377be1db5680249fe30e038cb3eb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:33 +0200 Subject: block: remove the alignment_offset field from struct hd_struct The alignment offset is only used in slow path callers, so just calculate it on the fly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++--- include/linux/genhd.h | 1 - 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0a1730b30ad2..ba1f5f5e11c6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1456,10 +1456,9 @@ static inline int bdev_alignment_offset(struct block_device *bdev) if (q->limits.misaligned) return -1; - if (bdev != bdev->bd_contains) - return bdev->bd_part->alignment_offset; - + return queue_limit_alignment_offset(&q->limits, + bdev->bd_part->start_sect); return q->limits.alignment_offset; } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 39025dc0397c..bfa411c80dbb 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -65,7 +65,6 @@ struct hd_struct { struct disk_stats __percpu *dkstats; struct percpu_ref ref; - sector_t alignment_offset; unsigned int discard_alignment; struct device __dev; struct kobject *holder_dir; -- cgit v1.2.3 From 7cf34d97ab45203b975396393ded9d3867dfa8bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:34 +0200 Subject: block: remove the discard_alignment field from struct hd_struct The alignment offset is only used in slow path callers, so just calculate it on the fly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- include/linux/genhd.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba1f5f5e11c6..d0d61bc81615 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1498,8 +1498,8 @@ static inline int bdev_discard_alignment(struct block_device *bdev) struct request_queue *q = bdev_get_queue(bdev); if (bdev != bdev->bd_contains) - return bdev->bd_part->discard_alignment; - + return queue_limit_discard_alignment(&q->limits, + bdev->bd_part->start_sect); return q->limits.discard_alignment; } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index bfa411c80dbb..9ea2ca31c278 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -65,7 +65,6 @@ struct hd_struct { struct disk_stats __percpu *dkstats; struct percpu_ref ref; - unsigned int discard_alignment; struct device __dev; struct kobject *holder_dir; int policy, partno; -- cgit v1.2.3 From 46d40cfad13ccbd0739019d754d46d8f93e1d5aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:35 +0200 Subject: block: remove an outdated comment on the bd_dev field kdev_t is long gone, so we don't need to comment a field isn't one.. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 63a39e47fc60..59d9150165c4 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -20,7 +20,7 @@ typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; struct block_device { - dev_t bd_dev; /* not a kdev_t - it's a search key */ + dev_t bd_dev; int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; -- cgit v1.2.3 From 1aa50d020c7148f5f0bde15ca80fe6f91a8c5a4e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 1 Sep 2020 14:52:44 -0400 Subject: blk-iocost: calculate iocg->usages[] from iocg->local_stat.usage_us Currently, iocg->usages[] which are used to guide inuse adjustments are calculated from vtime deltas. This, however, assumes that the hierarchical inuse weight at the time of calculation held for the entire period, which often isn't true and can lead to significant errors. Now that we have absolute usage information collected, we can derive iocg->usages[] from iocg->local_stat.usage_us so that inuse adjustment decisions are made based on actual absolute usage. The calculated usage is clamped between 1 and WEIGHT_ONE and WEIGHT_ONE is also used to signal saturation regardless of the current hierarchical inuse weight. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/trace/events/iocost.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index c2f580fd371b..a905ecc0342f 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -26,7 +26,6 @@ TRACE_EVENT(iocost_iocg_activate, __field(u64, vrate) __field(u64, last_period) __field(u64, cur_period) - __field(u64, last_vtime) __field(u64, vtime) __field(u32, weight) __field(u32, inuse) @@ -42,7 +41,6 @@ TRACE_EVENT(iocost_iocg_activate, __entry->vrate = now->vrate; __entry->last_period = last_period; __entry->cur_period = cur_period; - __entry->last_vtime = iocg->last_vtime; __entry->vtime = vtime; __entry->weight = iocg->weight; __entry->inuse = iocg->inuse; @@ -51,13 +49,12 @@ TRACE_EVENT(iocost_iocg_activate, ), TP_printk("[%s:%s] now=%llu:%llu vrate=%llu " - "period=%llu->%llu vtime=%llu->%llu " + "period=%llu->%llu vtime=%llu " "weight=%u/%u hweight=%llu/%llu", __get_str(devname), __get_str(cgroup), __entry->now, __entry->vnow, __entry->vrate, __entry->last_period, __entry->cur_period, - __entry->last_vtime, __entry->vtime, - __entry->inuse, __entry->weight, + __entry->vtime, __entry->inuse, __entry->weight, __entry->hweight_inuse, __entry->hweight_active ) ); -- cgit v1.2.3 From 065655c862fedf4b04e1b28b83ca6f338d81cf0b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 1 Sep 2020 14:52:46 -0400 Subject: blk-iocost: decouple vrate adjustment from surplus transfers Budget donations are inaccurate and could take multiple periods to converge. To prevent triggering vrate adjustments while surplus transfers were catching up, vrate adjustment was suppressed if donations were increasing, which was indicated by non-zero nr_surpluses. This entangling won't be necessary with the scheduled rewrite of donation mechanism which will make it precise and immediate. Let's decouple the two in preparation. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/trace/events/iocost.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index a905ecc0342f..ee024fe8fef6 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -128,11 +128,9 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset, TRACE_EVENT(iocost_ioc_vrate_adj, TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 *missed_ppm, - u32 rq_wait_pct, int nr_lagging, int nr_shortages, - int nr_surpluses), + u32 rq_wait_pct, int nr_lagging, int nr_shortages), - TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages, - nr_surpluses), + TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages), TP_STRUCT__entry ( __string(devname, ioc_name(ioc)) @@ -144,7 +142,6 @@ TRACE_EVENT(iocost_ioc_vrate_adj, __field(u32, rq_wait_pct) __field(int, nr_lagging) __field(int, nr_shortages) - __field(int, nr_surpluses) ), TP_fast_assign( @@ -157,15 +154,13 @@ TRACE_EVENT(iocost_ioc_vrate_adj, __entry->rq_wait_pct = rq_wait_pct; __entry->nr_lagging = nr_lagging; __entry->nr_shortages = nr_shortages; - __entry->nr_surpluses = nr_surpluses; ), - TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d surpluses=%d", + TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d", __get_str(devname), __entry->old_vrate, __entry->new_vrate, __entry->busy_level, __entry->read_missed_ppm, __entry->write_missed_ppm, - __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages, - __entry->nr_surpluses + __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages ) ); -- cgit v1.2.3 From 046037551721e8831f6718ac2149887f6bb1f802 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 1 Sep 2020 14:52:55 -0400 Subject: blk-iocost: restore inuse update tracepoints Update and restore the inuse update tracepoints. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/trace/events/iocost.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index ee024fe8fef6..b350860d2e71 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -95,7 +95,7 @@ DECLARE_EVENT_CLASS(iocg_inuse_update, ) ); -DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback, +DEFINE_EVENT(iocg_inuse_update, iocost_inuse_shortage, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, u32 old_inuse, u32 new_inuse, @@ -105,7 +105,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback, old_hw_inuse, new_hw_inuse) ); -DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway, +DEFINE_EVENT(iocg_inuse_update, iocost_inuse_transfer, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, u32 old_inuse, u32 new_inuse, @@ -115,7 +115,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway, old_hw_inuse, new_hw_inuse) ); -DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset, +DEFINE_EVENT(iocg_inuse_update, iocost_inuse_adjust, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, u32 old_inuse, u32 new_inuse, -- cgit v1.2.3 From 9d3a39a5f1e45827b008fff1ee9cf3cac3409665 Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Mon, 24 Aug 2020 15:10:34 -0700 Subject: block: grant IOPRIO_CLASS_RT to CAP_SYS_NICE CAP_SYS_ADMIN is too broad, and ionice fits into CAP_SYS_NICE's grouping. Retain CAP_SYS_ADMIN permission for backwards compatibility. Signed-off-by: Khazhismel Kumykov Reviewed-by: Bart Van Assche Acked-by: Serge Hallyn Signed-off-by: Jens Axboe --- include/uapi/linux/capability.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 395dd0df8d08..c6ca33034147 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -288,6 +288,8 @@ struct vfs_ns_cap_data { processes and setting the scheduling algorithm used by another process. */ /* Allow setting cpu affinity on other processes */ +/* Allow setting realtime ioprio class */ +/* Allow setting ioprio class on other processes */ #define CAP_SYS_NICE 23 -- cgit v1.2.3 From a8c7ffdb5fdde3a57c0b654f66f4d81325abe69f Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:56 +0200 Subject: mtd: nand: Introduce the ECC engine framework Create a generic ECC engine framework. This is a base to instantiate ECC engine objects. If we really want to be generic, bindings must evolve, so here is the new logic. The following three properties are mutually exclusive: - The nand-no-ecc-engine boolean property is set and there is no ECC engine to retrieve. - The nand-use-soft-ecc-engine boolean property is set and the core will force using the use of software correction. - There is a nand-ecc-engine property pointing at a node which will act as ECC engine. It the later case, the property may reference: - The NAND chip node itself (for the on-die ECC case). - The parent node if the NAND controller embeds an ECC engine. - Any other node being an external ECC controller as well. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-9-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 114 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 114 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index e754a6fc8a4b..8cf5bdbea782 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -127,6 +127,40 @@ struct nand_page_io_req { int mode; }; +const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void); +const struct mtd_ooblayout_ops *nand_get_large_page_ooblayout(void); +const struct mtd_ooblayout_ops *nand_get_large_page_hamming_ooblayout(void); + +/** + * enum nand_ecc_engine_type - NAND ECC engine type + * @NAND_ECC_ENGINE_TYPE_INVALID: Invalid value + * @NAND_ECC_ENGINE_TYPE_NONE: No ECC correction + * @NAND_ECC_ENGINE_TYPE_SOFT: Software ECC correction + * @NAND_ECC_ENGINE_TYPE_ON_HOST: On host hardware ECC correction + * @NAND_ECC_ENGINE_TYPE_ON_DIE: On chip hardware ECC correction + */ +enum nand_ecc_engine_type { + NAND_ECC_ENGINE_TYPE_INVALID, + NAND_ECC_ENGINE_TYPE_NONE, + NAND_ECC_ENGINE_TYPE_SOFT, + NAND_ECC_ENGINE_TYPE_ON_HOST, + NAND_ECC_ENGINE_TYPE_ON_DIE, +}; + +/** + * enum nand_ecc_placement - NAND ECC bytes placement + * @NAND_ECC_PLACEMENT_UNKNOWN: The actual position of the ECC bytes is unknown + * @NAND_ECC_PLACEMENT_OOB: The ECC bytes are located in the OOB area + * @NAND_ECC_PLACEMENT_INTERLEAVED: Syndrome layout, there are ECC bytes + * interleaved with regular data in the main + * area + */ +enum nand_ecc_placement { + NAND_ECC_PLACEMENT_UNKNOWN, + NAND_ECC_PLACEMENT_OOB, + NAND_ECC_PLACEMENT_INTERLEAVED, +}; + /** * enum nand_ecc_algo - NAND ECC algorithm * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm @@ -143,16 +177,27 @@ enum nand_ecc_algo { /** * struct nand_ecc_props - NAND ECC properties + * @engine_type: ECC engine type + * @placement: OOB placement (if relevant) + * @algo: ECC algorithm (if relevant) * @strength: ECC strength * @step_size: Number of bytes per step + * @flags: Misc properties */ struct nand_ecc_props { + enum nand_ecc_engine_type engine_type; + enum nand_ecc_placement placement; + enum nand_ecc_algo algo; unsigned int strength; unsigned int step_size; + unsigned int flags; }; #define NAND_ECCREQ(str, stp) { .strength = (str), .step_size = (stp) } +/* NAND ECC misc flags */ +#define NAND_ECC_MAXIMIZE_STRENGTH BIT(0) + /** * struct nand_bbt - bad block table object * @cache: in memory BBT cache @@ -183,6 +228,75 @@ struct nand_ops { bool (*isbad)(struct nand_device *nand, const struct nand_pos *pos); }; +/** + * struct nand_ecc_context - Context for the ECC engine + * @conf: basic ECC engine parameters + * @total: total number of bytes used for storing ECC codes, this is used by + * generic OOB layouts + * @priv: ECC engine driver private data + */ +struct nand_ecc_context { + struct nand_ecc_props conf; + unsigned int total; + void *priv; +}; + +/** + * struct nand_ecc_engine_ops - ECC engine operations + * @init_ctx: given a desired user configuration for the pointed NAND device, + * requests the ECC engine driver to setup a configuration with + * values it supports. + * @cleanup_ctx: clean the context initialized by @init_ctx. + * @prepare_io_req: is called before reading/writing a page to prepare the I/O + * request to be performed with ECC correction. + * @finish_io_req: is called after reading/writing a page to terminate the I/O + * request and ensure proper ECC correction. + */ +struct nand_ecc_engine_ops { + int (*init_ctx)(struct nand_device *nand); + void (*cleanup_ctx)(struct nand_device *nand); + int (*prepare_io_req)(struct nand_device *nand, + struct nand_page_io_req *req); + int (*finish_io_req)(struct nand_device *nand, + struct nand_page_io_req *req); +}; + +/** + * struct nand_ecc_engine - ECC engine abstraction for NAND devices + * @ops: ECC engine operations + */ +struct nand_ecc_engine { + struct nand_ecc_engine_ops *ops; +}; + +void of_get_nand_ecc_user_config(struct nand_device *nand); +int nand_ecc_init_ctx(struct nand_device *nand); +void nand_ecc_cleanup_ctx(struct nand_device *nand); +int nand_ecc_prepare_io_req(struct nand_device *nand, + struct nand_page_io_req *req); +int nand_ecc_finish_io_req(struct nand_device *nand, + struct nand_page_io_req *req); +bool nand_ecc_is_strong_enough(struct nand_device *nand); + +/** + * struct nand_ecc - Information relative to the ECC + * @defaults: Default values, depend on the underlying subsystem + * @requirements: ECC requirements from the NAND chip perspective + * @user_conf: User desires in terms of ECC parameters + * @ctx: ECC context for the ECC engine, derived from the device @requirements + * the @user_conf and the @defaults + * @ondie_engine: On-die ECC engine reference, if any + * @engine: ECC engine actually bound + */ +struct nand_ecc { + struct nand_ecc_props defaults; + struct nand_ecc_props requirements; + struct nand_ecc_props user_conf; + struct nand_ecc_context ctx; + struct nand_ecc_engine *ondie_engine; + struct nand_ecc_engine *engine; +}; + /** * struct nand_device - NAND device * @mtd: MTD instance attached to the NAND device -- cgit v1.2.3 From 0f50257f5348751bf5b93d052885de23b2367cd2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 30 Aug 2020 21:16:55 -0700 Subject: dma-buf: fix kernel-doc warning in MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix kernel-doc warning in : ../include/linux/dma-buf.h:330: warning: Function parameter or member 'name_lock' not described in 'dma_buf' Signed-off-by: Randy Dunlap Cc: Sumit Semwal Cc: Gustavo Padovan Cc: Christian König Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/388523/ Signed-off-by: Christian König --- include/linux/dma-buf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index a2ca294eaebe..957b398d30e5 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -283,6 +283,7 @@ struct dma_buf_ops { * @exp_name: name of the exporter; useful for debugging. * @name: userspace-provided name; useful for accounting and debugging, * protected by @resv. + * @name_lock: spinlock to protect name access * @owner: pointer to exporter module; used for refcounting when exporter is a * kernel module. * @list_node: node for dma_buf accounting and debugging. @@ -311,7 +312,7 @@ struct dma_buf { void *vmap_ptr; const char *exp_name; const char *name; - spinlock_t name_lock; /* spinlock to protect name access */ + spinlock_t name_lock; struct module *owner; struct list_head list_node; void *priv; -- cgit v1.2.3 From f4ad06f2bb8476548b08f89919ee65abc4e40212 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:42 +0200 Subject: block: rename bd_invalidated Replace bd_invalidate with a new BDEV_NEED_PART_SCAN flag in a bd_flags variable to better describe the condition. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 59d9150165c4..6ffa783e1633 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -19,6 +19,8 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; +#define BDEV_NEED_PART_SCAN 0 + struct block_device { dev_t bd_dev; int bd_openers; @@ -37,7 +39,7 @@ struct block_device { struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; - int bd_invalidated; + unsigned long bd_flags; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; -- cgit v1.2.3 From 659e56ba864d37b7ee0a49cd432205b2a5ca815e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:43 +0200 Subject: block: add a new revalidate_disk_size helper revalidate_disk is a relative awkward helper for driver use, as it first calls an optional driver method and then updates the block device size, while most callers either don't need the method call at all, or want to keep state between the caller and the called method. Add a revalidate_disk_size helper that just performs the update of the block device size from the gendisk one, and switch all drivers that do not implement ->revalidate_disk to use the new helper instead of revalidate_disk() Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Acked-by: Song Liu Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9ea2ca31c278..f76c8baf6b7d 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -371,6 +371,7 @@ int register_blkdev(unsigned int major, const char *name); void unregister_blkdev(unsigned int major, const char *name); int revalidate_disk(struct gendisk *disk); +void revalidate_disk_size(struct gendisk *disk, bool verbose); int check_disk_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); -- cgit v1.2.3 From b8086d3f5a0e88b1912d55a158b8a6a43ad6604b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:44 +0200 Subject: block: use revalidate_disk_size in set_capacity_revalidate_and_notify Only virtio_blk and xen-blkfront set the revalidate argument to true, and both do not implement the ->revalidate_disk method. So switch to the helper that just updates the size instead. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/genhd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f76c8baf6b7d..02a73198b289 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -313,8 +313,8 @@ static inline int get_disk_ro(struct gendisk *disk) extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -extern void set_capacity_revalidate_and_notify(struct gendisk *disk, - sector_t size, bool revalidate); +void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, + bool update_bdev); extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask); /* drivers/char/random.c */ -- cgit v1.2.3 From de09077c89183cbc627d9393706343662da7f5a3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:48 +0200 Subject: block: remove revalidate_disk() Remove the now unused helper. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Acked-by: Song Liu Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 02a73198b289..c618b27292fc 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -370,7 +370,6 @@ extern void blk_unregister_region(dev_t devt, unsigned long range); int register_blkdev(unsigned int major, const char *name); void unregister_blkdev(unsigned int major, const char *name); -int revalidate_disk(struct gendisk *disk); void revalidate_disk_size(struct gendisk *disk, bool verbose); int check_disk_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); -- cgit v1.2.3 From 21f8e4828c44da39b0670c5d99d5728b739542a1 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 2 Sep 2020 17:18:43 +0300 Subject: regmap: Add can_sleep configuration option Regmap can't sleep if spinlock is used for the locking protection. This patch fixes regression caused by a previous commit that switched regmap to use fsleep() and this broke Amlogic S922X platform. This patch adds new configuration option for regmap users, allowing to specify whether regmap operations can sleep and assuming that sleep is allowed if mutex is used for the regmap locking protection. Reported-by: Marek Szyprowski Fixes: 2b32d2f7ce0a ("regmap: Use flexible sleep") Signed-off-by: Dmitry Osipenko Tested-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200902141843.6591-1-digetx@gmail.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index d865d8fea535..0c49d59168b5 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -342,6 +342,7 @@ typedef void (*regmap_unlock)(void *); * @hwlock_id: Specify the hardware spinlock id. * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE, * HWLOCK_IRQ or 0. + * @can_sleep: Optional, specifies whether regmap operations can sleep. */ struct regmap_config { const char *name; @@ -398,6 +399,8 @@ struct regmap_config { bool use_hwlock; unsigned int hwlock_id; unsigned int hwlock_mode; + + bool can_sleep; }; /** -- cgit v1.2.3 From 2a5c98d2d2fe2aeaf95274a48fc9d92b5955dc74 Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 31 Aug 2020 14:35:18 -0700 Subject: scsi: fc: Add 256GBit speed setting to SCSI FC transport Add 256GBit speed setting to the SCSI FC transport. This speed can be reached via FC trunking techniques. Link: https://lore.kernel.org/r/20200831213518.48409-1-james.smart@broadcom.com Reviewed-by: Himanshu Madhani Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_fc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h index 7db2dd783834..1c7dd35cb7a0 100644 --- a/include/scsi/scsi_transport_fc.h +++ b/include/scsi/scsi_transport_fc.h @@ -124,6 +124,7 @@ enum fc_vport_state { #define FC_PORTSPEED_25GBIT 0x800 #define FC_PORTSPEED_64GBIT 0x1000 #define FC_PORTSPEED_128GBIT 0x2000 +#define FC_PORTSPEED_256GBIT 0x4000 #define FC_PORTSPEED_NOT_NEGOTIATED (1 << 15) /* Speed not established */ /* -- cgit v1.2.3 From 7547dbd3b198f309aaff54e3528898a8a196faff Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 28 Aug 2020 14:05:07 +0300 Subject: dmaengine: Mark dma_request_slave_channel() deprecated New drivers should use dma_request_chan() instead dma_request_slave_channel() dma_request_slave_channel() is a simple wrapper for dma_request_chan() eating up the error code for channel request failure and makes deferred probing impossible. Move the dma_request_slave_channel() into the header as inline function, mark it as deprecated. Signed-off-by: Peter Ujfalusi Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200828110507.22407-1-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 011371b7f081..dd357a747780 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1472,7 +1472,6 @@ void dma_issue_pending_all(void); struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param, struct device_node *np); -struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); struct dma_chan *dma_request_chan(struct device *dev, const char *name); struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask); @@ -1502,11 +1501,6 @@ static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, { return NULL; } -static inline struct dma_chan *dma_request_slave_channel(struct device *dev, - const char *name) -{ - return NULL; -} static inline struct dma_chan *dma_request_chan(struct device *dev, const char *name) { @@ -1575,6 +1569,15 @@ void dma_run_dependencies(struct dma_async_tx_descriptor *tx); #define dma_request_channel(mask, x, y) \ __dma_request_channel(&(mask), x, y, NULL) +/* Deprecated, please use dma_request_chan() directly */ +static inline struct dma_chan * __deprecated +dma_request_slave_channel(struct device *dev, const char *name) +{ + struct dma_chan *ch = dma_request_chan(dev, name); + + return IS_ERR(ch) ? NULL : ch; +} + static inline struct dma_chan *dma_request_slave_channel_compat(const dma_cap_mask_t mask, dma_filter_fn fn, void *fn_param, -- cgit v1.2.3 From 1faa39e0f3bcfe47dc7a61a72c234b24005c3a1a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 1 Sep 2020 11:09:26 +0200 Subject: media: videobuf-dma-sg: number of pages should be unsigned long As reported by smatch: drivers/media/v4l2-core/videobuf-dma-sg.c:245 videobuf_dma_init_kernel() warn: should 'nr_pages << 12' be a 64 bit type? The printk should not be using %d for the number of pages. After looking better, the real problem here is that the number of pages should be long int. Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf-dma-sg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h index 34450f7ad510..930ff8d454fc 100644 --- a/include/media/videobuf-dma-sg.h +++ b/include/media/videobuf-dma-sg.h @@ -60,7 +60,7 @@ struct videobuf_dmabuf { /* common */ struct scatterlist *sglist; int sglen; - int nr_pages; + unsigned long nr_pages; int direction; }; -- cgit v1.2.3 From fe662d846c957c8861ade7170115e88f6e6e5fdd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 30 Sep 2019 15:12:54 +0200 Subject: drm/ttm: remove io_reserve_lru handling v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit That is not used any more. v2: keep the NULL checks in TTM. v3: remove unused variable Signed-off-by: Christian König Acked-by: Daniel Vetter Reviewed-by: Ben Skeggs Link: https://patchwork.freedesktop.org/patch/388646/ --- include/drm/ttm/ttm_bo_api.h | 1 - include/drm/ttm/ttm_bo_driver.h | 5 ----- include/drm/ttm/ttm_resource.h | 16 ---------------- 3 files changed, 22 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 6c580987ba16..36ff64e2736c 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -151,7 +151,6 @@ struct ttm_buffer_object { struct list_head lru; struct list_head ddestroy; struct list_head swap; - struct list_head io_reserve_lru; /** * Members protected by a bo reservation. diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index bc8d0ebb7568..9744ed9d677e 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -441,11 +441,6 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo); */ void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo); -int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo); -void ttm_mem_io_free_vm(struct ttm_buffer_object *bo); -int ttm_mem_io_lock(struct ttm_resource_manager *man, bool interruptible); -void ttm_mem_io_unlock(struct ttm_resource_manager *man); - /** * ttm_bo_reserve: * diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 6d4226190480..406baa8f0068 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -113,10 +113,6 @@ struct ttm_resource_manager_func { * @default_caching: The default caching policy used for a buffer object * placed in this memory type if the user doesn't provide one. * @func: structure pointer implementing the range manager. See above - * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures - * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions - * reserved by the TTM vm system. - * @io_reserve_lru: Optional lru list for unreserving io mem regions. * @move_lock: lock for move fence * static information. bdev::driver::io_mem_free is never used. * @lru: The lru list for this memory type. @@ -134,16 +130,8 @@ struct ttm_resource_manager { uint32_t available_caching; uint32_t default_caching; const struct ttm_resource_manager_func *func; - struct mutex io_reserve_mutex; - bool use_io_reserve_lru; spinlock_t move_lock; - /* - * Protected by @io_reserve_mutex: - */ - - struct list_head io_reserve_lru; - /* * Protected by the global->lru_lock. */ @@ -163,8 +151,6 @@ struct ttm_resource_manager { * @base: bus base address * @is_iomem: is this io memory ? * @offset: offset from the base address - * @io_reserved_vm: The VM system has a refcount in @io_reserved_count - * @io_reserved_count: Refcounting the numbers of callers to ttm_mem_io_reserve * * Structure indicating the bus placement of an object. */ @@ -173,8 +159,6 @@ struct ttm_bus_placement { phys_addr_t base; unsigned long offset; bool is_iomem; - bool io_reserved_vm; - uint64_t io_reserved_count; }; /** -- cgit v1.2.3 From 63642595a78da42f841fabcc3f309f4c1362dc40 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 31 Aug 2020 21:43:17 +0800 Subject: soundwire: add definition for maximum number of ports A Device may have at most 15 physical ports (DP0, DP1..DP14). Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Guennadi Liakhovetski Link: https://lore.kernel.org/r/20200831134318.11443-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 76052f12c9f7..0aa4c6af7554 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -38,7 +38,8 @@ struct sdw_slave; #define SDW_FRAME_CTRL_BITS 48 #define SDW_MAX_DEVICES 11 -#define SDW_VALID_PORT_RANGE(n) ((n) <= 14 && (n) >= 1) +#define SDW_MAX_PORTS 15 +#define SDW_VALID_PORT_RANGE(n) ((n) < SDW_MAX_PORTS && (n) >= 1) enum { SDW_PORT_DIRN_SINK = 0, -- cgit v1.2.3 From 6073755886a463a7a7aecdd0abb32a1d38bdb7e6 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 31 Aug 2020 21:43:18 +0800 Subject: soundwire: fix port_ready[] dynamic allocation in mipi_disco The existing code allocates memory for the total number of ports. This only works if the ports are contiguous, but will break if e.g. a Devices uses port0, 1, and 14. The port_ready[] array would contain 3 elements, which would lead to an out-of-bounds access. Conversely in other cases, the wrong port index would be used leading to timeouts on prepare. This can be fixed by allocating for the worst-case of 15 ports (DP0..DP14). In addition since the number is now fixed, we can use an array instead of a dynamic allocation. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Guennadi Liakhovetski Link: https://lore.kernel.org/r/20200831134318.11443-4-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 0aa4c6af7554..63e71645fd13 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -619,7 +619,7 @@ struct sdw_slave { struct dentry *debugfs; #endif struct list_head node; - struct completion *port_ready; + struct completion port_ready[SDW_MAX_PORTS]; enum sdw_clk_stop_mode curr_clk_stop_mode; u16 dev_num; u16 dev_num_sticky; -- cgit v1.2.3 From 88d7c71ea5b29b322d9c72103a196234cb5040db Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 1 Sep 2020 23:05:51 +0800 Subject: soundwire: bus: update multi-link definition with hw sync details Hardware-based synchronization is typically required when the bus->multi_link flag is set. On Intel platforms, when the Cadence IP is configured in 'Multi Master Mode', the hardware synchronization is required even when a stream only uses a single segment. The existing code only deal with hardware synchronization when a stream uses more than one segment so to remain backwards compatible we add a configuration threshold. For Intel cases this threshold will be set to one, other platforms may be able to use the SSP-based sync in those cases. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200901150556.19432-6-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 63e71645fd13..78f52cdeb2c9 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -828,6 +828,11 @@ struct sdw_master_ops { * @multi_link: Store bus property that indicates if multi links * are supported. This flag is populated by drivers after reading * appropriate firmware (ACPI/DT). + * @hw_sync_min_links: Number of links used by a stream above which + * hardware-based synchronization is required. This value is only + * meaningful if multi_link is set. If set to 1, hardware-based + * synchronization will be used even if a stream only uses a single + * SoundWire segment. */ struct sdw_bus { struct device *dev; @@ -851,6 +856,7 @@ struct sdw_bus { unsigned int clk_stop_timeout; u32 bank_switch_timeout; bool multi_link; + int hw_sync_min_links; }; int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, -- cgit v1.2.3 From 528222d853f9283110f0118dd71d9f0ad686d586 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sun, 23 Aug 2020 19:23:05 +0200 Subject: media: rc: harmonize infrared durations to microseconds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rc-core kapi uses nanoseconds for infrared durations for receiving, and microseconds for sending. The uapi already uses microseconds for both, so this patch does not change the uapi. Infrared durations do not need nanosecond resolution. IR protocols do not have durations shorter than about 100 microseconds. Some IR hardware offers 250 microseconds resolution, which is sufficient for most protocols. Better hardware has 50 microsecond resolution and is enough for every protocol I am aware off. Unify on microseconds everywhere. This simplifies the code since less conversion between microseconds and nanoseconds needs to be done. This affects: - rx_resolution member of struct rc_dev - timeout member of struct rc_dev - duration member in struct ir_raw_event Cc: "Bruno Prémont" Cc: Hans Verkuil Cc: Maxim Levitsky Cc: Patrick Lerda Cc: Kevin Hilman Cc: Neil Armstrong Cc: Jerome Brunet Cc: Martin Blumenstingl Cc: Sean Wang Cc: Matthias Brugger Cc: Patrice Chotard Cc: Maxime Ripard Cc: Chen-Yu Tsai Cc: "David Härdeman" Cc: Benjamin Valentin Cc: Antti Palosaari Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-core.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/rc-core.h b/include/media/rc-core.h index d3f85df64bb2..a1019c4ab5e8 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -128,8 +128,8 @@ struct lirc_fh { * @timeout: optional time after which device stops sending data * @min_timeout: minimum timeout supported by device * @max_timeout: maximum timeout supported by device - * @rx_resolution : resolution (in ns) of input sampler - * @tx_resolution: resolution (in ns) of output sampler + * @rx_resolution : resolution (in us) of input sampler + * @tx_resolution: resolution (in us) of output sampler * @lirc_dev: lirc device * @lirc_cdev: lirc char cdev * @gap_start: time when gap starts @@ -157,7 +157,7 @@ struct lirc_fh { * @s_wakeup_filter: set the wakeup scancode filter. If the mask is zero * then wakeup should be disabled. wakeup_protocol will be set to * a valid protocol if mask is nonzero. - * @s_timeout: set hardware timeout in ns + * @s_timeout: set hardware timeout in us */ struct rc_dev { struct device dev; @@ -309,11 +309,10 @@ struct ir_raw_event { unsigned carrier_report:1; }; -#define IR_DEFAULT_TIMEOUT MS_TO_NS(125) -#define IR_MAX_DURATION 500000000 /* 500 ms */ #define US_TO_NS(usec) ((usec) * 1000) #define MS_TO_US(msec) ((msec) * 1000) -#define MS_TO_NS(msec) ((msec) * 1000 * 1000) +#define IR_MAX_DURATION MS_TO_US(500) +#define IR_DEFAULT_TIMEOUT MS_TO_US(125) void ir_raw_event_handle(struct rc_dev *dev); int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev); -- cgit v1.2.3 From 4c8e84b8876dc726a7e5327b3113d75423c46728 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 2 Sep 2020 09:26:27 +0200 Subject: drm/managed: Cleanup of unused functions and polishing docs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Following functions are only used internally, not by drivers: - devm_drm_dev_init Also, now that we have a very slick and polished way to allocate a drm_device with devm_drm_dev_alloc, update all the docs to reflect the new reality. Mostly this consists of deleting old and misleading hints. Two main ones: - it is no longer required that the drm_device base class is first in the structure. devm_drm_dev_alloc can cope with it being anywhere - obviously embedded now strongly recommends using devm_drm_dev_alloc v2: Fix typos (Noralf) v3: Split out the removal of drm_dev_init, that's blocked on some discussions on how to convert vgem/vkms/i915-selftests. Adjust commit message to reflect that. Cc: Noralf Trønnes Acked-by: Noralf Trønnes (v2) Acked-by: Sam Ravnborg Cc: Luben Tuikov Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200902072627.3617301-1-daniel.vetter@ffwll.ch --- include/drm/drm_device.h | 2 +- include/drm/drm_drv.h | 16 ++++++---------- 2 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h index 0988351d743c..f4f68e7a9149 100644 --- a/include/drm/drm_device.h +++ b/include/drm/drm_device.h @@ -92,7 +92,7 @@ struct drm_device { * NULL. * * Instead of using this pointer it is recommended that drivers use - * drm_dev_init() and embed struct &drm_device in their larger + * devm_drm_dev_alloc() and embed struct &drm_device in their larger * per-device structure. */ void *dev_private; diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index 7116abc1a04e..9b11a2f0babc 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -163,13 +163,12 @@ struct drm_driver { /** * @load: * - * Backward-compatible driver callback to complete - * initialization steps after the driver is registered. For - * this reason, may suffer from race conditions and its use is - * deprecated for new drivers. It is therefore only supported - * for existing drivers not yet converted to the new scheme. - * See drm_dev_init() and drm_dev_register() for proper and - * race-free way to set up a &struct drm_device. + * Backward-compatible driver callback to complete initialization steps + * after the driver is registered. For this reason, may suffer from + * race conditions and its use is deprecated for new drivers. It is + * therefore only supported for existing drivers not yet converted to + * the new scheme. See devm_drm_dev_alloc() and drm_dev_register() for + * proper and race-free way to set up a &struct drm_device. * * This is deprecated, do not use! * @@ -592,9 +591,6 @@ struct drm_driver { int drm_dev_init(struct drm_device *dev, struct drm_driver *driver, struct device *parent); -int devm_drm_dev_init(struct device *parent, - struct drm_device *dev, - struct drm_driver *driver); void *__devm_drm_dev_alloc(struct device *parent, struct drm_driver *driver, size_t size, size_t offset); -- cgit v1.2.3 From 1e9d90dbed120ec98517428ffff4dacd9797e39d Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 1 Sep 2020 15:16:45 -0700 Subject: dma-mapping: introduce dma_get_seg_boundary_nr_pages() We found that callers of dma_get_seg_boundary mostly do an ALIGN with page mask and then do a page shift to get number of pages: ALIGN(boundary + 1, 1 << shift) >> shift However, the boundary might be as large as ULONG_MAX, which means that a device has no specific boundary limit. So either "+ 1" or passing it to ALIGN() would potentially overflow. According to kernel defines: #define ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define ALIGN(x, a) ALIGN_MASK(x, (typeof(x))(a) - 1) We can simplify the logic here into a helper function doing: ALIGN(boundary + 1, 1 << shift) >> shift = ALIGN_MASK(b + 1, (1 << s) - 1) >> s = {[b + 1 + (1 << s) - 1] & ~[(1 << s) - 1]} >> s = [b + 1 + (1 << s) - 1] >> s = [b + (1 << s)] >> s = (b >> s) + 1 This patch introduces and applies dma_get_seg_boundary_nr_pages() as an overflow-free helper for the dma_get_seg_boundary() callers to get numbers of pages. It also takes care of the NULL dev case for non-DMA API callers. Suggested-by: Christoph Hellwig Signed-off-by: Nicolin Chen Acked-by: Niklas Schnelle Acked-by: Michael Ellerman (powerpc) Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 52635e91143b..faab0a8210b9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -632,6 +632,25 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev) return DMA_BIT_MASK(32); } +/** + * dma_get_seg_boundary_nr_pages - return the segment boundary in "page" units + * @dev: device to guery the boundary for + * @page_shift: ilog() of the IOMMU page size + * + * Return the segment boundary in IOMMU page units (which may be different from + * the CPU page size) for the passed in device. + * + * If @dev is NULL a boundary of U32_MAX is assumed, this case is just for + * non-DMA API callers. + */ +static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev, + unsigned int page_shift) +{ + if (!dev) + return (U32_MAX >> page_shift) + 1; + return (dma_get_seg_boundary(dev) >> page_shift) + 1; +} + static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) { if (dev->dma_parms) { -- cgit v1.2.3 From 135ba11a7a07b4ce9197d9fa4b196329a57f1e06 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 1 Sep 2020 15:16:46 -0700 Subject: dma-mapping: set default segment_boundary_mask to ULONG_MAX The default segment_boundary_mask was set to DMA_BIT_MAKS(32) a decade ago by referencing SCSI/block subsystem, as a 32-bit mask was good enough for most of the devices. Now more and more drivers set dma_masks above DMA_BIT_MAKS(32) while only a handful of them call dma_set_seg_boundary(). This means that most drivers have a 4GB segmention boundary because DMA API returns a 32-bit default value, though they might not really have such a limit. The default segment_boundary_mask should mean "no limit" since the device doesn't explicitly set the mask. But a 32-bit mask certainly limits those devices capable of 32+ bits addressing. So this patch sets default segment_boundary_mask to ULONG_MAX. Signed-off-by: Nicolin Chen Acked-by: Niklas Schnelle Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index faab0a8210b9..df0bff2ea750 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -629,7 +629,7 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev) { if (dev->dma_parms && dev->dma_parms->segment_boundary_mask) return dev->dma_parms->segment_boundary_mask; - return DMA_BIT_MASK(32); + return ULONG_MAX; } /** -- cgit v1.2.3 From 51db1c37ee166159c5753ce8d64d6bacf113e0f0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 19 Aug 2020 23:20:19 +0800 Subject: blk-mq: Rename BLK_MQ_F_TAG_SHARED as BLK_MQ_F_TAG_QUEUE_SHARED BLK_MQ_F_TAG_SHARED actually means that tags is shared among request queues, all of which should belong to LUNs attached to same HBA. So rename it to make the point explicitly. [jpg: rebase a few times, add rnbd-clt.c change] Suggested-by: Bart Van Assche Signed-off-by: Ming Lei Signed-off-by: John Garry Tested-by: Douglas Gilbert Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 21a02e0577dd..982c4f92b63c 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -378,7 +378,7 @@ struct blk_mq_ops { enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, - BLK_MQ_F_TAG_SHARED = 1 << 1, + BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for * completing IO: -- cgit v1.2.3 From 32bc15afed04bd73e29d713d8db47818d6aa89af Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:24 +0800 Subject: blk-mq: Facilitate a shared sbitmap per tagset Some SCSI HBAs (such as HPSA, megaraid, mpt3sas, hisi_sas_v3 ..) support multiple reply queues with single hostwide tags. In addition, these drivers want to use interrupt assignment in pci_alloc_irq_vectors(PCI_IRQ_AFFINITY). However, as discussed in [0], CPU hotplug may cause in-flight IO completion to not be serviced when an interrupt is shutdown. That problem is solved in commit bf0beec0607d ("blk-mq: drain I/O when all CPUs in a hctx are offline"). However, to take advantage of that blk-mq feature, the HBA HW queuess are required to be mapped to that of the blk-mq hctx's; to do that, the HBA HW queues need to be exposed to the upper layer. In making that transition, the per-SCSI command request tags are no longer unique per Scsi host - they are just unique per hctx. As such, the HBA LLDD would have to generate this tag internally, which has a certain performance overhead. However another problem is that blk-mq assumes the host may accept (Scsi_host.can_queue * #hw queue) commands. In commit 6eb045e092ef ("scsi: core: avoid host-wide host_busy counter for scsi_mq"), the Scsi host busy counter was removed, which would stop the LLDD being sent more than .can_queue commands; however, it should still be ensured that the block layer does not issue more than .can_queue commands to the Scsi host. To solve this problem, introduce a shared sbitmap per blk_mq_tag_set, which may be requested at init time. New flag BLK_MQ_F_TAG_HCTX_SHARED should be set when requesting the tagset to indicate whether the shared sbitmap should be used. Even when BLK_MQ_F_TAG_HCTX_SHARED is set, a full set of tags and requests are still allocated per hctx; the reason for this is that if tags and requests were only allocated for a single hctx - like hctx0 - it may break block drivers which expect a request be associated with a specific hctx, i.e. not always hctx0. This will introduce extra memory usage. This change is based on work originally from Ming Lei in [1] and from Bart's suggestion in [2]. [0] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/ [1] https://lore.kernel.org/linux-block/20190531022801.10003-1-ming.lei@redhat.com/ [2] https://lore.kernel.org/linux-block/ff77beff-5fd9-9f05-12b6-826922bace1f@huawei.com/T/#m3db0a602f095cbcbff27e9c884d6b4ae826144be Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 982c4f92b63c..df7b903ce7ae 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -231,6 +231,9 @@ enum hctx_type { * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. + * @__bitmap_tags: A shared tags sbitmap, used over all hctx's + * @__breserved_tags: + * A shared reserved tags sbitmap, used over all hctx's * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @tag_list_lock: Serializes tag_list accesses. @@ -250,6 +253,8 @@ struct blk_mq_tag_set { unsigned int flags; void *driver_data; + struct sbitmap_queue __bitmap_tags; + struct sbitmap_queue __breserved_tags; struct blk_mq_tags **tags; struct mutex tag_list_lock; @@ -384,6 +389,7 @@ enum { * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, + BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 5, BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, -- cgit v1.2.3 From bccf5e26d99c28980bd6ced474422a1b18402263 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:26 +0800 Subject: blk-mq: Record nr_active_requests per queue for when using shared sbitmap The per-hctx nr_active value can no longer be used to fairly assign a share of tag depth per request queue for when using a shared sbitmap, as it does not consider that the tags are shared tags over all hctx's. For this case, record the nr_active_requests per request_queue, and make the judgement based on that value. Co-developed-with: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d0d61bc81615..6277aee2aeaa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -485,6 +485,8 @@ struct request_queue { struct timer_list timeout; struct work_struct timeout_work; + atomic_t nr_active_requests_shared_sbitmap; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); -- cgit v1.2.3 From f1b49fdc1c64db110aa1315831e5fe0f8599fa56 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:27 +0800 Subject: blk-mq: Record active_queues_shared_sbitmap per tag_set for when using shared sbitmap For when using a shared sbitmap, no longer should the number of active request queues per hctx be relied on for when judging how to share the tag bitmap. Instead maintain the number of active request queues per tag_set, and make the judgement based on that. Originally-from: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + include/linux/blkdev.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index df7b903ce7ae..8279c807e1f3 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -252,6 +252,7 @@ struct blk_mq_tag_set { unsigned int timeout; unsigned int flags; void *driver_data; + atomic_t active_queues_shared_sbitmap; struct sbitmap_queue __bitmap_tags; struct sbitmap_queue __breserved_tags; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6277aee2aeaa..7d82959e7b86 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -618,6 +618,7 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ +#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP)) -- cgit v1.2.3 From b445547ec1bbd3e7bf4b1c142550942f70527d95 Mon Sep 17 00:00:00 2001 From: Kashyap Desai Date: Wed, 19 Aug 2020 23:20:28 +0800 Subject: blk-mq, elevator: Count requests per hctx to improve performance High CPU utilization on "native_queued_spin_lock_slowpath" due to lock contention is possible for mq-deadline and bfq IO schedulers when nr_hw_queues is more than one. It is because kblockd work queue can submit IO from all online CPUs (through blk_mq_run_hw_queues()) even though only one hctx has pending commands. The elevator callback .has_work for mq-deadline and bfq scheduler considers pending work if there are any IOs on request queue but it does not account hctx context. Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering the elevator even though there are no requests queued. [jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap] Signed-off-by: Kashyap Desai Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8279c807e1f3..b23eeca4d677 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -139,6 +139,10 @@ struct blk_mq_hw_ctx { * shared across request queues. */ atomic_t nr_active; + /** + * @elevator_queued: Number of queued requests on hctx. + */ + atomic_t elevator_queued; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; -- cgit v1.2.3 From c1077616142907bb6ee987ecd136d6857ffd8787 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 1 Sep 2020 15:10:08 -0700 Subject: ip: expose inet sockopts through inet_diag Expose all exisiting inet sockopt bits through inet_diag for debug purpose. Corresponding changes in iproute2 ss will be submitted to output all these values. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 2 ++ include/uapi/linux/inet_diag.h | 18 ++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 0ef2d800fda7..84abb30a3fbb 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -75,6 +75,8 @@ static inline size_t inet_diag_msg_attrs_size(void) #ifdef CONFIG_SOCK_CGROUP_DATA + nla_total_size_64bit(sizeof(u64)) /* INET_DIAG_CGROUP_ID */ #endif + + nla_total_size(sizeof(struct inet_diag_sockopt)) + /* INET_DIAG_SOCKOPT */ ; } int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 5ba122c1949a..20ee93f0f876 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -160,6 +160,7 @@ enum { INET_DIAG_ULP_INFO, INET_DIAG_SK_BPF_STORAGES, INET_DIAG_CGROUP_ID, + INET_DIAG_SOCKOPT, __INET_DIAG_MAX, }; @@ -183,6 +184,23 @@ struct inet_diag_meminfo { __u32 idiag_tmem; }; +/* INET_DIAG_SOCKOPT */ + +struct inet_diag_sockopt { + __u8 recverr:1, + is_icsk:1, + freebind:1, + hdrincl:1, + mc_loop:1, + transparent:1, + mc_all:1, + nodefrag:1; + __u8 bind_address_no_port:1, + recverr_rfc4884:1, + defer_connect:1, + unused:5; +}; + /* INET_DIAG_VEGASINFO */ struct tcpvegas_info { -- cgit v1.2.3 From fd5a13f4893c8df2a5a3af8599adecb52d05fe89 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Sep 2020 16:22:31 +0200 Subject: proc: add a read_iter method to proc proc_ops This will allow proc files to implement iter read semantics. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/proc_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2df965cd0974..270cab43ca3d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -30,6 +30,7 @@ struct proc_ops { unsigned int proc_flags; int (*proc_open)(struct inode *, struct file *); ssize_t (*proc_read)(struct file *, char __user *, size_t, loff_t *); + ssize_t (*proc_read_iter)(struct kiocb *, struct iov_iter *); ssize_t (*proc_write)(struct file *, const char __user *, size_t, loff_t *); loff_t (*proc_lseek)(struct file *, loff_t, int); int (*proc_release)(struct inode *, struct file *); -- cgit v1.2.3 From d1c6c4a9fd3da5c735386b0cdb44d79667f10a1b Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 2 Sep 2020 17:07:55 +0300 Subject: ASoC: SOF: support topology components on secondary cores Currently SOF supports running pipelines on secondary DSP cores in a limited way. This patch represents the next step in SOF multi-core DSP support, it adds checks for core ID to individual topology components. It takes care to power up all the requested cores. More advanced DSP core power management should be added in the future. Signed-off-by: Pan Xiuli Signed-off-by: Guennadi Liakhovetski Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200902140756.1427005-3-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/sof/tokens.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index 5941e2eb1588..37f5aaa09c2b 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -73,6 +73,7 @@ /* Token retired with ABI 3.2, do not use for new capabilities * #define SOF_TKN_COMP_PRELOAD_COUNT 403 */ +#define SOF_TKN_COMP_CORE_ID 404 /* SSP */ #define SOF_TKN_INTEL_SSP_CLKS_CONTROL 500 -- cgit v1.2.3 From aae4c8e27bd7567132bb931488e2faf1a57c66e9 Mon Sep 17 00:00:00 2001 From: Tom Murphy Date: Mon, 17 Aug 2020 22:00:49 +0100 Subject: iommu: Rename iommu_tlb_* functions to iommu_iotlb_* To keep naming consistent we should stick with *iotlb*. This patch renames a few remaining functions. Signed-off-by: Tom Murphy Link: https://lore.kernel.org/r/20200817210051.13546-1-murphyt7@tcd.ie Signed-off-by: Joerg Roedel --- include/linux/io-pgtable.h | 2 +- include/linux/iommu.h | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 23285ba645db..4cde111e425b 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -31,7 +31,7 @@ enum io_pgtable_fmt { * single page. IOMMUs that cannot batch TLB invalidation * operations efficiently will typically issue them here, but * others may decide to update the iommu_iotlb_gather structure - * and defer the invalidation until iommu_tlb_sync() instead. + * and defer the invalidation until iommu_iotlb_sync() instead. * * Note that these can all be called in atomic context and must therefore * not block. diff --git a/include/linux/iommu.h b/include/linux/iommu.h index fee209efb756..2ad26d8b4ab9 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -514,13 +514,13 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); -static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) { if (domain->ops->flush_iotlb_all) domain->ops->flush_iotlb_all(domain); } -static inline void iommu_tlb_sync(struct iommu_domain *domain, +static inline void iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { if (domain->ops->iotlb_sync) @@ -543,7 +543,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, if (gather->pgsize != size || end < gather->start || start > gather->end) { if (gather->pgsize) - iommu_tlb_sync(domain, gather); + iommu_iotlb_sync(domain, gather); gather->pgsize = size; } @@ -725,11 +725,11 @@ static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain, return 0; } -static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) { } -static inline void iommu_tlb_sync(struct iommu_domain *domain, +static inline void iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { } -- cgit v1.2.3 From 25e804926da39f1de7ae486920bfe65b099195f1 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 3 Sep 2020 17:14:56 +0530 Subject: soundwire: define and use addr bit masks Soundwire addr is a 52bit value encoding link, version, unique id, mfg id, part id and class id. Define bit masks for these and use FIELD_GET() to extract these fields. Signed-off-by: Vinod Koul Tested-by: Bard Liao Link: https://lore.kernel.org/r/20200903114504.1202143-2-vkoul@kernel.org Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 78f52cdeb2c9..1e9010c139f0 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -5,6 +5,7 @@ #define __SOUNDWIRE_H #include +#include struct sdw_bus; struct sdw_slave; @@ -456,13 +457,19 @@ struct sdw_slave_id { * * The MIPI DisCo for SoundWire defines in addition the link_id as bits 51:48 */ - -#define SDW_DISCO_LINK_ID(adr) (((adr) >> 48) & GENMASK(3, 0)) -#define SDW_VERSION(adr) (((adr) >> 44) & GENMASK(3, 0)) -#define SDW_UNIQUE_ID(adr) (((adr) >> 40) & GENMASK(3, 0)) -#define SDW_MFG_ID(adr) (((adr) >> 24) & GENMASK(15, 0)) -#define SDW_PART_ID(adr) (((adr) >> 8) & GENMASK(15, 0)) -#define SDW_CLASS_ID(adr) ((adr) & GENMASK(7, 0)) +#define SDW_DISCO_LINK_ID_MASK GENMASK_ULL(51, 48) +#define SDW_VERSION_MASK GENMASK_ULL(47, 44) +#define SDW_UNIQUE_ID_MASK GENMASK_ULL(43, 40) +#define SDW_MFG_ID_MASK GENMASK_ULL(39, 24) +#define SDW_PART_ID_MASK GENMASK_ULL(23, 8) +#define SDW_CLASS_ID_MASK GENMASK_ULL(7, 0) + +#define SDW_DISCO_LINK_ID(addr) FIELD_GET(SDW_DISCO_LINK_ID_MASK, addr) +#define SDW_VERSION(addr) FIELD_GET(SDW_VERSION_MASK, addr) +#define SDW_UNIQUE_ID(addr) FIELD_GET(SDW_UNIQUE_ID_MASK, addr) +#define SDW_MFG_ID(addr) FIELD_GET(SDW_MFG_ID_MASK, addr) +#define SDW_PART_ID(addr) FIELD_GET(SDW_PART_ID_MASK, addr) +#define SDW_CLASS_ID(addr) FIELD_GET(SDW_CLASS_ID_MASK, addr) /** * struct sdw_slave_intr_status - Slave interrupt status -- cgit v1.2.3 From 8be2f84acf2317068c93fea291d823ac30d172d6 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 3 Sep 2020 17:15:04 +0530 Subject: soundwire: remove SDW_REG_SHIFT() soundwire had defined SDW_REG_SHIFT to calculate shift values for bitmasks, but now that we have better things in bitfield.h, remove this. Signed-off-by: Vinod Koul Tested-by: Bard Liao Link: https://lore.kernel.org/r/20200903114504.1202143-10-vkoul@kernel.org Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_registers.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index 5d3c271af7d1..f420e8059779 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -4,13 +4,6 @@ #ifndef __SDW_REGISTERS_H #define __SDW_REGISTERS_H -/* - * typically we define register and shifts but if one observes carefully, - * the shift can be generated from MASKS using few bit primitaives like ffs - * etc, so we use that and avoid defining shifts - */ -#define SDW_REG_SHIFT(n) (ffs(n) - 1) - /* * SDW registers as defined by MIPI 1.2 Spec */ -- cgit v1.2.3 From c7eb900f5f45eeab1ea1bed997a2a12d8b5907bc Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 28 Aug 2020 19:12:11 +0300 Subject: iommu/vt-d: Move intel_iommu_gfx_mapped to Intel IOMMU header Static analyzer is not happy about intel_iommu_gfx_mapped declaration: .../drivers/iommu/intel/iommu.c:364:5: warning: symbol 'intel_iommu_gfx_mapped' was not declared. Should it be static? Move its declaration to Intel IOMMU header file. Signed-off-by: Andy Shevchenko Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20200828161212.71294-1-andriy.shevchenko@linux.intel.com Signed-off-by: Joerg Roedel --- include/drm/intel-gtt.h | 5 +---- include/linux/intel-iommu.h | 1 + 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index 71d81923e6b0..abfefaaf897a 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -5,6 +5,7 @@ #define _DRM_INTEL_GTT_H #include +#include #include void intel_gtt_get(u64 *gtt_total, @@ -33,8 +34,4 @@ void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries); /* flag for GFDT type */ #define AGP_USER_CACHED_MEMORY_GFDT (1 << 3) -#ifdef CONFIG_INTEL_IOMMU -extern int intel_iommu_gfx_mapped; -#endif - #endif diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b1ed2f25f7c0..6a3ddaabf3f5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -792,6 +792,7 @@ extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; extern int intel_iommu_enabled; extern int intel_iommu_tboot_noforce; +extern int intel_iommu_gfx_mapped; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) { -- cgit v1.2.3 From 6da73d15258a1e5e86d03d4ffba8776d17a8a287 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 2 Sep 2020 12:21:27 +0200 Subject: pidfd: support PIDFD_NONBLOCK in pidfd_open() Introduce PIDFD_NONBLOCK to support non-blocking pidfd file descriptors. Ever since the introduction of pidfds and more advanced async io various programming languages such as Rust have grown support for async event libraries. These libraries are created to help build epoll-based event loops around file descriptors. A common pattern is to automatically make all file descriptors they manage to O_NONBLOCK. For such libraries the EAGAIN error code is treated specially. When a function is called that returns EAGAIN the function isn't called again until the event loop indicates the the file descriptor is ready. Supporting EAGAIN when waiting on pidfds makes such libraries just work with little effort. In the following patch we will extend waitid() internally to support non-blocking pidfds. This introduces a new flag PIDFD_NONBLOCK that is equivalent to O_NONBLOCK. This follows the same patterns we have for other (anon inode) file descriptors such as EFD_NONBLOCK, IN_NONBLOCK, SFD_NONBLOCK, TFD_NONBLOCK and the same for close-on-exec flags. Suggested-by: Josh Triplett Signed-off-by: Christian Brauner Reviewed-by: Josh Triplett Reviewed-by: Oleg Nesterov Cc: Kees Cook Cc: Sargun Dhillon Cc: Oleg Nesterov Link: https://lore.kernel.org/lkml/20200811181236.GA18763@localhost/ Link: https://github.com/joshtriplett/async-pidfd Link: https://lore.kernel.org/r/20200902102130.147672-2-christian.brauner@ubuntu.com --- include/uapi/linux/pidfd.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 include/uapi/linux/pidfd.h (limited to 'include') diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h new file mode 100644 index 000000000000..5406fbc13074 --- /dev/null +++ b/include/uapi/linux/pidfd.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_PIDFD_H +#define _UAPI_LINUX_PIDFD_H + +#include +#include + +/* Flags for pidfd_open(). */ +#define PIDFD_NONBLOCK O_NONBLOCK + +#endif /* _UAPI_LINUX_PIDFD_H */ -- cgit v1.2.3 From c2c59456e1fcad3f464761c5839399176e3a934a Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Fri, 4 Sep 2020 18:40:38 +0800 Subject: iommu/mediatek: Check 4GB mode by reading infracfg In previous discussion [1] and [2], we found that it is risky to use max_pfn or totalram_pages to tell if 4GB mode is enabled. Check 4GB mode by reading infracfg register, remove the usage of the un-exported symbol max_pfn. This is a step towards building mtk_iommu as a kernel module. [1] https://lore.kernel.org/lkml/20200603161132.2441-1-miles.chen@mediatek.com/ [2] https://lore.kernel.org/lkml/20200604080120.2628-1-miles.chen@mediatek.com/ [3] https://lore.kernel.org/lkml/20200715205120.GA778876@bogus/ Cc: Mike Rapoport Cc: David Hildenbrand Cc: Yong Wu Cc: Yingjoe Chen Cc: Christoph Hellwig Cc: Rob Herring Cc: Matthias Brugger Cc: Joerg Roedel Reviewed-by: Matthias Brugger Signed-off-by: Miles Chen Link: https://lore.kernel.org/r/20200904104038.4979-1-miles.chen@mediatek.com Signed-off-by: Joerg Roedel --- include/linux/soc/mediatek/infracfg.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index fd25f0148566..233463d789c6 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -32,6 +32,9 @@ #define MT7622_TOP_AXI_PROT_EN_WB (BIT(2) | BIT(6) | \ BIT(7) | BIT(8)) +#define REG_INFRA_MISC 0xf00 +#define F_DDR_4GB_SUPPORT_EN BIT(13) + int mtk_infracfg_set_bus_protection(struct regmap *infracfg, u32 mask, bool reg_update); int mtk_infracfg_clear_bus_protection(struct regmap *infracfg, u32 mask, -- cgit v1.2.3 From 74f1082487feb90bbf880af14beb8e29c3030c9f Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Wed, 7 Aug 2019 12:21:05 +0100 Subject: arm64: mte: Add specific SIGSEGV codes Add MTE-specific SIGSEGV codes to siginfo.h and update the x86 BUILD_BUG_ON(NSIGSEGV != 7) compile check. Signed-off-by: Vincenzo Frascino [catalin.marinas@arm.com: renamed precise/imprecise to sync/async] [catalin.marinas@arm.com: dropped #ifdef __aarch64__, renumbered] Signed-off-by: Catalin Marinas Acked-by: "Eric W. Biederman" Cc: Arnd Bergmann Cc: Will Deacon --- include/uapi/asm-generic/siginfo.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index cb3d6c267181..7aacf9389010 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -229,7 +229,9 @@ typedef struct siginfo { #define SEGV_ACCADI 5 /* ADI not enabled for mapped object */ #define SEGV_ADIDERR 6 /* Disrupting MCD error */ #define SEGV_ADIPERR 7 /* Precise MCD exception */ -#define NSIGSEGV 7 +#define SEGV_MTEAERR 8 /* Asynchronous ARM MTE error */ +#define SEGV_MTESERR 9 /* Synchronous ARM MTE exception */ +#define NSIGSEGV 9 /* * SIGBUS si_codes -- cgit v1.2.3 From 4beba9486abd2f86d125271d6946f7c38ed0fe77 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Wed, 22 Apr 2020 15:25:27 +0100 Subject: mm: Add PG_arch_2 page flag For arm64 MTE support it is necessary to be able to mark pages that contain user space visible tags that will need to be saved/restored e.g. when swapped out. To support this add a new arch specific flag (PG_arch_2). This flag is only available on 64-bit architectures due to the limited number of spare page flags on the 32-bit ones. Signed-off-by: Steven Price [catalin.marinas@arm.com: use CONFIG_64BIT for guarding this new flag] Signed-off-by: Catalin Marinas Cc: Andrew Morton --- include/linux/kernel-page-flags.h | 1 + include/linux/page-flags.h | 3 +++ include/trace/events/mmflags.h | 9 ++++++++- 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h index abd20ef93c98..eee1877a354e 100644 --- a/include/linux/kernel-page-flags.h +++ b/include/linux/kernel-page-flags.h @@ -17,5 +17,6 @@ #define KPF_ARCH 38 #define KPF_UNCACHED 39 #define KPF_SOFTDIRTY 40 +#define KPF_ARCH_2 41 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6be1aa559b1e..276140c94f4a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -135,6 +135,9 @@ enum pageflags { #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) PG_young, PG_idle, +#endif +#ifdef CONFIG_64BIT + PG_arch_2, #endif __NR_PAGEFLAGS, diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 5fb752034386..67018d367b9f 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -79,6 +79,12 @@ #define IF_HAVE_PG_IDLE(flag,string) #endif +#ifdef CONFIG_64BIT +#define IF_HAVE_PG_ARCH_2(flag,string) ,{1UL << flag, string} +#else +#define IF_HAVE_PG_ARCH_2(flag,string) +#endif + #define __def_pageflag_names \ {1UL << PG_locked, "locked" }, \ {1UL << PG_waiters, "waiters" }, \ @@ -105,7 +111,8 @@ IF_HAVE_PG_MLOCK(PG_mlocked, "mlocked" ) \ IF_HAVE_PG_UNCACHED(PG_uncached, "uncached" ) \ IF_HAVE_PG_HWPOISON(PG_hwpoison, "hwpoison" ) \ IF_HAVE_PG_IDLE(PG_young, "young" ) \ -IF_HAVE_PG_IDLE(PG_idle, "idle" ) +IF_HAVE_PG_IDLE(PG_idle, "idle" ) \ +IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) #define show_page_flags(flags) \ (flags) ? __print_flags(flags, "|", \ -- cgit v1.2.3 From b3fbbea4c00220f62e6f7e2514466e6ee81f7f60 Mon Sep 17 00:00:00 2001 From: Kevin Brodsky Date: Mon, 25 Nov 2019 17:27:06 +0000 Subject: mm: Introduce arch_calc_vm_flag_bits() Similarly to arch_calc_vm_prot_bits(), introduce a dummy arch_calc_vm_flag_bits() invoked from calc_vm_flag_bits(). This macro can be overridden by architectures to insert specific VM_* flags derived from the mmap() MAP_* flags. Signed-off-by: Kevin Brodsky Signed-off-by: Catalin Marinas Cc: Andrew Morton --- include/linux/mman.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mman.h b/include/linux/mman.h index 6f34c33075f9..6fa15c9b12af 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -78,13 +78,18 @@ static inline void vm_unacct_memory(long pages) } /* - * Allow architectures to handle additional protection bits + * Allow architectures to handle additional protection and flag bits. The + * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif +#ifndef arch_calc_vm_flag_bits +#define arch_calc_vm_flag_bits(flags) 0 +#endif + #ifndef arch_vm_get_page_prot #define arch_vm_get_page_prot(vm_flags) __pgprot(0) #endif @@ -135,7 +140,8 @@ calc_vm_flag_bits(unsigned long flags) return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | - _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ); + _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | + arch_calc_vm_flag_bits(flags); } unsigned long vm_commit_limit(void); -- cgit v1.2.3 From 9f3419315f3cdc41a7318e4d50ba18a592b30c8c Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 27 Nov 2019 10:00:27 +0000 Subject: arm64: mte: Add PROT_MTE support to mmap() and mprotect() To enable tagging on a memory range, the user must explicitly opt in via a new PROT_MTE flag passed to mmap() or mprotect(). Since this is a new memory type in the AttrIndx field of a pte, simplify the or'ing of these bits over the protection_map[] attributes by making MT_NORMAL index 0. There are two conditions for arch_vm_get_page_prot() to return the MT_NORMAL_TAGGED memory type: (1) the user requested it via PROT_MTE, registered as VM_MTE in the vm_flags, and (2) the vma supports MTE, decided during the mmap() call (only) and registered as VM_MTE_ALLOWED. arch_calc_vm_prot_bits() is responsible for registering the user request as VM_MTE. The newly introduced arch_calc_vm_flag_bits() sets VM_MTE_ALLOWED if the mapping is MAP_ANONYMOUS. An MTE-capable filesystem (RAM-based) may be able to set VM_MTE_ALLOWED during its mmap() file ops call. In addition, update VM_DATA_DEFAULT_FLAGS to allow mprotect(PROT_MTE) on stack or brk area. The Linux mmap() syscall currently ignores unknown PROT_* flags. In the presence of MTE, an mmap(PROT_MTE) on a file which does not support MTE will not report an error and the memory will not be mapped as Normal Tagged. For consistency, mprotect(PROT_MTE) will not report an error either if the memory range does not support MTE. Two subsequent patches in the series will propose tightening of this behaviour. Co-developed-by: Vincenzo Frascino Signed-off-by: Vincenzo Frascino Signed-off-by: Catalin Marinas Cc: Will Deacon --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ca6e6a81576b..4312c6c808e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -340,6 +340,14 @@ extern unsigned int kobjsize(const void *objp); # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif +#if defined(CONFIG_ARM64_MTE) +# define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ +# define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ +#else +# define VM_MTE VM_NONE +# define VM_MTE_ALLOWED VM_NONE +#endif + #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif -- cgit v1.2.3 From c462ac288f2c97e0c1d9ff6a65955317e799f958 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 25 Nov 2019 17:27:06 +0000 Subject: mm: Introduce arch_validate_flags() Similarly to arch_validate_prot() called from do_mprotect_pkey(), an architecture may need to sanity-check the new vm_flags. Define a dummy function always returning true. In addition to do_mprotect_pkey(), also invoke it from mmap_region() prior to updating vma->vm_page_prot to allow the architecture code to veto potentially inconsistent vm_flags. Signed-off-by: Catalin Marinas Acked-by: Andrew Morton --- include/linux/mman.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/mman.h b/include/linux/mman.h index 6fa15c9b12af..629cefc4ecba 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -108,6 +108,19 @@ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) #define arch_validate_prot arch_validate_prot #endif +#ifndef arch_validate_flags +/* + * This is called from mmap() and mprotect() with the updated vma->vm_flags. + * + * Returns true if the VM_* flags are valid. + */ +static inline bool arch_validate_flags(unsigned long flags) +{ + return true; +} +#define arch_validate_flags arch_validate_flags +#endif + /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 -- cgit v1.2.3 From 1c101da8b971a36695319dce7a24711dc567a0dd Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 27 Nov 2019 10:30:15 +0000 Subject: arm64: mte: Allow user control of the tag check mode via prctl() By default, even if PROT_MTE is set on a memory range, there is no tag check fault reporting (SIGSEGV). Introduce a set of option to the exiting prctl(PR_SET_TAGGED_ADDR_CTRL) to allow user control of the tag check fault mode: PR_MTE_TCF_NONE - no reporting (default) PR_MTE_TCF_SYNC - synchronous tag check fault reporting PR_MTE_TCF_ASYNC - asynchronous tag check fault reporting These options translate into the corresponding SCTLR_EL1.TCF0 bitfield, context-switched by the kernel. Note that the kernel accesses to the user address space (e.g. read() system call) are not checked if the user thread tag checking mode is PR_MTE_TCF_NONE or PR_MTE_TCF_ASYNC. If the tag checking mode is PR_MTE_TCF_SYNC, the kernel makes a best effort to check its user address accesses, however it cannot always guarantee it. Signed-off-by: Catalin Marinas Cc: Will Deacon --- include/uapi/linux/prctl.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 07b4f8131e36..2390ab324afa 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -233,6 +233,12 @@ struct prctl_mm_map { #define PR_SET_TAGGED_ADDR_CTRL 55 #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) +/* MTE tag check fault modes */ +# define PR_MTE_TCF_SHIFT 1 +# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) /* Control reclaim behavior when allocating memory */ #define PR_SET_IO_FLUSHER 57 -- cgit v1.2.3 From af5ce95282dc99d08a27a407a02c763dde1c5558 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 10 Dec 2019 11:19:15 +0000 Subject: arm64: mte: Allow user control of the generated random tags via prctl() The IRG, ADDG and SUBG instructions insert a random tag in the resulting address. Certain tags can be excluded via the GCR_EL1.Exclude bitmap when, for example, the user wants a certain colour for freed buffers. Since the GCR_EL1 register is not accessible at EL0, extend the prctl(PR_SET_TAGGED_ADDR_CTRL) interface to include a 16-bit field in the first argument for controlling which tags can be generated by the above instruction (an include rather than exclude mask). Note that by default all non-zero tags are excluded. This setting is per-thread. Signed-off-by: Catalin Marinas Cc: Will Deacon --- include/uapi/linux/prctl.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 2390ab324afa..7f0827705c9a 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -239,6 +239,9 @@ struct prctl_mm_map { # define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) # define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) # define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) +/* MTE tag inclusion mask */ +# define PR_MTE_TAG_SHIFT 3 +# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) /* Control reclaim behavior when allocating memory */ #define PR_SET_IO_FLUSHER 57 -- cgit v1.2.3 From 2200aa7154cb7ef76bac93e98326883ba64bfa2e Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 3 Jul 2020 15:12:57 +0100 Subject: arm64: mte: ptrace: Add NT_ARM_TAGGED_ADDR_CTRL regset This regset allows read/write access to a ptraced process prctl(PR_SET_TAGGED_ADDR_CTRL) setting. Signed-off-by: Catalin Marinas Cc: Will Deacon Cc: Alan Hayward Cc: Luis Machado Cc: Omair Javaid --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 22220945a5fd..30f68b42eeb5 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -425,6 +425,7 @@ typedef struct elf64_shdr { #define NT_ARM_PAC_MASK 0x406 /* ARM pointer authentication code masks */ #define NT_ARM_PACA_KEYS 0x407 /* ARM pointer authentication address keys */ #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ +#define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From 8a84802e2a2b1a682761a31c2685506b9f4e1840 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Wed, 13 May 2020 16:37:49 +0100 Subject: mm: Add arch hooks for saving/restoring tags Arm's Memory Tagging Extension (MTE) adds some metadata (tags) to every physical page, when swapping pages out to disk it is necessary to save these tags, and later restore them when reading the pages back. Add some hooks along with dummy implementations to enable the arch code to handle this. Three new hooks are added to the swap code: * arch_prepare_to_swap() and * arch_swap_invalidate_page() / arch_swap_invalidate_area(). One new hook is added to shmem: * arch_swap_restore() Signed-off-by: Steven Price [catalin.marinas@arm.com: add unlock_page() on the error path] [catalin.marinas@arm.com: dropped the _tags suffix] Signed-off-by: Catalin Marinas Acked-by: Andrew Morton --- include/linux/pgtable.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e8cbc2e795d5..dc3b74129fbc 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -633,6 +633,34 @@ static inline int arch_unmap_one(struct mm_struct *mm, } #endif +/* + * Allow architectures to preserve additional metadata associated with + * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function + * prototypes must be defined in the arch-specific asm/pgtable.h file. + */ +#ifndef __HAVE_ARCH_PREPARE_TO_SWAP +static inline int arch_prepare_to_swap(struct page *page) +{ + return 0; +} +#endif + +#ifndef __HAVE_ARCH_SWAP_INVALIDATE +static inline void arch_swap_invalidate_page(int type, pgoff_t offset) +{ +} + +static inline void arch_swap_invalidate_area(int type) +{ +} +#endif + +#ifndef __HAVE_ARCH_SWAP_RESTORE +static inline void arch_swap_restore(swp_entry_t entry, struct page *page) +{ +} +#endif + #ifndef __HAVE_ARCH_PGD_OFFSET_GATE #define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) #endif -- cgit v1.2.3 From a2d375eda771a6a4866f3717a8ed81b63acb1dbd Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Mon, 31 Aug 2020 12:22:09 -0600 Subject: dyndbg: refine export, rename to dynamic_debug_exec_queries() commit 4c0d77828d4f ("dyndbg: export ddebug_exec_queries") had a few problems: - broken non DYNAMIC_DEBUG_CORE configs, sparse warning - the exported function modifies query string, breaks on RO strings. - func name follows internal convention, shouldn't be exposed as is. 1st is fixed in header with ifdefd function prototype or stub defn. Also remove an obsolete HAVE-symbol ifdef-comment, and add others. Fix others by wrapping existing internal function with a new one, named in accordance with module-prefix naming convention, before export hits v5.9.0. In new function, copy query string to a local buffer, so users can pass hard-coded/RO queries, and internal function can be used unchanged. Fixes: 4c0d77828d4f ("dyndbg: export ddebug_exec_queries") Signed-off-by: Jim Cromie Link: https://lore.kernel.org/r/20200831182210.850852-3-jim.cromie@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/dynamic_debug.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index aa9ff9e1c0b3..8aa0c7c2608c 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -49,6 +49,10 @@ struct _ddebug { #if defined(CONFIG_DYNAMIC_DEBUG_CORE) + +/* exported for module authors to exercise >control */ +int dynamic_debug_exec_queries(const char *query, const char *modname); + int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname); extern int ddebug_remove_module(const char *mod_name); @@ -105,7 +109,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, static_branch_unlikely(&descriptor.key.dd_key_false) #endif -#else /* !HAVE_JUMP_LABEL */ +#else /* !CONFIG_JUMP_LABEL */ #define _DPRINTK_KEY_INIT @@ -117,7 +121,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) #endif -#endif +#endif /* CONFIG_JUMP_LABEL */ #define __dynamic_func_call(id, fmt, func, ...) do { \ DEFINE_DYNAMIC_DEBUG_METADATA(id, fmt); \ @@ -172,10 +176,11 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) -#else +#else /* !CONFIG_DYNAMIC_DEBUG_CORE */ #include #include +#include static inline int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname) @@ -210,6 +215,13 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii); \ } while (0) -#endif + +static inline int dynamic_debug_exec_queries(const char *query, const char *modname) +{ + pr_warn("kernel not built with CONFIG_DYNAMIC_DEBUG_CORE\n"); + return 0; +} + +#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ #endif -- cgit v1.2.3 From e48c15b796d412ede883bb2ef7779b2a142f7962 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 29 Jun 2020 17:21:32 -0700 Subject: smp: Add source and destination CPUs to __call_single_data This commit adds a destination CPU to __call_single_data, and is inspired by an earlier commit by Peter Zijlstra. This version adds #ifdef to permit use by 32-bit systems and supplying the destination CPU for all smp_call_function*() requests, not just smp_call_function_single(). If need be, 32-bit systems could be accommodated by shrinking the flags field to 16 bits (the atomic_t variant is currently unused) and by providing only eight bits for CPU on such systems. It is not clear that the addition of the fields to __call_single_node are really needed. [ paulmck: Apply Boqun Feng feedback on 32-bit builds. ] Link: https://lore.kernel.org/lkml/20200615164048.GC2531@hirez.programming.kicks-ass.net/ Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/smp.h | 3 +++ include/linux/smp_types.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/smp.h b/include/linux/smp.h index 80d557ef8a11..9f13966d3d92 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -26,6 +26,9 @@ struct __call_single_data { struct { struct llist_node llist; unsigned int flags; +#ifdef CONFIG_64BIT + u16 src, dst; +#endif }; }; smp_call_func_t func; diff --git a/include/linux/smp_types.h b/include/linux/smp_types.h index 364b3ae3e41d..2e8461af8df6 100644 --- a/include/linux/smp_types.h +++ b/include/linux/smp_types.h @@ -61,6 +61,9 @@ struct __call_single_node { unsigned int u_flags; atomic_t a_flags; }; +#ifdef CONFIG_64BIT + u16 src, dst; +#endif }; #endif /* __LINUX_SMP_TYPES_H */ -- cgit v1.2.3 From 0f7c5317b89058e432d3e97efa19467ff4c3b86b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 4 Sep 2020 14:37:29 -0700 Subject: of: Export of_remove_property() to modules We will need to remove some OF properties in drivers/net/dsa/bcm_sf2.c with a subsequent commit. Export of_remove_property() to modules so we can keep bcm_sf2 modular and provide an empty stub for when CONFIG_OF is disabled to maintain the ability to compile test. Signed-off-by: Florian Fainelli Acked-by: Rob Herring Signed-off-by: Jakub Kicinski --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 5cf7ae0465d1..481ec0467285 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -929,6 +929,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_remove_property(struct device_node *np, struct property *prop) +{ + return 0; +} + static inline bool of_console_check(const struct device_node *dn, const char *name, int index) { return false; -- cgit v1.2.3 From 78366e9cbd7892ac3d321e62c4be7a7fe79a69ed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Mon, 27 Jul 2020 15:38:35 +0200 Subject: mmc: sdio: Parse CISTPL_VERS_1 major and minor revision numbers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit They should indicate compliance of standard. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200727133837.19086-3-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 2 ++ include/linux/mmc/sdio_func.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 7d46411ffaa2..42df06c6b19c 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -297,6 +297,8 @@ struct mmc_card { struct sdio_cis cis; /* common tuple info */ struct sdio_func *sdio_func[SDIO_MAX_FUNCS]; /* SDIO functions (devices) */ struct sdio_func *sdio_single_irq; /* SDIO function when only one IRQ active */ + u8 major_rev; /* major revision number */ + u8 minor_rev; /* minor revision number */ unsigned num_info; /* number of info strings */ const char **info; /* info strings */ struct sdio_func_tuple *tuples; /* unknown common tuples */ diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index fa2aaab5e57a..478855b8e406 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -51,6 +51,8 @@ struct sdio_func { u8 *tmpbuf; /* DMA:able scratch buffer */ + u8 major_rev; /* major revision number */ + u8 minor_rev; /* minor revision number */ unsigned num_info; /* number of info strings */ const char **info; /* info strings */ -- cgit v1.2.3 From 6932794192f63c5e105eade19fba26b8ef29ec79 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 21 Aug 2020 08:35:33 +0200 Subject: mmc: core: Improve documentation of MMC_CAP_HW_RESET MMC_CAP_HW_RESET means that the controller is capable of resetting the eMMC device via RST_n signal, not a reset of the controller. Two drivers got this wrong, so let's make it more clear. Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20200821063533.3771-1-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c5b6e97cb21a..799e23b0a23c 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -163,6 +163,7 @@ struct mmc_host_ops { int (*select_drive_strength)(struct mmc_card *card, unsigned int max_dtr, int host_drv, int card_drv, int *drv_type); + /* Reset the eMMC card via RST_n */ void (*hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); @@ -346,7 +347,7 @@ struct mmc_host { #define MMC_CAP_CD_WAKE (1 << 28) /* Enable card detect wake */ #define MMC_CAP_CMD_DURING_TFR (1 << 29) /* Commands during data transfer */ #define MMC_CAP_CMD23 (1 << 30) /* CMD23 supported. */ -#define MMC_CAP_HW_RESET (1 << 31) /* Hardware reset */ +#define MMC_CAP_HW_RESET (1 << 31) /* Reset the eMMC card via RST_n */ u32 caps2; /* More host capabilities */ -- cgit v1.2.3 From 97a7d87e96b02fc5b3944d7735e0f6b8446d07da Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 1 Sep 2020 17:02:48 +0200 Subject: mmc: core: add a 'doing_init_tune' flag and a 'mmc_doing_tune' helper Our driver needs to know when tuning is in progress. 'doing_retune' only covers re-tuning, not the initial tuning. Add another flag to detect the initial tuning state and add a helper which tells us if any kind of tuning is going on. Only implemented for MMC currently because that's where we need it. SD can be added later if it becomes necessary. Signed-off-by: Wolfram Sang Reviewed-by: Yoshihiro Shimoda Tested-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20200901150250.26236-3-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 799e23b0a23c..c079b932330f 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -400,6 +400,7 @@ struct mmc_host { unsigned int use_spi_crc:1; unsigned int claimed:1; /* host exclusively claimed */ unsigned int bus_dead:1; /* bus has been released */ + unsigned int doing_init_tune:1; /* initial tuning in progress */ unsigned int can_retune:1; /* re-tuning can be used */ unsigned int doing_retune:1; /* re-tuning in progress */ unsigned int retune_now:1; /* do re-tuning at next req */ @@ -595,6 +596,11 @@ static inline bool mmc_doing_retune(struct mmc_host *host) return host->doing_retune == 1; } +static inline bool mmc_doing_tune(struct mmc_host *host) +{ + return host->doing_retune == 1 || host->doing_init_tune == 1; +} + static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) { return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE; -- cgit v1.2.3 From 180c284ce4d66d2fb386b81bea59f01bc7be150a Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Fri, 4 Sep 2020 15:51:20 +0300 Subject: device connection: Remove device_connection_find() There are no users for that function. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200904125123.83725-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index ca18da4768e3..0704461e8aad 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -319,8 +319,6 @@ void *fwnode_connection_find_match(struct fwnode_handle *fwnode, void *device_connection_find_match(struct device *dev, const char *con_id, void *data, devcon_match_fn_t match); -struct device *device_connection_find(struct device *dev, const char *con_id); - void device_connection_add(struct device_connection *con); void device_connection_remove(struct device_connection *con); -- cgit v1.2.3 From 87ea5926247f7e15f0b5bc5b36cb210536177d77 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Fri, 4 Sep 2020 15:51:21 +0300 Subject: device connection: Remove device_connection_add() All the users of that API have now been converted to use software fwnodes instead. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200904125123.83725-3-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 29 ----------------------------- 1 file changed, 29 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 0704461e8aad..ea37debb0a98 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -297,7 +297,6 @@ struct device_dma_parameters { * @fwnode: The device node of the connected device * @endpoint: The names of the two devices connected together * @id: Unique identifier for the connection - * @list: List head, private, for internal use only * * NOTE: @fwnode is not used together with @endpoint. @fwnode is used when * platform firmware defines the connection. When the connection is registered @@ -307,7 +306,6 @@ struct device_connection { struct fwnode_handle *fwnode; const char *endpoint[2]; const char *id; - struct list_head list; }; typedef void *(*devcon_match_fn_t)(struct device_connection *con, int ep, @@ -319,33 +317,6 @@ void *fwnode_connection_find_match(struct fwnode_handle *fwnode, void *device_connection_find_match(struct device *dev, const char *con_id, void *data, devcon_match_fn_t match); -void device_connection_add(struct device_connection *con); -void device_connection_remove(struct device_connection *con); - -/** - * device_connections_add - Add multiple device connections at once - * @cons: Zero terminated array of device connection descriptors - */ -static inline void device_connections_add(struct device_connection *cons) -{ - struct device_connection *c; - - for (c = cons; c->endpoint[0]; c++) - device_connection_add(c); -} - -/** - * device_connections_remove - Remove multiple device connections at once - * @cons: Zero terminated array of device connection descriptors - */ -static inline void device_connections_remove(struct device_connection *cons) -{ - struct device_connection *c; - - for (c = cons; c->endpoint[0]; c++) - device_connection_remove(c); -} - /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. -- cgit v1.2.3 From f5514c91e9f72b719bfec64af6acac5ad41df7b5 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Fri, 4 Sep 2020 15:51:22 +0300 Subject: device connection: Remove struct device_connection Since the connection descriptors can't be stored into the list anymore, there is no need for the data structure. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200904125123.83725-4-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index ea37debb0a98..d4612efaab82 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -292,23 +292,7 @@ struct device_dma_parameters { unsigned long segment_boundary_mask; }; -/** - * struct device_connection - Device Connection Descriptor - * @fwnode: The device node of the connected device - * @endpoint: The names of the two devices connected together - * @id: Unique identifier for the connection - * - * NOTE: @fwnode is not used together with @endpoint. @fwnode is used when - * platform firmware defines the connection. When the connection is registered - * with device_connection_add() @endpoint is used instead. - */ -struct device_connection { - struct fwnode_handle *fwnode; - const char *endpoint[2]; - const char *id; -}; - -typedef void *(*devcon_match_fn_t)(struct device_connection *con, int ep, +typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id, void *data); void *fwnode_connection_find_match(struct fwnode_handle *fwnode, -- cgit v1.2.3 From 16270a92355722e387e9ca19627c5a4d7bae1354 Mon Sep 17 00:00:00 2001 From: Hou Zhiqiang Date: Tue, 18 Aug 2020 17:27:46 +0800 Subject: PCI: designware-ep: Fix the Header Type check The current check will result in the multiple function device fails to initialize. So fix the check by masking out the multiple function bit. Link: https://lore.kernel.org/r/20200818092746.24366-1-Zhiqiang.Hou@nxp.com Fixes: 0b24134f7888 ("PCI: dwc: Add validation that PCIe core is set to correct mode") Signed-off-by: Hou Zhiqiang Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f9701410d3b5..57a222014cd2 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -76,6 +76,7 @@ #define PCI_CACHE_LINE_SIZE 0x0c /* 8 bits */ #define PCI_LATENCY_TIMER 0x0d /* 8 bits */ #define PCI_HEADER_TYPE 0x0e /* 8 bits */ +#define PCI_HEADER_TYPE_MASK 0x7f #define PCI_HEADER_TYPE_NORMAL 0 #define PCI_HEADER_TYPE_BRIDGE 1 #define PCI_HEADER_TYPE_CARDBUS 2 -- cgit v1.2.3 From 07e292950b9368518c659c4d5f1dca4bf55779bd Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 20 Aug 2020 21:53:41 -0600 Subject: PCI: Allow root and child buses to have different pci_ops PCI host bridges often have different ways to access the root and child bus config spaces. The host bridge drivers have invented their own abstractions to handle this. Let's support having different root and child bus pci_ops so these per driver abstractions can be removed. Link: https://lore.kernel.org/r/20200821035420.380495-2-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Cc: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 835530605c0d..1fbe95a7d386 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -523,6 +523,7 @@ struct pci_host_bridge { struct device dev; struct pci_bus *bus; /* Root bus */ struct pci_ops *ops; + struct pci_ops *child_ops; void *sysdata; int busnr; struct list_head windows; /* resource_entry */ -- cgit v1.2.3 From e1f82a0dcf388d98bcc7ad195c03bd812405e6b2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 26 Aug 2020 13:44:59 +0300 Subject: driver core: Annotate dev_err_probe() with __must_check We have got already new users of this API which interpret it differently and miss the opportunity to optimize their code. In order to avoid similar cases in the future, annotate dev_err_probe() with __must_check. Fixes: a787e5400a1c ("driver core: add device probe log helper") Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200826104459.81979-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index d4612efaab82..0b3dc72f64b2 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -931,7 +931,7 @@ void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); extern __printf(3, 4) -int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +int __must_check dev_err_probe(const struct device *dev, int err, const char *fmt, ...); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ -- cgit v1.2.3 From 91a46c6d1b4fcbfa4773df9421b8ad3e58088101 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Fri, 4 Sep 2020 08:49:55 +0200 Subject: xfrm: clone XFRMA_REPLAY_ESN_VAL in xfrm_do_migrate XFRMA_REPLAY_ESN_VAL was not cloned completely from the old to the new. Migrate this attribute during XFRMA_MSG_MIGRATE v1->v2: - move curleft cloning to a separate patch Fixes: af2f464e326e ("xfrm: Assign esn pointers when cloning a state") Signed-off-by: Antony Antony Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2737d24ec244..9e806c781025 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1773,21 +1773,17 @@ static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_es static inline int xfrm_replay_clone(struct xfrm_state *x, struct xfrm_state *orig) { - x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn), + + x->replay_esn = kmemdup(orig->replay_esn, + xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; - - x->replay_esn->bmp_len = orig->replay_esn->bmp_len; - x->replay_esn->replay_window = orig->replay_esn->replay_window; - - x->preplay_esn = kmemdup(x->replay_esn, - xfrm_replay_state_esn_len(x->replay_esn), + x->preplay_esn = kmemdup(orig->preplay_esn, + xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); - if (!x->preplay_esn) { - kfree(x->replay_esn); + if (!x->preplay_esn) return -ENOMEM; - } return 0; } -- cgit v1.2.3 From 20244b2a8a8728c63233d33146e007dcacbcc5c4 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 7 Sep 2020 13:19:39 +0200 Subject: ASoC: core: Do not cleanup uninitialized dais on soc_pcm_open failure Introduce for_each_rtd_dais_rollback macro which behaves exactly like for_each_codec_dais_rollback and its cpu_dais equivalent but for all dais instead. Use newly added macro to fix soc_pcm_open error path and prevent uninitialized dais from being cleaned-up. Signed-off-by: Cezary Rojewski Fixes: 5d9fa03e6c35 ("ASoC: soc-pcm: tidyup soc_pcm_open() order") Acked-by: Liam Girdwood Acked-by: Kuninori Morimoto Link: https://lore.kernel.org/r/20200907111939.16169-1-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 4176071f61bf..fc4fcac72cf7 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1193,6 +1193,8 @@ struct snd_soc_pcm_runtime { ((i) < (rtd)->num_cpus + (rtd)->num_codecs) && \ ((dai) = (rtd)->dais[i]); \ (i)++) +#define for_each_rtd_dais_rollback(rtd, i, dai) \ + for (; (--(i) >= 0) && ((dai) = (rtd)->dais[i]);) void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd); -- cgit v1.2.3 From 82894c1d397f16c2208a35dbb1310559f31980bb Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Mon, 7 Sep 2020 01:04:51 +0200 Subject: firmware: arm_scmi: Constify ops pointers in scmi_handle These are never modified, so make them const to allow drivers to make them const. Link: https://lore.kernel.org/r/20200906230452.33410-3-rikard.falkeborn@gmail.com Signed-off-by: Rikard Falkeborn Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 7e5dd7d1e221..05570afc7f74 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -279,12 +279,12 @@ struct scmi_notify_ops { struct scmi_handle { struct device *dev; struct scmi_revision_info *version; - struct scmi_perf_ops *perf_ops; - struct scmi_clk_ops *clk_ops; - struct scmi_power_ops *power_ops; - struct scmi_sensor_ops *sensor_ops; - struct scmi_reset_ops *reset_ops; - struct scmi_notify_ops *notify_ops; + const struct scmi_perf_ops *perf_ops; + const struct scmi_clk_ops *clk_ops; + const struct scmi_power_ops *power_ops; + const struct scmi_sensor_ops *sensor_ops; + const struct scmi_reset_ops *reset_ops; + const struct scmi_notify_ops *notify_ops; /* for protocol internal use */ void *perf_priv; void *clk_priv; -- cgit v1.2.3 From d20e834e13ce349c9b901b9dd8b7013e255083e8 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Sat, 5 Sep 2020 02:28:52 +0800 Subject: ASoC: soc-dai: clarify return value for get_sdw_stream() Previous changes move to use ERR_PTR(-ENOTSUPP), but it's not clear what implementations can return in case of errors. Explicitly document that NULL is not a possible return value, only ERR_PTR with a negative error code is valid. Fixes: 308811a327c38 ('ASoC: soc-dai: return proper error for get_sdw_stream()') Cc: Srinivas Kandagatla Reported-by: Bard Liao Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200904182854.3944-2-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-dai.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 776a60529e70..8b693dade9c6 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -471,7 +471,8 @@ static inline int snd_soc_dai_set_sdw_stream(struct snd_soc_dai *dai, * This routine only retrieves that was previously configured * with snd_soc_dai_get_sdw_stream() * - * Returns pointer to stream or -ENOTSUPP if callback is not supported; + * Returns pointer to stream or an ERR_PTR value, e.g. + * ERR_PTR(-ENOTSUPP) if callback is not supported; */ static inline void *snd_soc_dai_get_sdw_stream(struct snd_soc_dai *dai, int direction) -- cgit v1.2.3 From 1c30474826682bc970c3200700d8bcfa2b771278 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:42:52 -0700 Subject: PM: : fix @em_pd kernel-doc warning Fix kernel-doc warning in : ../include/linux/device.h:613: warning: Function parameter or member 'em_pd' not described in 'device' Fixes: 1bc138c62295 ("PM / EM: add support for other devices than CPUs in Energy Model") Signed-off-by: Randy Dunlap Cc: Rafael J. Wysocki Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/d97f40ad-3033-703a-c3cb-2843ce0f6371@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index ca18da4768e3..9e6ea8931a52 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -454,6 +454,7 @@ struct dev_links_info { * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. + * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors -- cgit v1.2.3 From 43fbb0860c682859780907d00bdb4abbb1b6359e Mon Sep 17 00:00:00 2001 From: Keyon Jie Date: Fri, 4 Sep 2020 16:27:29 +0300 Subject: ASoC: SOF: tokens: add token for component UUID Add the definition SOF_TKN_COMP_UUID for the component UUID token, this shall be used for all types of component in the future. Signed-off-by: Keyon Jie Reviewed-by: Ranjani Sridharan Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200904132744.1699575-2-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/sof/tokens.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index 37f5aaa09c2b..d3aae4ad8959 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -74,6 +74,7 @@ * #define SOF_TKN_COMP_PRELOAD_COUNT 403 */ #define SOF_TKN_COMP_CORE_ID 404 +#define SOF_TKN_COMP_UUID 405 /* SSP */ #define SOF_TKN_INTEL_SSP_CLKS_CONTROL 500 -- cgit v1.2.3 From f970a77f1d064eeddc32a9ed0fd7db3a66d82fdd Mon Sep 17 00:00:00 2001 From: Keyon Jie Date: Fri, 4 Sep 2020 16:27:30 +0300 Subject: ASoC: SOF: add comp_ext to struct snd_sof_widget Add member comp_ext to struct snd_sof_widget, which will be used for topology extended tokens parsing. Signed-off-by: Keyon Jie Reviewed-by: Ranjani Sridharan Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200904132744.1699575-3-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/topology.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h index f56e80d09b32..796b6c8e851d 100644 --- a/include/sound/sof/topology.h +++ b/include/sound/sof/topology.h @@ -87,6 +87,9 @@ struct sof_ipc_comp { */ #define SOF_BUF_UNDERRUN_PERMITTED BIT(1) +/* the UUID size in bytes, shared between FW and host */ +#define SOF_UUID_SIZE 16 + /* create new component buffer - SOF_IPC_TPLG_BUFFER_NEW */ struct sof_ipc_buffer { struct sof_ipc_comp comp; @@ -300,4 +303,9 @@ enum sof_event_types { SOF_KEYWORD_DETECT_DAPM_EVENT, }; +/* extended data struct for UUID components */ +struct sof_ipc_comp_ext { + uint8_t uuid[SOF_UUID_SIZE]; +} __packed; + #endif -- cgit v1.2.3 From 50b55fd463ce565b768d8bc214dd0280bee8b10d Mon Sep 17 00:00:00 2001 From: Keyon Jie Date: Fri, 4 Sep 2020 16:27:33 +0300 Subject: ASoC: SOF: use the sof_ipc_comp reserved bytes for extended data Use the 32bit reserved member of the struct sof_ipc_comp as the extended data length, this will help to minimize the ABI change for adding new extended data to the struct sof_ipc_comp, usually only minor ABI version bump needed for every update with this new solution. Signed-off-by: Keyon Jie Reviewed-by: Ranjani Sridharan Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200904132744.1699575-6-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/topology.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h index 796b6c8e851d..d12736e14b69 100644 --- a/include/sound/sof/topology.h +++ b/include/sound/sof/topology.h @@ -57,8 +57,8 @@ struct sof_ipc_comp { uint32_t pipeline_id; uint32_t core; - /* reserved for future use */ - uint32_t reserved[1]; + /* extended data length, 0 if no extended data */ + uint32_t ext_data_length; } __packed; /* -- cgit v1.2.3 From 938c3efd9e650ca343d04e70d11a17c64119e17c Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 4 Sep 2020 17:14:53 +0100 Subject: bpf: Fix formatting in documentation for BPF helpers Fix a formatting error in the description of bpf_load_hdr_opt() (rst2man complains about a wrong indentation, but what is missing is actually a blank line before the bullet list). Fix and harmonise the formatting for other helpers. Signed-off-by: Quentin Monnet Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200904161454.31135-3-quentin@isovalent.com --- include/uapi/linux/bpf.h | 87 +++++++++++++++++++++++++----------------------- 1 file changed, 45 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8dda13880957..90359cab501d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3349,38 +3349,38 @@ union bpf_attr { * Description * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *tcp_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. * To achieve this, the helper needs *task*, which is a valid - * pointer to struct task_struct. To store the stacktrace, the - * bpf program provides *buf* with a nonnegative *size*. + * pointer to **struct task_struct**. To store the stacktrace, the + * bpf program provides *buf* with a nonnegative *size*. * * The last argument, *flags*, holds the number of stack frames to * skip (from 0 to 255), masked with @@ -3410,12 +3410,12 @@ union bpf_attr { * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) * Description * Load header option. Support reading a particular TCP header - * option for bpf program (BPF_PROG_TYPE_SOCK_OPS). + * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**). * * If *flags* is 0, it will search the option from the - * sock_ops->skb_data. The comment in "struct bpf_sock_ops" + * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops** * has details on what skb_data contains under different - * sock_ops->op. + * *skops*\ **->op**. * * The first byte of the *searchby_res* specifies the * kind that it wants to search. @@ -3435,7 +3435,7 @@ union bpf_attr { * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. * * To search for the standard window scale option (3), - * the searchby_res should be [ 3, 0, 0, .... 0 ]. + * the *searchby_res* should be [ 3, 0, 0, .... 0 ]. * Note, kind-length must be 0 for regular option. * * Searching for No-Op (0) and End-of-Option-List (1) are @@ -3445,27 +3445,30 @@ union bpf_attr { * of a header option. * * Supported flags: + * * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the * saved_syn packet or the just-received syn packet. * * Return - * >0 when found, the header option is copied to *searchby_res*. - * The return value is the total length copied. + * > 0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. On failure, a + * negative error code is returned: * - * **-EINVAL** If param is invalid + * **-EINVAL** if a parameter is invalid. * - * **-ENOMSG** The option is not found + * **-ENOMSG** if the option is not found. * - * **-ENOENT** No syn packet available when - * **BPF_LOAD_HDR_OPT_TCP_SYN** is used + * **-ENOENT** if no syn packet is available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used. * - * **-ENOSPC** Not enough space. Only *len* number of - * bytes are copied. + * **-ENOSPC** if there is not enough space. Only *len* number of + * bytes are copied. * - * **-EFAULT** Cannot parse the header options in the packet + * **-EFAULT** on failure to parse the header options in the + * packet. * - * **-EPERM** This helper cannot be used under the - * current sock_ops->op. + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. * * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) * Description @@ -3483,44 +3486,44 @@ union bpf_attr { * by searching the same option in the outgoing skb. * * This helper can only be called during - * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. * * Return * 0 on success, or negative error in case of failure: * - * **-EINVAL** If param is invalid + * **-EINVAL** If param is invalid. * - * **-ENOSPC** Not enough space in the header. - * Nothing has been written + * **-ENOSPC** if there is not enough space in the header. + * Nothing has been written * - * **-EEXIST** The option has already existed + * **-EEXIST** if the option already exists. * - * **-EFAULT** Cannot parse the existing header options + * **-EFAULT** on failrue to parse the existing header options. * - * **-EPERM** This helper cannot be used under the - * current sock_ops->op. + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. * * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) * Description * Reserve *len* bytes for the bpf header option. The - * space will be used by bpf_store_hdr_opt() later in - * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * space will be used by **bpf_store_hdr_opt**\ () later in + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. * - * If bpf_reserve_hdr_opt() is called multiple times, + * If **bpf_reserve_hdr_opt**\ () is called multiple times, * the total number of bytes will be reserved. * * This helper can only be called during - * BPF_SOCK_OPS_HDR_OPT_LEN_CB. + * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**. * * Return * 0 on success, or negative error in case of failure: * - * **-EINVAL** if param is invalid + * **-EINVAL** if a parameter is invalid. * - * **-ENOSPC** Not enough space in the header. + * **-ENOSPC** if there is not enough space in the header. * - * **-EPERM** This helper cannot be used under the - * current sock_ops->op. + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. * * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) * Description @@ -3560,9 +3563,9 @@ union bpf_attr { * * long bpf_d_path(struct path *path, char *buf, u32 sz) * Description - * Return full path for given 'struct path' object, which - * needs to be the kernel BTF 'path' object. The path is - * returned in the provided buffer 'buf' of size 'sz' and + * Return full path for given **struct path** object, which + * needs to be the kernel BTF *path* object. The path is + * returned in the provided buffer *buf* of size *sz* and * is zero terminated. * * Return @@ -3573,7 +3576,7 @@ union bpf_attr { * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) * Description * Read *size* bytes from user space address *user_ptr* and store - * the data in *dst*. This is a wrapper of copy_from_user(). + * the data in *dst*. This is a wrapper of **copy_from_user**\ (). * Return * 0 on success, or a negative error in case of failure. */ -- cgit v1.2.3 From eb02d39ad3099c3dcd96c5b3fdc0303541766ed1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:31:16 -0700 Subject: netdevice.h: fix proto_down_reason kernel-doc warning Fix kernel-doc warning in : ../include/linux/netdevice.h:2158: warning: Function parameter or member 'proto_down_reason' not described in 'net_device' Fixes: 829eb208e80d ("rtnetlink: add support for protodown reason") Signed-off-by: Randy Dunlap Acked-by: Roopa Prabhu Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..bf0e313486be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1784,6 +1784,7 @@ enum netdev_priv_flags { * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * + * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one -- cgit v1.2.3 From ffa59b0b396cb2c0ea6712ff30ee05c35d4c9c8d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:32:30 -0700 Subject: netdevice.h: fix xdp_state kernel-doc warning Fix kernel-doc warning in : ../include/linux/netdevice.h:2158: warning: Function parameter or member 'xdp_state' not described in 'net_device' Fixes: 7f0a838254bd ("bpf, xdp: Maintain info on attached XDP BPF programs in net_device") Signed-off-by: Randy Dunlap Cc: Andrii Nakryiko Cc: Alexei Starovoitov Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bf0e313486be..7bd4fcdd0738 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1849,6 +1849,7 @@ enum netdev_priv_flags { * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state + * @xdp_state: stores info on attached XDP BPF programs * * FIXME: cleanup struct net_device such that network protocol info * moves out. -- cgit v1.2.3 From 5205e919c9f0c5b48678f2c787871c96f665ca1b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 7 Sep 2020 12:56:08 +0300 Subject: net: bridge: mcast: add support for src list and filter mode dumping Support per port group src list (address and timer) and filter mode dumping. Protected by either multicast_lock or rcu. v3: add IPv6 support v2: require RCU or multicast_lock to traverse src groups Signed-off-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index c1227aecd38f..75a2ac479247 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -455,10 +455,31 @@ enum { enum { MDBA_MDB_EATTR_UNSPEC, MDBA_MDB_EATTR_TIMER, + MDBA_MDB_EATTR_SRC_LIST, + MDBA_MDB_EATTR_GROUP_MODE, __MDBA_MDB_EATTR_MAX }; #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1) +/* per mdb entry source */ +enum { + MDBA_MDB_SRCLIST_UNSPEC, + MDBA_MDB_SRCLIST_ENTRY, + __MDBA_MDB_SRCLIST_MAX +}; +#define MDBA_MDB_SRCLIST_MAX (__MDBA_MDB_SRCLIST_MAX - 1) + +/* per mdb entry per source attributes + * these are embedded in MDBA_MDB_SRCLIST_ENTRY + */ +enum { + MDBA_MDB_SRCATTR_UNSPEC, + MDBA_MDB_SRCATTR_ADDRESS, + MDBA_MDB_SRCATTR_TIMER, + __MDBA_MDB_SRCATTR_MAX +}; +#define MDBA_MDB_SRCATTR_MAX (__MDBA_MDB_SRCATTR_MAX - 1) + /* multicast router types */ enum { MDB_RTR_TYPE_DISABLED, -- cgit v1.2.3 From 0a667b500703db80eb30759bb67df671641dbc5b Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 25 Aug 2020 09:46:00 +1000 Subject: drm/ttm: remove bdev from ttm_tt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I want to split this structure up and use it differently, step one remove bdev pointer from it and pass it explicitly. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200826014428.828392-4-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 7 ++++--- include/drm/ttm/ttm_tt.h | 25 ++++++++++++------------- 2 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 9744ed9d677e..a694388f7b13 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -77,8 +77,9 @@ struct ttm_bo_driver { * Returns: * -ENOMEM: Out of memory. */ - int (*ttm_tt_populate)(struct ttm_tt *ttm, - struct ttm_operation_ctx *ctx); + int (*ttm_tt_populate)(struct ttm_bo_device *bdev, + struct ttm_tt *ttm, + struct ttm_operation_ctx *ctx); /** * ttm_tt_unpopulate @@ -87,7 +88,7 @@ struct ttm_bo_driver { * * Free all backing page */ - void (*ttm_tt_unpopulate)(struct ttm_tt *ttm); + void (*ttm_tt_unpopulate)(struct ttm_bo_device *bdev, struct ttm_tt *ttm); /** * struct ttm_bo_driver member eviction_valuable diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 241cc40839ed..6bda88f8da46 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -60,7 +60,7 @@ struct ttm_backend_func { * indicated by @bo_mem. This function should be able to handle * differences between aperture and system page sizes. */ - int (*bind) (struct ttm_tt *ttm, struct ttm_resource *bo_mem); + int (*bind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *bo_mem); /** * struct ttm_backend_func member unbind @@ -70,7 +70,7 @@ struct ttm_backend_func { * Unbind previously bound backend pages. This function should be * able to handle differences between aperture and system page sizes. */ - void (*unbind) (struct ttm_tt *ttm); + void (*unbind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm); /** * struct ttm_backend_func member destroy @@ -80,13 +80,12 @@ struct ttm_backend_func { * Destroy the backend. This will be call back from ttm_tt_destroy so * don't call ttm_tt_destroy from the callback or infinite loop. */ - void (*destroy) (struct ttm_tt *ttm); + void (*destroy) (struct ttm_bo_device *bdev, struct ttm_tt *ttm); }; /** * struct ttm_tt * - * @bdev: Pointer to a struct ttm_bo_device. * @func: Pointer to a struct ttm_backend_func that describes * the backend methods. * pointer. @@ -103,7 +102,6 @@ struct ttm_backend_func { * memory. */ struct ttm_tt { - struct ttm_bo_device *bdev; struct ttm_backend_func *func; struct page **pages; uint32_t page_flags; @@ -183,7 +181,8 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma); * * Bind the pages of @ttm to an aperture location identified by @bo_mem */ -int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem, +int ttm_tt_bind(struct ttm_bo_device *bdev, + struct ttm_tt *ttm, struct ttm_resource *bo_mem, struct ttm_operation_ctx *ctx); /** @@ -193,7 +192,7 @@ int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem, * * Unbind, unpopulate and destroy common struct ttm_tt. */ -void ttm_tt_destroy(struct ttm_tt *ttm); +void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm); /** * ttm_ttm_unbind: @@ -202,7 +201,7 @@ void ttm_tt_destroy(struct ttm_tt *ttm); * * Unbind a struct ttm_tt. */ -void ttm_tt_unbind(struct ttm_tt *ttm); +void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm); /** * ttm_tt_swapin: @@ -227,7 +226,7 @@ int ttm_tt_swapin(struct ttm_tt *ttm); * and cache flushes and potential page splitting / combining. */ int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement); -int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage); +int ttm_tt_swapout(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct file *persistent_swap_storage); /** * ttm_tt_populate - allocate pages for a ttm @@ -236,7 +235,7 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage); * * Calls the driver method to allocate pages for a ttm */ -int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); +int ttm_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); /** * ttm_tt_unpopulate - free pages from a ttm @@ -245,7 +244,7 @@ int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); * * Calls the driver method to free all pages from a ttm */ -void ttm_tt_unpopulate(struct ttm_tt *ttm); +void ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm); #if IS_ENABLED(CONFIG_AGP) #include @@ -265,8 +264,8 @@ void ttm_tt_unpopulate(struct ttm_tt *ttm); struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo, struct agp_bridge_data *bridge, uint32_t page_flags); -int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); -void ttm_agp_tt_unpopulate(struct ttm_tt *ttm); +int ttm_agp_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); +void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm); #endif #endif -- cgit v1.2.3 From 0db0c34cfbc9838c1a14cb04dd880602abd699a7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 3 Sep 2020 16:14:31 -0700 Subject: net: tighten the definition of interface statistics This patch is born out of an investigation into which IEEE statistics correspond to which struct rtnl_link_stats64 members. Turns out that there seems to be reasonable consensus on the matter, among many drivers. To save others the time (and it took more time than I'm comfortable admitting) I'm adding comments referring to IEEE attributes to struct rtnl_link_stats64. Up until now we had two forms of documentation for stats - in Documentation/ABI/testing/sysfs-class-net-statistics and the comments on struct rtnl_link_stats64 itself. While the former is very cautious in defining the expected behavior, the latter feel quite dated and may not be easy to understand for modern day driver author (e.g. rx_over_errors). At the same time modern systems are far more complex and once obvious definitions lost their clarity. For example - does rx_packet count at the MAC layer (aFramesReceivedOK)? packets processed correctly by hardware? received by the driver? or maybe received by the stack? I tried to clarify the expectations, further clarifications from others are very welcome. The part hardest to untangle is rx_over_errors vs rx_fifo_errors vs rx_missed_errors. After much deliberation I concluded that for modern HW only two of the counters will make sense. The distinction between internal FIFO overflow and packets dropped due to back-pressure from the host is likely too implementation (driver and device) specific to expose in the standard stats. Now - which two of those counters we select to use is anyone's pick: sysfs documentation suggests rx_over_errors counts packets which did not fit into buffers due to MTU being too small, which I reused. There don't seem to be many modern drivers using it (well, CAN drivers seem to love this statistic). Of the remaining two I picked rx_missed_errors to report device drops. bnxt reports it and it's folded into "drop"s in procfs (while rx_fifo_errors is an error, and modern devices usually receive the frame OK, they just can't admit it into the pipeline). Of the drivers I looked at only AMD Lance-like and NS8390-like use all three of these counters. rx_missed_errors counts missed frames, rx_over_errors counts overflow events, and rx_fifo_errors counts frames which were truncated because they didn't fit into buffers. This suggests that rx_fifo_errors may be the correct stat for truncated packets, but I'd think a FIFO stat counting truncated packets would be very confusing to a modern reader. v2: - add driver developer notes about ethtool stat count and reset - replace Ethernet with IEEE 802.3 to better indicate source of attrs - mention byte counters don't count FCS - clarify RX counter is from device to host - drop "sightly" from sysfs paragraph - add examples of ethtool stats - s/incoming/received/ s/incoming/transmitted/ Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_link.h | 204 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 187 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7fba4de511de..bf4667403cab 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -40,26 +40,197 @@ struct rtnl_link_stats { __u32 rx_nohandler; /* dropped, no handler found */ }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter should not include packets + * dropped by the device which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ -- cgit v1.2.3 From 8b10fe68985278de4926daa56ad6af701839e40a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 10 Aug 2020 10:21:39 -0400 Subject: fscrypt: drop unused inode argument from fscrypt_fname_alloc_buffer Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20200810142139.487631-1-jlayton@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 991ff8575d0e..eaf16eb55788 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -197,7 +197,7 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname) kfree(fname->crypto_buf.name); } -int fscrypt_fname_alloc_buffer(const struct inode *inode, u32 max_encrypted_len, +int fscrypt_fname_alloc_buffer(u32 max_encrypted_len, struct fscrypt_str *crypto_str); void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); int fscrypt_fname_disk_to_usr(const struct inode *inode, @@ -428,8 +428,7 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname) return; } -static inline int fscrypt_fname_alloc_buffer(const struct inode *inode, - u32 max_encrypted_len, +static inline int fscrypt_fname_alloc_buffer(u32 max_encrypted_len, struct fscrypt_str *crypto_str) { return -EOPNOTSUPP; -- cgit v1.2.3 From 384d87ef2c954fc58e6c5fd8253e4a1984f5fe02 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 4 Sep 2020 10:58:52 +0200 Subject: block: Do not discard buffers under a mounted filesystem Discarding blocks and buffers under a mounted filesystem is hardly anything admin wants to do. Usually it will confuse the filesystem and sometimes the loss of buffer_head state (including b_private field) can even cause crashes like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 PGD 0 P4D 0 Oops: 0002 [#1] SMP PTI CPU: 4 PID: 203778 Comm: jbd2/dm-3-8 Kdump: loaded Tainted: G O --------- - - 4.18.0-147.5.0.5.h126.eulerosv2r9.x86_64 #1 Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 1.57 08/11/2015 RIP: 0010:jbd2_journal_grab_journal_head+0x1b/0x40 [jbd2] ... Call Trace: __jbd2_journal_insert_checkpoint+0x23/0x70 [jbd2] jbd2_journal_commit_transaction+0x155f/0x1b60 [jbd2] kjournald2+0xbd/0x270 [jbd2] So if we don't have block device open with O_EXCL already, claim the block device while we truncate buffer cache. This makes sure any exclusive block device user (such as filesystem) cannot operate on the device while we are discarding buffer cache. Reported-by: Ye Bin Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig [axboe: fix !CONFIG_BLOCK error in truncate_bdev_range()] Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d82959e7b86..37ec5a73d027 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1987,11 +1987,18 @@ void bdput(struct block_device *); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); +int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, + loff_t lend); int sync_blockdev(struct block_device *bdev); #else static inline void invalidate_bdev(struct block_device *bdev) { } +static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode, + loff_t lstart, loff_t lend) +{ + return 0; +} static inline int sync_blockdev(struct block_device *bdev) { return 0; -- cgit v1.2.3 From 54d04ea8cdbd143496e4f5cc9c0a9f86c0e55a2e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 7 Sep 2020 13:44:36 +0200 Subject: drm/ttm: merge offset and base in ttm_bus_placement MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is used by TTM to communicate the physical address which should be used with ioremap(), ioremap_wc(). We don't need to separate the base and offset in any way here. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/389457/ --- include/drm/ttm/ttm_resource.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 406baa8f0068..7b8a3157fbb3 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -148,16 +148,14 @@ struct ttm_resource_manager { * struct ttm_bus_placement * * @addr: mapped virtual address - * @base: bus base address + * @offset: physical addr * @is_iomem: is this io memory ? - * @offset: offset from the base address * * Structure indicating the bus placement of an object. */ struct ttm_bus_placement { void *addr; - phys_addr_t base; - unsigned long offset; + phys_addr_t offset; bool is_iomem; }; -- cgit v1.2.3 From 66ada2ccae4ed4dd07ba91df3b5fdb4c11335bd1 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 29 Aug 2020 22:00:01 +0900 Subject: kprobes: Add generic kretprobe trampoline handler Add a generic kretprobe trampoline handler for unifying the all cloned /arch/* kretprobe trampoline handlers. The generic kretprobe trampoline handler is based on the x86 implementation, because it is the latest implementation. It has frame pointer checking, kprobe_busy_begin/end and return address fixup for user handlers. [ mingo: Minor edits. ] Signed-off-by: Masami Hiramatsu Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/159870600138.1229682.3424065380448088833.stgit@devnote2 --- include/linux/kprobes.h | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9be1bff4f586..72142ae5df3e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -187,10 +187,38 @@ static inline int kprobes_built_in(void) return 1; } +extern struct kprobe kprobe_busy; +extern void kprobe_busy_begin(void); +extern void kprobe_busy_end(void); + #ifdef CONFIG_KRETPROBES extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs); extern int arch_trampoline_kprobe(struct kprobe *p); + +/* If the trampoline handler called from a kprobe, use this version */ +unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, + void *trampoline_address, + void *frame_pointer); + +static nokprobe_inline +unsigned long kretprobe_trampoline_handler(struct pt_regs *regs, + void *trampoline_address, + void *frame_pointer) +{ + unsigned long ret; + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never runs in kprobe handler, no kprobe must + * be running at this point. + */ + kprobe_busy_begin(); + ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer); + kprobe_busy_end(); + + return ret; +} + #else /* CONFIG_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) @@ -354,10 +382,6 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) return this_cpu_ptr(&kprobe_ctlblk); } -extern struct kprobe kprobe_busy; -void kprobe_busy_begin(void); -void kprobe_busy_end(void); - kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); -- cgit v1.2.3 From b338817807538c893540e393856b79cbbdf777ea Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 29 Aug 2020 22:02:47 +0900 Subject: kprobes: Free kretprobe_instance with RCU callback Free kretprobe_instance with RCU callback instead of directly freeing the object in the kretprobe handler context. This will make kretprobe run safer in NMI context. Signed-off-by: Masami Hiramatsu Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/159870616685.1229682.11978742048709542226.stgit@devnote2 --- include/linux/kprobes.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 72142ae5df3e..3389067d88b1 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -156,7 +156,10 @@ struct kretprobe { }; struct kretprobe_instance { - struct hlist_node hlist; + union { + struct hlist_node hlist; + struct rcu_head rcu; + }; struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; @@ -395,7 +398,6 @@ int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); -void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); -- cgit v1.2.3 From 319f0ce284fff8e4f95167cb144acc905d0584c7 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 29 Aug 2020 22:03:02 +0900 Subject: kprobes: Make local functions static Since we unified the kretprobe trampoline handler from arch/* code, some functions and objects do not need to be exported anymore. Signed-off-by: Masami Hiramatsu Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/159870618256.1229682.8692046612635810882.stgit@devnote2 --- include/linux/kprobes.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 3389067d88b1..5c8c271fa1e9 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -190,7 +190,6 @@ static inline int kprobes_built_in(void) return 1; } -extern struct kprobe kprobe_busy; extern void kprobe_busy_begin(void); extern void kprobe_busy_end(void); @@ -235,16 +234,6 @@ static inline int arch_trampoline_kprobe(struct kprobe *p) extern struct kretprobe_blackpoint kretprobe_blacklist[]; -static inline void kretprobe_assert(struct kretprobe_instance *ri, - unsigned long orig_ret_address, unsigned long trampoline_address) -{ - if (!orig_ret_address || (orig_ret_address == trampoline_address)) { - printk("kretprobe BUG!: Processing kretprobe %p @ %p\n", - ri->rp, ri->rp->kp.addr); - BUG(); - } -} - #ifdef CONFIG_KPROBES_SANITY_TEST extern int init_test_probes(void); #else @@ -364,10 +353,6 @@ int arch_check_ftrace_location(struct kprobe *p); /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); -void kretprobe_hash_lock(struct task_struct *tsk, - struct hlist_head **head, unsigned long *flags); -void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags); -struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk); /* kprobe_running() will just return the current_kprobe on this CPU */ static inline struct kprobe *kprobe_running(void) -- cgit v1.2.3 From 67cc570edaa02016a8685a06a0ee91f05a6277d9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 27 Aug 2020 19:28:42 +0200 Subject: netfilter: nf_tables: coalesce multiple notifications into one skbuff On x86_64, each notification results in one skbuff allocation which consumes at least 768 bytes due to the skbuff overhead. This patch coalesces several notifications into one single skbuff, so each notification consumes at least ~211 bytes, that ~3.5 times less memory consumption. As a result, this is reducing the chances to exhaust the netlink socket receive buffer. Rule of thumb is that each notification batch only contains netlink messages whose report flag is the same, nfnetlink_send() requires this to do appropriate delivery to userspace, either via unicast (echo mode) or multicast (monitor mode). The skbuff control buffer is used to annotate the report flag for later handling at the new coalescing routine. The batch skbuff notification size is NLMSG_GOODSIZE, using a larger skbuff would allow for more socket receiver buffer savings (to amortize the cost of the skbuff even more), however, going over that size might break userspace applications, so let's be conservative and stick to NLMSG_GOODSIZE. Reported-by: Phil Sutter Acked-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netns/nftables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index a1a8d45adb42..6c0806bd8d1e 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -8,6 +8,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; struct list_head module_list; + struct list_head notify_list; struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; -- cgit v1.2.3 From d7cf5590393132993f2e6d2618fd23a20a6342ca Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 7 Sep 2020 15:05:31 +0300 Subject: device property: Move fwnode_connection_find_match() under drivers/base/property.c The function is now only a helper that searches the connection from device graph and then by checking if the supplied connection identifier matches a property that contains reference. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200907120532.37611-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 9 --------- include/linux/property.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 0b3dc72f64b2..bf480dbe3375 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -292,15 +292,6 @@ struct device_dma_parameters { unsigned long segment_boundary_mask; }; -typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id, - void *data); - -void *fwnode_connection_find_match(struct fwnode_handle *fwnode, - const char *con_id, void *data, - devcon_match_fn_t match); -void *device_connection_find_match(struct device *dev, const char *con_id, - void *data, devcon_match_fn_t match); - /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. diff --git a/include/linux/property.h b/include/linux/property.h index 9f805c442819..aedae94dcf41 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -418,6 +418,20 @@ fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); +typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id, + void *data); + +void *fwnode_connection_find_match(struct fwnode_handle *fwnode, + const char *con_id, void *data, + devcon_match_fn_t match); + +static inline void *device_connection_find_match(struct device *dev, + const char *con_id, void *data, + devcon_match_fn_t match) +{ + return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match); +} + /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ -- cgit v1.2.3 From 18efb2f9e897ac65e7a1b2892f4a53e404534eba Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 29 Jul 2020 10:58:29 -0700 Subject: test_firmware: Test platform fw loading on non-EFI systems On non-EFI systems, it wasn't possible to test the platform firmware loader because it will have never set "checked_fw" during __init. Instead, allow the test code to override this check. Additionally split the declarations into a private header file so it there is greater enforcement of the symbol visibility. Fixes: 548193cba2a7 ("test_firmware: add support for firmware_request_platform") Cc: stable@vger.kernel.org Reviewed-by: Luis Chamberlain Acked-by: Scott Branden Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20200729175845.1745471-2-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/efi_embedded_fw.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h index 57eac5241303..4ad5db9f5312 100644 --- a/include/linux/efi_embedded_fw.h +++ b/include/linux/efi_embedded_fw.h @@ -7,19 +7,6 @@ #define EFI_EMBEDDED_FW_PREFIX_LEN 8 -/* - * This struct and efi_embedded_fw_list are private to the efi-embedded fw - * implementation they are in this header for use by lib/test_firmware.c only! - */ -struct efi_embedded_fw { - struct list_head list; - const char *name; - const u8 *data; - size_t length; -}; - -extern struct list_head efi_embedded_fw_list; - /** * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw * code to search for embedded firmwares. -- cgit v1.2.3 From f82485722e5de5ebb08d3a1dd7302203346dbff9 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 24 Aug 2020 19:38:57 +0200 Subject: devres: provide devm_krealloc() Implement the managed variant of krealloc(). This function works with all memory allocated by devm_kmalloc() (or devres functions using it implicitly like devm_kmemdup(), devm_kstrdup() etc.). Managed realloc'ed chunks can be manually released with devm_kfree(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200824173859.4910-2-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index bf480dbe3375..85d5c28bed93 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -206,6 +206,8 @@ int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc; +void *devm_krealloc(struct device *dev, void *ptr, size_t size, + gfp_t gfp) __must_check; __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap) __malloc; __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, -- cgit v1.2.3 From ab5fe88aef4b4837bc2f92fc9f6f9c9b75ef633b Mon Sep 17 00:00:00 2001 From: Vaibhav Gupta Date: Thu, 20 Aug 2020 00:26:45 +0530 Subject: fbdev: via-core: use generic power management Drivers should do only device-specific jobs. But in general, drivers using legacy PCI PM framework for .suspend()/.resume() have to manage many PCI PM-related tasks themselves which can be done by PCI Core itself. This brings extra load on the driver and it directly calls PCI helper functions to handle them. Switch to the new generic framework by updating function signatures and define a "struct dev_pm_ops" variable to bind PM callbacks. The via_suspend() is designed to function only in the case of Suspend. Thus, the code checked for "if (state.event != PM_EVENT_SUSPEND)". This is because, in the legacy framework, this callback was invoked even in the event of Freeze and Hibernate. Hence, added the load of unnecessary function-calls. The goal can be achieved by binding the callback with only "via_pm_ops.suspend" in the new framework. This also avoids the step of checking "if (state.event != PM_EVENT_SUSPEND)" every time the callback is invoked. Signed-off-by: Vaibhav Gupta Cc: Bjorn Helgaas Cc: Bjorn Helgaas Cc: Bjorn Helgaas Cc: Vaibhav Gupta Cc: Sam Ravnborg Cc: Paul Mackerras Cc: Russell King Cc: Andres Salomon CC: Antonino Daplas Cc: Shuah Khan Signed-off-by: Bartlomiej Zolnierkiewicz Link: https://patchwork.freedesktop.org/patch/msgid/20200819185654.151170-4-vaibhavgupta40@gmail.com --- include/linux/via-core.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/via-core.h b/include/linux/via-core.h index 9e802deedb2d..8737599b9148 100644 --- a/include/linux/via-core.h +++ b/include/linux/via-core.h @@ -47,7 +47,6 @@ struct via_port_cfg { /* * Allow subdevs to register suspend/resume hooks. */ -#ifdef CONFIG_PM struct viafb_pm_hooks { struct list_head list; int (*suspend)(void *private); @@ -57,7 +56,6 @@ struct viafb_pm_hooks { void viafb_pm_register(struct viafb_pm_hooks *hooks); void viafb_pm_unregister(struct viafb_pm_hooks *hooks); -#endif /* CONFIG_PM */ /* * This is the global viafb "device" containing stuff needed by -- cgit v1.2.3 From e2028c8e6bf9a12dfe83fc12ce6d5d9ab1628b0b Mon Sep 17 00:00:00 2001 From: Sven Schneider Date: Thu, 20 Aug 2020 10:21:37 +0200 Subject: lib/fonts: add font 6x8 for OLED display This font is derived from lib/fonts/font_6x10.c and is useful for small OLED displays Signed-off-by: Sven Schneider Signed-off-by: Sascha Hauer Reviewed-by: Greg Kroah-Hartman Signed-off-by: Bartlomiej Zolnierkiewicz Link: https://patchwork.freedesktop.org/patch/msgid/20200820082137.5907-1-s.hauer@pengutronix.de --- include/linux/font.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/font.h b/include/linux/font.h index 51b91c8b69d5..4a3f8741bb7e 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -33,6 +33,7 @@ struct font_desc { #define MINI4x6_IDX 9 #define FONT6x10_IDX 10 #define TER16x32_IDX 11 +#define FONT6x8_IDX 12 extern const struct font_desc font_vga_8x8, font_vga_8x16, @@ -45,7 +46,8 @@ extern const struct font_desc font_vga_8x8, font_acorn_8x8, font_mini_4x6, font_6x10, - font_ter_16x32; + font_ter_16x32, + font_6x8; /* Find a font with a specific name */ -- cgit v1.2.3 From 5c15291223949763c13f8c79279dc9700069a2bc Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sun, 30 Aug 2020 14:55:24 +0300 Subject: fbdev: remove mbx framebuffer driver The only in-tree user for mbx driver for Intel 2700G graphics chip was cm-x270 platform. Since this platform was removed by the commit 9d3239147d6d ("ARM: pxa: remove Compulab pxa2xx boards") there is no point to keep the obsolete framebuffer driver. Signed-off-by: Mike Rapoport Cc: Jonathan Corbet Cc: Arnd Bergmann Signed-off-by: Bartlomiej Zolnierkiewicz Link: https://patchwork.freedesktop.org/patch/msgid/20200830115524.431278-1-rppt@kernel.org --- include/video/mbxfb.h | 99 --------------------------------------------------- 1 file changed, 99 deletions(-) delete mode 100644 include/video/mbxfb.h (limited to 'include') diff --git a/include/video/mbxfb.h b/include/video/mbxfb.h deleted file mode 100644 index 35921cb6d1e5..000000000000 --- a/include/video/mbxfb.h +++ /dev/null @@ -1,99 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __MBX_FB_H -#define __MBX_FB_H - -#include -#include - -struct mbxfb_val { - unsigned int defval; - unsigned int min; - unsigned int max; -}; - -struct fb_info; - -struct mbxfb_platform_data { - /* Screen info */ - struct mbxfb_val xres; - struct mbxfb_val yres; - struct mbxfb_val bpp; - - /* Memory info */ - unsigned long memsize; /* if 0 use ODFB? */ - unsigned long timings1; - unsigned long timings2; - unsigned long timings3; - - int (*probe)(struct fb_info *fb); - int (*remove)(struct fb_info *fb); -}; - -/* planar */ -#define MBXFB_FMT_YUV16 0 -#define MBXFB_FMT_YUV12 1 - -/* packed */ -#define MBXFB_FMT_UY0VY1 2 -#define MBXFB_FMT_VY0UY1 3 -#define MBXFB_FMT_Y0UY1V 4 -#define MBXFB_FMT_Y0VY1U 5 -struct mbxfb_overlaySetup { - __u32 enable; - __u32 x, y; - __u32 width, height; - __u32 fmt; - __u32 mem_offset; - __u32 scaled_width; - __u32 scaled_height; - - /* Filled by the driver */ - __u32 U_offset; - __u32 V_offset; - - __u16 Y_stride; - __u16 UV_stride; -}; - -#define MBXFB_ALPHABLEND_NONE 0 -#define MBXFB_ALPHABLEND_GLOBAL 1 -#define MBXFB_ALPHABLEND_PIXEL 2 - -#define MBXFB_COLORKEY_DISABLED 0 -#define MBXFB_COLORKEY_PREVIOUS 1 -#define MBXFB_COLORKEY_CURRENT 2 -struct mbxfb_alphaCtl { - __u8 overlay_blend_mode; - __u8 overlay_colorkey_mode; - __u8 overlay_global_alpha; - __u32 overlay_colorkey; - __u32 overlay_colorkey_mask; - - __u8 graphics_blend_mode; - __u8 graphics_colorkey_mode; - __u8 graphics_global_alpha; - __u32 graphics_colorkey; - __u32 graphics_colorkey_mask; -}; - -#define MBXFB_PLANE_GRAPHICS 0 -#define MBXFB_PLANE_VIDEO 1 -struct mbxfb_planeorder { - __u8 bottom; - __u8 top; -}; - -struct mbxfb_reg { - __u32 addr; /* offset from 0x03fe 0000 */ - __u32 val; /* value */ - __u32 mask; /* which bits to touch (for write) */ -}; - -#define MBXFB_IOCX_OVERLAY _IOWR(0xF4, 0x00,struct mbxfb_overlaySetup) -#define MBXFB_IOCG_ALPHA _IOR(0xF4, 0x01,struct mbxfb_alphaCtl) -#define MBXFB_IOCS_ALPHA _IOW(0xF4, 0x02,struct mbxfb_alphaCtl) -#define MBXFB_IOCS_PLANEORDER _IOR(0xF4, 0x03,struct mbxfb_planeorder) -#define MBXFB_IOCS_REG _IOW(0xF4, 0x04,struct mbxfb_reg) -#define MBXFB_IOCX_REG _IOWR(0xF4, 0x05,struct mbxfb_reg) - -#endif /* __MBX_FB_H */ -- cgit v1.2.3 From de394e7568ce2cdb4643ed230169f484f25f9442 Mon Sep 17 00:00:00 2001 From: "peterz@infradead.org" Date: Tue, 8 Sep 2020 12:57:43 +0200 Subject: tracepoint: Fix overly long tracepoint names Stephen Rothwell reported: > Exported symbols need to be <= (64 - sizeof(Elf_Addr)) long. This is > presumably 56 on 64 bit arches and the above symbol (including the '.') > is 56 characters long. Shorten the tracepoint symbol name. Fixes: d25e37d89dd2 ("tracepoint: Optimize using static_call()") Reported-by: Stephen Rothwell Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200908105743.GW2674@hirez.programming.kicks-ass.net --- include/linux/tracepoint.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 3722a10fc46d..81fa0b2f271e 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -154,7 +154,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #ifdef CONFIG_HAVE_STATIC_CALL #define __DO_TRACE_CALL(name) static_call(tp_func_##name) #else -#define __DO_TRACE_CALL(name) __tracepoint_iter_##name +#define __DO_TRACE_CALL(name) __traceiter_##name #endif /* CONFIG_HAVE_STATIC_CALL */ /* @@ -232,8 +232,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * poking RCU a bit. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ - extern int __tracepoint_iter_##name(data_proto); \ - DECLARE_STATIC_CALL(tp_func_##name, __tracepoint_iter_##name); \ + extern int __traceiter_##name(data_proto); \ + DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name); \ extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ @@ -288,19 +288,19 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static const char __tpstrtab_##_name[] \ __section(__tracepoints_strings) = #_name; \ extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name); \ - int __tracepoint_iter_##_name(void *__data, proto); \ + int __traceiter_##_name(void *__data, proto); \ struct tracepoint __tracepoint_##_name __used \ __section(__tracepoints) = { \ .name = __tpstrtab_##_name, \ .key = STATIC_KEY_INIT_FALSE, \ .static_call_key = &STATIC_CALL_KEY(tp_func_##_name), \ .static_call_tramp = STATIC_CALL_TRAMP_ADDR(tp_func_##_name), \ - .iterator = &__tracepoint_iter_##_name, \ + .iterator = &__traceiter_##_name, \ .regfunc = _reg, \ .unregfunc = _unreg, \ .funcs = NULL }; \ __TRACEPOINT_ENTRY(_name); \ - int __tracepoint_iter_##_name(void *__data, proto) \ + int __traceiter_##_name(void *__data, proto) \ { \ struct tracepoint_func *it_func_ptr; \ void *it_func; \ @@ -314,18 +314,18 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) } while ((++it_func_ptr)->func); \ return 0; \ } \ - DEFINE_STATIC_CALL(tp_func_##_name, __tracepoint_iter_##_name); + DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name); #define DEFINE_TRACE(name, proto, args) \ DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args)); #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \ EXPORT_SYMBOL_GPL(__tracepoint_##name); \ - EXPORT_SYMBOL_GPL(__tracepoint_iter_##name); \ + EXPORT_SYMBOL_GPL(__traceiter_##name); \ EXPORT_STATIC_CALL_GPL(tp_func_##name) #define EXPORT_TRACEPOINT_SYMBOL(name) \ EXPORT_SYMBOL(__tracepoint_##name); \ - EXPORT_SYMBOL(__tracepoint_iter_##name); \ + EXPORT_SYMBOL(__traceiter_##name); \ EXPORT_STATIC_CALL(tp_func_##name) -- cgit v1.2.3 From 783560d02dd61aee20d1d00c1c061bcafea30264 Mon Sep 17 00:00:00 2001 From: Dharageswari R Date: Tue, 8 Sep 2020 12:28:25 +0300 Subject: ASoC: SOF: Implement snd_sof_bytes_ext_volatile_get kcontrol IO This patch implements the snd_sof_bytes_ext_volatile_get() to read the actual parameters from DSP by sending the SOF_IPC_COMP_GET_DATA IPC for the kcontrol of type SOF_TPLG_KCTL_BYTES_VOLATILE_RO. Signed-off-by: Dharageswari R Reviewed-by: Guennadi Liakhovetski Reviewed-by: Ranjani Sridharan Reviewed-by: Pierre-Louis Bossart Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200908092825.1813847-2-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/sof/tokens.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index d3aae4ad8959..a642bf30c027 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -24,6 +24,9 @@ #define SOF_TPLG_KCTL_ENUM_ID 257 #define SOF_TPLG_KCTL_BYTES_ID 258 #define SOF_TPLG_KCTL_SWITCH_ID 259 +#define SOF_TPLG_KCTL_BYTES_VOLATILE_RO 260 +#define SOF_TPLG_KCTL_BYTES_VOLATILE_RW 261 +#define SOF_TPLG_KCTL_BYTES_WO_ID 262 /* * Tokens - must match values in topology configurations -- cgit v1.2.3 From b41b0ce5982693e27307cfe0aaf49bc8e3a20900 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Wed, 29 Jul 2020 15:34:39 +0300 Subject: interconnect: Add bulk API helpers There are drivers which just need to get multiple interconnect paths, request some predefined amounts of bandwidth and then just toggle the paths between enabled/disabled state. The aim of this patch is simplify the above and to allow drivers to put all the path names and bandwidth data into a single static icc_bulk_data table and call the icc_bulk_* functions on that table in order to scale all the interconnect paths in parallel. Suggested-by: Evan Green Suggested-by: Bjorn Andersson Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200729123439.9961-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index 3a63d98613fc..f2dd2fc8d3cd 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -23,6 +23,28 @@ struct icc_path; struct device; +/** + * struct icc_bulk_data - Data used for bulk icc operations. + * + * @path: reference to the interconnect path (internal use) + * @name: the name from the "interconnect-names" DT property + * @avg_bw: average bandwidth in icc units + * @peak_bw: peak bandwidth in icc units + */ +struct icc_bulk_data { + struct icc_path *path; + const char *name; + u32 avg_bw; + u32 peak_bw; +}; + +int __must_check of_icc_bulk_get(struct device *dev, int num_paths, + struct icc_bulk_data *paths); +void icc_bulk_put(int num_paths, struct icc_bulk_data *paths); +int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths); +int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths); +void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths); + #if IS_ENABLED(CONFIG_INTERCONNECT) struct icc_path *icc_get(struct device *dev, const int src_id, -- cgit v1.2.3 From 3fe3578c8a3e18d809ad4541ff708918509e89dd Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Mon, 27 Jul 2020 22:38:01 -0400 Subject: dt-bindings: interconnect: Add Qualcomm SM8150 DT bindings The Qualcomm SM8150 platform has several bus fabrics that could be controlled and tuned dynamically according to the bandwidth demand. Signed-off-by: Jonathan Marek Reviewed-by: Rob Herring Reviewed-by: Sibi Sankar Link: https://lore.kernel.org/r/20200728023811.5607-3-jonathan@marek.ca Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sm8150.h | 162 +++++++++++++++++++++++++ 1 file changed, 162 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,sm8150.h (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sm8150.h b/include/dt-bindings/interconnect/qcom,sm8150.h new file mode 100644 index 000000000000..a25684680c42 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sm8150.h @@ -0,0 +1,162 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Qualcomm SM8150 interconnect IDs + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM8150_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SM8150_H + +#define MASTER_A1NOC_CFG 0 +#define MASTER_QUP_0 1 +#define MASTER_EMAC 2 +#define MASTER_UFS_MEM 3 +#define MASTER_USB3 4 +#define MASTER_USB3_1 5 +#define A1NOC_SNOC_SLV 6 +#define SLAVE_SERVICE_A1NOC 7 + +#define MASTER_A2NOC_CFG 0 +#define MASTER_QDSS_BAM 1 +#define MASTER_QSPI 2 +#define MASTER_QUP_1 3 +#define MASTER_QUP_2 4 +#define MASTER_SENSORS_AHB 5 +#define MASTER_TSIF 6 +#define MASTER_CNOC_A2NOC 7 +#define MASTER_CRYPTO_CORE_0 8 +#define MASTER_IPA 9 +#define MASTER_PCIE 10 +#define MASTER_PCIE_1 11 +#define MASTER_QDSS_ETR 12 +#define MASTER_SDCC_2 13 +#define MASTER_SDCC_4 14 +#define A2NOC_SNOC_SLV 15 +#define SLAVE_ANOC_PCIE_GEM_NOC 16 +#define SLAVE_SERVICE_A2NOC 17 + +#define MASTER_CAMNOC_HF0_UNCOMP 0 +#define MASTER_CAMNOC_HF1_UNCOMP 1 +#define MASTER_CAMNOC_SF_UNCOMP 2 +#define SLAVE_CAMNOC_UNCOMP 3 + +#define MASTER_NPU 0 +#define SLAVE_CDSP_MEM_NOC 1 + +#define MASTER_SPDM 0 +#define SNOC_CNOC_MAS 1 +#define MASTER_QDSS_DAP 2 +#define SLAVE_A1NOC_CFG 3 +#define SLAVE_A2NOC_CFG 4 +#define SLAVE_AHB2PHY_SOUTH 5 +#define SLAVE_AOP 6 +#define SLAVE_AOSS 7 +#define SLAVE_CAMERA_CFG 8 +#define SLAVE_CLK_CTL 9 +#define SLAVE_CDSP_CFG 10 +#define SLAVE_RBCPR_CX_CFG 11 +#define SLAVE_RBCPR_MMCX_CFG 12 +#define SLAVE_RBCPR_MX_CFG 13 +#define SLAVE_CRYPTO_0_CFG 14 +#define SLAVE_CNOC_DDRSS 15 +#define SLAVE_DISPLAY_CFG 16 +#define SLAVE_EMAC_CFG 17 +#define SLAVE_GLM 18 +#define SLAVE_GRAPHICS_3D_CFG 19 +#define SLAVE_IMEM_CFG 20 +#define SLAVE_IPA_CFG 21 +#define SLAVE_CNOC_MNOC_CFG 22 +#define SLAVE_NPU_CFG 23 +#define SLAVE_PCIE_0_CFG 24 +#define SLAVE_PCIE_1_CFG 25 +#define SLAVE_NORTH_PHY_CFG 26 +#define SLAVE_PIMEM_CFG 27 +#define SLAVE_PRNG 28 +#define SLAVE_QDSS_CFG 29 +#define SLAVE_QSPI 30 +#define SLAVE_QUP_2 31 +#define SLAVE_QUP_1 32 +#define SLAVE_QUP_0 33 +#define SLAVE_SDCC_2 34 +#define SLAVE_SDCC_4 35 +#define SLAVE_SNOC_CFG 36 +#define SLAVE_SPDM_WRAPPER 37 +#define SLAVE_SPSS_CFG 38 +#define SLAVE_SSC_CFG 39 +#define SLAVE_TCSR 40 +#define SLAVE_TLMM_EAST 41 +#define SLAVE_TLMM_NORTH 42 +#define SLAVE_TLMM_SOUTH 43 +#define SLAVE_TLMM_WEST 44 +#define SLAVE_TSIF 45 +#define SLAVE_UFS_CARD_CFG 46 +#define SLAVE_UFS_MEM_CFG 47 +#define SLAVE_USB3 48 +#define SLAVE_USB3_1 49 +#define SLAVE_VENUS_CFG 50 +#define SLAVE_VSENSE_CTRL_CFG 51 +#define SLAVE_CNOC_A2NOC 52 +#define SLAVE_SERVICE_CNOC 53 + +#define MASTER_CNOC_DC_NOC 0 +#define SLAVE_LLCC_CFG 1 +#define SLAVE_GEM_NOC_CFG 2 + +#define MASTER_AMPSS_M0 0 +#define MASTER_GPU_TCU 1 +#define MASTER_SYS_TCU 2 +#define MASTER_GEM_NOC_CFG 3 +#define MASTER_COMPUTE_NOC 4 +#define MASTER_GRAPHICS_3D 5 +#define MASTER_MNOC_HF_MEM_NOC 6 +#define MASTER_MNOC_SF_MEM_NOC 7 +#define MASTER_GEM_NOC_PCIE_SNOC 8 +#define MASTER_SNOC_GC_MEM_NOC 9 +#define MASTER_SNOC_SF_MEM_NOC 10 +#define MASTER_ECC 11 +#define SLAVE_MSS_PROC_MS_MPU_CFG 12 +#define SLAVE_ECC 13 +#define SLAVE_GEM_NOC_SNOC 14 +#define SLAVE_LLCC 15 +#define SLAVE_SERVICE_GEM_NOC 16 + +#define MASTER_IPA_CORE 0 +#define SLAVE_IPA_CORE 1 + +#define MASTER_LLCC 0 +#define SLAVE_EBI_CH0 1 + +#define MASTER_CNOC_MNOC_CFG 0 +#define MASTER_CAMNOC_HF0 1 +#define MASTER_CAMNOC_HF1 2 +#define MASTER_CAMNOC_SF 3 +#define MASTER_MDP_PORT0 4 +#define MASTER_MDP_PORT1 5 +#define MASTER_ROTATOR 6 +#define MASTER_VIDEO_P0 7 +#define MASTER_VIDEO_P1 8 +#define MASTER_VIDEO_PROC 9 +#define SLAVE_MNOC_SF_MEM_NOC 10 +#define SLAVE_MNOC_HF_MEM_NOC 11 +#define SLAVE_SERVICE_MNOC 12 + +#define MASTER_SNOC_CFG 0 +#define A1NOC_SNOC_MAS 1 +#define A2NOC_SNOC_MAS 2 +#define MASTER_GEM_NOC_SNOC 3 +#define MASTER_PIMEM 4 +#define MASTER_GIC 5 +#define SLAVE_APPSS 6 +#define SNOC_CNOC_SLV 7 +#define SLAVE_SNOC_GEM_NOC_GC 8 +#define SLAVE_SNOC_GEM_NOC_SF 9 +#define SLAVE_OCIMEM 10 +#define SLAVE_PIMEM 11 +#define SLAVE_SERVICE_SNOC 12 +#define SLAVE_PCIE_0 13 +#define SLAVE_PCIE_1 14 +#define SLAVE_QDSS_STM 15 +#define SLAVE_TCU 16 + +#endif -- cgit v1.2.3 From cb6ffd717c9ea48f2a4f577bb128a51b3ed33fc3 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Mon, 27 Jul 2020 22:38:02 -0400 Subject: dt-bindings: interconnect: Add Qualcomm SM8250 DT bindings The Qualcomm SM8250 platform has several bus fabrics that could be controlled and tuned dynamically according to the bandwidth demand. Signed-off-by: Jonathan Marek Reviewed-by: Rob Herring Reviewed-by: Sibi Sankar Link: https://lore.kernel.org/r/20200728023811.5607-4-jonathan@marek.ca Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sm8250.h | 172 +++++++++++++++++++++++++ 1 file changed, 172 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,sm8250.h (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sm8250.h b/include/dt-bindings/interconnect/qcom,sm8250.h new file mode 100644 index 000000000000..1b4d9fbe888d --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sm8250.h @@ -0,0 +1,172 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Qualcomm SM8250 interconnect IDs + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM8250_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SM8250_H + +#define MASTER_A1NOC_CFG 0 +#define MASTER_QSPI_0 1 +#define MASTER_QUP_1 2 +#define MASTER_QUP_2 3 +#define MASTER_TSIF 4 +#define MASTER_PCIE_2 5 +#define MASTER_SDCC_4 6 +#define MASTER_UFS_MEM 7 +#define MASTER_USB3 8 +#define MASTER_USB3_1 9 +#define A1NOC_SNOC_SLV 10 +#define SLAVE_ANOC_PCIE_GEM_NOC_1 11 +#define SLAVE_SERVICE_A1NOC 12 + +#define MASTER_A2NOC_CFG 0 +#define MASTER_QDSS_BAM 1 +#define MASTER_QUP_0 2 +#define MASTER_CNOC_A2NOC 3 +#define MASTER_CRYPTO_CORE_0 4 +#define MASTER_IPA 5 +#define MASTER_PCIE 6 +#define MASTER_PCIE_1 7 +#define MASTER_QDSS_ETR 8 +#define MASTER_SDCC_2 9 +#define MASTER_UFS_CARD 10 +#define A2NOC_SNOC_SLV 11 +#define SLAVE_ANOC_PCIE_GEM_NOC 12 +#define SLAVE_SERVICE_A2NOC 13 + +#define MASTER_NPU 0 +#define SLAVE_CDSP_MEM_NOC 1 + +#define SNOC_CNOC_MAS 0 +#define MASTER_QDSS_DAP 1 +#define SLAVE_A1NOC_CFG 2 +#define SLAVE_A2NOC_CFG 3 +#define SLAVE_AHB2PHY_SOUTH 4 +#define SLAVE_AHB2PHY_NORTH 5 +#define SLAVE_AOSS 6 +#define SLAVE_CAMERA_CFG 7 +#define SLAVE_CLK_CTL 8 +#define SLAVE_CDSP_CFG 9 +#define SLAVE_RBCPR_CX_CFG 10 +#define SLAVE_RBCPR_MMCX_CFG 11 +#define SLAVE_RBCPR_MX_CFG 12 +#define SLAVE_CRYPTO_0_CFG 13 +#define SLAVE_CX_RDPM 14 +#define SLAVE_DCC_CFG 15 +#define SLAVE_CNOC_DDRSS 16 +#define SLAVE_DISPLAY_CFG 17 +#define SLAVE_GRAPHICS_3D_CFG 18 +#define SLAVE_IMEM_CFG 19 +#define SLAVE_IPA_CFG 20 +#define SLAVE_IPC_ROUTER_CFG 21 +#define SLAVE_LPASS 22 +#define SLAVE_CNOC_MNOC_CFG 23 +#define SLAVE_NPU_CFG 24 +#define SLAVE_PCIE_0_CFG 25 +#define SLAVE_PCIE_1_CFG 26 +#define SLAVE_PCIE_2_CFG 27 +#define SLAVE_PDM 28 +#define SLAVE_PIMEM_CFG 29 +#define SLAVE_PRNG 30 +#define SLAVE_QDSS_CFG 31 +#define SLAVE_QSPI_0 32 +#define SLAVE_QUP_0 33 +#define SLAVE_QUP_1 34 +#define SLAVE_QUP_2 35 +#define SLAVE_SDCC_2 36 +#define SLAVE_SDCC_4 37 +#define SLAVE_SNOC_CFG 38 +#define SLAVE_TCSR 39 +#define SLAVE_TLMM_NORTH 40 +#define SLAVE_TLMM_SOUTH 41 +#define SLAVE_TLMM_WEST 42 +#define SLAVE_TSIF 43 +#define SLAVE_UFS_CARD_CFG 44 +#define SLAVE_UFS_MEM_CFG 45 +#define SLAVE_USB3 46 +#define SLAVE_USB3_1 47 +#define SLAVE_VENUS_CFG 48 +#define SLAVE_VSENSE_CTRL_CFG 49 +#define SLAVE_CNOC_A2NOC 50 +#define SLAVE_SERVICE_CNOC 51 + +#define MASTER_CNOC_DC_NOC 0 +#define SLAVE_LLCC_CFG 1 +#define SLAVE_GEM_NOC_CFG 2 + +#define MASTER_GPU_TCU 0 +#define MASTER_SYS_TCU 1 +#define MASTER_AMPSS_M0 2 +#define MASTER_GEM_NOC_CFG 3 +#define MASTER_COMPUTE_NOC 4 +#define MASTER_GRAPHICS_3D 5 +#define MASTER_MNOC_HF_MEM_NOC 6 +#define MASTER_MNOC_SF_MEM_NOC 7 +#define MASTER_ANOC_PCIE_GEM_NOC 8 +#define MASTER_SNOC_GC_MEM_NOC 9 +#define MASTER_SNOC_SF_MEM_NOC 10 +#define SLAVE_GEM_NOC_SNOC 11 +#define SLAVE_LLCC 12 +#define SLAVE_MEM_NOC_PCIE_SNOC 13 +#define SLAVE_SERVICE_GEM_NOC_1 14 +#define SLAVE_SERVICE_GEM_NOC_2 15 +#define SLAVE_SERVICE_GEM_NOC 16 + +#define MASTER_IPA_CORE 0 +#define SLAVE_IPA_CORE 1 + +#define MASTER_LLCC 0 +#define SLAVE_EBI_CH0 1 + +#define MASTER_CNOC_MNOC_CFG 0 +#define MASTER_CAMNOC_HF 1 +#define MASTER_CAMNOC_ICP 2 +#define MASTER_CAMNOC_SF 3 +#define MASTER_VIDEO_P0 4 +#define MASTER_VIDEO_P1 5 +#define MASTER_VIDEO_PROC 6 +#define MASTER_MDP_PORT0 7 +#define MASTER_MDP_PORT1 8 +#define MASTER_ROTATOR 9 +#define SLAVE_MNOC_HF_MEM_NOC 10 +#define SLAVE_MNOC_SF_MEM_NOC 11 +#define SLAVE_SERVICE_MNOC 12 + +#define MASTER_NPU_SYS 0 +#define MASTER_NPU_CDP 1 +#define MASTER_NPU_NOC_CFG 2 +#define SLAVE_NPU_CAL_DP0 3 +#define SLAVE_NPU_CAL_DP1 4 +#define SLAVE_NPU_CP 5 +#define SLAVE_NPU_INT_DMA_BWMON_CFG 6 +#define SLAVE_NPU_DPM 7 +#define SLAVE_ISENSE_CFG 8 +#define SLAVE_NPU_LLM_CFG 9 +#define SLAVE_NPU_TCM 10 +#define SLAVE_NPU_COMPUTE_NOC 11 +#define SLAVE_SERVICE_NPU_NOC 12 + +#define MASTER_SNOC_CFG 0 +#define A1NOC_SNOC_MAS 1 +#define A2NOC_SNOC_MAS 2 +#define MASTER_GEM_NOC_SNOC 3 +#define MASTER_GEM_NOC_PCIE_SNOC 4 +#define MASTER_PIMEM 5 +#define MASTER_GIC 6 +#define SLAVE_APPSS 7 +#define SNOC_CNOC_SLV 8 +#define SLAVE_SNOC_GEM_NOC_GC 9 +#define SLAVE_SNOC_GEM_NOC_SF 10 +#define SLAVE_OCIMEM 11 +#define SLAVE_PIMEM 12 +#define SLAVE_SERVICE_SNOC 13 +#define SLAVE_PCIE_0 14 +#define SLAVE_PCIE_1 15 +#define SLAVE_PCIE_2 16 +#define SLAVE_QDSS_STM 17 +#define SLAVE_TCU 18 + +#endif -- cgit v1.2.3 From 65e0e4d67983dca775fc9ea39f092bc76caa495f Mon Sep 17 00:00:00 2001 From: Mike Tipton Date: Thu, 3 Sep 2020 12:21:45 -0700 Subject: dt-bindings: interconnect: Add generic qcom bindings Add generic qcom interconnect bindings that are common across platforms. In particular, these include QCOM_ICC_TAG_* macros that clients can use when calling icc_set_tag(). Signed-off-by: Mike Tipton Acked-by: Rob Herring Link: https://lore.kernel.org/r/20200903192149.30385-3-mdtipton@codeaurora.org Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,icc.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,icc.h (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,icc.h b/include/dt-bindings/interconnect/qcom,icc.h new file mode 100644 index 000000000000..cd34f36daaaa --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,icc.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_ICC_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_ICC_H + +/* + * The AMC bucket denotes constraints that are applied to hardware when + * icc_set_bw() completes, whereas the WAKE and SLEEP constraints are applied + * when the execution environment transitions between active and low power mode. + */ +#define QCOM_ICC_BUCKET_AMC 0 +#define QCOM_ICC_BUCKET_WAKE 1 +#define QCOM_ICC_BUCKET_SLEEP 2 +#define QCOM_ICC_NUM_BUCKETS 3 + +#define QCOM_ICC_TAG_AMC (1 << QCOM_ICC_BUCKET_AMC) +#define QCOM_ICC_TAG_WAKE (1 << QCOM_ICC_BUCKET_WAKE) +#define QCOM_ICC_TAG_SLEEP (1 << QCOM_ICC_BUCKET_SLEEP) +#define QCOM_ICC_TAG_ACTIVE_ONLY (QCOM_ICC_TAG_AMC | QCOM_ICC_TAG_WAKE) +#define QCOM_ICC_TAG_ALWAYS (QCOM_ICC_TAG_AMC | QCOM_ICC_TAG_WAKE |\ + QCOM_ICC_TAG_SLEEP) + +#endif -- cgit v1.2.3 From 1521e22bfa12db6225002ba3b040572a78dff996 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Thu, 3 Sep 2020 16:31:28 +0300 Subject: interconnect: Introduce xlate_extended() callback Currently there is the xlate() callback, which is used by providers for mapping the nodes from phandle arguments. That's fine for simple mappings, but the phandle arguments could contain an additional data, such as tag information. Let's create another callback xlate_extended() for the cases where providers want also populate the path tag data. Tested-by: Sibi Sankar Reviewed-by: Sibi Sankar Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20200903133134.17201-2-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 4735518de515..4d535fddd5d3 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -14,6 +14,17 @@ struct icc_node; struct of_phandle_args; +/** + * struct icc_node_data - icc node data + * + * @node: icc node + * @tag: tag + */ +struct icc_node_data { + struct icc_node *node; + u32 tag; +}; + /** * struct icc_onecell_data - driver data for onecell interconnect providers * @@ -39,6 +50,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec, * @pre_aggregate: pointer to device specific function that is called * before the aggregation begins (optional) * @xlate: provider-specific callback for mapping nodes from phandle arguments + * @xlate_extended: vendor-specific callback for mapping node data from phandle arguments * @dev: the device this interconnect provider belongs to * @users: count of active users * @inter_set: whether inter-provider pairs will be configured with @set @@ -52,6 +64,7 @@ struct icc_provider { u32 peak_bw, u32 *agg_avg, u32 *agg_peak); void (*pre_aggregate)(struct icc_node *node); struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data); + struct icc_node_data* (*xlate_extended)(struct of_phandle_args *spec, void *data); struct device *dev; int users; bool inter_set; @@ -105,7 +118,7 @@ void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); int icc_provider_add(struct icc_provider *provider); int icc_provider_del(struct icc_provider *provider); -struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec); +struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); #else @@ -157,7 +170,7 @@ static inline int icc_provider_del(struct icc_provider *provider) return -ENOTSUPP; } -static inline struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec) +static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) { return ERR_PTR(-ENOTSUPP); } -- cgit v1.2.3 From c4877059e0a4b88b59bc208f2608dc489553cf29 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Tue, 8 Sep 2020 16:29:01 +0300 Subject: dt-bindings: interconnect: Add EPSS L3 DT binding on SM8250 Add Epoch Subsystem (EPSS) L3 interconnect provider binding on SM8250 SoCs. Signed-off-by: Sibi Sankar Acked-by: Rob Herring Link: https://lore.kernel.org/r/20200801123049.32398-5-sibis@codeaurora.org Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,osm-l3.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,osm-l3.h b/include/dt-bindings/interconnect/qcom,osm-l3.h index 54858ff7674d..61ef649ae565 100644 --- a/include/dt-bindings/interconnect/qcom,osm-l3.h +++ b/include/dt-bindings/interconnect/qcom,osm-l3.h @@ -9,4 +9,7 @@ #define MASTER_OSM_L3_APPS 0 #define SLAVE_OSM_L3 1 +#define MASTER_EPSS_L3_APPS 0 +#define SLAVE_EPSS_L3_SHARED 1 + #endif -- cgit v1.2.3 From b131c96496b369c7b14125e7c50e89ac7cec8051 Mon Sep 17 00:00:00 2001 From: "Jose M. Guisado Gomez" Date: Tue, 8 Sep 2020 13:01:41 +0200 Subject: netfilter: nf_tables: add userdata support for nft_object Enables storing userdata for nft_object. Initially this will store an optional comment but can be extended in the future as needed. Adds new attribute NFTA_OBJ_USERDATA to nft_object. Signed-off-by: Jose M. Guisado Gomez Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ include/uapi/linux/netfilter/nf_tables.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 97a7e147a59a..99c1b3188b1e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1123,6 +1123,8 @@ struct nft_object { u32 genmask:2, use:30; u64 handle; + u16 udlen; + u8 *udata; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 543dc697b796..2a6e09dea1a0 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1559,6 +1559,7 @@ enum nft_ct_expectation_attributes { * @NFTA_OBJ_DATA: stateful object data (NLA_NESTED) * @NFTA_OBJ_USE: number of references to this expression (NLA_U32) * @NFTA_OBJ_HANDLE: object handle (NLA_U64) + * @NFTA_OBJ_USERDATA: user data (NLA_BINARY) */ enum nft_object_attributes { NFTA_OBJ_UNSPEC, @@ -1569,6 +1570,7 @@ enum nft_object_attributes { NFTA_OBJ_USE, NFTA_OBJ_HANDLE, NFTA_OBJ_PAD, + NFTA_OBJ_USERDATA, __NFTA_OBJ_MAX }; #define NFTA_OBJ_MAX (__NFTA_OBJ_MAX - 1) -- cgit v1.2.3 From a8803055127afb87640974adedac60435592b86d Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 7 Sep 2020 18:46:55 +0100 Subject: firmware: arm_scmi: Add system power protocol support Add bare protocol support for SCMI system power protocol as needed by an OSPM agent: basic initialization and SYSTEM_POWER_STATE_NOTIFIER core notification support. No event-handling logic is attached to such notification.. Link: https://lore.kernel.org/r/20200907174657.32466-2-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 05570afc7f74..4b10093ad671 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -292,6 +292,7 @@ struct scmi_handle { void *sensor_priv; void *reset_priv; void *notify_priv; + void *system_priv; }; enum scmi_std_protocol { @@ -304,6 +305,15 @@ enum scmi_std_protocol { SCMI_PROTOCOL_RESET = 0x16, }; +enum scmi_system_events { + SCMI_SYSTEM_SHUTDOWN, + SCMI_SYSTEM_COLDRESET, + SCMI_SYSTEM_WARMRESET, + SCMI_SYSTEM_POWERUP, + SCMI_SYSTEM_SUSPEND, + SCMI_SYSTEM_MAX +}; + struct scmi_device { u32 id; u8 protocol_id; @@ -378,6 +388,7 @@ enum scmi_notification_events { SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0, SCMI_EVENT_RESET_ISSUED = 0x0, SCMI_EVENT_BASE_ERROR_EVENT = 0x0, + SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER = 0x0, }; struct scmi_power_state_changed_report { @@ -387,6 +398,13 @@ struct scmi_power_state_changed_report { unsigned int power_state; }; +struct scmi_system_power_state_notifier_report { + ktime_t timestamp; + unsigned int agent_id; + unsigned int flags; + unsigned int system_state; +}; + struct scmi_perf_limits_report { ktime_t timestamp; unsigned int agent_id; -- cgit v1.2.3 From 245500d853e9f20036cec7df4f6984ece4c6bf26 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 1 Jul 2020 11:15:32 +0100 Subject: rxrpc: Rewrite the client connection manager Rewrite the rxrpc client connection manager so that it can support multiple connections for a given security key to a peer. The following changes are made: (1) For each open socket, the code currently maintains an rbtree with the connections placed into it, keyed by communications parameters. This is tricky to maintain as connections can be culled from the tree or replaced within it. Connections can require replacement for a number of reasons, e.g. their IDs span too great a range for the IDR data type to represent efficiently, the call ID numbers on that conn would overflow or the conn got aborted. This is changed so that there's now a connection bundle object placed in the tree, keyed on the same parameters. The bundle, however, does not need to be replaced. (2) An rxrpc_bundle object can now manage the available channels for a set of parallel connections. The lock that manages this is moved there from the rxrpc_connection struct (channel_lock). (3) There'a a dummy bundle for all incoming connections to share so that they have a channel_lock too. It might be better to give each incoming connection its own bundle. This bundle is not needed to manage which channels incoming calls are made on because that's the solely at whim of the client. (4) The restrictions on how many client connections are around are removed. Instead, a previous patch limits the number of client calls that can be allocated. Ordinarily, client connections are reaped after 2 minutes on the idle queue, but when more than a certain number of connections are in existence, the reaper starts reaping them after 2s of idleness instead to get the numbers back down. It could also be made such that new call allocations are forced to wait until the number of outstanding connections subsides. Signed-off-by: David Howells --- include/trace/events/rxrpc.h | 33 ++++----------------------------- 1 file changed, 4 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index c33079b986e8..3b67d5981224 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -68,21 +68,14 @@ enum rxrpc_client_trace { rxrpc_client_chan_activate, rxrpc_client_chan_disconnect, rxrpc_client_chan_pass, - rxrpc_client_chan_unstarted, rxrpc_client_chan_wait_failed, rxrpc_client_cleanup, - rxrpc_client_count, rxrpc_client_discard, rxrpc_client_duplicate, rxrpc_client_exposed, rxrpc_client_replace, rxrpc_client_to_active, - rxrpc_client_to_culled, rxrpc_client_to_idle, - rxrpc_client_to_inactive, - rxrpc_client_to_upgrade, - rxrpc_client_to_waiting, - rxrpc_client_uncount, }; enum rxrpc_call_trace { @@ -271,29 +264,14 @@ enum rxrpc_tx_point { EM(rxrpc_client_chan_activate, "ChActv") \ EM(rxrpc_client_chan_disconnect, "ChDisc") \ EM(rxrpc_client_chan_pass, "ChPass") \ - EM(rxrpc_client_chan_unstarted, "ChUnst") \ EM(rxrpc_client_chan_wait_failed, "ChWtFl") \ EM(rxrpc_client_cleanup, "Clean ") \ - EM(rxrpc_client_count, "Count ") \ EM(rxrpc_client_discard, "Discar") \ EM(rxrpc_client_duplicate, "Duplic") \ EM(rxrpc_client_exposed, "Expose") \ EM(rxrpc_client_replace, "Replac") \ EM(rxrpc_client_to_active, "->Actv") \ - EM(rxrpc_client_to_culled, "->Cull") \ - EM(rxrpc_client_to_idle, "->Idle") \ - EM(rxrpc_client_to_inactive, "->Inac") \ - EM(rxrpc_client_to_upgrade, "->Upgd") \ - EM(rxrpc_client_to_waiting, "->Wait") \ - E_(rxrpc_client_uncount, "Uncoun") - -#define rxrpc_conn_cache_states \ - EM(RXRPC_CONN_CLIENT_INACTIVE, "Inac") \ - EM(RXRPC_CONN_CLIENT_WAITING, "Wait") \ - EM(RXRPC_CONN_CLIENT_ACTIVE, "Actv") \ - EM(RXRPC_CONN_CLIENT_UPGRADE, "Upgd") \ - EM(RXRPC_CONN_CLIENT_CULLED, "Cull") \ - E_(RXRPC_CONN_CLIENT_IDLE, "Idle") \ + E_(rxrpc_client_to_idle, "->Idle") #define rxrpc_call_traces \ EM(rxrpc_call_connected, "CON") \ @@ -594,23 +572,20 @@ TRACE_EVENT(rxrpc_client, __field(int, channel ) __field(int, usage ) __field(enum rxrpc_client_trace, op ) - __field(enum rxrpc_conn_cache_state, cs ) ), TP_fast_assign( - __entry->conn = conn->debug_id; + __entry->conn = conn ? conn->debug_id : 0; __entry->channel = channel; - __entry->usage = atomic_read(&conn->usage); + __entry->usage = conn ? atomic_read(&conn->usage) : -2; __entry->op = op; __entry->cid = conn->proto.cid; - __entry->cs = conn->cache_state; ), - TP_printk("C=%08x h=%2d %s %s i=%08x u=%d", + TP_printk("C=%08x h=%2d %s i=%08x u=%d", __entry->conn, __entry->channel, __print_symbolic(__entry->op, rxrpc_client_traces), - __print_symbolic(__entry->cs, rxrpc_conn_cache_states), __entry->cid, __entry->usage) ); -- cgit v1.2.3 From ecfe6953fa00115414a6fefe49023a1ebc187a98 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 8 Sep 2020 06:46:18 +1000 Subject: drm/ttm: introduce ttm_bo_move_null MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This pattern is cut-n-pasted across 4 drivers, switch it to a WARN_ON instead, as BUG_ON is considered a bad idea usually. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-2-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index a694388f7b13..ebba282667ba 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -520,6 +520,23 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo spin_unlock(&ttm_bo_glob.lru_lock); } +/** + * ttm_bo_move_null = assign memory for a buffer object. + * @bo: The bo to assign the memory to + * @new_mem: The memory to be assigned. + * + * Assign the memory from new_mem to the memory of the buffer object bo. + */ +static inline void ttm_bo_move_null(struct ttm_buffer_object *bo, + struct ttm_resource *new_mem) +{ + struct ttm_resource *old_mem = &bo->mem; + + WARN_ON(old_mem->mm_node != NULL); + *old_mem = *new_mem; + new_mem->mm_node = NULL; +} + /** * ttm_bo_unreserve * -- cgit v1.2.3 From 86008a7553e6c57268e4a4f71e3a43e73b1b3ef1 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 8 Sep 2020 06:46:19 +1000 Subject: drm/ttm: add optional bind/unbind via driver. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I want to remove the backend funcs Reviewed-by: Christian König Signed-off-by: Dave Airlie Reviewed-by: Ben Skeggs Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-3-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index ebba282667ba..32c0651cc0fd 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -90,6 +90,42 @@ struct ttm_bo_driver { */ void (*ttm_tt_unpopulate)(struct ttm_bo_device *bdev, struct ttm_tt *ttm); + /** + * ttm_tt_bind + * + * @bdev: Pointer to a ttm device + * @ttm: Pointer to a struct ttm_tt. + * @bo_mem: Pointer to a struct ttm_resource describing the + * memory type and location for binding. + * + * Bind the backend pages into the aperture in the location + * indicated by @bo_mem. This function should be able to handle + * differences between aperture and system page sizes. + */ + int (*ttm_tt_bind)(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *bo_mem); + + /** + * ttm_tt_unbind + * + * @bdev: Pointer to a ttm device + * @ttm: Pointer to a struct ttm_tt. + * + * Unbind previously bound backend pages. This function should be + * able to handle differences between aperture and system page sizes. + */ + void (*ttm_tt_unbind)(struct ttm_bo_device *bdev, struct ttm_tt *ttm); + + /** + * ttm_tt_destroy + * + * @bdev: Pointer to a ttm device + * @ttm: Pointer to a struct ttm_tt. + * + * Destroy the backend. This will be call back from ttm_tt_destroy so + * don't call ttm_tt_destroy from the callback or infinite loop. + */ + void (*ttm_tt_destroy)(struct ttm_bo_device *bdev, struct ttm_tt *ttm); + /** * struct ttm_bo_driver member eviction_valuable * -- cgit v1.2.3 From 738edc0adb388f75aec67011f6e8f225b9f29783 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 8 Sep 2020 06:46:21 +1000 Subject: drm/ttm/agp: export bind/unbind/destroy for drivers to use. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-5-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 6bda88f8da46..5a34f1640865 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -266,6 +266,12 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo, uint32_t page_flags); int ttm_agp_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm); +int ttm_agp_bind(struct ttm_bo_device *bdev, + struct ttm_tt *ttm, struct ttm_resource *bo_mem); +void ttm_agp_unbind(struct ttm_bo_device *bdev, + struct ttm_tt *ttm); +void ttm_agp_destroy(struct ttm_bo_device *bdev, + struct ttm_tt *ttm); #endif #endif -- cgit v1.2.3 From 434825546e458325d8bdd3be08390d8cc214c64f Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 8 Sep 2020 06:46:28 +1000 Subject: drm/ttm: get rid of agp specific populate/unpopulate paths. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-12-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 5a34f1640865..591d4927d501 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -264,8 +264,6 @@ void ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm); struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo, struct agp_bridge_data *bridge, uint32_t page_flags); -int ttm_agp_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); -void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm); int ttm_agp_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *bo_mem); void ttm_agp_unbind(struct ttm_bo_device *bdev, -- cgit v1.2.3 From 48efa57e4f1b5c9ecb240f58f790d9872533f953 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 8 Sep 2020 06:46:29 +1000 Subject: drm/ttm/agp: remove bdev from agp helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since the agp bind/unbind/destroy are now getting called from drivers rather than via the func table, drop the bdev parameter. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-13-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 591d4927d501..bdc8aadf3246 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -264,12 +264,9 @@ void ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm); struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo, struct agp_bridge_data *bridge, uint32_t page_flags); -int ttm_agp_bind(struct ttm_bo_device *bdev, - struct ttm_tt *ttm, struct ttm_resource *bo_mem); -void ttm_agp_unbind(struct ttm_bo_device *bdev, - struct ttm_tt *ttm); -void ttm_agp_destroy(struct ttm_bo_device *bdev, - struct ttm_tt *ttm); +int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem); +void ttm_agp_unbind(struct ttm_tt *ttm); +void ttm_agp_destroy(struct ttm_tt *ttm); #endif #endif -- cgit v1.2.3 From 04e89ff364dec3dc261243c2f0780635448bc466 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 8 Sep 2020 06:46:30 +1000 Subject: drm/ttm: drop the tt backend function paths. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These are now driver side. Reviewed-by: Christian König Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-14-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 39 --------------------------------------- 1 file changed, 39 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index bdc8aadf3246..146544ba1c10 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -48,47 +48,9 @@ enum ttm_caching_state { tt_cached }; -struct ttm_backend_func { - /** - * struct ttm_backend_func member bind - * - * @ttm: Pointer to a struct ttm_tt. - * @bo_mem: Pointer to a struct ttm_resource describing the - * memory type and location for binding. - * - * Bind the backend pages into the aperture in the location - * indicated by @bo_mem. This function should be able to handle - * differences between aperture and system page sizes. - */ - int (*bind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *bo_mem); - - /** - * struct ttm_backend_func member unbind - * - * @ttm: Pointer to a struct ttm_tt. - * - * Unbind previously bound backend pages. This function should be - * able to handle differences between aperture and system page sizes. - */ - void (*unbind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm); - - /** - * struct ttm_backend_func member destroy - * - * @ttm: Pointer to a struct ttm_tt. - * - * Destroy the backend. This will be call back from ttm_tt_destroy so - * don't call ttm_tt_destroy from the callback or infinite loop. - */ - void (*destroy) (struct ttm_bo_device *bdev, struct ttm_tt *ttm); -}; - /** * struct ttm_tt * - * @func: Pointer to a struct ttm_backend_func that describes - * the backend methods. - * pointer. * @pages: Array of pages backing the data. * @num_pages: Number of pages in the page array. * @bdev: Pointer to the current struct ttm_bo_device. @@ -102,7 +64,6 @@ struct ttm_backend_func { * memory. */ struct ttm_tt { - struct ttm_backend_func *func; struct page **pages; uint32_t page_flags; unsigned long num_pages; -- cgit v1.2.3 From cd80ec795156346236e9b1cd9f5cbff5a9bbd212 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 8 Sep 2020 09:33:56 -0700 Subject: Input: allocate keycodes for notification-center, pickup-phone and hangup-phone New Lenovo Thinkpad models, e.g. the X1 Carbon 8th gen and the new T14 gen1 models have 3 new symbols / shortcuts on their F9-F11 keys (and the thinkpad_acpi driver receives 3 new "scancodes" for these): F9: Has a symbol resembling a rectangular speech balloon, the manual says the hotkey functions shows or hides the notification center F10: Has a symbol of a telephone horn which has been picked up from the receiver, the manual says: "Answer incoming calls" F11: Has a symbol of a telephone horn which is resting on the receiver, the manual says: "Decline incoming calls" We have no existing keycodes which are a good match for these, so add 3 new keycodes for these. I noticed that we have a hole in our keycodes between 0x1ba and 0x1c0 which does not seem to be reserved for any specific purpose, so these new 3 codes use 0x1bc - 0x1be, instead of starting at 0x27b. Acked-by: Henrique de Moraes Holschuh Acked-by: Andy Shevchenko Signed-off-by: Hans de Goede Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 0c2e27d28e0a..b74821d09145 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -515,6 +515,9 @@ #define KEY_10CHANNELSUP 0x1b8 /* 10 channels up (10+) */ #define KEY_10CHANNELSDOWN 0x1b9 /* 10 channels down (10-) */ #define KEY_IMAGES 0x1ba /* AL Image Browser */ +#define KEY_NOTIFICATION_CENTER 0x1bc /* Show/hide the notification center */ +#define KEY_PICKUP_PHONE 0x1bd /* Answer incoming call */ +#define KEY_HANGUP_PHONE 0x1be /* Decline incoming call */ #define KEY_DEL_EOL 0x1c0 #define KEY_DEL_EOS 0x1c1 -- cgit v1.2.3 From bba013e1ca5e7150b42a1a1a1e852010d772edad Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 8 Sep 2020 09:58:09 -0700 Subject: Input: allocate keycode for Fn + right shift The last 2 generations of Lenovo Thinkpads send an acpi_thinkpad event when Fn + right shift is pressed. This is intended for use with "Lenovo Quick Clean" software, which disables the touchpad + kbd for 2 minutes on this key-combo so that healthcare workes can disinfect it. But there is no silkscreen print on the right-keyboard to indicate this, so add a KEY_FN_RIGHT_SHIFT keycode define to use for this key-combo. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20200908135147.4044-3-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index b74821d09145..ee93428ced9a 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -545,6 +545,7 @@ #define KEY_FN_F 0x1e2 #define KEY_FN_S 0x1e3 #define KEY_FN_B 0x1e4 +#define KEY_FN_RIGHT_SHIFT 0x1e5 #define KEY_BRL_DOT1 0x1f1 #define KEY_BRL_DOT2 0x1f2 -- cgit v1.2.3 From 4bd6a7353ee14697fea645e941354976d2c4a452 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Sep 2020 16:22:32 +0200 Subject: sysctl: Convert to iter interfaces Using the read_iter/write_iter interfaces allows for in-kernel users to set sysctls without using set_fs(). Also, the buffer is a string, so give it the real type of 'char *', not void *. [AV: Christoph's fixup folded in] Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/bpf-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 64f367044e25..82b26a1386d8 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -136,7 +136,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, - void **buf, size_t *pcount, loff_t *ppos, + char **buf, size_t *pcount, loff_t *ppos, enum bpf_attach_type type); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, -- cgit v1.2.3 From 36e2c7421f02a22f71c9283e55fdb672a9eb58e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Sep 2020 16:22:34 +0200 Subject: fs: don't allow splice read/write without explicit ops default_file_splice_write is the last piece of generic code that uses set_fs to make the uaccess routines operate on kernel pointers. It implements a "fallback loop" for splicing from files that do not actually provide a proper splice_read method. The usual file systems and other high bandwidth instances all provide a ->splice_read, so this just removes support for various device drivers and procfs/debugfs files. If splice support for any of those turns out to be important it can be added back by switching them to the iter ops and using generic_file_splice_read. Signed-off-by: Christoph Hellwig Reviewed-by: Kees Cook Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e019ea2f1347..d33cc3e8ed41 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1894,8 +1894,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From 5e6e9852d6f76e01b2e6803c74258afa5b432bc5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Sep 2020 16:22:35 +0200 Subject: uaccess: add infrastructure for kernel builds with set_fs() Add a CONFIG_SET_FS option that is selected by architecturess that implement set_fs, which is all of them initially. If the option is not set stubs for routines related to overriding the address space are provided so that architectures can start to opt out of providing set_fs. Signed-off-by: Christoph Hellwig Reviewed-by: Kees Cook Signed-off-by: Al Viro --- include/linux/uaccess.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 94b285411659..70073c802b48 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -8,6 +8,7 @@ #include +#ifdef CONFIG_SET_FS /* * Force the uaccess routines to be wired up for actual userspace access, * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone @@ -25,6 +26,23 @@ static inline void force_uaccess_end(mm_segment_t oldfs) { set_fs(oldfs); } +#else /* CONFIG_SET_FS */ +typedef struct { + /* empty dummy */ +} mm_segment_t; + +#define uaccess_kernel() (false) +#define user_addr_max() (TASK_SIZE_MAX) + +static inline mm_segment_t force_uaccess_begin(void) +{ + return (mm_segment_t) { }; +} + +static inline void force_uaccess_end(mm_segment_t oldfs) +{ +} +#endif /* CONFIG_SET_FS */ /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) -- cgit v1.2.3 From 707d561f77b5e2a6f90c9786bee44ee7a8dedc7e Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Mon, 7 Sep 2020 13:24:25 +0200 Subject: drm: allow limiting the scatter list size. Add drm_device argument to drm_prime_pages_to_sg(), so we can call dma_max_mapping_size() to figure the segment size limit and call into __sg_alloc_table_from_pages() with the correct limit. This fixes virtio-gpu with sev. Possibly it'll fix other bugs too given that drm seems to totaly ignore segment size limits so far ... v2: place max_segment in drm driver not gem object. v3: move max_segment next to the other gem fields. v4: just use dma_max_mapping_size(). Signed-off-by: Gerd Hoffmann Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20200907112425.15610-2-kraxel@redhat.com --- include/drm/drm_prime.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index 9af7422b44cf..bf141e74a1c2 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -88,7 +88,8 @@ void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr); int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma); -struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_pages); +struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, + struct page **pages, unsigned int nr_pages); struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj, int flags); -- cgit v1.2.3 From 7c69898b86b45842e1c2799df845e203c71a667e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 9 Sep 2020 09:25:33 +0200 Subject: Revert "test_firmware: Test platform fw loading on non-EFI systems" This reverts commit 18efb2f9e897ac65e7a1b2892f4a53e404534eba as it is reported to break the build: https://lore.kernel.org/r/20200909154709.619fe9bb@canb.auug.org.au Reported-by: Stephen Rothwell Fixes: 18efb2f9e897 ("test_firmware: Test platform fw loading on non-EFI systems") Cc: stable@vger.kernel.org Cc: Luis Chamberlain Cc: Scott Branden Cc: Kees Cook Link: https://lore.kernel.org/r/20200909154709.619fe9bb@canb.auug.org.au Signed-off-by: Greg Kroah-Hartman --- include/linux/efi_embedded_fw.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h index 4ad5db9f5312..57eac5241303 100644 --- a/include/linux/efi_embedded_fw.h +++ b/include/linux/efi_embedded_fw.h @@ -7,6 +7,19 @@ #define EFI_EMBEDDED_FW_PREFIX_LEN 8 +/* + * This struct and efi_embedded_fw_list are private to the efi-embedded fw + * implementation they are in this header for use by lib/test_firmware.c only! + */ +struct efi_embedded_fw { + struct list_head list; + const char *name; + const u8 *data; + size_t length; +}; + +extern struct list_head efi_embedded_fw_list; + /** * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw * code to search for embedded firmwares. -- cgit v1.2.3 From f601e8f37c2c1c52f2923fffc48204a7f7dc023d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 9 Sep 2020 09:37:40 +0200 Subject: Revert "driver core: Annotate dev_err_probe() with __must_check" This reverts commit e1f82a0dcf388d98bcc7ad195c03bd812405e6b2 as it's already starting to cause build warnings in linux-next for things that are "obviously correct". It's up to driver authors do "do the right thing" here with this function, and if they don't want to call it as the last line of a function, that's up to them, otherwise code that looks like: ret = dev_err_probe(..., ret, ...); does look really "odd". Reported-by: Stephen Rothwell Reported-by: Krzysztof Kozlowski Fixes: e1f82a0dcf38 ("driver core: Annotate dev_err_probe() with __must_check") Cc: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 85d5c28bed93..7a0938cf8bd7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -924,7 +924,7 @@ void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); extern __printf(3, 4) -int __must_check dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ -- cgit v1.2.3 From 0a355aeb24081e4538d4d424cd189f16c0bbd983 Mon Sep 17 00:00:00 2001 From: Evan Nimmo Date: Wed, 9 Sep 2020 08:32:47 +1200 Subject: i2c: algo: pca: Reapply i2c bus settings after reset If something goes wrong (such as the SCL being stuck low) then we need to reset the PCA chip. The issue with this is that on reset we lose all config settings and the chip ends up in a disabled state which results in a lock up/high CPU usage. We need to re-apply any configuration that had previously been set and re-enable the chip. Signed-off-by: Evan Nimmo Reviewed-by: Chris Packham Reviewed-by: Andy Shevchenko Signed-off-by: Wolfram Sang --- include/linux/i2c-algo-pca.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h index d03071732db4..7c522fdd9ea7 100644 --- a/include/linux/i2c-algo-pca.h +++ b/include/linux/i2c-algo-pca.h @@ -53,6 +53,20 @@ #define I2C_PCA_CON_SI 0x08 /* Serial Interrupt */ #define I2C_PCA_CON_CR 0x07 /* Clock Rate (MASK) */ +/** + * struct pca_i2c_bus_settings - The configured PCA i2c bus settings + * @mode: Configured i2c bus mode + * @tlow: Configured SCL LOW period + * @thi: Configured SCL HIGH period + * @clock_freq: The configured clock frequency + */ +struct pca_i2c_bus_settings { + int mode; + int tlow; + int thi; + int clock_freq; +}; + struct i2c_algo_pca_data { void *data; /* private low level data */ void (*write_byte) (void *data, int reg, int val); @@ -64,6 +78,7 @@ struct i2c_algo_pca_data { * For PCA9665, use the frequency you want here. */ unsigned int i2c_clock; unsigned int chip; + struct pca_i2c_bus_settings bus_settings; }; int i2c_pca_add_bus(struct i2c_adapter *); -- cgit v1.2.3 From 2a71593da34d473461f2f5c3dbb53b883596188a Mon Sep 17 00:00:00 2001 From: Alain Volmat Date: Mon, 3 Aug 2020 07:17:55 +0200 Subject: i2c: smbus: add core function handling SMBus host-notify SMBus Host-Notify protocol, from the adapter point of view consist of receiving a message from a client, including the client address and some other data. It can be simply handled by creating a new slave device and registering a callback performing the parsing of the message received from the client. This commit introduces two new core functions * i2c_new_slave_host_notify_device * i2c_free_slave_host_notify_device that take care of registration of the new slave device and callback and will call i2c_handle_smbus_host_notify once a Host-Notify event is received. Signed-off-by: Alain Volmat Reviewed-by: Pierre-Yves MORDRET Signed-off-by: Wolfram Sang --- include/linux/i2c-smbus.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 1e4e0de4ef8b..1ef421818d3a 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -38,6 +38,18 @@ static inline int of_i2c_setup_smbus_alert(struct i2c_adapter *adap) return 0; } #endif +#if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_I2C_SLAVE) +struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter); +void i2c_free_slave_host_notify_device(struct i2c_client *client); +#else +static inline struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter) +{ + return ERR_PTR(-ENOSYS); +} +static inline void i2c_free_slave_host_notify_device(struct i2c_client *client) +{ +} +#endif #if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_DMI) void i2c_register_spd(struct i2c_adapter *adap); -- cgit v1.2.3 From d284c16f84c9f8facdde25c9c077cfdcb66163d5 Mon Sep 17 00:00:00 2001 From: dillon min Date: Thu, 3 Sep 2020 15:30:22 +0800 Subject: gpio: tc35894: Disable Direct KBD interrupts to enable gpio irq On tc35894, have to disable direct keypad interrupts to make it as general purpose interrupts functionality work. if not, after chip reset, IRQST(0x91) will always 0x20, IRQN always low level, can't be clear. Configure DIRECTx to enable general purpose gpio mode, else read GPIOMISx register always zero in irq routine. verified on tc35894, need more test on other tc3589x. Signed-off-by: dillon min Acked-by: Lee Jones Signed-off-by: Bartosz Golaszewski --- include/linux/mfd/tc3589x.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index bb2b19599761..b84955410e03 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -19,6 +19,9 @@ enum tx3589x_block { #define TC3589x_RSTCTRL_KBDRST (1 << 1) #define TC3589x_RSTCTRL_GPIRST (1 << 0) +#define TC3589x_DKBDMSK_ELINT (1 << 1) +#define TC3589x_DKBDMSK_EINT (1 << 0) + /* Keyboard Configuration Registers */ #define TC3589x_KBDSETTLE_REG 0x01 #define TC3589x_KBDBOUNCE 0x02 @@ -101,6 +104,9 @@ enum tx3589x_block { #define TC3589x_GPIOODM2 0xE4 #define TC3589x_GPIOODE2 0xE5 +#define TC3589x_DIRECT0 0xEC +#define TC3589x_DKBDMSK 0xF3 + #define TC3589x_INT_GPIIRQ 0 #define TC3589x_INT_TI0IRQ 1 #define TC3589x_INT_TI1IRQ 2 -- cgit v1.2.3 From f553246f7f794675da1794ae7ee07d1f35e561ae Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 2 Sep 2020 11:17:08 +0300 Subject: RDMA/core: Change how failing destroy is handled during uobj abort Currently it triggers a WARN_ON and then goes ahead and destroys the uobject anyhow, leaking any driver memory. The only place that leaks driver memory should be during FD close() in uverbs_destroy_ufile_hw(). Drivers are only allowed to fail destroy uobjects if they guarantee destroy will eventually succeed. uverbs_destroy_ufile_hw() provides the loop to give the driver that chance. Link: https://lore.kernel.org/r/20200902081708.746631-1-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index c868609a4ffa..3781d36df31c 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1463,11 +1463,6 @@ enum rdma_remove_reason { RDMA_REMOVE_DRIVER_REMOVE, /* uobj is being cleaned-up before being committed */ RDMA_REMOVE_ABORT, - /* - * uobj has been fully created, with the uobj->object set, but is being - * cleaned up before being comitted - */ - RDMA_REMOVE_ABORT_HWOBJ, }; struct ib_rdmacg_object { -- cgit v1.2.3 From bf0835957f553aeddec896f3de386562536feee4 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 3 Sep 2020 12:41:22 +0200 Subject: ALSA: timer: Replace tasklet with work The tasklet is an old API that should be deprecated, usually can be converted to another decent API. In ALSA core timer API, the callbacks can be offlined to a tasklet when a flag is set in the timer backend. It can be achieved gracefully with a work queued in the high-prio system workqueue. This patch replaces the usage of tasklet in ALSA timer API with a simple work. Currently the tasklet feature is used only in the system timer and hrtimer backends, so both are patched to use the new flag name SNDRV_TIMER_HW_WORK, too. Link: https://lore.kernel.org/r/20200903104131.21097-3-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/timer.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/sound/timer.h b/include/sound/timer.h index 23e885d31525..760e132cc0cd 100644 --- a/include/sound/timer.h +++ b/include/sound/timer.h @@ -21,13 +21,13 @@ #define SNDRV_TIMER_HW_STOP 0x00000002 /* call stop before start */ #define SNDRV_TIMER_HW_SLAVE 0x00000004 /* only slave timer (variable resolution) */ #define SNDRV_TIMER_HW_FIRST 0x00000008 /* first tick can be incomplete */ -#define SNDRV_TIMER_HW_TASKLET 0x00000010 /* timer is called from tasklet */ +#define SNDRV_TIMER_HW_WORK 0x00000010 /* timer is called from work */ #define SNDRV_TIMER_IFLG_SLAVE 0x00000001 #define SNDRV_TIMER_IFLG_RUNNING 0x00000002 #define SNDRV_TIMER_IFLG_START 0x00000004 #define SNDRV_TIMER_IFLG_AUTO 0x00000008 /* auto restart */ -#define SNDRV_TIMER_IFLG_FAST 0x00000010 /* fast callback (do not use tasklet) */ +#define SNDRV_TIMER_IFLG_FAST 0x00000010 /* fast callback (do not use work) */ #define SNDRV_TIMER_IFLG_CALLBACK 0x00000020 /* timer callback is active */ #define SNDRV_TIMER_IFLG_EXCLUSIVE 0x00000040 /* exclusive owner - no more instances */ #define SNDRV_TIMER_IFLG_EARLY_EVENT 0x00000080 /* write early event to the poll queue */ @@ -74,7 +74,7 @@ struct snd_timer { struct list_head active_list_head; struct list_head ack_list_head; struct list_head sack_list_head; /* slow ack list head */ - struct tasklet_struct task_queue; + struct work_struct task_work; int max_instances; /* upper limit of timer instances */ int num_instances; /* current number of timer instances */ }; @@ -96,7 +96,7 @@ struct snd_timer_instance { unsigned long ticks; /* auto-load ticks when expired */ unsigned long cticks; /* current ticks */ unsigned long pticks; /* accumulated ticks for callback */ - unsigned long resolution; /* current resolution for tasklet */ + unsigned long resolution; /* current resolution for work */ unsigned long lost; /* lost ticks */ int slave_class; unsigned int slave_id; -- cgit v1.2.3 From 5554743d88483934cabff45943913be0830e66bc Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 9 Sep 2020 21:57:44 +0800 Subject: ALSA: pcm: Remove unused inline function snd_mask_sizeof There is no caller in tree, so can remove it. Signed-off-by: YueHaibing Link: https://lore.kernel.org/r/20200909135744.33464-1-yuehaibing@huawei.com Signed-off-by: Takashi Iwai --- include/sound/pcm_params.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h index 36f94735d23d..ba184f49f7e1 100644 --- a/include/sound/pcm_params.h +++ b/include/sound/pcm_params.h @@ -23,11 +23,6 @@ int snd_pcm_hw_param_value(const struct snd_pcm_hw_params *params, #define MASK_OFS(i) ((i) >> 5) #define MASK_BIT(i) (1U << ((i) & 31)) -static inline size_t snd_mask_sizeof(void) -{ - return sizeof(struct snd_mask); -} - static inline void snd_mask_none(struct snd_mask *mask) { memset(mask, 0, sizeof(*mask)); -- cgit v1.2.3 From 91a7c58fce065506fd98954d27694e5d83c96638 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:13 +0300 Subject: RDMA: Restore ability to fail on PD deallocate The IB verbs objects are counted by the kernel and ib_core ensures that deallocate PD will success so it will be called once all other objects that depends on PD will be released. This is achieved by managing various reference counters on such objects. The mlx5 driver didn't follow this standard flow when allowed DEVX objects that are not managed by ib_core to be interleaved with the ones under ib_core responsibility. In such interleaved scenarios deallocate command can fail and ib_core will leave uobject in internal DB and attempt to clean it later to free resources anyway. This change partially restores returned value from dealloc_pd() for all drivers, but keeping in mind that non-DEVX devices and kernel verbs paths shouldn't fail. Fixes: 21a428a019c9 ("RDMA: Handle PD allocations by IB/core") Link: https://lore.kernel.org/r/20200907120921.476363-2-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 3781d36df31c..a49aaebaed58 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2398,7 +2398,7 @@ struct ib_device_ops { void (*mmap_free)(struct rdma_user_mmap_entry *entry); void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); - void (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); + int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); @@ -3456,12 +3456,7 @@ struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, #define ib_alloc_pd(device, flags) \ __ib_alloc_pd((device), (flags), KBUILD_MODNAME) -/** - * ib_dealloc_pd_user - Deallocate kernel/user PD - * @pd: The protection domain - * @udata: Valid user data or NULL for kernel objects - */ -void ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); +int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); /** * ib_dealloc_pd - Deallocate kernel PD @@ -3471,7 +3466,9 @@ void ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); */ static inline void ib_dealloc_pd(struct ib_pd *pd) { - ib_dealloc_pd_user(pd, NULL); + int ret = ib_dealloc_pd_user(pd, NULL); + + WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail"); } enum rdma_create_ah_flags { -- cgit v1.2.3 From 9a9ebf8cd72b809405ad571fb2f635ffc9df2420 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:14 +0300 Subject: RDMA: Restore ability to fail on AH destroy Like any other IB verbs objects, AH are refcounted by ib_core. The release of those objects are controlled by ib_core with promise that AH destroy can't fail. Being SW object for now, this change makes dealloc_ah() to behave like any other destroy IB flows. Fixes: d345691471b4 ("RDMA: Handle AH allocations by IB/core") Link: https://lore.kernel.org/r/20200907120921.476363-3-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a49aaebaed58..71b145f569a8 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2403,7 +2403,7 @@ struct ib_device_ops { struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); - void (*destroy_ah)(struct ib_ah *ah, u32 flags); + int (*destroy_ah)(struct ib_ah *ah, u32 flags); int (*create_srq)(struct ib_srq *srq, struct ib_srq_init_attr *srq_init_attr, struct ib_udata *udata); @@ -3596,9 +3596,11 @@ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata); * * NOTE: for user ah use rdma_destroy_ah_user with valid udata! */ -static inline int rdma_destroy_ah(struct ib_ah *ah, u32 flags) +static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags) { - return rdma_destroy_ah_user(ah, flags, NULL); + int ret = rdma_destroy_ah_user(ah, flags, NULL); + + WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail"); } struct ib_srq *ib_create_srq_user(struct ib_pd *pd, -- cgit v1.2.3 From 119181d1d4327d3259ab25aa0ea3d3bc364afcdc Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:16 +0300 Subject: RDMA: Restore ability to fail on SRQ destroy In similar way to other IB objects, restore the ability to return error on SRQ destroy. Strictly speaking, this change is not necessary, and provided here to ensure a symmetrical interface like other destroy functions. Fixes: 68e326dea1db ("RDMA: Handle SRQ allocations by IB/core") Link: https://lore.kernel.org/r/20200907120921.476363-5-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 71b145f569a8..40bb6a455960 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2411,7 +2411,7 @@ struct ib_device_ops { enum ib_srq_attr_mask srq_attr_mask, struct ib_udata *udata); int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr); - void (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata); + int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata); struct ib_qp *(*create_qp)(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, struct ib_udata *udata); @@ -3654,9 +3654,11 @@ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata); * * NOTE: for user srq use ib_destroy_srq_user with valid udata! */ -static inline int ib_destroy_srq(struct ib_srq *srq) +static inline void ib_destroy_srq(struct ib_srq *srq) { - return ib_destroy_srq_user(srq, NULL); + int ret = ib_destroy_srq_user(srq, NULL); + + WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail"); } /** -- cgit v1.2.3 From 7e3c66c9a989d5b53387ceebc88b9e4a9b1d6434 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:17 +0300 Subject: RDMA/core: Delete function indirection for alloc/free kernel CQ The ib_alloc_cq*() and ib_free_cq*() are solely kernel verbs to manage CQs and doesn't need extra indirection just to call same functions with constant parameter NULL as udata. Link: https://lore.kernel.org/r/20200907120921.476363-6-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 62 +++++-------------------------------------------- 1 file changed, 6 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 40bb6a455960..b74fd1a5ccb6 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -3802,46 +3802,15 @@ static inline int ib_post_recv(struct ib_qp *qp, return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy); } -struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private, - int nr_cqe, int comp_vector, - enum ib_poll_context poll_ctx, - const char *caller, struct ib_udata *udata); - -/** - * ib_alloc_cq_user: Allocate kernel/user CQ - * @dev: The IB device - * @private: Private data attached to the CQE - * @nr_cqe: Number of CQEs in the CQ - * @comp_vector: Completion vector used for the IRQs - * @poll_ctx: Context used for polling the CQ - * @udata: Valid user data or NULL for kernel objects - */ -static inline struct ib_cq *ib_alloc_cq_user(struct ib_device *dev, - void *private, int nr_cqe, - int comp_vector, - enum ib_poll_context poll_ctx, - struct ib_udata *udata) -{ - return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx, - KBUILD_MODNAME, udata); -} - -/** - * ib_alloc_cq: Allocate kernel CQ - * @dev: The IB device - * @private: Private data attached to the CQE - * @nr_cqe: Number of CQEs in the CQ - * @comp_vector: Completion vector used for the IRQs - * @poll_ctx: Context used for polling the CQ - * - * NOTE: for user cq use ib_alloc_cq_user with valid udata! - */ +struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, + int comp_vector, enum ib_poll_context poll_ctx, + const char *caller); static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx) { - return ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx, - NULL); + return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, + KBUILD_MODNAME); } struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, @@ -3863,26 +3832,7 @@ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, KBUILD_MODNAME); } -/** - * ib_free_cq_user - Free kernel/user CQ - * @cq: The CQ to free - * @udata: Valid user data or NULL for kernel objects - * - * NOTE: This function shouldn't be called on shared CQs. - */ -void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata); - -/** - * ib_free_cq - Free kernel CQ - * @cq: The CQ to free - * - * NOTE: for user cq use ib_free_cq_user with valid udata! - */ -static inline void ib_free_cq(struct ib_cq *cq) -{ - ib_free_cq_user(cq, NULL); -} - +void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** -- cgit v1.2.3 From 43d781b9fa562f0c6e50f62c870fbfeb9dc85213 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:18 +0300 Subject: RDMA: Allow fail of destroy CQ Like any other verbs objects, CQ shouldn't fail during destroy, but mlx5_ib didn't follow this contract with mixed IB verbs objects with DEVX. Such mix causes to the situation where FW and kernel are fully interdependent on the reference counting of each side. Kernel verbs and drivers that don't have DEVX flows shouldn't fail. Fixes: e39afe3d6dbd ("RDMA: Convert CQ allocations to be under core responsibility") Link: https://lore.kernel.org/r/20200907120921.476363-7-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index b74fd1a5ccb6..bec05baaeaed 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2423,7 +2423,7 @@ struct ib_device_ops { int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); - void (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); + int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, @@ -3890,7 +3890,9 @@ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata); */ static inline void ib_destroy_cq(struct ib_cq *cq) { - ib_destroy_cq_user(cq, NULL); + int ret = ib_destroy_cq_user(cq, NULL); + + WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); } /** -- cgit v1.2.3 From d0c45c8556e57342d44c9548763609ffcc4e3866 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:19 +0300 Subject: RDMA: Change XRCD destroy return value Update XRCD destroy flow to allow command failure. Fixes: 28ad5f65c314 ("RDMA: Move XRCD to be under ib_core responsibility") Link: https://lore.kernel.org/r/20200907120921.476363-8-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bec05baaeaed..e25e25ad8d2c 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2452,7 +2452,7 @@ struct ib_device_ops { int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); - void (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); + int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); struct ib_flow *(*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, struct ib_udata *udata); -- cgit v1.2.3 From add53535fb3033c249d9327ae3e7c36d3382bbd1 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:20 +0300 Subject: RDMA: Restore ability to return error for destroy WQ Make this interface symmetrical to other destroy paths. Fixes: a49b1dc7ae44 ("RDMA: Convert destroy_wq to be void") Link: https://lore.kernel.org/r/20200907120921.476363-9-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e25e25ad8d2c..23209bca8c1b 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2480,7 +2480,7 @@ struct ib_device_ops { struct ib_wq *(*create_wq)(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); - void (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); + int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); struct ib_rwq_ind_table *(*create_rwq_ind_table)( @@ -4316,7 +4316,7 @@ struct net_device *ib_device_netdev(struct ib_device *dev, u8 port); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); -int ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata); +int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask); int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table); -- cgit v1.2.3 From 71ff3f6268644783d556fab10066f1027030135f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 7 Sep 2020 15:09:21 +0300 Subject: RDMA: Make counters destroy symmetrical Change counters to return failure like any other verbs destroy, however this flow shouldn't return error at all. Link: https://lore.kernel.org/r/20200907120921.476363-10-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 23209bca8c1b..29a36ec662b5 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2498,7 +2498,7 @@ struct ib_device_ops { struct uverbs_attr_bundle *attrs); int (*create_counters)(struct ib_counters *counters, struct uverbs_attr_bundle *attrs); - void (*destroy_counters)(struct ib_counters *counters); + int (*destroy_counters)(struct ib_counters *counters); int (*read_counters)(struct ib_counters *counters, struct ib_counters_read_attr *counters_read_attr, struct uverbs_attr_bundle *attrs); -- cgit v1.2.3 From 4a009cb04aeca0de60b73f37b102573354214b52 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Sep 2020 01:27:40 -0700 Subject: net: add __must_check to skb_put_padto() skb_put_padto() and __skb_put_padto() callers must check return values or risk use-after-free. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ed9bea924dc3..04a18e01b362 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3223,8 +3223,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ -static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, - bool free_on_error) +static inline int __must_check __skb_put_padto(struct sk_buff *skb, + unsigned int len, + bool free_on_error) { unsigned int size = skb->len; @@ -3247,7 +3248,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } -- cgit v1.2.3 From 3361c29e9279e682c0e9a7d7461b4e3bbc77830b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 4 Sep 2020 19:41:44 -0300 Subject: RDMA/umem: Use simpler logic for ib_umem_find_best_pgsz() The calculation in rdma_find_pg_bit() is fairly complicated, and the function is never called anywhere else. Inline a simpler version into ib_umem_find_best_pgsz() Link: https://lore.kernel.org/r/3-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 29a36ec662b5..97658d706aa1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -3335,30 +3335,6 @@ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) return rdma_protocol_iwarp(dev, port_num); } -/** - * rdma_find_pg_bit - Find page bit given address and HW supported page sizes - * - * @addr: address - * @pgsz_bitmap: bitmap of HW supported page sizes - */ -static inline unsigned int rdma_find_pg_bit(unsigned long addr, - unsigned long pgsz_bitmap) -{ - unsigned long align; - unsigned long pgsz; - - align = addr & -addr; - - /* Find page bit such that addr is aligned to the highest supported - * HW page size - */ - pgsz = pgsz_bitmap & ~(-align << 1); - if (!pgsz) - return __ffs(pgsz_bitmap); - - return __fls(pgsz); -} - /** * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not. * @device: Device -- cgit v1.2.3 From ebc24096c4c40017d9f9b0fddc5d69b94ad10369 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 4 Sep 2020 19:41:45 -0300 Subject: RDMA/umem: Add rdma_umem_for_each_dma_block() This helper does the same as rdma_for_each_block(), except it works on a umem. This simplifies most of the call sites. Link: https://lore.kernel.org/r/4-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Acked-by: Miguel Ojeda Acked-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- include/rdma/ib_umem.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 07a764eb692e..b880512ba95f 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -40,6 +40,26 @@ static inline size_t ib_umem_num_pages(struct ib_umem *umem) PAGE_SHIFT; } +static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, + struct ib_umem *umem, + unsigned long pgsz) +{ + __rdma_block_iter_start(biter, umem->sg_head.sgl, umem->nmap, pgsz); +} + +/** + * rdma_umem_for_each_dma_block - iterate over contiguous DMA blocks of the umem + * @umem: umem to iterate over + * @pgsz: Page size to split the list into + * + * pgsz must be <= PAGE_SIZE or computed by ib_umem_find_best_pgsz(). The + * returned DMA blocks will be aligned to pgsz and span the range: + * ALIGN_DOWN(umem->address, pgsz) to ALIGN(umem->address + umem->length, pgsz) + */ +#define rdma_umem_for_each_dma_block(umem, biter, pgsz) \ + for (__rdma_umem_block_iter_start(biter, umem, pgsz); \ + __rdma_block_iter_next(biter);) + #ifdef CONFIG_INFINIBAND_USER_MEM struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, -- cgit v1.2.3 From 2efbe6aebea00269425ac7de622d47c2a397a871 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 9 Sep 2020 07:50:34 +0300 Subject: devlink: Add comment block for missing port attributes Add comment block for physical, PF and VF port attributes. Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Roi Dayan Signed-off-by: David S. Miller --- include/net/devlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 8f3c8a443238..3c7ba3e1f490 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -73,6 +73,9 @@ struct devlink_port_pci_vf_attrs { * @splittable: indicates if the port can be split. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL + * @phys: physical port attributes + * @pci_pf: PCI PF port attributes + * @pci_vf: PCI VF port attributes */ struct devlink_port_attrs { u8 split:1, -- cgit v1.2.3 From ff03e63ad1673eb75cce214556013fc2e52a1b77 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 9 Sep 2020 07:50:35 +0300 Subject: devlink: Move structure comments outside of structure To add more fields to the PCI PF and VF port attributes, follow standard structure comment format. Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3c7ba3e1f490..efff9274d248 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -57,13 +57,22 @@ struct devlink_port_phys_attrs { u32 split_subport_number; /* If the port is split, this is the number of subport. */ }; +/** + * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes + * @pf: Associated PCI PF number for this port. + */ struct devlink_port_pci_pf_attrs { - u16 pf; /* Associated PCI PF for this port. */ + u16 pf; }; +/** + * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes + * @pf: Associated PCI PF number for this port. + * @vf: Associated PCI VF for of the PCI PF for this port. + */ struct devlink_port_pci_vf_attrs { - u16 pf; /* Associated PCI PF for this port. */ - u16 vf; /* Associated PCI VF for of the PCI PF for this port. */ + u16 pf; + u16 vf; }; /** -- cgit v1.2.3 From 05b595e9c44acaca94192c6db430a489c1b212a7 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 9 Sep 2020 07:50:36 +0300 Subject: devlink: Introduce external controller flag A devlink eswitch port may represent PCI PF/VF ports of a controller. A controller either located on same system or it can be an external controller located in host where such NIC is plugged in. Add the ability for driver to specify if a port is for external controller. Use such flag in the mlx5_core driver. An example of an external controller having VF1 of PF0 belong to controller 1. $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev ens2f0pf0vf1 flavour pcivf pfnum 0 vfnum 1 external true splittable false function: hw_addr 00:00:00:00:00:00 $ devlink port show pci/0000:06:00.0/2 -jp { "port": { "pci/0000:06:00.0/2": { "type": "eth", "netdev": "ens2f0pf0vf1", "flavour": "pcivf", "pfnum": 0, "vfnum": 1, "external": true, "splittable": false, "function": { "hw_addr": "00:00:00:00:00:00" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++-- include/uapi/linux/devlink.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index efff9274d248..2dad8c9151f4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -60,19 +60,23 @@ struct devlink_port_phys_attrs { /** * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes * @pf: Associated PCI PF number for this port. + * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_pf_attrs { u16 pf; + u8 external:1; }; /** * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes * @pf: Associated PCI PF number for this port. * @vf: Associated PCI VF for of the PCI PF for this port. + * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_vf_attrs { u16 pf; u16 vf; + u8 external:1; }; /** @@ -1215,9 +1219,9 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port, void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_attrs_set(struct devlink_port *devlink_port, struct devlink_port_attrs *devlink_port_attrs); -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf); +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external); void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - u16 pf, u16 vf); + u16 pf, u16 vf, bool external); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cfef4245ea5a..40823ed7e05a 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -458,6 +458,7 @@ enum devlink_attr { DEVLINK_ATTR_PORT_LANES, /* u32 */ DEVLINK_ATTR_PORT_SPLITTABLE, /* u8 */ + DEVLINK_ATTR_PORT_EXTERNAL, /* u8 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From 3a2d9588c4f79adae6a0e986b64ebdd5b38085c6 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 9 Sep 2020 07:50:37 +0300 Subject: devlink: Introduce controller number A devlink port may be for a controller consist of PCI device. A devlink instance holds ports of two types of controllers. (1) controller discovered on same system where eswitch resides This is the case where PCI PF/VF of a controller and devlink eswitch instance both are located on a single system. (2) controller located on external host system. This is the case where a controller is located in one system and its devlink eswitch ports are located in a different system. When a devlink eswitch instance serves the devlink ports of both controllers together, PCI PF/VF numbers may overlap. Due to this a unique phys_port_name cannot be constructed. For example in below such system controller-0 and controller-1, each has PCI PF pf0 whose eswitch ports can be present in controller-0. These results in phys_port_name as "pf0" for both. Similar problem exists for VFs and upcoming Sub functions. An example view of two controller systems: --------------------------------------------------------- | | | --------- --------- ------- ------- | ----------- | | vf(s) | | sf(s) | |vf(s)| |sf(s)| | | server | | ------- ----/---- ---/----- ------- ---/--- ---/--- | | pci rc |=== | pf0 |______/________/ | pf1 |___/_______/ | | connect | | ------- ------- | ----------- | | controller_num=1 (no eswitch) | ------|-------------------------------------------------- (internal wire) | --------------------------------------------------------- | devlink eswitch ports and reps | | ----------------------------------------------------- | | |ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 |ctrl-0 | | | |pf0 | pf0vfN | pf0sfN | pf1 | pf1vfN |pf1sfN | | | ----------------------------------------------------- | | |ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 |ctrl-1 | | | |pf1 | pf1vfN | pf1sfN | pf1 | pf1vfN |pf0sfN | | | ----------------------------------------------------- | | | | | | --------- --------- ------- ------- | | | vf(s) | | sf(s) | |vf(s)| |sf(s)| | | ------- ----/---- ---/----- ------- ---/--- ---/--- | | | pf0 |______/________/ | pf1 |___/_______/ | | ------- ------- | | | | local controller_num=0 (eswitch) | --------------------------------------------------------- An example devlink port for external controller with controller number = 1 for a VF 1 of PF 0: $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev ens2f0pf0vf1 flavour pcivf controller 1 pfnum 0 vfnum 1 external true splittable false function: hw_addr 00:00:00:00:00:00 $ devlink port show pci/0000:06:00.0/2 -jp { "port": { "pci/0000:06:00.0/2": { "type": "eth", "netdev": "ens2f0pf0vf1", "flavour": "pcivf", "controller": 1, "pfnum": 0, "vfnum": 1, "external": true, "splittable": false, "function": { "hw_addr": "00:00:00:00:00:00" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 9 +++++++-- include/uapi/linux/devlink.h | 1 + 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 2dad8c9151f4..eaec0a8cc5ef 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -59,21 +59,25 @@ struct devlink_port_phys_attrs { /** * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes + * @controller: Associated controller number * @pf: Associated PCI PF number for this port. * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_pf_attrs { + u32 controller; u16 pf; u8 external:1; }; /** * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes + * @controller: Associated controller number * @pf: Associated PCI PF number for this port. * @vf: Associated PCI VF for of the PCI PF for this port. * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_vf_attrs { + u32 controller; u16 pf; u16 vf; u8 external:1; @@ -1219,8 +1223,9 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port, void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_attrs_set(struct devlink_port *devlink_port, struct devlink_port_attrs *devlink_port_attrs); -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external); -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external); +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u16 vf, bool external); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 40823ed7e05a..40d35145c879 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -459,6 +459,7 @@ enum devlink_attr { DEVLINK_ATTR_PORT_SPLITTABLE, /* u8 */ DEVLINK_ATTR_PORT_EXTERNAL, /* u8 */ + DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From 2d2fe8433796603091ac8ea235b9165ac5a85f9a Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Wed, 9 Sep 2020 20:43:08 +0300 Subject: net: qed: Disable aRFS for NPAR and 100G In CMT and NPAR the PF is unknown when the GFS block processes the packet. Therefore cannot use searcher as it has a per PF database, and thus ARFS must be disabled. Fixes: d51e4af5c209 ("qed: aRFS infrastructure support") Signed-off-by: Manish Chopra Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: Dmitry Bogdanov Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..cdd73afc4c46 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -623,6 +623,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; + bool b_arfs_capable; bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; -- cgit v1.2.3 From 2acd30b9f6032c6cbefc5e255c17ebbb0718e56a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 8 Sep 2020 21:45:15 +0800 Subject: ASoC/soundwire: bus: use property to set interrupt masks Add a slave-level property and program the SCP_INT1_MASK as desired by the codec driver. Since there is no DisCo property this has to be an implementation-specific firmware property or hard-coded in the driver. The only functionality change is that implementation-defined interrupts are no longer set for amplifiers - those interrupts are typically for jack detection or acoustic event detection/hotwording. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Tested-by: Srinivas Kandagatla Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Acked-by: Mark Brown Link: https://lore.kernel.org/r/20200908134521.6781-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 1e9010c139f0..9d94cdf6346f 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -357,6 +357,7 @@ struct sdw_dpn_prop { * @dp0_prop: Data Port 0 properties * @src_dpn_prop: Source Data Port N properties * @sink_dpn_prop: Sink Data Port N properties + * @scp_int1_mask: SCP_INT1_MASK desired settings */ struct sdw_slave_prop { u32 mipi_revision; @@ -378,6 +379,7 @@ struct sdw_slave_prop { struct sdw_dp0_prop *dp0_prop; struct sdw_dpn_prop *src_dpn_prop; struct sdw_dpn_prop *sink_dpn_prop; + u8 scp_int1_mask; }; /** -- cgit v1.2.3 From c2819e196b3cc1901a4612f72e66da4821966a5e Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 8 Sep 2020 21:45:17 +0800 Subject: soundwire: slave: add first_interrupt_done status Some Slaves report incorrect information in their interrupt status registers after a master/bus reset, track the initial interrupt handling so that quirks can be introduced to filter out incorrect information while keeping interrupts enabled in steady state. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Link: https://lore.kernel.org/r/20200908134521.6781-4-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 9d94cdf6346f..2b93a8ef7fad 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -616,6 +616,8 @@ struct sdw_slave_ops { * between the Master suspending and the codec resuming, and make sure that * when the Master triggered a reset the Slave is properly enumerated and * initialized + * @first_interrupt_done: status flag tracking if the interrupt handling + * for a Slave happens for the first time after enumeration */ struct sdw_slave { struct sdw_slave_id id; @@ -637,6 +639,7 @@ struct sdw_slave { struct completion enumeration_complete; struct completion initialization_complete; u32 unattach_request; + bool first_interrupt_done; }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) -- cgit v1.2.3 From 4724f12c1315efa79a0cbf74dfb0c9b98b1a4bff Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 8 Sep 2020 21:45:18 +0800 Subject: soundwire: bus: use quirk to filter out invalid parity errors If a Slave device reports with a quirk that its initial parity check may be incorrect, filter it but keep the parity checks active in steady state. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Link: https://lore.kernel.org/r/20200908134521.6781-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 2b93a8ef7fad..790823d2d33b 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -358,6 +358,7 @@ struct sdw_dpn_prop { * @src_dpn_prop: Source Data Port N properties * @sink_dpn_prop: Sink Data Port N properties * @scp_int1_mask: SCP_INT1_MASK desired settings + * @quirks: bitmask identifying deltas from the MIPI specification */ struct sdw_slave_prop { u32 mipi_revision; @@ -380,8 +381,11 @@ struct sdw_slave_prop { struct sdw_dpn_prop *src_dpn_prop; struct sdw_dpn_prop *sink_dpn_prop; u8 scp_int1_mask; + u32 quirks; }; +#define SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY BIT(0) + /** * struct sdw_master_prop - Master properties * @revision: MIPI spec version of the implementation -- cgit v1.2.3 From d46e7ae24b81533d21edfa90914d27efa0c5f85d Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 8 May 2020 16:04:44 +0200 Subject: drm: prime: add common helper to check scatterlist contiguity It is a common operation done by DRM drivers to check the contiguity of the DMA-mapped buffer described by a scatterlist in the sg_table object. Let's add a common helper for this operation. Signed-off-by: Marek Szyprowski Reviewed-by: Andrzej Hajda Reviewed-by: Robin Murphy --- include/drm/drm_prime.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index 9af7422b44cf..47ef11614627 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -92,6 +92,8 @@ struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_page struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj, int flags); +unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt); + /* helper functions for importing */ struct drm_gem_object *drm_gem_prime_import_dev(struct drm_device *dev, struct dma_buf *dma_buf, -- cgit v1.2.3 From ad47ff330b26a9fefa882032be2122700e1625ab Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 9 Sep 2020 09:34:13 -0700 Subject: quota: widen timestamps for the fs_disk_quota structure Soon, XFS will support quota grace period expiration timestamps beyond the year 2038, widen the timestamp fields to handle the extra time bits. Internally, XFS now stores unsigned 34-bit quantities, so the extra 8 bits here should work fine. (Note that XFS is the only user of this structure.) Link: https://lore.kernel.org/r/20200909163413.GJ7955@magnolia Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/uapi/linux/dqblk_xfs.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/dqblk_xfs.h b/include/uapi/linux/dqblk_xfs.h index 03d890b80ebc..16d73f54376d 100644 --- a/include/uapi/linux/dqblk_xfs.h +++ b/include/uapi/linux/dqblk_xfs.h @@ -66,7 +66,10 @@ typedef struct fs_disk_quota { __s32 d_btimer; /* similar to above; for disk blocks */ __u16 d_iwarns; /* # warnings issued wrt num inodes */ __u16 d_bwarns; /* # warnings issued wrt disk blocks */ - __s32 d_padding2; /* padding2 - for future use */ + __s8 d_itimer_hi; /* upper 8 bits of timer values */ + __s8 d_btimer_hi; + __s8 d_rtbtimer_hi; + __s8 d_padding2; /* padding2 - for future use */ __u64 d_rtb_hardlimit;/* absolute limit on realtime blks */ __u64 d_rtb_softlimit;/* preferred limit on RT disk blks */ __u64 d_rtbcount; /* # realtime blocks owned */ @@ -121,6 +124,12 @@ typedef struct fs_disk_quota { #define FS_DQ_RTBCOUNT (1<<14) #define FS_DQ_ACCT_MASK (FS_DQ_BCOUNT | FS_DQ_ICOUNT | FS_DQ_RTBCOUNT) +/* + * Quota expiration timestamps are 40-bit signed integers, with the upper 8 + * bits encoded in the _hi fields. + */ +#define FS_DQ_BIGTIME (1<<15) + /* * Various flags related to quotactl(2). */ -- cgit v1.2.3 From d1c10767837c4181f2e054865a58166fc117783b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 9 Sep 2020 15:54:46 +0200 Subject: quota: Expand comment describing d_itimer Expand comment describing d_itimer in struct fs_disk_quota. Reported-by: Matthew Wilcox Signed-off-by: Jan Kara --- include/uapi/linux/dqblk_xfs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/dqblk_xfs.h b/include/uapi/linux/dqblk_xfs.h index 16d73f54376d..c71d909addda 100644 --- a/include/uapi/linux/dqblk_xfs.h +++ b/include/uapi/linux/dqblk_xfs.h @@ -61,8 +61,9 @@ typedef struct fs_disk_quota { __u64 d_ino_softlimit;/* preferred inode limit */ __u64 d_bcount; /* # disk blocks owned by the user */ __u64 d_icount; /* # inodes owned by the user */ - __s32 d_itimer; /* zero if within inode limits */ - /* if not, we refuse service */ + __s32 d_itimer; /* Zero if within inode limits. If + * not, we refuse service at this time + * (in seconds since Unix epoch) */ __s32 d_btimer; /* similar to above; for disk blocks */ __u16 d_iwarns; /* # warnings issued wrt num inodes */ __u16 d_bwarns; /* # warnings issued wrt disk blocks */ -- cgit v1.2.3 From 5bfe37ca8ac8e9176bfd923d0a83802b7305d2f5 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Wed, 19 Aug 2020 18:19:41 -0400 Subject: virtio: Add get_shm_region method Virtio defines 'shared memory regions' that provide a continuously shared region between the host and guest. Provide a method to find a particular region on a device. Signed-off-by: Sebastien Boeuf Signed-off-by: Dr. David Alan Gilbert Acked-by: Michael S. Tsirkin Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: "Michael S. Tsirkin" Signed-off-by: Miklos Szeredi --- include/linux/virtio_config.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 8fe857e27ef3..4b8e38c5c4d8 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -11,6 +11,11 @@ struct irq_affinity; +struct virtio_shm_region { + u64 addr; + u64 len; +}; + /** * virtio_config_ops - operations for configuring a virtio device * Note: Do not assume that a transport implements all of the operations @@ -66,6 +71,7 @@ struct irq_affinity; * the caller can then copy. * @set_vq_affinity: set the affinity for a virtqueue (optional). * @get_vq_affinity: get the affinity for a virtqueue (optional). + * @get_shm_region: get a shared memory region based on the index. */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { @@ -89,6 +95,8 @@ struct virtio_config_ops { const struct cpumask *cpu_mask); const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev, int index); + bool (*get_shm_region)(struct virtio_device *vdev, + struct virtio_shm_region *region, u8 id); }; /* If driver didn't advertise the feature, it will never appear. */ @@ -251,6 +259,15 @@ int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) return 0; } +static inline +bool virtio_get_shm_region(struct virtio_device *vdev, + struct virtio_shm_region *region, u8 id) +{ + if (!vdev->config->get_shm_region) + return false; + return vdev->config->get_shm_region(vdev, region, id); +} + static inline bool virtio_is_little_endian(struct virtio_device *vdev) { return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || -- cgit v1.2.3 From 0dd4ff93f4c8dba016ad79384007da4938cd54a1 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Wed, 19 Aug 2020 18:19:42 -0400 Subject: virtio: Implement get_shm_region for PCI transport On PCI the shm regions are found using capability entries; find a region by searching for the capability. Signed-off-by: Sebastien Boeuf Signed-off-by: Dr. David Alan Gilbert Signed-off-by: kbuild test robot Acked-by: Michael S. Tsirkin Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: "Michael S. Tsirkin" Signed-off-by: Miklos Szeredi --- include/uapi/linux/virtio_pci.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 90007a1abcab..3a86f36d7e3d 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -113,6 +113,8 @@ #define VIRTIO_PCI_CAP_DEVICE_CFG 4 /* PCI configuration access */ #define VIRTIO_PCI_CAP_PCI_CFG 5 +/* Additional shared memory capability */ +#define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8 /* This is the PCI capability header: */ struct virtio_pci_cap { @@ -121,11 +123,18 @@ struct virtio_pci_cap { __u8 cap_len; /* Generic PCI field: capability length */ __u8 cfg_type; /* Identifies the structure. */ __u8 bar; /* Where to find it. */ - __u8 padding[3]; /* Pad to full dword. */ + __u8 id; /* Multiple capabilities of the same type */ + __u8 padding[2]; /* Pad to full dword. */ __le32 offset; /* Offset within bar. */ __le32 length; /* Length of the structure, in bytes. */ }; +struct virtio_pci_cap64 { + struct virtio_pci_cap cap; + __le32 offset_hi; /* Most sig 32 bits of offset */ + __le32 length_hi; /* Most sig 32 bits of length */ +}; + struct virtio_pci_notify_cap { struct virtio_pci_cap cap; __le32 notify_off_multiplier; /* Multiplier for queue_notify_off. */ -- cgit v1.2.3 From 38e895487afc2ed42c11045853cbb3fa20b52b6e Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Wed, 19 Aug 2020 18:19:43 -0400 Subject: virtio: Implement get_shm_region for MMIO transport On MMIO a new set of registers is defined for finding SHM regions. Add their definitions and use them to find the region. Signed-off-by: Sebastien Boeuf Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: "Michael S. Tsirkin" Signed-off-by: Miklos Szeredi --- include/uapi/linux/virtio_mmio.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_mmio.h b/include/uapi/linux/virtio_mmio.h index c4b09689ab64..0650f91bea6c 100644 --- a/include/uapi/linux/virtio_mmio.h +++ b/include/uapi/linux/virtio_mmio.h @@ -122,6 +122,17 @@ #define VIRTIO_MMIO_QUEUE_USED_LOW 0x0a0 #define VIRTIO_MMIO_QUEUE_USED_HIGH 0x0a4 +/* Shared memory region id */ +#define VIRTIO_MMIO_SHM_SEL 0x0ac + +/* Shared memory region length, 64 bits in two halves */ +#define VIRTIO_MMIO_SHM_LEN_LOW 0x0b0 +#define VIRTIO_MMIO_SHM_LEN_HIGH 0x0b4 + +/* Shared memory region base address, 64 bits in two halves */ +#define VIRTIO_MMIO_SHM_BASE_LOW 0x0b8 +#define VIRTIO_MMIO_SHM_BASE_HIGH 0x0bc + /* Configuration atomicity value */ #define VIRTIO_MMIO_CONFIG_GENERATION 0x0fc -- cgit v1.2.3 From 80793c3471d90d4dc2b48deadb6413bdfe39500f Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Thu, 27 Aug 2020 13:40:39 +0200 Subject: seqlock: Introduce seqcount_latch_t Latch sequence counters are a multiversion concurrency control mechanism where the seqcount_t counter even/odd value is used to switch between two copies of protected data. This allows the seqcount_t read path to safely interrupt its write side critical section (e.g. from NMIs). Initially, latch sequence counters were implemented as a single write function above plain seqcount_t: raw_write_seqcount_latch(). The read side was expected to use plain seqcount_t raw_read_seqcount(). A specialized latch read function, raw_read_seqcount_latch(), was later added. It became the standardized way for latch read paths. Due to the dependent load, it has one read memory barrier less than the plain seqcount_t raw_read_seqcount() API. Only raw_write_seqcount_latch() and raw_read_seqcount_latch() should be used with latch sequence counters. Having *unique* read and write path APIs means that latch sequence counters are actually a data type of their own -- just inappropriately overloading plain seqcount_t. Introduce seqcount_latch_t. This adds type-safety and ensures that only the correct latch-safe APIs are to be used. Not to break bisection, let the latch APIs also accept plain seqcount_t or seqcount_raw_spinlock_t. After converting all call sites to seqcount_latch_t, only that new data type will be allowed. References: 9b0fd802e8c0 ("seqcount: Add raw_write_seqcount_latch()") References: 7fc26327b756 ("seqlock: Introduce raw_read_seqcount_latch()") References: aadd6e5caaac ("time/sched_clock: Use raw_read_seqcount_latch()") Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200827114044.11173-4-a.darwish@linutronix.de --- include/linux/seqlock.h | 104 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 73 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 300cbf312546..88b917d4ebde 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -587,34 +587,76 @@ static inline void write_seqcount_t_invalidate(seqcount_t *s) kcsan_nestable_atomic_end(); } -/** - * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants +/* + * Latch sequence counters (seqcount_latch_t) * - * Use seqcount_t latching to switch between two storage places protected - * by a sequence counter. Doing so allows having interruptible, preemptible, - * seqcount_t write side critical sections. + * A sequence counter variant where the counter even/odd value is used to + * switch between two copies of protected data. This allows the read path, + * typically NMIs, to safely interrupt the write side critical section. * - * Check raw_write_seqcount_latch() for more details and a full reader and - * writer usage example. + * As the write sections are fully preemptible, no special handling for + * PREEMPT_RT is needed. + */ +typedef struct { + seqcount_t seqcount; +} seqcount_latch_t; + +/** + * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t + * @seq_name: Name of the seqcount_latch_t instance + */ +#define SEQCNT_LATCH_ZERO(seq_name) { \ + .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ +} + +/** + * seqcount_latch_init() - runtime initializer for seqcount_latch_t + * @s: Pointer to the seqcount_latch_t instance + */ +static inline void seqcount_latch_init(seqcount_latch_t *s) +{ + seqcount_init(&s->seqcount); +} + +/** + * raw_read_seqcount_latch() - pick even/odd latch data copy + * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t + * + * See raw_write_seqcount_latch() for details and a full reader/writer + * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for - * picking which data copy to read. The full counter value must then be - * checked with read_seqcount_retry(). + * picking which data copy to read. The full counter must then be checked + * with read_seqcount_latch_retry(). */ -#define raw_read_seqcount_latch(s) \ - raw_read_seqcount_t_latch(__seqcount_ptr(s)) +#define raw_read_seqcount_latch(s) \ +({ \ + /* \ + * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). \ + * Due to the dependent load, a full smp_rmb() is not needed. \ + */ \ + _Generic(*(s), \ + seqcount_t: READ_ONCE(((seqcount_t *)s)->sequence), \ + seqcount_raw_spinlock_t: READ_ONCE(((seqcount_raw_spinlock_t *)s)->seqcount.sequence), \ + seqcount_latch_t: READ_ONCE(((seqcount_latch_t *)s)->seqcount.sequence)); \ +}) -static inline int raw_read_seqcount_t_latch(seqcount_t *s) +/** + * read_seqcount_latch_retry() - end a seqcount_latch_t read section + * @s: Pointer to seqcount_latch_t + * @start: count, from raw_read_seqcount_latch() + * + * Return: true if a read section retry is required, else false + */ +static inline int +read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { - /* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */ - int seq = READ_ONCE(s->sequence); /* ^^^ */ - return seq; + return read_seqcount_retry(&s->seqcount, start); } /** - * raw_write_seqcount_latch() - redirect readers to even/odd copy - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * raw_write_seqcount_latch() - redirect latch readers to even/odd copy + * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never @@ -633,7 +675,7 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s) * The basic form is a data structure like:: * * struct latch_struct { - * seqcount_t seq; + * seqcount_latch_t seq; * struct data_struct data[2]; * }; * @@ -643,13 +685,13 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s) * void latch_modify(struct latch_struct *latch, ...) * { * smp_wmb(); // Ensure that the last data[1] update is visible - * latch->seq++; + * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[0], ...); * * smp_wmb(); // Ensure that the data[0] update is visible - * latch->seq++; + * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[1], ...); @@ -668,8 +710,8 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s) * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * - * // read_seqcount_retry() includes needed smp_rmb() - * } while (read_seqcount_retry(&latch->seq, seq)); + * // This includes needed smp_rmb() + * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } @@ -693,14 +735,14 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s) * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ -#define raw_write_seqcount_latch(s) \ - raw_write_seqcount_t_latch(__seqcount_ptr(s)) - -static inline void raw_write_seqcount_t_latch(seqcount_t *s) -{ - smp_wmb(); /* prior stores before incrementing "sequence" */ - s->sequence++; - smp_wmb(); /* increment "sequence" before following stores */ +#define raw_write_seqcount_latch(s) \ +{ \ + smp_wmb(); /* prior stores before incrementing "sequence" */ \ + _Generic(*(s), \ + seqcount_t: ((seqcount_t *)s)->sequence++, \ + seqcount_raw_spinlock_t:((seqcount_raw_spinlock_t *)s)->seqcount.sequence++, \ + seqcount_latch_t: ((seqcount_latch_t *)s)->seqcount.sequence++); \ + smp_wmb(); /* increment "sequence" before following stores */ \ } /* -- cgit v1.2.3 From 24bf401cebfd630cc9e2c3746e43945e836626f9 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Thu, 27 Aug 2020 13:40:43 +0200 Subject: rbtree_latch: Use seqcount_latch_t Latch sequence counters have unique read and write APIs, and thus seqcount_latch_t was recently introduced at seqlock.h. Use that new data type instead of plain seqcount_t. This adds the necessary type-safety and ensures that only latching-safe seqcount APIs are to be used. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200827114044.11173-8-a.darwish@linutronix.de --- include/linux/rbtree_latch.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h index 7d012faa509a..3d1a9e716b80 100644 --- a/include/linux/rbtree_latch.h +++ b/include/linux/rbtree_latch.h @@ -42,8 +42,8 @@ struct latch_tree_node { }; struct latch_tree_root { - seqcount_t seq; - struct rb_root tree[2]; + seqcount_latch_t seq; + struct rb_root tree[2]; }; /** @@ -206,7 +206,7 @@ latch_tree_find(void *key, struct latch_tree_root *root, do { seq = raw_read_seqcount_latch(&root->seq); node = __lt_find(key, root, seq & 1, ops->comp); - } while (read_seqcount_retry(&root->seq, seq)); + } while (read_seqcount_latch_retry(&root->seq, seq)); return node; } -- cgit v1.2.3 From 0c9794c8b6781eb7dad8e19b78c5d4557790597a Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Thu, 27 Aug 2020 13:40:44 +0200 Subject: seqlock: seqcount latch APIs: Only allow seqcount_latch_t All latch sequence counter call-sites have now been converted from plain seqcount_t to the new seqcount_latch_t data type. Enforce type-safety by modifying seqlock.h latch APIs to only accept seqcount_latch_t. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200827114044.11173-9-a.darwish@linutronix.de --- include/linux/seqlock.h | 36 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 88b917d4ebde..f2a7a467e998 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -620,7 +620,7 @@ static inline void seqcount_latch_init(seqcount_latch_t *s) /** * raw_read_seqcount_latch() - pick even/odd latch data copy - * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t + * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. @@ -629,17 +629,14 @@ static inline void seqcount_latch_init(seqcount_latch_t *s) * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ -#define raw_read_seqcount_latch(s) \ -({ \ - /* \ - * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). \ - * Due to the dependent load, a full smp_rmb() is not needed. \ - */ \ - _Generic(*(s), \ - seqcount_t: READ_ONCE(((seqcount_t *)s)->sequence), \ - seqcount_raw_spinlock_t: READ_ONCE(((seqcount_raw_spinlock_t *)s)->seqcount.sequence), \ - seqcount_latch_t: READ_ONCE(((seqcount_latch_t *)s)->seqcount.sequence)); \ -}) +static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) +{ + /* + * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). + * Due to the dependent load, a full smp_rmb() is not needed. + */ + return READ_ONCE(s->seqcount.sequence); +} /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section @@ -656,7 +653,7 @@ read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy - * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t + * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never @@ -735,14 +732,11 @@ read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ -#define raw_write_seqcount_latch(s) \ -{ \ - smp_wmb(); /* prior stores before incrementing "sequence" */ \ - _Generic(*(s), \ - seqcount_t: ((seqcount_t *)s)->sequence++, \ - seqcount_raw_spinlock_t:((seqcount_raw_spinlock_t *)s)->seqcount.sequence++, \ - seqcount_latch_t: ((seqcount_latch_t *)s)->seqcount.sequence++); \ - smp_wmb(); /* increment "sequence" before following stores */ \ +static inline void raw_write_seqcount_latch(seqcount_latch_t *s) +{ + smp_wmb(); /* prior stores before incrementing "sequence" */ + s->seqcount.sequence++; + smp_wmb(); /* increment "sequence" before following stores */ } /* -- cgit v1.2.3 From 6dd699b13d53f26a7603702d8bada3482312df74 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 4 Sep 2020 17:32:27 +0200 Subject: seqlock: seqcount_LOCKNAME_t: Standardize naming convention At seqlock.h, sequence counters with associated locks are either called seqcount_LOCKNAME_t, seqcount_LOCKTYPE_t, or seqcount_locktype_t. Standardize on seqcount_LOCKNAME_t for all instances in comments, kernel-doc, and SEQCOUNT_LOCKNAME() generative macro paramters. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200904153231.11994-2-a.darwish@linutronix.de --- include/linux/seqlock.h | 79 +++++++++++++++++++++++++------------------------ 1 file changed, 40 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index f2a7a467e998..820ace2f5911 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -53,7 +53,7 @@ * * If the write serialization mechanism is one of the common kernel * locking primitives, use a sequence counter with associated lock - * (seqcount_LOCKTYPE_t) instead. + * (seqcount_LOCKNAME_t) instead. * * If it's desired to automatically handle the sequence counter writer * serialization and non-preemptibility requirements, use a sequential @@ -117,7 +117,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* - * Sequence counters with associated locks (seqcount_LOCKTYPE_t) + * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate @@ -138,30 +138,32 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #endif /** - * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPE associated + * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter - * @lock: Pointer to the associated spinlock + * @lock: Pointer to the associated lock * - * A plain sequence counter with external writer synchronization by a - * spinlock. The spinlock is associated to the sequence count in the + * A plain sequence counter with external writer synchronization by + * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. + * + * LOCKNAME: raw_spinlock, spinlock, rwlock, mutex, or ww_mutex. */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance - * @lock: Pointer to the associated LOCKTYPE + * @lock: Pointer to the associated lock */ /* - * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers - * @locktype: actual typename - * @lockname: name - * @preemptible: preemptibility of above locktype + * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers + * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t + * @locktype: LOCKNAME canonical C data type + * @preemptible: preemptibility of above lockname * @lockmember: argument for lockdep_assert_held() */ -#define SEQCOUNT_LOCKTYPE(locktype, lockname, preemptible, lockmember) \ +#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember) \ typedef struct seqcount_##lockname { \ seqcount_t seqcount; \ __SEQ_LOCK(locktype *lock); \ @@ -211,29 +213,28 @@ static inline void __seqcount_assert(seqcount_t *s) lockdep_assert_preemption_disabled(); } -SEQCOUNT_LOCKTYPE(raw_spinlock_t, raw_spinlock, false, s->lock) -SEQCOUNT_LOCKTYPE(spinlock_t, spinlock, false, s->lock) -SEQCOUNT_LOCKTYPE(rwlock_t, rwlock, false, s->lock) -SEQCOUNT_LOCKTYPE(struct mutex, mutex, true, s->lock) -SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base) +SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock) +SEQCOUNT_LOCKNAME(spinlock, spinlock_t, false, s->lock) +SEQCOUNT_LOCKNAME(rwlock, rwlock_t, false, s->lock) +SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock) +SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance - * @lock: Pointer to the associated LOCKTYPE + * @lock: Pointer to the associated LOCKNAME */ -#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) { \ +#define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } -#define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) -#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) -#define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) -#define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) -#define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) - +#define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) +#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) +#define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) +#define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) +#define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s)) @@ -252,7 +253,7 @@ SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base) /** * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is @@ -283,7 +284,7 @@ repeat: /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ @@ -299,7 +300,7 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s) /** * read_seqcount_begin() - begin a seqcount_t read critical section - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ @@ -314,7 +315,7 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s) /** * raw_read_seqcount() - read the raw seqcount_t counter value - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or @@ -337,7 +338,7 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait @@ -365,7 +366,7 @@ static inline unsigned raw_seqcount_t_begin(const seqcount_t *s) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() @@ -389,7 +390,7 @@ static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start) /** * read_seqcount_retry() - end a seqcount_t read critical section - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given @@ -409,7 +410,7 @@ static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start) /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_begin(s) \ do { \ @@ -428,7 +429,7 @@ static inline void raw_write_seqcount_t_begin(seqcount_t *s) /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_end(s) \ do { \ @@ -448,7 +449,7 @@ static inline void raw_write_seqcount_t_end(seqcount_t *s) /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst @@ -471,7 +472,7 @@ static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass) /** * write_seqcount_begin() - start a seqcount_t write side critical section - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * write_seqcount_begin opens a write side critical section of the given * seqcount_t. @@ -497,7 +498,7 @@ static inline void write_seqcount_t_begin(seqcount_t *s) /** * write_seqcount_end() - end a seqcount_t write side critical section - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * The write section must've been opened with write_seqcount_begin(). */ @@ -517,7 +518,7 @@ static inline void write_seqcount_t_end(seqcount_t *s) /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse @@ -571,7 +572,7 @@ static inline void raw_write_seqcount_t_barrier(seqcount_t *s) /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations - * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. -- cgit v1.2.3 From 5cdd25572a29e46f932d3e6eedbd07429de66431 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 4 Sep 2020 17:32:28 +0200 Subject: seqlock: Use unique prefix for seqcount_t property accessors At seqlock.h, the following set of functions: - __seqcount_ptr() - __seqcount_preemptible() - __seqcount_assert() act as plain seqcount_t "property" accessors. Meanwhile, the following group: - __seqcount_ptr() - __seqcount_lock_preemptible() - __seqcount_assert_lock_held() act as the equivalent set, but in the generic form, taking either seqcount_t or any of the seqcount_LOCKNAME_t variants. This is quite confusing, especially the first member where it is called exactly the same in both groups. Differentiate the first group by using "__seqprop" as prefix, and also use that same prefix for all of seqcount_LOCKNAME_t property accessors. While at it, constify the property accessors first parameter when appropriate. References: 55f3560df975 ("seqlock: Extend seqcount API with associated locks") Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200904153231.11994-3-a.darwish@linutronix.de --- include/linux/seqlock.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 820ace2f5911..0b4a22f33ac3 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -157,7 +157,9 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) */ /* - * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers + * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers + * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t + * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above lockname @@ -177,19 +179,19 @@ seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock) \ } \ \ static __always_inline seqcount_t * \ -__seqcount_##lockname##_ptr(seqcount_##lockname##_t *s) \ +__seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline bool \ -__seqcount_##lockname##_preemptible(seqcount_##lockname##_t *s) \ +__seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ return preemptible; \ } \ \ static __always_inline void \ -__seqcount_##lockname##_assert(seqcount_##lockname##_t *s) \ +__seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(lockmember)); \ } @@ -198,17 +200,17 @@ __seqcount_##lockname##_assert(seqcount_##lockname##_t *s) \ * __seqprop() for seqcount_t */ -static inline seqcount_t *__seqcount_ptr(seqcount_t *s) +static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } -static inline bool __seqcount_preemptible(seqcount_t *s) +static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } -static inline void __seqcount_assert(seqcount_t *s) +static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } @@ -237,10 +239,10 @@ SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ - seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s)) + seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s)) #define __seqprop(s, prop) _Generic(*(s), \ - seqcount_t: __seqcount_##prop((void *)(s)), \ + seqcount_t: __seqprop_##prop((void *)(s)), \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ -- cgit v1.2.3 From 52ac39e5db5148f70392edb654ad882ac8da88a8 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 4 Sep 2020 17:32:29 +0200 Subject: seqlock: seqcount_t: Implement all read APIs as statement expressions The sequence counters read APIs are implemented as CPP macros, so they can take either seqcount_t or any of the seqcount_LOCKNAME_t variants. Such macros then get *directly* transformed to internal C functions that only take plain seqcount_t. Further commits need access to seqcount_LOCKNAME_t inside of the actual read APIs code. Thus transform all of the seqcount read APIs to pure GCC statement expressions instead. This will not break type-safety: all of the transformed APIs resolve to a _Generic() selection that does not have a "default" case. This will also not affect the transformed APIs readability: previously added kernel-doc above all of seqlock.h functions makes the expectations quite clear for call-site developers. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200904153231.11994-4-a.darwish@linutronix.de --- include/linux/seqlock.h | 94 +++++++++++++++++++++++-------------------------- 1 file changed, 45 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 0b4a22f33ac3..f3b78277e26b 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -184,6 +184,12 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ return &s->seqcount; \ } \ \ +static __always_inline unsigned \ +__seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ +{ \ + return READ_ONCE(s->seqcount.sequence); \ +} \ + \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ @@ -205,6 +211,11 @@ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) return s; } +static inline unsigned __seqprop_sequence(const seqcount_t *s) +{ + return READ_ONCE(s->sequence); +} + static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; @@ -250,6 +261,7 @@ SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base) __seqprop_case((s), ww_mutex, prop)) #define __seqcount_ptr(s) __seqprop(s, ptr) +#define __seqcount_sequence(s) __seqprop(s, sequence) #define __seqcount_lock_preemptible(s) __seqprop(s, preemptible) #define __seqcount_assert_lock_held(s) __seqprop(s, assert) @@ -268,21 +280,15 @@ SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base) * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ - __read_seqcount_t_begin(__seqcount_ptr(s)) - -static inline unsigned __read_seqcount_t_begin(const seqcount_t *s) -{ - unsigned ret; - -repeat: - ret = READ_ONCE(s->sequence); - if (unlikely(ret & 1)) { - cpu_relax(); - goto repeat; - } - kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); - return ret; -} +({ \ + unsigned seq; \ + \ + while ((seq = __seqcount_sequence(s)) & 1) \ + cpu_relax(); \ + \ + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ + seq; \ +}) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep @@ -291,14 +297,12 @@ repeat: * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) \ - raw_read_seqcount_t_begin(__seqcount_ptr(s)) - -static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s) -{ - unsigned ret = __read_seqcount_t_begin(s); - smp_rmb(); - return ret; -} +({ \ + unsigned seq = __read_seqcount_begin(s); \ + \ + smp_rmb(); \ + seq; \ +}) /** * read_seqcount_begin() - begin a seqcount_t read critical section @@ -307,13 +311,10 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s) * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ - read_seqcount_t_begin(__seqcount_ptr(s)) - -static inline unsigned read_seqcount_t_begin(const seqcount_t *s) -{ - seqcount_lockdep_reader_access(s); - return raw_read_seqcount_t_begin(s); -} +({ \ + seqcount_lockdep_reader_access(__seqcount_ptr(s)); \ + raw_read_seqcount_begin(s); \ +}) /** * raw_read_seqcount() - read the raw seqcount_t counter value @@ -327,15 +328,13 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s) * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ - raw_read_seqcount_t(__seqcount_ptr(s)) - -static inline unsigned raw_read_seqcount_t(const seqcount_t *s) -{ - unsigned ret = READ_ONCE(s->sequence); - smp_rmb(); - kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); - return ret; -} +({ \ + unsigned seq = __seqcount_sequence(s); \ + \ + smp_rmb(); \ + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ + seq; \ +}) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o @@ -355,16 +354,13 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s) * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ - raw_seqcount_t_begin(__seqcount_ptr(s)) - -static inline unsigned raw_seqcount_t_begin(const seqcount_t *s) -{ - /* - * If the counter is odd, let read_seqcount_retry() fail - * by decrementing the counter. - */ - return raw_read_seqcount_t(s) & ~1; -} +({ \ + /* \ + * If the counter is odd, let read_seqcount_retry() fail \ + * by decrementing the counter. \ + */ \ + raw_read_seqcount(s) & ~1; \ +}) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier -- cgit v1.2.3 From 8117ab508f9c476e0a10b9db7f4818f784cf3176 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 4 Sep 2020 17:32:30 +0200 Subject: seqlock: seqcount_LOCKNAME_t: Introduce PREEMPT_RT support Preemption must be disabled before entering a sequence counter write side critical section. Otherwise the read side section can preempt the write side section and spin for the entire scheduler tick. If that reader belongs to a real-time scheduling class, it can spin forever and the kernel will livelock. Disabling preemption cannot be done for PREEMPT_RT though: it can lead to higher latencies, and the write side sections will not be able to acquire locks which become sleeping locks (e.g. spinlock_t). To remain preemptible, while avoiding a possible livelock caused by the reader preempting the writer, use a different technique: let the reader detect if a seqcount_LOCKNAME_t writer is in progress. If that's the case, acquire then release the associated LOCKNAME writer serialization lock. This will allow any possibly-preempted writer to make progress until the end of its writer serialization lock critical section. Implement this lock-unlock technique for all seqcount_LOCKNAME_t with an associated (PREEMPT_RT) sleeping lock. References: 55f3560df975 ("seqlock: Extend seqcount API with associated locks") Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200519214547.352050-1-a.darwish@linutronix.de --- include/linux/seqlock.h | 61 +++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 51 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index f3b78277e26b..2bc95104ab1b 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -131,7 +132,23 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * See Documentation/locking/seqlock.rst */ -#ifdef CONFIG_LOCKDEP +/* + * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot + * disable preemption. It can lead to higher latencies, and the write side + * sections will not be able to acquire locks which become sleeping locks + * (e.g. spinlock_t). + * + * To remain preemptible while avoiding a possible livelock caused by the + * reader preempting the writer, use a different technique: let the reader + * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the + * case, acquire then release the associated LOCKNAME writer serialization + * lock. This will allow any possibly-preempted writer to make progress + * until the end of its writer serialization lock critical section. + * + * This lock-unlock technique must be implemented for all of PREEMPT_RT + * sleeping locks. See Documentation/locking/locktypes.rst + */ +#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) #define __SEQ_LOCK(expr) expr #else #define __SEQ_LOCK(expr) @@ -162,10 +179,12 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type - * @preemptible: preemptibility of above lockname + * @preemptible: preemptibility of above locktype * @lockmember: argument for lockdep_assert_held() + * @lockbase: associated lock release function (prefix only) + * @lock_acquire: associated lock acquisition function (full call) */ -#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember) \ +#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \ typedef struct seqcount_##lockname { \ seqcount_t seqcount; \ __SEQ_LOCK(locktype *lock); \ @@ -187,13 +206,33 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ - return READ_ONCE(s->seqcount.sequence); \ + unsigned seq = READ_ONCE(s->seqcount.sequence); \ + \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ + return seq; \ + \ + if (preemptible && unlikely(seq & 1)) { \ + __SEQ_LOCK(lock_acquire); \ + __SEQ_LOCK(lockbase##_unlock(s->lock)); \ + \ + /* \ + * Re-read the sequence counter since the (possibly \ + * preempted) writer made progress. \ + */ \ + seq = READ_ONCE(s->seqcount.sequence); \ + } \ + \ + return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ - return preemptible; \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ + return preemptible; \ + \ + /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ + return false; \ } \ \ static __always_inline void \ @@ -226,11 +265,13 @@ static inline void __seqprop_assert(const seqcount_t *s) lockdep_assert_preemption_disabled(); } -SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock) -SEQCOUNT_LOCKNAME(spinlock, spinlock_t, false, s->lock) -SEQCOUNT_LOCKNAME(rwlock, rwlock_t, false, s->lock) -SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock) -SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base) +#define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) + +SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_spin, raw_spin_lock(s->lock)) +SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) +SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) +SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) +SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL)) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t -- cgit v1.2.3 From 1909760f5fc3f123e47b4e24e0ccdc0fc8f3f106 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 4 Sep 2020 17:32:31 +0200 Subject: seqlock: PREEMPT_RT: Do not starve seqlock_t writers On PREEMPT_RT, seqlock_t is transformed to a sleeping lock that do not disable preemption. A seqlock_t reader can thus preempt its write side section and spin for the enter scheduler tick. If that reader belongs to a real-time scheduling class, it can spin forever and the kernel will livelock. To break this livelock possibility on PREEMPT_RT, implement seqlock_t in terms of "seqcount_spinlock_t" instead of plain "seqcount_t". Beside its pure annotational value, this will leverage the existing seqcount_LOCKNAME_T PREEMPT_RT anti-livelock mechanisms, without adding any extra code. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200904153231.11994-6-a.darwish@linutronix.de --- include/linux/seqlock.h | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 2bc95104ab1b..f73c7eb68f27 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -790,13 +790,17 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) * - Documentation/locking/seqlock.rst */ typedef struct { - struct seqcount seqcount; + /* + * Make sure that readers don't starve writers on PREEMPT_RT: use + * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). + */ + seqcount_spinlock_t seqcount; spinlock_t lock; } seqlock_t; #define __SEQLOCK_UNLOCKED(lockname) \ { \ - .seqcount = SEQCNT_ZERO(lockname), \ + .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } @@ -806,8 +810,8 @@ typedef struct { */ #define seqlock_init(sl) \ do { \ - seqcount_init(&(sl)->seqcount); \ spin_lock_init(&(sl)->lock); \ + seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** @@ -854,6 +858,12 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) return read_seqcount_retry(&sl->seqcount, start); } +/* + * For all seqlock_t write side functions, use write_seqcount_*t*_begin() + * instead of the generic write_seqcount_begin(). This way, no redundant + * lockdep_assert_held() checks are added. + */ + /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t @@ -870,7 +880,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); - write_seqcount_t_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount.seqcount); } /** @@ -882,7 +892,7 @@ static inline void write_seqlock(seqlock_t *sl) */ static inline void write_sequnlock(seqlock_t *sl) { - write_seqcount_t_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } @@ -896,7 +906,7 @@ static inline void write_sequnlock(seqlock_t *sl) static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); - write_seqcount_t_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount.seqcount); } /** @@ -909,7 +919,7 @@ static inline void write_seqlock_bh(seqlock_t *sl) */ static inline void write_sequnlock_bh(seqlock_t *sl) { - write_seqcount_t_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } @@ -923,7 +933,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl) static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); - write_seqcount_t_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount.seqcount); } /** @@ -935,7 +945,7 @@ static inline void write_seqlock_irq(seqlock_t *sl) */ static inline void write_sequnlock_irq(seqlock_t *sl) { - write_seqcount_t_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } @@ -944,7 +954,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) unsigned long flags; spin_lock_irqsave(&sl->lock, flags); - write_seqcount_t_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount.seqcount); return flags; } @@ -973,7 +983,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { - write_seqcount_t_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } -- cgit v1.2.3 From 44fae179ce73a26733d9e2d346da4e1a1cb94647 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 21 Aug 2020 12:57:53 -0700 Subject: perf/core: Pull pmu::sched_task() into perf_event_context_sched_out() The pmu::sched_task() is a context switch callback. It passes the cpuctx->task_ctx as a parameter to the lower code. To find the cpuctx->task_ctx, the current code iterates a cpuctx list. The same context will iterated in perf_event_context_sched_out() soon. Share the cpuctx->task_ctx can avoid the unnecessary iteration of the cpuctx list. The pmu::sched_task() is also required for the optimization case for equivalent contexts. The task_ctx_sched_out() will eventually disable and reenable the PMU when schedule out events. Add perf_pmu_disable() and perf_pmu_enable() around task_ctx_sched_out() don't break anything. Drop the cpuctx->ctx.lock for the pmu::sched_task(). The lock is for per-CPU context, which is not necessary for the per-task context schedule. No one uses sched_cb_entry, perf_sched_cb_usages, sched_cb_list, and perf_pmu_sched_task() any more. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200821195754.20159-2-kan.liang@linux.intel.com --- include/linux/perf_event.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 46a3974eb4fe..0c19d279b97f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -872,7 +872,6 @@ struct perf_cpu_context { struct list_head cgrp_cpuctx_entry; #endif - struct list_head sched_cb_entry; int sched_cb_usage; int online; -- cgit v1.2.3 From 6bbdd563ee9a6078725727571586c66c8613db64 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Tue, 3 Mar 2020 14:58:21 -0500 Subject: dax: Create a range version of dax_layout_busy_page() virtiofs device has a range of memory which is mapped into file inodes using dax. This memory is mapped in qemu on host and maps different sections of real file on host. Size of this memory is limited (determined by administrator) and depending on filesystem size, we will soon reach a situation where all the memory is in use and we need to reclaim some. As part of reclaim process, we will need to make sure that there are no active references to pages (taken by get_user_pages()) on the memory range we are trying to reclaim. I am planning to use dax_layout_busy_page() for this. But in current form this is per inode and scans through all the pages of the inode. We want to reclaim only a portion of memory (say 2MB page). So we want to make sure that only that 2MB range of pages do not have any references (and don't want to unmap all the pages of inode). Hence, create a range version of this function named dax_layout_busy_page_range() which can be used to pass a range which needs to be unmapped. Cc: Dan Williams Cc: linux-nvdimm@lists.01.org Cc: Jan Kara Cc: Vishal L Verma Cc: "Weiny, Ira" Signed-off-by: Vivek Goyal Reviewed-by: Jan Kara Signed-off-by: Miklos Szeredi --- include/linux/dax.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 6904d4e0b2e0..9016929db4c6 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -141,6 +141,7 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); +struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); #else @@ -171,6 +172,11 @@ static inline struct page *dax_layout_busy_page(struct address_space *mapping) return NULL; } +static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) +{ + return NULL; +} + static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { -- cgit v1.2.3 From 22f3787e9d95e72d1f09795f294fb010e2998f43 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Wed, 19 Aug 2020 18:19:46 -0400 Subject: virtiofs: set up virtio_fs dax_device Setup a dax device. Use the shm capability to find the cache entry and map it. The DAX window is accessed by the fs/dax.c infrastructure and must have struct pages (at least on x86). Use devm_memremap_pages() to map the DAX window PCI BAR and allocate struct page. Signed-off-by: Stefan Hajnoczi Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Vivek Goyal Signed-off-by: Sebastien Boeuf Signed-off-by: Liu Bo Signed-off-by: Miklos Szeredi --- include/uapi/linux/virtio_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_fs.h b/include/uapi/linux/virtio_fs.h index 3056b6e9f8ce..bea38291421b 100644 --- a/include/uapi/linux/virtio_fs.h +++ b/include/uapi/linux/virtio_fs.h @@ -16,4 +16,7 @@ struct virtio_fs_config { __le32 num_request_queues; } __attribute__((packed)); +/* For the id field in virtio_pci_shm_cap */ +#define VIRTIO_FS_SHMCAP_ID_CACHE 0 + #endif /* _UAPI_LINUX_VIRTIO_FS_H */ -- cgit v1.2.3 From fd1a1dc6f5aa7361e3562790336e116935f8fcfa Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Wed, 19 Aug 2020 18:19:49 -0400 Subject: virtiofs: implement FUSE_INIT map_alignment field The device communicates FUSE_SETUPMAPPING/FUSE_REMOVMAPPING alignment constraints via the FUST_INIT map_alignment field. Parse this field and ensure our DAX mappings meet the alignment constraints. We don't actually align anything differently since our mappings are already 2MB aligned. Just check the value when the connection is established. If it becomes necessary to honor arbitrary alignments in the future we'll have to adjust how mappings are sized. The upshot of this commit is that we can be confident that mappings will work even when emulating x86 on Power and similar combinations where the host page sizes are different. Signed-off-by: Stefan Hajnoczi Signed-off-by: Vivek Goyal Signed-off-by: Miklos Szeredi --- include/uapi/linux/fuse.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 373cada89815..5b85819e045f 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -313,7 +313,9 @@ struct fuse_file_lock { * FUSE_CACHE_SYMLINKS: cache READLINK responses * FUSE_NO_OPENDIR_SUPPORT: kernel supports zero-message opendir * FUSE_EXPLICIT_INVAL_DATA: only invalidate cached pages on explicit request - * FUSE_MAP_ALIGNMENT: map_alignment field is valid + * FUSE_MAP_ALIGNMENT: init_out.map_alignment contains log2(byte alignment) for + * foffset and moffset fields in struct + * fuse_setupmapping_out and fuse_removemapping_one. */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) -- cgit v1.2.3 From ceec02d4354a317cacce4b053a580ea3c7fc6cdc Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 19 Aug 2020 18:19:50 -0400 Subject: virtiofs: introduce setupmapping/removemapping commands Introduce two new fuse commands to setup/remove memory mappings. This will be used to setup/tear down file mapping in dax window. Signed-off-by: Vivek Goyal Signed-off-by: Peng Tao Signed-off-by: Miklos Szeredi --- include/uapi/linux/fuse.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 5b85819e045f..60a7bfc787ce 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -894,4 +894,33 @@ struct fuse_copy_file_range_in { uint64_t flags; }; +#define FUSE_SETUPMAPPING_FLAG_WRITE (1ull << 0) +struct fuse_setupmapping_in { + /* An already open handle */ + uint64_t fh; + /* Offset into the file to start the mapping */ + uint64_t foffset; + /* Length of mapping required */ + uint64_t len; + /* Flags, FUSE_SETUPMAPPING_FLAG_* */ + uint64_t flags; + /* Offset in Memory Window */ + uint64_t moffset; +}; + +struct fuse_removemapping_in { + /* number of fuse_removemapping_one follows */ + uint32_t count; +}; + +struct fuse_removemapping_one { + /* Offset into the dax window start the unmapping */ + uint64_t moffset; + /* Length of mapping required */ + uint64_t len; +}; + +#define FUSE_REMOVEMAPPING_MAX_ENTRY \ + (PAGE_SIZE / sizeof(struct fuse_removemapping_one)) + #endif /* _LINUX_FUSE_H */ -- cgit v1.2.3 From c2d0ad00d948de73c78f05d2b3e5bdfa605035cc Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 19 Aug 2020 18:19:51 -0400 Subject: virtiofs: implement dax read/write operations This patch implements basic DAX support. mmap() is not implemented yet and will come in later patches. This patch looks into implemeting read/write. We make use of interval tree to keep track of per inode dax mappings. Do not use dax for file extending writes, instead just send WRITE message to daemon (like we do for direct I/O path). This will keep write and i_size change atomic w.r.t crash. Signed-off-by: Stefan Hajnoczi Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Vivek Goyal Signed-off-by: Liu Bo Signed-off-by: Peng Tao Cc: Dave Chinner Signed-off-by: Miklos Szeredi --- include/uapi/linux/fuse.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 60a7bfc787ce..8899e4862309 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -895,6 +895,7 @@ struct fuse_copy_file_range_in { }; #define FUSE_SETUPMAPPING_FLAG_WRITE (1ull << 0) +#define FUSE_SETUPMAPPING_FLAG_READ (1ull << 1) struct fuse_setupmapping_in { /* An already open handle */ uint64_t fh; -- cgit v1.2.3 From 6c11631480e9a0554ae5ee89dc12acaa1f1a93a0 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 11 Aug 2020 22:59:35 +0200 Subject: media: v4l2-async: Document asd allocation requirements The v4l2_async_notifier_add_subdev() function requires the asd pointer it receives to be allocated dynamically, but doesn't explicitly say so. Only one driver out of 13 get its right (atmel-sama5d2-isc.c, but with memory leaks in the error paths), clearly showing we have an issue. Update the v4l2_async_notifier_add_subdev() documentation to clearly state the allocation requirement. Whether this will be enough to avoid new offending code isn't certain, but it's a good first step nonetheless. Fixes: 9ca465312132 ("media: v4l: fwnode: Support generic parsing of graph endpoints in a device") Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-async.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-async.h b/include/media/v4l2-async.h index 8319284c93cb..d6e31234826f 100644 --- a/include/media/v4l2-async.h +++ b/include/media/v4l2-async.h @@ -154,8 +154,9 @@ void v4l2_async_notifier_init(struct v4l2_async_notifier *notifier); * @notifier: pointer to &struct v4l2_async_notifier * @asd: pointer to &struct v4l2_async_subdev * - * Call this function before registering a notifier to link the - * provided asd to the notifiers master @asd_list. + * Call this function before registering a notifier to link the provided @asd to + * the notifiers master @asd_list. The @asd must be allocated with k*alloc() as + * it will be freed by the framework when the notifier is destroyed. */ int v4l2_async_notifier_add_subdev(struct v4l2_async_notifier *notifier, struct v4l2_async_subdev *asd); -- cgit v1.2.3 From 2e654432a260d968cd505898e1c056ce6ab63c31 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 8 Sep 2020 10:16:57 +0200 Subject: media: v4l2-fwnode: Make number of data lanes a character The maximum is currently four (4). No short is needed. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fwnode.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index c47b70636e42..81e7eb123294 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -40,7 +40,7 @@ struct v4l2_fwnode_bus_mipi_csi2 { unsigned int flags; unsigned char data_lanes[V4L2_FWNODE_CSI2_MAX_DATA_LANES]; unsigned char clock_lane; - unsigned short num_data_lanes; + unsigned char num_data_lanes; bool lane_polarities[1 + V4L2_FWNODE_CSI2_MAX_DATA_LANES]; }; -- cgit v1.2.3 From bb4bba9232fc90f173a2215035334ceec0457f2f Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 8 Sep 2020 10:20:28 +0200 Subject: media: v4l2-fwnode: Make bus configuration a struct The bus specific parameters were a union. This made providing bus specific defaults impossible as the memory used to store the defaults for multiple different busses was the same. Make it struct instead. It's not large so the size isn't really an issue. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fwnode.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index 81e7eb123294..d04f39b60096 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -78,7 +78,7 @@ struct v4l2_fwnode_bus_mipi_csi1 { * struct v4l2_fwnode_endpoint - the endpoint data structure * @base: fwnode endpoint of the v4l2_fwnode * @bus_type: bus type - * @bus: union with bus configuration data structure + * @bus: bus configuration data structure * @bus.parallel: embedded &struct v4l2_fwnode_bus_parallel. * Used if the bus is parallel. * @bus.mipi_csi1: embedded &struct v4l2_fwnode_bus_mipi_csi1. @@ -99,7 +99,7 @@ struct v4l2_fwnode_endpoint { * v4l2_fwnode_endpoint_parse() */ enum v4l2_mbus_type bus_type; - union { + struct { struct v4l2_fwnode_bus_parallel parallel; struct v4l2_fwnode_bus_mipi_csi1 mipi_csi1; struct v4l2_fwnode_bus_mipi_csi2 mipi_csi2; -- cgit v1.2.3 From da5c791cfcdf11d6c2be276896cf0cb8181da1fd Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 8 Sep 2020 10:23:29 +0200 Subject: media: v4l2-fwnode: Document new usage patterns of v4l2_fwnode_endpoint_parse Document that it is possible to provide defaults for multiple bus types to v4l2_fwnode_endpoint_parse and v4l2_fwnode_endpoint_alloc_parse. Also underline the fact that detecting the bus type without bus-type property is only for the old drivers. Also correct capitalisation of BT.656. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fwnode.h | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index d04f39b60096..c09074276543 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -226,11 +226,10 @@ struct v4l2_fwnode_connector { * call this function once the correct type is found --- with a default * configuration valid for that type. * - * As a compatibility means guessing the bus type is also supported by setting - * @vep.bus_type to V4L2_MBUS_UNKNOWN. The caller may not provide a default - * configuration in this case as the defaults are specific to a given bus type. - * This functionality is deprecated and should not be used in new drivers and it - * is only supported for CSI-2 D-PHY, parallel and Bt.656 buses. + * It is also allowed to set @vep.bus_type to V4L2_MBUS_UNKNOWN. USING THIS + * FEATURE REQUIRES "bus-type" PROPERTY IN DT BINDINGS. For old drivers, + * guessing @vep.bus_type between CSI-2 D-PHY, parallel and BT.656 busses is + * supported. NEVER RELY ON GUESSING @vep.bus_type IN NEW DRIVERS! * * The function does not change the V4L2 fwnode endpoint state if it fails. * @@ -269,11 +268,10 @@ void v4l2_fwnode_endpoint_free(struct v4l2_fwnode_endpoint *vep); * call this function once the correct type is found --- with a default * configuration valid for that type. * - * As a compatibility means guessing the bus type is also supported by setting - * @vep.bus_type to V4L2_MBUS_UNKNOWN. The caller may not provide a default - * configuration in this case as the defaults are specific to a given bus type. - * This functionality is deprecated and should not be used in new drivers and it - * is only supported for CSI-2 D-PHY, parallel and Bt.656 buses. + * It is also allowed to set @vep.bus_type to V4L2_MBUS_UNKNOWN. USING THIS + * FEATURE REQUIRES "bus-type" PROPERTY IN DT BINDINGS. For old drivers, + * guessing @vep.bus_type between CSI-2 D-PHY, parallel and BT.656 busses is + * supported. NEVER RELY ON GUESSING @vep.bus_type IN NEW DRIVERS! * * The function does not change the V4L2 fwnode endpoint state if it fails. * -- cgit v1.2.3 From 150b2e86c54ad09c26e60f32925aeaf1fca1a5d3 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 10 Sep 2020 11:17:25 +0100 Subject: ASoC: q6dsp: q6afe: add support to Codec DMA ports New LPASS supports various codec macros, DSP firmware already has support to those ports. Add corresponding configuration support to those ports in adsp drivers. Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20200910101732.23484-2-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- include/dt-bindings/sound/qcom,q6afe.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/sound/qcom,q6afe.h b/include/dt-bindings/sound/qcom,q6afe.h index 1df06f8ad5c3..7207ab2b57bf 100644 --- a/include/dt-bindings/sound/qcom,q6afe.h +++ b/include/dt-bindings/sound/qcom,q6afe.h @@ -107,6 +107,28 @@ #define QUINARY_TDM_RX_7 102 #define QUINARY_TDM_TX_7 103 #define DISPLAY_PORT_RX 104 +#define WSA_CODEC_DMA_RX_0 105 +#define WSA_CODEC_DMA_TX_0 106 +#define WSA_CODEC_DMA_RX_1 107 +#define WSA_CODEC_DMA_TX_1 108 +#define WSA_CODEC_DMA_TX_2 109 +#define VA_CODEC_DMA_TX_0 110 +#define VA_CODEC_DMA_TX_1 111 +#define VA_CODEC_DMA_TX_2 112 +#define RX_CODEC_DMA_RX_0 113 +#define TX_CODEC_DMA_TX_0 114 +#define RX_CODEC_DMA_RX_1 115 +#define TX_CODEC_DMA_TX_1 116 +#define RX_CODEC_DMA_RX_2 117 +#define TX_CODEC_DMA_TX_2 118 +#define RX_CODEC_DMA_RX_3 119 +#define TX_CODEC_DMA_TX_3 120 +#define RX_CODEC_DMA_RX_4 121 +#define TX_CODEC_DMA_TX_4 122 +#define RX_CODEC_DMA_RX_5 123 +#define TX_CODEC_DMA_TX_5 124 +#define RX_CODEC_DMA_RX_6 125 +#define RX_CODEC_DMA_RX_7 126 #endif /* __DT_BINDINGS_Q6_AFE_H__ */ -- cgit v1.2.3 From 61b82bbf693ecd307550ee64a8af192e8e33c46c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 2 Sep 2020 20:31:04 +0300 Subject: swiotlb: Declare swiotlb_late_init_with_default_size() in header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Compiler is not happy about one function prototype: CC kernel/dma/swiotlb.o kernel/dma/swiotlb.c:275:1: warning: no previous prototype for ‘swiotlb_late_init_with_default_size’ [-Wmissing-prototypes] 275 | swiotlb_late_init_with_default_size(size_t default_size) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Since it's used outside of the module, move its declaration to the header from the user. Signed-off-by: Andy Shevchenko Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 046bb94bd4d6..513913ff7486 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -34,6 +34,7 @@ int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); +extern int swiotlb_late_init_with_default_size(size_t default_size); extern void __init swiotlb_update_mem_attributes(void); /* -- cgit v1.2.3 From c2ff0810934a925c9e6d96d7c400dee9bef8808e Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 7 Sep 2020 18:19:40 +0900 Subject: dt-bindings: power: Add r8a779a0 SYSC power domain definitions Add power domain indices for R-Car V3U (r8a779a0). Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/1599470390-29719-5-git-send-email-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/power/r8a779a0-sysc.h | 59 +++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 include/dt-bindings/power/r8a779a0-sysc.h (limited to 'include') diff --git a/include/dt-bindings/power/r8a779a0-sysc.h b/include/dt-bindings/power/r8a779a0-sysc.h new file mode 100644 index 000000000000..57929e459a67 --- /dev/null +++ b/include/dt-bindings/power/r8a779a0-sysc.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_POWER_R8A779A0_SYSC_H__ +#define __DT_BINDINGS_POWER_R8A779A0_SYSC_H__ + +/* + * These power domain indices match the Power Domain Register Numbers (PDR) + */ + +#define R8A779A0_PD_A1E0D0C0 0 +#define R8A779A0_PD_A1E0D0C1 1 +#define R8A779A0_PD_A1E0D1C0 2 +#define R8A779A0_PD_A1E0D1C1 3 +#define R8A779A0_PD_A1E1D0C0 4 +#define R8A779A0_PD_A1E1D0C1 5 +#define R8A779A0_PD_A1E1D1C0 6 +#define R8A779A0_PD_A1E1D1C1 7 +#define R8A779A0_PD_A2E0D0 16 +#define R8A779A0_PD_A2E0D1 17 +#define R8A779A0_PD_A2E1D0 18 +#define R8A779A0_PD_A2E1D1 19 +#define R8A779A0_PD_A3E0 20 +#define R8A779A0_PD_A3E1 21 +#define R8A779A0_PD_3DG_A 24 +#define R8A779A0_PD_3DG_B 25 +#define R8A779A0_PD_A1CNN2 32 +#define R8A779A0_PD_A1DSP0 33 +#define R8A779A0_PD_A2IMP01 34 +#define R8A779A0_PD_A2DP0 35 +#define R8A779A0_PD_A2CV0 36 +#define R8A779A0_PD_A2CV1 37 +#define R8A779A0_PD_A2CV4 38 +#define R8A779A0_PD_A2CV6 39 +#define R8A779A0_PD_A2CN2 40 +#define R8A779A0_PD_A1CNN0 41 +#define R8A779A0_PD_A2CN0 42 +#define R8A779A0_PD_A3IR 43 +#define R8A779A0_PD_A1CNN1 44 +#define R8A779A0_PD_A1DSP1 45 +#define R8A779A0_PD_A2IMP23 46 +#define R8A779A0_PD_A2DP1 47 +#define R8A779A0_PD_A2CV2 48 +#define R8A779A0_PD_A2CV3 49 +#define R8A779A0_PD_A2CV5 50 +#define R8A779A0_PD_A2CV7 51 +#define R8A779A0_PD_A2CN1 52 +#define R8A779A0_PD_A3VIP0 56 +#define R8A779A0_PD_A3VIP1 57 +#define R8A779A0_PD_A3VIP2 58 +#define R8A779A0_PD_A3VIP3 59 +#define R8A779A0_PD_A3ISP01 60 +#define R8A779A0_PD_A3ISP23 61 + +/* Always-on power area */ +#define R8A779A0_PD_ALWAYS_ON 64 + +#endif /* __DT_BINDINGS_POWER_R8A779A0_SYSC_H__ */ -- cgit v1.2.3 From fa2d185f7518423ffcdba617ad09ff77ac51f198 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 9 Sep 2020 22:13:28 +0900 Subject: dt-bindings: clock: Add r8a779a0 CPG Core Clock Definitions Add all Clock Pulse Generator Core Clock Outputs for the Renesas R-Car V3U (R8A779A0) SoC. Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/1599657211-17504-2-git-send-email-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r8a779a0-cpg-mssr.h | 55 +++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 include/dt-bindings/clock/r8a779a0-cpg-mssr.h (limited to 'include') diff --git a/include/dt-bindings/clock/r8a779a0-cpg-mssr.h b/include/dt-bindings/clock/r8a779a0-cpg-mssr.h new file mode 100644 index 000000000000..f1d737ca7ca1 --- /dev/null +++ b/include/dt-bindings/clock/r8a779a0-cpg-mssr.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R8A779A0_CPG_MSSR_H__ +#define __DT_BINDINGS_CLOCK_R8A779A0_CPG_MSSR_H__ + +#include + +/* r8a779A0 CPG Core Clocks */ +#define R8A779A0_CLK_Z0 0 +#define R8A779A0_CLK_ZX 1 +#define R8A779A0_CLK_Z1 2 +#define R8A779A0_CLK_ZR 3 +#define R8A779A0_CLK_ZS 4 +#define R8A779A0_CLK_ZT 5 +#define R8A779A0_CLK_ZTR 6 +#define R8A779A0_CLK_S1D1 7 +#define R8A779A0_CLK_S1D2 8 +#define R8A779A0_CLK_S1D4 9 +#define R8A779A0_CLK_S1D8 10 +#define R8A779A0_CLK_S1D12 11 +#define R8A779A0_CLK_S3D1 12 +#define R8A779A0_CLK_S3D2 13 +#define R8A779A0_CLK_S3D4 14 +#define R8A779A0_CLK_LB 15 +#define R8A779A0_CLK_CP 16 +#define R8A779A0_CLK_CL 17 +#define R8A779A0_CLK_CL16MCK 18 +#define R8A779A0_CLK_ZB30 19 +#define R8A779A0_CLK_ZB30D2 20 +#define R8A779A0_CLK_ZB30D4 21 +#define R8A779A0_CLK_ZB31 22 +#define R8A779A0_CLK_ZB31D2 23 +#define R8A779A0_CLK_ZB31D4 24 +#define R8A779A0_CLK_SD0H 25 +#define R8A779A0_CLK_SD0 26 +#define R8A779A0_CLK_RPC 27 +#define R8A779A0_CLK_RPCD2 28 +#define R8A779A0_CLK_MSO 29 +#define R8A779A0_CLK_CANFD 30 +#define R8A779A0_CLK_CSI0 31 +#define R8A779A0_CLK_FRAY 32 +#define R8A779A0_CLK_DSI 33 +#define R8A779A0_CLK_VIP 34 +#define R8A779A0_CLK_ADGH 35 +#define R8A779A0_CLK_CNNDSP 36 +#define R8A779A0_CLK_ICU 37 +#define R8A779A0_CLK_ICUD2 38 +#define R8A779A0_CLK_VCBUS 39 +#define R8A779A0_CLK_CBFUSA 40 +#define R8A779A0_CLK_R 41 +#define R8A779A0_CLK_OSC 42 + +#endif /* __DT_BINDINGS_CLOCK_R8A779A0_CPG_MSSR_H__ */ -- cgit v1.2.3 From 95f6f3a46fc4ee1a2b216a6b46bdf2b450f1877f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 16:53:29 +0200 Subject: block: add a bdev_check_media_change helper Like check_disk_changed, except that it does not call ->revalidate_disk but leaves that to the caller. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index c618b27292fc..322d48a20772 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -315,7 +315,6 @@ extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev); -extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; @@ -372,6 +371,7 @@ void unregister_blkdev(unsigned int major, const char *name); void revalidate_disk_size(struct gendisk *disk, bool verbose); int check_disk_change(struct block_device *bdev); +bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); -- cgit v1.2.3 From fec2cf607ba9305770436b1e5c485963a9f0a7bd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 16:53:42 +0200 Subject: ide-gd: stop using the disk events mechanism ide-gd is only using the disk events mechanism to be able to force an invalidation and partition scan on opening removable media. Just open code the logic without invoving the block layer. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index a254841bd315..62653769509f 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -490,8 +490,6 @@ enum { IDE_DFLAG_NOPROBE = BIT(9), /* need to do check_media_change() */ IDE_DFLAG_REMOVABLE = BIT(10), - /* needed for removable devices */ - IDE_DFLAG_ATTACH = BIT(11), IDE_DFLAG_FORCED_GEOM = BIT(12), /* disallow setting unmask bit */ IDE_DFLAG_NO_UNMASK = BIT(13), -- cgit v1.2.3 From b92b53079aedbfb56bbb9ea360e5119fb563a2a1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 16:53:47 +0200 Subject: block: remove check_disk_change Remove the now unused check_disk_change helper. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 322d48a20772..1c97cf84f011 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -370,7 +370,6 @@ int register_blkdev(unsigned int major, const char *name); void unregister_blkdev(unsigned int major, const char *name); void revalidate_disk_size(struct gendisk *disk, bool verbose); -int check_disk_change(struct block_device *bdev); bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); -- cgit v1.2.3 From 00089c048eb4a8250325efb32a2724fd0da68cce Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Fri, 4 Sep 2020 16:30:25 +0100 Subject: objtool: Rename frame.h -> objtool.h Header frame.h is getting more code annotations to help objtool analyze object files. Rename the file to objtool.h. [ jpoimboe: add objtool.h to MAINTAINERS ] Signed-off-by: Julien Thierry Signed-off-by: Josh Poimboeuf --- include/linux/frame.h | 35 ----------------------------------- include/linux/objtool.h | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 35 deletions(-) delete mode 100644 include/linux/frame.h create mode 100644 include/linux/objtool.h (limited to 'include') diff --git a/include/linux/frame.h b/include/linux/frame.h deleted file mode 100644 index 303cda600e56..000000000000 --- a/include/linux/frame.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_FRAME_H -#define _LINUX_FRAME_H - -#ifdef CONFIG_STACK_VALIDATION -/* - * This macro marks the given function's stack frame as "non-standard", which - * tells objtool to ignore the function when doing stack metadata validation. - * It should only be used in special cases where you're 100% sure it won't - * affect the reliability of frame pointers and kernel stack traces. - * - * For more information, see tools/objtool/Documentation/stack-validation.txt. - */ -#define STACK_FRAME_NON_STANDARD(func) \ - static void __used __section(.discard.func_stack_frame_non_standard) \ - *__func_stack_frame_non_standard_##func = func - -/* - * This macro indicates that the following intra-function call is valid. - * Any non-annotated intra-function call will cause objtool to issue a warning. - */ -#define ANNOTATE_INTRA_FUNCTION_CALL \ - 999: \ - .pushsection .discard.intra_function_calls; \ - .long 999b; \ - .popsection; - -#else /* !CONFIG_STACK_VALIDATION */ - -#define STACK_FRAME_NON_STANDARD(func) -#define ANNOTATE_INTRA_FUNCTION_CALL - -#endif /* CONFIG_STACK_VALIDATION */ - -#endif /* _LINUX_FRAME_H */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h new file mode 100644 index 000000000000..358175c9c2b5 --- /dev/null +++ b/include/linux/objtool.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_OBJTOOL_H +#define _LINUX_OBJTOOL_H + +#ifdef CONFIG_STACK_VALIDATION +/* + * This macro marks the given function's stack frame as "non-standard", which + * tells objtool to ignore the function when doing stack metadata validation. + * It should only be used in special cases where you're 100% sure it won't + * affect the reliability of frame pointers and kernel stack traces. + * + * For more information, see tools/objtool/Documentation/stack-validation.txt. + */ +#define STACK_FRAME_NON_STANDARD(func) \ + static void __used __section(.discard.func_stack_frame_non_standard) \ + *__func_stack_frame_non_standard_##func = func + +/* + * This macro indicates that the following intra-function call is valid. + * Any non-annotated intra-function call will cause objtool to issue a warning. + */ +#define ANNOTATE_INTRA_FUNCTION_CALL \ + 999: \ + .pushsection .discard.intra_function_calls; \ + .long 999b; \ + .popsection; + +#else /* !CONFIG_STACK_VALIDATION */ + +#define STACK_FRAME_NON_STANDARD(func) +#define ANNOTATE_INTRA_FUNCTION_CALL + +#endif /* CONFIG_STACK_VALIDATION */ + +#endif /* _LINUX_OBJTOOL_H */ -- cgit v1.2.3 From 5567c6c39f3404e4492c18c0c1abff5556684f6e Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Fri, 4 Sep 2020 16:30:26 +0100 Subject: objtool: Only include valid definitions depending on source file type Header include/linux/objtool.h contains both C and assembly definition that are visible regardless of the file including them. Place definition under conditional __ASSEMBLY__. Reviewed-by: Miroslav Benes Signed-off-by: Julien Thierry Signed-off-by: Josh Poimboeuf --- include/linux/objtool.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 358175c9c2b5..15e9997a9fb4 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -3,6 +3,8 @@ #define _LINUX_OBJTOOL_H #ifdef CONFIG_STACK_VALIDATION + +#ifndef __ASSEMBLY__ /* * This macro marks the given function's stack frame as "non-standard", which * tells objtool to ignore the function when doing stack metadata validation. @@ -15,6 +17,8 @@ static void __used __section(.discard.func_stack_frame_non_standard) \ *__func_stack_frame_non_standard_##func = func +#else /* __ASSEMBLY__ */ + /* * This macro indicates that the following intra-function call is valid. * Any non-annotated intra-function call will cause objtool to issue a warning. @@ -25,6 +29,8 @@ .long 999b; \ .popsection; +#endif /* __ASSEMBLY__ */ + #else /* !CONFIG_STACK_VALIDATION */ #define STACK_FRAME_NON_STANDARD(func) -- cgit v1.2.3 From ee819aedf34a8f35cd54ee3967c7beb4d1d4a635 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Fri, 4 Sep 2020 16:30:27 +0100 Subject: objtool: Make unwind hint definitions available to other architectures Unwind hints are useful to provide objtool with information about stack states in non-standard functions/code. While the type of information being provided might be very arch specific, the mechanism to provide the information can be useful for other architectures. Move the relevant unwint hint definitions for all architectures to see. [ jpoimboe: REGS_IRET -> REGS_PARTIAL ] Signed-off-by: Julien Thierry Signed-off-by: Josh Poimboeuf --- include/linux/objtool.h | 88 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) (limited to 'include') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 15e9997a9fb4..ab82c793c897 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -2,9 +2,55 @@ #ifndef _LINUX_OBJTOOL_H #define _LINUX_OBJTOOL_H +#ifndef __ASSEMBLY__ + +#include + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; + u8 end; +}; +#endif + +/* + * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP + * (the caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset + * points to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that + * sp_reg+sp_offset points to the iret return frame. + */ +#define UNWIND_HINT_TYPE_CALL 0 +#define UNWIND_HINT_TYPE_REGS 1 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +#define UNWIND_HINT_TYPE_RET_OFFSET 3 + #ifdef CONFIG_STACK_VALIDATION #ifndef __ASSEMBLY__ + +#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ + "987: \n\t" \ + ".pushsection .discard.unwind_hints\n\t" \ + /* struct unwind_hint */ \ + ".long 987b - .\n\t" \ + ".short " __stringify(sp_offset) "\n\t" \ + ".byte " __stringify(sp_reg) "\n\t" \ + ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(end) "\n\t" \ + ".balign 4 \n\t" \ + ".popsection\n\t" + /* * This macro marks the given function's stack frame as "non-standard", which * tells objtool to ignore the function when doing stack metadata validation. @@ -29,12 +75,54 @@ .long 999b; \ .popsection; +/* + * In asm, there are two kinds of code: normal C-type callable functions and + * the rest. The normal callable functions can be called by other code, and + * don't do anything unusual with the stack. Such normal callable functions + * are annotated with the ENTRY/ENDPROC macros. Most asm code falls in this + * category. In this case, no special debugging annotations are needed because + * objtool can automatically generate the ORC data for the ORC unwinder to read + * at runtime. + * + * Anything which doesn't fall into the above category, such as syscall and + * interrupt handlers, tends to not be called directly by other functions, and + * often does unusual non-C-function-type things with the stack pointer. Such + * code needs to be annotated such that objtool can understand it. The + * following CFI hint macros are for this type of code. + * + * These macros provide hints to objtool about the state of the stack at each + * instruction. Objtool starts from the hints and follows the code flow, + * making automatic CFI adjustments when it sees pushes and pops, filling out + * the debuginfo as necessary. It will also warn if it sees any + * inconsistencies. + */ +.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.Lunwind_hint_ip_\@: + .pushsection .discard.unwind_hints + /* struct unwind_hint */ + .long .Lunwind_hint_ip_\@ - . + .short \sp_offset + .byte \sp_reg + .byte \type + .byte \end + .balign 4 + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ +#ifndef __ASSEMBLY__ + +#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ + "\n\t" #define STACK_FRAME_NON_STANDARD(func) +#else #define ANNOTATE_INTRA_FUNCTION_CALL +.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.endm +#endif #endif /* CONFIG_STACK_VALIDATION */ -- cgit v1.2.3 From baaabecfc80fad255f866563b53b8c7a3eec176e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 9 Sep 2020 15:53:54 -0700 Subject: test_firmware: Test platform fw loading on non-EFI systems On non-EFI systems, it wasn't possible to test the platform firmware loader because it will have never set "checked_fw" during __init. Instead, allow the test code to override this check. Additionally split the declarations into a private symbol namespace so there is greater enforcement of the symbol visibility. Fixes: 548193cba2a7 ("test_firmware: add support for firmware_request_platform") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20200909225354.3118328-1-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/efi_embedded_fw.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h index 57eac5241303..a97a12bb2c9e 100644 --- a/include/linux/efi_embedded_fw.h +++ b/include/linux/efi_embedded_fw.h @@ -8,8 +8,8 @@ #define EFI_EMBEDDED_FW_PREFIX_LEN 8 /* - * This struct and efi_embedded_fw_list are private to the efi-embedded fw - * implementation they are in this header for use by lib/test_firmware.c only! + * This struct is private to the efi-embedded fw implementation. + * They are in this header for use by lib/test_firmware.c only! */ struct efi_embedded_fw { struct list_head list; @@ -18,8 +18,6 @@ struct efi_embedded_fw { size_t length; }; -extern struct list_head efi_embedded_fw_list; - /** * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw * code to search for embedded firmwares. -- cgit v1.2.3 From 0feea33d79825d05b5ede30947db4df34722b463 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Wed, 22 Jul 2020 15:01:20 -0700 Subject: soc: qcom-geni-se: Don't use relaxed writes when writing commands Writing the command is the final step in kicking off a transfer. Let's use writel() to ensure that any other memory accesses are done before the command kicks off. It's expected that this is mostly relevant if we're in DMA mode but since it doesn't appear to regress performance in a measurable way [1] even in PIO mode and it's easier to reason about then let's just always use it. NOTE: this patch came about due to code inspection. No actual problems were observed that this patch fixes. [1] Tested by timing "flashrom -p ec" on a Chromebook which stresses GENI SPI a lot. Reviewed-by: Mukesh Kumar Savaliya Reviewed-by: Akash Asthana Reviewed-by: Stephen Boyd Suggested-by: Stephen Boyd Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20200722150113.1.Ia50ab5cb8a6d3a73d302e6bdc25542d48ffd27f4@changeid Signed-off-by: Bjorn Andersson --- include/linux/qcom-geni-se.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 8f385fbe5a0e..ae4a8a766b69 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -296,7 +296,7 @@ static inline void geni_se_setup_m_cmd(struct geni_se *se, u32 cmd, u32 params) u32 m_cmd; m_cmd = (cmd << M_OPCODE_SHFT) | (params & M_PARAMS_MSK); - writel_relaxed(m_cmd, se->base + SE_GENI_M_CMD0); + writel(m_cmd, se->base + SE_GENI_M_CMD0); } /** @@ -316,7 +316,7 @@ static inline void geni_se_setup_s_cmd(struct geni_se *se, u32 cmd, u32 params) s_cmd &= ~(S_OPCODE_MSK | S_PARAMS_MSK); s_cmd |= (cmd << S_OPCODE_SHFT); s_cmd |= (params & S_PARAMS_MSK); - writel_relaxed(s_cmd, se->base + SE_GENI_S_CMD0); + writel(s_cmd, se->base + SE_GENI_S_CMD0); } /** -- cgit v1.2.3 From 95035eac763294eb4543aea9afd48d2f7c8caa5c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:42:52 -0700 Subject: PM: : fix @em_pd kernel-doc warning Fix kernel-doc warning in : ../include/linux/device.h:613: warning: Function parameter or member 'em_pd' not described in 'device' Fixes: 1bc138c62295 ("PM / EM: add support for other devices than CPUs in Energy Model") Signed-off-by: Randy Dunlap Reviewed-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index ca18da4768e3..9e6ea8931a52 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -454,6 +454,7 @@ struct dev_links_info { * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. + * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors -- cgit v1.2.3 From cc88b78c0870ebcab2123ba9e73689d97fbf3b14 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Thu, 10 Sep 2020 15:57:46 +0530 Subject: powercap: make documentation reflect code Fix up the documentation of the struct powercap_control_type members to match the code. Also fixup stray whitespace. Signed-off-by: Amit Kucheria [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/powercap.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/powercap.h b/include/linux/powercap.h index 4537f57f9e42..3d557bbcd2c7 100644 --- a/include/linux/powercap.h +++ b/include/linux/powercap.h @@ -44,19 +44,18 @@ struct powercap_control_type_ops { }; /** - * struct powercap_control_type- Defines a powercap control_type - * @name: name of control_type + * struct powercap_control_type - Defines a powercap control_type * @dev: device for this control_type * @idr: idr to have unique id for its child - * @root_node: Root holding power zones for this control_type + * @nr_zones: counter for number of zones of this type * @ops: Pointer to callback struct - * @node_lock: mutex for control type + * @lock: mutex for control type * @allocated: This is possible that client owns the memory * used by this structure. In this case * this flag is set to false by framework to * prevent deallocation during release process. * Otherwise this flag is set to true. - * @ctrl_inst: link to the control_type list + * @node: linked-list node * * Defines powercap control_type. This acts as a container for power * zones, which use same method to control power. E.g. RAPL, RAPL-PCI etc. @@ -129,7 +128,7 @@ struct powercap_zone_ops { * this flag is set to false by framework to * prevent deallocation during release process. * Otherwise this flag is set to true. - * @constraint_ptr: List of constraints for this zone. + * @constraints: List of constraints for this zone. * * This defines a power zone instance. The fields of this structure are * private, and should not be used by client drivers. -- cgit v1.2.3 From 501cb008906631a019f3ab2104a17ef8b2651ed0 Mon Sep 17 00:00:00 2001 From: Paul Davey Date: Tue, 8 Sep 2020 10:04:06 +1200 Subject: ipmr: Add route table ID to netlink cache reports Insert the multicast route table ID as a Netlink attribute to Netlink cache report notifications. When multiple route tables are in use it is necessary to have a way to determine which route table a given cache report belongs to when receiving the cache report. Signed-off-by: Paul Davey Signed-off-by: David S. Miller --- include/uapi/linux/mroute.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h index 11c8c1fc1124..918f1ef32ffe 100644 --- a/include/uapi/linux/mroute.h +++ b/include/uapi/linux/mroute.h @@ -169,6 +169,7 @@ enum { IPMRA_CREPORT_SRC_ADDR, IPMRA_CREPORT_DST_ADDR, IPMRA_CREPORT_PKT, + IPMRA_CREPORT_TABLE, __IPMRA_CREPORT_MAX }; #define IPMRA_CREPORT_MAX (__IPMRA_CREPORT_MAX - 1) -- cgit v1.2.3 From c8715a8e9f38906e73d6d78764216742db13ba0e Mon Sep 17 00:00:00 2001 From: Paul Davey Date: Tue, 8 Sep 2020 10:04:07 +1200 Subject: ipmr: Add high byte of VIF ID to igmpmsg Use the unused3 byte in struct igmpmsg to hold the high 8 bits of the VIF ID. If using more than 255 IPv4 multicast interfaces it is necessary to have access to a VIF ID for cache reports that is wider than 8 bits, the VIF ID present in the igmpmsg reports sent to mroute_sk was only 8 bits wide in the igmpmsg header. Adding the high 8 bits of the 16 bit VIF ID in the unused byte allows use of more than 255 IPv4 multicast interfaces. Signed-off-by: Paul Davey Signed-off-by: David S. Miller --- include/uapi/linux/mroute.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h index 918f1ef32ffe..1a42f5f9b31b 100644 --- a/include/uapi/linux/mroute.h +++ b/include/uapi/linux/mroute.h @@ -113,8 +113,8 @@ struct igmpmsg { __u32 unused1,unused2; unsigned char im_msgtype; /* What is this */ unsigned char im_mbz; /* Must be zero */ - unsigned char im_vif; /* Interface (this ought to be a vifi_t!) */ - unsigned char unused3; + unsigned char im_vif; /* Low 8 bits of Interface */ + unsigned char im_vif_hi; /* High 8 bits of Interface */ struct in_addr im_src,im_dst; }; -- cgit v1.2.3 From 5198d545dba8ad893f5e5a029ca8d43ee7bcf011 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 9 Sep 2020 10:37:51 -0700 Subject: net: remove napi_hash_del() from driver-facing API We allow drivers to call napi_hash_del() before calling netif_napi_del() to batch RCU grace periods. This makes the API asymmetric and leaks internal implementation details. Soon we will want the grace period to protect more than just the NAPI hash table. Restructure the API and have drivers call a new function - __netif_napi_del() if they want to take care of RCU waits. Note that only core was checking the return status from napi_hash_del() so the new helper does not report if the NAPI was actually deleted. Some notes on driver oddness: - veth observed the grace period before calling netif_napi_del() but that should not matter - myri10ge observed normal RCU flavor - bnx2x and enic did not actually observe the grace period (unless they did so implicitly) - virtio_net and enic only unhashed Rx NAPIs The last two points seem to indicate that the calls to napi_hash_del() were a left over rather than an optimization. Regardless, it's easy enough to correct them. This patch may introduce extra synchronize_net() calls for interfaces which set NAPI_STATE_NO_BUSY_POLL and depend on free_netdev() to call netif_napi_del(). This seems inevitable since we want to use RCU for netpoll dev->napi_list traversal, and almost no drivers set IFF_DISABLE_NETPOLL. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f9fcfd15942..74ed95215091 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -70,6 +70,7 @@ struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; +void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -488,20 +489,6 @@ static inline bool napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } -/** - * napi_hash_del - remove a NAPI from global table - * @napi: NAPI context - * - * Warning: caller must observe RCU grace period - * before freeing memory containing @napi, if - * this function returns true. - * Note: core networking stack automatically calls it - * from netif_napi_del(). - * Drivers might want to call this helper to combine all - * the needed RCU grace periods into a single one. - */ -bool napi_hash_del(struct napi_struct *napi); - /** * napi_disable - prevent NAPI from scheduling * @n: NAPI context @@ -2367,13 +2354,27 @@ static inline void netif_tx_napi_add(struct net_device *dev, netif_napi_add(dev, napi, poll, weight); } +/** + * __netif_napi_del - remove a NAPI context + * @napi: NAPI context + * + * Warning: caller must observe RCU grace period before freeing memory + * containing @napi. Drivers might want to call this helper to combine + * all the needed RCU grace periods into a single one. + */ +void __netif_napi_del(struct napi_struct *napi); + /** * netif_napi_del - remove a NAPI context * @napi: NAPI context * * netif_napi_del() removes a NAPI context from the network device NAPI list */ -void netif_napi_del(struct napi_struct *napi); +static inline void netif_napi_del(struct napi_struct *napi) +{ + __netif_napi_del(napi); + synchronize_net(); +} struct napi_gro_cb { /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ @@ -2797,7 +2798,6 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); void netdev_freemem(struct net_device *dev); -void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, -- cgit v1.2.3 From 4d092dd2041a5f328410ad16d63b8606c24e8604 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 9 Sep 2020 10:37:52 -0700 Subject: net: manage napi add/del idempotence explicitly To RCUify napi->dev_list we need to replace list_del_init() with list_del_rcu(). There is no _init() version for RCU for obvious reasons. Up until now netif_napi_del() was idempotent so to make sure it remains such add a bit which is set when NAPI is listed, and cleared when it removed. Since we don't expect multiple calls to netif_napi_add() to be correct, add a warning on that side. Now that napi_hash_add / napi_hash_del are only called by napi_add / del we can actually steal its bit. We just need to make sure hash node is initialized correctly. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 74ed95215091..157e0242e9ee 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -355,7 +355,7 @@ enum { NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ - NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ + NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ }; @@ -365,7 +365,7 @@ enum { NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), - NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED), + NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; -- cgit v1.2.3 From e9b12edc133b54e15ecd105620d51fb8e8fa8bde Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Wed, 9 Sep 2020 17:50:46 -0700 Subject: tcp: record received TOS value in the request socket A new field is added to the request sock to record the TOS value received on the listening socket during 3WHS: When not under syn flood, it is recording the TOS value sent in SYN. When under syn flood, it is recording the TOS value sent in the ACK. This is a preparation patch in order to do TOS reflection in the later commit. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 56ff2952edaf..2f87377e9af7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -134,6 +134,7 @@ struct tcp_request_sock { * FastOpen it's the seq# * after data-in-SYN. */ + u8 syn_tos; }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) -- cgit v1.2.3 From de033b7d1568a8f1252055c96cdd99954d5450c4 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Wed, 9 Sep 2020 17:50:47 -0700 Subject: ip: pass tos into ip_build_and_send_pkt() This commit adds tos as a new passed in parameter to ip_build_and_send_pkt() which will be used in the later commit. This is a pure restructure and does not have any functional change. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index b09c48d862cc..0f72bf8c0cbf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -151,7 +151,7 @@ int igmp_mc_init(void); int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, - struct ip_options_rcu *opt); + struct ip_options_rcu *opt, u8 tos); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ip_list_rcv(struct list_head *head, struct packet_type *pt, -- cgit v1.2.3 From ac8f1710c12bb4c3626280ce03f05459ba8feef6 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Wed, 9 Sep 2020 17:50:48 -0700 Subject: tcp: reflect tos value received in SYN to the socket This commit adds a new TCP feature to reflect the tos value received in SYN, and send it out on the SYN-ACK, and eventually set the tos value of the established socket with this reflected tos value. This provides a way to set the traffic class/QoS level for all traffic in the same connection to be the same as the incoming SYN request. It could be useful in data centers to provide equivalent QoS according to the incoming request. This feature is guarded by /proc/sys/net/ipv4/tcp_reflect_tos, and is by default turned off. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 9e36738c1fe1..8e4fcac4df72 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -183,6 +183,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; + int sysctl_tcp_reflect_tos; int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; -- cgit v1.2.3 From 83896b0bd8223ac33bcc609bcc82a57a587002ff Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 10 Sep 2020 04:46:40 -0400 Subject: net: Fix broken NETIF_F_CSUM_MASK spell in netdev_features.h Remove the weird space inside the NETIF_F_CSUM_MASK. Signed-off-by: Miaohe Lin Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2cc3cf80b49a..0b17c4322b09 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -193,7 +193,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \ __NETIF_F_BIT(NETIF_F_GSO_SHIFT)) -/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be +/* List of IP checksum features. Note that NETIF_F_HW_CSUM should not be * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- * this would be contradictory */ -- cgit v1.2.3 From 3d7bfea8b8378277a25b42b28fe5a2a5ca76a7cf Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 8 Jul 2020 02:12:34 -0700 Subject: unicode: Add utf8_casefold_hash This adds a case insensitive hash function to allow taking the hash without needing to allocate a casefolded copy of the string. The existing d_hash implementations for casefolding allocate memory within rcu-walk, by avoiding it we can be more efficient and avoid worrying about a failed allocation. Signed-off-by: Daniel Rosenberg Reviewed-by: Gabriel Krisman Bertazi Reviewed-by: Eric Biggers Signed-off-by: Jaegeuk Kim --- include/linux/unicode.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 990aa97d8049..74484d44c755 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -27,6 +27,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str, int utf8_casefold(const struct unicode_map *um, const struct qstr *str, unsigned char *dest, size_t dlen); +int utf8_casefold_hash(const struct unicode_map *um, const void *salt, + struct qstr *str); + struct unicode_map *utf8_load(const char *version); void utf8_unload(struct unicode_map *um); -- cgit v1.2.3 From c843843e714c8f17280d7db009412b1b1baf448b Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 8 Jul 2020 02:12:35 -0700 Subject: fs: Add standard casefolding support This adds general supporting functions for filesystems that use utf8 casefolding. It provides standard dentry_operations and adds the necessary structures in struct super_block to allow this standardization. The new dentry operations are functionally equivalent to the existing operations in ext4 and f2fs, apart from the use of utf8_casefold_hash to avoid an allocation. By providing a common implementation, all users can benefit from any optimizations without needing to port over improvements. Signed-off-by: Daniel Rosenberg Reviewed-by: Eric Biggers Signed-off-by: Jaegeuk Kim --- include/linux/fs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a08..bc5417c61e12 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1371,6 +1371,12 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_ACTIVE (1<<30) #define SB_NOUSER (1<<31) +/* These flags relate to encoding and casefolding */ +#define SB_ENC_STRICT_MODE_FL (1 << 0) + +#define sb_has_strict_encoding(sb) \ + (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) + /* * Umount options */ @@ -1440,6 +1446,10 @@ struct super_block { #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; +#endif +#ifdef CONFIG_UNICODE + struct unicode_map *s_encoding; + __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ @@ -3262,6 +3272,12 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); +#ifdef CONFIG_UNICODE +extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); +extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name); +#endif + #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, struct page *, struct page *, -- cgit v1.2.3 From eca4873ee1b63ee051e0eed91099fa42c97b2438 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 8 Jul 2020 02:12:36 -0700 Subject: f2fs: Use generic casefolding support This switches f2fs over to the generic support provided in the previous patch. Since casefolded dentries behave the same in ext4 and f2fs, we decrease the maintenance burden by unifying them, and any optimizations will immediately apply to both. Signed-off-by: Daniel Rosenberg Reviewed-by: Eric Biggers Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 3c383ddd92dd..a5dbb57a687f 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -38,9 +38,6 @@ #define F2FS_MAX_QUOTAS 3 #define F2FS_ENC_UTF8_12_1 1 -#define F2FS_ENC_STRICT_MODE_FL (1 << 0) -#define f2fs_has_strict_mode(sbi) \ - (sbi->s_encoding_flags & F2FS_ENC_STRICT_MODE_FL) #define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ #define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ -- cgit v1.2.3 From 553d87b658fed0e22a0f86b4f1b093c39d3e3074 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 10 Sep 2020 15:34:39 +0200 Subject: netlink: fix doc about nlmsg_parse/nla_validate There is no @validate argument. CC: Johannes Berg Fixes: 3de644035446 ("netlink: re-add parse/validate functions in strict mode") Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/netlink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index c0411f14fb53..8e0eb2c9c528 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -726,7 +726,6 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected - * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() @@ -824,7 +823,6 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy - * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the -- cgit v1.2.3 From d66423fbe11e141206f117b232916aa899d44959 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 10 Sep 2020 12:02:48 +0100 Subject: bpf: Plug hole in struct bpf_sk_lookup_kern As Alexei points out, struct bpf_sk_lookup_kern has two 4-byte holes. This leads to suboptimal instructions being generated (IPv4, x86): 1372 struct bpf_sk_lookup_kern ctx = { 0xffffffff81b87f30 <+624>: xor %eax,%eax 0xffffffff81b87f32 <+626>: mov $0x6,%ecx 0xffffffff81b87f37 <+631>: lea 0x90(%rsp),%rdi 0xffffffff81b87f3f <+639>: movl $0x110002,0x88(%rsp) 0xffffffff81b87f4a <+650>: rep stos %rax,%es:(%rdi) 0xffffffff81b87f4d <+653>: mov 0x8(%rsp),%eax 0xffffffff81b87f51 <+657>: mov %r13d,0x90(%rsp) 0xffffffff81b87f59 <+665>: incl %gs:0x7e4970a0(%rip) 0xffffffff81b87f60 <+672>: mov %eax,0x8c(%rsp) 0xffffffff81b87f67 <+679>: movzwl 0x10(%rsp),%eax 0xffffffff81b87f6c <+684>: mov %ax,0xa8(%rsp) 0xffffffff81b87f74 <+692>: movzwl 0x38(%rsp),%eax 0xffffffff81b87f79 <+697>: mov %ax,0xaa(%rsp) Fix this by moving around sport and dport. pahole confirms there are no more holes: struct bpf_sk_lookup_kern { u16 family; /* 0 2 */ u16 protocol; /* 2 2 */ __be16 sport; /* 4 2 */ u16 dport; /* 6 2 */ struct { __be32 saddr; /* 8 4 */ __be32 daddr; /* 12 4 */ } v4; /* 8 8 */ struct { const struct in6_addr * saddr; /* 16 8 */ const struct in6_addr * daddr; /* 24 8 */ } v6; /* 16 16 */ struct sock * selected_sk; /* 32 8 */ bool no_reuseport; /* 40 1 */ /* size: 48, cachelines: 1, members: 8 */ /* padding: 7 */ /* last cacheline: 48 bytes */ }; The assembly also doesn't contain the pesky rep stos anymore: 1372 struct bpf_sk_lookup_kern ctx = { 0xffffffff81b87f60 <+624>: movzwl 0x10(%rsp),%eax 0xffffffff81b87f65 <+629>: movq $0x0,0xa8(%rsp) 0xffffffff81b87f71 <+641>: movq $0x0,0xb0(%rsp) 0xffffffff81b87f7d <+653>: mov %ax,0x9c(%rsp) 0xffffffff81b87f85 <+661>: movzwl 0x38(%rsp),%eax 0xffffffff81b87f8a <+666>: movq $0x0,0xb8(%rsp) 0xffffffff81b87f96 <+678>: mov %ax,0x9e(%rsp) 0xffffffff81b87f9e <+686>: mov 0x8(%rsp),%eax 0xffffffff81b87fa2 <+690>: movq $0x0,0xc0(%rsp) 0xffffffff81b87fae <+702>: movl $0x110002,0x98(%rsp) 0xffffffff81b87fb9 <+713>: mov %eax,0xa0(%rsp) 0xffffffff81b87fc0 <+720>: mov %r13d,0xa4(%rsp) 1: https://lore.kernel.org/bpf/CAADnVQKE6y9h2fwX6OS837v-Uf+aBXnT_JXiN_bbo2gitZQ3tA@mail.gmail.com/ Fixes: e9ddbb7707ff ("bpf: Introduce SK_LOOKUP program type with a dedicated attach point") Suggested-by: Alexei Starovoitov Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/20200910110248.198326-1-lmb@cloudflare.com --- include/linux/filter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 995625950cc1..e962dd8117d8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1287,6 +1287,8 @@ int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; + __be16 sport; + u16 dport; struct { __be32 saddr; __be32 daddr; @@ -1295,8 +1297,6 @@ struct bpf_sk_lookup_kern { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; - __be16 sport; - u16 dport; struct sock *selected_sk; bool no_reuseport; }; -- cgit v1.2.3 From 1aef5b4391f0c75c0a1523706a7b0311846ee12f Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 10 Sep 2020 13:33:14 -0700 Subject: bpf: Fix comment for helper bpf_current_task_under_cgroup() This should be "current" not "skb". Fixes: c6b5fb8690fa ("bpf: add documentation for eBPF helpers (42-50)") Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Cc: Link: https://lore.kernel.org/bpf/20200910203314.70018-1-songliubraving@fb.com --- include/uapi/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 90359cab501d..7dd314176df7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1447,8 +1447,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if the *skb* task belongs to the cgroup2. - * * 1, if the *skb* task does not belong to the cgroup2. + * * 0, if current task belongs to the cgroup2. + * * 1, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) -- cgit v1.2.3 From 8919a9b31eb4fb4c0a93e5fb350a626924302aa6 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Thu, 10 Sep 2020 15:35:32 -0400 Subject: tcp: Only init congestion control if not initialized already Change tcp_init_transfer() to only initialize congestion control if it has not been initialized already. With this new approach, we can arrange things so that if the EBPF code sets the congestion control by calling setsockopt(TCP_CONGESTION) then tcp_init_transfer() will not re-initialize the CC module. This is an approach that has the following beneficial properties: (1) This allows CC module customizations made by the EBPF called in tcp_init_transfer() to persist, and not be wiped out by a later call to tcp_init_congestion_control() in tcp_init_transfer(). (2) Does not flip the order of EBPF and CC init, to avoid causing bugs for existing code upstream that depends on the current order. (3) Does not cause 2 initializations for for CC in the case where the EBPF called in tcp_init_transfer() wants to set the CC to a new CC algorithm. (4) Allows follow-on simplifications to the code in net/core/filter.c and net/ipv4/tcp_cong.c, which currently both have some complexity to special-case CC initialization to avoid double CC initialization if EBPF sets the CC. Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Acked-by: Yuchung Cheng Acked-by: Kevin Yang Cc: Lawrence Brakmo --- include/net/inet_connection_sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c738abeb3265..dc763ca9413c 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -96,7 +96,8 @@ struct inet_connection_sock { void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); - __u8 icsk_ca_state:6, + __u8 icsk_ca_state:5, + icsk_ca_initialized:1, icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; -- cgit v1.2.3 From 29a949325c6c90f1431db9af64592275c83d9b2a Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Thu, 10 Sep 2020 15:35:34 -0400 Subject: tcp: simplify tcp_set_congestion_control(): Always reinitialize Now that the previous patches ensure that all call sites for tcp_set_congestion_control() want to initialize congestion control, we can simplify tcp_set_congestion_control() by removing the reinit argument and the code to support it. Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Acked-by: Yuchung Cheng Acked-by: Kevin Yang Cc: Lawrence Brakmo --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index e85d564446c6..f857146c17a5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1104,7 +1104,7 @@ void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, - bool reinit, bool cap_net_admin); + bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); -- cgit v1.2.3 From e33d2a7b3041d7f8cd1f0a2a4ca42a5bc112b14e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 31 Aug 2020 18:16:45 +0300 Subject: SUNRPC: remove RC4-HMAC-MD5 support from KerberosV The RC4-HMAC-MD5 KerberosV algorithm is based on RFC 4757 [0], which was specifically issued for interoperability with Windows 2000, but was never intended to receive the same level of support. The RFC says The IETF Kerberos community supports publishing this specification as an informational document in order to describe this widely implemented technology. However, while these encryption types provide the operations necessary to implement the base Kerberos specification [RFC4120], they do not provide all the required operations in the Kerberos cryptography framework [RFC3961]. As a result, it is not generally possible to implement potential extensions to Kerberos using these encryption types. The Kerberos encryption type negotiation mechanism [RFC4537] provides one approach for using such extensions even when a Kerberos infrastructure uses long-term RC4 keys. Because this specification does not implement operations required by RFC 3961 and because of security concerns with the use of RC4 and MD4 discussed in Section 8, this specification is not appropriate for publication on the standards track. The RC4-HMAC encryption types are used to ease upgrade of existing Windows NT environments, provide strong cryptography (128-bit key lengths), and provide exportable (meet United States government export restriction requirements) encryption. This document describes the implementation of those encryption types. Furthermore, this RFC was re-classified as 'historic' by RFC 8429 [1] in 2018, stating that 'none of the encryption types it specifies should be used' Note that other outdated algorithms are left in place (some of which are guarded by CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES), so this should only adversely affect interoperability with Windows NT/2000 systems that have not received any updates since 2008 (but are connected to a network nonetheless) [0] https://tools.ietf.org/html/rfc4757 [1] https://tools.ietf.org/html/rfc8429 Signed-off-by: Ard Biesheuvel Acked-by: J. Bruce Fields Signed-off-by: Herbert Xu --- include/linux/sunrpc/gss_krb5.h | 11 ----------- include/linux/sunrpc/gss_krb5_enctypes.h | 9 +++------ 2 files changed, 3 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index e8f8ffe7448b..91f43d86879d 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -141,14 +141,12 @@ enum sgn_alg { SGN_ALG_MD2_5 = 0x0001, SGN_ALG_DES_MAC = 0x0002, SGN_ALG_3 = 0x0003, /* not published */ - SGN_ALG_HMAC_MD5 = 0x0011, /* microsoft w2k; no support */ SGN_ALG_HMAC_SHA1_DES3_KD = 0x0004 }; enum seal_alg { SEAL_ALG_NONE = 0xffff, SEAL_ALG_DES = 0x0000, SEAL_ALG_1 = 0x0001, /* not published */ - SEAL_ALG_MICROSOFT_RC4 = 0x0010,/* microsoft w2k; no support */ SEAL_ALG_DES3KD = 0x0002 }; @@ -316,14 +314,5 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *plainoffset, u32 *plainlen); -int -krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, - struct crypto_sync_skcipher *cipher, - unsigned char *cksum); - -int -krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, - struct crypto_sync_skcipher *cipher, - s32 seqnum); void gss_krb5_make_confounder(char *p, u32 conflen); diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h index 981c89cef19d..87eea679d750 100644 --- a/include/linux/sunrpc/gss_krb5_enctypes.h +++ b/include/linux/sunrpc/gss_krb5_enctypes.h @@ -13,15 +13,13 @@ #ifdef CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES /* - * NB: This list includes encryption types that were deprecated - * by RFC 8429 (DES3_CBC_SHA1 and ARCFOUR_HMAC). + * NB: This list includes DES3_CBC_SHA1, which was deprecated by RFC 8429. * * ENCTYPE_AES256_CTS_HMAC_SHA1_96 * ENCTYPE_AES128_CTS_HMAC_SHA1_96 * ENCTYPE_DES3_CBC_SHA1 - * ENCTYPE_ARCFOUR_HMAC */ -#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23" +#define KRB5_SUPPORTED_ENCTYPES "18,17,16" #else /* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */ @@ -32,12 +30,11 @@ * ENCTYPE_AES256_CTS_HMAC_SHA1_96 * ENCTYPE_AES128_CTS_HMAC_SHA1_96 * ENCTYPE_DES3_CBC_SHA1 - * ENCTYPE_ARCFOUR_HMAC * ENCTYPE_DES_CBC_MD5 * ENCTYPE_DES_CBC_CRC * ENCTYPE_DES_CBC_MD4 */ -#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2" +#define KRB5_SUPPORTED_ENCTYPES "18,17,16,3,1,2" #endif /* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */ -- cgit v1.2.3 From 5f254dd440fbad0c00632f9ac7645f07d8df9229 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 1 Sep 2020 21:49:11 +1000 Subject: crypto: cbc - Remove cbc.h Now that crypto/cbc.h is only used by the generic cbc template, we can merge it back into the CBC code. Signed-off-by: Herbert Xu --- include/crypto/cbc.h | 141 --------------------------------------------------- 1 file changed, 141 deletions(-) delete mode 100644 include/crypto/cbc.h (limited to 'include') diff --git a/include/crypto/cbc.h b/include/crypto/cbc.h deleted file mode 100644 index 2b6422db42e2..000000000000 --- a/include/crypto/cbc.h +++ /dev/null @@ -1,141 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * CBC: Cipher Block Chaining mode - * - * Copyright (c) 2016 Herbert Xu - */ - -#ifndef _CRYPTO_CBC_H -#define _CRYPTO_CBC_H - -#include -#include -#include - -static inline int crypto_cbc_encrypt_segment( - struct skcipher_walk *walk, struct crypto_skcipher *tfm, - void (*fn)(struct crypto_skcipher *, const u8 *, u8 *)) -{ - unsigned int bsize = crypto_skcipher_blocksize(tfm); - unsigned int nbytes = walk->nbytes; - u8 *src = walk->src.virt.addr; - u8 *dst = walk->dst.virt.addr; - u8 *iv = walk->iv; - - do { - crypto_xor(iv, src, bsize); - fn(tfm, iv, dst); - memcpy(iv, dst, bsize); - - src += bsize; - dst += bsize; - } while ((nbytes -= bsize) >= bsize); - - return nbytes; -} - -static inline int crypto_cbc_encrypt_inplace( - struct skcipher_walk *walk, struct crypto_skcipher *tfm, - void (*fn)(struct crypto_skcipher *, const u8 *, u8 *)) -{ - unsigned int bsize = crypto_skcipher_blocksize(tfm); - unsigned int nbytes = walk->nbytes; - u8 *src = walk->src.virt.addr; - u8 *iv = walk->iv; - - do { - crypto_xor(src, iv, bsize); - fn(tfm, src, src); - iv = src; - - src += bsize; - } while ((nbytes -= bsize) >= bsize); - - memcpy(walk->iv, iv, bsize); - - return nbytes; -} - -static inline int crypto_cbc_encrypt_walk(struct skcipher_request *req, - void (*fn)(struct crypto_skcipher *, - const u8 *, u8 *)) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct skcipher_walk walk; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while (walk.nbytes) { - if (walk.src.virt.addr == walk.dst.virt.addr) - err = crypto_cbc_encrypt_inplace(&walk, tfm, fn); - else - err = crypto_cbc_encrypt_segment(&walk, tfm, fn); - err = skcipher_walk_done(&walk, err); - } - - return err; -} - -static inline int crypto_cbc_decrypt_segment( - struct skcipher_walk *walk, struct crypto_skcipher *tfm, - void (*fn)(struct crypto_skcipher *, const u8 *, u8 *)) -{ - unsigned int bsize = crypto_skcipher_blocksize(tfm); - unsigned int nbytes = walk->nbytes; - u8 *src = walk->src.virt.addr; - u8 *dst = walk->dst.virt.addr; - u8 *iv = walk->iv; - - do { - fn(tfm, src, dst); - crypto_xor(dst, iv, bsize); - iv = src; - - src += bsize; - dst += bsize; - } while ((nbytes -= bsize) >= bsize); - - memcpy(walk->iv, iv, bsize); - - return nbytes; -} - -static inline int crypto_cbc_decrypt_inplace( - struct skcipher_walk *walk, struct crypto_skcipher *tfm, - void (*fn)(struct crypto_skcipher *, const u8 *, u8 *)) -{ - unsigned int bsize = crypto_skcipher_blocksize(tfm); - unsigned int nbytes = walk->nbytes; - u8 *src = walk->src.virt.addr; - u8 last_iv[MAX_CIPHER_BLOCKSIZE]; - - /* Start of the last block. */ - src += nbytes - (nbytes & (bsize - 1)) - bsize; - memcpy(last_iv, src, bsize); - - for (;;) { - fn(tfm, src, src); - if ((nbytes -= bsize) < bsize) - break; - crypto_xor(src, src - bsize, bsize); - src -= bsize; - } - - crypto_xor(src, walk->iv, bsize); - memcpy(walk->iv, last_iv, bsize); - - return nbytes; -} - -static inline int crypto_cbc_decrypt_blocks( - struct skcipher_walk *walk, struct crypto_skcipher *tfm, - void (*fn)(struct crypto_skcipher *, const u8 *, u8 *)) -{ - if (walk->src.virt.addr == walk->dst.virt.addr) - return crypto_cbc_decrypt_inplace(walk, tfm, fn); - else - return crypto_cbc_decrypt_segment(walk, tfm, fn); -} - -#endif /* _CRYPTO_CBC_H */ -- cgit v1.2.3 From 6d0fd536183034953bf84826fecb37e47779d24b Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Fri, 28 Aug 2020 10:20:31 -0700 Subject: include: pe.h: Add RISC-V related PE definition Define RISC-V related machine types. Signed-off-by: Atish Patra Reviewed-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20200415195422.19866-3-atish.patra@wdc.com Signed-off-by: Ard Biesheuvel --- include/linux/pe.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/pe.h b/include/linux/pe.h index 8ad71d763a77..daf09ffffe38 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -55,6 +55,9 @@ #define IMAGE_FILE_MACHINE_POWERPC 0x01f0 #define IMAGE_FILE_MACHINE_POWERPCFP 0x01f1 #define IMAGE_FILE_MACHINE_R4000 0x0166 +#define IMAGE_FILE_MACHINE_RISCV32 0x5032 +#define IMAGE_FILE_MACHINE_RISCV64 0x5064 +#define IMAGE_FILE_MACHINE_RISCV128 0x5128 #define IMAGE_FILE_MACHINE_SH3 0x01a2 #define IMAGE_FILE_MACHINE_SH3DSP 0x01a3 #define IMAGE_FILE_MACHINE_SH3E 0x01a4 -- cgit v1.2.3 From abdaf11ac18925ce8cc229e62e35b342d548ece2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 17 Aug 2020 16:41:50 +0200 Subject: dma-mapping: add (back) arch_dma_mark_clean for ia64 Add back a hook to optimize dcache flushing after reading executable code using DMA. This gets ia64 out of the business of pretending to be dma incoherent just for this optimization. Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 3 +++ include/linux/dma-noncoherent.h | 8 ++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 6e87225600ae..95e3e28bd93f 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -150,6 +150,9 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev, if (unlikely(is_swiotlb_buffer(paddr))) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); + + if (dir == DMA_FROM_DEVICE) + arch_dma_mark_clean(paddr, size); } static inline dma_addr_t dma_direct_map_page(struct device *dev, diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index ca09a4e07d2d..b9bc6c557ea4 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -108,6 +108,14 @@ static inline void arch_dma_prep_coherent(struct page *page, size_t size) } #endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */ +#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN +void arch_dma_mark_clean(phys_addr_t paddr, size_t size); +#else +static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size) +{ +} +#endif /* ARCH_HAS_DMA_MARK_CLEAN */ + void *arch_dma_set_uncached(void *addr, size_t size); void arch_dma_clear_uncached(void *addr, size_t size); -- cgit v1.2.3 From 2f5388a29be82a62529d146499e70987e856f6f7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 17 Aug 2020 17:06:40 +0200 Subject: dma-direct: remove dma_direct_{alloc,free}_pages Just merge these helpers into the main dma_direct_{alloc,free} routines, as the additional checks are always false for the two callers. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-direct.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 95e3e28bd93f..20eceb2e4f91 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -77,10 +77,6 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); -void *dma_direct_alloc_pages(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); -void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_addr, unsigned long attrs); int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); -- cgit v1.2.3 From 7bc5c428a660d4d1bc95ba54bf4cb6bccf8c3029 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 17:56:22 +0200 Subject: dma-direct: remove __dma_to_phys There is no harm in just always clearing the SME encryption bit, while significantly simplifying the interface. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-direct.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 20eceb2e4f91..f00e262ab6b1 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -24,11 +24,12 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); } -static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr) +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) { - phys_addr_t paddr = (phys_addr_t)dev_addr; + phys_addr_t paddr = (phys_addr_t)dev_addr + + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); - return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); + return __sme_clr(paddr); } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ @@ -44,7 +45,7 @@ static inline bool force_dma_unencrypted(struct device *dev) /* * If memory encryption is supported, phys_to_dma will set the memory encryption * bit in the DMA address, and dma_to_phys will clear it. The raw __phys_to_dma - * and __dma_to_phys versions should only be used on non-encrypted memory for + * version should only be used on non-encrypted memory for * special occasions like DMA coherent buffers. */ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) @@ -52,11 +53,6 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) return __sme_set(__phys_to_dma(dev, paddr)); } -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) -{ - return __sme_clr(__dma_to_phys(dev, daddr)); -} - static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, bool is_ram) { -- cgit v1.2.3 From 5ceda74093a5c1c3f42a02b894df031f3bbc9af1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 17 Aug 2020 17:34:03 +0200 Subject: dma-direct: rename and cleanup __phys_to_dma The __phys_to_dma vs phys_to_dma distinction isn't exactly obvious. Try to improve the situation by renaming __phys_to_dma to phys_to_dma_unencryped, and not forcing architectures that want to override phys_to_dma to actually provide __phys_to_dma. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-direct.h | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index f00e262ab6b1..805010ea5346 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -16,14 +16,29 @@ extern unsigned int zone_dma_bits; #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include +#ifndef phys_to_dma_unencrypted +#define phys_to_dma_unencrypted phys_to_dma +#endif #else -static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev, + phys_addr_t paddr) { dma_addr_t dev_addr = (dma_addr_t)paddr; return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); } +/* + * If memory encryption is supported, phys_to_dma will set the memory encryption + * bit in the DMA address, and dma_to_phys will clear it. + * phys_to_dma_unencrypted is for use on special unencrypted memory like swiotlb + * buffers. + */ +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + return __sme_set(phys_to_dma_unencrypted(dev, paddr)); +} + static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) { phys_addr_t paddr = (phys_addr_t)dev_addr + @@ -42,17 +57,6 @@ static inline bool force_dma_unencrypted(struct device *dev) } #endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */ -/* - * If memory encryption is supported, phys_to_dma will set the memory encryption - * bit in the DMA address, and dma_to_phys will clear it. The raw __phys_to_dma - * version should only be used on non-encrypted memory for - * special occasions like DMA coherent buffers. - */ -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - return __sme_set(__phys_to_dma(dev, paddr)); -} - static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, bool is_ram) { -- cgit v1.2.3 From d5ea32da878d4572761ca4580631748e398542de Mon Sep 17 00:00:00 2001 From: Daniel Winkler Date: Tue, 25 Aug 2020 16:31:51 -0700 Subject: Bluetooth: Add MGMT capability flags for tx power and ext advertising For new advertising features, it will be important for userspace to know the capabilities of the controller and kernel. If the controller and kernel support extended advertising, we include flags indicating hardware offloading support and support for setting tx power of adv instances. In the future, vendor-specific commands may allow the setting of tx power in advertising instances, but for now this feature is only marked available if extended advertising is supported. This change is manually verified in userspace by ensuring the advertising manager's supported_flags field is updated with new flags on hatch chromebook (ext advertising supported). Signed-off-by: Daniel Winkler Signed-off-by: Marcel Holtmann --- include/net/bluetooth/mgmt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index beae5c3980f0..9ad505b9e694 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -572,6 +572,8 @@ struct mgmt_rp_add_advertising { #define MGMT_ADV_FLAG_SEC_1M BIT(7) #define MGMT_ADV_FLAG_SEC_2M BIT(8) #define MGMT_ADV_FLAG_SEC_CODED BIT(9) +#define MGMT_ADV_FLAG_CAN_SET_TX_POWER BIT(10) +#define MGMT_ADV_FLAG_HW_OFFLOAD BIT(11) #define MGMT_ADV_FLAG_SEC_MASK (MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \ MGMT_ADV_FLAG_SEC_CODED) -- cgit v1.2.3 From 7053e0eab473119503f6565b4e398f9a73122481 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 7 Sep 2020 16:14:52 +0200 Subject: drm/vram-helper: stop using TTM placement flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Those are going to be removed, stop using them here. Instead define separate flags for the helper. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/389823/?series=81551&rev=1 --- include/drm/drm_gem_vram_helper.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h index 035332f3723f..a5e477bf96cc 100644 --- a/include/drm/drm_gem_vram_helper.h +++ b/include/drm/drm_gem_vram_helper.h @@ -9,7 +9,6 @@ #include #include #include -#include #include /* for container_of() */ @@ -20,9 +19,9 @@ struct drm_simple_display_pipe; struct filp; struct vm_area_struct; -#define DRM_GEM_VRAM_PL_FLAG_VRAM TTM_PL_FLAG_VRAM -#define DRM_GEM_VRAM_PL_FLAG_SYSTEM TTM_PL_FLAG_SYSTEM -#define DRM_GEM_VRAM_PL_FLAG_TOPDOWN TTM_PL_FLAG_TOPDOWN +#define DRM_GEM_VRAM_PL_FLAG_SYSTEM (1 << 0) +#define DRM_GEM_VRAM_PL_FLAG_VRAM (1 << 1) +#define DRM_GEM_VRAM_PL_FLAG_TOPDOWN (1 << 2) /* * Buffer-object helpers -- cgit v1.2.3 From 48e07c23cbeba2a2cda7ca73be0015e727818536 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 10 Sep 2020 13:39:41 +0200 Subject: drm/ttm: nuke memory type flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's not supported to specify more than one of those flags. So it never made sense to make this a flag in the first place. Nuke the flags and specify directly which memory type to use. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/389826/?series=81551&rev=1 --- include/drm/ttm/ttm_bo_driver.h | 17 ----------------- include/drm/ttm/ttm_placement.h | 9 +-------- 2 files changed, 1 insertion(+), 25 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 32c0651cc0fd..303a89d1066d 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -393,23 +393,6 @@ struct ttm_lru_bulk_move { struct ttm_lru_bulk_move_pos swap[TTM_MAX_BO_PRIORITY]; }; -/** - * ttm_flag_masked - * - * @old: Pointer to the result and original value. - * @new: New value of bits. - * @mask: Mask of bits to change. - * - * Convenience function to change a number of bits identified by a mask. - */ - -static inline uint32_t -ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask) -{ - *old ^= (*old ^ new) & mask; - return *old; -} - /* * ttm_bo.c */ diff --git a/include/drm/ttm/ttm_placement.h b/include/drm/ttm/ttm_placement.h index e88a8e39767b..d4022655eae4 100644 --- a/include/drm/ttm/ttm_placement.h +++ b/include/drm/ttm/ttm_placement.h @@ -42,12 +42,6 @@ #define TTM_PL_VRAM 2 #define TTM_PL_PRIV 3 -#define TTM_PL_FLAG_SYSTEM (1 << TTM_PL_SYSTEM) -#define TTM_PL_FLAG_TT (1 << TTM_PL_TT) -#define TTM_PL_FLAG_VRAM (1 << TTM_PL_VRAM) -#define TTM_PL_FLAG_PRIV (1 << TTM_PL_PRIV) -#define TTM_PL_MASK_MEM 0x0000FFFF - /* * Other flags that affects data placement. * TTM_PL_FLAG_CACHED indicates cache-coherent mappings @@ -71,8 +65,6 @@ TTM_PL_FLAG_UNCACHED | \ TTM_PL_FLAG_WC) -#define TTM_PL_MASK_MEMTYPE (TTM_PL_MASK_MEM | TTM_PL_MASK_CACHING) - /** * struct ttm_place * @@ -85,6 +77,7 @@ struct ttm_place { unsigned fpfn; unsigned lpfn; + uint32_t mem_type; uint32_t flags; }; -- cgit v1.2.3 From a328ca7e4af347e47742f36933df0fdac1c24ea5 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Fri, 4 Sep 2020 14:55:31 +0200 Subject: drm/bridge: dw-mipi-dsi: permit configuring the escape clock rate The Amlogic D-PHY in the Amlogic AXG SoC Family does support a frequency higher than 10MHz for the TX Escape Clock, thus make the target rate configurable. Signed-off-by: Neil Armstrong Reviewed-by: Philippe Cornu Link: https://patchwork.freedesktop.org/patch/msgid/20200904125531.15248-1-narmstrong@baylibre.com --- include/drm/bridge/dw_mipi_dsi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/bridge/dw_mipi_dsi.h b/include/drm/bridge/dw_mipi_dsi.h index b0e390b3288e..bda8aa7c2280 100644 --- a/include/drm/bridge/dw_mipi_dsi.h +++ b/include/drm/bridge/dw_mipi_dsi.h @@ -36,6 +36,7 @@ struct dw_mipi_dsi_phy_ops { unsigned int *lane_mbps); int (*get_timing)(void *priv_data, unsigned int lane_mbps, struct dw_mipi_dsi_dphy_timing *timing); + int (*get_esc_clk_rate)(void *priv_data, unsigned int *esc_clk_rate); }; struct dw_mipi_dsi_host_ops { -- cgit v1.2.3 From a665aca89a411115e35ea937c2d3fb2ee4f5a701 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 4 Sep 2020 19:41:47 -0300 Subject: RDMA/umem: Split ib_umem_num_pages() into ib_umem_num_dma_blocks() ib_umem_num_pages() should only be used by things working with the SGL in CPU pages directly. Drivers building DMA lists should use the new ib_num_dma_blocks() which returns the number of blocks rdma_umem_for_each_block() will return. To make this general for DMA drivers requires a different implementation. Computing DMA block count based on umem->address only works if the requested page size is < PAGE_SIZE and/or the IOVA == umem->address. Instead the number of DMA pages should be computed in the IOVA address space, not umem->address. Thus the IOVA has to be stored inside the umem so it can be used for these calculations. For now set it to umem->address by default and fix it up if ib_umem_find_best_pgsz() was called. This allows drivers to be converted to ib_umem_num_dma_blocks() safely. Link: https://lore.kernel.org/r/6-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Signed-off-by: Jason Gunthorpe --- include/rdma/ib_umem.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index b880512ba95f..cf001d4e0a4f 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -17,6 +17,7 @@ struct ib_umem_odp; struct ib_umem { struct ib_device *ibdev; struct mm_struct *owning_mm; + u64 iova; size_t length; unsigned long address; u32 writable : 1; @@ -33,11 +34,17 @@ static inline int ib_umem_offset(struct ib_umem *umem) return umem->address & ~PAGE_MASK; } +static inline size_t ib_umem_num_dma_blocks(struct ib_umem *umem, + unsigned long pgsz) +{ + return (size_t)((ALIGN(umem->iova + umem->length, pgsz) - + ALIGN_DOWN(umem->iova, pgsz))) / + pgsz; +} + static inline size_t ib_umem_num_pages(struct ib_umem *umem) { - return (ALIGN(umem->address + umem->length, PAGE_SIZE) - - ALIGN_DOWN(umem->address, PAGE_SIZE)) >> - PAGE_SHIFT; + return ib_umem_num_dma_blocks(umem, PAGE_SIZE); } static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, @@ -55,6 +62,8 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, * pgsz must be <= PAGE_SIZE or computed by ib_umem_find_best_pgsz(). The * returned DMA blocks will be aligned to pgsz and span the range: * ALIGN_DOWN(umem->address, pgsz) to ALIGN(umem->address + umem->length, pgsz) + * + * Performs exactly ib_umem_num_dma_blocks() iterations. */ #define rdma_umem_for_each_dma_block(umem, biter, pgsz) \ for (__rdma_umem_block_iter_start(biter, umem, pgsz); \ -- cgit v1.2.3 From 81655d3c4a95f05495f3213acbbc5423fc4dbdfb Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 4 Sep 2020 19:41:56 -0300 Subject: RDMA/mlx4: Use ib_umem_num_dma_blocks() For the calls linked to mlx4_ib_umem_calc_optimal_mtt_size() use ib_umem_num_dma_blocks() inside the function, it is just some weird static default. All other places are just using it with PAGE_SIZE, switch to ib_umem_num_dma_blocks(). As this is the last call site, remove ib_umem_num_count(). Link: https://lore.kernel.org/r/15-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Signed-off-by: Jason Gunthorpe --- include/rdma/ib_umem.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index cf001d4e0a4f..70597508c765 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -74,7 +74,6 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, size_t size, int access); void ib_umem_release(struct ib_umem *umem); -int ib_umem_page_count(struct ib_umem *umem); int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, size_t length); unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, @@ -92,7 +91,6 @@ static inline struct ib_umem *ib_umem_get(struct ib_device *device, return ERR_PTR(-EINVAL); } static inline void ib_umem_release(struct ib_umem *umem) { } -static inline int ib_umem_page_count(struct ib_umem *umem) { return 0; } static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, size_t length) { return -EINVAL; -- cgit v1.2.3 From b3003a74456f0c1f614a46c07e16abe33bfdd087 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 4 Sep 2020 19:41:57 -0300 Subject: RDMA/qedr: Remove fbo and zbva from the MR MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit zbva is always false, so fbo is never read. A 'zero-based-virtual-address' is simply IOVA == 0, and the driver already supports this. Link: https://lore.kernel.org/r/16-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Acked-by: Michal Kalderon  Signed-off-by: Jason Gunthorpe --- include/linux/qed/qed_rdma_if.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index f464d85e88a4..aeb242cefebf 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -242,10 +242,8 @@ struct qed_rdma_register_tid_in_params { bool pbl_two_level; u8 pbl_page_size_log; u8 page_size_log; - u32 fbo; u64 length; u64 vaddr; - bool zbva; bool phy_mr; bool dma_mr; -- cgit v1.2.3 From b60b9c0274007fe68439cd9cefdabbd7fb8a2ce6 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Thu, 3 Sep 2020 17:40:34 -0500 Subject: RDMA/core: Added missing WR and WC opcodes Add work completion opcodes to a new ib_uverbs_wc_opcode enum in ib_user_verbs.h. This plays the same role as ib_uverbs_wr_opcode documenting the opcodes in the user space API. Assigned the IB_WC_XXX opcodes in ib_verbs.h to the IB_UVERBS_WC_XXX where they are defined. This follows the same pattern as the IB_WR_XXX opcodes. This fixes an incorrect value for LSO that had crept in but is not currently being used. Added a missing IB_WR_BIND_MW opcode in ib_verbs.h. Link: https://lore.kernel.org/r/20200903224039.437391-2-rpearson@hpe.com Signed-off-by: Bob Pearson Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 16 +++++++++------- include/uapi/rdma/ib_user_verbs.h | 11 +++++++++++ 2 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 97658d706aa1..5ae1d9849881 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -952,13 +952,14 @@ enum ib_wc_status { const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status); enum ib_wc_opcode { - IB_WC_SEND, - IB_WC_RDMA_WRITE, - IB_WC_RDMA_READ, - IB_WC_COMP_SWAP, - IB_WC_FETCH_ADD, - IB_WC_LSO, - IB_WC_LOCAL_INV, + IB_WC_SEND = IB_UVERBS_WC_SEND, + IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE, + IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ, + IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP, + IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD, + IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW, + IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV, + IB_WC_LSO = IB_UVERBS_WC_TSO, IB_WC_REG_MR, IB_WC_MASKED_COMP_SWAP, IB_WC_MASKED_FETCH_ADD, @@ -1291,6 +1292,7 @@ enum ib_wr_opcode { IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, + IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW, IB_WR_LSO = IB_UVERBS_WR_TSO, IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 0474c7400268..456438c18c2c 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -457,6 +457,17 @@ struct ib_uverbs_poll_cq { __u32 ne; }; +enum ib_uverbs_wc_opcode { + IB_UVERBS_WC_SEND = 0, + IB_UVERBS_WC_RDMA_WRITE = 1, + IB_UVERBS_WC_RDMA_READ = 2, + IB_UVERBS_WC_COMP_SWAP = 3, + IB_UVERBS_WC_FETCH_ADD = 4, + IB_UVERBS_WC_BIND_MW = 5, + IB_UVERBS_WC_LOCAL_INV = 6, + IB_UVERBS_WC_TSO = 7, +}; + struct ib_uverbs_wc { __aligned_u64 wr_id; __u32 status; -- cgit v1.2.3 From 97fb3e33474897c35b7cfe6ff0e16a3e172d9249 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Wed, 2 Sep 2020 19:57:38 +0300 Subject: qede: Notify qedr when mtu has changed MTU change on ethtool is currently not supported for iWARP. Notify qedr driver so that appropriate logging can take place. Link: https://lore.kernel.org/r/20200902165741.8355-6-michal.kalderon@marvell.com Signed-off-by: Michal Kalderon Signed-off-by: Jason Gunthorpe --- include/linux/qed/qede_rdma.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 072da2f6da37..0d5564a59a59 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -20,7 +20,8 @@ enum qede_rdma_event { QEDE_UP, QEDE_DOWN, QEDE_CHANGE_ADDR, - QEDE_CLOSE + QEDE_CLOSE, + QEDE_CHANGE_MTU, }; struct qede_rdma_event_work { @@ -54,6 +55,7 @@ void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); void qede_rdma_dev_remove(struct qede_dev *dev, bool recovery); void qede_rdma_event_changeaddr(struct qede_dev *edr); +void qede_rdma_event_change_mtu(struct qede_dev *edev); #else static inline int qede_rdma_dev_add(struct qede_dev *dev, -- cgit v1.2.3 From 6915564dc5a8ab831a016e0cd0a8a3c68230287b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 11 Sep 2020 14:59:35 +0200 Subject: ACPI: OSL: Change the type of acpi_os_map_generic_address() return value Modify acpi_os_map_generic_address() to return the pointer returned by acpi_os_map_iomem() which represents the logical address corresponding to the struct acpi_generic_address argument passed to it or NULL if that address cannot be obtained (for example, the argument does not represent an address in system memory or it could not be mapped by the OS). Among other things, that will allow the ACPI OS layer to pass the logical addresses of the FADT GPE blocks 0 and 1 to ACPICA going forward. Signed-off-by: Rafael J. Wysocki --- include/acpi/acpi_io.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h index 12d8bd333fe7..027faa8883aa 100644 --- a/include/acpi/acpi_io.h +++ b/include/acpi/acpi_io.h @@ -21,7 +21,7 @@ void __iomem __ref void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size); void __iomem *acpi_os_get_iomem(acpi_physical_address phys, unsigned int size); -int acpi_os_map_generic_address(struct acpi_generic_address *addr); +void __iomem *acpi_os_map_generic_address(struct acpi_generic_address *addr); void acpi_os_unmap_generic_address(struct acpi_generic_address *addr); #endif -- cgit v1.2.3 From 85f94020033f931a5918ab26281b2afbe4d68b73 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 11 Sep 2020 14:59:42 +0200 Subject: ACPI: OSL: Make ACPICA use logical addresses of GPE blocks Define ACPI_GPE_USE_LOGICAL_ADDRESSES in aclinux.h and modify acpi_os_initialize() to store the logical addresses of the FADT GPE blocks 0 and 1 in acpi_gbl_xgpe0_block_logical_address and acpi_gbl_xgpe1_block_logical_address, respectively, so as to allow ACPICA to use them for accessing GPE registers in system memory, instead of using their physical addresses and looking up the corresponding logical addresses on every access attempt, which is inefficient. Signed-off-by: Rafael J. Wysocki --- include/acpi/platform/aclinux.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 987e2af7c335..4151c76141fa 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -118,6 +118,10 @@ #define USE_NATIVE_ALLOCATE_ZEROED +/* Use logical addresses for accessing GPE registers in system memory */ + +#define ACPI_GPE_USE_LOGICAL_ADDRESSES + /* * Overrides for in-kernel ACPICA */ -- cgit v1.2.3 From 78ff97ebd4e9d02a99ca894b643c78c8fda7df5d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 9 Sep 2020 16:10:57 +0200 Subject: iio: iio.h: fix a warning at the kernel-doc markup There's a warning at iio.h kernel-doc markup: ./include/linux/iio/iio.h:644: WARNING: Unknown target name: "devm". Because it is using {devm_}foo notation. Well, this is not a valid kernel-doc notation. Also, it prevents creating hyperlinks to other documentation functions. So, replace it to a better notation. Signed-off-by: Mauro Carvalho Chehab Acked-by: Jonathan Cameron Link: https://lore.kernel.org/r/d8f2275c438c459ede4e6fba03ce719cc6ad898b.1599660067.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e2df67a3b9ab..f1daaba9e706 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -641,7 +641,7 @@ static inline struct iio_dev *iio_device_get(struct iio_dev *indio_dev) * * This utility must be called between IIO device allocation * (via devm_iio_device_alloc()) & IIO device registration - * (via {devm_}iio_device_register()). + * (via iio_device_register() and devm_iio_device_register())). * By default, the device allocation will also assign a parent device to * the IIO device object. In cases where devm_iio_device_alloc() is used, * sometimes the parent device must be different than the device used to -- cgit v1.2.3 From 15e9e35cd1dec2bc138464de6bf8ef828df19235 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 10 Sep 2020 18:33:51 +0800 Subject: KVM: MIPS: Change the definition of kvm type MIPS defines two kvm types: #define KVM_VM_MIPS_TE 0 #define KVM_VM_MIPS_VZ 1 In Documentation/virt/kvm/api.rst it is said that "You probably want to use 0 as machine type", which implies that type 0 be the "automatic" or "default" type. And, in user-space libvirt use the null-machine (with type 0) to detect the kvm capability, which returns "KVM not supported" on a VZ platform. I try to fix it in QEMU but it is ugly: https://lists.nongnu.org/archive/html/qemu-devel/2020-08/msg05629.html And Thomas Huth suggests me to change the definition of kvm type: https://lists.nongnu.org/archive/html/qemu-devel/2020-09/msg03281.html So I define like this: #define KVM_VM_MIPS_AUTO 0 #define KVM_VM_MIPS_VZ 1 #define KVM_VM_MIPS_TE 2 Since VZ and TE cannot co-exists, using type 0 on a TE platform will still return success (so old user-space tools have no problems on new kernels); the advantage is that using type 0 on a VZ platform will not return failure. So, the only problem is "new user-space tools use type 2 on old kernels", but if we treat this as a kernel bug, we can backport this patch to old stable kernels. Signed-off-by: Huacai Chen Message-Id: <1599734031-28746-1-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 3d8023474f2a..7d8eced6f459 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt { #define KVM_VM_PPC_HV 1 #define KVM_VM_PPC_PR 2 -/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */ -#define KVM_VM_MIPS_TE 0 +/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */ +#define KVM_VM_MIPS_AUTO 0 #define KVM_VM_MIPS_VZ 1 +#define KVM_VM_MIPS_TE 2 #define KVM_S390_SIE_PAGE_OFFSET 1 -- cgit v1.2.3 From 093749e296e29a4b0162eb925a6701a01e8c9a98 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 4 Aug 2020 21:14:49 +0800 Subject: f2fs: support age threshold based garbage collection There are several issues in current background GC algorithm: - valid blocks is one of key factors during cost overhead calculation, so if segment has less valid block, however even its age is young or it locates hot segment, CB algorithm will still choose the segment as victim, it's not appropriate. - GCed data/node will go to existing logs, no matter in-there datas' update frequency is the same or not, it may mix hot and cold data again. - GC alloctor mainly use LFS type segment, it will cost free segment more quickly. This patch introduces a new algorithm named age threshold based garbage collection to solve above issues, there are three steps mainly: 1. select a source victim: - set an age threshold, and select candidates beased threshold: e.g. 0 means youngest, 100 means oldest, if we set age threshold to 80 then select dirty segments which has age in range of [80, 100] as candiddates; - set candidate_ratio threshold, and select candidates based the ratio, so that we can shrink candidates to those oldest segments; - select target segment with fewest valid blocks in order to migrate blocks with minimum cost; 2. select a target victim: - select candidates beased age threshold; - set candidate_radius threshold, search candidates whose age is around source victims, searching radius should less than the radius threshold. - select target segment with most valid blocks in order to avoid migrating current target segment. 3. merge valid blocks from source victim into target victim with SSR alloctor. Test steps: - create 160 dirty segments: * half of them have 128 valid blocks per segment * left of them have 384 valid blocks per segment - run background GC Benefit: GC count and block movement count both decrease obviously: - Before: - Valid: 86 - Dirty: 1 - Prefree: 11 - Free: 6001 (6001) GC calls: 162 (BG: 220) - data segments : 160 (160) - node segments : 2 (2) Try to move 41454 blocks (BG: 41454) - data blocks : 40960 (40960) - node blocks : 494 (494) IPU: 0 blocks SSR: 0 blocks in 0 segments LFS: 41364 blocks in 81 segments - After: - Valid: 87 - Dirty: 0 - Prefree: 4 - Free: 6008 (6008) GC calls: 75 (BG: 76) - data segments : 74 (74) - node segments : 1 (1) Try to move 12813 blocks (BG: 12813) - data blocks : 12544 (12544) - node blocks : 269 (269) IPU: 0 blocks SSR: 12032 blocks in 77 segments LFS: 855 blocks in 2 segments Signed-off-by: Chao Yu [Jaegeuk Kim: fix a bug along with pinfile in-mem segment & clean up] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 8a1c1311acac..06c73f3f6dd2 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -111,13 +111,15 @@ TRACE_DEFINE_ENUM(CP_RESIZE); #define show_alloc_mode(type) \ __print_symbolic(type, \ - { LFS, "LFS-mode" }, \ - { SSR, "SSR-mode" }) + { LFS, "LFS-mode" }, \ + { SSR, "SSR-mode" }, \ + { AT_SSR, "AT_SSR-mode" }) #define show_victim_policy(type) \ __print_symbolic(type, \ { GC_GREEDY, "Greedy" }, \ - { GC_CB, "Cost-Benefit" }) + { GC_CB, "Cost-Benefit" }, \ + { GC_AT, "Age-threshold" }) #define show_cpreason(type) \ __print_flags(type, "|", \ -- cgit v1.2.3 From 32c0fec1aa85f1a9aebfd9445208f4223bcd96e8 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 3 Sep 2020 10:15:15 +0800 Subject: f2fs: trace: fix typo Fixes a typo from 'compreesed' to 'compressed'. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 06c73f3f6dd2..f8f1e85ff130 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -136,7 +136,7 @@ TRACE_DEFINE_ENUM(CP_RESIZE); __print_symbolic(type, \ { CP_NO_NEEDED, "no needed" }, \ { CP_NON_REGULAR, "non regular" }, \ - { CP_COMPRESSED, "compreesed" }, \ + { CP_COMPRESSED, "compressed" }, \ { CP_HARDLINK, "hardlink" }, \ { CP_SB_NEED_CP, "sb needs cp" }, \ { CP_WRONG_PINO, "wrong pino" }, \ -- cgit v1.2.3 From 7b26410b05f8c262688de8a689ba8e5d0c3cff01 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 31 Aug 2020 15:27:23 -0700 Subject: block: introduce part_[begin|end]_io_acct These functions can be used to enable iostat for partitions on devices like md, bcache. Signed-off-by: Song Liu Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 37ec5a73d027..5bd96fbab9b4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1933,6 +1933,11 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); +unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, + struct bio *bio); +void part_end_io_acct(struct hd_struct *part, struct bio *bio, + unsigned long start_time); + /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for -- cgit v1.2.3 From 568a36a69bad4f2efcfa4f94c83aa150a463735c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 10 Sep 2020 19:48:54 +0300 Subject: net: dsa: tag_8021q: include missing refcount.h The previous assumption was that the caller would already have this header file included. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 311aa04e7520..804750122c66 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -5,6 +5,7 @@ #ifndef _NET_DSA_8021Q_H #define _NET_DSA_8021Q_H +#include #include struct dsa_switch; -- cgit v1.2.3 From 7e092af2f3b33694b9117ffd978d42b04ec4f260 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 10 Sep 2020 19:48:55 +0300 Subject: net: dsa: tag_8021q: setup tagging via a single function call There is no point in calling dsa_port_setup_8021q_tagging for each individual port. Additionally, it will become more difficult to do that when we'll have a context structure to tag_8021q (next patch). So refactor this now. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 804750122c66..8586d8cdf956 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -25,8 +25,7 @@ struct dsa_8021q_crosschip_link { #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) -int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, - bool enabled); +int dsa_8021q_setup(struct dsa_switch *ds, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, @@ -57,8 +56,7 @@ bool vid_is_dsa_8021q(u16 vid); #else -int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, - bool enabled) +int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) { return 0; } -- cgit v1.2.3 From 5899ee367ab3fec885aa04d9a2b573bf2e464e7f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 10 Sep 2020 19:48:56 +0300 Subject: net: dsa: tag_8021q: add a context structure While working on another tag_8021q driver implementation, some things became apparent: - It is not mandatory for a DSA driver to offload the tag_8021q VLANs by using the VLAN table per se. For example, it can add custom TCAM rules that simply encapsulate RX traffic, and redirect & decapsulate rules for TX traffic. For such a driver, it makes no sense to receive the tag_8021q configuration through the same callback as it receives the VLAN configuration from the bridge and the 8021q modules. - Currently, sja1105 (the only tag_8021q user) sets a priv->expect_dsa_8021q variable to distinguish between the bridge calling, and tag_8021q calling. That can be improved, to say the least. - The crosschip bridging operations are, in fact, stateful already. The list of crosschip_links must be kept by the caller and passed to the relevant tag_8021q functions. So it would be nice if the tag_8021q configuration was more self-contained. This patch attempts to do that. Create a struct dsa_8021q_context which encapsulates a struct dsa_switch, and has 2 function pointers for adding and deleting a VLAN. These will replace the previous channel to the driver, which was through the .port_vlan_add and .port_vlan_del callbacks of dsa_switch_ops. Also put the list of crosschip_links into this dsa_8021q_context. Drivers that don't support cross-chip bridging can simply omit to initialize this list, as long as they dont call any cross-chip function. The sja1105_vlan_add and sja1105_vlan_del functions are refactored into a smaller sja1105_vlan_add_one, which now has 2 entry points: - sja1105_vlan_add, from struct dsa_switch_ops - sja1105_dsa_8021q_vlan_add, from the tag_8021q ops But even this change is fairly trivial. It just reflects the fact that for sja1105, the VLANs from these 2 channels end up in the same hardware table. However that is not necessarily true in the general sense (and that's the reason for making this change). The rest of the patch is mostly plain refactoring of "ds" -> "ctx". The dsa_8021q_context structure needs to be propagated because adding a VLAN is now done through the ops function pointers inside of it. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 46 +++++++++++++++++++++++++++------------------- 1 file changed, 27 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 8586d8cdf956..2b003ae9fb38 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -12,30 +12,40 @@ struct dsa_switch; struct sk_buff; struct net_device; struct packet_type; +struct dsa_8021q_context; struct dsa_8021q_crosschip_link { struct list_head list; int port; - struct dsa_switch *other_ds; + struct dsa_8021q_context *other_ctx; int other_port; refcount_t refcount; }; +struct dsa_8021q_ops { + int (*vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); + int (*vlan_del)(struct dsa_switch *ds, int port, u16 vid); +}; + +struct dsa_8021q_context { + const struct dsa_8021q_ops *ops; + struct dsa_switch *ds; + struct list_head crosschip_links; +}; + #define DSA_8021Q_N_SUBVLAN 8 #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) -int dsa_8021q_setup(struct dsa_switch *ds, bool enabled); +int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links); +int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port); -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links); +int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); @@ -56,23 +66,21 @@ bool vid_is_dsa_8021q(u16 vid); #else -int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) +int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) { return 0; } -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { return 0; } -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { return 0; } -- cgit v1.2.3 From 1623ad8ec04c771a54975fb84b22bc21c2dbcac1 Mon Sep 17 00:00:00 2001 From: Divya Koppera Date: Fri, 11 Sep 2020 18:48:44 +0530 Subject: net: phy: mchp: Add support for LAN8814 QUAD PHY LAN8814 is a low-power, quad-port triple-speed (10BASE-T/100BASETX/1000BASE-T) Ethernet physical layer transceiver (PHY). It supports transmission and reception of data on standard CAT-5, as well as CAT-5e and CAT-6, unshielded twisted pair (UTP) cables. LAN8814 supports industry-standard QSGMII (Quad Serial Gigabit Media Independent Interface) and Q-USGMII (Quad Universal Serial Gigabit Media Independent Interface) providing chip-to-chip connection to four Gigabit Ethernet MACs using a single serialized link (differential pair) in each direction. The LAN8814 SKU supports high-accuracy timestamping functions to support IEEE-1588 solutions using Microchip Ethernet switches, as well as customer solutions based on SoCs and FPGAs. The LAN8804 SKU has same features as that of LAN8814 SKU except that it does not support 1588, SyncE, or Q-USGMII with PCH/MCH. This adds support for 10BASE-T, 100BASE-TX, and 1000BASE-T, QSGMII link with the MAC. Signed-off-by: Divya Koppera Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 75f880c25bb8..416ee6dd2574 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -27,6 +27,7 @@ #define PHY_ID_KSZ8061 0x00221570 #define PHY_ID_KSZ9031 0x00221620 #define PHY_ID_KSZ9131 0x00221640 +#define PHY_ID_LAN8814 0x00221660 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -- cgit v1.2.3 From dc1129564a0147feb459159fd220ae22357e2eb6 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 11 Sep 2020 21:43:34 -0700 Subject: soc: ti: pruss: Add a platform driver for PRUSS in TI SoCs The Programmable Real-Time Unit - Industrial Communication Subsystem (PRU-ICSS) is present on various TI SoCs such as AM335x or AM437x or the Keystone 66AK2G. Each SoC can have one or more PRUSS instances that may or may not be identical. For example, AM335x SoCs have a single PRUSS, while AM437x has two PRUSS instances PRUSS1 and PRUSS0, with the PRUSS0 being a cut-down version of the PRUSS1. The PRUSS consists of dual 32-bit RISC cores called the Programmable Real-Time Units (PRUs), some shared, data and instruction memories, some internal peripheral modules, and an interrupt controller. The programmable nature of the PRUs provide flexibility to implement custom peripheral interfaces, fast real-time responses, or specialized data handling. The PRU-ICSS functionality is achieved through three different platform drivers addressing a specific portion of the PRUSS. Some sub-modules of the PRU-ICSS IP reuse some of the existing drivers (like davinci mdio driver or the generic syscon driver). This design provides flexibility in representing the different modules of PRUSS accordingly, and at the same time allowing the PRUSS driver to add some instance specific configuration within an SoC. The PRUSS platform driver deals with the overall PRUSS and is used for managing the subsystem level resources like various memories and the CFG module. It is responsible for the creation and deletion of the platform devices for the child PRU devices and other child devices (like Interrupt Controller, MDIO node and some syscon nodes) so that they can be managed by specific platform drivers. The PRUSS interrupt controller is managed by an irqchip driver, while the individual PRU RISC cores are managed by a PRU remoteproc driver. The driver currently supports the AM335x SoC, and support for other TI SoCs will be added in subsequent patches. Signed-off-by: Suman Anna Signed-off-by: Andrew F. Davis Signed-off-by: Tero Kristo Signed-off-by: Grzegorz Jaszczyk Signed-off-by: Santosh Shilimkar --- include/linux/pruss_driver.h | 48 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/linux/pruss_driver.h (limited to 'include') diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h new file mode 100644 index 000000000000..0701fe1953dd --- /dev/null +++ b/include/linux/pruss_driver.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * PRU-ICSS sub-system specific definitions + * + * Copyright (C) 2014-2020 Texas Instruments Incorporated - http://www.ti.com/ + * Suman Anna + */ + +#ifndef _PRUSS_DRIVER_H_ +#define _PRUSS_DRIVER_H_ + +#include + +/* + * enum pruss_mem - PRUSS memory range identifiers + */ +enum pruss_mem { + PRUSS_MEM_DRAM0 = 0, + PRUSS_MEM_DRAM1, + PRUSS_MEM_SHRD_RAM2, + PRUSS_MEM_MAX, +}; + +/** + * struct pruss_mem_region - PRUSS memory region structure + * @va: kernel virtual address of the PRUSS memory region + * @pa: physical (bus) address of the PRUSS memory region + * @size: size of the PRUSS memory region + */ +struct pruss_mem_region { + void __iomem *va; + phys_addr_t pa; + size_t size; +}; + +/** + * struct pruss - PRUSS parent structure + * @dev: pruss device pointer + * @cfg_regmap: regmap for config region + * @mem_regions: data for each of the PRUSS memory regions + */ +struct pruss { + struct device *dev; + struct regmap *cfg_regmap; + struct pruss_mem_region mem_regions[PRUSS_MEM_MAX]; +}; + +#endif /* _PRUSS_DRIVER_H_ */ -- cgit v1.2.3 From ba59c9b43c86b2c2396acac94e41d946cbaec9fe Mon Sep 17 00:00:00 2001 From: Grzegorz Jaszczyk Date: Fri, 11 Sep 2020 21:47:10 -0700 Subject: soc: ti: pruss: support CORECLK_MUX and IEPCLK_MUX The IEPCLK_MUX is present on all SoCs whereas the CORECLK_MUX is present only on AM65x SoCs and J721E. Add support for both these CLK muxes. This allows the clock rates and clock parents for these to be controlled through DT leveraging the clk infrastructure for configuring the default parents and rates. Signed-off-by: Roger Quadros Signed-off-by: Suman Anna Signed-off-by: Grzegorz Jaszczyk Signed-off-by: Santosh Shilimkar --- include/linux/pruss_driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h index 0701fe1953dd..ecfded30ed05 100644 --- a/include/linux/pruss_driver.h +++ b/include/linux/pruss_driver.h @@ -36,13 +36,19 @@ struct pruss_mem_region { /** * struct pruss - PRUSS parent structure * @dev: pruss device pointer + * @cfg_base: base iomap for CFG region * @cfg_regmap: regmap for config region * @mem_regions: data for each of the PRUSS memory regions + * @core_clk_mux: clk handle for PRUSS CORE_CLK_MUX + * @iep_clk_mux: clk handle for PRUSS IEP_CLK_MUX */ struct pruss { struct device *dev; + void __iomem *cfg_base; struct regmap *cfg_regmap; struct pruss_mem_region mem_regions[PRUSS_MEM_MAX]; + struct clk *core_clk_mux; + struct clk *iep_clk_mux; }; #endif /* _PRUSS_DRIVER_H_ */ -- cgit v1.2.3 From 2fc7b1561fbe502f7a08f3df7e0d0cecee985966 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 17 Aug 2020 15:01:30 -0700 Subject: drm/msm: Add private interface for adreno-smmu This interface will be used for drm/msm to coordinate with the qcom_adreno_smmu_impl to enable/disable TTBR0 translation. Once TTBR0 translation is enabled, the GPU's CP (Command Processor) will directly switch TTBR0 pgtables (and do the necessary TLB inv) synchronized to the GPU's operation. But help from the SMMU driver is needed to initially bootstrap TTBR0 translation, which cannot be done from the GPU. Since this is a very special case, a private interface is used to avoid adding highly driver specific things to the public iommu interface. Signed-off-by: Rob Clark Reviewed-by: Jordan Crouse Reviewed-by: Bjorn Andersson --- include/linux/adreno-smmu-priv.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/linux/adreno-smmu-priv.h (limited to 'include') diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h new file mode 100644 index 000000000000..a889f28afb42 --- /dev/null +++ b/include/linux/adreno-smmu-priv.h @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google, Inc + */ + +#ifndef __ADRENO_SMMU_PRIV_H +#define __ADRENO_SMMU_PRIV_H + +#include + +/** + * struct adreno_smmu_priv - private interface between adreno-smmu and GPU + * + * @cookie: An opque token provided by adreno-smmu and passed + * back into the callbacks + * @get_ttbr1_cfg: Get the TTBR1 config for the GPUs context-bank + * @set_ttbr0_cfg: Set the TTBR0 config for the GPUs context bank. A + * NULL config disables TTBR0 translation, otherwise + * TTBR0 translation is enabled with the specified cfg + * + * The GPU driver (drm/msm) and adreno-smmu work together for controlling + * the GPU's SMMU instance. This is by necessity, as the GPU is directly + * updating the SMMU for context switches, while on the other hand we do + * not want to duplicate all of the initial setup logic from arm-smmu. + * + * This private interface is used for the two drivers to coordinate. The + * cookie and callback functions are populated when the GPU driver attaches + * it's domain. + */ +struct adreno_smmu_priv { + const void *cookie; + const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie); + int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg); +}; + +#endif /* __ADRENO_SMMU_PRIV_H */ \ No newline at end of file -- cgit v1.2.3 From 346ce5b7d624e8cc2ec5a6abd0ea00f0e06ea8ac Mon Sep 17 00:00:00 2001 From: Abhishek Pandit-Subedi Date: Fri, 11 Sep 2020 14:07:11 -0700 Subject: Bluetooth: Add mgmt suspend and resume events Add the controller suspend and resume events, which will signal when Bluetooth has completed preparing for suspend and when it's ready for resume. Signed-off-by: Abhishek Pandit-Subedi Reviewed-by: Miao-chen Chou Reviewed-by: Sonny Sasaka Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 +++ include/net/bluetooth/mgmt.h | 11 +++++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8caac20556b4..02a6ee056b23 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1750,6 +1750,9 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, s8 rssi, u8 *name, u8 name_len); void mgmt_discovering(struct hci_dev *hdev, u8 discovering); +void mgmt_suspending(struct hci_dev *hdev, u8 state); +void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr, + u8 addr_type); bool mgmt_powering_down(struct hci_dev *hdev); void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent); void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 9ad505b9e694..e19e33c7b65c 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1030,3 +1030,14 @@ struct mgmt_ev_adv_monitor_added { struct mgmt_ev_adv_monitor_removed { __le16 monitor_handle; } __packed; + +#define MGMT_EV_CONTROLLER_SUSPEND 0x002d +struct mgmt_ev_controller_suspend { + __u8 suspend_state; +} __packed; + +#define MGMT_EV_CONTROLLER_RESUME 0x002e +struct mgmt_ev_controller_resume { + __u8 wake_reason; + struct mgmt_addr_info addr; +} __packed; -- cgit v1.2.3 From f0cfc486f796dc3b67a4017357a6a8e76a8141c5 Mon Sep 17 00:00:00 2001 From: Abhishek Pandit-Subedi Date: Fri, 11 Sep 2020 14:07:12 -0700 Subject: Bluetooth: Add suspend reason for device disconnect Update device disconnect event with reason 0x5 to indicate that device disconnected because the controller is suspending. Signed-off-by: Abhishek Pandit-Subedi Reviewed-by: Miao-chen Chou Reviewed-by: Sonny Sasaka Signed-off-by: Marcel Holtmann --- include/net/bluetooth/mgmt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index e19e33c7b65c..a4b8935e0db9 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -842,6 +842,7 @@ struct mgmt_ev_device_connected { #define MGMT_DEV_DISCONN_LOCAL_HOST 0x02 #define MGMT_DEV_DISCONN_REMOTE 0x03 #define MGMT_DEV_DISCONN_AUTH_FAILURE 0x04 +#define MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND 0x05 #define MGMT_EV_DEVICE_DISCONNECTED 0x000C struct mgmt_ev_device_disconnected { -- cgit v1.2.3 From 2f20216c1d6fe17c1a224f658be0dc6fab2269c7 Mon Sep 17 00:00:00 2001 From: Abhishek Pandit-Subedi Date: Fri, 11 Sep 2020 14:07:13 -0700 Subject: Bluetooth: Emit controller suspend and resume events Emit controller suspend and resume events when we are ready for suspend and we've resumed from suspend. The controller suspend event will report whatever suspend state was successfully entered. The controller resume event will check the first HCI event that was received after we finished preparing for suspend and, if it was a connection event, store the address of the peer that caused the event. If it was not a connection event, we mark the wake reason as an unexpected event. Here is a sample btmon trace with these events: @ MGMT Event: Controller Suspended (0x002d) plen 1 Suspend state: Page scanning and/or passive scanning (2) @ MGMT Event: Controller Resumed (0x002e) plen 8 Wake reason: Remote wake due to peer device connection (2) LE Address: CD:F3:CD:13:C5:9A (OUI CD-F3-CD) Signed-off-by: Abhishek Pandit-Subedi Reviewed-by: Miao-chen Chou Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 +++ include/net/bluetooth/mgmt.h | 4 ++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 02a6ee056b23..9873e1c8cd16 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -484,6 +484,9 @@ struct hci_dev { enum suspended_state suspend_state; bool scanning_paused; bool suspended; + u8 wake_reason; + bdaddr_t wake_addr; + u8 wake_addr_type; wait_queue_head_t suspend_wait_q; DECLARE_BITMAP(suspend_tasks, __SUSPEND_NUM_TASKS); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index a4b8935e0db9..6b55155e05e9 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1042,3 +1042,7 @@ struct mgmt_ev_controller_resume { __u8 wake_reason; struct mgmt_addr_info addr; } __packed; + +#define MGMT_WAKE_REASON_NON_BT_WAKE 0x0 +#define MGMT_WAKE_REASON_UNEXPECTED 0x1 +#define MGMT_WAKE_REASON_REMOTE_WAKE 0x2 -- cgit v1.2.3 From dde8ceec9e29fe2abf4fabee7d5a0445d0b75b66 Mon Sep 17 00:00:00 2001 From: Crt Mori Date: Sun, 6 Sep 2020 23:02:31 +0200 Subject: iio: temperature: mlx90632: Interface to change object ambient temperature Since object temperature might be different than the sensor temperature the infrared sensors should provide an interface to inject ambient temperature. This was in past done via write to ambient temperature interface (in_temp_ambient_raw), but I think most people did not know about it. This solution introduces a new iio type of the CALIBAMBIENT which is hopefully more descriptive and more explicit about the purpose and capabilities of the sensors. Signed-off-by: Crt Mori Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200906210231.383976-1-cmo@melexis.com Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index e6fd3645963c..1e3ed6f55bca 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -59,6 +59,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_CALIBEMISSIVITY, IIO_CHAN_INFO_OVERSAMPLING_RATIO, IIO_CHAN_INFO_THERMOCOUPLE_TYPE, + IIO_CHAN_INFO_CALIBAMBIENT, }; #endif /* _IIO_TYPES_H_ */ -- cgit v1.2.3 From c5e5ec033c4ab25c53f1fd217849e75deb0bf7bf Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 May 2020 10:41:00 +0100 Subject: genirq: Add fasteoi IPI flow For irqchips using the fasteoi flow, IPIs are a bit special. They need to be EOI'd early (before calling the handler), as funny things may happen in the handler (they do not necessarily behave like a normal interrupt). Reviewed-by: Valentin Schneider Signed-off-by: Marc Zyngier --- include/linux/irq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 1b7f4dfee35b..57205bbf46bf 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -634,6 +634,7 @@ static inline int irq_set_parent(int irq, int parent_irq) */ extern void handle_level_irq(struct irq_desc *desc); extern void handle_fasteoi_irq(struct irq_desc *desc); +extern void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc); extern void handle_edge_irq(struct irq_desc *desc); extern void handle_edge_eoi_irq(struct irq_desc *desc); extern void handle_simple_irq(struct irq_desc *desc); -- cgit v1.2.3 From 83cfac95c01817819c2a51f0931d798d851f8a08 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 May 2020 14:58:13 +0100 Subject: genirq: Allow interrupts to be excluded from /proc/interrupts A number of architectures implement IPI statistics directly, duplicating the core kstat_irqs accounting. As we move IPIs to being actual IRQs, we would end-up with a confusing display in /proc/interrupts (where the IPIs would appear twice). In order to solve this, allow interrupts to be flagged as "hidden", which excludes them from /proc/interrupts. Reviewed-by: Valentin Schneider Signed-off-by: Marc Zyngier --- include/linux/irq.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 57205bbf46bf..63b9d962ee67 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -71,6 +71,7 @@ enum irqchip_irq_state; * it from the spurious interrupt detection * mechanism and from core side polling. * IRQ_DISABLE_UNLAZY - Disable lazy irq disable + * IRQ_HIDDEN - Don't show up in /proc/interrupts */ enum { IRQ_TYPE_NONE = 0x00000000, @@ -97,13 +98,14 @@ enum { IRQ_PER_CPU_DEVID = (1 << 17), IRQ_IS_POLLED = (1 << 18), IRQ_DISABLE_UNLAZY = (1 << 19), + IRQ_HIDDEN = (1 << 20), }; #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ - IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY) + IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN) #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) -- cgit v1.2.3 From 66d90f6ecee755e9c19a119c9255e80091165498 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 7 Sep 2020 12:09:23 +0100 Subject: firmware: arm_scmi: Enable building as a single module Now, with all the plumbing in place to enable building scmi as a module instead of built-in modules, let us enable the same. Link: https://lore.kernel.org/r/20200907195046.56615-5-sudeep.holla@arm.com Tested-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 4b10093ad671..9cd312a1ff92 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -345,7 +345,7 @@ struct scmi_driver { #define to_scmi_driver(d) container_of(d, struct scmi_driver, driver) -#ifdef CONFIG_ARM_SCMI_PROTOCOL +#if IS_REACHABLE(CONFIG_ARM_SCMI_PROTOCOL) int scmi_driver_register(struct scmi_driver *driver, struct module *owner, const char *mod_name); void scmi_driver_unregister(struct scmi_driver *driver); -- cgit v1.2.3 From d88656f475d9eba9b23fa71ab59b225459776d6f Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 11 Sep 2020 09:59:22 +0200 Subject: drm/vboxvideo: Use drm_gem_vram_vmap() interfaces VRAM helpers support ref counting for pin and vmap operations, no need to avoid these operations by employing the internal kmap interface. Just use drm_gem_vram_vmap() and let it handle the details. Also unexport the kmap interfaces from VRAM helpers. Vboxvideo was the last user of these internal functions. v2: * fixed a comma in commit description Signed-off-by: Thomas Zimmermann Reviewed-by: Daniel Vetter Tested-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20200911075922.19317-1-tzimmermann@suse.de --- include/drm/drm_gem_vram_helper.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h index a5e477bf96cc..62cc6e6c3a4f 100644 --- a/include/drm/drm_gem_vram_helper.h +++ b/include/drm/drm_gem_vram_helper.h @@ -100,9 +100,6 @@ u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo); s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo); int drm_gem_vram_pin(struct drm_gem_vram_object *gbo, unsigned long pl_flag); int drm_gem_vram_unpin(struct drm_gem_vram_object *gbo); -void *drm_gem_vram_kmap(struct drm_gem_vram_object *gbo, bool map, - bool *is_iomem); -void drm_gem_vram_kunmap(struct drm_gem_vram_object *gbo); void *drm_gem_vram_vmap(struct drm_gem_vram_object *gbo); void drm_gem_vram_vunmap(struct drm_gem_vram_object *gbo, void *vaddr); -- cgit v1.2.3 From 6b6ff4acb310a0351005474673f1e09a90020efd Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 9 Sep 2020 10:54:24 +0200 Subject: device: property: add helpers to count items in string arrays Instead of doing the following: count = device_property_read_string_array(dev, propname, NULL, 0); Let's provide inline helpers with hardcoded arguments for counting strings in property arrays. Suggested-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski Reviewed-by: Mika Westerberg Reviewed-by: Andy Shevchenko --- include/linux/property.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 9f805c442819..75c178055bc9 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -170,6 +170,12 @@ static inline int device_property_count_u64(struct device *dev, const char *prop return device_property_read_u64_array(dev, propname, NULL, 0); } +static inline int device_property_string_array_count(struct device *dev, + const char *propname) +{ + return device_property_read_string_array(dev, propname, NULL, 0); +} + static inline bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, const char *propname) { @@ -224,6 +230,13 @@ static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode, return fwnode_property_read_u64_array(fwnode, propname, NULL, 0); } +static inline int +fwnode_property_string_array_count(const struct fwnode_handle *fwnode, + const char *propname) +{ + return fwnode_property_read_string_array(fwnode, propname, NULL, 0); +} + struct software_node; /** -- cgit v1.2.3 From 7cba1a4d5e1628e099728d849918de50dab2e24e Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 9 Sep 2020 10:54:25 +0200 Subject: gpiolib: generalize devprop_gpiochip_set_names() for device properties devprop_gpiochip_set_names() is overly complicated with taking the fwnode argument (which requires using dev_fwnode() & of_fwnode_handle() in ACPI and OF GPIO code respectively). Let's just switch to using the generic device properties. This allows us to pull the code setting line names directly into gpiochip_add_data_with_key() instead of handling it separately for ACPI and OF. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg --- include/linux/gpio/driver.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index d1cef5c2715c..56485a040b82 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -756,8 +756,7 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, enum gpiod_flags dflags); void gpiochip_free_own_desc(struct gpio_desc *desc); -void devprop_gpiochip_set_names(struct gpio_chip *gc, - const struct fwnode_handle *fwnode); +int devprop_gpiochip_set_names(struct gpio_chip *gc); #ifdef CONFIG_GPIOLIB -- cgit v1.2.3 From 32fc5aa2df12c7a95dbd1c2c9ee3eb8d7f920d9e Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 9 Sep 2020 10:54:26 +0200 Subject: gpiolib: unexport devprop_gpiochip_set_names() Now that devprop_gpiochip_set_names() is only used in a single place inside drivers/gpio/gpiolib.c, there's no need anymore for it to be exported or to even live in its own source file. Pull this function into the core source file for gpiolib. Signed-off-by: Bartosz Golaszewski Reviewed-by: Mika Westerberg Reviewed-by: Andy Shevchenko --- include/linux/gpio/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 56485a040b82..4a7e295c3640 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -756,8 +756,6 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, enum gpiod_flags dflags); void gpiochip_free_own_desc(struct gpio_desc *desc); -int devprop_gpiochip_set_names(struct gpio_chip *gc); - #ifdef CONFIG_GPIOLIB /* lock/unlock as IRQ */ -- cgit v1.2.3 From 129134e5415d46f38b9978b3809af94ed649b57d Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Fri, 11 Sep 2020 05:07:58 +0200 Subject: media: media/v4l2: remove V4L2_FLAG_MEMORY_NON_CONSISTENT flag The patch partially reverts some of the UAPI bits of the buffer cache management hints. Namely, the queue consistency (memory coherency) user-space hint because, as it turned out, the kernel implementation of this feature was misusing DMA_ATTR_NON_CONSISTENT. The patch reverts both kernel and user space parts: removes the DMA consistency attr functions, rolls back changes to v4l2_requestbuffers, v4l2_create_buffers structures and corresponding UAPI functions (plus compat32 layer) and cleans up the documentation. [hverkuil: fixed a few typos in the commit log] [hverkuil: fixed vb2_core_reqbufs call in drivers/media/dvb-core/dvb_vb2.c] [mchehab: fixed a typo in the commit log: revers->reverts] Signed-off-by: Christoph Hellwig Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf2-core.h | 7 ++----- include/uapi/linux/videodev2.h | 13 ++----------- 2 files changed, 4 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 52ef92049073..bbb3f26fbde9 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -744,8 +744,6 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb); * vb2_core_reqbufs() - Initiate streaming. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. - * @flags: auxiliary queue/buffer management flags. Currently, the only - * used flag is %V4L2_FLAG_MEMORY_NON_CONSISTENT. * @count: requested buffer count. * * Videobuf2 core helper to implement VIDIOC_REQBUF() operation. It is called @@ -770,13 +768,12 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb); * Return: returns zero on success; an error code otherwise. */ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count); + unsigned int *count); /** * vb2_core_create_bufs() - Allocate buffers and any required auxiliary structs * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. - * @flags: auxiliary queue/buffer management flags. * @count: requested buffer count. * @requested_planes: number of planes requested. * @requested_sizes: array with the size of the planes. @@ -794,7 +791,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, * Return: returns zero on success; an error code otherwise. */ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count, + unsigned int *count, unsigned int requested_planes, const unsigned int requested_sizes[]); diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c7b70ff53bc1..235db7754606 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -191,8 +191,6 @@ enum v4l2_memory { V4L2_MEMORY_DMABUF = 4, }; -#define V4L2_FLAG_MEMORY_NON_CONSISTENT (1 << 0) - /* see also http://vektor.theorem.ca/graphics/ycbcr/ */ enum v4l2_colorspace { /* @@ -949,10 +947,7 @@ struct v4l2_requestbuffers { __u32 type; /* enum v4l2_buf_type */ __u32 memory; /* enum v4l2_memory */ __u32 capabilities; - union { - __u32 flags; - __u32 reserved[1]; - }; + __u32 reserved[1]; }; /* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */ @@ -2456,9 +2451,6 @@ struct v4l2_dbg_chip_info { * @memory: enum v4l2_memory; buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. - * @flags: additional buffer management attributes (ignored unless the - * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability - * and configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers { @@ -2467,8 +2459,7 @@ struct v4l2_create_buffers { __u32 memory; struct v4l2_format format; __u32 capabilities; - __u32 flags; - __u32 reserved[6]; + __u32 reserved[7]; }; /* -- cgit v1.2.3 From 5823833c9adab5a9ce5500e7f1ce7deeff00ee73 Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Sat, 11 Jul 2020 14:52:36 +0200 Subject: media: v4l2-ctrl: Add VP9 codec levels Add menu control for VP9 codec levels. A total of 14 levels are defined for Profile 0 (8bit) and Profile 2 (10bit). Each level is a set of constrained bitstreams coded with targeted resolutions, frame rates, and bitrates. The definitions have been taken from webm project [1]. [1] https://www.webmproject.org/vp9/levels/ Signed-off-by: Stanimir Varbanov Reviewed-by: Nicolas Dufresne Reviewed-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 053827cda8e6..a184c4939438 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -651,6 +651,23 @@ enum v4l2_mpeg_video_vp9_profile { V4L2_MPEG_VIDEO_VP9_PROFILE_2 = 2, V4L2_MPEG_VIDEO_VP9_PROFILE_3 = 3, }; +#define V4L2_CID_MPEG_VIDEO_VP9_LEVEL (V4L2_CID_MPEG_BASE+513) +enum v4l2_mpeg_video_vp9_level { + V4L2_MPEG_VIDEO_VP9_LEVEL_1_0 = 0, + V4L2_MPEG_VIDEO_VP9_LEVEL_1_1 = 1, + V4L2_MPEG_VIDEO_VP9_LEVEL_2_0 = 2, + V4L2_MPEG_VIDEO_VP9_LEVEL_2_1 = 3, + V4L2_MPEG_VIDEO_VP9_LEVEL_3_0 = 4, + V4L2_MPEG_VIDEO_VP9_LEVEL_3_1 = 5, + V4L2_MPEG_VIDEO_VP9_LEVEL_4_0 = 6, + V4L2_MPEG_VIDEO_VP9_LEVEL_4_1 = 7, + V4L2_MPEG_VIDEO_VP9_LEVEL_5_0 = 8, + V4L2_MPEG_VIDEO_VP9_LEVEL_5_1 = 9, + V4L2_MPEG_VIDEO_VP9_LEVEL_5_2 = 10, + V4L2_MPEG_VIDEO_VP9_LEVEL_6_0 = 11, + V4L2_MPEG_VIDEO_VP9_LEVEL_6_1 = 12, + V4L2_MPEG_VIDEO_VP9_LEVEL_6_2 = 13, +}; /* CIDs for HEVC encoding. */ -- cgit v1.2.3 From 6d885330fa3daede6bf24b7422da9d6d9a577eb8 Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Mon, 17 Aug 2020 10:27:22 +0200 Subject: media: firmware: qcom_scm: Add memory protect virtual address ranges This adds a new SCM memprotect command to set virtual address ranges. Signed-off-by: Stanimir Varbanov Reviewed-by: Elliot Berman Acked-by: Bjorn Andersson Signed-off-by: Mauro Carvalho Chehab --- include/linux/qcom_scm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 2e1193a3fb5f..0165824c5128 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -84,6 +84,9 @@ extern bool qcom_scm_restore_sec_cfg_available(void); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, + u32 cp_nonpixel_start, + u32 cp_nonpixel_size); extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, unsigned int *src, const struct qcom_scm_vmperm *newvm, @@ -141,6 +144,10 @@ static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) { return -ENODEV; } static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) { return -ENODEV; } +extern inline int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, + u32 cp_nonpixel_start, + u32 cp_nonpixel_size) + { return -ENODEV; } static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, unsigned int *src, const struct qcom_scm_vmperm *newvm, unsigned int dest_cnt) { return -ENODEV; } -- cgit v1.2.3 From 96a9c425e234aac193afb9da6ca11fafc679c7e2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 14 Sep 2020 13:02:58 +0100 Subject: rxrpc: Fix a missing NULL-pointer check in a trace Fix the rxrpc_client tracepoint to not dereference conn to get the cid if conn is NULL, as it does for other fields. RIP: 0010:trace_event_raw_event_rxrpc_client+0x7e/0xe0 [rxrpc] Call Trace: rxrpc_activate_channels+0x62/0xb0 [rxrpc] rxrpc_connect_call+0x481/0x650 [rxrpc] ? wake_up_q+0xa0/0xa0 ? rxrpc_kernel_begin_call+0x12a/0x1b0 [rxrpc] rxrpc_new_client_call+0x2a5/0x5e0 [rxrpc] Fixes: 245500d853e9 ("rxrpc: Rewrite the client connection manager") Reported-by: Marc Dionne Signed-off-by: David Howells Tested-by: Marc Dionne --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 3b67d5981224..e70c90116eda 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -579,7 +579,7 @@ TRACE_EVENT(rxrpc_client, __entry->channel = channel; __entry->usage = conn ? atomic_read(&conn->usage) : -2; __entry->op = op; - __entry->cid = conn->proto.cid; + __entry->cid = conn ? conn->proto.cid : 0; ), TP_printk("C=%08x h=%2d %s i=%08x u=%d", -- cgit v1.2.3 From 1fa5cef283420b3dad93cd6ab04d7125bc1562de Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Tue, 18 Aug 2020 15:07:57 +0800 Subject: i40e: optimise prefetch page refcount refcount of rx_buffer page will be added here originally, so prefetchw is needed, but after commit 1793668c3b8c ("i40e/i40evf: Update code to better handle incrementing page count"), and refcount is not added every time, so change prefetchw as prefetch. Now it mainly services page_address(), but which accesses struct page only when WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL is defined otherwise it returns address based on offset, so we prefetch it conditionally. Jakub suggested to define prefetch_page_address in a common header. Reported-by: kernel test robot Suggested-by: Jakub Kicinski Signed-off-by: Li RongQing Reviewed-by: Jesse Brandeburg Tested-by: Aaron Brown Signed-off-by: Tony Nguyen --- include/linux/prefetch.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h index 13eafebf3549..b83a3f944f28 100644 --- a/include/linux/prefetch.h +++ b/include/linux/prefetch.h @@ -15,6 +15,7 @@ #include #include +struct page; /* prefetch(x) attempts to pre-emptively get the memory pointed to by address "x" into the CPU L1 cache. @@ -62,4 +63,11 @@ static inline void prefetch_range(void *addr, size_t len) #endif } +static inline void prefetch_page_address(struct page *page) +{ +#if defined(WANT_PAGE_VIRTUAL) || defined(HASHED_PAGE_VIRTUAL) + prefetch(page); +#endif +} + #endif -- cgit v1.2.3 From 4b31a9c77bf87f9d9e957f7a42f84c57a407e1f8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 7 Sep 2020 15:00:24 +0300 Subject: drm/atomic-helper: Extract drm_atomic_helper_calc_timestamping_constants() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Put the vblank timestamping constants update loop into its own function. It has no business living inside drm_atomic_helper_update_legacy_modeset_state() so we'll be wanting to move it out entirely. As a first step we'll still call it from drm_atomic_helper_update_legacy_modeset_state(). v2: Drop comment about 'legacy state' in the new function Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200907120026.6360-1-ville.syrjala@linux.intel.com Reviewed-by: Daniel Vetter --- include/drm/drm_atomic_helper.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index b268180c97eb..85df04c8e62f 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -74,6 +74,9 @@ void drm_atomic_helper_update_legacy_modeset_state(struct drm_device *dev, struct drm_atomic_state *old_state); +void +drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *state); + void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev, struct drm_atomic_state *state); void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, -- cgit v1.2.3 From c76c6956566f974bac2470bd72fc22fb923e04a1 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 14 Sep 2020 10:01:18 +0200 Subject: mptcp: call tcp_cleanup_rbuf on subflows That is needed to let the subflows announce promptly when new space is available in the receive buffer. tcp_cleanup_rbuf() is currently a static function, drop the scope modifier and add a declaration in the TCP header. Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index e85d564446c6..852f0d71dd40 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1414,6 +1414,8 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +void tcp_cleanup_rbuf(struct sock *sk, int copied); + /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small -- cgit v1.2.3 From 0cbe6a8f089e5912a577537c97833546d558c357 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 14 Sep 2020 03:20:27 -0700 Subject: tcp: remove SOCK_QUEUE_SHRUNK SOCK_QUEUE_SHRUNK is currently used by TCP as a temporary state that remembers if some room has been made in the rtx queue by an incoming ACK packet. This is later used from tcp_check_space() before considering to send EPOLLOUT. Problem is: If we receive SACK packets, and no packet is removed from RTX queue, we can send fresh packets, thus moving them from write queue to rtx queue and eventually empty the write queue. This stall can happen if TCP_NOTSENT_LOWAT is used. With this fix, we no longer risk stalling sends while holes are repaired, and we can fully use socket sndbuf. This also removes a cache line dirtying for typical RPC workloads. Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option") Signed-off-by: Eric Dumazet Cc: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/sock.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 7dd3051551fb..eaa5cac5e836 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -845,7 +845,6 @@ enum sock_flags { SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ - SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ @@ -1526,7 +1525,6 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && -- cgit v1.2.3 From 1869e226a7b3ef75b4f70ede2f1b7229f7157fa4 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 13 Sep 2020 12:43:39 -0600 Subject: ipv4: Initialize flowi4_multipath_hash in data path flowi4_multipath_hash was added by the commit referenced below for tunnels. Unfortunately, the patch did not initialize the new field for several fast path lookups that do not initialize the entire flow struct to 0. Fix those locations. Currently, flowi4_multipath_hash is random garbage and affects the hash value computed by fib_multipath_hash for multipath selection. Fixes: 24ba14406c5c ("route: Add multipath_hash in flowi_common to make user-define hash") Signed-off-by: David Ahern Cc: wenxu Signed-off-by: David S. Miller --- include/net/flow.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 929d3ca614d0..b2531df3f65f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = sport; + fl4->flowi4_multipath_hash = 0; } /* Reset some input parameters after previous lookup */ -- cgit v1.2.3 From 13e6ce98aa65ab5ce19351c020419360dfe8af29 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 13 Sep 2020 19:51:50 +0800 Subject: net: sched: only keep the available bits when setting vxlan md->gbp As we can see from vxlan_build/parse_gbp_hdr(), when processing metadata on vxlan rx/tx path, only dont_learn/policy_applied/policy_id fields can be set to or parse from the packet for vxlan gbp option. So we'd better do the mask when set it in act_tunnel_key and cls_flower. Otherwise, when users don't know these bits, they may configure with a value which can never be matched. Reported-by: Shuang Li Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/vxlan.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3a41627cbdfe..08537aa14f7c 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -121,6 +121,9 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) +#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \ + VXLAN_GBP_ID_MASK) + /* * VXLAN Generic Protocol Extension (VXLAN_F_GPE): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -- cgit v1.2.3 From 36d818f610f218e9e8711bf498b62a27778dae3f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 11 Sep 2020 20:02:02 +0300 Subject: kernel.h: Move oops_in_progress to printk.h The oops_in_progress is defined in printk.c, so it's logical to move oops_in_progress to printk.h. Signed-off-by: Andy Shevchenko Acked-by: Sergey Senozhatsky Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20200911170202.8565-1-andriy.shevchenko@linux.intel.com --- include/linux/debug_locks.h | 2 +- include/linux/kernel.h | 1 - include/linux/printk.h | 2 ++ 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index e7e45f0cc7da..2915f56ad421 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -2,9 +2,9 @@ #ifndef __LINUX_DEBUG_LOCKING_H #define __LINUX_DEBUG_LOCKING_H -#include #include #include +#include struct task_struct; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 82d91547d122..6cef4ca5589c 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -527,7 +527,6 @@ extern unsigned int sysctl_oops_all_cpu_backtrace; #endif /* CONFIG_SMP */ extern void bust_spinlocks(int yes); -extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; diff --git a/include/linux/printk.h b/include/linux/printk.h index 34c1a7be3e01..f749a2c2e7a5 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -12,6 +12,8 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; +extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ + #define PRINTK_MAX_SINGLE_HEADER_LEN 2 static inline int printk_get_level(const char *buffer) -- cgit v1.2.3 From e47168f3d1b14af5281cf50c59561d59d28201f9 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 31 Aug 2020 08:30:44 +0000 Subject: powerpc/8xx: Support 16k hugepages with 4k pages The 8xx has 4 page sizes: 4k, 16k, 512k and 8M 4k and 16k can be selected at build time as standard page sizes, and 512k and 8M are hugepages. When 4k standard pages are selected, 16k pages are not available. Allow 16k pages as hugepages when 4k pages are used. To allow that, implement arch_make_huge_pte() which receives the necessary arguments to allow setting the PTE in accordance with the page size: - 512 k pages must have _PAGE_HUGE and _PAGE_SPS. They are set by pte_mkhuge(). arch_make_huge_pte() does nothing. - 16 k pages must have only _PAGE_SPS. arch_make_huge_pte() clears _PAGE_HUGE. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a518abc29266a708dfbccc8fce9ae6694fe4c2c6.1598862623.git.christophe.leroy@csgroup.eu --- include/uapi/asm-generic/hugetlb_encode.h | 1 + include/uapi/linux/mman.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/asm-generic/hugetlb_encode.h b/include/uapi/asm-generic/hugetlb_encode.h index b0f8e87235bd..4f3d5aaa11f5 100644 --- a/include/uapi/asm-generic/hugetlb_encode.h +++ b/include/uapi/asm-generic/hugetlb_encode.h @@ -20,6 +20,7 @@ #define HUGETLB_FLAG_ENCODE_SHIFT 26 #define HUGETLB_FLAG_ENCODE_MASK 0x3f +#define HUGETLB_FLAG_ENCODE_16KB (14 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index 923cc162609c..f55bc680b5b0 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -27,6 +27,7 @@ #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT #define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK +#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB #define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB #define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB #define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB -- cgit v1.2.3 From 0fe438cec9e1d263a831e62a0499e14ee228fb30 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 11 Sep 2020 15:06:53 +0200 Subject: drm/ttm: remove default caching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As far as I can tell this was never used either and we just always fallback to the order cached > wc > uncached anyway. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/390142/ --- include/drm/ttm/ttm_bo_driver.h | 2 -- include/drm/ttm/ttm_resource.h | 3 --- 2 files changed, 5 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 303a89d1066d..bf000d69e533 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -690,7 +690,6 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); * @bdev: ttm device * @type: memory manager type * @available_caching: TTM_PL_FLAG_* for allowed caching modes - * @default_caching: default caching mode * @use_tt: if the memory manager uses tt * @p_size: size of area to be managed in pages. * @@ -700,7 +699,6 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); int ttm_range_man_init(struct ttm_bo_device *bdev, unsigned type, uint32_t available_caching, - uint32_t default_caching, bool use_tt, unsigned long p_size); diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 7b8a3157fbb3..a6ae4bf9c3e1 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -110,8 +110,6 @@ struct ttm_resource_manager_func { * @size: Size of the managed region. * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX, * as defined in ttm_placement_common.h - * @default_caching: The default caching policy used for a buffer object - * placed in this memory type if the user doesn't provide one. * @func: structure pointer implementing the range manager. See above * @move_lock: lock for move fence * static information. bdev::driver::io_mem_free is never used. @@ -128,7 +126,6 @@ struct ttm_resource_manager { bool use_tt; uint64_t size; uint32_t available_caching; - uint32_t default_caching; const struct ttm_resource_manager_func *func; spinlock_t move_lock; -- cgit v1.2.3 From 9c3006a4cc1b165652a07727caf7926054f9aa9f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 11 Sep 2020 16:01:21 +0200 Subject: drm/ttm: remove available_caching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of letting TTM make an educated guess based on some mask all drivers should just specify what caching they want for their CPU mappings. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/390207/ --- include/drm/ttm/ttm_bo_driver.h | 5 +---- include/drm/ttm/ttm_resource.h | 3 --- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index bf000d69e533..0b7d18650dc5 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -689,7 +689,6 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); * * @bdev: ttm device * @type: memory manager type - * @available_caching: TTM_PL_FLAG_* for allowed caching modes * @use_tt: if the memory manager uses tt * @p_size: size of area to be managed in pages. * @@ -697,9 +696,7 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); * The range manager is installed for this device in the type slot. */ int ttm_range_man_init(struct ttm_bo_device *bdev, - unsigned type, - uint32_t available_caching, - bool use_tt, + unsigned type, bool use_tt, unsigned long p_size); /** diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index a6ae4bf9c3e1..0e172d94a0c1 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -108,8 +108,6 @@ struct ttm_resource_manager_func { * @gpu_offset: If used, the GPU offset of the first managed page of * fixed memory or the first managed location in an aperture. * @size: Size of the managed region. - * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX, - * as defined in ttm_placement_common.h * @func: structure pointer implementing the range manager. See above * @move_lock: lock for move fence * static information. bdev::driver::io_mem_free is never used. @@ -125,7 +123,6 @@ struct ttm_resource_manager { bool use_type; bool use_tt; uint64_t size; - uint32_t available_caching; const struct ttm_resource_manager_func *func; spinlock_t move_lock; -- cgit v1.2.3 From f8910ffa81b085030dc54814c85d338c26a3157e Mon Sep 17 00:00:00 2001 From: Xianting Tian Date: Tue, 15 Sep 2020 15:18:17 +0800 Subject: ipmi:msghandler: retry to get device id on an error We fail to get the BMCS's device id with low probability when loading the ipmi driver and it causes BMC device registration failed. When this issue occurs we got below kernel prints: [Wed Sep 9 19:52:03 2020] ipmi_si IPI0001:00: IPMI message handler: device id demangle failed: -22 [Wed Sep 9 19:52:03 2020] IPMI BT: using default values [Wed Sep 9 19:52:03 2020] IPMI BT: req2rsp=5 secs retries=2 [Wed Sep 9 19:52:03 2020] ipmi_si IPI0001:00: Unable to get the device id: -5 [Wed Sep 9 19:52:04 2020] ipmi_si IPI0001:00: Unable to register device: error -5 When this issue happens, we want to manually unload the driver and try to load it again, but it can't be unloaded by 'rmmod' as it is already 'in use'. We add a print in handle_one_recv_msg(), when this issue happens, the msg we received is "Recv: 1c 01 d5", which means the data_len is 1, data[0] is 0xd5 (completion code), which means "bmc cannot execute command. Command, or request parameter(s), not supported in present state". Debug code: static int handle_one_recv_msg(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { printk("Recv: %*ph\n", msg->rsp_size, msg->rsp); ... ... } Then in ipmi_demangle_device_id(), it returned '-EINVAL' as 'data_len < 7' and 'data[0] != 0'. We created this patch to retry the get device id when this error happens. We reproduced this issue again and the retry succeed on the first retry, we finally got the correct msg and then all is ok: Recv: 1c 01 00 01 81 05 84 02 af db 07 00 01 00 b9 00 10 00 So use a retry machanism in this patch to give bmc more opportunity to correctly response kernel when we received specific completion codes. Signed-off-by: Xianting Tian Message-Id: <20200915071817.4484-1-tian.xianting@h3c.com> [Cleaned up the verbage a bit in the header and prints.] Signed-off-by: Corey Minyard --- include/uapi/linux/ipmi_msgdefs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/ipmi_msgdefs.h b/include/uapi/linux/ipmi_msgdefs.h index c2b23a9fdf3d..0934af3b8037 100644 --- a/include/uapi/linux/ipmi_msgdefs.h +++ b/include/uapi/linux/ipmi_msgdefs.h @@ -69,6 +69,8 @@ #define IPMI_ERR_MSG_TRUNCATED 0xc6 #define IPMI_REQ_LEN_INVALID_ERR 0xc7 #define IPMI_REQ_LEN_EXCEEDED_ERR 0xc8 +#define IPMI_DEVICE_IN_FW_UPDATE_ERR 0xd1 +#define IPMI_DEVICE_IN_INIT_ERR 0xd2 #define IPMI_NOT_IN_MY_STATE_ERR 0xd5 /* IPMI 2.0 */ #define IPMI_LOST_ARBITRATION_ERR 0x81 #define IPMI_BUS_ERR 0x82 -- cgit v1.2.3 From b22960b8f274382ff165db50faebbde5f8a16c32 Mon Sep 17 00:00:00 2001 From: Chandan Uddaraju Date: Thu, 27 Aug 2020 14:16:54 -0700 Subject: drm: add constant N value in helper file The constant N value (0x8000) is used by i915 DP driver. Define this value in dp helper header file to use in multiple Display Port drivers. Change i915 driver accordingly. Change in v6: Change commit message Signed-off-by: Chandan Uddaraju Signed-off-by: Vara Reddy Signed-off-by: Tanmay Shah Reviewed-by: Stephen Boyd Acked-by: Jani Nikula Signed-off-by: Rob Clark --- include/drm/drm_dp_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index e47dc22ebf50..a31d7aebb8b8 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1134,6 +1134,7 @@ #define DP_MST_PHYSICAL_PORT_0 0 #define DP_MST_LOGICAL_PORT_0 8 +#define DP_LINK_CONSTANT_N_VALUE 0x8000 #define DP_LINK_STATUS_SIZE 6 bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], int lane_count); -- cgit v1.2.3 From fb609b5112bd74b4ba93c86d7af4089ffd9432c2 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 13 May 2020 11:06:47 +0300 Subject: net/mlx5: Always use container_of to find mdev pointer from clock struct Clock struct is part of struct mlx5_core_dev. Code was inconsistent, on some cases used container_of and on another used clock->mdev. Align code to use container_of amd remove clock->mdev pointer. While here, fix reverse xmas tree coding style. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c145de0473bc..8dc3da6e6480 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -643,7 +643,6 @@ struct mlx5_pps { }; struct mlx5_clock { - struct mlx5_core_dev *mdev; struct mlx5_nb pps_nb; seqlock_t lock; struct cyclecounter cycles; -- cgit v1.2.3 From b7cf0806e8783e38f881cae3c56f0869e70b8da2 Mon Sep 17 00:00:00 2001 From: Ofer Levi Date: Sun, 17 May 2020 10:16:49 +0300 Subject: net/mlx5e: Add CQE compression support for multi-strides packets Add CQE compression support for completions of packets that span multiple strides in a Striding RQ, per the HW capability. In our memory model, we use small strides (256B as of today) for the non-linear SKB mode. This feature allows CQE compression to work also for multiple strides packets. In this case decompressing the mini CQE array will use stride index provided by HW as part of the mini CQE. Before this feature, compression was possible only for single-strided packets, i.e. for packets of size up to 256 bytes when in non-linear mode, and the index was maintained by SW. This feature is supported for ConnectX-5 and above. Feature performance test: This was whitebox-tested, we reduced the PCI speed from 125Gb/s to 62.5Gb/s to overload pci and manipulated mlx5 driver to drop incoming packets before building the SKB to achieve low cpu utilization. Outcome is low cpu utilization and bottleneck on pci only. Test setup: Server: Intel(R) Xeon(R) Silver 4108 CPU @ 1.80GHz server, 32 cores NIC: ConnectX-6 DX. Sender side generates 300 byte packets at full pci bandwidth. Receiver side configuration: Single channel, one cpu processing with one ring allocated. Cpu utilization is ~20% while pci bandwidth is fully utilized. For the generated traffic and interface MTU of 4500B (to activate the non-linear SKB mode), packet rate improvement is about 19% from ~17.6Mpps to ~21Mpps. Without this feature, counters show no CQE compression blocks for this setup, while with the feature, counters show ~20.7Mpps compressed CQEs in ~500K compression blocks. Signed-off-by: Ofer Levi Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 4d3376e20f5e..81ca5989009b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -816,7 +816,7 @@ struct mlx5_mini_cqe8 { __be32 rx_hash_result; struct { __be16 checksum; - __be16 rsvd; + __be16 stridx; }; struct { __be16 wqe_counter; @@ -836,6 +836,7 @@ enum { enum { MLX5_CQE_FORMAT_CSUM = 0x1, + MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3, }; #define MLX5_MINI_CQE_ARRAY_SIZE 8 -- cgit v1.2.3 From d05e8e68b07cef9d52bbf53e75fa5faea81e1da6 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Thu, 10 Sep 2020 19:23:48 +0200 Subject: bridge: Add SWITCHDEV_FDB_FLUSH_TO_BRIDGE notifier so the switchdev can notifiy the bridge to flush non-permanent fdb entries for this port. This is useful whenever the hardware fdb of the switchdev is reset, but the netdev and the bridgeport are not deleted. Note that this has the same effect as the IFLA_BRPORT_FLUSH attribute. CC: Jiri Pirko CC: Ivan Vecera CC: Roopa Prabhu CC: Nikolay Aleksandrov Signed-off-by: Alexandra Winter Signed-off-by: Julian Wiedmann Acked-by: Nikolay Aleksandrov Acked-by: Ivan Vecera Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index ff2246914301..53e8b4994296 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -203,6 +203,7 @@ enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_DEVICE, SWITCHDEV_FDB_DEL_TO_DEVICE, SWITCHDEV_FDB_OFFLOADED, + SWITCHDEV_FDB_FLUSH_TO_BRIDGE, SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */ SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */ -- cgit v1.2.3 From 9a27a33027f22a716ce362be48d70ae0eb012ab7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Sep 2020 17:11:52 -0700 Subject: ethtool: add standard pause stats Currently drivers have to report their pause frames statistics via ethtool -S, and there is a wide variety of names used for these statistics. Add the two statistics defined in IEEE 802.3x to the standard API. Create a new ethtool request header flag for including statistics in the response to GET commands. Always create the ETHTOOL_A_PAUSE_STATS nest in replies when flag is set. Testing if driver declares the op is not a reliable way of checking if any stats will actually be included and therefore we don't want to give the impression that presence of ETHTOOL_A_PAUSE_STATS indicates driver support. Note that this patch does not include PFC counters, which may fit better in dcbnl? But mostly I don't need them/have a setup to test them so I haven't looked deeply into exposing them :) v3: - add a helper for "uninitializing" stats, rather than a cryptic memset() (Andrew) Signed-off-by: Jakub Kicinski Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/ethtool.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 18 +++++++++++++++++- 2 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 969a80211df6..060b20f0b20f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -241,6 +241,27 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, ETHTOOL_COALESCE_PKT_RATE_LOW | ETHTOOL_COALESCE_PKT_RATE_HIGH | \ ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL) +#define ETHTOOL_STAT_NOT_SET (~0ULL) + +/** + * struct ethtool_pause_stats - statistics for IEEE 802.3x pause frames + * @tx_pause_frames: transmitted pause frame count. Reported to user space + * as %ETHTOOL_A_PAUSE_STAT_TX_FRAMES. + * + * Equivalent to `30.3.4.2 aPAUSEMACCtrlFramesTransmitted` + * from the standard. + * + * @rx_pause_frames: received pause frame count. Reported to user space + * as %ETHTOOL_A_PAUSE_STAT_RX_FRAMES. Equivalent to: + * + * Equivalent to `30.3.4.3 aPAUSEMACCtrlFramesReceived` + * from the standard. + */ +struct ethtool_pause_stats { + u64 tx_pause_frames; + u64 rx_pause_frames; +}; + /** * struct ethtool_ops - optional netdev operations * @supported_coalesce_params: supported types of interrupt coalescing. @@ -282,6 +303,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * Returns a negative error code or zero. * @get_ringparam: Report ring sizes * @set_ringparam: Set ring sizes. Returns a negative error code or zero. + * @get_pause_stats: Report pause frame statistics. Drivers must not zero + * statistics which they don't report. The stats structure is initialized + * to ETHTOOL_STAT_NOT_SET indicating driver does not report statistics. * @get_pauseparam: Report pause parameters * @set_pauseparam: Set pause parameters. Returns a negative error code * or zero. @@ -418,6 +442,8 @@ struct ethtool_ops { struct ethtool_ringparam *); int (*set_ringparam)(struct net_device *, struct ethtool_ringparam *); + void (*get_pause_stats)(struct net_device *dev, + struct ethtool_pause_stats *pause_stats); void (*get_pauseparam)(struct net_device *, struct ethtool_pauseparam*); int (*set_pauseparam)(struct net_device *, diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5dcd24cb33ea..9cee6df01a10 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -91,9 +91,12 @@ enum { #define ETHTOOL_FLAG_COMPACT_BITSETS (1 << 0) /* provide optional reply for SET or ACT requests */ #define ETHTOOL_FLAG_OMIT_REPLY (1 << 1) +/* request statistics, if supported by the driver */ +#define ETHTOOL_FLAG_STATS (1 << 2) #define ETHTOOL_FLAG_ALL (ETHTOOL_FLAG_COMPACT_BITSETS | \ - ETHTOOL_FLAG_OMIT_REPLY) + ETHTOOL_FLAG_OMIT_REPLY | \ + ETHTOOL_FLAG_STATS) enum { ETHTOOL_A_HEADER_UNSPEC, @@ -376,12 +379,25 @@ enum { ETHTOOL_A_PAUSE_AUTONEG, /* u8 */ ETHTOOL_A_PAUSE_RX, /* u8 */ ETHTOOL_A_PAUSE_TX, /* u8 */ + ETHTOOL_A_PAUSE_STATS, /* nest - _PAUSE_STAT_* */ /* add new constants above here */ __ETHTOOL_A_PAUSE_CNT, ETHTOOL_A_PAUSE_MAX = (__ETHTOOL_A_PAUSE_CNT - 1) }; +enum { + ETHTOOL_A_PAUSE_STAT_UNSPEC, + ETHTOOL_A_PAUSE_STAT_PAD, + + ETHTOOL_A_PAUSE_STAT_TX_FRAMES, + ETHTOOL_A_PAUSE_STAT_RX_FRAMES, + + /* add new constants above here */ + __ETHTOOL_A_PAUSE_STAT_CNT, + ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) +}; + /* EEE */ enum { -- cgit v1.2.3 From e2ce94dc1d89e0f76ddd202cea72e0f505083d0a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 15 Sep 2020 11:40:57 +0300 Subject: devlink: introduce the health reporter test command Introduce a test command for health reporters. User might use this command to trigger test event on a reporter if the reporter supports it. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 3 +++ include/uapi/linux/devlink.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index eaec0a8cc5ef..48b1c1ef1ebd 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -566,6 +566,7 @@ enum devlink_health_reporter_state { * @dump: callback to dump an object * if priv_ctx is NULL, run a full dump * @diagnose: callback to diagnose the current status + * @test: callback to trigger a test event */ struct devlink_health_reporter_ops { @@ -578,6 +579,8 @@ struct devlink_health_reporter_ops { int (*diagnose)(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, struct netlink_ext_ack *extack); + int (*test)(struct devlink_health_reporter *reporter, + struct netlink_ext_ack *extack); }; /** diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 40d35145c879..631f5bdf1707 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -122,6 +122,8 @@ enum devlink_command { DEVLINK_CMD_TRAP_POLICER_NEW, DEVLINK_CMD_TRAP_POLICER_DEL, + DEVLINK_CMD_HEALTH_REPORTER_TEST, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 -- cgit v1.2.3 From 7d61588f690def55ba2885f7f4b03d13ff45b163 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 15 Sep 2020 14:40:59 +0300 Subject: nexthop: Remove unused function declaration from header file Not used or implemented anywhere. Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 3a4f9e3b91a5..2e44efe5709b 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -109,9 +109,6 @@ enum nexthop_event_type { NEXTHOP_EVENT_DEL }; -int call_nexthop_notifier(struct notifier_block *nb, struct net *net, - enum nexthop_event_type event_type, - struct nexthop *nh); int register_nexthop_notifier(struct net *net, struct notifier_block *nb); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); -- cgit v1.2.3 From 52f7232a790a36da30eb64c6de6067a9e4ad194c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 15 Sep 2020 14:41:00 +0300 Subject: nexthop: Remove NEXTHOP_EVENT_ADD Not used anywhere. Signed-off-by: Ido Schimmel Suggested-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 2e44efe5709b..2fd76a9b6dc8 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,7 +105,6 @@ struct nexthop { }; enum nexthop_event_type { - NEXTHOP_EVENT_ADD, NEXTHOP_EVENT_DEL }; -- cgit v1.2.3 From 80690ec6b595807db9a52ec5b225a2d88033ddb5 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 15 Sep 2020 14:41:01 +0300 Subject: nexthop: Convert to blocking notification chain Currently, the only listener of the nexthop notification chain is the VXLAN driver. Subsequent patches will add more listeners (e.g., device drivers such as netdevsim) that need to be able to block when processing notifications. Therefore, convert the notification chain to a blocking one. This is safe as notifications are always emitted from process context. Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/netns/nexthop.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h index 1937476c94a0..1849e77eb68a 100644 --- a/include/net/netns/nexthop.h +++ b/include/net/netns/nexthop.h @@ -14,6 +14,6 @@ struct netns_nexthop { unsigned int seq; /* protected by rtnl_mutex */ u32 last_id_allocated; - struct atomic_notifier_head notifier_chain; + struct blocking_notifier_head notifier_chain; }; #endif -- cgit v1.2.3 From 7eec915138279d7a83ff8f219846bf7c8ae637c1 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 15 Sep 2020 10:21:15 +1000 Subject: drm/ttm/tt: add wrappers to set tt state. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds 2 getters and 4 setters, however unbound and populated are currently the same thing, this will change, it also drops a BUG_ON that seems not that useful. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-2-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 146544ba1c10..86ae759ff018 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -74,9 +74,39 @@ struct ttm_tt { tt_bound, tt_unbound, tt_unpopulated, - } state; + } _state; }; +static inline bool ttm_tt_is_populated(struct ttm_tt *tt) +{ + return tt->_state != tt_unpopulated; +} + +static inline bool ttm_tt_is_bound(struct ttm_tt *tt) +{ + return tt->_state == tt_bound; +} + +static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt) +{ + tt->_state = tt_unpopulated; +} + +static inline void ttm_tt_set_populated(struct ttm_tt *tt) +{ + tt->_state = tt_unbound; +} + +static inline void ttm_tt_set_unbound(struct ttm_tt *tt) +{ + tt->_state = tt_unbound; +} + +static inline void ttm_tt_set_bound(struct ttm_tt *tt) +{ + tt->_state = tt_bound; +} + /** * struct ttm_dma_tt * -- cgit v1.2.3 From 2ff6e69c0449846197c52d7c591b983e23e3e3c9 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 15 Sep 2020 11:02:12 +1000 Subject: drm/ttm: wrap tt destroy. (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All places this was called was using bo->ttm either direct or indirectly. v2: move to ttm_bo Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-3-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 0b7d18650dc5..70557e2de9be 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -684,6 +684,11 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo); */ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); +/** + * ttm_bo_tt_destroy. + */ +void ttm_bo_tt_destroy(struct ttm_buffer_object *bo); + /** * ttm_range_man_init * -- cgit v1.2.3 From 2040ec970e94dde0b94e200ae9bb8f21a61c928f Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 15 Sep 2020 11:16:53 +1000 Subject: drm/ttm: split populate out from binding. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers have to call populate themselves now before binding. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-5-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 86ae759ff018..8f57d86ee67b 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -173,8 +173,7 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma); * Bind the pages of @ttm to an aperture location identified by @bo_mem */ int ttm_tt_bind(struct ttm_bo_device *bdev, - struct ttm_tt *ttm, struct ttm_resource *bo_mem, - struct ttm_operation_ctx *ctx); + struct ttm_tt *ttm, struct ttm_resource *bo_mem); /** * ttm_ttm_destroy: -- cgit v1.2.3 From 9e9a153bdf2555a931fd37678a8e44d170a5d943 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 15 Sep 2020 11:34:51 +1000 Subject: drm/ttm: move ttm binding/unbinding out of ttm_tt paths. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move these up to the bo level, moving ttm_tt to just being backing store. Next step is to move the bound flag out. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-6-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 28 ++++++++++++++++++++++++++++ include/drm/ttm/ttm_tt.h | 35 ----------------------------------- 2 files changed, 28 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 70557e2de9be..d2bea22f35ae 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -684,6 +684,34 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo); */ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp); +/** + * ttm_bo_tt_bind + * + * Bind the object tt to a memory resource. + */ +int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem); + +/** + * ttm_bo_tt_bind + * + * Unbind the object tt from a memory resource. + */ +void ttm_bo_tt_unbind(struct ttm_buffer_object *bo); + +static inline bool ttm_bo_tt_is_bound(struct ttm_buffer_object *bo) +{ + return bo->ttm->_state == tt_bound; +} + +static inline void ttm_bo_tt_set_unbound(struct ttm_buffer_object *bo) +{ + bo->ttm->_state = tt_unbound; +} + +static inline void ttm_bo_tt_set_bound(struct ttm_buffer_object *bo) +{ + bo->ttm->_state = tt_bound; +} /** * ttm_bo_tt_destroy. */ diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 8f57d86ee67b..1ac56730d952 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -82,11 +82,6 @@ static inline bool ttm_tt_is_populated(struct ttm_tt *tt) return tt->_state != tt_unpopulated; } -static inline bool ttm_tt_is_bound(struct ttm_tt *tt) -{ - return tt->_state == tt_bound; -} - static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt) { tt->_state = tt_unpopulated; @@ -97,16 +92,6 @@ static inline void ttm_tt_set_populated(struct ttm_tt *tt) tt->_state = tt_unbound; } -static inline void ttm_tt_set_unbound(struct ttm_tt *tt) -{ - tt->_state = tt_unbound; -} - -static inline void ttm_tt_set_bound(struct ttm_tt *tt) -{ - tt->_state = tt_bound; -} - /** * struct ttm_dma_tt * @@ -164,17 +149,6 @@ int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo, void ttm_tt_fini(struct ttm_tt *ttm); void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma); -/** - * ttm_ttm_bind: - * - * @ttm: The struct ttm_tt containing backing pages. - * @bo_mem: The struct ttm_resource identifying the binding location. - * - * Bind the pages of @ttm to an aperture location identified by @bo_mem - */ -int ttm_tt_bind(struct ttm_bo_device *bdev, - struct ttm_tt *ttm, struct ttm_resource *bo_mem); - /** * ttm_ttm_destroy: * @@ -184,15 +158,6 @@ int ttm_tt_bind(struct ttm_bo_device *bdev, */ void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm); -/** - * ttm_ttm_unbind: - * - * @ttm: The struct ttm_tt. - * - * Unbind a struct ttm_tt. - */ -void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm); - /** * ttm_tt_swapin: * -- cgit v1.2.3 From 3a4ab168a5df5c9532763ac26cde5c2ad06ca1e5 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 15 Sep 2020 11:42:30 +1000 Subject: drm/ttm: split bound/populated flags. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move bound up into the bo object, and keep populated with the tt object. The ghost object handling needs to follow the flags at the bo level now instead of it being part of the ttm tt object. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-7-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 1 + include/drm/ttm/ttm_bo_driver.h | 6 +++--- include/drm/ttm/ttm_tt.h | 12 ++++-------- 3 files changed, 8 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 36ff64e2736c..1d20a7f15a7a 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -141,6 +141,7 @@ struct ttm_buffer_object { struct ttm_resource mem; struct file *persistent_swap_storage; struct ttm_tt *ttm; + bool ttm_bound; bool evicted; bool deleted; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index d2bea22f35ae..e66672f703a3 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -700,17 +700,17 @@ void ttm_bo_tt_unbind(struct ttm_buffer_object *bo); static inline bool ttm_bo_tt_is_bound(struct ttm_buffer_object *bo) { - return bo->ttm->_state == tt_bound; + return bo->ttm_bound; } static inline void ttm_bo_tt_set_unbound(struct ttm_buffer_object *bo) { - bo->ttm->_state = tt_unbound; + bo->ttm_bound = false; } static inline void ttm_bo_tt_set_bound(struct ttm_buffer_object *bo) { - bo->ttm->_state = tt_bound; + bo->ttm_bound = true; } /** * ttm_bo_tt_destroy. diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 1ac56730d952..94e16238c93d 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -70,26 +70,22 @@ struct ttm_tt { struct sg_table *sg; /* for SG objects via dma-buf */ struct file *swap_storage; enum ttm_caching_state caching_state; - enum { - tt_bound, - tt_unbound, - tt_unpopulated, - } _state; + bool populated; }; static inline bool ttm_tt_is_populated(struct ttm_tt *tt) { - return tt->_state != tt_unpopulated; + return tt->populated; } static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt) { - tt->_state = tt_unpopulated; + tt->populated = false; } static inline void ttm_tt_set_populated(struct ttm_tt *tt) { - tt->_state = tt_unbound; + tt->populated = true; } /** -- cgit v1.2.3 From 3312be8f6fc8a8dc7cef01986dbd436eab7af0f7 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 15 Sep 2020 11:47:19 +1000 Subject: drm/ttm: move populated state into page flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just use the top bit of page flags to store the populated state. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-8-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 94e16238c93d..c777b72063db 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -42,6 +42,8 @@ struct ttm_operation_ctx; #define TTM_PAGE_FLAG_SG (1 << 8) #define TTM_PAGE_FLAG_NO_RETRY (1 << 9) +#define TTM_PAGE_FLAG_PRIV_POPULATED (1 << 31) + enum ttm_caching_state { tt_uncached, tt_wc, @@ -70,22 +72,21 @@ struct ttm_tt { struct sg_table *sg; /* for SG objects via dma-buf */ struct file *swap_storage; enum ttm_caching_state caching_state; - bool populated; }; static inline bool ttm_tt_is_populated(struct ttm_tt *tt) { - return tt->populated; + return tt->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED; } static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt) { - tt->populated = false; + tt->page_flags &= ~TTM_PAGE_FLAG_PRIV_POPULATED; } static inline void ttm_tt_set_populated(struct ttm_tt *tt) { - tt->populated = true; + tt->page_flags |= TTM_PAGE_FLAG_PRIV_POPULATED; } /** -- cgit v1.2.3 From 27ba3e8ff3ab86449e63d38a8d623053591e65fa Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 15 Sep 2020 16:33:46 +0900 Subject: scsi: sd: sd_zbc: Fix handling of host-aware ZBC disks When CONFIG_BLK_DEV_ZONED is disabled, allow using host-aware ZBC disks as regular disks. In this case, ensure that command completion is correctly executed by changing sd_zbc_complete() to return good_bytes instead of 0 and causing a hang during device probe (endless retries). When CONFIG_BLK_DEV_ZONED is enabled and a host-aware disk is detected to have partitions, it will be used as a regular disk. In this case, make sure to not do anything in sd_zbc_revalidate_zones() as that triggers warnings. Since all these different cases result in subtle settings of the disk queue zoned model, introduce the block layer helper function blk_queue_set_zoned() to generically implement setting up the effective zoned model according to the disk type, the presence of partitions on the disk and CONFIG_BLK_DEV_ZONED configuration. Link: https://lore.kernel.org/r/20200915073347.832424-2-damien.lemoal@wdc.com Fixes: b72053072c0b ("block: allow partitions on host aware zone devices") Cc: Reported-by: Borislav Petkov Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Damien Le Moal Signed-off-by: Martin K. Petersen --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..868e11face00 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -352,6 +352,8 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); + #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) -- cgit v1.2.3 From 984fe94f94756dacb3c8cc52904a23adf9e04da1 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Tue, 15 Sep 2020 16:45:39 -0700 Subject: bpf: Mutex protect used_maps array and count To support modifying the used_maps array, we use a mutex to protect the use of the counter and the array. The mutex is initialized right after the prog aux is allocated, and destroyed right before prog aux is freed. This way we guarantee it's initialized for both cBPF and eBPF. Signed-off-by: YiFei Zhu Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Cc: YiFei Zhu Link: https://lore.kernel.org/bpf/20200915234543.3220146-2-sdf@google.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c6d9f2c444f4..5dcce0364634 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -751,6 +751,7 @@ struct bpf_prog_aux { struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; + struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ -- cgit v1.2.3 From ef15314aa5de955c6afd87d512e8b00f5ac08d06 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Tue, 15 Sep 2020 16:45:40 -0700 Subject: bpf: Add BPF_PROG_BIND_MAP syscall This syscall binds a map to a program. Returns success if the map is already bound to the program. Signed-off-by: YiFei Zhu Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Cc: YiFei Zhu Link: https://lore.kernel.org/bpf/20200915234543.3220146-3-sdf@google.com --- include/uapi/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7dd314176df7..a22812561064 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -124,6 +124,7 @@ enum bpf_cmd { BPF_ENABLE_STATS, BPF_ITER_CREATE, BPF_LINK_DETACH, + BPF_PROG_BIND_MAP, }; enum bpf_map_type { @@ -658,6 +659,12 @@ union bpf_attr { __u32 flags; } iter_create; + struct { /* struct used by BPF_PROG_BIND_MAP command */ + __u32 prog_fd; + __u32 map_fd; + __u32 flags; /* extra flags */ + } prog_bind_map; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From ed5dd6a67d5eac5fb8873697b55dc1699752a9f3 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 10 Sep 2020 15:50:56 +0800 Subject: scsi: core: Only re-run queue in scsi_end_request() if device queue is busy The request queue is currently run unconditionally in scsi_end_request() if both target queue and host queue are ready. Recently Long Li reported that cost of a queue run can be very heavy in case of high queue depth. Improve this situation by only running the request queue when this LUN is busy. Link: https://lore.kernel.org/r/20200910075056.36509-1-ming.lei@redhat.com Reported-by: Long Li Tested-by: Long Li Tested-by: Kashyap Desai Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Ewan D. Milne Reviewed-by: John Garry Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index bc5909033d13..1a5c9a3df6d6 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -109,6 +109,7 @@ struct scsi_device { atomic_t device_busy; /* commands actually active on LLDD */ atomic_t device_blocked; /* Device returned QUEUE_FULL. */ + atomic_t restarts; spinlock_t list_lock; struct list_head starved_entry; unsigned short queue_depth; /* How deep of a queue we want */ -- cgit v1.2.3 From fcc2cc1f35613c016e1de25bb001bfdd9eaa25f9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 14 Sep 2020 17:37:46 +0200 Subject: USB: move snd_usb_pipe_sanity_check into the USB core snd_usb_pipe_sanity_check() is a great function, so let's move it into the USB core so that other parts of the kernel, including the USB core, can call it. Name it usb_pipe_type_check() to match the existing usb_urb_ep_type_check() call, which now uses this function. Cc: Jaroslav Kysela Cc: "Gustavo A. R. Silva" Cc: Eli Billauer Cc: Emiliano Ingrassia Cc: Alan Stern Cc: Alexander Tsoy Cc: "Geoffrey D. Bennett" Cc: Jussi Laako Cc: Nick Kossifidis Cc: Dmitry Panchenko Cc: Chris Wulff Cc: Jesus Ramos Reviewed-by: Takashi Iwai Link: https://lore.kernel.org/r/20200914153756.3412156-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 20c555db4621..0b3963d7ec38 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1764,6 +1764,7 @@ static inline int usb_urb_dir_out(struct urb *urb) return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_OUT; } +int usb_pipe_type_check(struct usb_device *dev, unsigned int pipe); int usb_urb_ep_type_check(const struct urb *urb); void *usb_alloc_coherent(struct usb_device *dev, size_t size, -- cgit v1.2.3 From 719b8f2850d3d9b863cc5e4f08e9ef0206e45b26 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 14 Sep 2020 17:37:47 +0200 Subject: USB: add usb_control_msg_send() and usb_control_msg_recv() New core functions to make sending/receiving USB control messages easier and saner. In discussions, it turns out that the large majority of users of usb_control_msg() do so in potentially incorrect ways. The most common issue is where a "short" message is received, yet never detected properly due to "incorrect" error handling. Handle all of this in the USB core with two new functions to try to make working with USB control messages simpler. No more need for dynamic data, messages can be on the stack, and only "complete" send/receive will work without causing an error. Link: https://lore.kernel.org/r/20200914153756.3412156-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 0b3963d7ec38..a5460f08126e 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1802,6 +1802,12 @@ extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, int timeout); /* wrappers around usb_control_msg() for the most common standard requests */ +int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, + __u8 requesttype, __u16 value, __u16 index, + const void *data, __u16 size, int timeout); +int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request, + __u8 requesttype, __u16 value, __u16 index, + void *data, __u16 size, int timeout); extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype, unsigned char descindex, void *buf, int size); extern int usb_get_status(struct usb_device *dev, -- cgit v1.2.3 From 9aa9cf3ee9451d08adafc03cef8e44c7ea3898e7 Mon Sep 17 00:00:00 2001 From: Shiju Jose Date: Thu, 3 Sep 2020 13:34:55 +0100 Subject: ACPI / APEI: Add a notifier chain for unknown (vendor) CPER records CPER records describing a firmware-first error are identified by GUID. The ghes driver currently logs, but ignores any unknown CPER records. This prevents describing errors that can't be represented by a standard entry, that would otherwise allow a driver to recover from an error. The UEFI spec calls these 'Non-standard Section Body' (N.2.3 of version 2.8). Add a notifier chain for these non-standard/vendor-records. Callers must identify their type of records by GUID. Record data is copied to memory from the ghes_estatus_pool to allow us to keep it until after the notifier has run. Co-developed-by: James Morse Link: https://lore.kernel.org/r/20200903123456.1823-2-shiju.jose@huawei.com Signed-off-by: James Morse Signed-off-by: Shiju Jose Signed-off-by: Lorenzo Pieralisi Acked-by: "Rafael J. Wysocki" --- include/acpi/ghes.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 517a5231cc1b..34fb3431a8f3 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -53,6 +53,24 @@ enum { GHES_SEV_PANIC = 0x3, }; +#ifdef CONFIG_ACPI_APEI_GHES +/** + * ghes_register_vendor_record_notifier - register a notifier for vendor + * records that the kernel would otherwise ignore. + * @nb: pointer to the notifier_block structure of the event handler. + * + * return 0 : SUCCESS, non-zero : FAIL + */ +int ghes_register_vendor_record_notifier(struct notifier_block *nb); + +/** + * ghes_unregister_vendor_record_notifier - unregister the previously + * registered vendor record notifier. + * @nb: pointer to the notifier_block structure of the vendor record handler. + */ +void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); +#endif + int ghes_estatus_pool_init(int num_ghes); /* From drivers/edac/ghes_edac.c */ -- cgit v1.2.3 From e0830dbf71f191851ed3772d2760f007b7c5bc3a Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 9 Sep 2020 16:31:01 +0200 Subject: serial: core: fix console port-lock regression Fix the port-lock initialisation regression introduced by commit a3cb39d258ef ("serial: core: Allow detach and attach serial device for console") by making sure that the lock is again initialised during console setup. The console may be registered before the serial controller has been probed in which case the port lock needs to be initialised during console setup by a call to uart_set_options(). The console-detach changes introduced a regression in several drivers by effectively removing that initialisation by not initialising the lock when the port is used as a console (which is always the case during console setup). Add back the early lock initialisation and instead use a new console-reinit flag to handle the case where a console is being re-attached through sysfs. The question whether the console-detach interface should have been added in the first place is left for another discussion. Note that the console-enabled check in uart_set_options() is not redundant because of kgdboc, which can end up reinitialising an already enabled console (see commit 42b6a1baa3ec ("serial_core: Don't re-initialize a previously initialized spinlock.")). Fixes: a3cb39d258ef ("serial: core: Allow detach and attach serial device for console") Cc: stable # 5.7 Signed-off-by: Johan Hovold Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200909143101.15389-3-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 01fc4d9c9c54..8a99279a579b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -248,6 +248,7 @@ struct uart_port { unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; + unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ -- cgit v1.2.3 From 3babbe447d76ac2919ec4d0eb3b0adfb22f5b03c Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 7 Aug 2020 13:15:16 +0530 Subject: sched/topology: Allow archs to override cpu_smt_mask cpu_smt_mask tracks topology_sibling_cpumask. This would be good for most architectures. One of the users of cpu_smt_mask(), would be to identify idle-cores. On Power9, a pair of SMT4 cores can be presented by the firmware as a SMT8 core for backward compatibility reasons. powerpc allows LPARs to be live migrated from Power8 to Power9. Do note Power8 had only SMT8 cores. Existing software which has been developed/configured for Power8 would expect to see SMT8 core. Maintaining the illusion of SMT8 core is a requirement to make that work. In order to maintain above userspace backward compatibility with previous versions of processor, Power9 onwards there is option to the firmware to advertise a pair of SMT4 cores as a fused cores aka SMT8 core. On Power9 this pair shares the L2 cache as well. However, from the scheduler's point of view, a core should be determined by SMT4, since its a completely independent unit of compute. Hence allow powerpc architecture to override the default cpu_smt_mask() to point to the SMT4 cores in a SMT8 mode. This will ensure the scheduler is always given the right information. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200807074517.27957-1-srikar@linux.vnet.ibm.com --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/topology.h b/include/linux/topology.h index 608fa4aadf0e..ad03df1cc266 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -198,7 +198,7 @@ static inline int cpu_to_mem(int cpu) #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif -#ifdef CONFIG_SCHED_SMT +#if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); -- cgit v1.2.3 From a25536e8d57dd6fdd70b07219fc2c38e3b8c6503 Mon Sep 17 00:00:00 2001 From: Swapnil Jakhade Date: Fri, 11 Sep 2020 08:18:33 +0200 Subject: phy: Add new PHY attribute max_link_rate Add new PHY attribute max_link_rate to struct phy_attrs. This indicates maximum link rate supported by PHY (in Mbps). Signed-off-by: Yuti Amonkar Signed-off-by: Swapnil Jakhade Reviewed-by: Laurent Pinchart Acked-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/1599805114-22063-2-git-send-email-sjakhade@cadence.com Signed-off-by: Vinod Koul --- include/linux/phy/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index bcee8eba62b3..e435bdb0bab3 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -115,10 +115,12 @@ struct phy_ops { /** * struct phy_attrs - represents phy attributes * @bus_width: Data path width implemented by PHY + * @max_link_rate: Maximum link rate supported by PHY (in Mbps) * @mode: PHY mode */ struct phy_attrs { u32 bus_width; + u32 max_link_rate; enum phy_mode mode; }; -- cgit v1.2.3 From 42d8a346c5c06689f4f25aecfa287a5aca501a55 Mon Sep 17 00:00:00 2001 From: Xianting Tian Date: Wed, 16 Sep 2020 14:21:29 +0800 Subject: ipmi: add retry in try_get_dev_id() Use a retry machanism to give the BMC more opportunities to correctly respond when we receive specific completion codes. This is similar to what is done in __get_device_id(). Signed-off-by: Xianting Tian Message-Id: <20200916062129.26129-1-tian.xianting@h3c.com> [Moved GET_DEVICE_ID_MAX_RETRY to include/linux/ipmi.h, reworded some text.] Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index ef61676cfe05..52850a02a3d0 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -333,4 +333,6 @@ struct ipmi_smi_info { /* This is to get the private info of struct ipmi_smi */ extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data); +#define GET_DEVICE_ID_MAX_RETRY 5 + #endif /* __LINUX_IPMI_H */ -- cgit v1.2.3 From e6b1a44eccfcab5e5e280be376f65478c3b2c7a2 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 15 Sep 2020 22:07:50 +0800 Subject: locking/percpu-rwsem: Use this_cpu_{inc,dec}() for read_count The __this_cpu*() accessors are (in general) IRQ-unsafe which, given that percpu-rwsem is a blocking primitive, should be just fine. However, file_end_write() is used from IRQ context and will cause load-store issues on architectures where the per-cpu accessors are not natively irq-safe. Fix it by using the IRQ-safe this_cpu_*() for operations on read_count. This will generate more expensive code on a number of platforms, which might cause a performance regression for some of the other percpu-rwsem users. If any such is reported, we can consider alternative solutions. Fixes: 70fe2f48152e ("aio: fix freeze protection of aio writes") Signed-off-by: Hou Tao Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Acked-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20200915140750.137881-1-houtao1@huawei.com --- include/linux/percpu-rwsem.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5e033fe1ff4e..5fda40f97fe9 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -60,7 +60,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem) * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* @@ -79,7 +79,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); @@ -103,7 +103,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked @@ -115,7 +115,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); -- cgit v1.2.3 From 267580db047ef428a70bef8287ca62c5a450c139 Mon Sep 17 00:00:00 2001 From: "peterz@infradead.org" Date: Tue, 15 Sep 2020 16:30:28 +0200 Subject: seqlock: Unbreak lockdep seqcount_LOCKNAME_init() needs to be a macro due to the lockdep annotation in seqcount_init(). Since a macro cannot define another macro, we need to effectively revert commit: e4e9ab3f9f91 ("seqlock: Fold seqcount_LOCKNAME_init() definition"). Fixes: e4e9ab3f9f91 ("seqlock: Fold seqcount_LOCKNAME_init() definition") Reported-by: Qian Cai Debugged-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Tested-by: Qian Cai Link: https://lkml.kernel.org/r/20200915143028.GB2674@hirez.programming.kicks-ass.net --- include/linux/seqlock.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index f73c7eb68f27..76e44e6c0100 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -173,6 +173,19 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * @lock: Pointer to the associated lock */ +#define seqcount_LOCKNAME_init(s, _lock, lockname) \ + do { \ + seqcount_##lockname##_t *____s = (s); \ + seqcount_init(&____s->seqcount); \ + __SEQ_LOCK(____s->lock = (_lock)); \ + } while (0) + +#define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) +#define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) +#define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock); +#define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex); +#define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex); + /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t @@ -190,13 +203,6 @@ typedef struct seqcount_##lockname { \ __SEQ_LOCK(locktype *lock); \ } seqcount_##lockname##_t; \ \ -static __always_inline void \ -seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock) \ -{ \ - seqcount_init(&s->seqcount); \ - __SEQ_LOCK(s->lock = lock); \ -} \ - \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ @@ -284,8 +290,8 @@ SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mu __SEQ_LOCK(.lock = (assoc_lock)) \ } -#define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) +#define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) -- cgit v1.2.3 From dfb9eb7cf6cd0c0b0f2a1111fcc47b0a297b097d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 26 Aug 2020 13:16:45 +0200 Subject: PCI/MSI: Rework pci_msi_domain_calc_hwirq() Retrieve the PCI device from the msi descriptor instead of doing so at the call sites. Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20200826112332.352583299@linutronix.de --- include/linux/msi.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index 8ad679e9d9c0..d360cc7c4f94 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -369,8 +369,7 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev, - struct msi_desc *desc); +irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc); int pci_msi_domain_check_cap(struct irq_domain *domain, struct msi_domain_info *info, struct device *dev); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); -- cgit v1.2.3 From 9006c133a422f474d7d8e10a8baae179f70c22f5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 26 Aug 2020 13:16:47 +0200 Subject: x86/msi: Use generic MSI domain ops pci_msi_get_hwirq() and pci_msi_set_desc are not longer special. Enable the generic MSI domain ops in the core and PCI MSI code unconditionally and get rid of the x86 specific implementations in the X86 MSI code and in the hyperv PCI driver. Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20200826112332.564274859@linutronix.de --- include/linux/msi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index d360cc7c4f94..5aa126b7820b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -369,7 +369,6 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc); int pci_msi_domain_check_cap(struct irq_domain *domain, struct msi_domain_info *info, struct device *dev); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); -- cgit v1.2.3 From c6c9e2838c5f0b94773511586123bcb125757f2a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 26 Aug 2020 13:16:51 +0200 Subject: irqdomain/msi: Provide DOMAIN_BUS_VMD_MSI PCI devices behind a VMD bus are not subject to interrupt remapping, but the irq domain for VMD MSI cannot be distinguished from a regular PCI/MSI irq domain. Add a new domain bus token and allow it in the bus token check in msi_check_reservation_mode() to keep the functionality the same once VMD uses this token. Signed-off-by: Thomas Gleixner Acked-by: Marc Zyngier Acked-by: Jon Derrick Link: https://lore.kernel.org/r/20200826112332.954409970@linutronix.de --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b37350c4fe37..44445d9de881 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -84,6 +84,7 @@ enum irq_domain_bus_token { DOMAIN_BUS_FSL_MC_MSI, DOMAIN_BUS_TI_SCI_INTA_MSI, DOMAIN_BUS_WAKEUP, + DOMAIN_BUS_VMD_MSI, }; /** -- cgit v1.2.3 From 2fd602669ee6d749a7dc47b84b87cef1a5075999 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 26 Aug 2020 13:16:53 +0200 Subject: PCI/MSI: Provide pci_dev_has_special_msi_domain() helper Provide a helper function to check whether a PCI device is handled by a non-standard PCI/MSI domain. This will be used to exclude such devices which hang of a special bus, e.g. VMD, to be excluded from the irq domain override in irq remapping. Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200826112333.139387358@linutronix.de --- include/linux/msi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index 5aa126b7820b..a65cc47d0610 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -373,6 +373,7 @@ int pci_msi_domain_check_cap(struct irq_domain *domain, struct msi_domain_info *info, struct device *dev); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); +bool pci_dev_has_special_msi_domain(struct pci_dev *pdev); #else static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) { -- cgit v1.2.3 From 43e9e705dd57c466c4bfe32ab8c17db537b89297 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 26 Aug 2020 13:16:57 +0200 Subject: irqdomain/msi: Allow to override msi_domain_alloc/free_irqs() To support MSI irq domains which do not fit at all into the regular MSI irqdomain scheme, like the XEN MSI interrupt management for PV/HVM/DOM0, it's necessary to allow to override the alloc/free implementation. This is a preperatory step to switch X86 away from arch_*_msi_irqs() and store the irq domain pointer right in struct device. No functional change for existing MSI irq domain users. Aside of the evil XEN wrapper this is also useful for special MSI domains which need to do extra alloc/free work before/after calling the generic core function. Work like allocating/freeing MSI descriptors, MSI storage space etc. Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20200826112333.526797548@linutronix.de --- include/linux/msi.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index a65cc47d0610..0180534b5428 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -241,6 +241,10 @@ struct msi_domain_info; * @msi_finish: Optional callback to finalize the allocation * @set_desc: Set the msi descriptor for an interrupt * @handle_error: Optional error handler if the allocation fails + * @domain_alloc_irqs: Optional function to override the default allocation + * function. + * @domain_free_irqs: Optional function to override the default free + * function. * * @get_hwirq, @msi_init and @msi_free are callbacks used by * msi_create_irq_domain() and related interfaces @@ -248,6 +252,22 @@ struct msi_domain_info; * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error * are callbacks used by msi_domain_alloc_irqs() and related * interfaces which are based on msi_desc. + * + * @domain_alloc_irqs, @domain_free_irqs can be used to override the + * default allocation/free functions (__msi_domain_alloc/free_irqs). This + * is initially for a wrapper around XENs seperate MSI universe which can't + * be wrapped into the regular irq domains concepts by mere mortals. This + * allows to universally use msi_domain_alloc/free_irqs without having to + * special case XEN all over the place. + * + * Contrary to other operations @domain_alloc_irqs and @domain_free_irqs + * are set to the default implementation if NULL and even when + * MSI_FLAG_USE_DEF_DOM_OPS is not set to avoid breaking existing users and + * because these callbacks are obviously mandatory. + * + * This is NOT meant to be abused, but it can be useful to build wrappers + * for specialized MSI irq domains which need extra work before and after + * calling __msi_domain_alloc_irqs()/__msi_domain_free_irqs(). */ struct msi_domain_ops { irq_hw_number_t (*get_hwirq)(struct msi_domain_info *info, @@ -270,6 +290,10 @@ struct msi_domain_ops { struct msi_desc *desc); int (*handle_error)(struct irq_domain *domain, struct msi_desc *desc, int error); + int (*domain_alloc_irqs)(struct irq_domain *domain, + struct device *dev, int nvec); + void (*domain_free_irqs)(struct irq_domain *domain, + struct device *dev); }; /** @@ -327,8 +351,11 @@ int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); +int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, + int nvec); int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); +void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); -- cgit v1.2.3 From 85a8dfc57a0b96785881735e09a61a0fde911ca4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 26 Aug 2020 13:16:59 +0200 Subject: iommm/vt-d: Store irq domain in struct device As a first step to make X86 utilize the direct MSI irq domain operations store the irq domain pointer in the device struct when a device is probed. This is done from dmar_pci_bus_add_dev() because it has to work even when DMA remapping is disabled. It only overrides the irqdomain of devices which are handled by a regular PCI/MSI irq domain which protects PCI devices behind special busses like VMD which have their own irq domain. No functional change. It just avoids the redirection through arch_*_msi_irqs() and allows the PCI/MSI core to directly invoke the irq domain alloc/free functions instead of having to look up the irq domain for every single MSI interupt. Signed-off-by: Thomas Gleixner Acked-by: Joerg Roedel Link: https://lore.kernel.org/r/20200826112333.714566121@linutronix.de --- include/linux/intel-iommu.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b1ed2f25f7c0..46f5aaaa66ff 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -425,6 +425,8 @@ struct q_inval { int free_cnt; }; +struct dmar_pci_notify_info; + #ifdef CONFIG_IRQ_REMAP /* 1MB - maximum possible interrupt remapping table size */ #define INTR_REMAP_PAGE_ORDER 8 @@ -439,6 +441,11 @@ struct ir_table { struct irte *base; unsigned long *bitmap; }; + +void intel_irq_remap_add_device(struct dmar_pci_notify_info *info); +#else +static inline void +intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { } #endif struct iommu_flush { -- cgit v1.2.3 From 077ee78e392869e46ae6bdc6ba2a3c4249d0b5e1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 26 Aug 2020 13:17:02 +0200 Subject: PCI/MSI: Make arch_.*_msi_irq[s] fallbacks selectable The arch_.*_msi_irq[s] fallbacks are compiled in whether an architecture requires them or not. Architectures which are fully utilizing hierarchical irq domains should never call into that code. It's not only architectures which depend on that by implementing one or more of the weak functions, there is also a bunch of drivers which relies on the weak functions which invoke msi_controller::setup_irq[s] and msi_controller::teardown_irq. Make the architectures and drivers which rely on them select them in Kconfig and if not selected replace them by stub functions which emit a warning and fail the PCI/MSI interrupt allocation. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20200826112333.992429909@linutronix.de --- include/linux/msi.h | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index 0180534b5428..6b584cc4757c 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -193,17 +193,38 @@ void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); /* - * The arch hooks to setup up msi irqs. Those functions are - * implemented as weak symbols so that they /can/ be overriden by - * architecture specific code if needed. + * The arch hooks to setup up msi irqs. Default functions are implemented + * as weak symbols so that they /can/ be overriden by architecture specific + * code if needed. These hooks must be enabled by the architecture or by + * drivers which depend on them via msi_controller based MSI handling. + * + * If CONFIG_PCI_MSI_ARCH_FALLBACKS is not selected they are replaced by + * stubs with warnings. */ +#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); -void arch_restore_msi_irqs(struct pci_dev *dev); - void default_teardown_msi_irqs(struct pci_dev *dev); +#else +static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + WARN_ON_ONCE(1); + return -ENODEV; +} + +static inline void arch_teardown_msi_irqs(struct pci_dev *dev) +{ + WARN_ON_ONCE(1); +} +#endif + +/* + * The restore hooks are still available as they are useful even + * for fully irq domain based setups. Courtesy to XEN/X86. + */ +void arch_restore_msi_irqs(struct pci_dev *dev); void default_restore_msi_irqs(struct pci_dev *dev); struct msi_controller { -- cgit v1.2.3 From 7c920da30e04c2dd78d988e0cefb8e5bd2e48b26 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Tue, 8 Sep 2020 09:10:09 -0400 Subject: misc: fastrpc: fix indentation error in uapi header Use tabs instead of spaces. Fixes: 2419e55e532d ("misc: fastrpc: add mmap/unmap support") Signed-off-by: Jonathan Marek Link: https://lore.kernel.org/r/20200908131013.19630-2-jonathan@marek.ca Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/fastrpc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 07de2b7aac85..de31f0bd4779 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -10,8 +10,8 @@ #define FASTRPC_IOCTL_INVOKE _IOWR('R', 3, struct fastrpc_invoke) #define FASTRPC_IOCTL_INIT_ATTACH _IO('R', 4) #define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create) -#define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap) -#define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) +#define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap) +#define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) struct fastrpc_invoke_args { __u64 ptr; -- cgit v1.2.3 From 6010d9befc8df899b61378adfd153f0b53075092 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Tue, 8 Sep 2020 09:10:11 -0400 Subject: misc: fastrpc: add ioctl for attaching to sensors pd Initializing sensors requires attaching to pd 2. Add an ioctl for that. This corresponds to FASTRPC_INIT_ATTACH_SENSORS in the downstream driver. Signed-off-by: Jonathan Marek Link: https://lore.kernel.org/r/20200908131013.19630-4-jonathan@marek.ca Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/fastrpc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index de31f0bd4779..0a89f95463f6 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -12,6 +12,7 @@ #define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create) #define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap) #define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) +#define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8) struct fastrpc_invoke_args { __u64 ptr; -- cgit v1.2.3 From 58c909022a5a56cd1d9e89c8c5461fd1f6a27bb5 Mon Sep 17 00:00:00 2001 From: Lenny Szubowicz Date: Fri, 4 Sep 2020 21:31:05 -0400 Subject: efi: Support for MOK variable config table Because of system-specific EFI firmware limitations, EFI volatile variables may not be capable of holding the required contents of the Machine Owner Key (MOK) certificate store when the certificate list grows above some size. Therefore, an EFI boot loader may pass the MOK certs via a EFI configuration table created specifically for this purpose to avoid this firmware limitation. An EFI configuration table is a much more primitive mechanism compared to EFI variables and is well suited for one-way passage of static information from a pre-OS environment to the kernel. This patch adds initial kernel support to recognize, parse, and validate the EFI MOK configuration table, where named entries contain the same data that would otherwise be provided in similarly named EFI variables. Additionally, this patch creates a sysfs binary file for each EFI MOK configuration table entry found. These files are read-only to root and are provided for use by user space utilities such as mokutil. A subsequent patch will load MOK certs into the trusted platform key ring using this infrastructure. Signed-off-by: Lenny Szubowicz Link: https://lore.kernel.org/r/20200905013107.10457-2-lszubowi@redhat.com Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 73db1ae04cef..4a2332f146eb 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -357,6 +357,7 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_TPM_FINAL_LOG_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) +#define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -546,6 +547,7 @@ extern struct efi { unsigned long esrt; /* ESRT table */ unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ + unsigned long mokvar_table; /* MOK variable config table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1252,4 +1254,36 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size); char *efi_systab_show_arch(char *str); +/* + * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table can be provided + * to the kernel by an EFI boot loader. The table contains a packed + * sequence of these entries, one for each named MOK variable. + * The sequence is terminated by an entry with a completely NULL + * name and 0 data size. + */ +struct efi_mokvar_table_entry { + char name[256]; + u64 data_size; + u8 data[]; +} __attribute((packed)); + +#ifdef CONFIG_LOAD_UEFI_KEYS +extern void __init efi_mokvar_table_init(void); +extern struct efi_mokvar_table_entry *efi_mokvar_entry_next( + struct efi_mokvar_table_entry **mokvar_entry); +extern struct efi_mokvar_table_entry *efi_mokvar_entry_find(const char *name); +#else +static inline void efi_mokvar_table_init(void) { } +static inline struct efi_mokvar_table_entry *efi_mokvar_entry_next( + struct efi_mokvar_table_entry **mokvar_entry) +{ + return NULL; +} +static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find( + const char *name) +{ + return NULL; +} +#endif + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 8747f2022fe8d8029193707ee86ff5c792cbef9b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Sep 2020 12:32:00 +0200 Subject: cpuidle: Allow cpuidle drivers to take over RCU-idle Some drivers have to do significant work, some of which relies on RCU still being active. Instead of using RCU_NONIDLE in the drivers and flipping RCU back on, allow drivers to take over RCU-idle duty. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ulf Hansson Tested-by: Borislav Petkov Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 75895e6363b8..6175c77bf25e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -82,6 +82,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ #define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ #define CPUIDLE_FLAG_TLB_FLUSHED BIT(5) /* idle-state flushes TLBs */ +#define CPUIDLE_FLAG_RCU_IDLE BIT(6) /* idle-state takes care of RCU */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; -- cgit v1.2.3 From d8f0cd76684e679d4a8ec4929fcdf6c3a030a007 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Tue, 15 Sep 2020 14:02:58 +0200 Subject: iio: adis: Drop non Managed device functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop `adis_setup_buffer_and_trigger()`. All users were updated to use the devm version of this function. This avoids having almost the same code repeated. Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20200915120258.161587-11-nuno.sa@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 2df67448f0d1..01ba691da2f3 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -517,14 +517,8 @@ struct adis_burst { int devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, irq_handler_t trigger_handler); -int adis_setup_buffer_and_trigger(struct adis *adis, - struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *)); -void adis_cleanup_buffer_and_trigger(struct adis *adis, - struct iio_dev *indio_dev); int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); -int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); -void adis_remove_trigger(struct adis *adis); int adis_update_scan_mode(struct iio_dev *indio_dev, const unsigned long *scan_mask); @@ -538,33 +532,12 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, return 0; } -static inline int adis_setup_buffer_and_trigger(struct adis *adis, - struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *)) -{ - return 0; -} - -static inline void adis_cleanup_buffer_and_trigger(struct adis *adis, - struct iio_dev *indio_dev) -{ -} - static inline int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) { return 0; } -static inline int adis_probe_trigger(struct adis *adis, - struct iio_dev *indio_dev) -{ - return 0; -} - -static inline void adis_remove_trigger(struct adis *adis) -{ -} - #define adis_update_scan_mode NULL #endif /* CONFIG_IIO_BUFFER */ -- cgit v1.2.3 From ffbc3dd1975f1e2dac7b1752aa8b5cac3cd5b459 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 16 Sep 2020 23:18:43 +0300 Subject: fs: fix cast in fsparam_u32hex() macro Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro --- include/linux/fs_parser.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 2eab6d5f6736..aab0ffc6bac6 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -120,7 +120,7 @@ static inline bool fs_validate_description(const char *name, #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *16)) + __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) -- cgit v1.2.3 From aabf59432c51be174994ecfe280f75ac139b5550 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Sun, 6 Sep 2020 22:39:49 +0000 Subject: fs: Remove duplicated flag O_NDELAY occurring twice in VALID_OPEN_FLAGS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The O_NDELAY flag occurs twice in the VALID_OPEN_FLAGS definition, this change removes the duplicate. There is no change to the functionality. Note, that the flags O_NONBLOCK and O_NDELAY are not duplicates, as values of these flags are platform dependent, and on platforms like Sparc O_NONBLOCK and O_NDELAY are not the same. This has been done that way to maintain the ABI compatibility with Solaris since the Sparc port was first introduced. This change resolves the following Coccinelle warning: include/linux/fcntl.h:11:13-21: duplicated argument to & or | Signed-off-by: Krzysztof Wilczyński Signed-off-by: Al Viro --- include/linux/fcntl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 7bcdcf4f6ab2..921e750843e6 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -8,7 +8,7 @@ /* List of all valid flags for the open/openat flags argument: */ #define VALID_OPEN_FLAGS \ (O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \ - O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \ + O_APPEND | O_NDELAY | O_NONBLOCK | __O_SYNC | O_DSYNC | \ FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \ O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE) -- cgit v1.2.3 From ba3a86e47232ad9f76160929f33ac9c64e4d0567 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 14 Sep 2020 15:44:37 -0700 Subject: rcu-tasks: Fix grace-period/unlock race in RCU Tasks Trace The more intense grace-period processing resulting from the 50x RCU Tasks Trace grace-period speedups exposed the following race condition: o Task A running on CPU 0 executes rcu_read_lock_trace(), entering a read-side critical section. o When Task A eventually invokes rcu_read_unlock_trace() to exit its read-side critical section, this function notes that the ->trc_reader_special.s flag is zero and and therefore invoke wil set ->trc_reader_nesting to zero using WRITE_ONCE(). But before that happens... o The RCU Tasks Trace grace-period kthread running on some other CPU interrogates Task A, but this fails because this task is currently running. This kthread therefore sends an IPI to CPU 0. o CPU 0 receives the IPI, and thus invokes trc_read_check_handler(). Because Task A has not yet cleared its ->trc_reader_nesting counter, this function sees that Task A is still within its read-side critical section. This function therefore sets the ->trc_reader_nesting.b.need_qs flag, AKA the .need_qs flag. Except that Task A has already checked the .need_qs flag, which is part of the ->trc_reader_special.s flag. The .need_qs flag therefore remains set until Task A's next rcu_read_unlock_trace(). o Task A now invokes synchronize_rcu_tasks_trace(), which cannot start a new grace period until the current grace period completes. And thus cannot return until after that time. But Task A's .need_qs flag is still set, which prevents the current grace period from completing. And because Task A is blocked, it will never execute rcu_read_unlock_trace() until its call to synchronize_rcu_tasks_trace() returns. We are therefore deadlocked. This race is improbable, but 80 hours of rcutorture made it happen twice. The race was possible before the grace-period speedup, but roughly 50x less probable. Several thousand hours of rcutorture would have been necessary to have a reasonable chance of making this happen before this 50x speedup. This commit therefore eliminates this deadlock by setting ->trc_reader_nesting to a large negative number before checking the .need_qs and zeroing (or decrementing with respect to its initial value) ->trc_reader_nesting. For its part, the IPI handler's trc_read_check_handler() function adds a check for negative values, deferring evaluation of the task in this case. Taken together, these changes avoid this deadlock scenario. Fixes: 276c410448db ("rcu-tasks: Split ->trc_reader_need_end") Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Cc: # 5.7.x Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index d9015aac78c6..a6a6a3acab5a 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -50,6 +50,7 @@ static inline void rcu_read_lock_trace(void) struct task_struct *t = current; WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); + barrier(); if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && t->trc_reader_special.b.need_mb) smp_mb(); // Pairs with update-side barriers @@ -72,6 +73,9 @@ static inline void rcu_read_unlock_trace(void) rcu_lock_release(&rcu_trace_lock_map); nesting = READ_ONCE(t->trc_reader_nesting) - 1; + barrier(); // Critical section before disabling. + // Disable IPI-based setting of .need_qs. + WRITE_ONCE(t->trc_reader_nesting, INT_MIN); if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) { WRITE_ONCE(t->trc_reader_nesting, nesting); return; // We assume shallow reader nesting. -- cgit v1.2.3 From 9baf68cc4544056f33797b78ec09388f54ecc8f0 Mon Sep 17 00:00:00 2001 From: Alex Kluver Date: Wed, 19 Aug 2020 09:35:43 -0500 Subject: edac,ghes,cper: Add Row Extension to Memory Error Record Memory errors could be printed with incorrect row values since the DIMM size has outgrown the 16 bit row field in the CPER structure. UEFI Specification Version 2.8 has increased the size of row by allowing it to use the first 2 bits from a previously reserved space within the structure. When needed, add the extension bits to the row value printed. Based on UEFI 2.8 Table 299. Memory Error Record Signed-off-by: Alex Kluver Tested-by: Russ Anderson Reviewed-by: Steve Wahl Reviewed-by: Kyle Meyer Acked-by: Borislav Petkov Link: https://lore.kernel.org/r/20200819143544.155096-2-alex.kluver@hpe.com Signed-off-by: Ard Biesheuvel --- include/linux/cper.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cper.h b/include/linux/cper.h index 8537e9282a65..bd2d8a77a784 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -230,6 +230,10 @@ enum { #define CPER_MEM_VALID_RANK_NUMBER 0x8000 #define CPER_MEM_VALID_CARD_HANDLE 0x10000 #define CPER_MEM_VALID_MODULE_HANDLE 0x20000 +#define CPER_MEM_VALID_ROW_EXT 0x40000 + +#define CPER_MEM_EXT_ROW_MASK 0x3 +#define CPER_MEM_EXT_ROW_SHIFT 16 #define CPER_PCIE_VALID_PORT_TYPE 0x0001 #define CPER_PCIE_VALID_VERSION 0x0002 @@ -443,7 +447,7 @@ struct cper_sec_mem_err_old { u8 error_type; }; -/* Memory Error Section (UEFI >= v2.3), UEFI v2.7 sec N.2.5 */ +/* Memory Error Section (UEFI >= v2.3), UEFI v2.8 sec N.2.5 */ struct cper_sec_mem_err { u64 validation_bits; u64 error_status; @@ -461,7 +465,7 @@ struct cper_sec_mem_err { u64 responder_id; u64 target_id; u8 error_type; - u8 reserved; + u8 extended; u16 rank; u16 mem_array_handle; /* "card handle" in UEFI 2.4 */ u16 mem_dev_handle; /* "module handle" in UEFI 2.4 */ @@ -483,8 +487,16 @@ struct cper_mem_err_compact { u16 rank; u16 mem_array_handle; u16 mem_dev_handle; + u8 extended; }; +static inline u32 cper_get_mem_extension(u64 mem_valid, u8 mem_extended) +{ + if (!(mem_valid & CPER_MEM_VALID_ROW_EXT)) + return 0; + return (mem_extended & CPER_MEM_EXT_ROW_MASK) << CPER_MEM_EXT_ROW_SHIFT; +} + /* PCI Express Error Section, UEFI v2.7 sec N.2.7 */ struct cper_sec_pcie { u64 validation_bits; -- cgit v1.2.3 From 612b5d506d066cdf0a739963e7cd28642d500ec1 Mon Sep 17 00:00:00 2001 From: Alex Kluver Date: Wed, 19 Aug 2020 09:35:44 -0500 Subject: cper,edac,efi: Memory Error Record: bank group/address and chip id Updates to the UEFI 2.8 Memory Error Record allow splitting the bank field into bank address and bank group, and using the last 3 bits of the extended field as a chip identifier. When needed, print correct version of bank field, bank group, and chip identification. Based on UEFI 2.8 Table 299. Memory Error Record. Signed-off-by: Alex Kluver Reviewed-by: Russ Anderson Reviewed-by: Kyle Meyer Reviewed-by: Steve Wahl Acked-by: Borislav Petkov Link: https://lore.kernel.org/r/20200819143544.155096-3-alex.kluver@hpe.com Signed-off-by: Ard Biesheuvel --- include/linux/cper.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/cper.h b/include/linux/cper.h index bd2d8a77a784..6a511a1078ca 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -231,10 +231,18 @@ enum { #define CPER_MEM_VALID_CARD_HANDLE 0x10000 #define CPER_MEM_VALID_MODULE_HANDLE 0x20000 #define CPER_MEM_VALID_ROW_EXT 0x40000 +#define CPER_MEM_VALID_BANK_GROUP 0x80000 +#define CPER_MEM_VALID_BANK_ADDRESS 0x100000 +#define CPER_MEM_VALID_CHIP_ID 0x200000 #define CPER_MEM_EXT_ROW_MASK 0x3 #define CPER_MEM_EXT_ROW_SHIFT 16 +#define CPER_MEM_BANK_ADDRESS_MASK 0xff +#define CPER_MEM_BANK_GROUP_SHIFT 8 + +#define CPER_MEM_CHIP_ID_SHIFT 5 + #define CPER_PCIE_VALID_PORT_TYPE 0x0001 #define CPER_PCIE_VALID_VERSION 0x0002 #define CPER_PCIE_VALID_COMMAND_STATUS 0x0004 -- cgit v1.2.3 From 36183150e086977cadcffba84ecd84cbbeec9324 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 15 Sep 2020 16:29:26 +0200 Subject: drm/ttm: some cleanups MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Unexport ttm_check_under_lowerlimit. Make ttm_bo_acc_size static and unexport it. Remove ttm_get_kernel_zone_memory_size. Signed-off-by: Christian König Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/390515/ --- include/drm/ttm/ttm_bo_api.h | 12 ------------ include/drm/ttm/ttm_memory.h | 1 - 2 files changed, 13 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 1d20a7f15a7a..89ad6f213fc0 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -353,18 +353,6 @@ void ttm_bo_unlock_delayed_workqueue(struct ttm_bo_device *bdev, int resched); bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place); -/** - * ttm_bo_acc_size - * - * @bdev: Pointer to a ttm_bo_device struct. - * @bo_size: size of the buffer object in byte. - * @struct_size: size of the structure holding buffer object datas - * - * Returns size to account for a buffer object - */ -size_t ttm_bo_acc_size(struct ttm_bo_device *bdev, - unsigned long bo_size, - unsigned struct_size); size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev, unsigned long bo_size, unsigned struct_size); diff --git a/include/drm/ttm/ttm_memory.h b/include/drm/ttm/ttm_memory.h index c78ea99c42cf..2d468d7c94e6 100644 --- a/include/drm/ttm/ttm_memory.h +++ b/include/drm/ttm/ttm_memory.h @@ -91,7 +91,6 @@ extern int ttm_mem_global_alloc_page(struct ttm_mem_global *glob, extern void ttm_mem_global_free_page(struct ttm_mem_global *glob, struct page *page, uint64_t size); extern size_t ttm_round_pot(size_t size); -extern uint64_t ttm_get_kernel_zone_memory_size(struct ttm_mem_global *glob); extern bool ttm_check_under_lowerlimit(struct ttm_mem_global *glob, uint64_t num_pages, struct ttm_operation_ctx *ctx); #endif -- cgit v1.2.3 From 3f1cc53b5f6f26e80e3176936714ec5dcab74244 Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Tue, 11 Aug 2020 17:12:50 +0200 Subject: clk: samsung: exynos5420: Add definition of clock ID for mout_sw_aclk_g3d This patch adds ID for the mout_sw_aclk_g3d (SW_CLKMUX_ACLK_G3D) clock, mostly for internal use in the CMU driver. It will allow to avoid the __clk_lookup() call when setting up the clock during the clock provider initialization. Link: https://lore.kernel.org/r/20200811151251.31613-1-s.nawrocki@samsung.com Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5420.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5420.h b/include/dt-bindings/clock/exynos5420.h index 02d5ac469a3d..ff917c818f05 100644 --- a/include/dt-bindings/clock/exynos5420.h +++ b/include/dt-bindings/clock/exynos5420.h @@ -230,6 +230,7 @@ #define CLK_MOUT_USER_MAU_EPLL 659 #define CLK_MOUT_SCLK_SPLL 660 #define CLK_MOUT_MX_MSPLL_CCORE_PHY 661 +#define CLK_MOUT_SW_ACLK_G3D 662 /* divider clocks */ #define CLK_DOUT_PIXEL 768 -- cgit v1.2.3 From f493602db56beee1514b37180599a1f3f66f816e Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Wed, 26 Aug 2020 19:15:27 +0200 Subject: clk: samsung: Add clk ID definitions for the CPU parent clocks Add clock ID definitions for the CPU parent clocks for SoCs which don't have such definitions yet. This will allow us to reference the parent clocks directly by cached struct clk_hw pointers in the clock provider, rather than doing clk lookup by name. Reviewed-by: Krzysztof Kozlowski Acked-by: Chanwoo Choi Acked-by: Rob Herring Link: https://lore.kernel.org/r/20200826171529.23618-1-s.nawrocki@samsung.com Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5250.h | 4 +++- include/dt-bindings/clock/exynos5420.h | 5 +++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5250.h b/include/dt-bindings/clock/exynos5250.h index bc8a3c53a54b..e259cc01f22f 100644 --- a/include/dt-bindings/clock/exynos5250.h +++ b/include/dt-bindings/clock/exynos5250.h @@ -172,8 +172,10 @@ #define CLK_MOUT_GPLL 1025 #define CLK_MOUT_ACLK200_DISP1_SUB 1026 #define CLK_MOUT_ACLK300_DISP1_SUB 1027 +#define CLK_MOUT_APLL 1028 +#define CLK_MOUT_MPLL 1029 /* must be greater than maximal clock id */ -#define CLK_NR_CLKS 1028 +#define CLK_NR_CLKS 1030 #endif /* _DT_BINDINGS_CLOCK_EXYNOS_5250_H */ diff --git a/include/dt-bindings/clock/exynos5420.h b/include/dt-bindings/clock/exynos5420.h index ff917c818f05..9fffc6ceaadd 100644 --- a/include/dt-bindings/clock/exynos5420.h +++ b/include/dt-bindings/clock/exynos5420.h @@ -231,6 +231,11 @@ #define CLK_MOUT_SCLK_SPLL 660 #define CLK_MOUT_MX_MSPLL_CCORE_PHY 661 #define CLK_MOUT_SW_ACLK_G3D 662 +#define CLK_MOUT_APLL 663 +#define CLK_MOUT_MSPLL_CPU 664 +#define CLK_MOUT_KPLL 665 +#define CLK_MOUT_MSPLL_KFC 666 + /* divider clocks */ #define CLK_DOUT_PIXEL 768 -- cgit v1.2.3 From e5e1065f922380ced35e6b6ec3c58c28f57b74fd Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Thu, 17 Sep 2020 10:04:32 +0800 Subject: drm: fix spelling error in comments Change the comment typo: "manger" -> "manager". Signed-off-by: Wang Qing Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/1600308275-32094-1-git-send-email-wangqing@vivo.com --- include/drm/drm_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h index a01bc6fac83c..9b4292f229c6 100644 --- a/include/drm/drm_mm.h +++ b/include/drm/drm_mm.h @@ -338,7 +338,7 @@ static inline u64 drm_mm_hole_node_end(const struct drm_mm_node *hole_node) /** * drm_mm_nodes - list of nodes under the drm_mm range manager - * @mm: the struct drm_mm range manger + * @mm: the struct drm_mm range manager * * As the drm_mm range manager hides its node_list deep with its * structure, extracting it looks painful and repetitive. This is -- cgit v1.2.3 From a77ed90da6bb4062e3d8bc6daaa200a5494c7b0e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:39 +0300 Subject: drm/dp: Define protocol converter DPCD registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DP 1.3 and 1.4 introduced some new registers for DP->HDMI protocol converters. Define those. Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-4-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 5c45195ced32..17d32d7632b6 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -984,6 +984,16 @@ #define DP_CEC_TX_MESSAGE_BUFFER 0x3020 #define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 +#define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ +# define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR420_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_HDMI_EDID_PROCESSING_DISABLE (1 << 1) /* DP 1.4 */ +# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE (1 << 2) /* DP 1.4 */ +# define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ + #define DP_AUX_HDCP_BKSV 0x68000 #define DP_AUX_HDCP_RI_PRIME 0x68005 #define DP_AUX_HDCP_AKSV 0x68007 -- cgit v1.2.3 From 57d6a6851f05bf594d2918888c350347fb0c2eef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:40 +0300 Subject: drm/dp: Define more downstream facing port caps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Our definitions for the DPCD DFP capabilities are lacking. Add the missing bits. Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-5-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 17d32d7632b6..86461a40066b 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -386,12 +386,18 @@ # define DP_DS_PORT_TYPE_WIRELESS 6 # define DP_DS_PORT_HPD (1 << 3) /* offset 1 for VGA is maximum megapixels per second / 8 */ -/* offset 2 */ +/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ +/* offset 2 for VGA/DVI/HDMI */ # define DP_DS_MAX_BPC_MASK (3 << 0) # define DP_DS_8BPC 0 # define DP_DS_10BPC 1 # define DP_DS_12BPC 2 # define DP_DS_16BPC 3 +/* offset 3 for DVI */ +# define DP_DS_DVI_DUAL_LINK (1 << 1) +# define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) +/* offset 3 for HDMI */ +# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) #define DP_MAX_DOWNSTREAM_PORTS 0x10 -- cgit v1.2.3 From 38784f6f880580cbe168edbe7ba38c161dee3216 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:42 +0300 Subject: drm/dp: Add helpers to identify downstream facing port types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a few helpers to let us better identify which kind of DFP we're dealing with. v2: Use Returns: for kdoc (Lyude) Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-7-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 86461a40066b..4f946826dfce 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1638,6 +1638,11 @@ bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, int drm_dp_read_downstream_info(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]); +bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], u8 type); +bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4]); int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], -- cgit v1.2.3 From 42f2562ca1b52810415107d919535c552196384e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:43 +0300 Subject: drm/dp: Pimp drm_dp_downstream_max_bpc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Deal with more cases in drm_dp_downstream_max_bpc(): - DPCD 1.0 -> assume 8bpc for non-DP - DPCD 1.1+ DP (or DP++ with DP sink) -> allow anything - DPCD 1.1+ TMDS -> check the caps, assume 8bpc if the value is crap - anything else -> assume 8bpc v2: Use Returns: for kdoc (Lyude) Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-8-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 4f946826dfce..6218de1294c1 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1646,10 +1646,14 @@ bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4]); int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); + const u8 port_cap[4], + const struct edid *edid); int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); -void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], struct drm_dp_aux *aux); +void drm_dp_downstream_debug(struct seq_file *m, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid, + struct drm_dp_aux *aux); enum drm_mode_subconnector drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4]); -- cgit v1.2.3 From 67d6a8b358eac488112a4775f77dc3dbf63bea88 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 16 Sep 2020 15:31:28 +0200 Subject: drm/ttm: remove superflous extern attribute from funcs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extern is the default attribute for functions anyway. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/390972/ --- include/drm/ttm/ttm_execbuf_util.h | 19 ++++++++----------- include/drm/ttm/ttm_memory.h | 25 ++++++++++++------------- 2 files changed, 20 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h index 5a19843bb80d..a99d7fdf2964 100644 --- a/include/drm/ttm/ttm_execbuf_util.h +++ b/include/drm/ttm/ttm_execbuf_util.h @@ -58,9 +58,8 @@ struct ttm_validate_buffer { * Undoes all buffer validation reservations for bos pointed to by * the list entries. */ - -extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket, - struct list_head *list); +void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket, + struct list_head *list); /** * function ttm_eu_reserve_buffers @@ -96,10 +95,9 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket, * ttm_eu_fence_buffer_objects() when command submission is complete or * has failed. */ - -extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, - struct list_head *list, bool intr, - struct list_head *dups); +int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, + struct list_head *list, bool intr, + struct list_head *dups); /** * function ttm_eu_fence_buffer_objects. @@ -113,9 +111,8 @@ extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, * It also unreserves all buffers, putting them on lru lists. * */ - -extern void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket, - struct list_head *list, - struct dma_fence *fence); +void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket, + struct list_head *list, + struct dma_fence *fence); #endif diff --git a/include/drm/ttm/ttm_memory.h b/include/drm/ttm/ttm_memory.h index 2d468d7c94e6..c1f167881e33 100644 --- a/include/drm/ttm/ttm_memory.h +++ b/include/drm/ttm/ttm_memory.h @@ -79,18 +79,17 @@ extern struct ttm_mem_global { #endif } ttm_mem_glob; -extern int ttm_mem_global_init(struct ttm_mem_global *glob); -extern void ttm_mem_global_release(struct ttm_mem_global *glob); -extern int ttm_mem_global_alloc(struct ttm_mem_global *glob, uint64_t memory, +int ttm_mem_global_init(struct ttm_mem_global *glob); +void ttm_mem_global_release(struct ttm_mem_global *glob); +int ttm_mem_global_alloc(struct ttm_mem_global *glob, uint64_t memory, + struct ttm_operation_ctx *ctx); +void ttm_mem_global_free(struct ttm_mem_global *glob, uint64_t amount); +int ttm_mem_global_alloc_page(struct ttm_mem_global *glob, + struct page *page, uint64_t size, + struct ttm_operation_ctx *ctx); +void ttm_mem_global_free_page(struct ttm_mem_global *glob, + struct page *page, uint64_t size); +size_t ttm_round_pot(size_t size); +bool ttm_check_under_lowerlimit(struct ttm_mem_global *glob, uint64_t num_pages, struct ttm_operation_ctx *ctx); -extern void ttm_mem_global_free(struct ttm_mem_global *glob, - uint64_t amount); -extern int ttm_mem_global_alloc_page(struct ttm_mem_global *glob, - struct page *page, uint64_t size, - struct ttm_operation_ctx *ctx); -extern void ttm_mem_global_free_page(struct ttm_mem_global *glob, - struct page *page, uint64_t size); -extern size_t ttm_round_pot(size_t size); -extern bool ttm_check_under_lowerlimit(struct ttm_mem_global *glob, - uint64_t num_pages, struct ttm_operation_ctx *ctx); #endif -- cgit v1.2.3 From 6eab771472af50e11a484d56ba444e2ec82e9126 Mon Sep 17 00:00:00 2001 From: Karol Trzcinski Date: Thu, 17 Sep 2020 13:56:27 +0300 Subject: ASoC: SOF: Add `src_hash` to `sof_ipc_fw_version` structure This field will be used to compare ldc file with loaded fw version, to assert validity of trace logs. Value used in sof-logger. Signed-off-by: Karol Trzcinski Reviewed-by: Guennadi Liakhovetski Reviewed-by: Pierre-Louis Bossart Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200917105633.2579047-3-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/info.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h index 313e3e70c630..0b7101aef596 100644 --- a/include/sound/sof/info.h +++ b/include/sound/sof/info.h @@ -46,9 +46,11 @@ struct sof_ipc_fw_version { uint8_t time[10]; uint8_t tag[6]; uint32_t abi_version; + /* used to check FW and ldc file compatibility, reproducible value */ + uint32_t src_hash; /* reserved for future use */ - uint32_t reserved[4]; + uint32_t reserved[3]; } __packed; /* FW ready Message - sent by firmware when boot has completed */ -- cgit v1.2.3 From 4e398353a7e51410c34fd19f8b7dfc56fff5901b Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 10 Sep 2020 14:57:07 +0100 Subject: ASoC: q6afe: dt-bindings: add q6afe clock bindings q6afe exposes various lpass clocks controls via q6dsp q6afe commands. This patch adds bindings required for this clock controller. Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20200910135708.14842-2-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- include/dt-bindings/sound/qcom,q6afe.h | 74 +++++++++++++++++++++++++++++++++- 1 file changed, 73 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/sound/qcom,q6afe.h b/include/dt-bindings/sound/qcom,q6afe.h index 7207ab2b57bf..f64b5d2e6efd 100644 --- a/include/dt-bindings/sound/qcom,q6afe.h +++ b/include/dt-bindings/sound/qcom,q6afe.h @@ -130,5 +130,77 @@ #define RX_CODEC_DMA_RX_6 125 #define RX_CODEC_DMA_RX_7 126 -#endif /* __DT_BINDINGS_Q6_AFE_H__ */ +#define LPASS_CLK_ID_PRI_MI2S_IBIT 1 +#define LPASS_CLK_ID_PRI_MI2S_EBIT 2 +#define LPASS_CLK_ID_SEC_MI2S_IBIT 3 +#define LPASS_CLK_ID_SEC_MI2S_EBIT 4 +#define LPASS_CLK_ID_TER_MI2S_IBIT 5 +#define LPASS_CLK_ID_TER_MI2S_EBIT 6 +#define LPASS_CLK_ID_QUAD_MI2S_IBIT 7 +#define LPASS_CLK_ID_QUAD_MI2S_EBIT 8 +#define LPASS_CLK_ID_SPEAKER_I2S_IBIT 9 +#define LPASS_CLK_ID_SPEAKER_I2S_EBIT 10 +#define LPASS_CLK_ID_SPEAKER_I2S_OSR 11 +#define LPASS_CLK_ID_QUI_MI2S_IBIT 12 +#define LPASS_CLK_ID_QUI_MI2S_EBIT 13 +#define LPASS_CLK_ID_SEN_MI2S_IBIT 14 +#define LPASS_CLK_ID_SEN_MI2S_EBIT 15 +#define LPASS_CLK_ID_INT0_MI2S_IBIT 16 +#define LPASS_CLK_ID_INT1_MI2S_IBIT 17 +#define LPASS_CLK_ID_INT2_MI2S_IBIT 18 +#define LPASS_CLK_ID_INT3_MI2S_IBIT 19 +#define LPASS_CLK_ID_INT4_MI2S_IBIT 20 +#define LPASS_CLK_ID_INT5_MI2S_IBIT 21 +#define LPASS_CLK_ID_INT6_MI2S_IBIT 22 +#define LPASS_CLK_ID_QUI_MI2S_OSR 23 +#define LPASS_CLK_ID_PRI_PCM_IBIT 24 +#define LPASS_CLK_ID_PRI_PCM_EBIT 25 +#define LPASS_CLK_ID_SEC_PCM_IBIT 26 +#define LPASS_CLK_ID_SEC_PCM_EBIT 27 +#define LPASS_CLK_ID_TER_PCM_IBIT 28 +#define LPASS_CLK_ID_TER_PCM_EBIT 29 +#define LPASS_CLK_ID_QUAD_PCM_IBIT 30 +#define LPASS_CLK_ID_QUAD_PCM_EBIT 31 +#define LPASS_CLK_ID_QUIN_PCM_IBIT 32 +#define LPASS_CLK_ID_QUIN_PCM_EBIT 33 +#define LPASS_CLK_ID_QUI_PCM_OSR 34 +#define LPASS_CLK_ID_PRI_TDM_IBIT 35 +#define LPASS_CLK_ID_PRI_TDM_EBIT 36 +#define LPASS_CLK_ID_SEC_TDM_IBIT 37 +#define LPASS_CLK_ID_SEC_TDM_EBIT 38 +#define LPASS_CLK_ID_TER_TDM_IBIT 39 +#define LPASS_CLK_ID_TER_TDM_EBIT 40 +#define LPASS_CLK_ID_QUAD_TDM_IBIT 41 +#define LPASS_CLK_ID_QUAD_TDM_EBIT 42 +#define LPASS_CLK_ID_QUIN_TDM_IBIT 43 +#define LPASS_CLK_ID_QUIN_TDM_EBIT 44 +#define LPASS_CLK_ID_QUIN_TDM_OSR 45 +#define LPASS_CLK_ID_MCLK_1 46 +#define LPASS_CLK_ID_MCLK_2 47 +#define LPASS_CLK_ID_MCLK_3 48 +#define LPASS_CLK_ID_MCLK_4 49 +#define LPASS_CLK_ID_INTERNAL_DIGITAL_CODEC_CORE 50 +#define LPASS_CLK_ID_INT_MCLK_0 51 +#define LPASS_CLK_ID_INT_MCLK_1 52 +#define LPASS_CLK_ID_MCLK_5 53 +#define LPASS_CLK_ID_WSA_CORE_MCLK 54 +#define LPASS_CLK_ID_WSA_CORE_NPL_MCLK 55 +#define LPASS_CLK_ID_VA_CORE_MCLK 56 +#define LPASS_CLK_ID_TX_CORE_MCLK 57 +#define LPASS_CLK_ID_TX_CORE_NPL_MCLK 58 +#define LPASS_CLK_ID_RX_CORE_MCLK 59 +#define LPASS_CLK_ID_RX_CORE_NPL_MCLK 60 +#define LPASS_CLK_ID_VA_CORE_2X_MCLK 61 + +#define LPASS_HW_AVTIMER_VOTE 101 +#define LPASS_HW_MACRO_VOTE 102 +#define LPASS_HW_DCODEC_VOTE 103 + +#define Q6AFE_MAX_CLK_ID 104 +#define LPASS_CLK_ATTRIBUTE_INVALID 0x0 +#define LPASS_CLK_ATTRIBUTE_COUPLE_NO 0x1 +#define LPASS_CLK_ATTRIBUTE_COUPLE_DIVIDEND 0x2 +#define LPASS_CLK_ATTRIBUTE_COUPLE_DIVISOR 0x3 + +#endif /* __DT_BINDINGS_Q6_AFE_H__ */ -- cgit v1.2.3 From b770e84311451506d822574595631009267c7e78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:44 +0300 Subject: drm/dp: Redo drm_dp_downstream_max_clock() as drm_dp_downstream_max_dotclock() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We want to differentiate between the DFP dotclock and TMDS clock limits. Let's convert the current thing to just give us the dotclock limit. v2: Use Returns: for kdoc (Lyude) Fix up nouveau code too Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-9-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 6218de1294c1..19bc04207788 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1643,8 +1643,8 @@ bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4], const struct edid *edid); -int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); +int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4], const struct edid *edid); -- cgit v1.2.3 From 6509ca051abf4ff60d63732badcb2173a715f741 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:46 +0300 Subject: drm/dp: Add drm_dp_downstream_{min,max}_tmds_clock() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add helpers to get the TMDS clock limits for HDMI/DVI downstream facing ports. Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-11-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 19bc04207788..6812a3e0de8d 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1645,6 +1645,12 @@ bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const struct edid *edid); int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4]); +int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4], const struct edid *edid); -- cgit v1.2.3 From 7af655bce275f49b200b552921e55673624943c5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:49 +0300 Subject: drm/dp: Add drm_dp_downstream_mode() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The downstream facing port caps in the DPCD can give us a hint as to what kind of display mode the sink can use if it doesn't have an EDID. Use that information to pick a suitable mode. v2: Use Returns: for kdoc (Lyude) Add kdocs for drm_display_mode_from_cea_vic() (Lyude) Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-14-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 12 ++++++++++++ include/drm/drm_edid.h | 4 ++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 6812a3e0de8d..fbba4a0f7366 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -28,6 +28,8 @@ #include #include +struct drm_device; + /* * Unless otherwise noted, all values are from the DP 1.1a spec. Note that * DP and DPCD versions are independent. Differences from 1.0 are not noted, @@ -385,6 +387,13 @@ # define DP_DS_PORT_TYPE_DP_DUALMODE 5 # define DP_DS_PORT_TYPE_WIRELESS 6 # define DP_DS_PORT_HPD (1 << 3) +# define DP_DS_NON_EDID_MASK (0xf << 4) +# define DP_DS_NON_EDID_720x480i_60 (1 << 4) +# define DP_DS_NON_EDID_720x480i_50 (2 << 4) +# define DP_DS_NON_EDID_1920x1080i_60 (3 << 4) +# define DP_DS_NON_EDID_1920x1080i_50 (4 << 4) +# define DP_DS_NON_EDID_1280x720_60 (5 << 4) +# define DP_DS_NON_EDID_1280x720_50 (7 << 4) /* offset 1 for VGA is maximum megapixels per second / 8 */ /* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ /* offset 2 for VGA/DVI/HDMI */ @@ -1654,6 +1663,9 @@ int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4], const struct edid *edid); +struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE], diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index cfa4f5af49af..b27a0e2169c8 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -517,4 +517,8 @@ void drm_edid_get_monitor_name(struct edid *edid, char *name, struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev, int hsize, int vsize, int fresh, bool rb); +struct drm_display_mode * +drm_display_mode_from_cea_vic(struct drm_device *dev, + u8 video_code); + #endif /* __DRM_EDID_H__ */ -- cgit v1.2.3 From 2ef8d0f7de0ec0bc30c48e5f544a6082eb03e9f7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 4 Sep 2020 14:53:53 +0300 Subject: drm/dp: Add helpers for DFP YCbCr 4:2:0 handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add helpers to determine whether the DFP supports YCbCr 4:2:0 passthrough or YCbCr 4:4:4->4:2:0 conversion. v2: Add kdocs (Lyude) Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-18-ville.syrjala@linux.intel.com Reviewed-by: Lyude Paul Acked-by: Daniel Vetter --- include/drm/drm_dp_helper.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index fbba4a0f7366..c9f2851904d0 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -407,6 +407,10 @@ struct drm_device; # define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) /* offset 3 for HDMI */ # define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) +# define DP_DS_HDMI_YCBCR422_PASS_THROUGH (1 << 1) +# define DP_DS_HDMI_YCBCR420_PASS_THROUGH (1 << 2) +# define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) +# define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) #define DP_MAX_DOWNSTREAM_PORTS 0x10 @@ -1663,6 +1667,10 @@ int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4], const struct edid *edid); +bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev, const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4]); -- cgit v1.2.3 From 639bf4415cadff4c18e13aa5cb0dba2d443e3aa7 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Thu, 17 Sep 2020 12:02:21 +0300 Subject: net/mlx5: Refactor query port speed functions The functions mlx5_query_port_link_width_oper and mlx5_query_port_ib_proto_oper are always called together, so combine them to a new function called mlx5_query_port_oper to avoid duplication. And while the mlx5i_get_port_settings is the same as mlx5_query_port_oper therefore let's remove it. According to the IB spec link_width_oper and ib_proto_oper should be u16 and not as written u8, so perform casting as a preparation to cross-RDMA patch which will fix that type for all drivers in the RDMA subsystem. Fixes: ada68c31ba9c ("net/mlx5: Introduce a new header file for physical port functions") Signed-off-by: Aharon Landau Reviewed-by: Michael Guralnik Signed-off-by: Leon Romanovsky --- include/linux/mlx5/port.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 2d45a6af52a4..4d33ae0c2d97 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -133,10 +133,9 @@ enum mlx5e_connector_type { int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int ptys_size, int proto_mask, u8 local_port); -int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, - u8 *link_width_oper, u8 local_port); -int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, - u8 *proto_oper, u8 local_port); + +int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper, + u16 *proto_oper, u8 local_port); void mlx5_toggle_port_link(struct mlx5_core_dev *dev); int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status status); -- cgit v1.2.3 From e27014bdb47eb435f78573685f4196c07329f1f7 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Thu, 17 Sep 2020 12:02:22 +0300 Subject: RDMA/mlx5: Delete duplicated mlx5_ptys_width enum Combine two same enums to avoid duplication. Signed-off-by: Aharon Landau Reviewed-by: Michael Guralnik Signed-off-by: Leon Romanovsky --- include/linux/mlx5/port.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 4d33ae0c2d97..23edd2db4803 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -125,6 +125,14 @@ enum mlx5e_connector_type { MLX5E_CONNECTOR_TYPE_NUMBER, }; +enum mlx5_ptys_width { + MLX5_PTYS_WIDTH_1X = 1 << 0, + MLX5_PTYS_WIDTH_2X = 1 << 1, + MLX5_PTYS_WIDTH_4X = 1 << 2, + MLX5_PTYS_WIDTH_8X = 1 << 3, + MLX5_PTYS_WIDTH_12X = 1 << 4, +}; + #define MLX5E_PROT_MASK(link_mode) (1 << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ -- cgit v1.2.3 From f959dcd6ddfd29235030e8026471ac1b022ad2b0 Mon Sep 17 00:00:00 2001 From: Thomas Tai Date: Thu, 17 Sep 2020 18:43:03 +0200 Subject: dma-direct: Fix potential NULL pointer dereference When booting the kernel v5.9-rc4 on a VM, the kernel would panic when printing a warning message in swiotlb_map(). The dev->dma_mask must not be a NULL pointer when calling the dma mapping layer. A NULL pointer check can potentially avoid the panic. Signed-off-by: Thomas Tai Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 805010ea5346..2929685e88aa 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -62,9 +62,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, { dma_addr_t end = addr + size - 1; - if (!dev->dma_mask) - return false; - if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) return false; -- cgit v1.2.3 From e0d072782c734d27f5af062c62266f2598f68542 Mon Sep 17 00:00:00 2001 From: Jim Quinlan Date: Thu, 17 Sep 2020 18:43:40 +0200 Subject: dma-mapping: introduce DMA range map, supplanting dma_pfn_offset The new field 'dma_range_map' in struct device is used to facilitate the use of single or multiple offsets between mapping regions of cpu addrs and dma addrs. It subsumes the role of "dev->dma_pfn_offset" which was only capable of holding a single uniform offset and had no region bounds checking. The function of_dma_get_range() has been modified so that it takes a single argument -- the device node -- and returns a map, NULL, or an error code. The map is an array that holds the information regarding the DMA regions. Each range entry contains the address offset, the cpu_start address, the dma_start address, and the size of the region. of_dma_configure() is the typical manner to set range offsets but there are a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel driver code. These cases now invoke the function dma_direct_set_offset(dev, cpu_addr, dma_addr, size). Signed-off-by: Jim Quinlan [hch: various interface cleanups] Signed-off-by: Christoph Hellwig Reviewed-by: Mathieu Poirier Tested-by: Mathieu Poirier Tested-by: Nathan Chancellor --- include/linux/device.h | 4 ++-- include/linux/dma-direct.h | 53 ++++++++++++++++++++++++++++++++++++++++----- include/linux/dma-mapping.h | 9 +++++++- 3 files changed, 57 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index ca18da4768e3..1c78621fc3c0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -466,7 +466,7 @@ struct dev_links_info { * such descriptors. * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller * DMA limit than the device itself supports. - * @dma_pfn_offset: offset of DMA memory range relatively of RAM + * @dma_range_map: map for DMA memory ranges relative to that of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. * @dma_pools: Dma pools (if dma'ble device). @@ -561,7 +561,7 @@ struct device { 64 bit addresses for consistent allocations such descriptors. */ u64 bus_dma_limit; /* upstream dma constraint */ - unsigned long dma_pfn_offset; + const struct bus_dma_region *dma_range_map; struct device_dma_parameters *dma_parms; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 2929685e88aa..83f797e0cb78 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -14,6 +14,41 @@ extern unsigned int zone_dma_bits; +/* + * Record the mapping of CPU physical to DMA addresses for a given region. + */ +struct bus_dma_region { + phys_addr_t cpu_start; + dma_addr_t dma_start; + u64 size; + u64 offset; +}; + +static inline dma_addr_t translate_phys_to_dma(struct device *dev, + phys_addr_t paddr) +{ + const struct bus_dma_region *m; + + for (m = dev->dma_range_map; m->size; m++) + if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size) + return (dma_addr_t)paddr - m->offset; + + /* make sure dma_capable fails when no translation is available */ + return DMA_MAPPING_ERROR; +} + +static inline phys_addr_t translate_dma_to_phys(struct device *dev, + dma_addr_t dma_addr) +{ + const struct bus_dma_region *m; + + for (m = dev->dma_range_map; m->size; m++) + if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size) + return (phys_addr_t)dma_addr + m->offset; + + return (phys_addr_t)-1; +} + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #ifndef phys_to_dma_unencrypted @@ -23,9 +58,9 @@ extern unsigned int zone_dma_bits; static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev, phys_addr_t paddr) { - dma_addr_t dev_addr = (dma_addr_t)paddr; - - return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); + if (dev->dma_range_map) + return translate_phys_to_dma(dev, paddr); + return paddr; } /* @@ -39,10 +74,14 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) return __sme_set(phys_to_dma_unencrypted(dev, paddr)); } -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr) { - phys_addr_t paddr = (phys_addr_t)dev_addr + - ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); + phys_addr_t paddr; + + if (dev->dma_range_map) + paddr = translate_dma_to_phys(dev, dma_addr); + else + paddr = dma_addr; return __sme_clr(paddr); } @@ -62,6 +101,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, { dma_addr_t end = addr + size - 1; + if (addr == DMA_MAPPING_ERROR) + return false; if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) return false; diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index df0bff2ea750..bb138ac6f5e6 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -730,4 +730,11 @@ static inline int dma_mmap_wc(struct device *dev, #define dma_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) #endif -#endif +/* + * Legacy interface to set up the dma offset map. Drivers really should not + * actually use it, but we have a few legacy cases left. + */ +int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start, + dma_addr_t dma_start, u64 size); + +#endif /* _LINUX_DMA_MAPPING_H */ -- cgit v1.2.3 From 4af8b3d3eb5032fe6f4a8104c48c176bf68a6946 Mon Sep 17 00:00:00 2001 From: Tingwei Zhang Date: Wed, 16 Sep 2020 13:17:23 -0600 Subject: coresight: stm: Support marked packet STP_PACKET_MARKED is not supported by STM currently. Add STM_FLAG_MARKED to support marked packet in STM. Signed-off-by: Tingwei Zhang Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200916191737.4001561-3-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/coresight-stm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/coresight-stm.h b/include/uapi/linux/coresight-stm.h index 8847dbf24151..7ff3709c01b8 100644 --- a/include/uapi/linux/coresight-stm.h +++ b/include/uapi/linux/coresight-stm.h @@ -5,6 +5,7 @@ #include #define STM_FLAG_TIMESTAMPED _BITUL(3) +#define STM_FLAG_MARKED _BITUL(4) #define STM_FLAG_GUARANTEED _BITUL(7) /* -- cgit v1.2.3 From cc7886d25bcaffe7f4412d774365d85b462366f8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Sep 2020 09:41:57 +0200 Subject: compat: lift compat_s64 and compat_u64 to lift the compat_s64 and compat_u64 definitions into common code using the COMPAT_FOR_U64_ALIGNMENT symbol for the x86 special case. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/asm-generic/compat.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index a86f65bffab8..30f7b18a36f9 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -22,4 +22,12 @@ typedef u32 compat_ulong_t; typedef u32 compat_uptr_t; typedef u32 compat_aio_context_t; +#ifdef CONFIG_COMPAT_FOR_U64_ALIGNMENT +typedef s64 __attribute__((aligned(4))) compat_s64; +typedef u64 __attribute__((aligned(4))) compat_u64; +#else +typedef s64 compat_s64; +typedef u64 compat_u64; +#endif + #endif -- cgit v1.2.3 From 527c412519eb63ed354790f4291c3728815d11a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Sep 2020 09:41:58 +0200 Subject: compat: add a compat_need_64bit_alignment_fixup() helper Add a helper to check if the calling syscall needs a fixup for non-natural 64-bit type alignment in the compat ABI. This will only return true for i386 syscalls on x86_64. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index d38c4d7e83bd..f0026a344482 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -932,6 +932,15 @@ static inline bool in_compat_syscall(void) { return false; } #endif /* CONFIG_COMPAT */ +/* + * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit + * types, and will need special compat treatment for that. Most architectures + * don't need that special handling even for compat syscalls. + */ +#ifndef compat_need_64bit_alignment_fixup +#define compat_need_64bit_alignment_fixup() false +#endif + /* * A pointer passed in from user mode. This should not * be used for syscall parameters, just declare them -- cgit v1.2.3 From 80bdad3d7e3ec03f812471d9309f5f682e10f52b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Sep 2020 09:41:59 +0200 Subject: quota: simplify the quotactl compat handling Fold the misaligned u64 workarounds into the main quotactl flow instead of implementing a separate compat syscall handler. Signed-off-by: Christoph Hellwig Acked-by: Jan Kara Signed-off-by: Al Viro --- include/linux/quotaops.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 9cf0cd3dc88c..a0f6668924d3 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -27,9 +27,6 @@ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) (ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid)); } -int kernel_quotactl(unsigned int cmd, const char __user *special, - qid_t id, void __user *addr); - #if defined(CONFIG_QUOTA) #define quota_error(sb, fmt, args...) \ -- cgit v1.2.3 From d18bb3e15201918b8d07e85a6e010ca5ed28dad5 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 2 Sep 2020 11:16:22 +0300 Subject: RDMA: Clean MW allocation and free flows Move allocation and destruction of memory windows under ib_core responsibility and clean drivers to ensure that no updates to MW ib_core structures are done in driver layer. Link: https://lore.kernel.org/r/20200902081623.746359-2-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 5ae1d9849881..a292647c3db3 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2448,8 +2448,7 @@ struct ib_device_ops { unsigned int *sg_offset); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); - struct ib_mw *(*alloc_mw)(struct ib_pd *pd, enum ib_mw_type type, - struct ib_udata *udata); + int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); @@ -2610,6 +2609,7 @@ struct ib_device_ops { DECLARE_RDMA_OBJ_SIZE(ib_ah); DECLARE_RDMA_OBJ_SIZE(ib_counters); DECLARE_RDMA_OBJ_SIZE(ib_cq); + DECLARE_RDMA_OBJ_SIZE(ib_mw); DECLARE_RDMA_OBJ_SIZE(ib_pd); DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); -- cgit v1.2.3 From c0a6b5ecc5b7dd028c2921415ea036074a8f8b00 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 2 Sep 2020 11:16:23 +0300 Subject: RDMA: Convert RWQ table logic to ib_core allocation scheme Move struct ib_rwq_ind_table allocation to ib_core. Link: https://lore.kernel.org/r/20200902081623.746359-3-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a292647c3db3..fc9a55c140fa 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2484,10 +2484,9 @@ struct ib_device_ops { int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); - struct ib_rwq_ind_table *(*create_rwq_ind_table)( - struct ib_device *device, - struct ib_rwq_ind_table_init_attr *init_attr, - struct ib_udata *udata); + int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table, + struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata); int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dm *(*alloc_dm)(struct ib_device *device, struct ib_ucontext *context, @@ -2611,6 +2610,7 @@ struct ib_device_ops { DECLARE_RDMA_OBJ_SIZE(ib_cq); DECLARE_RDMA_OBJ_SIZE(ib_mw); DECLARE_RDMA_OBJ_SIZE(ib_pd); + DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table); DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); @@ -4297,7 +4297,6 @@ struct ib_wq *ib_create_wq(struct ib_pd *pd, int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask); -int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); -- cgit v1.2.3 From 75df529bec9110dad43ab30e2d9490242529e8b8 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Wed, 16 Sep 2020 17:45:30 +0200 Subject: arm64: paravirt: Initialize steal time when cpu is online Steal time initialization requires mapping a memory region which invokes a memory allocation. Doing this at CPU starting time results in the following trace when CONFIG_DEBUG_ATOMIC_SLEEP is enabled: BUG: sleeping function called from invalid context at mm/slab.h:498 in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 0, name: swapper/1 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.9.0-rc5+ #1 Call trace: dump_backtrace+0x0/0x208 show_stack+0x1c/0x28 dump_stack+0xc4/0x11c ___might_sleep+0xf8/0x130 __might_sleep+0x58/0x90 slab_pre_alloc_hook.constprop.101+0xd0/0x118 kmem_cache_alloc_node_trace+0x84/0x270 __get_vm_area_node+0x88/0x210 get_vm_area_caller+0x38/0x40 __ioremap_caller+0x70/0xf8 ioremap_cache+0x78/0xb0 memremap+0x9c/0x1a8 init_stolen_time_cpu+0x54/0xf0 cpuhp_invoke_callback+0xa8/0x720 notify_cpu_starting+0xc8/0xd8 secondary_start_kernel+0x114/0x180 CPU1: Booted secondary processor 0x0000000001 [0x431f0a11] However we don't need to initialize steal time at CPU starting time. We can simply wait until CPU online time, just sacrificing a bit of accuracy by returning zero for steal time until we know better. While at it, add __init to the functions that are only called by pv_time_init() which is __init. Signed-off-by: Andrew Jones Fixes: e0685fa228fd ("arm64: Retrieve stolen time as paravirtualized guest") Cc: stable@vger.kernel.org Reviewed-by: Steven Price Link: https://lore.kernel.org/r/20200916154530.40809-1-drjones@redhat.com Signed-off-by: Catalin Marinas --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3215023d4852..bf9181cef444 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -142,7 +142,6 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, - CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, -- cgit v1.2.3 From c7b6bac9c72c5fcbd6e9e12545bd3022c7f21860 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 15 Sep 2020 09:30:05 -0700 Subject: drm, iommu: Change type of pasid to u32 PASID is defined as a few different types in iommu including "int", "u32", and "unsigned int". To be consistent and to match with uapi definitions, define PASID and its variations (e.g. max PASID) as "u32". "u32" is also shorter and a little more explicit than "unsigned int". No PASID type change in uapi although it defines PASID as __u64 in some places. Suggested-by: Thomas Gleixner Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Lu Baolu Acked-by: Felix Kuehling Acked-by: Joerg Roedel Link: https://lkml.kernel.org/r/1600187413-163670-2-git-send-email-fenghua.yu@intel.com --- include/linux/amd-iommu.h | 8 ++++---- include/linux/intel-iommu.h | 12 ++++++------ include/linux/intel-svm.h | 2 +- include/linux/iommu.h | 10 +++++----- include/linux/uacce.h | 2 +- 5 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 21e950e4ab62..450717299928 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -76,7 +76,7 @@ extern void amd_iommu_free_device(struct pci_dev *pdev); * * The function returns 0 on success or a negative value on error. */ -extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid, +extern int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid, struct task_struct *task); /** @@ -88,7 +88,7 @@ extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid, * When this function returns the device is no longer using the PASID * and the PASID is no longer bound to its task. */ -extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid); +extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid); /** * amd_iommu_set_invalid_ppr_cb() - Register a call-back for failed @@ -114,7 +114,7 @@ extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid); #define AMD_IOMMU_INV_PRI_RSP_FAIL 2 typedef int (*amd_iommu_invalid_ppr_cb)(struct pci_dev *pdev, - int pasid, + u32 pasid, unsigned long address, u16); @@ -166,7 +166,7 @@ extern int amd_iommu_device_info(struct pci_dev *pdev, * @cb: The call-back function */ -typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, int pasid); +typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, u32 pasid); extern int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev, amd_iommu_invalidate_ctx cb); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b1ed2f25f7c0..7322073f62d0 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -549,7 +549,7 @@ struct dmar_domain { 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ u64 max_addr; /* maximum mapped address */ - int default_pasid; /* + u32 default_pasid; /* * The default pasid used for non-SVM * traffic on mediated devices. */ @@ -708,7 +708,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, u32 pasid, u16 qdep, u64 addr, unsigned int size_order); void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, - int pasid); + u32 pasid); int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, unsigned int count, unsigned long options); @@ -737,11 +737,11 @@ extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, struct iommu_gpasid_bind_data *data); -int intel_svm_unbind_gpasid(struct device *dev, int pasid); +int intel_svm_unbind_gpasid(struct device *dev, u32 pasid); struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata); void intel_svm_unbind(struct iommu_sva *handle); -int intel_svm_get_pasid(struct iommu_sva *handle); +u32 intel_svm_get_pasid(struct iommu_sva *handle); int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); @@ -753,7 +753,7 @@ struct intel_svm_dev { struct device *dev; struct svm_dev_ops *ops; struct iommu_sva sva; - int pasid; + u32 pasid; int users; u16 did; u16 dev_iotlb:1; @@ -766,7 +766,7 @@ struct intel_svm { struct intel_iommu *iommu; int flags; - int pasid; + u32 pasid; int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; struct list_head list; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index c9e7e601950d..39d368a810b8 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -11,7 +11,7 @@ struct device; struct svm_dev_ops { - void (*fault_cb)(struct device *dev, int pasid, u64 address, + void (*fault_cb)(struct device *dev, u32 pasid, u64 address, void *private, int rwxp, int response); }; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index fee209efb756..e57e819aaf2e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -286,7 +286,7 @@ struct iommu_ops { struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm, void *drvdata); void (*sva_unbind)(struct iommu_sva *handle); - int (*sva_get_pasid)(struct iommu_sva *handle); + u32 (*sva_get_pasid)(struct iommu_sva *handle); int (*page_response)(struct device *dev, struct iommu_fault_event *evt, @@ -296,7 +296,7 @@ struct iommu_ops { int (*sva_bind_gpasid)(struct iommu_domain *domain, struct device *dev, struct iommu_gpasid_bind_data *data); - int (*sva_unbind_gpasid)(struct device *dev, int pasid); + int (*sva_unbind_gpasid)(struct device *dev, u32 pasid); int (*def_domain_type)(struct device *dev); @@ -634,7 +634,7 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata); void iommu_sva_unbind_device(struct iommu_sva *handle); -int iommu_sva_get_pasid(struct iommu_sva *handle); +u32 iommu_sva_get_pasid(struct iommu_sva *handle); #else /* CONFIG_IOMMU_API */ @@ -1027,7 +1027,7 @@ static inline void iommu_sva_unbind_device(struct iommu_sva *handle) { } -static inline int iommu_sva_get_pasid(struct iommu_sva *handle) +static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; } @@ -1046,7 +1046,7 @@ static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain, } static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, int pasid) + struct device *dev, u32 pasid) { return -ENODEV; } diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 454c2f6672d7..48e319f40275 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -81,7 +81,7 @@ struct uacce_queue { struct list_head list; struct uacce_qfile_region *qfrs[UACCE_MAX_REGION]; enum uacce_q_state state; - int pasid; + u32 pasid; struct iommu_sva *handle; }; -- cgit v1.2.3 From 2a5054c6e7b16906984ac36a7363ca46b8d99ade Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 15 Sep 2020 09:30:06 -0700 Subject: iommu/vt-d: Change flags type to unsigned int in binding mm "flags" passed to intel_svm_bind_mm() is a bit mask and should be defined as "unsigned int" instead of "int". Change its type to "unsigned int". Suggested-by: Thomas Gleixner Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Lu Baolu Acked-by: Joerg Roedel Link: https://lkml.kernel.org/r/1600187413-163670-3-git-send-email-fenghua.yu@intel.com --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 7322073f62d0..9c3e8337442a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -765,7 +765,7 @@ struct intel_svm { struct mm_struct *mm; struct intel_iommu *iommu; - int flags; + unsigned int flags; u32 pasid; int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; -- cgit v1.2.3 From 5ef64cc8987a9211d3f3667331ba3411a94ddc79 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2020 14:05:35 -0700 Subject: mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel Tested-by: Matthieu Baerts Cc: Dave Chinner Cc: Matthew Wilcox Cc: Chris Mason Cc: Jan Kara Cc: Amir Goldstein Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/wait.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ca6e6a81576b..b2f370f0b420 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -41,6 +41,8 @@ struct writeback_control; struct bdi_writeback; struct pt_regs; +extern int sysctl_page_lock_unfairness; + void init_mm_internals(void); #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 898c890fc153..27fb99cfeb02 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -21,6 +21,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_BOOKMARK 0x04 #define WQ_FLAG_CUSTOM 0x08 +#define WQ_FLAG_DONE 0x10 /* * A single wait-queue entry structure: -- cgit v1.2.3 From 877c1a5f79c6984bbe3f2924234c08e2f4f1acd5 Mon Sep 17 00:00:00 2001 From: Tuan Phan Date: Thu, 6 Aug 2020 14:57:34 -0700 Subject: PCI/ACPI: Add Ampere Altra SOC MCFG quirk Ampere Altra SOC supports only 32-bit ECAM reads. Add an MCFG quirk for the platform. Link: https://lore.kernel.org/r/1596751055-12316-1-git-send-email-tuanphan@os.amperecomputing.com Signed-off-by: Tuan Phan Signed-off-by: Bjorn Helgaas --- include/linux/pci-ecam.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 1af5cb02ef7f..033ce74f02e8 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -51,6 +51,7 @@ extern const struct pci_ecam_ops pci_generic_ecam_ops; #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) extern const struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ +extern const struct pci_ecam_ops pci_32b_read_ops; /* 32-bit read only */ extern const struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ extern const struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */ extern const struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ -- cgit v1.2.3 From 9d8feb460adb90e89e64101ce2c1cfcd548a6d83 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Mon, 31 Aug 2020 10:01:48 +0300 Subject: RDMA/mlx5: Add sw_owner_v2 bit capability Added sw_owner_v2 which will be enabled for future devices, replacing sw_owner bit. Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index de1ffb4804d6..3061ceebbaf3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -420,7 +420,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_1a[0x2]; u8 ipsec_encrypt[0x1]; u8 ipsec_decrypt[0x1]; - u8 reserved_at_1e[0x2]; + u8 sw_owner_v2[0x1]; + u8 reserved_at_1f[0x1]; u8 termination_table_raw_traffic[0x1]; u8 reserved_at_21[0x1]; -- cgit v1.2.3 From 52ad9bc64c74167466e70e0df4b99ee5ccef0078 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 15 Sep 2020 09:30:11 -0700 Subject: mm: Add a pasid member to struct mm_struct A PASID is shared by all threads in a process. So the logical place to keep track of it is in the mm_struct. Both ARM and x86 would use this PASID. [ bp: Massage commit message. ] Suggested-by: Christoph Hellwig Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lkml.kernel.org/r/1600187413-163670-8-git-send-email-fenghua.yu@intel.com --- include/linux/mm_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 496c3ff97cce..1ff0615ef19f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -542,6 +542,10 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; + +#ifdef CONFIG_IOMMU_SUPPORT + u32 pasid; +#endif } __randomize_layout; /* -- cgit v1.2.3 From a748c6975dea325da540610c2ba9b5f332c603e6 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 16 Sep 2020 23:10:05 +0200 Subject: bpf: propagate poke descriptors to subprograms Previously, there was no need for poke descriptors being present in subprogram's bpf_prog_aux struct since tailcalls were simply not allowed in them. Each subprog is JITed independently so in order to enable JITing subprograms that use tailcalls, do the following: - in fixup_bpf_calls() store the index of tailcall insn onto the generated poke descriptor, - in case when insn patching occurs, adjust the tailcall insn idx from bpf_patch_insn_data, - then in jit_subprogs() check whether the given poke descriptor belongs to the current subprog by checking if that previously stored absolute index of tail call insn is in the scope of the insns of given subprog, - update the insn->imm with new poke descriptor slot so that while JITing the proper poke descriptor will be grabbed This way each of the main program's poke descriptors are distributed across the subprograms poke descriptor array, so main program's descriptors can be untracked out of the prog array map. Add also subprog's aux struct to the BPF map poke_progs list by calling on it map_poke_track(). In case of any error, call the map_poke_untrack() on subprog's aux structs that have already been registered to prog array map. Signed-off-by: Maciej Fijalkowski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5dcce0364634..a23e5eb728c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -707,6 +707,7 @@ struct bpf_jit_poke_descriptor { bool ip_stable; u8 adj_off; u16 reason; + u32 insn_idx; }; /* reg_type info for ctx arguments */ -- cgit v1.2.3 From cf71b174d3464c7dc22f86f25d629a8d9d5c3519 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 16 Sep 2020 23:10:06 +0200 Subject: bpf: rename poke descriptor's 'ip' member to 'tailcall_target' Reflect the actual purpose of poke->ip and rename it to poke->tailcall_target so that it will not the be confused with another poke target that will be introduced in next commit. While at it, do the same thing with poke->ip_stable - rename it to poke->tailcall_target_stable. Signed-off-by: Maciej Fijalkowski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a23e5eb728c8..f3790c9cf542 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -697,14 +697,14 @@ enum bpf_jit_poke_reason { /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { - void *ip; + void *tailcall_target; union { struct { struct bpf_map *map; u32 key; } tail_call; }; - bool ip_stable; + bool tailcall_target_stable; u8 adj_off; u16 reason; u32 insn_idx; -- cgit v1.2.3 From 0b988ca1c7c4c73983b4ea96ef7c2af2263c87eb Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 17 Sep 2020 12:54:24 +1000 Subject: drm/ttm: protect against reentrant bind in the drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This moves the generic tracking into the drivers and protects against reentrancy in the drivers. It fixes up radeon and agp to be able to query the bound status as that is required. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200917043040.146575-2-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 1 - include/drm/ttm/ttm_bo_driver.h | 14 -------------- include/drm/ttm/ttm_tt.h | 1 + 3 files changed, 1 insertion(+), 15 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 89ad6f213fc0..fd8d29f5f370 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -141,7 +141,6 @@ struct ttm_buffer_object { struct ttm_resource mem; struct file *persistent_swap_storage; struct ttm_tt *ttm; - bool ttm_bound; bool evicted; bool deleted; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index e66672f703a3..7846dfa507f7 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -698,20 +698,6 @@ int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem); */ void ttm_bo_tt_unbind(struct ttm_buffer_object *bo); -static inline bool ttm_bo_tt_is_bound(struct ttm_buffer_object *bo) -{ - return bo->ttm_bound; -} - -static inline void ttm_bo_tt_set_unbound(struct ttm_buffer_object *bo) -{ - bo->ttm_bound = false; -} - -static inline void ttm_bo_tt_set_bound(struct ttm_buffer_object *bo) -{ - bo->ttm_bound = true; -} /** * ttm_bo_tt_destroy. */ diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index c777b72063db..4e906e32d08c 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -219,6 +219,7 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo, int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem); void ttm_agp_unbind(struct ttm_tt *ttm); void ttm_agp_destroy(struct ttm_tt *ttm); +bool ttm_agp_is_bound(struct ttm_tt *ttm); #endif #endif -- cgit v1.2.3 From 7626168fd132009c79a0457bccc58014abc738f5 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 17 Sep 2020 13:20:48 +1000 Subject: drm/ttm: flip tt destroy ordering. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Call the driver first and have it call the common code cleanup. This is useful later to fix unbind. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200917043040.146575-3-airlied@gmail.com --- include/drm/ttm/ttm_tt.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 4e906e32d08c..75208c0a0cac 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -155,6 +155,13 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma); */ void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm); +/** + * ttm_tt_destroy_common: + * + * Called from driver to destroy common path. + */ +void ttm_tt_destroy_common(struct ttm_bo_device *bdev, struct ttm_tt *ttm); + /** * ttm_tt_swapin: * -- cgit v1.2.3 From 2ee476f77ffe5a7ecbd4e1e20fa0859cb541530d Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 17 Sep 2020 14:03:46 +1000 Subject: drm/ttm: add a simple assign mem to bo wrapper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This pattern is called in a few places, just clean it up. Reviewed-by: Christian König Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20200917043040.146575-6-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 7846dfa507f7..25cc932d63f1 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -539,6 +539,13 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo spin_unlock(&ttm_bo_glob.lru_lock); } +static inline void ttm_bo_assign_mem(struct ttm_buffer_object *bo, + struct ttm_resource *new_mem) +{ + bo->mem = *new_mem; + new_mem->mm_node = NULL; +} + /** * ttm_bo_move_null = assign memory for a buffer object. * @bo: The bo to assign the memory to @@ -552,8 +559,7 @@ static inline void ttm_bo_move_null(struct ttm_buffer_object *bo, struct ttm_resource *old_mem = &bo->mem; WARN_ON(old_mem->mm_node != NULL); - *old_mem = *new_mem; - new_mem->mm_node = NULL; + ttm_bo_assign_mem(bo, new_mem); } /** -- cgit v1.2.3 From e46f468fef953dea30e7a7c69ad7e0370af26855 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 17 Sep 2020 16:36:14 +1000 Subject: drm/ttm: drop special pipeline accel cleanup function. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The two accel cleanup paths were mostly the same once refactored. Just pass a bool to say if the evictions are to be pipelined. Signed-off-by: Dave Airlie Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20200917064132.148521-2-airlied@gmail.com --- include/drm/ttm/ttm_bo_driver.h | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 25cc932d63f1..864afa8f6f18 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -642,6 +642,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo); * @bo: A pointer to a struct ttm_buffer_object. * @fence: A fence object that signals when moving is complete. * @evict: This is an evict move. Don't return until the buffer is idle. + * @pipeline: evictions are to be pipelined. * @new_mem: struct ttm_resource indicating where to move. * * Accelerated move function to be called when an accelerated move @@ -653,23 +654,9 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo); */ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct dma_fence *fence, bool evict, + bool pipeline, struct ttm_resource *new_mem); -/** - * ttm_bo_pipeline_move. - * - * @bo: A pointer to a struct ttm_buffer_object. - * @fence: A fence object that signals when moving is complete. - * @evict: This is an evict move. Don't return until the buffer is idle. - * @new_mem: struct ttm_resource indicating where to move. - * - * Function for pipelining accelerated moves. Either free the memory - * immediately or hang it on a temporary buffer object. - */ -int ttm_bo_pipeline_move(struct ttm_buffer_object *bo, - struct dma_fence *fence, bool evict, - struct ttm_resource *new_mem); - /** * ttm_bo_pipeline_gutting. * -- cgit v1.2.3 From 4856e5aa0ef1d4c62f6f30bf273a778735507837 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 17 Sep 2020 16:13:03 +1000 Subject: drm/ttm: drop evicted from ttm_bo. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This was unused. Signed-off-by: Dave Airlie Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20200917064132.148521-3-airlied@gmail.com --- include/drm/ttm/ttm_bo_api.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index fd8d29f5f370..0f7cd21d6d74 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -141,7 +141,6 @@ struct ttm_buffer_object { struct ttm_resource mem; struct file *persistent_swap_storage; struct ttm_tt *ttm; - bool evicted; bool deleted; /** -- cgit v1.2.3 From 32b313ce9db54991a053da66883289e99d6ad820 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 17 Sep 2020 23:30:27 +0200 Subject: PCI: endpoint: Use "NULL" instead of "0" as a NULL pointer When returning a NULL pointer, use "NULL" instead of "0". Fixes sparse warning given by executing "make C=2 drivers/pci/": CHECK drivers/pci/endpoint/pci-epc-core.c drivers/pci/endpoint/pci-epc-core.c: note: in included file: ./include/linux/pci-ep-cfs.h:22:16: warning: Using plain integer as NULL pointer CHECK drivers/pci/endpoint/pci-epf-core.c drivers/pci/endpoint/pci-epf-core.c: note: in included file: ./include/linux/pci-ep-cfs.h:31:16: warning: Using plain integer as NULL pointer Link: https://lore.kernel.org/r/80895f7465719edb3aa259e907acc4bc3217945c.1600378209.git.gustavo.pimentel@synopsys.com Reported-by: Bjorn Helgaas Signed-off-by: Gustavo Pimentel Signed-off-by: Bjorn Helgaas Cc: Kishon Vijay Abraham I Cc: Joao Pinto --- include/linux/pci-ep-cfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pci-ep-cfs.h b/include/linux/pci-ep-cfs.h index f42b0fd4b4bc..662881335c7e 100644 --- a/include/linux/pci-ep-cfs.h +++ b/include/linux/pci-ep-cfs.h @@ -19,7 +19,7 @@ void pci_ep_cfs_remove_epf_group(struct config_group *group); #else static inline struct config_group *pci_ep_cfs_add_epc_group(const char *name) { - return 0; + return NULL; } static inline void pci_ep_cfs_remove_epc_group(struct config_group *group) @@ -28,7 +28,7 @@ static inline void pci_ep_cfs_remove_epc_group(struct config_group *group) static inline struct config_group *pci_ep_cfs_add_epf_group(const char *name) { - return 0; + return NULL; } static inline void pci_ep_cfs_remove_epf_group(struct config_group *group) -- cgit v1.2.3 From 2b7ea122a0c437442bf54a5f1c60155757df270c Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 16 Sep 2020 22:16:29 +0800 Subject: net/sched: Remove unused function qdisc_queue_drop_head() It is not used since commit a09ceb0e0814 ("sched: remove qdisc->drop") Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- include/net/sch_generic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d60e7c39d60c..6c762457122f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1047,12 +1047,6 @@ static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, return 0; } -static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch, - struct sk_buff **to_free) -{ - return __qdisc_queue_drop_head(sch, &sch->q, to_free); -} - static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { const struct qdisc_skb_head *qh = &sch->q; -- cgit v1.2.3 From 5114b331051981ecbdf144b5ad33387ae8d0f0d5 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 16 Sep 2020 22:17:28 +0800 Subject: genetlink: Remove unused function genl_err_attr() It is never used, so can remove it. Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- include/net/genetlink.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 6e5f1e1aa822..b9eb92f3fe86 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -101,14 +101,6 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) -static inline int genl_err_attr(struct genl_info *info, int err, - const struct nlattr *attr) -{ - info->extack->bad_attr = attr; - - return err; -} - enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), -- cgit v1.2.3 From 19a83d36f9837e8bd27435ebb31564a717a5d15a Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Thu, 17 Sep 2020 01:04:10 +0200 Subject: ethtool: add and use message type for tunnel info reply Tunnel offload info code uses ETHTOOL_MSG_TUNNEL_INFO_GET message type (cmd field in genetlink header) for replies to tunnel info netlink request, i.e. the same value as the request have. This is a problem because we are using two separate enums for userspace to kernel and kernel to userspace message types so that this ETHTOOL_MSG_TUNNEL_INFO_GET (28) collides with ETHTOOL_MSG_CABLE_TEST_TDR_NTF which is what message type 28 means for kernel to userspace messages. As the tunnel info request reached mainline in 5.9 merge window, we should still be able to fix the reply message type without breaking backward compatibility. Fixes: c7d759eb7b12 ("ethtool: add tunnel info interface") Signed-off-by: Michal Kubecek Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/ethtool_netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5dcd24cb33ea..72ba36be9655 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -79,6 +79,7 @@ enum { ETHTOOL_MSG_TSINFO_GET_REPLY, ETHTOOL_MSG_CABLE_TEST_NTF, ETHTOOL_MSG_CABLE_TEST_TDR_NTF, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, -- cgit v1.2.3 From 2492c205d2bbbc01f5c9e49fffe4b2e633c33f38 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 17 Sep 2020 10:19:10 +0800 Subject: netdev: Remove unused functions There is no callers in tree, so can remove it. Signed-off-by: YueHaibing Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 157e0242e9ee..909b1fbb0481 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4677,16 +4677,6 @@ int netdev_class_create_file_ns(const struct class_attribute *class_attr, void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns); -static inline int netdev_class_create_file(const struct class_attribute *class_attr) -{ - return netdev_class_create_file_ns(class_attr, NULL); -} - -static inline void netdev_class_remove_file(const struct class_attribute *class_attr) -{ - netdev_class_remove_file_ns(class_attr, NULL); -} - extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); -- cgit v1.2.3 From 78a3ea5557137b0811f3c5a020afaafa7b61d6aa Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 17 Sep 2020 10:51:32 -0700 Subject: net: remove comments on struct rtnl_link_stats We removed the misleading comments from struct rtnl_link_stats64 when we added proper kdoc. struct rtnl_link_stats has the same inline comments, so remove them, too. Signed-off-by: Jakub Kicinski Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index bf4667403cab..c4b23f06f69e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,7 +36,7 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; /** -- cgit v1.2.3 From 7f6e4312e15a5c370e84eaa685879b6bdcc717e4 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 16 Sep 2020 23:10:07 +0200 Subject: bpf: Limit caller's stack depth 256 for subprogs with tailcalls Protect against potential stack overflow that might happen when bpf2bpf calls get combined with tailcalls. Limit the caller's stack depth for such case down to 256 so that the worst case scenario would result in 8k stack size (32 which is tailcall limit * 256 = 8k). Suggested-by: Alexei Starovoitov Signed-off-by: Maciej Fijalkowski Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 53c7bd568c5d..5026b75db972 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -358,6 +358,7 @@ struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ + bool has_tail_call; }; /* single container for all structs -- cgit v1.2.3 From ebf7d1f508a73871acf3b2bfbfa1323a477acdb3 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 16 Sep 2020 23:10:08 +0200 Subject: bpf, x64: rework pro/epilogue and tailcall handling in JIT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit serves two things: 1) it optimizes BPF prologue/epilogue generation 2) it makes possible to have tailcalls within BPF subprogram Both points are related to each other since without 1), 2) could not be achieved. In [1], Alexei says: "The prologue will look like: nop5 xor eax,eax  // two new bytes if bpf_tail_call() is used in this // function push rbp mov rbp, rsp sub rsp, rounded_stack_depth push rax // zero init tail_call counter variable number of push rbx,r13,r14,r15 Then bpf_tail_call will pop variable number rbx,.. and final 'pop rax' Then 'add rsp, size_of_current_stack_frame' jmp to next function and skip over 'nop5; xor eax,eax; push rpb; mov rbp, rsp' This way new function will set its own stack size and will init tail call counter with whatever value the parent had. If next function doesn't use bpf_tail_call it won't have 'xor eax,eax'. Instead it would need to have 'nop2' in there." Implement that suggestion. Since the layout of stack is changed, tail call counter handling can not rely anymore on popping it to rbx just like it have been handled for constant prologue case and later overwrite of rbx with actual value of rbx pushed to stack. Therefore, let's use one of the register (%rcx) that is considered to be volatile/caller-saved and pop the value of tail call counter in there in the epilogue. Drop the BUILD_BUG_ON in emit_prologue and in emit_bpf_tail_call_indirect where instruction layout is not constant anymore. Introduce new poke target, 'tailcall_bypass' to poke descriptor that is dedicated for skipping the register pops and stack unwind that are generated right before the actual jump to target program. For case when the target program is not present, BPF program will skip the pop instructions and nop5 dedicated for jmpq $target. An example of such state when only R6 of callee saved registers is used by program: ffffffffc0513aa1: e9 0e 00 00 00 jmpq 0xffffffffc0513ab4 ffffffffc0513aa6: 5b pop %rbx ffffffffc0513aa7: 58 pop %rax ffffffffc0513aa8: 48 81 c4 00 00 00 00 add $0x0,%rsp ffffffffc0513aaf: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) ffffffffc0513ab4: 48 89 df mov %rbx,%rdi When target program is inserted, the jump that was there to skip pops/nop5 will become the nop5, so CPU will go over pops and do the actual tailcall. One might ask why there simply can not be pushes after the nop5? In the following example snippet: ffffffffc037030c: 48 89 fb mov %rdi,%rbx (...) ffffffffc0370332: 5b pop %rbx ffffffffc0370333: 58 pop %rax ffffffffc0370334: 48 81 c4 00 00 00 00 add $0x0,%rsp ffffffffc037033b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) ffffffffc0370340: 48 81 ec 00 00 00 00 sub $0x0,%rsp ffffffffc0370347: 50 push %rax ffffffffc0370348: 53 push %rbx ffffffffc0370349: 48 89 df mov %rbx,%rdi ffffffffc037034c: e8 f7 21 00 00 callq 0xffffffffc0372548 There is the bpf2bpf call (at ffffffffc037034c) right after the tailcall and jump target is not present. ctx is in %rbx register and BPF subprogram that we will call into on ffffffffc037034c is relying on it, e.g. it will pick ctx from there. Such code layout is therefore broken as we would overwrite the content of %rbx with the value that was pushed on the prologue. That is the reason for the 'bypass' approach. Special care needs to be taken during the install/update/remove of tailcall target. In case when target program is not present, the CPU must not execute the pop instructions that precede the tailcall. To address that, the following states can be defined: A nop, unwind, nop B nop, unwind, tail C skip, unwind, nop D skip, unwind, tail A is forbidden (lead to incorrectness). The state transitions between tailcall install/update/remove will work as follows: First install tail call f: C->D->B(f) * poke the tailcall, after that get rid of the skip Update tail call f to f': B(f)->B(f') * poke the tailcall (poke->tailcall_target) and do NOT touch the poke->tailcall_bypass Remove tail call: B(f')->C(f') * poke->tailcall_bypass is poked back to jump, then we wait the RCU grace period so that other programs will finish its execution and after that we are safe to remove the poke->tailcall_target Install new tail call (f''): C(f')->D(f'')->B(f''). * same as first step This way CPU can never be exposed to "unwind, tail" state. Last but not least, when tailcalls get mixed with bpf2bpf calls, it would be possible to encounter the endless loop due to clearing the tailcall counter if for example we would use the tailcall3-like from BPF selftests program that would be subprogram-based, meaning the tailcall would be present within the BPF subprogram. This test, broken down to particular steps, would do: entry -> set tailcall counter to 0, bump it by 1, tailcall to func0 func0 -> call subprog_tail (we are NOT skipping the first 11 bytes of prologue and this subprogram has a tailcall, therefore we clear the counter...) subprog -> do the same thing as entry and then loop forever. To address this, the idea is to go through the call chain of bpf2bpf progs and look for a tailcall presence throughout whole chain. If we saw a single tail call then each node in this call chain needs to be marked as a subprog that can reach the tailcall. We would later feed the JIT with this info and: - set eax to 0 only when tailcall is reachable and this is the entry prog - if tailcall is reachable but there's no tailcall in insns of currently JITed prog then push rax anyway, so that it will be possible to propagate further down the call chain - finally if tailcall is reachable, then we need to precede the 'call' insn with mov rax, [rbp - (stack_depth + 8)] Tail call related cases from test_verifier kselftest are also working fine. Sample BPF programs that utilize tail calls (sockex3, tracex5) work properly as well. [1]: https://lore.kernel.org/bpf/20200517043227.2gpq22ifoq37ogst@ast-mbp.dhcp.thefacebook.com/ Suggested-by: Alexei Starovoitov Signed-off-by: Maciej Fijalkowski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 +++ include/linux/bpf_verifier.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f3790c9cf542..d7c5a6ed87e3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -698,6 +698,8 @@ enum bpf_jit_poke_reason { /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { void *tailcall_target; + void *tailcall_bypass; + void *bypass_addr; union { struct { struct bpf_map *map; @@ -738,6 +740,7 @@ struct bpf_prog_aux { bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; bool sleepable; + bool tail_call_reachable; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5026b75db972..fbc964526ba3 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -359,6 +359,7 @@ struct bpf_subprog_info { u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ bool has_tail_call; + bool tail_call_reachable; }; /* single container for all structs -- cgit v1.2.3 From 09b28d76eac48e922dc293da1aa2b2b85c32aeee Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 17 Sep 2020 19:09:18 -0700 Subject: bpf: Add abnormal return checks. LD_[ABS|IND] instructions may return from the function early. bpf_tail_call pseudo instruction is either fallthrough or return. Allow them in the subprograms only when subprograms are BTF annotated and have scalar return types. Allow ld_abs and tail_call in the main program even if it calls into subprograms. In the past that was not ok to do for ld_abs, since it was JITed with special exit sequence. Since bpf_gen_ld_abs() was introduced the ld_abs looks like normal exit insn from JIT point of view, so it's safe to allow them in the main program. Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index fbc964526ba3..2bb48a2c4d08 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -360,6 +360,7 @@ struct bpf_subprog_info { u16 stack_depth; /* max. stack depth used by this function */ bool has_tail_call; bool tail_call_reachable; + bool has_ld_abs; }; /* single container for all structs -- cgit v1.2.3 From 962fad301c33dec69324dc2d9320fd84a119a24c Mon Sep 17 00:00:00 2001 From: Swapnil Jakhade Date: Wed, 16 Sep 2020 20:28:30 +0200 Subject: dt-bindings: phy: cadence-torrent: Add binding to specify SSC mode Add binding to specify Spread Spectrum Clocking mode used. Signed-off-by: Swapnil Jakhade Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/1600280911-9214-7-git-send-email-sjakhade@cadence.com Signed-off-by: Vinod Koul --- include/dt-bindings/phy/phy-cadence-torrent.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/dt-bindings/phy/phy-cadence-torrent.h (limited to 'include') diff --git a/include/dt-bindings/phy/phy-cadence-torrent.h b/include/dt-bindings/phy/phy-cadence-torrent.h new file mode 100644 index 000000000000..e387b6a95741 --- /dev/null +++ b/include/dt-bindings/phy/phy-cadence-torrent.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This header provides constants for Cadence Torrent SERDES. + */ + +#ifndef _DT_BINDINGS_TORRENT_SERDES_H +#define _DT_BINDINGS_TORRENT_SERDES_H + +#define TORRENT_SERDES_NO_SSC 0 +#define TORRENT_SERDES_EXTERNAL_SSC 1 +#define TORRENT_SERDES_INTERNAL_SSC 2 + +#endif /* _DT_BINDINGS_TORRENT_SERDES_H */ -- cgit v1.2.3 From 51862859fb7483421a6f498ffd364f06a51a57bf Mon Sep 17 00:00:00 2001 From: Swapnil Jakhade Date: Thu, 17 Sep 2020 09:30:37 +0200 Subject: dt-bindings: phy: Add PHY_TYPE_QSGMII definition Add definition for QSGMII phy type. Signed-off-by: Swapnil Jakhade Acked-by: Rob Herring Link: https://lore.kernel.org/r/1600327846-9733-5-git-send-email-sjakhade@cadence.com Signed-off-by: Vinod Koul --- include/dt-bindings/phy/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/phy/phy.h b/include/dt-bindings/phy/phy.h index 36e8c241cf48..887a31b250a8 100644 --- a/include/dt-bindings/phy/phy.h +++ b/include/dt-bindings/phy/phy.h @@ -19,5 +19,6 @@ #define PHY_TYPE_DP 6 #define PHY_TYPE_XPCS 7 #define PHY_TYPE_SGMII 8 +#define PHY_TYPE_QSGMII 9 #endif /* _DT_BINDINGS_PHY */ -- cgit v1.2.3 From cc80d10d6fcf6f47a2a3efe2c4139e50906a4764 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 25 Aug 2020 20:01:50 +0300 Subject: interconnect: Add get_bw() callback The interconnect controller hardware may support querying the current bandwidth settings, so add a callback for providers to implement this functionality if supported. Link: https://lore.kernel.org/r/20200825170152.6434-2-georgi.djakov@linaro.org Reviewed-by: Saravana Kannan Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 4735518de515..520f70fe5a31 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -38,6 +38,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec, * @aggregate: pointer to device specific aggregate operation function * @pre_aggregate: pointer to device specific function that is called * before the aggregation begins (optional) + * @get_bw: pointer to device specific function to get current bandwidth * @xlate: provider-specific callback for mapping nodes from phandle arguments * @dev: the device this interconnect provider belongs to * @users: count of active users @@ -51,6 +52,7 @@ struct icc_provider { int (*aggregate)(struct icc_node *node, u32 tag, u32 avg_bw, u32 peak_bw, u32 *agg_avg, u32 *agg_peak); void (*pre_aggregate)(struct icc_node *node); + int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak); struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data); struct device *dev; int users; -- cgit v1.2.3 From b1d681d8d32499bcf284462d92aeb5f9fe72bf5b Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 25 Aug 2020 20:01:51 +0300 Subject: interconnect: Add sync state support The bootloaders often do some initial configuration of the interconnects in the system and we want to keep this configuration until all consumers have probed and expressed their bandwidth needs. This is because we don't want to change the configuration by starting to disable unused paths until every user had a chance to request the amount of bandwidth it needs. To accomplish this we will implement an interconnect specific sync_state callback which will synchronize (aggregate and set) the current bandwidth settings when all consumers have been probed. Link: https://lore.kernel.org/r/20200825170152.6434-3-georgi.djakov@linaro.org Reviewed-by: Saravana Kannan Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 520f70fe5a31..f713308b8a8f 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -75,6 +75,8 @@ struct icc_provider { * @req_list: a list of QoS constraint requests associated with this node * @avg_bw: aggregated value of average bandwidth requests from all consumers * @peak_bw: aggregated value of peak bandwidth requests from all consumers + * @init_avg: average bandwidth value that is read from the hardware during init + * @init_peak: peak bandwidth value that is read from the hardware during init * @data: pointer to private data */ struct icc_node { @@ -91,6 +93,8 @@ struct icc_node { struct hlist_head req_list; u32 avg_bw; u32 peak_bw; + u32 init_avg; + u32 init_peak; void *data; }; @@ -108,6 +112,7 @@ int icc_nodes_remove(struct icc_provider *provider); int icc_provider_add(struct icc_provider *provider); int icc_provider_del(struct icc_provider *provider); struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec); +void icc_sync_state(struct device *dev); #else -- cgit v1.2.3 From f7f842cc1fe8a9be1916aa0ff8a52f08389bf394 Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Mon, 7 Sep 2020 12:16:47 +0200 Subject: dt-bindings: iommu: Add binding for MediaTek MT8167 IOMMU This commit adds IOMMU binding documentation and larb port definitions for the MT8167 SoC. Signed-off-by: Fabien Parent Acked-by: Rob Herring Link: https://lore.kernel.org/r/20200907101649.1573134-1-fparent@baylibre.com Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt8167-larb-port.h | 51 +++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 include/dt-bindings/memory/mt8167-larb-port.h (limited to 'include') diff --git a/include/dt-bindings/memory/mt8167-larb-port.h b/include/dt-bindings/memory/mt8167-larb-port.h new file mode 100644 index 000000000000..000fb299a408 --- /dev/null +++ b/include/dt-bindings/memory/mt8167-larb-port.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + * Copyright (c) 2020 BayLibre, SAS + * Author: Honghui Zhang + * Author: Fabien Parent + */ +#ifndef __DTS_IOMMU_PORT_MT8167_H +#define __DTS_IOMMU_PORT_MT8167_H + +#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) + +#define M4U_LARB0_ID 0 +#define M4U_LARB1_ID 1 +#define M4U_LARB2_ID 2 + +/* larb0 */ +#define M4U_PORT_DISP_OVL0 MTK_M4U_ID(M4U_LARB0_ID, 0) +#define M4U_PORT_DISP_RDMA0 MTK_M4U_ID(M4U_LARB0_ID, 1) +#define M4U_PORT_DISP_WDMA0 MTK_M4U_ID(M4U_LARB0_ID, 2) +#define M4U_PORT_DISP_RDMA1 MTK_M4U_ID(M4U_LARB0_ID, 3) +#define M4U_PORT_MDP_RDMA MTK_M4U_ID(M4U_LARB0_ID, 4) +#define M4U_PORT_MDP_WDMA MTK_M4U_ID(M4U_LARB0_ID, 5) +#define M4U_PORT_MDP_WROT MTK_M4U_ID(M4U_LARB0_ID, 6) +#define M4U_PORT_DISP_FAKE MTK_M4U_ID(M4U_LARB0_ID, 7) + +/* larb1*/ +#define M4U_PORT_CAM_IMGO MTK_M4U_ID(M4U_LARB1_ID, 0) +#define M4U_PORT_CAM_IMG2O MTK_M4U_ID(M4U_LARB1_ID, 1) +#define M4U_PORT_CAM_LSCI MTK_M4U_ID(M4U_LARB1_ID, 2) +#define M4U_PORT_CAM_ESFKO MTK_M4U_ID(M4U_LARB1_ID, 3) +#define M4U_PORT_CAM_AAO MTK_M4U_ID(M4U_LARB1_ID, 4) +#define M4U_PORT_VENC_REC MTK_M4U_ID(M4U_LARB1_ID, 5) +#define M4U_PORT_VENC_BSDMA MTK_M4U_ID(M4U_LARB1_ID, 6) +#define M4U_PORT_VENC_RD_COMV MTK_M4U_ID(M4U_LARB1_ID, 7) +#define M4U_PORT_CAM_IMGI MTK_M4U_ID(M4U_LARB1_ID, 8) +#define M4U_PORT_VENC_CUR_LUMA MTK_M4U_ID(M4U_LARB1_ID, 9) +#define M4U_PORT_VENC_CUR_CHROMA MTK_M4U_ID(M4U_LARB1_ID, 10) +#define M4U_PORT_VENC_REF_LUMA MTK_M4U_ID(M4U_LARB1_ID, 11) +#define M4U_PORT_VENC_REF_CHROMA MTK_M4U_ID(M4U_LARB1_ID, 12) + +/* larb2*/ +#define M4U_PORT_HW_VDEC_MC_EXT MTK_M4U_ID(M4U_LARB2_ID, 0) +#define M4U_PORT_HW_VDEC_PP_EXT MTK_M4U_ID(M4U_LARB2_ID, 1) +#define M4U_PORT_HW_VDEC_VLD_EXT MTK_M4U_ID(M4U_LARB2_ID, 2) +#define M4U_PORT_HW_VDEC_AVC_MV_EXT MTK_M4U_ID(M4U_LARB2_ID, 3) +#define M4U_PORT_HW_VDEC_PRED_RD_EXT MTK_M4U_ID(M4U_LARB2_ID, 4) +#define M4U_PORT_HW_VDEC_PRED_WR_EXT MTK_M4U_ID(M4U_LARB2_ID, 5) +#define M4U_PORT_HW_VDEC_PPWRAP_EXT MTK_M4U_ID(M4U_LARB2_ID, 6) + +#endif -- cgit v1.2.3 From 9d6e371dda7f3294e1b7d2a00d8e77a042b42988 Mon Sep 17 00:00:00 2001 From: Wright Feng Date: Tue, 8 Sep 2020 01:01:57 -0500 Subject: cfg80211: add more comments for ap_isolate in bss_parameters The value of struct bss_parameters::ap_isolate will be -1, 0 or 1. The value -1 means not to change. To prevent developers from thinking ap_isolate is only 0 or 1, I add more comments on it. Signed-off-by: Wright Feng Reviewed-by: Kalle Valo Link: https://lore.kernel.org/r/20200908060157.98846-1-wright.feng@cypress.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index c9bce9bba511..7ad530912b21 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1787,6 +1787,7 @@ struct mpath_info { * (or NULL for no change) * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations + * (0 = no, 1 = yes, -1 = do not change) * @ht_opmode: HT Operation mode * (u16 = opmode, -1 = do not change) * @p2p_ctwindow: P2P CT Window (-1 = no change) -- cgit v1.2.3 From 6aea26ce5a4cf854c1a86f3760753b5e2617578f Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 8 Sep 2020 14:36:53 +0200 Subject: mac80211: rework tx encapsulation offload API The current API (which lets the driver turn on/off per vif directly) has a number of limitations: - it does not deal with AP_VLAN - conditions for enabling (no tkip, no monitor) are only checked at add_interface time - no way to indicate 4-addr support In order to address this, store offload flags in struct ieee80211_vif (easy to extend for decap offload later). mac80211 initially sets the enable flag, but gives the driver a chance to modify it before its settings are applied. In addition to the .add_interface op, a .update_vif_offload op is introduced, which can be used for runtime changes. If a driver can't disable encap offload at runtime, or if it has some extra limitations, it can simply override the flags within those ops. Support for encap offload with 4-address mode interfaces can be enabled by setting a flag from .add_interface or .update_vif_offload. Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20200908123702.88454-6-nbd@nbd.name [resolved conflict with commit aa2092a9bab3 ("ath11k: add raw mode and software crypto support")] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ec148b3e9c41..01612a82aacf 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1606,6 +1606,21 @@ enum ieee80211_vif_flags { IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), }; + +/** + * enum ieee80211_offload_flags - virtual interface offload flags + * + * @IEEE80211_OFFLOAD_ENCAP_ENABLED: tx encapsulation offload is enabled + * The driver supports sending frames passed as 802.3 frames by mac80211. + * It must also support sending 802.11 packets for the same interface. + * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload + */ + +enum ieee80211_offload_flags { + IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0), + IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1), +}; + /** * struct ieee80211_vif - per-interface data * @@ -1626,6 +1641,11 @@ enum ieee80211_vif_flags { * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field + * @offloaad_flags: hardware offload capabilities/flags for this interface. + * These are initialized by mac80211 before calling .add_interface, + * .change_interface or .update_vif_offload and updated by the driver + * within these ops, based on supported features or runtime change + * restrictions. * @hw_queue: hardware queue for each AC * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only * @chanctx_conf: The channel context this interface is assigned to, or %NULL @@ -1662,6 +1682,7 @@ struct ieee80211_vif { struct ieee80211_chanctx_conf __rcu *chanctx_conf; u32 driver_flags; + u32 offload_flags; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; @@ -2328,6 +2349,9 @@ struct ieee80211_txq { * aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx * A-MPDU sessions active while rekeying with Extended Key ID. * + * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation + * offload + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2380,6 +2404,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT, + IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3814,6 +3839,8 @@ enum ieee80211_reconfig_type { * @set_tid_config: Apply TID specific configurations. This callback may sleep. * @reset_tid_config: Reset TID specific configuration for the peer. * This callback may sleep. + * @update_vif_config: Update virtual interface offload flags + * This callback may sleep. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4125,6 +4152,8 @@ struct ieee80211_ops { int (*reset_tid_config)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u8 tids); + void (*update_vif_offload)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); }; /** -- cgit v1.2.3 From c74114d7d51521bd785bf6aa0f90ee87d99bee8a Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 8 Sep 2020 14:36:55 +0200 Subject: mac80211: remove tx status call to ieee80211_sta_register_airtime All drivers using airtime fairness are calling ieee80211_sta_register_airtime directly, now they must. Document this as well. Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20200908123702.88454-8-nbd@nbd.name [johannes: update the documentation to suit] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 01612a82aacf..ca270f7d82b9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1002,7 +1002,8 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @status.ampdu_ack_len: AMPDU ack length * @status.ampdu_len: AMPDU length * @status.antenna: (legacy, kept only for iwlegacy) - * @status.tx_time: airtime consumed for transmission + * @status.tx_time: airtime consumed for transmission; note this is only + * used for WMM AC, not for airtime fairness * @status.is_valid_ack_signal: ACK signal is valid * @status.status_driver_data: driver use area * @ack: union part for pure ACK data @@ -5676,7 +5677,7 @@ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); /** * ieee80211_sta_register_airtime - register airtime usage for a sta/tid * - * Register airtime usage for a given sta on a given tid. The driver can call + * Register airtime usage for a given sta on a given tid. The driver must call * this function to notify mac80211 that a station used a certain amount of * airtime. This information will be used by the TXQ scheduler to schedule * stations in a way that ensures airtime fairness. -- cgit v1.2.3 From cc20ff2c6b5d3e28747c6d30ecd097ea1a4d2502 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 8 Sep 2020 14:36:57 +0200 Subject: mac80211: swap NEED_TXPROCESSING and HW_80211_ENCAP tx flags In order to unify the tx status path, the hw 802.11 encapsulation flag needs to survive the trip to the tx status call. Since we don't have any free bits in info->flags, we need to move one. IEEE80211_TX_INTFL_NEED_TXPROCESSING is only used internally in mac80211, and only before the call into the driver. Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20200908123702.88454-10-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/mac80211.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ca270f7d82b9..3a9ab3c10050 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -720,9 +720,8 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_INTFL_OFFCHAN_TX_OK: Internal to mac80211. Used to indicate * that a frame can be transmitted while the queues are stopped for * off-channel operation. - * @IEEE80211_TX_INTFL_NEED_TXPROCESSING: completely internal to mac80211, - * used to indicate that a pending frame requires TX processing before - * it can be sent out. + * @IEEE80211_TX_CTL_HW_80211_ENCAP: This frame uses hardware encapsulation + * (header conversion) * @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211, * used to indicate that a frame was already retried due to PS * @IEEE80211_TX_INTFL_DONT_ENCRYPT: completely internal to mac80211, @@ -791,7 +790,7 @@ enum mac80211_tx_info_flags { IEEE80211_TX_STAT_AMPDU_NO_BACK = BIT(11), IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12), IEEE80211_TX_INTFL_OFFCHAN_TX_OK = BIT(13), - IEEE80211_TX_INTFL_NEED_TXPROCESSING = BIT(14), + IEEE80211_TX_CTL_HW_80211_ENCAP = BIT(14), IEEE80211_TX_INTFL_RETRIED = BIT(15), IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16), IEEE80211_TX_CTL_NO_PS_BUFFER = BIT(17), @@ -823,8 +822,9 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup - * @IEEE80211_TX_CTRL_HW_80211_ENCAP: This frame uses hardware encapsulation - * (header conversion) + * @IEEE80211_TX_INTCFL_NEED_TXPROCESSING: completely internal to mac80211, + * used to indicate that a pending frame requires TX processing before + * it can be sent out. * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that * has already been assigned to this frame. * @@ -837,7 +837,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_AMSDU = BIT(3), IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), - IEEE80211_TX_CTRL_HW_80211_ENCAP = BIT(6), + IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), }; -- cgit v1.2.3 From 1ff4e8f2dec8b145b451f05320e4f9e01d254ae2 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 8 Sep 2020 14:37:01 +0200 Subject: mac80211: notify the driver when a sta uses 4-address mode This is needed for encapsulation offload of 4-address mode packets Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20200908123702.88454-14-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3a9ab3c10050..07c4dd7ab55f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3842,6 +3842,8 @@ enum ieee80211_reconfig_type { * This callback may sleep. * @update_vif_config: Update virtual interface offload flags * This callback may sleep. + * @sta_set_4addr: Called to notify the driver when a station starts/stops using + * 4-address mode */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4155,6 +4157,8 @@ struct ieee80211_ops { struct ieee80211_sta *sta, u8 tids); void (*update_vif_offload)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); + void (*sta_set_4addr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, bool enabled); }; /** -- cgit v1.2.3 From f02dff93e26bef46f5511f1e8229061bd23c3074 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 8 Sep 2020 14:37:00 +0200 Subject: mac80211: extend ieee80211_tx_status_ext to support bulk free Store processed skbs ready to be freed in a list so the driver bulk free them Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20200908123702.88454-13-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 07c4dd7ab55f..d3c43420779c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1096,12 +1096,14 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) * @rate: The TX rate that was used when sending the packet + * @free_list: list where processed skbs are stored to be free'd by the driver */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; struct rate_info *rate; + struct list_head *free_list; }; /** -- cgit v1.2.3 From 37050e3ab0b3f02819e3d70ab01d97addb810b28 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Tue, 8 Sep 2020 12:03:02 -0700 Subject: ieee80211: redefine S1G bits with GENMASK The S1G capability fields were defined by ORing BITS() together, and expecting a custom macro to use the _SHIFT definitions. Use the Linux kernel GENMASK for the definitions now, and FIELD_{GET,PREP} to access the fields in the future. Take the chance to rename eg. S1G_CAPAB_B0 to the more compact S1G_CAP0. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200908190323.15814-2-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 156 +++++++++++++++++++++++----------------------- 1 file changed, 78 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c47f43e65a2f..53fba39d4ba6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2330,84 +2330,84 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) } /* S1G Capabilities Information field */ -#define S1G_CAPAB_B0_S1G_LONG BIT(0) -#define S1G_CAPAB_B0_SGI_1MHZ BIT(1) -#define S1G_CAPAB_B0_SGI_2MHZ BIT(2) -#define S1G_CAPAB_B0_SGI_4MHZ BIT(3) -#define S1G_CAPAB_B0_SGI_8MHZ BIT(4) -#define S1G_CAPAB_B0_SGI_16MHZ BIT(5) -#define S1G_CAPAB_B0_SUPP_CH_WIDTH_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B0_SUPP_CH_WIDTH_SHIFT 6 - -#define S1G_CAPAB_B1_RX_LDPC BIT(0) -#define S1G_CAPAB_B1_TX_STBC BIT(1) -#define S1G_CAPAB_B1_RX_STBC BIT(2) -#define S1G_CAPAB_B1_SU_BFER BIT(3) -#define S1G_CAPAB_B1_SU_BFEE BIT(4) -#define S1G_CAPAB_B1_BFEE_STS_MASK (BIT(5) | BIT(6) | BIT(7)) -#define S1G_CAPAB_B1_BFEE_STS_SHIFT 5 - -#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_MASK (BIT(0) | BIT(1) | BIT(2)) -#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_SHIFT 0 -#define S1G_CAPAB_B2_MU_BFER BIT(3) -#define S1G_CAPAB_B2_MU_BFEE BIT(4) -#define S1G_CAPAB_B2_PLUS_HTC_VHT BIT(5) -#define S1G_CAPAB_B2_TRAVELING_PILOT_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B2_TRAVELING_PILOT_SHIFT 6 - -#define S1G_CAPAB_B3_RD_RESPONDER BIT(0) -#define S1G_CAPAB_B3_HT_DELAYED_BA BIT(1) -#define S1G_CAPAB_B3_MAX_MPDU_LEN BIT(2) -#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_MASK (BIT(3) | BIT(4)) -#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_SHIFT 3 -#define S1G_CAPAB_B3_MIN_MPDU_START_MASK (BIT(5) | BIT(6) | BIT(7)) -#define S1G_CAPAB_B3_MIN_MPDU_START_SHIFT 5 - -#define S1G_CAPAB_B4_UPLINK_SYNC BIT(0) -#define S1G_CAPAB_B4_DYNAMIC_AID BIT(1) -#define S1G_CAPAB_B4_BAT BIT(2) -#define S1G_CAPAB_B4_TIME_ADE BIT(3) -#define S1G_CAPAB_B4_NON_TIM BIT(4) -#define S1G_CAPAB_B4_GROUP_AID BIT(5) -#define S1G_CAPAB_B4_STA_TYPE_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B4_STA_TYPE_SHIFT 6 - -#define S1G_CAPAB_B5_CENT_AUTH_CONTROL BIT(0) -#define S1G_CAPAB_B5_DIST_AUTH_CONTROL BIT(1) -#define S1G_CAPAB_B5_AMSDU BIT(2) -#define S1G_CAPAB_B5_AMPDU BIT(3) -#define S1G_CAPAB_B5_ASYMMETRIC_BA BIT(4) -#define S1G_CAPAB_B5_FLOW_CONTROL BIT(5) -#define S1G_CAPAB_B5_SECTORIZED_BEAM_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B5_SECTORIZED_BEAM_SHIFT 6 - -#define S1G_CAPAB_B6_OBSS_MITIGATION BIT(0) -#define S1G_CAPAB_B6_FRAGMENT_BA BIT(1) -#define S1G_CAPAB_B6_NDP_PS_POLL BIT(2) -#define S1G_CAPAB_B6_RAW_OPERATION BIT(3) -#define S1G_CAPAB_B6_PAGE_SLICING BIT(4) -#define S1G_CAPAB_B6_TXOP_SHARING_IMP_ACK BIT(5) -#define S1G_CAPAB_B6_VHT_LINK_ADAPT_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B6_VHT_LINK_ADAPT_SHIFT 6 - -#define S1G_CAPAB_B7_TACK_AS_PS_POLL BIT(0) -#define S1G_CAPAB_B7_DUP_1MHZ BIT(1) -#define S1G_CAPAB_B7_MCS_NEGOTIATION BIT(2) -#define S1G_CAPAB_B7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) -#define S1G_CAPAB_B7_NDP_BFING_REPORT_POLL BIT(4) -#define S1G_CAPAB_B7_UNSOLICITED_DYN_AID BIT(5) -#define S1G_CAPAB_B7_SECTOR_TRAINING_OPERATION BIT(6) -#define S1G_CAPAB_B7_TEMP_PS_MODE_SWITCH BIT(7) - -#define S1G_CAPAB_B8_TWT_GROUPING BIT(0) -#define S1G_CAPAB_B8_BDT BIT(1) -#define S1G_CAPAB_B8_COLOR_MASK (BIT(2) | BIT(3) | BIT(4)) -#define S1G_CAPAB_B8_COLOR_SHIFT 2 -#define S1G_CAPAB_B8_TWT_REQUEST BIT(5) -#define S1G_CAPAB_B8_TWT_RESPOND BIT(6) -#define S1G_CAPAB_B8_PV1_FRAME BIT(7) - -#define S1G_CAPAB_B9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) +#define S1G_CAP0_S1G_LONG BIT(0) +#define S1G_CAP0_SGI_1MHZ BIT(1) +#define S1G_CAP0_SGI_2MHZ BIT(2) +#define S1G_CAP0_SGI_4MHZ BIT(3) +#define S1G_CAP0_SGI_8MHZ BIT(4) +#define S1G_CAP0_SGI_16MHZ BIT(5) +#define S1G_CAP0_SUPP_CH_WIDTH GENMASK(7, 6) + +#define S1G_SUPP_CH_WIDTH_2 0 +#define S1G_SUPP_CH_WIDTH_4 1 +#define S1G_SUPP_CH_WIDTH_8 2 +#define S1G_SUPP_CH_WIDTH_16 3 +#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \ + cap[0])) << 1) + +#define S1G_CAP1_RX_LDPC BIT(0) +#define S1G_CAP1_TX_STBC BIT(1) +#define S1G_CAP1_RX_STBC BIT(2) +#define S1G_CAP1_SU_BFER BIT(3) +#define S1G_CAP1_SU_BFEE BIT(4) +#define S1G_CAP1_BFEE_STS GENMASK(7, 5) + +#define S1G_CAP2_SOUNDING_DIMENSIONS GENMASK(2, 0) +#define S1G_CAP2_MU_BFER BIT(3) +#define S1G_CAP2_MU_BFEE BIT(4) +#define S1G_CAP2_PLUS_HTC_VHT BIT(5) +#define S1G_CAP2_TRAVELING_PILOT GENMASK(7, 6) + +#define S1G_CAP3_RD_RESPONDER BIT(0) +#define S1G_CAP3_HT_DELAYED_BA BIT(1) +#define S1G_CAP3_MAX_MPDU_LEN BIT(2) +#define S1G_CAP3_MAX_AMPDU_LEN_EXP GENMASK(4, 3) +#define S1G_CAP3_MIN_MPDU_START GENMASK(7, 5) + +#define S1G_CAP4_UPLINK_SYNC BIT(0) +#define S1G_CAP4_DYNAMIC_AID BIT(1) +#define S1G_CAP4_BAT BIT(2) +#define S1G_CAP4_TIME_ADE BIT(3) +#define S1G_CAP4_NON_TIM BIT(4) +#define S1G_CAP4_GROUP_AID BIT(5) +#define S1G_CAP4_STA_TYPE GENMASK(7, 6) + +#define S1G_CAP5_CENT_AUTH_CONTROL BIT(0) +#define S1G_CAP5_DIST_AUTH_CONTROL BIT(1) +#define S1G_CAP5_AMSDU BIT(2) +#define S1G_CAP5_AMPDU BIT(3) +#define S1G_CAP5_ASYMMETRIC_BA BIT(4) +#define S1G_CAP5_FLOW_CONTROL BIT(5) +#define S1G_CAP5_SECTORIZED_BEAM GENMASK(7, 6) + +#define S1G_CAP6_OBSS_MITIGATION BIT(0) +#define S1G_CAP6_FRAGMENT_BA BIT(1) +#define S1G_CAP6_NDP_PS_POLL BIT(2) +#define S1G_CAP6_RAW_OPERATION BIT(3) +#define S1G_CAP6_PAGE_SLICING BIT(4) +#define S1G_CAP6_TXOP_SHARING_IMP_ACK BIT(5) +#define S1G_CAP6_VHT_LINK_ADAPT GENMASK(7, 6) + +#define S1G_CAP7_TACK_AS_PS_POLL BIT(0) +#define S1G_CAP7_DUP_1MHZ BIT(1) +#define S1G_CAP7_MCS_NEGOTIATION BIT(2) +#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) +#define S1G_CAP7_NDP_BFING_REPORT_POLL BIT(4) +#define S1G_CAP7_UNSOLICITED_DYN_AID BIT(5) +#define S1G_CAP7_SECTOR_TRAINING_OPERATION BIT(6) +#define S1G_CAP7_TEMP_PS_MODE_SWITCH BIT(7) + +#define S1G_CAP8_TWT_GROUPING BIT(0) +#define S1G_CAP8_BDT BIT(1) +#define S1G_CAP8_COLOR GENMASK(4, 2) +#define S1G_CAP8_TWT_REQUEST BIT(5) +#define S1G_CAP8_TWT_RESPOND BIT(6) +#define S1G_CAP8_PV1_FRAME BIT(7) + +#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) + +#define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) +#define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 -- cgit v1.2.3 From d65a977087f94f3bb97f351798d864556063109a Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Tue, 8 Sep 2020 12:03:03 -0700 Subject: nl80211: advertise supported channel width in S1G S1G supports 5 channel widths: 1, 2, 4, 8, and 16. One channel width is allowed per frequency in each operating class, so it makes more sense to advertise the specific channel width allowed. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200908190323.15814-3-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 15 +++++++++++++++ include/uapi/linux/nl80211.h | 15 +++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7ad530912b21..2a7561743717 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -96,6 +96,16 @@ struct wiphy; * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted * on this channel. * @IEEE80211_CHAN_NO_HE: HE operation is not permitted on this channel. + * @IEEE80211_CHAN_1MHZ: 1 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_2MHZ: 2 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_4MHZ: 4 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_8MHZ: 8 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_16MHZ: 16 MHz bandwidth is permitted + * on this channel. * */ enum ieee80211_channel_flags { @@ -113,6 +123,11 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_20MHZ = 1<<11, IEEE80211_CHAN_NO_10MHZ = 1<<12, IEEE80211_CHAN_NO_HE = 1<<13, + IEEE80211_CHAN_1MHZ = 1<<14, + IEEE80211_CHAN_2MHZ = 1<<15, + IEEE80211_CHAN_4MHZ = 1<<16, + IEEE80211_CHAN_8MHZ = 1<<17, + IEEE80211_CHAN_16MHZ = 1<<18, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 0584e0d349f0..4e119c6afa31 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3737,6 +3737,16 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_NO_HE: HE operation is not allowed on this channel * in current regulatory domain. * @NL80211_FREQUENCY_ATTR_OFFSET: frequency offset in KHz + * @NL80211_FREQUENCY_ATTR_1MHZ: 1 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_2MHZ: 2 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_4MHZ: 4 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_8MHZ: 8 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_16MHZ: 16 MHz operation is allowed + * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -3768,6 +3778,11 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_WMM, NL80211_FREQUENCY_ATTR_NO_HE, NL80211_FREQUENCY_ATTR_OFFSET, + NL80211_FREQUENCY_ATTR_1MHZ, + NL80211_FREQUENCY_ATTR_2MHZ, + NL80211_FREQUENCY_ATTR_4MHZ, + NL80211_FREQUENCY_ATTR_8MHZ, + NL80211_FREQUENCY_ATTR_16MHZ, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, -- cgit v1.2.3 From 11b34737b18a70c74d5cf13ee58d36e95879013c Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Tue, 8 Sep 2020 12:03:06 -0700 Subject: nl80211: support setting S1G channels S1G channels have a single width defined per frequency, so derive it from the channel flags with ieee80211_s1g_channel_width(). Also support setting an S1G channel where control frequency may differ from operating, and add some basic validation to ensure the control channel is with the operating. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200908190323.15814-6-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2a7561743717..44db9f80e495 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5294,6 +5294,16 @@ ieee80211_channel_to_khz(const struct ieee80211_channel *chan) return MHZ_TO_KHZ(chan->center_freq) + chan->freq_offset; } +/** + * ieee80211_s1g_channel_width - get allowed channel width from @chan + * + * Only allowed for band NL80211_BAND_S1GHZ + * @chan: channel + * Return: The allowed channel width for this center_freq + */ +enum nl80211_chan_width +ieee80211_s1g_channel_width(const struct ieee80211_channel *chan); + /** * ieee80211_channel_to_freq_khz - convert channel number to frequency * @chan: channel number -- cgit v1.2.3 From 291c49ded2fda1fd0d7bd6056de99fe47d2332e6 Mon Sep 17 00:00:00 2001 From: Aloka Dixit Date: Fri, 11 Sep 2020 00:05:29 +0000 Subject: nl80211: Add FILS discovery support FILS discovery attribute, NL80211_ATTR_FILS_DISCOVERY, is nested which supports following parameters as given in IEEE Std 802.11ai-2016, Annex C.3 MIB detail: (1) NL80211_FILS_DISCOVERY_ATTR_INT_MIN - Minimum packet interval (2) NL80211_FILS_DISCOVERY_ATTR_INT_MAX - Maximum packet interval (3) NL80211_FILS_DISCOVERY_ATTR_TMPL - Template data Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/20200805011838.28166-2-alokad@codeaurora.org [fix attribute and other names, use NLA_RANGE(), use policy only once] Link: https://lore.kernel.org/r/010101747a7b38a8-306f06b2-9061-4baf-81c1-054a42a18e22-000000@us-west-2.amazonses.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 19 +++++++++++++++++++ include/uapi/linux/nl80211.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 44db9f80e495..c90700727945 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1082,6 +1082,23 @@ struct cfg80211_acl_data { struct mac_address mac_addrs[]; }; +/** + * struct cfg80211_fils_discovery - FILS discovery parameters from + * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @min_interval: Minimum packet interval in TUs (0 - 10000) + * @max_interval: Maximum packet interval in TUs (0 - 10000) + * @tmpl_len: Template length + * @tmpl: Template data for FILS discovery frame including the action + * frame headers. + */ +struct cfg80211_fils_discovery { + u32 min_interval; + u32 max_interval; + size_t tmpl_len; + const u8 *tmpl; +}; + /** * enum cfg80211_ap_settings_flags - AP settings flags * @@ -1129,6 +1146,7 @@ enum cfg80211_ap_settings_flags { * @he_obss_pd: OBSS Packet Detection settings * @he_bss_color: BSS Color settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) + * @fils_discovery: FILS discovery transmission parameters */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1159,6 +1177,7 @@ struct cfg80211_ap_settings { u32 flags; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; + struct cfg80211_fils_discovery fils_discovery; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 4e119c6afa31..ad2bea3b07e3 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2513,6 +2513,10 @@ enum nl80211_commands { * @NL80211_ATTR_HE_6GHZ_CAPABILITY: HE 6 GHz Band Capability element (from * association request when used with NL80211_CMD_NEW_STATION). * + * @NL80211_ATTR_FILS_DISCOVERY: Optional parameter to configure FILS + * discovery. It is a nested attribute, see + * &enum nl80211_fils_discovery_attributes. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2995,6 +2999,8 @@ enum nl80211_attrs { NL80211_ATTR_HE_6GHZ_CAPABILITY, + NL80211_ATTR_FILS_DISCOVERY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -5867,6 +5873,9 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP: Device wants to do SAE authentication * in AP mode (SAE password is passed as part of the start AP command). * + * @NL80211_EXT_FEATURE_FILS_DISCOVERY: Driver/device supports FILS discovery + * frames transmission + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5925,6 +5934,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, NL80211_EXT_FEATURE_SAE_OFFLOAD_AP, + NL80211_EXT_FEATURE_FILS_DISCOVERY, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -7019,4 +7029,38 @@ enum nl80211_iftype_akm_attributes { NL80211_IFTYPE_AKM_ATTR_MAX = __NL80211_IFTYPE_AKM_ATTR_LAST - 1, }; +/** + * enum nl80211_fils_discovery_attributes - FILS discovery configuration + * from IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @__NL80211_FILS_DISCOVERY_ATTR_INVALID: Invalid + * + * @NL80211_FILS_DISCOVERY_ATTR_INT_MIN: Minimum packet interval (u32, TU). + * Allowed range: 0..10000 (TU = Time Unit) + * @NL80211_FILS_DISCOVERY_ATTR_INT_MAX: Maximum packet interval (u32, TU). + * Allowed range: 0..10000 (TU = Time Unit) + * @NL80211_FILS_DISCOVERY_ATTR_TMPL: Template data for FILS discovery action + * frame including the headers. + * + * @__NL80211_FILS_DISCOVERY_ATTR_LAST: Internal + * @NL80211_FILS_DISCOVERY_ATTR_MAX: highest attribute + */ +enum nl80211_fils_discovery_attributes { + __NL80211_FILS_DISCOVERY_ATTR_INVALID, + + NL80211_FILS_DISCOVERY_ATTR_INT_MIN, + NL80211_FILS_DISCOVERY_ATTR_INT_MAX, + NL80211_FILS_DISCOVERY_ATTR_TMPL, + + /* keep last */ + __NL80211_FILS_DISCOVERY_ATTR_LAST, + NL80211_FILS_DISCOVERY_ATTR_MAX = __NL80211_FILS_DISCOVERY_ATTR_LAST - 1 +}; + +/* + * FILS discovery template minimum length with action frame headers and + * mandatory fields. + */ +#define NL80211_FILS_DISCOVERY_TMPL_MIN_LEN 42 + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 295b02c4be74bebf988593b8322369513fcecf68 Mon Sep 17 00:00:00 2001 From: Aloka Dixit Date: Fri, 11 Sep 2020 00:05:31 +0000 Subject: mac80211: Add FILS discovery support This patch adds mac80211 support to configure FILS discovery transmission. Changes include functions to store and retrieve FILS discovery template, minimum and maximum packet intervals. Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/20200805011838.28166-3-alokad@codeaurora.org [remove SUPPORTS_FILS_DISCOVERY, driver can just set wiphy info] Link: https://lore.kernel.org/r/010101747a7b3cbb-6edaa89c-436d-4391-8765-61456d7f5f4e-000000@us-west-2.amazonses.com Signed-off-by: Johannes Berg --- include/net/mac80211.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d3c43420779c..9381f00d0942 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -317,6 +317,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_TWT: TWT status changed * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed + * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed. * */ enum ieee80211_bss_change { @@ -350,6 +351,7 @@ enum ieee80211_bss_change { BSS_CHANGED_TWT = 1<<27, BSS_CHANGED_HE_OBSS_PD = 1<<28, BSS_CHANGED_HE_BSS_COLOR = 1<<29, + BSS_CHANGED_FILS_DISCOVERY = 1<<30, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -490,6 +492,18 @@ struct ieee80211_ftm_responder_params { size_t civicloc_len; }; +/** + * struct ieee80211_fils_discovery - FILS discovery parameters from + * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @min_interval: Minimum packet interval in TUs (0 - 10000) + * @max_interval: Maximum packet interval in TUs (0 - 10000) + */ +struct ieee80211_fils_discovery { + u32 min_interval; + u32 max_interval; +}; + /** * struct ieee80211_bss_conf - holds the BSS's changing parameters * @@ -607,6 +621,7 @@ struct ieee80211_ftm_responder_params { * @he_oper: HE operation information of the AP we are connected to * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE + * @fils_discovery: FILS discovery configuration */ struct ieee80211_bss_conf { const u8 *bssid; @@ -674,6 +689,7 @@ struct ieee80211_bss_conf { } he_oper; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; + struct ieee80211_fils_discovery fils_discovery; }; /** @@ -6629,4 +6645,15 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, */ bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable); +/** + * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template. + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * The driver is responsible for freeing the returned skb. + * + * Return: FILS discovery template. %NULL on error. + */ +struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); #endif /* MAC80211_H */ -- cgit v1.2.3 From 7443dcd1f1718a355e9c4ebeb7e95c3f9f27bb5f Mon Sep 17 00:00:00 2001 From: Aloka Dixit Date: Fri, 11 Sep 2020 00:33:00 +0000 Subject: nl80211: Unsolicited broadcast probe response support This patch adds new attributes to support unsolicited broadcast probe response transmission used for in-band discovery in 6GHz band (IEEE P802.11ax/D6.0 26.17.2.3.2, AP behavior for fast passive scanning). The new attribute, NL80211_ATTR_UNSOL_BCAST_PROBE_RESP, is nested which supports following parameters: (1) NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT - Packet interval (2) NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL - Template data Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/010101747a946698-aac263ae-2ed3-4dab-9590-0bc7131214e1-000000@us-west-2.amazonses.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 18 ++++++++++++++++++ include/uapi/linux/nl80211.h | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index c90700727945..93d666a571da 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1099,6 +1099,22 @@ struct cfg80211_fils_discovery { const u8 *tmpl; }; +/** + * struct cfg80211_unsol_bcast_probe_resp - Unsolicited broadcast probe + * response parameters in 6GHz. + * + * @interval: Packet interval in TUs. Maximum allowed is 20 TU, as mentioned + * in IEEE P802.11ax/D6.0 26.17.2.3.2 - AP behavior for fast passive + * scanning + * @tmpl_len: Template length + * @tmpl: Template data for probe response + */ +struct cfg80211_unsol_bcast_probe_resp { + u32 interval; + size_t tmpl_len; + const u8 *tmpl; +}; + /** * enum cfg80211_ap_settings_flags - AP settings flags * @@ -1147,6 +1163,7 @@ enum cfg80211_ap_settings_flags { * @he_bss_color: BSS Color settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters + * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1178,6 +1195,7 @@ struct cfg80211_ap_settings { struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; + struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ad2bea3b07e3..bdc90b8dfd24 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2517,6 +2517,10 @@ enum nl80211_commands { * discovery. It is a nested attribute, see * &enum nl80211_fils_discovery_attributes. * + * @NL80211_ATTR_UNSOL_BCAST_PROBE_RESP: Optional parameter to configure + * unsolicited broadcast probe response. It is a nested attribute, see + * &enum nl80211_unsol_bcast_probe_resp_attributes. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3001,6 +3005,8 @@ enum nl80211_attrs { NL80211_ATTR_FILS_DISCOVERY, + NL80211_ATTR_UNSOL_BCAST_PROBE_RESP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -5876,6 +5882,9 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_FILS_DISCOVERY: Driver/device supports FILS discovery * frames transmission * + * @NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP: Driver/device supports + * unsolicited broadcast probe response transmission + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5935,6 +5944,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, NL80211_EXT_FEATURE_SAE_OFFLOAD_AP, NL80211_EXT_FEATURE_FILS_DISCOVERY, + NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -7063,4 +7073,30 @@ enum nl80211_fils_discovery_attributes { */ #define NL80211_FILS_DISCOVERY_TMPL_MIN_LEN 42 +/** + * enum nl80211_unsol_bcast_probe_resp_attributes - Unsolicited broadcast probe + * response configuration. Applicable only in 6GHz. + * + * @__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INVALID: Invalid + * + * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT: Maximum packet interval (u32, TU). + * Allowed range: 0..20 (TU = Time Unit). IEEE P802.11ax/D6.0 + * 26.17.2.3.2 (AP behavior for fast passive scanning). + * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL: Unsolicited broadcast probe response + * frame template (binary). + * + * @__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST: Internal + * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX: highest attribute + */ +enum nl80211_unsol_bcast_probe_resp_attributes { + __NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INVALID, + + NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT, + NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL, + + /* keep last */ + __NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST, + NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX = + __NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST - 1 +}; #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 632189a0180fdaae6715c83c68cc5c8998d6c841 Mon Sep 17 00:00:00 2001 From: Aloka Dixit Date: Fri, 11 Sep 2020 00:33:01 +0000 Subject: mac80211: Unsolicited broadcast probe response support This patch adds mac80211 support to configure unsolicited broadcast probe response transmission for in-band discovery in 6GHz. Changes include functions to store and retrieve probe response template, and packet interval (0 - 20 TUs). Setting interval to 0 disables the unsolicited broadcast probe response transmission. Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/010101747a946b35-ad25858a-1f1f-48df-909e-dc7bf26d9169-000000@us-west-2.amazonses.com Signed-off-by: Johannes Berg --- include/net/mac80211.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9381f00d0942..f0908b567d65 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -318,6 +318,8 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed. + * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response + * status changed. * */ enum ieee80211_bss_change { @@ -352,6 +354,7 @@ enum ieee80211_bss_change { BSS_CHANGED_HE_OBSS_PD = 1<<28, BSS_CHANGED_HE_BSS_COLOR = 1<<29, BSS_CHANGED_FILS_DISCOVERY = 1<<30, + BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = 1<<31, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -622,6 +625,8 @@ struct ieee80211_fils_discovery { * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE * @fils_discovery: FILS discovery configuration + * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response + * interval. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -690,6 +695,7 @@ struct ieee80211_bss_conf { struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; struct ieee80211_fils_discovery fils_discovery; + u32 unsol_bcast_probe_resp_interval; }; /** @@ -6656,4 +6662,18 @@ bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable); */ struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, struct ieee80211_vif *vif); + +/** + * ieee80211_get_unsol_bcast_probe_resp_tmpl - Get unsolicited broadcast + * probe response template. + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * The driver is responsible for freeing the returned skb. + * + * Return: Unsolicited broadcast probe response template. %NULL on error. + */ +struct sk_buff * +ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); #endif /* MAC80211_H */ -- cgit v1.2.3 From 9ff167e178224069221a5771c12dfea9737bf3a3 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Sep 2020 13:19:22 +0200 Subject: cfg80211: add missing kernel-doc for S1G band capabilities Add missing kernel-doc for the S1G band capabilities in the per band data. Link: https://lore.kernel.org/r/20200918131921.08c893cd73a1.Id71583c37baca8a9a3329426e02b66d9ab65ac03@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 93d666a571da..10c2cc8f0efc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -465,6 +465,7 @@ struct ieee80211_sta_s1g_cap { * @ht_cap: HT capabilities in this band * @vht_cap: VHT capabilities in this band * @edmg_cap: EDMG capabilities in this band + * @s1g_cap: S1G capabilities in this band (S1B band only, of course) * @n_iftype_data: number of iftype data entries * @iftype_data: interface type data entries. Note that the bits in * @types_mask inside this structure cannot overlap (i.e. only -- cgit v1.2.3 From 7fba53ebb5b2d89d95b697f4c42c73c6fb7ba0c6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Sep 2020 13:21:16 +0200 Subject: mac80211: fix some encapsulation offload kernel-doc Add a missing kernel-doc entry for the offload_flags, and correct the name of the update_vif_offload method. Link: https://lore.kernel.org/r/20200918132115.d46a0915ba8a.Ibba536d04a5a5fb655f8ef6e51b247457bfda4ca@changeid Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f0908b567d65..e90089d104b0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1690,6 +1690,8 @@ enum ieee80211_offload_flags { * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped, * protected by fq->lock. + * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see + * &enum ieee80211_offload_flags. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -3864,7 +3866,7 @@ enum ieee80211_reconfig_type { * @set_tid_config: Apply TID specific configurations. This callback may sleep. * @reset_tid_config: Reset TID specific configuration for the peer. * This callback may sleep. - * @update_vif_config: Update virtual interface offload flags + * @update_vif_offload: Update virtual interface offload flags * This callback may sleep. * @sta_set_4addr: Called to notify the driver when a station starts/stops using * 4-address mode -- cgit v1.2.3 From 9026118f20e28f202dab34f219bbb831ffb8c4dc Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Tue, 8 Sep 2020 21:15:20 +0800 Subject: soundwire: Add generic bandwidth allocation algorithm This algorithm computes bus parameters like clock frequency, frame shape and port transport parameters based on active stream(s) running on the bus. Developers can also implement their own .compute_params() callback for specific resource management algorithm, and set if before calling sdw_add_bus_master() Credits: this patch is based on an earlier internal contribution by Vinod Koul, Sanyog Kale, Shreyas Nc and Hardik Shah. All hard-coded values were removed from the initial contribution to use BIOS information instead. Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200908131520.5712-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 790823d2d33b..de9ea2ce2d35 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -964,6 +964,9 @@ struct sdw_stream_runtime { struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name); void sdw_release_stream(struct sdw_stream_runtime *stream); + +int sdw_compute_params(struct sdw_bus *bus); + int sdw_stream_add_master(struct sdw_bus *bus, struct sdw_stream_config *stream_config, struct sdw_port_config *port_config, -- cgit v1.2.3 From c6ff213fe5b8696c9539a1b34ff03de9306dfff9 Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Tue, 8 Sep 2020 18:01:48 +0200 Subject: fuse: add submount support to - Add fuse_attr.flags - Add FUSE_ATTR_SUBMOUNT This is a flag for fuse_attr.flags that indicates that the given entry resides on a different filesystem than the parent, and as such should have a different st_dev. - Add FUSE_SUBMOUNTS The client sets this flag if it supports automounting directories. Signed-off-by: Max Reitz Signed-off-by: Miklos Szeredi --- include/uapi/linux/fuse.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 8899e4862309..7233502ea991 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -172,6 +172,9 @@ * - add FUSE_WRITE_KILL_PRIV flag * - add FUSE_SETUPMAPPING and FUSE_REMOVEMAPPING * - add map_alignment to fuse_init_out, add FUSE_MAP_ALIGNMENT flag + * + * 7.32 + * - add flags to fuse_attr, add FUSE_ATTR_SUBMOUNT, add FUSE_SUBMOUNTS */ #ifndef _LINUX_FUSE_H @@ -207,7 +210,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 31 +#define FUSE_KERNEL_MINOR_VERSION 32 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -231,7 +234,7 @@ struct fuse_attr { uint32_t gid; uint32_t rdev; uint32_t blksize; - uint32_t padding; + uint32_t flags; }; struct fuse_kstatfs { @@ -316,6 +319,7 @@ struct fuse_file_lock { * FUSE_MAP_ALIGNMENT: init_out.map_alignment contains log2(byte alignment) for * foffset and moffset fields in struct * fuse_setupmapping_out and fuse_removemapping_one. + * FUSE_SUBMOUNTS: kernel supports auto-mounting directory submounts */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -344,6 +348,7 @@ struct fuse_file_lock { #define FUSE_NO_OPENDIR_SUPPORT (1 << 24) #define FUSE_EXPLICIT_INVAL_DATA (1 << 25) #define FUSE_MAP_ALIGNMENT (1 << 26) +#define FUSE_SUBMOUNTS (1 << 27) /** * CUSE INIT request/reply flags @@ -419,6 +424,13 @@ struct fuse_file_lock { */ #define FUSE_FSYNC_FDATASYNC (1 << 0) +/** + * fuse_attr flags + * + * FUSE_ATTR_SUBMOUNT: Object is a submount root + */ +#define FUSE_ATTR_SUBMOUNT (1 << 0) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ -- cgit v1.2.3 From 264c03a245de7c5b1cc3836db45de6b991f877ca Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 14 Sep 2020 16:34:07 +0100 Subject: stacktrace: Remove reliable argument from arch_stack_walk() callback Currently the callback passed to arch_stack_walk() has an argument called reliable passed to it to indicate if the stack entry is reliable, a comment says that this is used by some printk() consumers. However in the current kernel none of the arch_stack_walk() implementations ever set this flag to true and the only callback implementation we have is in the generic stacktrace code which ignores the flag. It therefore appears that this flag is redundant so we can simplify and clarify things by removing it. Signed-off-by: Mark Brown Reviewed-by: Miroslav Benes Link: https://lore.kernel.org/r/20200914153409.25097-2-broonie@kernel.org Signed-off-by: Will Deacon --- include/linux/stacktrace.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index b7af8cc13eda..50e2df30b0aa 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -29,14 +29,11 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); * stack_trace_consume_fn - Callback for arch_stack_walk() * @cookie: Caller supplied pointer handed back by arch_stack_walk() * @addr: The stack entry address to consume - * @reliable: True when the stack entry is reliable. Required by - * some printk based consumers. * * Return: True, if the entry was consumed or skipped * False, if there is no space left to store */ -typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr, - bool reliable); +typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr); /** * arch_stack_walk - Architecture specific function to walk the stack * @consume_entry: Callback which is invoked by the architecture code for -- cgit v1.2.3 From b9df46d08a8d098ea2124cb9e3b84458a474b4d4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 18 Sep 2020 09:19:43 -0400 Subject: pNFS/flexfiles: Be consistent about mirror index types A mirror index is always of type u32. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9408f3252c8e..69cb46f7b8d2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1611,8 +1611,8 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_commit_idx; /* ds index if ds_clp is set */ - int pgio_mirror_idx;/* mirror index in pgio layer */ + u32 ds_commit_idx; /* ds index if ds_clp is set */ + u32 pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From 376ceb31ff879c2ee6b48eef841d6fa7720f6f43 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Thu, 17 Sep 2020 12:02:23 +0300 Subject: RDMA: Fix link active_speed size According to the IB spec active_speed size should be u16 and not u8 as before. Changing it to allow further extensions in offered speeds. Link: https://lore.kernel.org/r/20200917090223.1018224-4-leon@kernel.org Signed-off-by: Aharon Landau Reviewed-by: Michael Guralnik Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index c0b2fa7e9b95..a7e203bcb012 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -535,7 +535,8 @@ enum ib_port_speed { IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, - IB_SPEED_HDR = 64 + IB_SPEED_HDR = 64, + IB_SPEED_NDR = 128, }; /** @@ -669,7 +670,7 @@ struct ib_port_attr { u8 subnet_timeout; u8 init_type_reply; u8 active_width; - u8 active_speed; + u16 active_speed; u8 phys_state; u16 port_cap_flags2; }; @@ -4410,7 +4411,7 @@ void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); -int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width); +int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u16 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) { -- cgit v1.2.3 From 2312c291f6ac340af88eee0867fdfdfa2299ffc3 Mon Sep 17 00:00:00 2001 From: David Heidelberg Date: Fri, 14 Aug 2020 00:34:01 +0300 Subject: dt-bindings: power: supply: Add device-tree binding for Summit SMB3xx Summit SMB3xx series is a Programmable Switching Li+ Battery Charger. This patch adds device-tree binding for Summit SMB345, SMB347 and SMB358 chargers. Signed-off-by: David Heidelberg Signed-off-by: Dmitry Osipenko Reviewed-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/power/summit,smb347-charger.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/dt-bindings/power/summit,smb347-charger.h (limited to 'include') diff --git a/include/dt-bindings/power/summit,smb347-charger.h b/include/dt-bindings/power/summit,smb347-charger.h new file mode 100644 index 000000000000..d918bf321a71 --- /dev/null +++ b/include/dt-bindings/power/summit,smb347-charger.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0-or-later or MIT) */ +/* + * Author: David Heidelberg + */ + +#ifndef _DT_BINDINGS_SMB347_CHARGER_H +#define _DT_BINDINGS_SMB347_CHARGER_H + +/* Charging compensation method */ +#define SMB3XX_SOFT_TEMP_COMPENSATE_NONE 0 +#define SMB3XX_SOFT_TEMP_COMPENSATE_CURRENT 1 +#define SMB3XX_SOFT_TEMP_COMPENSATE_VOLTAGE 2 + +/* Charging enable control */ +#define SMB3XX_CHG_ENABLE_SW 0 +#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_LOW 1 +#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH 2 + +#endif -- cgit v1.2.3 From 775edf7856d81fde852968212cd58fc9a3f8cd7d Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 17 Sep 2020 12:07:45 +0200 Subject: soc/tegra: fuse: Extract tegra_get_platform() This function extracts the PRE_SI_PLATFORM field from the HIDREV register and can be used to determine which platform the kernel runs on (silicon, simulation, ...). Note that while only Tegra194 and later define this field, it should be safe to call this on prior generations as well since this field should read as 0, indicating silicon. Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- include/soc/tegra/fuse.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h index 1097feca41ed..214908fc5581 100644 --- a/include/soc/tegra/fuse.h +++ b/include/soc/tegra/fuse.h @@ -23,6 +23,7 @@ u32 tegra_read_chipid(void); u8 tegra_get_chip_id(void); +u8 tegra_get_platform(void); enum tegra_revision { TEGRA_REVISION_UNKNOWN = 0, -- cgit v1.2.3 From 52e6d399a41da68125ec107f5f5f688a74ab7ac4 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 17 Sep 2020 12:07:46 +0200 Subject: soc/tegra: fuse: Implement tegra_is_silicon() This function can be used by drivers to determine whether code is running on silicon or on a simulation platform. Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- include/soc/tegra/fuse.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h index 214908fc5581..a9db917a1d06 100644 --- a/include/soc/tegra/fuse.h +++ b/include/soc/tegra/fuse.h @@ -24,6 +24,7 @@ u32 tegra_read_chipid(void); u8 tegra_get_chip_id(void); u8 tegra_get_platform(void); +bool tegra_is_silicon(void); enum tegra_revision { TEGRA_REVISION_UNKNOWN = 0, -- cgit v1.2.3 From 1f44febf71ba3d8a8694669197ec5a384c8d3011 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 17 Sep 2020 12:07:47 +0200 Subject: soc/tegra: fuse: Add Tegra234 support Add support for FUSE block found on the Tegra234 SoC, which is largely similar to the IP found on previous generations. Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- include/soc/tegra/fuse.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h index a9db917a1d06..c702bd2911bc 100644 --- a/include/soc/tegra/fuse.h +++ b/include/soc/tegra/fuse.h @@ -14,6 +14,7 @@ #define TEGRA210 0x21 #define TEGRA186 0x18 #define TEGRA194 0x19 +#define TEGRA234 0x23 #define TEGRA_FUSE_SKU_CALIB_0 0xf0 #define TEGRA30_FUSE_SATA_CALIB 0x124 -- cgit v1.2.3 From 639448912ba17a9af9e759efbab37d36c6e29dea Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 17 Sep 2020 12:07:52 +0200 Subject: arm64: tegra: Initial Tegra234 VDK support The NVIDIA Tegra234 VDK is a simulation platform for the Orin SoC. It supports a subset of the peripherals that will be available in the final chip and serves as a bootstrapping platform. Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 14 ++++++++++++++ include/dt-bindings/reset/tegra234-reset.h | 10 ++++++++++ 2 files changed, 24 insertions(+) create mode 100644 include/dt-bindings/clock/tegra234-clock.h create mode 100644 include/dt-bindings/reset/tegra234-reset.h (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h new file mode 100644 index 000000000000..2c82072950ee --- /dev/null +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018-2019, NVIDIA CORPORATION. All rights reserved. */ + +#ifndef DT_BINDINGS_CLOCK_TEGRA234_CLOCK_H +#define DT_BINDINGS_CLOCK_TEGRA234_CLOCK_H + +/** @brief output of gate CLK_ENB_FUSE */ +#define TEGRA234_CLK_FUSE 40 +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC4 */ +#define TEGRA234_CLK_SDMMC4 123 +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_UARTA */ +#define TEGRA234_CLK_UARTA 155 + +#endif diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h new file mode 100644 index 000000000000..b3c63be06d2d --- /dev/null +++ b/include/dt-bindings/reset/tegra234-reset.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018-2020, NVIDIA CORPORATION. All rights reserved. */ + +#ifndef DT_BINDINGS_RESET_TEGRA234_RESET_H +#define DT_BINDINGS_RESET_TEGRA234_RESET_H + +#define TEGRA234_RESET_SDMMC4 85 +#define TEGRA234_RESET_UARTA 100 + +#endif -- cgit v1.2.3 From 874f635310648a5adcedbd7e02ea0555cfa1da56 Mon Sep 17 00:00:00 2001 From: Ionela Voinescu Date: Tue, 1 Sep 2020 21:55:47 +0100 Subject: cpufreq: report whether cpufreq supports Frequency Invariance (FI) Now that the update of the FI scale factor is done in cpufreq core for selected functions - target(), target_index() and fast_switch(), we can provide feedback to the task scheduler and architecture code on whether cpufreq supports FI. For this purpose provide an external function to expose whether the cpufreq drivers support FI, by using a static key. The logic behind the enablement of cpufreq-based invariance is as follows: - cpufreq-based invariance is disabled by default - cpufreq-based invariance is enabled if any of the callbacks above is implemented while the unsupported setpolicy() is not The cpufreq_supports_freq_invariance() function only returns whether cpufreq is instrumented with the arch_set_freq_scale() calls that result in support for frequency invariance. Due to the lack of knowledge on whether the implementation of arch_set_freq_scale() actually results in the setting of a scale factor based on cpufreq information, it is up to the architecture code to ensure the setting and provision of the scale factor to the scheduler. Signed-off-by: Ionela Voinescu Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a911e5d06845..e54767e2a68a 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -217,6 +217,7 @@ void refresh_frequency_limits(struct cpufreq_policy *policy); void cpufreq_update_policy(unsigned int cpu); void cpufreq_update_limits(unsigned int cpu); bool have_governor_per_policy(void); +bool cpufreq_supports_freq_invariance(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); void cpufreq_disable_fast_switch(struct cpufreq_policy *policy); @@ -237,6 +238,10 @@ static inline unsigned int cpufreq_get_hw_max_freq(unsigned int cpu) { return 0; } +static inline bool cpufreq_supports_freq_invariance(void) +{ + return false; +} static inline void disable_cpufreq(void) { } #endif -- cgit v1.2.3 From ecddc3a0d5d752071c627aa1a1d4d7b529ddae67 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 1 Sep 2020 21:55:48 +0100 Subject: arch_topology, cpufreq: constify arch_* cpumasks The passed cpumask arguments to arch_set_freq_scale() and arch_freq_counters_available() are only iterated over, so reflect this in the prototype. This also allows to pass system cpumasks like cpu_online_mask without getting a warning. Signed-off-by: Valentin Schneider Signed-off-by: Ionela Voinescu Acked-by: Catalin Marinas Acked-by: Viresh Kumar Reviewed-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/linux/arch_topology.h | 2 +- include/linux/cpufreq.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 69b1dabe39dc..810c83336257 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -30,7 +30,7 @@ static inline unsigned long topology_get_freq_scale(int cpu) return per_cpu(freq_scale, cpu); } -bool arch_freq_counters_available(struct cpumask *cpus); +bool arch_freq_counters_available(const struct cpumask *cpus); DECLARE_PER_CPU(unsigned long, thermal_pressure); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index e54767e2a68a..9f779fbdbe7b 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1011,7 +1011,8 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); -extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq, +extern void arch_set_freq_scale(const struct cpumask *cpus, + unsigned long cur_freq, unsigned long max_freq); /* the following are really really optional */ -- cgit v1.2.3 From 15e5d5b45b2b7072214af519357a1c0af078c50b Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 1 Sep 2020 21:55:49 +0100 Subject: arch_topology, arm, arm64: define arch_scale_freq_invariant() arch_scale_freq_invariant() is used by schedutil to determine whether the scheduler's load-tracking signals are frequency invariant. Its definition is overridable, though by default it is hardcoded to 'true' if arch_scale_freq_capacity() is defined ('false' otherwise). This behaviour is not overridden on arm, arm64 and other users of the generic arch topology driver, which is somewhat precarious: arch_scale_freq_capacity() will always be defined, yet not all cpufreq drivers are guaranteed to drive the frequency invariance scale factor setting. In other words, the load-tracking signals may very well *not* be frequency invariant. Now that cpufreq can be queried on whether the current driver is driving the Frequency Invariance (FI) scale setting, the current situation can be improved. This combines the query of whether cpufreq supports the setting of the frequency scale factor, with whether all online CPUs are counter-based FI enabled. While cpufreq FI enablement applies at system level, for all CPUs, counter-based FI support could also be used for only a subset of CPUs to set the invariance scale factor. Therefore, if cpufreq-based FI support is present, we consider the system to be invariant. If missing, we require all online CPUs to be counter-based FI enabled in order for the full system to be considered invariant. If the system ends up not being invariant, a new condition is needed in the counter initialization code that disables all scale factor setting based on counters. Precedence of counters over cpufreq use is not important here. The invariant status is only given to the system if all CPUs have at least one method of setting the frequency scale factor. Signed-off-by: Valentin Schneider Signed-off-by: Ionela Voinescu Acked-by: Catalin Marinas Acked-by: Viresh Kumar Reviewed-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/linux/arch_topology.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 810c83336257..083df331a3c9 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -30,6 +30,8 @@ static inline unsigned long topology_get_freq_scale(int cpu) return per_cpu(freq_scale, cpu); } +bool topology_scale_freq_invariant(void); + bool arch_freq_counters_available(const struct cpumask *cpus); DECLARE_PER_CPU(unsigned long, thermal_pressure); -- cgit v1.2.3 From 54fa9ba564b717fc2cf689427e195c360315999d Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Mon, 7 Sep 2020 11:32:07 +0200 Subject: ftrace: Let ftrace_enable_sysctl take a kernel pointer buffer Commit 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") changed ctl_table.proc_handler to take a kernel pointer. Adjust the signature of ftrace_enable_sysctl to match ctl_table.proc_handler which fixes the following sparse warning: kernel/trace/ftrace.c:7544:43: warning: incorrect type in argument 3 (different address spaces) kernel/trace/ftrace.c:7544:43: expected void * kernel/trace/ftrace.c:7544:43: got void [noderef] __user *buffer Link: https://lkml.kernel.org/r/20200907093207.13540-1-tklauser@distanz.ch Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Cc: Andrew Morton Cc: Ingo Molnar Cc: Christoph Hellwig Cc: Al Viro Signed-off-by: Tobias Klauser Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ce2c06f72e86..e5c2d5cc6e6a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -85,8 +85,7 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); struct ftrace_ops; -- cgit v1.2.3 From 82d083ab60c3693201c6f5c7a5f23a6ed422098d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 10 Sep 2020 17:55:05 +0900 Subject: kprobes: tracing/kprobes: Fix to kill kprobes on initmem after boot Since kprobe_event= cmdline option allows user to put kprobes on the functions in initmem, kprobe has to make such probes gone after boot. Currently the probes on the init functions in modules will be handled by module callback, but the kernel init text isn't handled. Without this, kprobes may access non-exist text area to disable or remove it. Link: https://lkml.kernel.org/r/159972810544.428528.1839307531600646955.stgit@devnote2 Fixes: 970988e19eb0 ("tracing/kprobe: Add kprobe_event= boot parameter") Cc: Jonathan Corbet Cc: Shuah Khan Cc: Randy Dunlap Cc: Ingo Molnar Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9be1bff4f586..8aab327b5539 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -373,6 +373,8 @@ void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); +void kprobe_free_init_mem(void); + int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); @@ -435,6 +437,9 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num) static inline void kprobe_flush_task(struct task_struct *tk) { } +static inline void kprobe_free_init_mem(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; -- cgit v1.2.3 From 97de44c5ecd413d3da3d4ace74272a1ad6a409ca Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Thu, 17 Sep 2020 08:47:01 +0200 Subject: dt-bindings: power: amlogic, meson-ee-pwrc: add Amlogic AXG power controller bindings This add the bindings of the Power Controller found in the Amlogic AXG SoCs. Signed-off-by: Neil Armstrong Signed-off-by: Kevin Hilman Reviewed-by: Rob Herring Acked-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20200917064702.1459-2-narmstrong@baylibre.com --- include/dt-bindings/power/meson-axg-power.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/dt-bindings/power/meson-axg-power.h (limited to 'include') diff --git a/include/dt-bindings/power/meson-axg-power.h b/include/dt-bindings/power/meson-axg-power.h new file mode 100644 index 000000000000..e5243884b249 --- /dev/null +++ b/include/dt-bindings/power/meson-axg-power.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ +/* + * Copyright (c) 2020 BayLibre, SAS + * Author: Neil Armstrong + */ + +#ifndef _DT_BINDINGS_MESON_AXG_POWER_H +#define _DT_BINDINGS_MESON_AXG_POWER_H + +#define PWRC_AXG_VPU_ID 0 +#define PWRC_AXG_ETHERNET_MEM_ID 1 +#define PWRC_AXG_AUDIO_ID 2 + +#endif -- cgit v1.2.3 From 6d1349c769ea28543bdde20a658cbc93c3bc936d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 18 Sep 2020 16:45:50 -0400 Subject: [PATCH] reduce boilerplate in fsid handling Get rid of boilerplate in most of ->statfs() instances... Signed-off-by: Al Viro --- include/linux/statfs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/statfs.h b/include/linux/statfs.h index fac4356ea1bf..20f695b90aab 100644 --- a/include/linux/statfs.h +++ b/include/linux/statfs.h @@ -45,4 +45,9 @@ struct kstatfs { struct dentry; extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid); +static inline __kernel_fsid_t u64_to_fsid(u64 v) +{ + return (__kernel_fsid_t){.val = {(u32)v, (u32)(v>>32)}}; +} + #endif -- cgit v1.2.3 From 6565243c0677aa2befa5a953cf11bc7b4a6f0a47 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 18 Sep 2020 04:07:24 +0300 Subject: net: mscc: ocelot: add locking for the port TX timestamp ID The ocelot_port->ts_id is used to: (a) populate skb->cb[0] for matching the TX timestamp in the PTP IRQ with an skb. (b) populate the REW_OP from the injection header of the ongoing skb. Only then is ocelot_port->ts_id incremented. This is a problem because, at least theoretically, another timestampable skb might use the same ocelot_port->ts_id before that is incremented. Normally all transmit calls are serialized by the netdev transmit spinlock, but in this case, ocelot_port_add_txtstamp_skb() is also called by DSA, which has started declaring the NETIF_F_LLTX feature since commit 2b86cb829976 ("net: dsa: declare lockless TX feature for slave ports"). So the logic of using and incrementing the timestamp id should be atomic per port. The solution is to use the global ocelot_port->ts_id only while protected by the associated ocelot_port->ts_id_lock. That's where we populate skb->cb[0]. Note that for ocelot, ocelot_port_add_txtstamp_skb is called for the actual skb, but for felix, it is called for the skb's clone. That is something which will also be changed in the future. Signed-off-by: Vladimir Oltean Reviewed-by: Horatiu Vultur Reviewed-by: Florian Fainelli Tested-by: Alexandre Belloni Reviewed-by: Alexandre Belloni Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index da369b12005f..4521dd602ddc 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -566,6 +566,7 @@ struct ocelot_port { u8 ptp_cmd; struct sk_buff_head tx_skbs; u8 ts_id; + spinlock_t ts_id_lock; phy_interface_t phy_mode; -- cgit v1.2.3 From e5fb512d81d021b7c7a0c2547c3dafb9de759285 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 18 Sep 2020 04:07:30 +0300 Subject: net: mscc: ocelot: deinitialize only initialized ports Currently mscc_ocelot_init_ports() will skip initializing a port when it doesn't have a phy-handle, so the ocelot->ports[port] pointer will be NULL. Take this into consideration when tearing down the driver, and add a new function ocelot_deinit_port() to the switch library, mirror of ocelot_init_port(), which needs to be called by the driver for all ports it has initialized. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Tested-by: Alexandre Belloni Reviewed-by: Alexandre Belloni Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 4521dd602ddc..0ac4e7fba086 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -678,6 +678,7 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi, int ocelot_init(struct ocelot *ocelot); void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); +void ocelot_deinit_port(struct ocelot *ocelot, int port); /* DSA callbacks */ void ocelot_port_enable(struct ocelot *ocelot, int port, -- cgit v1.2.3 From f92970c694b36a4dbac2b650b173c78c0f0954cc Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Thu, 17 Sep 2020 18:13:23 -0700 Subject: devlink: add timeout information to status_notify Add a timeout element to the DEVLINK_CMD_FLASH_UPDATE_STATUS netlink message for use by a userland utility to show that a particular firmware flash activity may take a long but bounded time to finish. Also add a handy helper for drivers to make use of the new timeout value. UI usage hints: - if non-zero, add timeout display to the end of the status line [component] status_msg ( Xm Ys : Am Bs ) using the timeout value for Am Bs and updating the Xm Ys every second - if the timeout expires while awaiting the next update, display something like [component] status_msg ( timeout reached : Am Bs ) - if new status notify messages are received, remove the timeout and start over Signed-off-by: Shannon Nelson Reviewed-by: Jakub Kicinski Reviewed-by: Jacob Keller Signed-off-by: David S. Miller --- include/net/devlink.h | 4 ++++ include/uapi/linux/devlink.h | 3 +++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 48b1c1ef1ebd..be132c17fbcc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1403,6 +1403,10 @@ void devlink_flash_update_status_notify(struct devlink *devlink, const char *component, unsigned long done, unsigned long total); +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout); int devlink_traps_register(struct devlink *devlink, const struct devlink_trap *traps, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 631f5bdf1707..a2ecc8b00611 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -462,6 +462,9 @@ enum devlink_attr { DEVLINK_ATTR_PORT_EXTERNAL, /* u8 */ DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, /* u32 */ + + DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, /* u64 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From 6700acc5f1fe97b5705832f2678cba9e9756a0dc Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Thu, 17 Sep 2020 18:13:24 -0700 Subject: devlink: collect flash notify params into a struct The dev flash status notify function parameter lists are getting rather long, so add a struct to be filled and passed rather than continuously changing the function signatures. Signed-off-by: Shannon Nelson Reviewed-by: Jacob Keller Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/devlink.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index be132c17fbcc..73065f07bf17 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -391,6 +391,25 @@ struct devlink_param_gset_ctx { enum devlink_param_cmode cmode; }; +/** + * struct devlink_flash_notify - devlink dev flash notify data + * @status_msg: current status string + * @component: firmware component being updated + * @done: amount of work completed of total amount + * @total: amount of work expected to be done + * @timeout: expected max timeout in seconds + * + * These are values to be given to userland to be displayed in order + * to show current activity in a firmware update process. + */ +struct devlink_flash_notify { + const char *status_msg; + const char *component; + unsigned long done; + unsigned long total; + unsigned long timeout; +}; + /** * struct devlink_param - devlink configuration parameter data * @name: name of the parameter -- cgit v1.2.3 From daef1ee3798b25e8464b8eb618eaa74b8f423ac7 Mon Sep 17 00:00:00 2001 From: Tuong Lien Date: Fri, 18 Sep 2020 08:17:27 +0700 Subject: tipc: introduce encryption master key In addition to the supported cluster & per-node encryption keys for the en/decryption of TIPC messages, we now introduce one option for user to set a cluster key as 'master key', which is simply a symmetric key like the former but has a longer life cycle. It has two purposes: - Authentication of new member nodes in the cluster. New nodes, having no knowledge of current session keys in the cluster will still be able to join the cluster as long as they know the master key. This is because all neighbor discovery (LINK_CONFIG) messages must be encrypted with this key. - Encryption of session encryption keys during automatic exchange and update of those.This is a feature we will introduce in a later commit in this series. We insert the new key into the currently unused slot 0 in the key array and start using it immediately once the user has set it. After joining, a node only knowing the master key should be fully communicable to existing nodes in the cluster, although those nodes may have their own session keys activated (i.e. not the master one). To support this, we define a 'grace period', starting from the time a node itself reports having no RX keys, so the existing nodes will use the master key for encryption instead. The grace period can be extended but will automatically stop after e.g. 5 seconds without a new report. This is also the basis for later key exchanging feature as the new node will be impossible to decrypt anything without the support from master key. For user to set a master key, we define a new netlink flag - 'TIPC_NLA_NODE_KEY_MASTER', so it can be added to the current 'set key' netlink command to specify the setting key to be a master key. Above all, the traditional cluster/per-node key mechanism is guaranteed to work when user comes not to use this master key option. This is also compatible to legacy nodes without the feature supported. Even this master key can be updated without any interruption of cluster connectivity but is so is needed, this has to be coordinated and set by the user. Acked-by: Jon Maloy Signed-off-by: Tuong Lien Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index dc0d23a50e69..d484baa9d365 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -165,6 +165,7 @@ enum { TIPC_NLA_NODE_UP, /* flag */ TIPC_NLA_NODE_ID, /* data */ TIPC_NLA_NODE_KEY, /* data */ + TIPC_NLA_NODE_KEY_MASTER, /* flag */ __TIPC_NLA_NODE_MAX, TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1 -- cgit v1.2.3 From 23700da29b83e859a8c3727fddd33ba74c4f3a39 Mon Sep 17 00:00:00 2001 From: Tuong Lien Date: Fri, 18 Sep 2020 08:17:29 +0700 Subject: tipc: add automatic rekeying for encryption key Rekeying is required for security since a key is less secure when using for a long time. Also, key will be detached when its nonce value (or seqno ...) is exhausted. We now make the rekeying process automatic and configurable by user. Basically, TIPC will at a specific interval generate a new key by using the kernel 'Random Number Generator' cipher, then attach it as the node TX key and securely distribute to others in the cluster as RX keys (- the key exchange). The automatic key switching will then take over, and make the new key active shortly. Afterwards, the traffic from this node will be encrypted with the new session key. The same can happen in peer nodes but not necessarily at the same time. For simplicity, the automatically generated key will be initiated as a per node key. It is not too hard to also support a cluster key rekeying (e.g. a given node will generate a unique cluster key and update to the others in the cluster...), but that doesn't bring much benefit, while a per-node key is even more secure. We also enable user to force a rekeying or change the rekeying interval via netlink, the new 'set key' command option: 'TIPC_NLA_NODE_REKEYING' is added for these purposes as follows: - A value >= 1 will be set as the rekeying interval (in minutes); - A value of 0 will disable the rekeying; - A value of 'TIPC_REKEYING_NOW' (~0) will force an immediate rekeying; The default rekeying interval is (60 * 24) minutes i.e. done every day. There isn't any restriction for the value but user shouldn't set it too small or too large which results in an "ineffective" rekeying (thats ok for testing though). Acked-by: Jon Maloy Signed-off-by: Tuong Lien Signed-off-by: David S. Miller --- include/uapi/linux/tipc.h | 2 ++ include/uapi/linux/tipc_netlink.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index add01db1daef..80ea15e12113 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -254,6 +254,8 @@ static inline int tipc_aead_key_size(struct tipc_aead_key *key) return sizeof(*key) + key->keylen; } +#define TIPC_REKEYING_NOW (~0U) + /* The macros and functions below are deprecated: */ diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index d484baa9d365..d847dd671d79 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -166,6 +166,7 @@ enum { TIPC_NLA_NODE_ID, /* data */ TIPC_NLA_NODE_KEY, /* data */ TIPC_NLA_NODE_KEY_MASTER, /* flag */ + TIPC_NLA_NODE_REKEYING, /* u32 */ __TIPC_NLA_NODE_MAX, TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1 -- cgit v1.2.3 From 3753d9779038ab011e01b949253492aaa37bf57a Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 17 Sep 2020 22:08:32 -0700 Subject: net: fix build without CONFIG_SYSCTL definition Earlier commit 316cdaa1158a ("net: add option to not create fall-back tunnels in root-ns as well") removed the CONFIG_SYSCTL to enable the kernel-commandline to work. However, this variable gets defined only when CONFIG_SYSCTL option is selected. With this change the behavior would default to creating fall-back tunnels in all namespaces when CONFIG_SYSCTL is not selected and the kernel commandline option will be ignored. Fixes: 316cdaa1158a ("net: add option to not create fall-back tunnels in root-ns as well") Signed-off-by: Mahesh Bandewar Reported-by: Randy Dunlap Reported-by: kernel test robot Acked-by: Randy Dunlap # build-tested Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 909b1fbb0481..fef0eb96cf69 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -634,8 +634,9 @@ extern int sysctl_devconf_inherit_init_net; */ static inline bool net_has_fallback_tunnels(const struct net *net) { - return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) || - !sysctl_fb_tunnels_only_for_init_net; + return !IS_ENABLED(CONFIG_SYSCTL) || + !sysctl_fb_tunnels_only_for_init_net || + (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1); } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) -- cgit v1.2.3 From 6d23d831e9bd0b1d2bcd9a1ecdc6ac8e6d162c36 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Fri, 18 Sep 2020 17:48:01 +0800 Subject: ptp_qoriq: support FIPER3 The FIPER3 (fixed interval period pulse generator) is supported on DPAA2 and ENETC network controller hardware. This patch is to support it in ptp_qoriq driver. Signed-off-by: Yangbo Lu Acked-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 884b8f8ca06d..01acebe37fab 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -136,6 +136,7 @@ struct ptp_qoriq_registers { #define DEFAULT_TMR_PRSC 2 #define DEFAULT_FIPER1_PERIOD 1000000000 #define DEFAULT_FIPER2_PERIOD 1000000000 +#define DEFAULT_FIPER3_PERIOD 1000000000 struct ptp_qoriq { void __iomem *base; @@ -147,6 +148,7 @@ struct ptp_qoriq { struct dentry *debugfs_root; struct device *dev; bool extts_fifo_support; + bool fiper3_support; int irq; int phc_index; u32 tclk_period; /* nanoseconds */ @@ -155,6 +157,7 @@ struct ptp_qoriq { u32 cksel; u32 tmr_fiper1; u32 tmr_fiper2; + u32 tmr_fiper3; u32 (*read)(unsigned __iomem *addr); void (*write)(unsigned __iomem *addr, u32 val); }; -- cgit v1.2.3 From 881321b6ed9e983ad733268404245fcf0be0b23c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 18 Sep 2020 13:57:51 +0300 Subject: net: mscc: ocelot: make ocelot_init_timestamp take a const struct ptp_clock_info It is a good measure to ensure correctness if the structures that are meant to remain constant are only processed by functions that thake constant arguments. Signed-off-by: Vladimir Oltean Reviewed-by: Alexandre Belloni Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_ptp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h index 4a6b2f71b6b2..6a7388fa7cc5 100644 --- a/include/soc/mscc/ocelot_ptp.h +++ b/include/soc/mscc/ocelot_ptp.h @@ -53,6 +53,7 @@ int ocelot_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan); int ocelot_ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on); -int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info); +int ocelot_init_timestamp(struct ocelot *ocelot, + const struct ptp_clock_info *info); int ocelot_deinit_timestamp(struct ocelot *ocelot); #endif -- cgit v1.2.3 From e14e05e71d106aef973e2cf100e540d911703a6e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 18 Sep 2020 21:11:01 +0200 Subject: net: devlink: regions: Add a priv member to the regions ops struct The driver may have multiple regions which can be dumped using one function. However, for this to work, additional information is needed. Add a priv member to the ops structure for the driver to use however it likes. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 73065f07bf17..b68e483d9267 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -561,12 +561,14 @@ struct devlink_info_req; * the data variable must be updated to point to the snapshot data. * The function will be called while the devlink instance lock is * held. + * @priv: Pointer to driver private data for the region operation */ struct devlink_region_ops { const char *name; void (*destructor)(const void *data); int (*snapshot)(struct devlink *devlink, struct netlink_ext_ack *extack, u8 **data); + void *priv; }; struct devlink_fmsg; -- cgit v1.2.3 From d4602a9f47196dd62deba66ec361b5897f1ae62b Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 18 Sep 2020 21:11:02 +0200 Subject: net: devlink: region: Pass the region ops to the snapshot function Pass the region to be snapshotted to the function performing the snapshot. This allows one function to operate on numerous regions. v4: Add missing kerneldoc for ICE Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/devlink.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index b68e483d9267..4883dbae7faf 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -566,7 +566,9 @@ struct devlink_info_req; struct devlink_region_ops { const char *name; void (*destructor)(const void *data); - int (*snapshot)(struct devlink *devlink, struct netlink_ext_ack *extack, + int (*snapshot)(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, u8 **data); void *priv; }; -- cgit v1.2.3 From ccc3e6b0191c58784c4b4ffc735f81970df33a11 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 18 Sep 2020 21:11:03 +0200 Subject: net: dsa: Add helper to convert from devlink to ds Given a devlink instance, return the dsa switch it is associated to. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 75c8fac82017..42ae6d4d9d43 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -664,6 +664,13 @@ struct dsa_devlink_priv { struct dsa_switch *ds; }; +static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) +{ + struct dsa_devlink_priv *dl_priv = devlink_priv(dl); + + return dl_priv->ds; +} + struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; -- cgit v1.2.3 From 97c82c23135187878acea76bc5f0b03007e17ac7 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 18 Sep 2020 21:11:04 +0200 Subject: net: dsa: Add devlink regions support to DSA Allow DSA drivers to make use of devlink regions, via simple wrappers. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 42ae6d4d9d43..431efb5098be 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -658,6 +658,12 @@ void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); +struct devlink_region * +dsa_devlink_region_create(struct dsa_switch *ds, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, u64 region_size); +void dsa_devlink_region_destroy(struct devlink_region *region); + struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { -- cgit v1.2.3 From 0f06b855a93c3b449253b91abc94c4d483af0a44 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 18 Sep 2020 21:11:08 +0200 Subject: net: dsa: wire up devlink info get Allow the DSA drivers to implement the devlink call to get info info, e.g. driver name, firmware version, ASIC ID, etc. v2: Combine declaration and the assignment on a single line. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 431efb5098be..d16057c5987a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -612,11 +612,14 @@ struct dsa_switch_ops { bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); - /* Devlink parameters */ + /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); + int (*devlink_info_get)(struct dsa_switch *ds, + struct devlink_info_req *req, + struct netlink_ext_ack *extack); /* * MTU change functionality. Switches can also adjust their MRU through -- cgit v1.2.3 From 7bb82ac30c3dd4ecf1485685cbe84d2ba10dddf4 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 18 Sep 2020 21:20:34 -0700 Subject: ftrace: let ftrace_enable_sysctl take a kernel pointer buffer Commit 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") changed ctl_table.proc_handler to take a kernel pointer. Adjust the signature of ftrace_enable_sysctl to match ctl_table.proc_handler which fixes the following sparse warning: kernel/trace/ftrace.c:7544:43: warning: incorrect type in argument 3 (different address spaces) kernel/trace/ftrace.c:7544:43: expected void * kernel/trace/ftrace.c:7544:43: got void [noderef] __user *buffer Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Signed-off-by: Tobias Klauser Signed-off-by: Andrew Morton Cc: Christoph Hellwig Cc: Al Viro Link: https://lkml.kernel.org/r/20200907093207.13540-1-tklauser@distanz.ch Signed-off-by: Linus Torvalds --- include/linux/ftrace.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ce2c06f72e86..e5c2d5cc6e6a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -85,8 +85,7 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); struct ftrace_ops; -- cgit v1.2.3 From 4773ef33fc6e59bad2e5d19e334de2fa79c27b74 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 18 Sep 2020 21:20:37 -0700 Subject: stackleak: let stack_erasing_sysctl take a kernel pointer buffer Commit 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") changed ctl_table.proc_handler to take a kernel pointer. Adjust the signature of stack_erasing_sysctl to match ctl_table.proc_handler which fixes the following sparse warning: kernel/stackleak.c:31:50: warning: incorrect type in argument 3 (different address spaces) kernel/stackleak.c:31:50: expected void * kernel/stackleak.c:31:50: got void [noderef] __user *buffer Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Signed-off-by: Tobias Klauser Signed-off-by: Andrew Morton Cc: Christoph Hellwig Cc: Al Viro Link: https://lkml.kernel.org/r/20200907093253.13656-1-tklauser@distanz.ch Signed-off-by: Linus Torvalds --- include/linux/stackleak.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 3d5c3271a9a8..a59db2f08e76 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -25,7 +25,7 @@ static inline void stackleak_task_init(struct task_struct *t) #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE int stack_erasing_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ -- cgit v1.2.3 From 55f13311785cebd60b9bab9ca7fd64205436c462 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Fri, 18 Sep 2020 14:14:51 -0500 Subject: ethtool: Add 100base-FX link mode entries Add entries for the 100base-FX full and half duplex supported modes. $ ethtool eth0 Supported ports: [ FIBRE ] Supported link modes: 100baseFX/Half 100baseFX/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: No Supported FEC modes: Not reported Advertised link modes: 100baseFX/Half 100baseFX/Full Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: Not reported Speed: 100Mb/s Duplex: Full Auto-negotiation: off Port: MII PHYAD: 1 Transceiver: external Supports Wake-on: gs Wake-on: d SecureOn password: 00:00:00:00:00:00 Current message level: 0x00000000 (0) Link detected: yes Signed-off-by: Dan Murphy Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index b4f2d134e713..9ca87bc73c44 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1617,6 +1617,8 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87, ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT = 88, ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, + ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, + ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; -- cgit v1.2.3 From e2ec5128254518cae320d5dc631b71b94160f663 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sun, 20 Sep 2020 08:54:42 -0700 Subject: dm: Call proper helper to determine dax support DM was calling generic_fsdax_supported() to determine whether a device referenced in the DM table supports DAX. However this is a helper for "leaf" device drivers so that they don't have to duplicate common generic checks. High level code should call dax_supported() helper which that calls into appropriate helper for the particular device. This problem manifested itself as kernel messages: dm-3: error: dax access failed (-95) when lvm2-testsuite run in cases where a DM device was stacked on top of another DM device. Fixes: 7bf7eac8d648 ("dax: Arrange for dax_supported check to span multiple devices") Cc: Tested-by: Adrian Huang Signed-off-by: Jan Kara Acked-by: Mike Snitzer Reported-by: kernel test robot Link: https://lore.kernel.org/r/160061715195.13131.5503173247632041975.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/dax.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 6904d4e0b2e0..497031392e0a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -130,6 +130,8 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return __generic_fsdax_supported(dax_dev, bdev, blocksize, start, sectors); } +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len); static inline void fs_put_dax(struct dax_device *dax_dev) { @@ -157,6 +159,13 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } +static inline bool dax_supported(struct dax_device *dax_dev, + struct block_device *bdev, int blocksize, sector_t start, + sector_t len) +{ + return false; +} + static inline void fs_put_dax(struct dax_device *dax_dev) { } @@ -189,14 +198,23 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) } #endif +#if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); +#else +static inline int dax_read_lock(void) +{ + return 0; +} + +static inline void dax_read_unlock(int id) +{ +} +#endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, -- cgit v1.2.3 From fe81d9f6182d1160e625894eecb3d7ff0222cac5 Mon Sep 17 00:00:00 2001 From: Henry Ptasinski Date: Sat, 19 Sep 2020 00:12:11 +0000 Subject: net: sctp: Fix IPv6 ancestor_size calc in sctp_copy_descendant When calculating ancestor_size with IPv6 enabled, simply using sizeof(struct ipv6_pinfo) doesn't account for extra bytes needed for alignment in the struct sctp6_sock. On x86, there aren't any extra bytes, but on ARM the ipv6_pinfo structure is aligned on an 8-byte boundary so there were 4 pad bytes that were omitted from the ancestor_size calculation. This would lead to corruption of the pd_lobby pointers, causing an oops when trying to free the sctp structure on socket close. Fixes: 636d25d557d1 ("sctp: not copy sctp_sock pd_lobby in sctp_copy_descendant") Signed-off-by: Henry Ptasinski Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index b33f1aefad09..0bdff38eb4bb 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -226,12 +226,14 @@ struct sctp_sock { data_ready_signalled:1; atomic_t pd_mode; + + /* Fields after this point will be skipped on copies, like on accept + * and peeloff operations + */ + /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; - /* These must be the last fields, as they will skipped on copies, - * like on accept and peeloff operations - */ struct list_head auto_asconf_list; int do_auto_asconf; }; -- cgit v1.2.3 From bbed0bbdddaf46260aeb1a8910a3b32941e321a2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 21 Sep 2020 03:10:30 +0300 Subject: net: dsa: tag_8021q: add VLANs to the master interface too The whole purpose of tag_8021q is to send VLAN-tagged traffic to the CPU, from which the driver can decode the source port and switch id. Currently this only works if the VLAN filtering on the master is disabled. Change that by explicitly adding code to tag_8021q.c to add the VLANs corresponding to the tags to the filter of the master interface. Because we now need to call vlan_vid_add, then we also need to hold the RTNL mutex. Propagate that requirement to the callers of dsa_8021q_setup and modify the existing call sites as appropriate. Note that one call path, sja1105_best_effort_vlan_filtering_set -> sja1105_vlan_filtering -> sja1105_setup_8021q_tagging, was already holding this lock. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 2b003ae9fb38..88cd72dfa4e0 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -31,6 +31,8 @@ struct dsa_8021q_context { const struct dsa_8021q_ops *ops; struct dsa_switch *ds; struct list_head crosschip_links; + /* EtherType of RX VID, used for filtering on master interface */ + __be16 proto; }; #define DSA_8021Q_N_SUBVLAN 8 -- cgit v1.2.3 From 49347755a84052fd1317c3897c7cea954c8f89fe Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 16 Sep 2020 00:34:53 +0200 Subject: can: include: fix spelling mistakes This patch fixes spelling erros found by "codespell" in the include/linux/can subtree. Link: https://lore.kernel.org/r/20200915223527.1417033-4-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 2 +- include/linux/can/dev.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index e20a0cd09ba5..7da9f1f82e8e 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -2,7 +2,7 @@ /* * linux/can/core.h * - * Protoypes and definitions for CAN protocol modules using the PF_CAN core + * Prototypes and definitions for CAN protocol modules using the PF_CAN core * * Authors: Oliver Hartkopp * Urs Thuermann diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5e3d45525bd3..516892566ac9 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -108,7 +108,7 @@ static inline bool can_skb_headroom_valid(struct net_device *dev, skb->ip_summed = CHECKSUM_UNNECESSARY; - /* preform proper loopback on capable devices */ + /* perform proper loopback on capable devices */ if (dev->flags & IFF_ECHO) skb->pkt_type = PACKET_LOOPBACK; else -- cgit v1.2.3 From 80a71815d8cd1be6481ad16fad3167f095045a06 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 16 Sep 2020 00:35:01 +0200 Subject: can: dev: can_put_echo_skb(): propagate error in case of errors The function can_put_echo_skb() can fail for several reasons. It may fail due to OOM, but when it fails it's usually due to locking problems in the driver. In order to help developing and debugging of new drivers propagate error value in case of errors. Link: https://lore.kernel.org/r/20200915223527.1417033-12-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 516892566ac9..ed0482b2f4b2 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -201,8 +201,8 @@ void can_bus_off(struct net_device *dev); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); -void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, - unsigned int idx); +int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, + unsigned int idx); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); -- cgit v1.2.3 From 728fc9ff73d3f25220f6b8a52aaf063ec51ef294 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 16 Sep 2020 00:35:22 +0200 Subject: can: rx-offload: can_rx_offload_add_manual(): add new initialization function This patch adds a new initialization function: can_rx_offload_add_manual() It should be used to add support rx-offload to a driver, if the callback mechanism should not be used. Use e.g. can_rx_offload_queue_sorted() to queue skbs into rx-offload. Link: https://lore.kernel.org/r/20200915223527.1417033-33-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 1b78a0cfb615..f1b38088b765 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -35,6 +35,9 @@ int can_rx_offload_add_timestamp(struct net_device *dev, int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight); +int can_rx_offload_add_manual(struct net_device *dev, + struct can_rx_offload *offload, + unsigned int weight); int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); -- cgit v1.2.3 From a7d39439f8bd14b5becebc095aef3f1ec3191fe2 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 18 Sep 2020 15:25:05 +0200 Subject: drm/dev: Remove drm_dev_init We can now also delete drm_dev_init, now that vkms, vgem and i915 selftests are resolved. Reviewed-by: Thomas Zimmermann Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200918132505.2316382-5-daniel.vetter@ffwll.ch --- include/drm/drm_drv.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index 9b11a2f0babc..e57d0440f00f 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -588,10 +588,6 @@ struct drm_driver { int dev_priv_size; }; -int drm_dev_init(struct drm_device *dev, - struct drm_driver *driver, - struct device *parent); - void *__devm_drm_dev_alloc(struct device *parent, struct drm_driver *driver, size_t size, size_t offset); -- cgit v1.2.3 From b1d4dc15b2f430a4f541ab6c91e63a71cf230b7d Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Tue, 15 Sep 2020 09:38:18 +0800 Subject: i2c: Switch to using the new API kobj_to_dev() Switch to using the new API kobj_to_dev(). Signed-off-by: Tian Tao Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index fc55ea41d323..56622658b215 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -344,7 +344,7 @@ const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj) { - struct device * const dev = container_of(kobj, struct device, kobj); + struct device * const dev = kobj_to_dev(kobj); return to_i2c_client(dev); } -- cgit v1.2.3 From c65176fd49f45bd5a5ffaa1790109745d1fa462c Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 18 Sep 2020 19:59:30 +0300 Subject: arm64: dts: ti: k3-j721e: Rename mux header and update macro names We intend to use one header file for SERDES MUX for all TI SoCs so rename the header file. The exsting macros are too generic. Prefix them with SoC name. While at that, add the missing configurations for completeness. Fixes: b766e3b0d5f6 ("arm64: dts: ti: k3-j721e-main: Add system controller node and SERDES lane mux") Reported-by: Peter Rosin Signed-off-by: Roger Quadros Signed-off-by: Nishanth Menon Acked-by: Peter Rosin Link: https://lore.kernel.org/r/20200918165930.2031-1-rogerq@ti.com --- include/dt-bindings/mux/mux-j721e-wiz.h | 53 ------------------------ include/dt-bindings/mux/ti-serdes.h | 71 +++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+), 53 deletions(-) delete mode 100644 include/dt-bindings/mux/mux-j721e-wiz.h create mode 100644 include/dt-bindings/mux/ti-serdes.h (limited to 'include') diff --git a/include/dt-bindings/mux/mux-j721e-wiz.h b/include/dt-bindings/mux/mux-j721e-wiz.h deleted file mode 100644 index fd1c4ea9fc7f..000000000000 --- a/include/dt-bindings/mux/mux-j721e-wiz.h +++ /dev/null @@ -1,53 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This header provides constants for J721E WIZ. - */ - -#ifndef _DT_BINDINGS_J721E_WIZ -#define _DT_BINDINGS_J721E_WIZ - -#define SERDES0_LANE0_QSGMII_LANE1 0x0 -#define SERDES0_LANE0_PCIE0_LANE0 0x1 -#define SERDES0_LANE0_USB3_0_SWAP 0x2 - -#define SERDES0_LANE1_QSGMII_LANE2 0x0 -#define SERDES0_LANE1_PCIE0_LANE1 0x1 -#define SERDES0_LANE1_USB3_0 0x2 - -#define SERDES1_LANE0_QSGMII_LANE3 0x0 -#define SERDES1_LANE0_PCIE1_LANE0 0x1 -#define SERDES1_LANE0_USB3_1_SWAP 0x2 -#define SERDES1_LANE0_SGMII_LANE0 0x3 - -#define SERDES1_LANE1_QSGMII_LANE4 0x0 -#define SERDES1_LANE1_PCIE1_LANE1 0x1 -#define SERDES1_LANE1_USB3_1 0x2 -#define SERDES1_LANE1_SGMII_LANE1 0x3 - -#define SERDES2_LANE0_PCIE2_LANE0 0x1 -#define SERDES2_LANE0_SGMII_LANE0 0x3 -#define SERDES2_LANE0_USB3_1_SWAP 0x2 - -#define SERDES2_LANE1_PCIE2_LANE1 0x1 -#define SERDES2_LANE1_USB3_1 0x2 -#define SERDES2_LANE1_SGMII_LANE1 0x3 - -#define SERDES3_LANE0_PCIE3_LANE0 0x1 -#define SERDES3_LANE0_USB3_0_SWAP 0x2 - -#define SERDES3_LANE1_PCIE3_LANE1 0x1 -#define SERDES3_LANE1_USB3_0 0x2 - -#define SERDES4_LANE0_EDP_LANE0 0x0 -#define SERDES4_LANE0_QSGMII_LANE5 0x2 - -#define SERDES4_LANE1_EDP_LANE1 0x0 -#define SERDES4_LANE1_QSGMII_LANE6 0x2 - -#define SERDES4_LANE2_EDP_LANE2 0x0 -#define SERDES4_LANE2_QSGMII_LANE7 0x2 - -#define SERDES4_LANE3_EDP_LANE3 0x0 -#define SERDES4_LANE3_QSGMII_LANE8 0x2 - -#endif /* _DT_BINDINGS_J721E_WIZ */ diff --git a/include/dt-bindings/mux/ti-serdes.h b/include/dt-bindings/mux/ti-serdes.h new file mode 100644 index 000000000000..146d0685a925 --- /dev/null +++ b/include/dt-bindings/mux/ti-serdes.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This header provides constants for SERDES MUX for TI SoCs + */ + +#ifndef _DT_BINDINGS_MUX_TI_SERDES +#define _DT_BINDINGS_MUX_TI_SERDES + +/* J721E */ + +#define J721E_SERDES0_LANE0_QSGMII_LANE1 0x0 +#define J721E_SERDES0_LANE0_PCIE0_LANE0 0x1 +#define J721E_SERDES0_LANE0_USB3_0_SWAP 0x2 +#define J721E_SERDES0_LANE0_IP4_UNUSED 0x3 + +#define J721E_SERDES0_LANE1_QSGMII_LANE2 0x0 +#define J721E_SERDES0_LANE1_PCIE0_LANE1 0x1 +#define J721E_SERDES0_LANE1_USB3_0 0x2 +#define J721E_SERDES0_LANE1_IP4_UNUSED 0x3 + +#define J721E_SERDES1_LANE0_QSGMII_LANE3 0x0 +#define J721E_SERDES1_LANE0_PCIE1_LANE0 0x1 +#define J721E_SERDES1_LANE0_USB3_1_SWAP 0x2 +#define J721E_SERDES1_LANE0_SGMII_LANE0 0x3 + +#define J721E_SERDES1_LANE1_QSGMII_LANE4 0x0 +#define J721E_SERDES1_LANE1_PCIE1_LANE1 0x1 +#define J721E_SERDES1_LANE1_USB3_1 0x2 +#define J721E_SERDES1_LANE1_SGMII_LANE1 0x3 + +#define J721E_SERDES2_LANE0_IP1_UNUSED 0x0 +#define J721E_SERDES2_LANE0_PCIE2_LANE0 0x1 +#define J721E_SERDES2_LANE0_USB3_1_SWAP 0x2 +#define J721E_SERDES2_LANE0_SGMII_LANE0 0x3 + +#define J721E_SERDES2_LANE1_IP1_UNUSED 0x0 +#define J721E_SERDES2_LANE1_PCIE2_LANE1 0x1 +#define J721E_SERDES2_LANE1_USB3_1 0x2 +#define J721E_SERDES2_LANE1_SGMII_LANE1 0x3 + +#define J721E_SERDES3_LANE0_IP1_UNUSED 0x0 +#define J721E_SERDES3_LANE0_PCIE3_LANE0 0x1 +#define J721E_SERDES3_LANE0_USB3_0_SWAP 0x2 +#define J721E_SERDES3_LANE0_IP4_UNUSED 0x3 + +#define J721E_SERDES3_LANE1_IP1_UNUSED 0x0 +#define J721E_SERDES3_LANE1_PCIE3_LANE1 0x1 +#define J721E_SERDES3_LANE1_USB3_0 0x2 +#define J721E_SERDES3_LANE1_IP4_UNUSED 0x3 + +#define J721E_SERDES4_LANE0_EDP_LANE0 0x0 +#define J721E_SERDES4_LANE0_IP2_UNUSED 0x1 +#define J721E_SERDES4_LANE0_QSGMII_LANE5 0x2 +#define J721E_SERDES4_LANE0_IP4_UNUSED 0x3 + +#define J721E_SERDES4_LANE1_EDP_LANE1 0x0 +#define J721E_SERDES4_LANE1_IP2_UNUSED 0x1 +#define J721E_SERDES4_LANE1_QSGMII_LANE6 0x2 +#define J721E_SERDES4_LANE1_IP4_UNUSED 0x3 + +#define J721E_SERDES4_LANE2_EDP_LANE2 0x0 +#define J721E_SERDES4_LANE2_IP2_UNUSED 0x1 +#define J721E_SERDES4_LANE2_QSGMII_LANE7 0x2 +#define J721E_SERDES4_LANE2_IP4_UNUSED 0x3 + +#define J721E_SERDES4_LANE3_EDP_LANE3 0x0 +#define J721E_SERDES4_LANE3_IP2_UNUSED 0x1 +#define J721E_SERDES4_LANE3_QSGMII_LANE8 0x2 +#define J721E_SERDES4_LANE3_IP4_UNUSED 0x3 + +#endif /* _DT_BINDINGS_MUX_TI_SERDES */ -- cgit v1.2.3 From 88b67edd7247466bc47f01e1dc539b0d0d4b931e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 21 Sep 2020 11:33:23 +0200 Subject: dax: Fix compilation for CONFIG_DAX && !CONFIG_FS_DAX dax_supported() is defined whenever CONFIG_DAX is enabled. So dummy implementation should be defined only in !CONFIG_DAX case, not in !CONFIG_FS_DAX case. Fixes: e2ec51282545 ("dm: Call proper helper to determine dax support") Cc: Reported-by: Geert Uytterhoeven Reported-by: Naresh Kamboju Reported-by: kernel test robot Signed-off-by: Jan Kara Signed-off-by: Dan Williams --- include/linux/dax.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 497031392e0a..43b39ab9de1a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -58,6 +58,8 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len); /* * Check if given mapping is supported by the file / underlying device. */ @@ -104,6 +106,12 @@ static inline bool dax_synchronous(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } +static inline bool dax_supported(struct dax_device *dax_dev, + struct block_device *bdev, int blocksize, sector_t start, + sector_t len) +{ + return false; +} static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { @@ -130,8 +138,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return __generic_fsdax_supported(dax_dev, bdev, blocksize, start, sectors); } -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); static inline void fs_put_dax(struct dax_device *dax_dev) { @@ -159,13 +165,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } -static inline bool dax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t len) -{ - return false; -} - static inline void fs_put_dax(struct dax_device *dax_dev) { } -- cgit v1.2.3 From e4378a0fdd43a676bb4dbd858bc9e61c6661193b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:05 -0400 Subject: SUNRPC: Remove trace_xprt_complete_rqst() Request completion is already recorded by an "rpc_task_wakeup queue=xprt_pending" trace record. A subsequent rpc_xdr_recvfrom trace record shows the number of bytes received. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 65d7dfbbc9cd..75b5df2a02fa 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -969,7 +969,6 @@ DECLARE_EVENT_CLASS(rpc_xprt_event, DEFINE_RPC_XPRT_EVENT(timer); DEFINE_RPC_XPRT_EVENT(lookup_rqst); -DEFINE_RPC_XPRT_EVENT(complete_rqst); TRACE_EVENT(xprt_transmit, TP_PROTO( -- cgit v1.2.3 From 06e234c6132784c56198423c653f1ad0e1e1fdc1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:11 -0400 Subject: SUNRPC: Hoist trace_xprtrdma_op_allocate into generic code Introduce a tracepoint in call_allocate that reports the exact sizes in the RPC buffer allocation request and the status of the result. This helps catch problems with XDR buffer provisioning, and replaces transport-specific debugging instrumentation. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 30 ------------------------------ include/trace/events/sunrpc.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index abe942225637..c187a9a8ead6 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1191,36 +1191,6 @@ TRACE_EVENT(xprtrdma_decode_seg, ** Allocation/release of rpcrdma_reqs and rpcrdma_reps **/ -TRACE_EVENT(xprtrdma_op_allocate, - TP_PROTO( - const struct rpc_task *task, - const struct rpcrdma_req *req - ), - - TP_ARGS(task, req), - - TP_STRUCT__entry( - __field(unsigned int, task_id) - __field(unsigned int, client_id) - __field(const void *, req) - __field(size_t, callsize) - __field(size_t, rcvsize) - ), - - TP_fast_assign( - __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; - __entry->req = req; - __entry->callsize = task->tk_rqstp->rq_callsize; - __entry->rcvsize = task->tk_rqstp->rq_rcvsize; - ), - - TP_printk("task:%u@%u req=%p (%zu, %zu)", - __entry->task_id, __entry->client_id, - __entry->req, __entry->callsize, __entry->rcvsize - ) -); - TRACE_EVENT(xprtrdma_op_free, TP_PROTO( const struct rpc_task *task, diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 75b5df2a02fa..7addf7d1596b 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -517,6 +517,36 @@ DEFINE_RPC_REPLY_EVENT(stale_creds); DEFINE_RPC_REPLY_EVENT(bad_creds); DEFINE_RPC_REPLY_EVENT(auth_tooweak); +TRACE_EVENT(rpc_buf_alloc, + TP_PROTO( + const struct rpc_task *task, + int status + ), + + TP_ARGS(task, status), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(size_t, callsize) + __field(size_t, recvsize) + __field(int, status) + ), + + TP_fast_assign( + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client->cl_clid; + __entry->callsize = task->tk_rqstp->rq_callsize; + __entry->recvsize = task->tk_rqstp->rq_rcvsize; + __entry->status = status; + ), + + TP_printk("task:%u@%u callsize=%zu recvsize=%zu status=%d", + __entry->task_id, __entry->client_id, + __entry->callsize, __entry->recvsize, __entry->status + ) +); + TRACE_EVENT(rpc_call_rpcerror, TP_PROTO( const struct rpc_task *task, -- cgit v1.2.3 From 78069487539dbb18e10aae15644019b468829ab2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:16 -0400 Subject: SUNRPC: Remove debugging instrumentation from xprt_release These instruments don't appear to add any substantial value. We already have this at the termination of each RPC: iozone-2617 [002] 975.713126: rpc_stats_latency: task:418@5 xid=0x260eab5d nfsv3 LOOKUP backlog=15 rtt=32 execute=58 iozone-2617 [002] 975.713127: xprt_release_cong: task:418@5 snd_task:4294967295 cong=256 cwnd=16384 iozone-2617 [002] 975.713127: xprt_put_cong: task:418@5 snd_task:4294967295 cong=0 cwnd=16384 Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index c187a9a8ead6..1e17c2fc9640 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1187,38 +1187,6 @@ TRACE_EVENT(xprtrdma_decode_seg, ) ); -/** - ** Allocation/release of rpcrdma_reqs and rpcrdma_reps - **/ - -TRACE_EVENT(xprtrdma_op_free, - TP_PROTO( - const struct rpc_task *task, - const struct rpcrdma_req *req - ), - - TP_ARGS(task, req), - - TP_STRUCT__entry( - __field(unsigned int, task_id) - __field(unsigned int, client_id) - __field(const void *, req) - __field(const void *, rep) - ), - - TP_fast_assign( - __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; - __entry->req = req; - __entry->rep = req->rl_reply; - ), - - TP_printk("task:%u@%u req=%p rep=%p", - __entry->task_id, __entry->client_id, - __entry->req, __entry->rep - ) -); - /** ** Callback events **/ -- cgit v1.2.3 From 09d2ba0cb1b311b2e3b144a0bbccc99f3c0d82d1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:21 -0400 Subject: SUNRPC: Update debugging instrumentation in xprt_do_reserve() Replace a dprintk() with a tracepoint. The tracepoint marks the point where an RPC request is assigned an XID. Additional clean up: Remove trace_xprt_enq_xmit, which reports much the same thing. That tracepoint was added for debugging commit 918f3c1fe83c ("SUNRPC: Improve latency for interactive tasks"). Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 55 +++++++++++++++++++------------------------ 1 file changed, 24 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 7addf7d1596b..781277bb9cb2 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1031,37 +1031,6 @@ TRACE_EVENT(xprt_transmit, __entry->seqno, __entry->status) ); -TRACE_EVENT(xprt_enq_xmit, - TP_PROTO( - const struct rpc_task *task, - int stage - ), - - TP_ARGS(task, stage), - - TP_STRUCT__entry( - __field(unsigned int, task_id) - __field(unsigned int, client_id) - __field(u32, xid) - __field(u32, seqno) - __field(int, stage) - ), - - TP_fast_assign( - __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client ? - task->tk_client->cl_clid : -1; - __entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid); - __entry->seqno = task->tk_rqstp->rq_seqno; - __entry->stage = stage; - ), - - TP_printk( - "task:%u@%u xid=0x%08x seqno=%u stage=%d", - __entry->task_id, __entry->client_id, __entry->xid, - __entry->seqno, __entry->stage) -); - TRACE_EVENT(xprt_ping, TP_PROTO(const struct rpc_xprt *xprt, int status), @@ -1176,6 +1145,30 @@ DEFINE_CONG_EVENT(release_cong); DEFINE_CONG_EVENT(get_cong); DEFINE_CONG_EVENT(put_cong); +TRACE_EVENT(xprt_reserve, + TP_PROTO( + const struct rpc_rqst *rqst + ), + + TP_ARGS(rqst), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, xid) + ), + + TP_fast_assign( + __entry->task_id = rqst->rq_task->tk_pid; + __entry->client_id = rqst->rq_task->tk_client->cl_clid; + __entry->xid = be32_to_cpu(rqst->rq_xid); + ), + + TP_printk("task:%u@%u xid=0x%08x", + __entry->task_id, __entry->client_id, __entry->xid + ) +); + TRACE_EVENT(xs_stream_read_data, TP_PROTO(struct rpc_xprt *xprt, ssize_t err, size_t total), -- cgit v1.2.3 From 9ce07ae5eb1d968c975a4dace0cac25d9e602c9a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:26 -0400 Subject: SUNRPC: Replace dprintk() call site in xprt_prepare_transmit Generate a trace event when an RPC request is queued without being sent immediately. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 781277bb9cb2..9746a722c5a2 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1093,6 +1093,7 @@ DECLARE_EVENT_CLASS(xprt_writelock_event, DEFINE_WRITELOCK_EVENT(reserve_xprt); DEFINE_WRITELOCK_EVENT(release_xprt); +DEFINE_WRITELOCK_EVENT(transmit_queued); DECLARE_EVENT_CLASS(xprt_cong_event, TP_PROTO( -- cgit v1.2.3 From 015747d296798510f94035a832252fcf477db434 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:32 -0400 Subject: SUNRPC: Replace dprintk() call site in xs_nospace() "no socket space" is an exceptional and infrequent condition that troubleshooters want to know about. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 9746a722c5a2..90d7b9916fe3 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -898,6 +898,34 @@ DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection); DEFINE_RPC_SOCKET_EVENT(rpc_socket_close); DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown); +TRACE_EVENT(rpc_socket_nospace, + TP_PROTO( + const struct rpc_rqst *rqst, + const struct sock_xprt *transport + ), + + TP_ARGS(rqst, transport), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(unsigned int, total) + __field(unsigned int, remaining) + ), + + TP_fast_assign( + __entry->task_id = rqst->rq_task->tk_pid; + __entry->client_id = rqst->rq_task->tk_client->cl_clid; + __entry->total = rqst->rq_slen; + __entry->remaining = rqst->rq_slen - transport->xmit.offset; + ), + + TP_printk("task:%u@%u total=%u remaining=%u", + __entry->task_id, __entry->client_id, + __entry->total, __entry->remaining + ) +); + TRACE_DEFINE_ENUM(XPRT_LOCKED); TRACE_DEFINE_ENUM(XPRT_CONNECTED); TRACE_DEFINE_ENUM(XPRT_CONNECTING); -- cgit v1.2.3 From db0a86c4266ac36769f54e2ce33fff0300c9bc00 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:47 -0400 Subject: SUNRPC: Replace connect dprintk call sites with a tracepoint This trace event can be used to audit transport connections from the client. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 90d7b9916fe3..0aa15cc3985d 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -983,6 +983,7 @@ DECLARE_EVENT_CLASS(rpc_xprt_lifetime_class, TP_ARGS(xprt)) DEFINE_RPC_XPRT_LIFETIME_EVENT(create); +DEFINE_RPC_XPRT_LIFETIME_EVENT(connect); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); -- cgit v1.2.3 From 914cdcc78a668a90bc627542f82fc3a92525141c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:09:58 -0400 Subject: SUNRPC: Add trace_rpc_timeout_status() For a long while we've wanted a tracepoint that fires when a major timeout is reported in the system log. Such a tracepoint can be attached to other actions that can take place when a timeout is detected (eg, server or connection health assessment). Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 0aa15cc3985d..edb41e187cf6 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -261,6 +261,7 @@ DECLARE_EVENT_CLASS(rpc_task_status, DEFINE_RPC_STATUS_EVENT(call); DEFINE_RPC_STATUS_EVENT(bind); DEFINE_RPC_STATUS_EVENT(connect); +DEFINE_RPC_STATUS_EVENT(timeout); TRACE_EVENT(rpc_request, TP_PROTO(const struct rpc_task *task), -- cgit v1.2.3 From 7c8099f6ada2654ef87aa992ec1b69b86249a353 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:10:03 -0400 Subject: SUNRPC: Trace call_refresh events Clean up: Replace dprintk call sites. Note that rpc_call_rpcerror() already has a trace point, so perhaps adding trace_rpc_refresh_status() isn't necessary. However, it does report a particular category of error. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index edb41e187cf6..3c5d707f7d54 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -262,6 +262,8 @@ DEFINE_RPC_STATUS_EVENT(call); DEFINE_RPC_STATUS_EVENT(bind); DEFINE_RPC_STATUS_EVENT(connect); DEFINE_RPC_STATUS_EVENT(timeout); +DEFINE_RPC_STATUS_EVENT(retry_refresh); +DEFINE_RPC_STATUS_EVENT(refresh); TRACE_EVENT(rpc_request, TP_PROTO(const struct rpc_task *task), -- cgit v1.2.3 From 42ebfc2cbf22df0abf2a17414db256d1db87c154 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:10:14 -0400 Subject: SUNRPC: Clean up call_bind_status() observability Time to remove dprintk call sites in here. Regarding the rpc_bind_status tracepoint: It's friendlier to administrators if they don't have to look up the error code to figure out what went wrong. Replace trace_rpc_bind_status with a set of tracepoints that report more specifically what the problem was, and what RPC program/version was being queried. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 3c5d707f7d54..353d9a18e254 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -259,7 +259,6 @@ DECLARE_EVENT_CLASS(rpc_task_status, TP_ARGS(task)) DEFINE_RPC_STATUS_EVENT(call); -DEFINE_RPC_STATUS_EVENT(bind); DEFINE_RPC_STATUS_EVENT(connect); DEFINE_RPC_STATUS_EVENT(timeout); DEFINE_RPC_STATUS_EVENT(retry_refresh); @@ -520,6 +519,19 @@ DEFINE_RPC_REPLY_EVENT(stale_creds); DEFINE_RPC_REPLY_EVENT(bad_creds); DEFINE_RPC_REPLY_EVENT(auth_tooweak); +#define DEFINE_RPCB_ERROR_EVENT(name) \ + DEFINE_EVENT(rpc_reply_event, rpcb_##name##_err, \ + TP_PROTO( \ + const struct rpc_task *task \ + ), \ + TP_ARGS(task)) + +DEFINE_RPCB_ERROR_EVENT(prog_unavail); +DEFINE_RPCB_ERROR_EVENT(timeout); +DEFINE_RPCB_ERROR_EVENT(bind_version); +DEFINE_RPCB_ERROR_EVENT(unreachable); +DEFINE_RPCB_ERROR_EVENT(unrecognized); + TRACE_EVENT(rpc_buf_alloc, TP_PROTO( const struct rpc_task *task, -- cgit v1.2.3 From e465cc3fa86341121205d3faca26866bdf331ed5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:10:19 -0400 Subject: SUNRPC: Remove rpcb_getport_async dprintk call sites In many cases, tracepoints already report these errors. In others, the dprintks were mainly useful when this code was less mature. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 353d9a18e254..6e5eba54fd30 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1269,6 +1269,41 @@ TRACE_EVENT(xs_stream_read_request, __entry->copied, __entry->reclen, __entry->offset) ); +TRACE_EVENT(rpcb_getport, + TP_PROTO( + const struct rpc_clnt *clnt, + const struct rpc_task *task, + unsigned int bind_version + ), + + TP_ARGS(clnt, task, bind_version), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(unsigned int, program) + __field(unsigned int, version) + __field(int, protocol) + __field(unsigned int, bind_version) + __string(servername, task->tk_xprt->servername) + ), + + TP_fast_assign( + __entry->task_id = task->tk_pid; + __entry->client_id = clnt->cl_clid; + __entry->program = clnt->cl_prog; + __entry->version = clnt->cl_vers; + __entry->protocol = task->tk_xprt->prot; + __entry->bind_version = bind_version; + __assign_str(servername, task->tk_xprt->servername); + ), + + TP_printk("task:%u@%u server=%s program=%u version=%u protocol=%d bind_version=%u", + __entry->task_id, __entry->client_id, __get_str(servername), + __entry->program, __entry->version, __entry->protocol, + __entry->bind_version + ) +); DECLARE_EVENT_CLASS(svc_xdr_buf_class, TP_PROTO( -- cgit v1.2.3 From ac1ae534215b9b0a346547654b4720abd0882f15 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:10:24 -0400 Subject: SUNRPC: Hoist trace_xprtrdma_op_setport into generic code Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 1 - include/trace/events/sunrpc.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 1e17c2fc9640..ad46bec3a65e 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -423,7 +423,6 @@ DEFINE_CONN_EVENT(connect); DEFINE_CONN_EVENT(disconnect); DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc); -DEFINE_RXPRT_EVENT(xprtrdma_op_setport); TRACE_EVENT(xprtrdma_op_connect, TP_PROTO( diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 6e5eba54fd30..05291ce099d6 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1305,6 +1305,35 @@ TRACE_EVENT(rpcb_getport, ) ); +TRACE_EVENT(rpcb_setport, + TP_PROTO( + const struct rpc_task *task, + int status, + unsigned short port + ), + + TP_ARGS(task, status, port), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(int, status) + __field(unsigned short, port) + ), + + TP_fast_assign( + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client->cl_clid; + __entry->status = status; + __entry->port = port; + ), + + TP_printk("task:%u@%u status=%d port=%u", + __entry->task_id, __entry->client_id, + __entry->status, __entry->port + ) +); + DECLARE_EVENT_CLASS(svc_xdr_buf_class, TP_PROTO( const struct svc_rqst *rqst, -- cgit v1.2.3 From c3adcc7dfbfcb1bd7e29fa95f03d1f96b514e03e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:10:40 -0400 Subject: SUNRPC: Replace rpcbind dprintk call sites with tracepoints In many cases, tracepoints already report these errors. In others, the dprintks were mainly useful when this code was less mature. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 86 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 05291ce099d6..b5d4cbbaf4b0 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1334,6 +1334,92 @@ TRACE_EVENT(rpcb_setport, ) ); +TRACE_EVENT(pmap_register, + TP_PROTO( + u32 program, + u32 version, + int protocol, + unsigned short port + ), + + TP_ARGS(program, version, protocol, port), + + TP_STRUCT__entry( + __field(unsigned int, program) + __field(unsigned int, version) + __field(int, protocol) + __field(unsigned int, port) + ), + + TP_fast_assign( + __entry->program = program; + __entry->version = version; + __entry->protocol = protocol; + __entry->port = port; + ), + + TP_printk("program=%u version=%u protocol=%d port=%u", + __entry->program, __entry->version, + __entry->protocol, __entry->port + ) +); + +TRACE_EVENT(rpcb_register, + TP_PROTO( + u32 program, + u32 version, + const char *addr, + const char *netid + ), + + TP_ARGS(program, version, addr, netid), + + TP_STRUCT__entry( + __field(unsigned int, program) + __field(unsigned int, version) + __string(addr, addr) + __string(netid, netid) + ), + + TP_fast_assign( + __entry->program = program; + __entry->version = version; + __assign_str(addr, addr); + __assign_str(netid, netid); + ), + + TP_printk("program=%u version=%u addr=%s netid=%s", + __entry->program, __entry->version, + __get_str(addr), __get_str(netid) + ) +); + +TRACE_EVENT(rpcb_unregister, + TP_PROTO( + u32 program, + u32 version, + const char *netid + ), + + TP_ARGS(program, version, netid), + + TP_STRUCT__entry( + __field(unsigned int, program) + __field(unsigned int, version) + __string(netid, netid) + ), + + TP_fast_assign( + __entry->program = program; + __entry->version = version; + __assign_str(netid, netid); + ), + + TP_printk("program=%u version=%u netid=%s", + __entry->program, __entry->version, __get_str(netid) + ) +); + DECLARE_EVENT_CLASS(svc_xdr_buf_class, TP_PROTO( const struct svc_rqst *rqst, -- cgit v1.2.3 From 1466c2216382fc392817fc8888e4ebefb2ef4816 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:10:45 -0400 Subject: SUNRPC: Clean up RPC scheduler tracepoints Remove several redundant dprintk call sites, and replace a couple of potentially useful ones with tracepoints. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index b5d4cbbaf4b0..11e5e52f4ce5 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -387,6 +387,8 @@ DECLARE_EVENT_CLASS(rpc_task_running, DEFINE_RPC_RUNNING_EVENT(begin); DEFINE_RPC_RUNNING_EVENT(run_action); +DEFINE_RPC_RUNNING_EVENT(sync_sleep); +DEFINE_RPC_RUNNING_EVENT(sync_wake); DEFINE_RPC_RUNNING_EVENT(complete); DEFINE_RPC_RUNNING_EVENT(signalled); DEFINE_RPC_RUNNING_EVENT(end); -- cgit v1.2.3 From 721a1d388b5536adb220aba25775a256f09790c3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 8 Jul 2020 16:10:50 -0400 Subject: SUNRPC: Remove dprintk call sites in RPC queuing functions Remove redundant call sites or call sites that are already covered by tracepoints. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/sunrpc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 11e5e52f4ce5..f45b3c01370c 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -390,6 +390,7 @@ DEFINE_RPC_RUNNING_EVENT(run_action); DEFINE_RPC_RUNNING_EVENT(sync_sleep); DEFINE_RPC_RUNNING_EVENT(sync_wake); DEFINE_RPC_RUNNING_EVENT(complete); +DEFINE_RPC_RUNNING_EVENT(timeout); DEFINE_RPC_RUNNING_EVENT(signalled); DEFINE_RPC_RUNNING_EVENT(end); -- cgit v1.2.3 From 1138ce1cf60954d1c0e2d7b4eba5b4df5813fd86 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:31:30 -0700 Subject: sunrpc: fix duplicated word in Change "time time" to "time expiry_time" to match the field name. Signed-off-by: Randy Dunlap Cc: "J. Bruce Fields" Cc: Chuck Lever Cc: Trond Myklebust Cc: Anna Schumaker Cc: linux-nfs@vger.kernel.org Signed-off-by: Anna Schumaker --- include/linux/sunrpc/cache.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 10891b70fc7b..d0965e2997b0 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -45,7 +45,8 @@ */ struct cache_head { struct hlist_node cache_list; - time64_t expiry_time; /* After time time, don't use the data */ + time64_t expiry_time; /* After time expiry_time, don't use + * the data */ time64_t last_refresh; /* If CACHE_PENDING, this is when upcall was * sent, else this is when update was * received, though it is alway set to -- cgit v1.2.3 From 0bdd4cea12a9fd79a7eb7de8493a5fef54d0eea6 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Tue, 7 Jul 2020 21:50:12 +0200 Subject: Replace HTTP links with HTTPS ones: NFS, SUNRPC, and LOCKD clients Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Signed-off-by: Anna Schumaker --- include/linux/sunrpc/bc_xprt.h | 2 +- include/linux/sunrpc/msg_prot.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index d796058cdff2..f07c334c599f 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -4,7 +4,7 @@ NetApp provides this source code under the GPL v2 License. The GPL v2 license is available at -http://opensource.org/licenses/gpl-license.php. +https://opensource.org/licenses/gpl-license.php. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index bea40d9f03a1..43f854487539 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -143,7 +143,7 @@ typedef __be32 rpc_fraghdr; /* * Well-known netids. See: * - * http://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml + * https://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml */ #define RPCBIND_NETID_UDP "udp" #define RPCBIND_NETID_TCP "tcp" -- cgit v1.2.3 From 24addd848a45747bcda68418710c72fdc8e145e4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 21 Sep 2020 08:58:39 -0700 Subject: fs: Introduce i_blocks_per_page This helper is useful for both THPs and for supporting block size larger than page size. Convert all users that I could find (we have a few different ways of writing this idiom, and I may have missed some). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Acked-by: Dave Kleikamp --- include/linux/pagemap.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7de11dcd534d..853733286138 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -899,4 +899,20 @@ static inline int page_mkwrite_check_truncate(struct page *page, return offset; } +/** + * i_blocks_per_page - How many blocks fit in this page. + * @inode: The inode which contains the blocks. + * @page: The page (head page if the page is a THP). + * + * If the block size is larger than the size of this page, return zero. + * + * Context: The caller should hold a refcount on the page to prevent it + * from being split. + * Return: The number of filesystem blocks covered by this page. + */ +static inline +unsigned int i_blocks_per_page(struct inode *inode, struct page *page) +{ + return thp_size(page) >> inode->i_blkbits; +} #endif /* _LINUX_PAGEMAP_H */ -- cgit v1.2.3 From 81ee8e52a71c712dbe04994f1430cb4c88b87ad6 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 21 Sep 2020 08:58:42 -0700 Subject: iomap: Change calling convention for zeroing Pass the full length to iomap_zero() and dax_iomap_zero(), and have them return how many bytes they actually handled. This is preparatory work for handling THP, although it looks like DAX could actually take advantage of it if there's a larger contiguous area. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- include/linux/dax.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 6904d4e0b2e0..951a851a0481 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -214,8 +214,7 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size, - struct iomap *iomap); +s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- cgit v1.2.3 From c754e137f55e075d6b6ad9b866c32e9aad260a83 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 18 Sep 2020 15:29:59 -0400 Subject: pNFS/flexfiles: Be consistent about mirror index types A mirror index is always of type u32. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9408f3252c8e..69cb46f7b8d2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1611,8 +1611,8 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_commit_idx; /* ds index if ds_clp is set */ - int pgio_mirror_idx;/* mirror index in pgio layer */ + u32 ds_commit_idx; /* ds index if ds_clp is set */ + u32 pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From 43437d0417a36bc9174deedce4ecc2c516ffde57 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Mon, 21 Sep 2020 13:50:38 +0300 Subject: ASoC: SOF: pm: Fix prepare callback behavior for OF usecase On i.MX platforms PM is not managed via ACPI although CONFIG_ACPI can be set. So, in order to correctly set the system target state we introduce a flag for platforms that require to use acpi target states. Signed-off-by: Daniel Baluta Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200921105038.2909899-1-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index f3e716c8ce1c..9aa055289dcc 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -66,6 +66,8 @@ struct sof_dev_desc { /* alternate list of machines using this configuration */ struct snd_soc_acpi_mach *alt_machines; + bool use_acpi_target_states; + /* Platform resource indexes in BAR / ACPI resources. */ /* Must set to -1 if not used - add new items to end */ int resindex_lpe_base; -- cgit v1.2.3 From 4c9db39361da5dcf0e77f4aeb4817be3bf7d626b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Sat, 19 Sep 2020 23:28:25 +0200 Subject: regulator: unexport regulator_lock/unlock() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit regulator_lock/unlock() was used only to guard regulator_notifier_call_chain(). As no users remain, make the functions internal. Signed-off-by: Michał Mirosław Link: https://lore.kernel.org/r/d3381aabd2632aff5e7b839d55868bec6e85c811.1600550732.git.mirq-linux@rere.qmqm.pl Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 8539f34ae42b..11cade73726c 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -533,9 +533,6 @@ int regulator_set_current_limit_regmap(struct regulator_dev *rdev, int regulator_get_current_limit_regmap(struct regulator_dev *rdev); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data); -void regulator_lock(struct regulator_dev *rdev); -void regulator_unlock(struct regulator_dev *rdev); - /* * Helper functions intended to be used by regulator drivers prior registering * their regulators. -- cgit v1.2.3 From cd7798cbd28044a3026619e36993160ba8fa118d Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sun, 13 Sep 2020 14:21:14 +0100 Subject: iio: Add __printf() attributes to various allocation functions A partial set of these was added to IIO a long time back. This fills in some gaps in coverage highlighted by building with W=1 Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200913132115.800131-3-jic23@kernel.org --- include/linux/iio/iio.h | 3 ++- include/linux/iio/trigger_consumer.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e2df67a3b9ab..2e45b3ceafa7 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -691,8 +691,9 @@ static inline void *iio_priv(const struct iio_dev *indio_dev) void iio_device_free(struct iio_dev *indio_dev); struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv); +__printf(2, 3) struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, - const char *fmt, ...); + const char *fmt, ...); /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device diff --git a/include/linux/iio/trigger_consumer.h b/include/linux/iio/trigger_consumer.h index 3aa2f132dd67..2c05dfad88d7 100644 --- a/include/linux/iio/trigger_consumer.h +++ b/include/linux/iio/trigger_consumer.h @@ -38,7 +38,7 @@ struct iio_poll_func { }; -struct iio_poll_func +__printf(5, 6) struct iio_poll_func *iio_alloc_pollfunc(irqreturn_t (*h)(int irq, void *p), irqreturn_t (*thread)(int irq, void *p), int type, -- cgit v1.2.3 From 36e322ec5dd24f1d0840061ffe406458669bccf1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Thu, 17 Sep 2020 17:52:20 +0200 Subject: iio: adis: Move burst mode into adis_data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add burst mode variables in the per device specific data structure. As some drivers support multiple devices with different burst sizes it makes sense this data to be in `adis_data`. While moving the variables, there are two main differences: 1. The `en`variable is dropped. If a device supports burst mode, it will just use it as it will has better performance for almost all real use cases. 2. Replace `extra_len` by `burst_len`. Users should now explicitly define the length of the burst buffer as it is typically constant. This also allows to remove the following line from the library: ``` /* All but the timestamp channel */ burst_length = (indio_dev->num_channels - 1) * sizeof(u16); ``` The library should not assume that a timestamp channel is defined. Moreover, most parts also include some diagnostic data, crc, etc.. in the burst buffer that needed to be included in an `extra_len` variable which is not that nice. On top of this, some devices already start to have some 32bit size channels ... This patch is also a move to completely drop the `struct adis_burst` from the library. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron Link: https://lore.kernel.org/r/20200917155223.218500-2-nuno.sa@analog.com --- include/linux/iio/imu/adis.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 01ba691da2f3..c502ea3b9199 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -51,6 +51,11 @@ struct adis_timeout { * @timeouts: Chip specific delays * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable * @has_paging: True if ADIS device has paged registers + * @burst_reg_cmd: Register command that triggers burst + * @burst_len: Burst size in the SPI RX buffer. If @burst_max_len is defined, + * this should be the minimum size supported by the device. + * @burst_max_len: Holds the maximum burst size when the device supports + * more than one burst mode with different sizes */ struct adis_data { unsigned int read_delay; @@ -75,6 +80,10 @@ struct adis_data { int (*enable_irq)(struct adis *adis, bool enable); bool has_paging; + + unsigned int burst_reg_cmd; + unsigned int burst_len; + unsigned int burst_max_len; }; /** -- cgit v1.2.3 From e8173161746d1d8a8b9dfd8968cf695efaa90d09 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Thu, 17 Sep 2020 17:52:23 +0200 Subject: iio: adis. Drop adis_burst struct MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As there are no users anymore of this structure, it can be safely removed. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron Link: https://lore.kernel.org/r/20200917155223.218500-5-nuno.sa@analog.com --- include/linux/iio/imu/adis.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index c502ea3b9199..04e96d688ba9 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -20,7 +20,6 @@ #define ADIS_REG_PAGE_ID 0x00 struct adis; -struct adis_burst; /** * struct adis_timeouts - ADIS chip variant timeouts @@ -108,7 +107,6 @@ struct adis { struct iio_trigger *trig; const struct adis_data *data; - struct adis_burst *burst; unsigned int burst_extra_len; /** * The state_lock is meant to be used during operations that require @@ -508,21 +506,6 @@ int adis_single_conversion(struct iio_dev *indio_dev, #ifdef CONFIG_IIO_ADIS_LIB_BUFFER -/** - * struct adis_burst - ADIS data for burst transfers - * @en burst mode enabled - * @reg_cmd register command that triggers burst - * @extra_len extra length to account in the SPI RX buffer - * @burst_max_len holds the maximum burst size when the device supports - * more than one burst mode with different sizes - */ -struct adis_burst { - bool en; - unsigned int reg_cmd; - const u32 extra_len; - const u32 burst_max_len; -}; - int devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, irq_handler_t trigger_handler); -- cgit v1.2.3 From 65c204398928f9c79f1a29912b410439f7052635 Mon Sep 17 00:00:00 2001 From: Tony Ambardar Date: Sat, 19 Sep 2020 22:01:34 -0700 Subject: bpf: Prevent .BTF section elimination Systems with memory or disk constraints often reduce the kernel footprint by configuring LD_DEAD_CODE_DATA_ELIMINATION. However, this can result in removal of any BTF information. Use the KEEP() macro to preserve the BTF data as done with other important sections, while still allowing for smaller kernels. Fixes: 90ceddcb4950 ("bpf: Support llvm-objcopy for vmlinux BTF") Signed-off-by: Tony Ambardar Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/a635b5d3e2da044e7b51ec1315e8910fbce0083f.1600417359.git.Tony.Ambardar@gmail.com --- include/asm-generic/vmlinux.lds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 5430febd34be..7636bc71c71f 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -661,7 +661,7 @@ #define BTF \ .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \ __start_BTF = .; \ - *(.BTF) \ + KEEP(*(.BTF)) \ __stop_BTF = .; \ } \ . = ALIGN(4); \ -- cgit v1.2.3 From c12fa88c6d16ed3865072d91154cff6fd1cd9cd4 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 10 Sep 2020 20:25:08 +0800 Subject: vfio: Fix typo of the device_state A typo fix ("_RUNNNG" => "_RUNNING") in comment block of the uapi header. Signed-off-by: Zenghui Yu Reviewed-by: Cornelia Huck Reviewed-by: Kirti Wankhede Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 920470502329..d4bd39e124bf 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -462,7 +462,7 @@ struct vfio_region_gfx_edid { * 5. Resumed * |--------->| * - * 0. Default state of VFIO device is _RUNNNG when the user application starts. + * 0. Default state of VFIO device is _RUNNING when the user application starts. * 1. During normal shutdown of the user application, the user application may * optionally change the VFIO device state from _RUNNING to _STOP. This * transition is optional. The vendor driver must support this transition but -- cgit v1.2.3 From 12856e7acde4702b7c3238c15fcba86ff6aa507f Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Thu, 10 Sep 2020 10:59:55 -0400 Subject: PCI/IOV: Mark VFs as not implementing PCI_COMMAND_MEMORY For VFs, the Memory Space Enable bit in the Command Register is hard-wired to 0. Add a new bit to signify devices where the Command Register Memory Space Enable bit does not control the device's response to MMIO accesses. Fixes: abafbc551fdd ("vfio-pci: Invalidate mmaps and block MMIO access on disabled memory") Signed-off-by: Matthew Rosato Acked-by: Bjorn Helgaas Signed-off-by: Alex Williamson --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 835530605c0d..3ff723124ca7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -445,6 +445,7 @@ struct pci_dev { unsigned int is_probed:1; /* Device probing in progress */ unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ + unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From 7d6e1329652ed971d1b6e0e7bea66fba5044e271 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Tue, 15 Sep 2020 15:05:18 -0400 Subject: vfio iommu: Add dma available capability Commit 492855939bdb ("vfio/type1: Limit DMA mappings per container") added the ability to limit the number of memory backed DMA mappings. However on s390x, when lazy mapping is in use, we use a very large number of concurrent mappings. Let's provide the current allowable number of DMA mappings to userspace via the IOMMU info chain so that userspace can take appropriate mitigation. Signed-off-by: Matthew Rosato Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 920470502329..3891e03d3af0 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1039,6 +1039,21 @@ struct vfio_iommu_type1_info_cap_migration { __u64 max_dirty_bitmap_size; /* in bytes */ }; +/* + * The DMA available capability allows to report the current number of + * simultaneously outstanding DMA mappings that are allowed. + * + * The structure below defines version 1 of this capability. + * + * avail: specifies the current number of outstanding DMA mappings allowed. + */ +#define VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL 3 + +struct vfio_iommu_type1_info_dma_avail { + struct vfio_info_cap_header header; + __u32 avail; +}; + #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) /** -- cgit v1.2.3 From 2af30f115d6957f372ce3096c7198763ff253d97 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 21 Sep 2020 13:12:17 +0100 Subject: btf: Make btf_set_contains take a const pointer bsearch doesn't modify the contents of the array, so we can take a const pointer. Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200921121227.255763-2-lmb@cloudflare.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d7c5a6ed87e3..0478b20d335b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1905,6 +1905,6 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); struct btf_id_set; -bool btf_id_set_contains(struct btf_id_set *set, u32 id); +bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From 27774b7073b5d520c80f1fcb8e9993fc139f21bd Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 21 Sep 2020 13:12:19 +0100 Subject: btf: Add BTF_ID_LIST_SINGLE macro Add a convenience macro that allows defining a BTF ID list with a single item. This lets us cut down on repetitive macros. Suggested-by: Andrii Nakryiko Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200921121227.255763-4-lmb@cloudflare.com --- include/linux/btf_ids.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 210b086188a3..57890b357f85 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -76,6 +76,13 @@ extern u32 name[]; #define BTF_ID_LIST_GLOBAL(name) \ __BTF_ID_LIST(name, globl) +/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with + * a single entry. + */ +#define BTF_ID_LIST_SINGLE(name, prefix, typename) \ + BTF_ID_LIST(name) \ + BTF_ID(prefix, typename) + /* * The BTF_ID_UNUSED macro defines 4 zero bytes. * It's used when we want to define 'unused' entry @@ -140,6 +147,7 @@ extern struct btf_id_set name; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED #define BTF_ID_LIST_GLOBAL(name) u32 name[1]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; #define BTF_SET_START(name) static struct btf_id_set name = { 0 }; #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; #define BTF_SET_END(name) -- cgit v1.2.3 From 9436ef6e862b9ca22e5b12f87b106e07d5af4cae Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 21 Sep 2020 13:12:20 +0100 Subject: bpf: Allow specifying a BTF ID per argument in function protos Function prototypes using ARG_PTR_TO_BTF_ID currently use two ways to signal which BTF IDs are acceptable. First, bpf_func_proto.btf_id is an array of IDs, one for each argument. This array is only accessed up to the highest numbered argument that uses ARG_PTR_TO_BTF_ID and may therefore be less than five arguments long. It usually points at a BTF_ID_LIST. Second, check_btf_id is a function pointer that is called by the verifier if present. It gets the actual BTF ID of the register, and the argument number we're currently checking. It turns out that the only user check_arg_btf_id ignores the argument, and is simply used to check whether the BTF ID has a struct sock_common at it's start. Replace both of these mechanisms with an explicit BTF ID for each argument in a function proto. Thanks to btf_struct_ids_match this is very flexible: check_arg_btf_id can be replaced by requiring struct sock_common. Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200921121227.255763-5-lmb@cloudflare.com --- include/linux/bpf.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0478b20d335b..87b0d5dcc1ff 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -326,12 +326,16 @@ struct bpf_func_proto { }; enum bpf_arg_type arg_type[5]; }; - int *btf_id; /* BTF ids of arguments */ - bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is - * valid. Often used if more - * than one btf id is permitted - * for this argument. - */ + union { + struct { + u32 *arg1_btf_id; + u32 *arg2_btf_id; + u32 *arg3_btf_id; + u32 *arg4_btf_id; + u32 *arg5_btf_id; + }; + u32 *arg_btf_id[5]; + }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); }; @@ -1385,8 +1389,6 @@ int btf_struct_access(struct bpf_verifier_log *log, u32 *next_btf_id); bool btf_struct_ids_match(struct bpf_verifier_log *log, int off, u32 id, u32 need_type_id); -int btf_resolve_helper_id(struct bpf_verifier_log *log, - const struct bpf_func_proto *fn, int); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, -- cgit v1.2.3 From f79e7ea571732a6e16f15c6e2f000c347e2d7431 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 21 Sep 2020 13:12:27 +0100 Subject: bpf: Use a table to drive helper arg type checks The mapping between bpf_arg_type and bpf_reg_type is encoded in a big hairy if statement that is hard to follow. The debug output also leaves to be desired: if a reg_type doesn't match we only print one of the options, instead printing all the valid ones. Convert the if statement into a table which is then used to drive type checking. If none of the reg_types match we print all options, e.g.: R2 type=rdonly_buf expected=fp, pkt, pkt_meta, map_value Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200921121227.255763-12-lmb@cloudflare.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 87b0d5dcc1ff..fc5c901c7542 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -292,6 +292,7 @@ enum bpf_arg_type { ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ + __BPF_ARG_TYPE_MAX, }; /* type of values returned from helper functions */ -- cgit v1.2.3 From 163cd1059a85d225b811ddb4192fabd1553f77f1 Mon Sep 17 00:00:00 2001 From: Kai Vehmanen Date: Mon, 21 Sep 2020 13:08:41 +0300 Subject: ASoC: hdac: make SOF HDA codec driver probe deterministic To provide backward compatibility to older systems, the SOF HDA driver allows user to specify which HDMI codec driver to use at runtime via kernel parameter. This mechanism has a subtle flaw in that it assumes the codec drivers not to be loaded when the SOF PCI driver is loaded. The problem is rooted in use of the hdev->type field. snd_hdac_ext_bus_device_init() initializes this field to HDA_DEV_ASOC. This signals the HDA core that ASoC drivers should be considered in driver matching (hda_bus_match()). The SOF and SST drivers continue by overriding this field to HDA_DEV_LEGACY and proceeding to load driver modules with request_module(). Correct drivers will get loaded and attached. If however the codec drivers are already loaded when snd_hdac_ext_bus_device_init() is called, the matching will not work as expected as device type is still set to HDA_DEV_ASOC. Specifically if hdac-hdmi is attached when machine driver is configured to use hdac-hda, this leads to out-of-bounds memory access in hda_dsp_hdmi_build_controls(). Fix the issue by adding codec type as a parameter to snd_hdac_ext_bus_device_init() and ensuring type is set correctly from the start. Fixes: 139c7febad1a ("ASoC: SOF: Intel: add support for snd-hda-codec-hdmi") Signed-off-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20200921100841.2882662-1-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/sound/hdaudio_ext.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index ef88b20c7b0a..7abf74c1c474 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -10,7 +10,7 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, void snd_hdac_ext_bus_exit(struct hdac_bus *bus); int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr, - struct hdac_device *hdev); + struct hdac_device *hdev, int type); void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev); void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus); -- cgit v1.2.3 From 8a8b9047a8975ad4bdee34b7affad66edfbe626d Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 16 Sep 2020 22:16:56 +0800 Subject: netfilter: nf_tables: Remove ununsed function nft_data_debug It is never used, so can be removed. Signed-off-by: YueHaibing Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 8ceca0e419b3..c4c526507ddb 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -148,13 +148,6 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src, memcpy(dst, src, len); } -static inline void nft_data_debug(const struct nft_data *data) -{ - pr_debug("data[0]=%x data[1]=%x data[2]=%x data[3]=%x\n", - data->data[0], data->data[1], - data->data[2], data->data[3]); -} - /** * struct nft_ctx - nf_tables rule/set context * -- cgit v1.2.3 From 92ec804f3dbf0d986f8e10850bfff14f316d7aaf Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 21 Sep 2020 15:10:53 -0700 Subject: net: phy: bcm7xxx: Add an entry for BCM72113 BCM72113 features a 28nm integrated EPHY, add an entry to the driver for it. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6ad4c000661a..d0bd226d6bd9 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -30,6 +30,7 @@ #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM89610 0x03625cd0 +#define PHY_ID_BCM72113 0x35905310 #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 -- cgit v1.2.3 From 74caba7f2a0685575b3ee5330a118f5922485e02 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 21 Sep 2020 13:24:45 +0206 Subject: printk: move dictionary keys to dev_printk_info Dictionaries are only used for SUBSYSTEM and DEVICE properties. The current implementation stores the property names each time they are used. This requires more space than otherwise necessary. Also, because the dictionary entries are currently considered optional, it cannot be relied upon that they are always available, even if the writer wanted to store them. These issues will increase should new dictionary properties be introduced. Rather than storing the subsystem and device properties in the dict ring, introduce a struct dev_printk_info with separate fields to store only the property values. Embed this struct within the struct printk_info to provide guaranteed availability. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/87mu1jl6ne.fsf@jogness.linutronix.de --- include/linux/dev_printk.h | 8 ++++++++ include/linux/printk.h | 6 ++++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 3028b644b4fb..6f009559ee54 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -21,6 +21,14 @@ struct device; +#define PRINTK_INFO_SUBSYSTEM_LEN 16 +#define PRINTK_INFO_DEVICE_LEN 48 + +struct dev_printk_info { + char subsystem[PRINTK_INFO_SUBSYSTEM_LEN]; + char device[PRINTK_INFO_DEVICE_LEN]; +}; + #ifdef CONFIG_PRINTK __printf(3, 0) __cold diff --git a/include/linux/printk.h b/include/linux/printk.h index fc8f03c54543..071500ee7281 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -158,10 +158,12 @@ static inline void printk_nmi_direct_enter(void) { } static inline void printk_nmi_direct_exit(void) { } #endif /* PRINTK_NMI */ +struct dev_printk_info; + #ifdef CONFIG_PRINTK -asmlinkage __printf(5, 0) +asmlinkage __printf(4, 0) int vprintk_emit(int facility, int level, - const char *dict, size_t dictlen, + const struct dev_printk_info *dev_info, const char *fmt, va_list args); asmlinkage __printf(1, 0) -- cgit v1.2.3 From 55c5cc63ab3277aa20637dc20f6528987ac23743 Mon Sep 17 00:00:00 2001 From: Cheng-Yi Chiang Date: Tue, 22 Sep 2020 14:23:16 +0800 Subject: ASoC: hdmi-codec: Use set_jack ops to set jack Use set_jack ops to set jack so machine drivers do not need to include hdmi-codec.h explicitly. Signed-off-by: Cheng-Yi Chiang Reviewed-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20200922062316.1172935-1-cychiang@chromium.org Signed-off-by: Mark Brown --- include/sound/hdmi-codec.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/sound/hdmi-codec.h b/include/sound/hdmi-codec.h index 7754631a3102..b55970859a13 100644 --- a/include/sound/hdmi-codec.h +++ b/include/sound/hdmi-codec.h @@ -117,9 +117,6 @@ struct hdmi_codec_pdata { struct snd_soc_component; struct snd_soc_jack; -int hdmi_codec_set_jack_detect(struct snd_soc_component *component, - struct snd_soc_jack *jack); - #define HDMI_CODEC_DRV_NAME "hdmi-audio-codec" #endif /* __HDMI_CODEC_H__ */ -- cgit v1.2.3 From 15b760c37ad3c3f2b922506eaca4ca8b4292e621 Mon Sep 17 00:00:00 2001 From: Andra Paraschiv Date: Mon, 21 Sep 2020 15:17:15 +0300 Subject: nitro_enclaves: Add ioctl interface definition The Nitro Enclaves driver handles the enclave lifetime management. This includes enclave creation, termination and setting up its resources such as memory and CPU. An enclave runs alongside the VM that spawned it. It is abstracted as a process running in the VM that launched it. The process interacts with the NE driver, that exposes an ioctl interface for creating an enclave and setting up its resources. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * No changes. v7 -> v8 * Add NE custom error codes for user space memory regions not backed by pages multiple of 2 MiB, invalid flags and enclave CID. * Add max flag value for enclave image load info. v6 -> v7 * Clarify in the ioctls documentation that the return value is -1 and errno is set on failure. * Update the error code value for NE_ERR_INVALID_MEM_REGION_SIZE as it gets in user space as value 25 (ENOTTY) instead of 515. Update the NE custom error codes values range to not be the same as the ones defined in include/linux/errno.h, although these are not propagated to user space. v5 -> v6 * Fix typo in the description about the NE CPU pool. * Update documentation to kernel-doc format. * Remove the ioctl to query API version. v4 -> v5 * Add more details about the ioctl calls usage e.g. error codes, file descriptors used. * Update the ioctl to set an enclave vCPU to not return a file descriptor. * Add specific NE error codes. v3 -> v4 * Decouple NE ioctl interface from KVM API. * Add NE API version and the corresponding ioctl call. * Add enclave / image load flags options. v2 -> v3 * Remove the GPL additional wording as SPDX-License-Identifier is already in place. v1 -> v2 * Add ioctl for getting enclave image load metadata. * Update NE_ENCLAVE_START ioctl name to NE_START_ENCLAVE. * Add entry in Documentation/userspace-api/ioctl/ioctl-number.rst for NE ioctls. * Update NE ioctls definition based on the updated ioctl range for major and minor. Reviewed-by: Alexander Graf Reviewed-by: Stefan Hajnoczi Signed-off-by: Alexandru Vasile Signed-off-by: Andra Paraschiv Link: https://lore.kernel.org/r/20200921121732.44291-2-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman --- include/linux/nitro_enclaves.h | 11 ++ include/uapi/linux/nitro_enclaves.h | 359 ++++++++++++++++++++++++++++++++++++ 2 files changed, 370 insertions(+) create mode 100644 include/linux/nitro_enclaves.h create mode 100644 include/uapi/linux/nitro_enclaves.h (limited to 'include') diff --git a/include/linux/nitro_enclaves.h b/include/linux/nitro_enclaves.h new file mode 100644 index 000000000000..d91ef2bfdf47 --- /dev/null +++ b/include/linux/nitro_enclaves.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + */ + +#ifndef _LINUX_NITRO_ENCLAVES_H_ +#define _LINUX_NITRO_ENCLAVES_H_ + +#include + +#endif /* _LINUX_NITRO_ENCLAVES_H_ */ diff --git a/include/uapi/linux/nitro_enclaves.h b/include/uapi/linux/nitro_enclaves.h new file mode 100644 index 000000000000..b945073fe544 --- /dev/null +++ b/include/uapi/linux/nitro_enclaves.h @@ -0,0 +1,359 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + */ + +#ifndef _UAPI_LINUX_NITRO_ENCLAVES_H_ +#define _UAPI_LINUX_NITRO_ENCLAVES_H_ + +#include + +/** + * DOC: Nitro Enclaves (NE) Kernel Driver Interface + */ + +/** + * NE_CREATE_VM - The command is used to create a slot that is associated with + * an enclave VM. + * The generated unique slot id is an output parameter. + * The ioctl can be invoked on the /dev/nitro_enclaves fd, before + * setting any resources, such as memory and vCPUs, for an + * enclave. Memory and vCPUs are set for the slot mapped to an enclave. + * A NE CPU pool has to be set before calling this function. The + * pool can be set after the NE driver load, using + * /sys/module/nitro_enclaves/parameters/ne_cpus. + * Its format is the detailed in the cpu-lists section: + * https://www.kernel.org/doc/html/latest/admin-guide/kernel-parameters.html + * CPU 0 and its siblings have to remain available for the + * primary / parent VM, so they cannot be set for enclaves. Full + * CPU core(s), from the same NUMA node, need(s) to be included + * in the CPU pool. + * + * Context: Process context. + * Return: + * * Enclave file descriptor - Enclave file descriptor used with + * ioctl calls to set vCPUs and memory + * regions, then start the enclave. + * * -1 - There was a failure in the ioctl logic. + * On failure, errno is set to: + * * EFAULT - copy_to_user() failure. + * * ENOMEM - Memory allocation failure for internal + * bookkeeping variables. + * * NE_ERR_NO_CPUS_AVAIL_IN_POOL - No NE CPU pool set / no CPUs available + * in the pool. + * * Error codes from get_unused_fd_flags() and anon_inode_getfile(). + * * Error codes from the NE PCI device request. + */ +#define NE_CREATE_VM _IOR(0xAE, 0x20, __u64) + +/** + * NE_ADD_VCPU - The command is used to set a vCPU for an enclave. The vCPU can + * be auto-chosen from the NE CPU pool or it can be set by the + * caller, with the note that it needs to be available in the NE + * CPU pool. Full CPU core(s), from the same NUMA node, need(s) to + * be associated with an enclave. + * The vCPU id is an input / output parameter. If its value is 0, + * then a CPU is chosen from the enclave CPU pool and returned via + * this parameter. + * The ioctl can be invoked on the enclave fd, before an enclave + * is started. + * + * Context: Process context. + * Return: + * * 0 - Logic succesfully completed. + * * -1 - There was a failure in the ioctl logic. + * On failure, errno is set to: + * * EFAULT - copy_from_user() / copy_to_user() failure. + * * ENOMEM - Memory allocation failure for internal + * bookkeeping variables. + * * EIO - Current task mm is not the same as the one + * that created the enclave. + * * NE_ERR_NO_CPUS_AVAIL_IN_POOL - No CPUs available in the NE CPU pool. + * * NE_ERR_VCPU_ALREADY_USED - The provided vCPU is already used. + * * NE_ERR_VCPU_NOT_IN_CPU_POOL - The provided vCPU is not available in the + * NE CPU pool. + * * NE_ERR_VCPU_INVALID_CPU_CORE - The core id of the provided vCPU is invalid + * or out of range. + * * NE_ERR_NOT_IN_INIT_STATE - The enclave is not in init state + * (init = before being started). + * * NE_ERR_INVALID_VCPU - The provided vCPU is not in the available + * CPUs range. + * * Error codes from the NE PCI device request. + */ +#define NE_ADD_VCPU _IOWR(0xAE, 0x21, __u32) + +/** + * NE_GET_IMAGE_LOAD_INFO - The command is used to get information needed for + * in-memory enclave image loading e.g. offset in + * enclave memory to start placing the enclave image. + * The image load info is an input / output parameter. + * It includes info provided by the caller - flags - + * and returns the offset in enclave memory where to + * start placing the enclave image. + * The ioctl can be invoked on the enclave fd, before + * an enclave is started. + * + * Context: Process context. + * Return: + * * 0 - Logic succesfully completed. + * * -1 - There was a failure in the ioctl logic. + * On failure, errno is set to: + * * EFAULT - copy_from_user() / copy_to_user() failure. + * * NE_ERR_NOT_IN_INIT_STATE - The enclave is not in init state (init = + * before being started). + * * NE_ERR_INVALID_FLAG_VALUE - The value of the provided flag is invalid. + */ +#define NE_GET_IMAGE_LOAD_INFO _IOWR(0xAE, 0x22, struct ne_image_load_info) + +/** + * NE_SET_USER_MEMORY_REGION - The command is used to set a memory region for an + * enclave, given the allocated memory from the + * userspace. Enclave memory needs to be from the + * same NUMA node as the enclave CPUs. + * The user memory region is an input parameter. It + * includes info provided by the caller - flags, + * memory size and userspace address. + * The ioctl can be invoked on the enclave fd, + * before an enclave is started. + * + * Context: Process context. + * Return: + * * 0 - Logic succesfully completed. + * * -1 - There was a failure in the ioctl logic. + * On failure, errno is set to: + * * EFAULT - copy_from_user() failure. + * * EINVAL - Invalid physical memory region(s) e.g. + * unaligned address. + * * EIO - Current task mm is not the same as + * the one that created the enclave. + * * ENOMEM - Memory allocation failure for internal + * bookkeeping variables. + * * NE_ERR_NOT_IN_INIT_STATE - The enclave is not in init state + * (init = before being started). + * * NE_ERR_INVALID_MEM_REGION_SIZE - The memory size of the region is not + * multiple of 2 MiB. + * * NE_ERR_INVALID_MEM_REGION_ADDR - Invalid user space address given. + * * NE_ERR_UNALIGNED_MEM_REGION_ADDR - Unaligned user space address given. + * * NE_ERR_MEM_REGION_ALREADY_USED - The memory region is already used. + * * NE_ERR_MEM_NOT_HUGE_PAGE - The memory region is not backed by + * huge pages. + * * NE_ERR_MEM_DIFFERENT_NUMA_NODE - The memory region is not from the same + * NUMA node as the CPUs. + * * NE_ERR_MEM_MAX_REGIONS - The number of memory regions set for + * the enclave reached maximum. + * * NE_ERR_INVALID_PAGE_SIZE - The memory region is not backed by + * pages multiple of 2 MiB. + * * NE_ERR_INVALID_FLAG_VALUE - The value of the provided flag is invalid. + * * Error codes from get_user_pages(). + * * Error codes from the NE PCI device request. + */ +#define NE_SET_USER_MEMORY_REGION _IOW(0xAE, 0x23, struct ne_user_memory_region) + +/** + * NE_START_ENCLAVE - The command is used to trigger enclave start after the + * enclave resources, such as memory and CPU, have been set. + * The enclave start info is an input / output parameter. It + * includes info provided by the caller - enclave cid and + * flags - and returns the cid (if input cid is 0). + * The ioctl can be invoked on the enclave fd, after an + * enclave slot is created and resources, such as memory and + * vCPUs are set for an enclave. + * + * Context: Process context. + * Return: + * * 0 - Logic succesfully completed. + * * -1 - There was a failure in the ioctl logic. + * On failure, errno is set to: + * * EFAULT - copy_from_user() / copy_to_user() failure. + * * NE_ERR_NOT_IN_INIT_STATE - The enclave is not in init state + * (init = before being started). + * * NE_ERR_NO_MEM_REGIONS_ADDED - No memory regions are set. + * * NE_ERR_NO_VCPUS_ADDED - No vCPUs are set. + * * NE_ERR_FULL_CORES_NOT_USED - Full core(s) not set for the enclave. + * * NE_ERR_ENCLAVE_MEM_MIN_SIZE - Enclave memory is less than minimum + * memory size (64 MiB). + * * NE_ERR_INVALID_FLAG_VALUE - The value of the provided flag is invalid. + * * NE_ERR_INVALID_ENCLAVE_CID - The provided enclave CID is invalid. + * * Error codes from the NE PCI device request. + */ +#define NE_START_ENCLAVE _IOWR(0xAE, 0x24, struct ne_enclave_start_info) + +/** + * DOC: NE specific error codes + */ + +/** + * NE_ERR_VCPU_ALREADY_USED - The provided vCPU is already used. + */ +#define NE_ERR_VCPU_ALREADY_USED (256) +/** + * NE_ERR_VCPU_NOT_IN_CPU_POOL - The provided vCPU is not available in the + * NE CPU pool. + */ +#define NE_ERR_VCPU_NOT_IN_CPU_POOL (257) +/** + * NE_ERR_VCPU_INVALID_CPU_CORE - The core id of the provided vCPU is invalid + * or out of range of the NE CPU pool. + */ +#define NE_ERR_VCPU_INVALID_CPU_CORE (258) +/** + * NE_ERR_INVALID_MEM_REGION_SIZE - The user space memory region size is not + * multiple of 2 MiB. + */ +#define NE_ERR_INVALID_MEM_REGION_SIZE (259) +/** + * NE_ERR_INVALID_MEM_REGION_ADDR - The user space memory region address range + * is invalid. + */ +#define NE_ERR_INVALID_MEM_REGION_ADDR (260) +/** + * NE_ERR_UNALIGNED_MEM_REGION_ADDR - The user space memory region address is + * not aligned. + */ +#define NE_ERR_UNALIGNED_MEM_REGION_ADDR (261) +/** + * NE_ERR_MEM_REGION_ALREADY_USED - The user space memory region is already used. + */ +#define NE_ERR_MEM_REGION_ALREADY_USED (262) +/** + * NE_ERR_MEM_NOT_HUGE_PAGE - The user space memory region is not backed by + * contiguous physical huge page(s). + */ +#define NE_ERR_MEM_NOT_HUGE_PAGE (263) +/** + * NE_ERR_MEM_DIFFERENT_NUMA_NODE - The user space memory region is backed by + * pages from different NUMA nodes than the CPUs. + */ +#define NE_ERR_MEM_DIFFERENT_NUMA_NODE (264) +/** + * NE_ERR_MEM_MAX_REGIONS - The supported max memory regions per enclaves has + * been reached. + */ +#define NE_ERR_MEM_MAX_REGIONS (265) +/** + * NE_ERR_NO_MEM_REGIONS_ADDED - The command to start an enclave is triggered + * and no memory regions are added. + */ +#define NE_ERR_NO_MEM_REGIONS_ADDED (266) +/** + * NE_ERR_NO_VCPUS_ADDED - The command to start an enclave is triggered and no + * vCPUs are added. + */ +#define NE_ERR_NO_VCPUS_ADDED (267) +/** + * NE_ERR_ENCLAVE_MEM_MIN_SIZE - The enclave memory size is lower than the + * minimum supported. + */ +#define NE_ERR_ENCLAVE_MEM_MIN_SIZE (268) +/** + * NE_ERR_FULL_CORES_NOT_USED - The command to start an enclave is triggered and + * full CPU cores are not set. + */ +#define NE_ERR_FULL_CORES_NOT_USED (269) +/** + * NE_ERR_NOT_IN_INIT_STATE - The enclave is not in init state when setting + * resources or triggering start. + */ +#define NE_ERR_NOT_IN_INIT_STATE (270) +/** + * NE_ERR_INVALID_VCPU - The provided vCPU is out of range of the available CPUs. + */ +#define NE_ERR_INVALID_VCPU (271) +/** + * NE_ERR_NO_CPUS_AVAIL_IN_POOL - The command to create an enclave is triggered + * and no CPUs are available in the pool. + */ +#define NE_ERR_NO_CPUS_AVAIL_IN_POOL (272) +/** + * NE_ERR_INVALID_PAGE_SIZE - The user space memory region is not backed by pages + * multiple of 2 MiB. + */ +#define NE_ERR_INVALID_PAGE_SIZE (273) +/** + * NE_ERR_INVALID_FLAG_VALUE - The provided flag value is invalid. + */ +#define NE_ERR_INVALID_FLAG_VALUE (274) +/** + * NE_ERR_INVALID_ENCLAVE_CID - The provided enclave CID is invalid, either + * being a well-known value or the CID of the + * parent / primary VM. + */ +#define NE_ERR_INVALID_ENCLAVE_CID (275) + +/** + * DOC: Image load info flags + */ + +/** + * NE_EIF_IMAGE - Enclave Image Format (EIF) + */ +#define NE_EIF_IMAGE (0x01) + +#define NE_IMAGE_LOAD_MAX_FLAG_VAL (0x02) + +/** + * struct ne_image_load_info - Info necessary for in-memory enclave image + * loading (in / out). + * @flags: Flags to determine the enclave image type + * (e.g. Enclave Image Format - EIF) (in). + * @memory_offset: Offset in enclave memory where to start placing the + * enclave image (out). + */ +struct ne_image_load_info { + __u64 flags; + __u64 memory_offset; +}; + +/** + * DOC: User memory region flags + */ + +/** + * NE_DEFAULT_MEMORY_REGION - Memory region for enclave general usage. + */ +#define NE_DEFAULT_MEMORY_REGION (0x00) + +#define NE_MEMORY_REGION_MAX_FLAG_VAL (0x01) + +/** + * struct ne_user_memory_region - Memory region to be set for an enclave (in). + * @flags: Flags to determine the usage for the memory region (in). + * @memory_size: The size, in bytes, of the memory region to be set for + * an enclave (in). + * @userspace_addr: The start address of the userspace allocated memory of + * the memory region to set for an enclave (in). + */ +struct ne_user_memory_region { + __u64 flags; + __u64 memory_size; + __u64 userspace_addr; +}; + +/** + * DOC: Enclave start info flags + */ + +/** + * NE_ENCLAVE_PRODUCTION_MODE - Start enclave in production mode. + */ +#define NE_ENCLAVE_PRODUCTION_MODE (0x00) +/** + * NE_ENCLAVE_DEBUG_MODE - Start enclave in debug mode. + */ +#define NE_ENCLAVE_DEBUG_MODE (0x01) + +#define NE_ENCLAVE_START_MAX_FLAG_VAL (0x02) + +/** + * struct ne_enclave_start_info - Setup info necessary for enclave start (in / out). + * @flags: Flags for the enclave to start with (e.g. debug mode) (in). + * @enclave_cid: Context ID (CID) for the enclave vsock device. If 0 as + * input, the CID is autogenerated by the hypervisor and + * returned back as output by the driver (in / out). + */ +struct ne_enclave_start_info { + __u64 flags; + __u64 enclave_cid; +}; + +#endif /* _UAPI_LINUX_NITRO_ENCLAVES_H_ */ -- cgit v1.2.3 From a992b20cd4ee360dbbe6f69339cb07146e4304d6 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 16 Sep 2020 21:11:24 -0700 Subject: fscrypt: add fscrypt_prepare_new_inode() and fscrypt_set_context() fscrypt_get_encryption_info() is intended to be GFP_NOFS-safe. But actually it isn't, since it uses functions like crypto_alloc_skcipher() which aren't GFP_NOFS-safe, even when called under memalloc_nofs_save(). Therefore it can deadlock when called from a context that needs GFP_NOFS, e.g. during an ext4 transaction or between f2fs_lock_op() and f2fs_unlock_op(). This happens when creating a new encrypted file. We can't fix this by just not setting up the key for new inodes right away, since new symlinks need their key to encrypt the symlink target. So we need to set up the new inode's key before starting the transaction. But just calling fscrypt_get_encryption_info() earlier doesn't work, since it assumes the encryption context is already set, and the encryption context can't be set until the transaction. The recently proposed fscrypt support for the ceph filesystem (https://lkml.kernel.org/linux-fscrypt/20200821182813.52570-1-jlayton@kernel.org/T/#u) will have this same ordering problem too, since ceph will need to encrypt new symlinks before setting their encryption context. Finally, f2fs can deadlock when the filesystem is mounted with '-o test_dummy_encryption' and a new file is created in an existing unencrypted directory. Similarly, this is caused by holding too many locks when calling fscrypt_get_encryption_info(). To solve all these problems, add new helper functions: - fscrypt_prepare_new_inode() sets up a new inode's encryption key (fscrypt_info), using the parent directory's encryption policy and a new random nonce. It neither reads nor writes the encryption context. - fscrypt_set_context() persists the encryption context of a new inode, using the information from the fscrypt_info already in memory. This replaces fscrypt_inherit_context(). Temporarily keep fscrypt_inherit_context() around until all filesystems have been converted to use fscrypt_set_context(). Acked-by: Jeff Layton Link: https://lore.kernel.org/r/20200917041136.178600-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index eaf16eb55788..9cf7ca90f3ab 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -158,6 +158,7 @@ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); int fscrypt_inherit_context(struct inode *parent, struct inode *child, void *fs_data, bool preload); +int fscrypt_set_context(struct inode *inode, void *fs_data); struct fscrypt_dummy_context { const union fscrypt_context *ctx; @@ -184,6 +185,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ int fscrypt_get_encryption_info(struct inode *inode); +int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode, + bool *encrypt_ret); void fscrypt_put_encryption_info(struct inode *inode); void fscrypt_free_inode(struct inode *inode); int fscrypt_drop_inode(struct inode *inode); @@ -347,6 +350,11 @@ static inline int fscrypt_inherit_context(struct inode *parent, return -EOPNOTSUPP; } +static inline int fscrypt_set_context(struct inode *inode, void *fs_data) +{ + return -EOPNOTSUPP; +} + struct fscrypt_dummy_context { }; @@ -394,6 +402,15 @@ static inline int fscrypt_get_encryption_info(struct inode *inode) return -EOPNOTSUPP; } +static inline int fscrypt_prepare_new_inode(struct inode *dir, + struct inode *inode, + bool *encrypt_ret) +{ + if (IS_ENCRYPTED(dir)) + return -EOPNOTSUPP; + return 0; +} + static inline void fscrypt_put_encryption_info(struct inode *inode) { return; -- cgit v1.2.3 From e9d5e31d2fe39825b0fc276b14f2a322faf3c77b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 16 Sep 2020 21:11:30 -0700 Subject: fscrypt: remove fscrypt_inherit_context() Now that all filesystems have been converted to use fscrypt_prepare_new_inode() and fscrypt_set_context(), fscrypt_inherit_context() is no longer used. Remove it. Acked-by: Jeff Layton Link: https://lore.kernel.org/r/20200917041136.178600-8-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 9cf7ca90f3ab..81d6ded24328 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -156,8 +156,6 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); -int fscrypt_inherit_context(struct inode *parent, struct inode *child, - void *fs_data, bool preload); int fscrypt_set_context(struct inode *inode, void *fs_data); struct fscrypt_dummy_context { @@ -343,13 +341,6 @@ static inline int fscrypt_has_permitted_context(struct inode *parent, return 0; } -static inline int fscrypt_inherit_context(struct inode *parent, - struct inode *child, - void *fs_data, bool preload) -{ - return -EOPNOTSUPP; -} - static inline int fscrypt_set_context(struct inode *inode, void *fs_data) { return -EOPNOTSUPP; -- cgit v1.2.3 From c7f0207b613033c56b1217032d2f6326d0c69217 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 16 Sep 2020 21:11:33 -0700 Subject: fscrypt: make "#define fscrypt_policy" user-only The fscrypt UAPI header defines fscrypt_policy to fscrypt_policy_v1, for source compatibility with old userspace programs. Internally, the kernel doesn't want that compatibility definition. Instead, fscrypt_private.h #undefs it and re-defines it to a union. That works for now. However, in order to add fscrypt_operations::get_dummy_policy(), we'll need to forward declare 'union fscrypt_policy' in include/linux/fscrypt.h. That would cause build errors because "fscrypt_policy" is used in ioctl numbers. To avoid this, modify the UAPI header to make the fscrypt_policy compatibility definition conditional on !__KERNEL__, and make the ioctls use fscrypt_policy_v1 instead of fscrypt_policy. Note that this doesn't change the actual ioctl numbers. Acked-by: Jeff Layton Link: https://lore.kernel.org/r/20200917041136.178600-11-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/uapi/linux/fscrypt.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 7875709ccfeb..e5de60336938 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -45,7 +45,6 @@ struct fscrypt_policy_v1 { __u8 flags; __u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; }; -#define fscrypt_policy fscrypt_policy_v1 /* * Process-subscribed "logon" key description prefix and payload format. @@ -156,9 +155,9 @@ struct fscrypt_get_key_status_arg { __u32 __out_reserved[13]; }; -#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy) +#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1) #define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) -#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy) +#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1) #define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */ #define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg) #define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg) @@ -170,6 +169,7 @@ struct fscrypt_get_key_status_arg { /* old names; don't add anything new here! */ #ifndef __KERNEL__ +#define fscrypt_policy fscrypt_policy_v1 #define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE #define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4 #define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8 -- cgit v1.2.3 From 31114726b69364f3bf8dd945c600ceed4c430f4f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 16 Sep 2020 21:11:34 -0700 Subject: fscrypt: move fscrypt_prepare_symlink() out-of-line In preparation for moving the logic for "get the encryption policy inherited by new files in this directory" to a single place, make fscrypt_prepare_symlink() a regular function rather than an inline function that wraps __fscrypt_prepare_symlink(). This way, the new function fscrypt_policy_to_inherit() won't need to be exported to filesystems. Acked-by: Jeff Layton Link: https://lore.kernel.org/r/20200917041136.178600-12-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 63 ++++++++++++------------------------------------- 1 file changed, 15 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 81d6ded24328..39e7397a3f10 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -225,9 +225,9 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname); int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags); -int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, - unsigned int max_len, - struct fscrypt_str *disk_link); +int fscrypt_prepare_symlink(struct inode *dir, const char *target, + unsigned int len, unsigned int max_len, + struct fscrypt_str *disk_link); int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, struct fscrypt_str *disk_link); const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, @@ -520,15 +520,21 @@ static inline int fscrypt_prepare_setflags(struct inode *inode, return 0; } -static inline int __fscrypt_prepare_symlink(struct inode *dir, - unsigned int len, - unsigned int max_len, - struct fscrypt_str *disk_link) +static inline int fscrypt_prepare_symlink(struct inode *dir, + const char *target, + unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link) { - return -EOPNOTSUPP; + if (IS_ENCRYPTED(dir)) + return -EOPNOTSUPP; + disk_link->name = (unsigned char *)target; + disk_link->len = len + 1; + if (disk_link->len > max_len) + return -ENAMETOOLONG; + return 0; } - static inline int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, @@ -793,45 +799,6 @@ static inline int fscrypt_prepare_setattr(struct dentry *dentry, return 0; } -/** - * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink - * @dir: directory in which the symlink is being created - * @target: plaintext symlink target - * @len: length of @target excluding null terminator - * @max_len: space the filesystem has available to store the symlink target - * @disk_link: (out) the on-disk symlink target being prepared - * - * This function computes the size the symlink target will require on-disk, - * stores it in @disk_link->len, and validates it against @max_len. An - * encrypted symlink may be longer than the original. - * - * Additionally, @disk_link->name is set to @target if the symlink will be - * unencrypted, but left NULL if the symlink will be encrypted. For encrypted - * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the - * on-disk target later. (The reason for the two-step process is that some - * filesystems need to know the size of the symlink target before creating the - * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.) - * - * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long, - * -ENOKEY if the encryption key is missing, or another -errno code if a problem - * occurred while setting up the encryption key. - */ -static inline int fscrypt_prepare_symlink(struct inode *dir, - const char *target, - unsigned int len, - unsigned int max_len, - struct fscrypt_str *disk_link) -{ - if (IS_ENCRYPTED(dir) || fscrypt_get_dummy_context(dir->i_sb) != NULL) - return __fscrypt_prepare_symlink(dir, len, max_len, disk_link); - - disk_link->name = (unsigned char *)target; - disk_link->len = len + 1; - if (disk_link->len > max_len) - return -ENAMETOOLONG; - return 0; -} - /** * fscrypt_encrypt_symlink() - encrypt the symlink target if needed * @inode: symlink inode -- cgit v1.2.3 From ac4acb1f4b2b6b7e8d913537cccec8789903e164 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 16 Sep 2020 21:11:35 -0700 Subject: fscrypt: handle test_dummy_encryption in more logical way The behavior of the test_dummy_encryption mount option is that when a new file (or directory or symlink) is created in an unencrypted directory, it's automatically encrypted using a dummy encryption policy. That's it; in particular, the encryption (or lack thereof) of existing files (or directories or symlinks) doesn't change. Unfortunately the implementation of test_dummy_encryption is a bit weird and confusing. When test_dummy_encryption is enabled and a file is being created in an unencrypted directory, we set up an encryption key (->i_crypt_info) for the directory. This isn't actually used to do any encryption, however, since the directory is still unencrypted! Instead, ->i_crypt_info is only used for inheriting the encryption policy. One consequence of this is that the filesystem ends up providing a "dummy context" (policy + nonce) instead of a "dummy policy". In commit ed318a6cc0b6 ("fscrypt: support test_dummy_encryption=v2"), I mistakenly thought this was required. However, actually the nonce only ends up being used to derive a key that is never used. Another consequence of this implementation is that it allows for 'inode->i_crypt_info != NULL && !IS_ENCRYPTED(inode)', which is an edge case that can be forgotten about. For example, currently FS_IOC_GET_ENCRYPTION_POLICY on an unencrypted directory may return the dummy encryption policy when the filesystem is mounted with test_dummy_encryption. That seems like the wrong thing to do, since again, the directory itself is not actually encrypted. Therefore, switch to a more logical and maintainable implementation where the dummy encryption policy inheritance is done without setting up keys for unencrypted directories. This involves: - Adding a function fscrypt_policy_to_inherit() which returns the encryption policy to inherit from a directory. This can be a real policy, a dummy policy, or no policy. - Replacing struct fscrypt_dummy_context, ->get_dummy_context(), etc. with struct fscrypt_dummy_policy, ->get_dummy_policy(), etc. - Making fscrypt_fname_encrypted_size() take an fscrypt_policy instead of an inode. Acked-by: Jaegeuk Kim Acked-by: Jeff Layton Link: https://lore.kernel.org/r/20200917041136.178600-13-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 40 +++++++++++++--------------------------- 1 file changed, 13 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 39e7397a3f10..b3b0c5675c6b 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -21,7 +21,7 @@ #define FS_CRYPTO_BLOCK_SIZE 16 -union fscrypt_context; +union fscrypt_policy; struct fscrypt_info; struct seq_file; @@ -62,8 +62,7 @@ struct fscrypt_operations { int (*get_context)(struct inode *inode, void *ctx, size_t len); int (*set_context)(struct inode *inode, const void *ctx, size_t len, void *fs_data); - const union fscrypt_context *(*get_dummy_context)( - struct super_block *sb); + const union fscrypt_policy *(*get_dummy_policy)(struct super_block *sb); bool (*empty_dir)(struct inode *inode); unsigned int max_namelen; bool (*has_stable_inodes)(struct super_block *sb); @@ -101,14 +100,6 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); } -static inline const union fscrypt_context * -fscrypt_get_dummy_context(struct super_block *sb) -{ - if (!sb->s_cop->get_dummy_context) - return NULL; - return sb->s_cop->get_dummy_context(sb); -} - /* * When d_splice_alias() moves a directory's encrypted alias to its decrypted * alias as a result of the encryption key being added, DCACHE_ENCRYPTED_NAME @@ -158,20 +149,21 @@ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); int fscrypt_set_context(struct inode *inode, void *fs_data); -struct fscrypt_dummy_context { - const union fscrypt_context *ctx; +struct fscrypt_dummy_policy { + const union fscrypt_policy *policy; }; -int fscrypt_set_test_dummy_encryption(struct super_block *sb, - const substring_t *arg, - struct fscrypt_dummy_context *dummy_ctx); +int fscrypt_set_test_dummy_encryption( + struct super_block *sb, + const substring_t *arg, + struct fscrypt_dummy_policy *dummy_policy); void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb); static inline void -fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { - kfree(dummy_ctx->ctx); - dummy_ctx->ctx = NULL; + kfree(dummy_policy->policy); + dummy_policy->policy = NULL; } /* keyring.c */ @@ -250,12 +242,6 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) return false; } -static inline const union fscrypt_context * -fscrypt_get_dummy_context(struct super_block *sb) -{ - return NULL; -} - static inline void fscrypt_handle_d_move(struct dentry *dentry) { } @@ -346,7 +332,7 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data) return -EOPNOTSUPP; } -struct fscrypt_dummy_context { +struct fscrypt_dummy_policy { }; static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, @@ -356,7 +342,7 @@ static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, } static inline void -fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { } -- cgit v1.2.3 From c8c868abc91ff23f6f5c4444c419de7c277d77e1 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 16 Sep 2020 21:11:36 -0700 Subject: fscrypt: make fscrypt_set_test_dummy_encryption() take a 'const char *' fscrypt_set_test_dummy_encryption() requires that the optional argument to the test_dummy_encryption mount option be specified as a substring_t. That doesn't work well with filesystems that use the new mount API, since the new way of parsing mount options doesn't use substring_t. Make it take the argument as a 'const char *' instead. Instead of moving the match_strdup() into the callers in ext4 and f2fs, make them just use arg->from directly. Since the pattern is "test_dummy_encryption=%s", the argument will be null-terminated. Acked-by: Jeff Layton Link: https://lore.kernel.org/r/20200917041136.178600-14-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index b3b0c5675c6b..fc67c4cbaa96 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -15,7 +15,6 @@ #include #include -#include #include #include @@ -153,9 +152,7 @@ struct fscrypt_dummy_policy { const union fscrypt_policy *policy; }; -int fscrypt_set_test_dummy_encryption( - struct super_block *sb, - const substring_t *arg, +int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg, struct fscrypt_dummy_policy *dummy_policy); void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb); -- cgit v1.2.3 From 0a068adde505a90ece23caaf19b77567e1d18298 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Tue, 21 Jul 2020 10:49:51 +0300 Subject: habanalabs: add information about PCIe controller Update firmware header with new API for getting pcie info such as tx/rx throughput and replay counter. These counters are needed by customers for monitor and maintenance of multiple devices. Add new opcodes to the INFO ioctl to retrieve these counters. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index d5c4f983b7a8..ee13b919db35 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -264,6 +264,8 @@ enum hl_device_status { * HL_INFO_TIME_SYNC - Retrieve the device's time alongside the host's time * for synchronization. * HL_INFO_CS_COUNTERS - Retrieve command submission counters + * HL_INFO_PCI_COUNTERS - Retrieve PCI counters + * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -276,6 +278,8 @@ enum hl_device_status { #define HL_INFO_RESET_COUNT 9 #define HL_INFO_TIME_SYNC 10 #define HL_INFO_CS_COUNTERS 11 +#define HL_INFO_PCI_COUNTERS 12 +#define HL_INFO_CLK_THROTTLE_REASON 13 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -340,6 +344,29 @@ struct hl_info_time_sync { __u64 host_time; }; +/** + * struct hl_info_pci_counters - pci counters + * @rx_throughput: PCI rx throughput KBps + * @tx_throughput: PCI tx throughput KBps + * @replay_cnt: PCI replay counter + */ +struct hl_info_pci_counters { + __u64 rx_throughput; + __u64 tx_throughput; + __u64 replay_cnt; +}; + +#define HL_CLK_THROTTLE_POWER 0x1 +#define HL_CLK_THROTTLE_THERMAL 0x2 + +/** + * struct hl_info_clk_throttle - clock throttling reason + * @clk_throttling_reason: each bit represents a clk throttling reason + */ +struct hl_info_clk_throttle { + __u32 clk_throttling_reason; +}; + /** * struct hl_info_cs_counters - command submission counters * @out_of_mem_drop_cnt: dropped due to memory allocation issue -- cgit v1.2.3 From 843839bec3a304f8313d6ae554f618a91e52731a Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Sun, 19 Jul 2020 11:08:09 +0300 Subject: habanalabs: expose sync manager resources allocation in INFO IOCTL Although the driver defines the first user-available sync manager object and monitor in habanalabs.h, we would like to also expose this information via the INFO IOCTL so the runtime can get this information dynamically. This is because in future ASICs we won't need to define it statically. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ee13b919db35..ca6dc1fc250e 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -266,6 +266,7 @@ enum hl_device_status { * HL_INFO_CS_COUNTERS - Retrieve command submission counters * HL_INFO_PCI_COUNTERS - Retrieve PCI counters * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason + * HL_INFO_SYNC_MANAGER - Retrieve sync manager info per dcore */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -280,6 +281,7 @@ enum hl_device_status { #define HL_INFO_CS_COUNTERS 11 #define HL_INFO_PCI_COUNTERS 12 #define HL_INFO_CLK_THROTTLE_REASON 13 +#define HL_INFO_SYNC_MANAGER 14 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -367,6 +369,16 @@ struct hl_info_clk_throttle { __u32 clk_throttling_reason; }; +/** + * struct hl_info_sync_manager - sync manager information + * @first_available_sync_object: first available sob + * @first_available_monitor: first available monitor + */ +struct hl_info_sync_manager { + __u32 first_available_sync_object; + __u32 first_available_monitor; +}; + /** * struct hl_info_cs_counters - command submission counters * @out_of_mem_drop_cnt: dropped due to memory allocation issue @@ -386,6 +398,13 @@ struct hl_info_cs_counters { struct hl_cs_counters ctx_cs_counters; }; +enum gaudi_dcores { + HL_GAUDI_WS_DCORE, + HL_GAUDI_WN_DCORE, + HL_GAUDI_EN_DCORE, + HL_GAUDI_ES_DCORE +}; + struct hl_info_args { /* Location of relevant struct in userspace */ __u64 return_pointer; @@ -402,6 +421,10 @@ struct hl_info_args { __u32 op; union { + /* Dcore id for which the information is relevant. + * For Gaudi refer to 'enum gaudi_dcores' + */ + __u32 dcore_id; /* Context ID - Currently not in use */ __u32 ctx_id; /* Period value for utilization rate (100ms - 1000ms, in 100ms -- cgit v1.2.3 From d90416c84d86ff78a2181f135d72d564430107b8 Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Wed, 12 Aug 2020 17:20:13 +0300 Subject: habanalabs: extend busy engines mask to 64 bits change busy engines bitmask to 64 bits in order to represent more engines, needed for future ASIC support. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ca6dc1fc250e..693081728ef3 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -319,6 +319,12 @@ struct hl_info_hw_idle { * Bits definition is according to `enum _enging_id'. */ __u32 busy_engines_mask; + + /* + * Extended Bitmask of busy engines. + * Bits definition is according to `enum _enging_id'. + */ + __u64 busy_engines_mask_ext; }; struct hl_info_device_status { -- cgit v1.2.3 From 9f3064913e1b9b4153accbd33aaf1983be92c569 Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Sun, 9 Aug 2020 16:25:53 +0300 Subject: habanalabs: add support for getting device total energy Add driver implementation for reading the total energy consumption from the device ARM FW. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 693081728ef3..6803991726e8 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -267,6 +267,7 @@ enum hl_device_status { * HL_INFO_PCI_COUNTERS - Retrieve PCI counters * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason * HL_INFO_SYNC_MANAGER - Retrieve sync manager info per dcore + * HL_INFO_TOTAL_ENERGY - Retrieve total energy consumption */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -282,6 +283,7 @@ enum hl_device_status { #define HL_INFO_PCI_COUNTERS 12 #define HL_INFO_CLK_THROTTLE_REASON 13 #define HL_INFO_SYNC_MANAGER 14 +#define HL_INFO_TOTAL_ENERGY 15 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -375,6 +377,14 @@ struct hl_info_clk_throttle { __u32 clk_throttling_reason; }; +/** + * struct hl_info_energy - device energy information + * @total_energy_consumption: total device energy consumption + */ +struct hl_info_energy { + __u64 total_energy_consumption; +}; + /** * struct hl_info_sync_manager - sync manager information * @first_available_sync_object: first available sob -- cgit v1.2.3 From 2f55342c5e4d3ea94c0b8237f3ad26963269f90f Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sat, 15 Aug 2020 16:28:10 +0300 Subject: habanalabs: replace armcp with the generic cpucp ArmCP mandates that the device CPU is always an ARM processor, which might be wrong in the future. Most of this change is an internal renaming of variables, functions and defines but there are two entries in sysfs which have armcp in their names. Add identical cpucp entries but don't remove yet the armcp entries. Those will be deprecated next year. Add the documentation about it in sysfs documentation. Signed-off-by: Moti Haimovski Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 6803991726e8..a2dcad29340f 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -297,7 +297,7 @@ struct hl_info_hw_ip_info { __u32 device_id; /* PCI Device ID */ __u32 module_id; /* For mezzanine cards in servers (From OCP spec.) */ __u32 reserved[2]; - __u32 armcp_cpld_version; + __u32 cpld_version; __u32 psoc_pci_pll_nr; __u32 psoc_pci_pll_nf; __u32 psoc_pci_pll_od; @@ -305,7 +305,7 @@ struct hl_info_hw_ip_info { __u8 tpc_enabled_mask; __u8 dram_enabled; __u8 pad[2]; - __u8 armcp_version[HL_INFO_VERSION_MAX_LEN]; + __u8 cpucp_version[HL_INFO_VERSION_MAX_LEN]; __u8 card_name[HL_INFO_CARD_NAME_MAX_LEN]; }; -- cgit v1.2.3 From 975ab7b32b90c97046ddbdd53798391b7d8a6a1e Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Tue, 1 Sep 2020 11:22:05 +0300 Subject: habanalabs: count dropped CS because max CS in-flight There is a case where the user reaches the maximum number of CS in-flight. In that case, the driver rejects the new CS of the user with EAGAIN. Count that event so the user can query the driver later to see if it happened. Reviewed-by: Tomer Tayar Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index a2dcad29340f..69fb44d35292 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -401,12 +401,14 @@ struct hl_info_sync_manager { * @parsing_drop_cnt: dropped due to error in packet parsing * @queue_full_drop_cnt: dropped due to queue full * @device_in_reset_drop_cnt: dropped due to device in reset + * @max_cs_in_flight_drop_cnt: dropped due to maximum CS in-flight */ struct hl_cs_counters { __u64 out_of_mem_drop_cnt; __u64 parsing_drop_cnt; __u64 queue_full_drop_cnt; __u64 device_in_reset_drop_cnt; + __u64 max_cs_in_flight_drop_cnt; }; struct hl_info_cs_counters { -- cgit v1.2.3 From 681a22f55f1506023da06ebf660a4a252b35bc93 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Mon, 7 Sep 2020 18:08:51 +0300 Subject: habanalabs: allow to wait on CS without sleep The user sometimes wants to check if a CS has completed to clean resources. In that case, the user doesn't want to sleep but just to check if the CS has finished and continue with his code. Add a new definition to the API of the wait on CS. The new definition says that if the timeout is 0, the driver won't sleep at all but return immediately after checking if the CS has finished. Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 69fb44d35292..d449f8a31ce6 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -914,6 +914,9 @@ struct hl_debug_args { * inside the kernel until the CS has finished or until the user-requested * timeout has expired. * + * If the timeout value is 0, the driver won't sleep at all. It will check + * the status of the CS and return immediately + * * The return value of the IOCTL is a standard Linux error code. The possible * values are: * -- cgit v1.2.3 From ef6a0f6caa4a5dbfbb42b642e23fb06182798d30 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Thu, 9 Jul 2020 16:17:48 +0300 Subject: habanalabs: Add an option to map CB to device MMU There are cases in which the device should access the host memory of a CB through the device MMU, and thus this memory should be mapped. The patch adds a flag to the CB IOCTL, in which a user can ask the driver to perform the mapping when creating a CB. The mapping is allowed only if a dedicated VA range was allocated for the specific ASIC. Signed-off-by: Tomer Tayar Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index d449f8a31ce6..9705b8adb60c 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -462,6 +462,9 @@ struct hl_info_args { /* 2MB minus 32 bytes for 2xMSG_PROT */ #define HL_MAX_CB_SIZE (0x200000 - 32) +/* Indicates whether the command buffer should be mapped to the device's MMU */ +#define HL_CB_FLAGS_MAP 0x1 + struct hl_cb_in { /* Handle of CB or 0 if we want to create one */ __u64 cb_handle; @@ -473,7 +476,8 @@ struct hl_cb_in { __u32 cb_size; /* Context ID - Currently not in use */ __u32 ctx_id; - __u32 pad; + /* HL_CB_FLAGS_* */ + __u32 flags; }; struct hl_cb_out { @@ -856,6 +860,12 @@ struct hl_debug_args { * When creating a new CB, the IOCTL returns a handle of it, and the user-space * process needs to use that handle to mmap the buffer so it can access them. * + * In some instances, the device must access the command buffer through the + * device's MMU, and thus its memory should be mapped. In these cases, user can + * indicate the driver that such a mapping is required. + * The resulting device virtual address will be used internally by the driver, + * and won't be returned to user. + * */ #define HL_IOCTL_CB \ _IOWR('H', 0x02, union hl_cb_args) -- cgit v1.2.3 From 10942019040c5557556ec22aae0f771b2a1a1a6d Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 1 Sep 2020 16:28:58 +0200 Subject: firmware: psci: Extend psci_set_osi_mode() to allow reset to PC mode The current user (cpuidle-psci) of psci_set_osi_mode() only needs to enable the PSCI OSI mode. Although, as subsequent changes shows, there is a need to be able to reset back into the PSCI PC mode. Therefore, let's extend psci_set_osi_mode() to take a bool as in-parameter, to let the user indicate whether to enable OSI or to switch back to PC mode. Reviewed-by: Sudeep Holla Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/psci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/psci.h b/include/linux/psci.h index 14ad9b9ebcd6..2a1bfb890e58 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -18,7 +18,7 @@ bool psci_tos_resident_on(int cpu); int psci_cpu_suspend_enter(u32 state); bool psci_power_state_is_valid(u32 state); -int psci_set_osi_mode(void); +int psci_set_osi_mode(bool enable); bool psci_has_osi_support(void); struct psci_operations { -- cgit v1.2.3 From 900ffe39fec908e0aa26a30612e43ebc7140db79 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 19 Sep 2020 01:09:36 -0700 Subject: x86/entry: Fix typo in comments for syscall_enter_from_user_mode() Just to help myself and others with finding the correct function names, fix a typo for "usermode" vs "user_mode". Signed-off-by: Kees Cook Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200919080936.259819-1-keescook@chromium.org --- include/linux/entry-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index efebbffcd5cc..3b6754d5a604 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -38,7 +38,7 @@ #endif /* - * TIF flags handled in syscall_enter_from_usermode() + * TIF flags handled in syscall_enter_from_user_mode() */ #ifndef ARCH_SYSCALL_ENTER_WORK # define ARCH_SYSCALL_ENTER_WORK (0) -- cgit v1.2.3 From 6045124ebe722434bb52e89881c5fa41911c24f0 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Mon, 7 Sep 2020 11:26:00 +0300 Subject: clk: ti: dra7: add missing clkctrl register for SHA2 instance DRA7 SoC has two SHA instances. Add the clkctrl entry for the second one. Signed-off-by: Tero Kristo Link: https://lore.kernel.org/r/20200907082600.454-4-t-kristo@ti.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/dra7.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/dra7.h b/include/dt-bindings/clock/dra7.h index 8cec5a1e1806..5ec4137231e3 100644 --- a/include/dt-bindings/clock/dra7.h +++ b/include/dt-bindings/clock/dra7.h @@ -332,6 +332,7 @@ #define DRA7_L4SEC_DES_CLKCTRL DRA7_L4SEC_CLKCTRL_INDEX(0x1b0) #define DRA7_L4SEC_RNG_CLKCTRL DRA7_L4SEC_CLKCTRL_INDEX(0x1c0) #define DRA7_L4SEC_SHAM_CLKCTRL DRA7_L4SEC_CLKCTRL_INDEX(0x1c8) +#define DRA7_L4SEC_SHAM2_CLKCTRL DRA7_L4SEC_CLKCTRL_INDEX(0x1f8) /* l4per2 clocks */ #define DRA7_L4PER2_CLKCTRL_OFFSET 0xc -- cgit v1.2.3 From 1fe44191f361a88b0f9600a5bbc8ebf7ede642ce Mon Sep 17 00:00:00 2001 From: Li Yang Date: Tue, 22 Sep 2020 17:38:21 -0500 Subject: soc: fsl: qman: fix -Wpacked-not-aligned warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes compile warnings from the -Wpacked-not-aligned option. In file included from ../drivers/crypto/caam/qi.c:12: ../include/soc/fsl/qman.h:259:1: warning: alignment 1 of ‘struct qm_dqrr_entry’ is less than 8 [-Wpacked-not-aligned] } __packed; ^ ../include/soc/fsl/qman.h:292:2: warning: alignment 1 of ‘struct ’ is less than 8 [-Wpacked-not-aligned] } __packed ern; ^ Reported-by: Herbert Xu Signed-off-by: Li Yang --- include/soc/fsl/qman.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h index cfe00e08e85b..9f484113cfda 100644 --- a/include/soc/fsl/qman.h +++ b/include/soc/fsl/qman.h @@ -256,7 +256,7 @@ struct qm_dqrr_entry { __be32 context_b; struct qm_fd fd; u8 __reserved4[32]; -} __packed; +} __packed __aligned(64); #define QM_DQRR_VERB_VBIT 0x80 #define QM_DQRR_VERB_MASK 0x7f /* where the verb contains; */ #define QM_DQRR_VERB_FRAME_DEQUEUE 0x60 /* "this format" */ @@ -289,7 +289,7 @@ union qm_mr_entry { __be32 tag; struct qm_fd fd; u8 __reserved1[32]; - } __packed ern; + } __packed __aligned(64) ern; struct { u8 verb; u8 fqs; /* Frame Queue Status */ -- cgit v1.2.3 From 13ef5539def732dc7b9c58c320d97a0a95b52634 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 22 Sep 2020 12:11:04 +0300 Subject: RDMA/restrack: Count references to the verbs objects Refactor the restrack code to make sure the kref inside the restrack entry properly kref's the object in which it is embedded. This slight change is needed for future conversions of MR and QP which are refcounted before the release and kfree. The ideal flow from ib_core perspective as follows: * Allocate ib_* structure with rdma_zalloc_*. * Set everything that is known to ib_core to that newly created object. * Initialize kref with restrack help * Call to driver specific allocation functions. * Insert into restrack DB .... * Return and release restrack with restrack_put. Largely this means a rdma_restrack_new() should be called near allocating the containing structure. Link: https://lore.kernel.org/r/20200922091106.2152715-4-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/restrack.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h index 7682d1bcf789..d7c166237939 100644 --- a/include/rdma/restrack.h +++ b/include/rdma/restrack.h @@ -110,13 +110,6 @@ int rdma_restrack_count(struct ib_device *dev, void rdma_restrack_kadd(struct rdma_restrack_entry *res); void rdma_restrack_uadd(struct rdma_restrack_entry *res); -/** - * rdma_restrack_del() - delete object from the reource tracking database - * @res: resource entry - * @type: actual type of object to operate - */ -void rdma_restrack_del(struct rdma_restrack_entry *res); - /** * rdma_is_kernel_res() - check the owner of resource * @res: resource entry -- cgit v1.2.3 From c34a23c28c6b0045b1f21649de30f68da72547af Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 22 Sep 2020 12:11:05 +0300 Subject: RDMA/restrack: Simplify restrack tracking in kernel flows Have a single rdma_restrack_add() that adds an entry, there is no reason to split the user/kernel here, the rdma_restrack_set_task() is responsible for this difference. This patch prepares the code to the future requirement of making restrack is mandatory for managing ib objects. Link: https://lore.kernel.org/r/20200922091106.2152715-5-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/restrack.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h index d7c166237939..db59e208f5e8 100644 --- a/include/rdma/restrack.h +++ b/include/rdma/restrack.h @@ -107,7 +107,6 @@ struct rdma_restrack_entry { int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type); -void rdma_restrack_kadd(struct rdma_restrack_entry *res); void rdma_restrack_uadd(struct rdma_restrack_entry *res); /** -- cgit v1.2.3 From b09c4d70122091c1865cb63a9c4dad1a94a8e339 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 22 Sep 2020 12:11:06 +0300 Subject: RDMA/restrack: Improve readability in task name management Use rdma_restrack_set_name() and rdma_restrack_parent_name() instead of tricky uses of rdma_restrack_attach_task()/rdma_restrack_uadd(). This uniformly makes all restracks add'd using rdma_restrack_add(). Link: https://lore.kernel.org/r/20200922091106.2152715-6-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/rdma_cm.h | 47 ++++++++++++++--------------------------------- include/rdma/restrack.h | 13 +------------ 2 files changed, 15 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index c1334c9a7aa8..c672ae1da26b 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -110,11 +110,14 @@ struct rdma_cm_id { u8 port_num; }; -struct rdma_cm_id *__rdma_create_id(struct net *net, - rdma_cm_event_handler event_handler, - void *context, enum rdma_ucm_port_space ps, - enum ib_qp_type qp_type, - const char *caller); +struct rdma_cm_id * +__rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler, + void *context, enum rdma_ucm_port_space ps, + enum ib_qp_type qp_type, const char *caller); +struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler, + void *context, + enum rdma_ucm_port_space ps, + enum ib_qp_type qp_type); /** * rdma_create_id - Create an RDMA identifier. @@ -132,9 +135,9 @@ struct rdma_cm_id *__rdma_create_id(struct net *net, * The event handler callback serializes on the id's mutex and is * allowed to sleep. */ -#define rdma_create_id(net, event_handler, context, ps, qp_type) \ - __rdma_create_id((net), (event_handler), (context), (ps), (qp_type), \ - KBUILD_MODNAME) +#define rdma_create_id(net, event_handler, context, ps, qp_type) \ + __rdma_create_kernel_id(net, event_handler, context, ps, qp_type, \ + KBUILD_MODNAME) /** * rdma_destroy_id - Destroys an RDMA identifier. @@ -250,34 +253,12 @@ int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, */ int rdma_listen(struct rdma_cm_id *id, int backlog); -int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, - const char *caller); +int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param); void rdma_lock_handler(struct rdma_cm_id *id); void rdma_unlock_handler(struct rdma_cm_id *id); -int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, - const char *caller, struct rdma_ucm_ece *ece); - -/** - * rdma_accept - Called to accept a connection request or response. - * @id: Connection identifier associated with the request. - * @conn_param: Information needed to establish the connection. This must be - * provided if accepting a connection request. If accepting a connection - * response, this parameter must be NULL. - * - * Typically, this routine is only called by the listener to accept a connection - * request. It must also be called on the active side of a connection if the - * user is performing their own QP transitions. - * - * In the case of error, a reject message is sent to the remote side and the - * state of the qp associated with the id is modified to error, such that any - * previously posted receive buffers would be flushed. - * - * This function is for use by kernel ULPs and must be called from under the - * handler callback. - */ -#define rdma_accept(id, conn_param) \ - __rdma_accept((id), (conn_param), KBUILD_MODNAME) +int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, + struct rdma_ucm_ece *ece); /** * rdma_notify - Notifies the RDMA CM of an asynchronous event that has diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h index db59e208f5e8..d3a1cc5be7bc 100644 --- a/include/rdma/restrack.h +++ b/include/rdma/restrack.h @@ -106,14 +106,11 @@ struct rdma_restrack_entry { int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type); - -void rdma_restrack_uadd(struct rdma_restrack_entry *res); - /** * rdma_is_kernel_res() - check the owner of resource * @res: resource entry */ -static inline bool rdma_is_kernel_res(struct rdma_restrack_entry *res) +static inline bool rdma_is_kernel_res(const struct rdma_restrack_entry *res) { return !res->user; } @@ -130,14 +127,6 @@ int __must_check rdma_restrack_get(struct rdma_restrack_entry *res); */ int rdma_restrack_put(struct rdma_restrack_entry *res); -/** - * rdma_restrack_set_task() - set the task for this resource - * @res: resource entry - * @caller: kernel name, the current task will be used if the caller is NULL. - */ -void rdma_restrack_set_task(struct rdma_restrack_entry *res, - const char *caller); - /* * Helper functions for rdma drivers when filling out * nldev driver attributes. -- cgit v1.2.3 From 028abd9222df0cf5855dab5014a5ebaf06f90565 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Sep 2020 10:22:34 +0200 Subject: fs: remove compat_sys_mount compat_sys_mount is identical to the regular sys_mount now, so remove it and use the native version everywhere. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 6 ------ include/uapi/asm-generic/unistd.h | 2 +- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index d38c4d7e83bd..100632280ccc 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -522,12 +522,6 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, compat_ulong_t arg); -/* fs/namespace.c */ -asmlinkage long compat_sys_mount(const char __user *dev_name, - const char __user *dir_name, - const char __user *type, compat_ulong_t flags, - const void __user *data); - /* fs/open.c */ asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 995b36c2ea7d..fc98c9437609 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -140,7 +140,7 @@ __SYSCALL(__NR_renameat, sys_renameat) #define __NR_umount2 39 __SYSCALL(__NR_umount2, sys_umount) #define __NR_mount 40 -__SC_COMP(__NR_mount, sys_mount, compat_sys_mount) +__SYSCALL(__NR_mount, sys_mount) #define __NR_pivot_root 41 __SYSCALL(__NR_pivot_root, sys_pivot_root) -- cgit v1.2.3 From b753e41d9999c040c601de53cc1e072160472d80 Mon Sep 17 00:00:00 2001 From: Drew Fustini Date: Tue, 22 Sep 2020 00:50:55 +0200 Subject: ARM: dts: am33xx: modify AM33XX_IOPAD for #pinctrl-cells = 2 Modify the AM33XX_IOPAD macro so that it works now that #pinctrl-cells = <2>. The third parameter is just a zero and the pinctrl-single driver will just OR this with the second parameter so it has no actual effect. There are no longer any dts files using this macro (following my patch to am335x-guardian.dts), but this will keep dts files not in mainline from breaking. Fixes: 27c90e5e48d0 ("ARM: dts: am33xx-l4: change #pinctrl-cells from 1 to 2") Suggested-by: Tony Lindgren Reported-by: Trent Piepho Link: https://lore.kernel.org/linux-devicetree/20200921064707.GN7101@atomide.com/ Signed-off-by: Drew Fustini Signed-off-by: Tony Lindgren --- include/dt-bindings/pinctrl/omap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/pinctrl/omap.h b/include/dt-bindings/pinctrl/omap.h index 2d2a8c737822..f48245ff87e5 100644 --- a/include/dt-bindings/pinctrl/omap.h +++ b/include/dt-bindings/pinctrl/omap.h @@ -64,7 +64,7 @@ #define OMAP3_WKUP_IOPAD(pa, val) OMAP_IOPAD_OFFSET((pa), 0x2a00) (val) #define DM814X_IOPAD(pa, val) OMAP_IOPAD_OFFSET((pa), 0x0800) (val) #define DM816X_IOPAD(pa, val) OMAP_IOPAD_OFFSET((pa), 0x0800) (val) -#define AM33XX_IOPAD(pa, val) OMAP_IOPAD_OFFSET((pa), 0x0800) (val) +#define AM33XX_IOPAD(pa, val) OMAP_IOPAD_OFFSET((pa), 0x0800) (val) (0) #define AM33XX_PADCONF(pa, conf, mux) OMAP_IOPAD_OFFSET((pa), 0x0800) (conf) (mux) /* -- cgit v1.2.3 From dd87a72ae968f70852cd7a2d939acd9693e76095 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 21 Sep 2020 03:32:05 +0800 Subject: soundwire: enable Data Port test modes Test modes are required for all SoundWire IP, and help debug integration issues. In theory each port can be configured with a different mode but to simplify this patch only offers separate configurations for the Master and Slave ports - this covers 99% of the intended cases during platform integration. The test mode value is set via platform-specific ways. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200920193207.31241-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index de9ea2ce2d35..41cc1192f9aa 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -554,6 +554,10 @@ enum sdw_port_prep_ops { * @bandwidth: Current bandwidth * @col: Active columns * @row: Active rows + * @s_data_mode: NORMAL, STATIC or PRBS mode for all Slave ports + * @m_data_mode: NORMAL, STATIC or PRBS mode for all Master ports. The value + * should be the same to detect transmission issues, but can be different to + * test the interrupt reports */ struct sdw_bus_params { enum sdw_reg_bank curr_bank; @@ -563,6 +567,8 @@ struct sdw_bus_params { unsigned int bandwidth; unsigned int col; unsigned int row; + int s_data_mode; + int m_data_mode; }; /** -- cgit v1.2.3 From f49735f4978f479b0de4f50ab217d5a56bc83c55 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Tue, 22 Sep 2020 12:34:16 -0600 Subject: cpuidle: record state entry rejection statistics CPUs may fail to enter the chosen idle state if there was a pending interrupt, causing the cpuidle driver to return an error value. Record that and export it via sysfs along with the other idle state statistics. This could prove useful in understanding behavior of the governor and the system during usecases that involve multiple CPUs. Signed-off-by: Lina Iyer [ rjw: Changelog and documentation edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 6175c77bf25e..ed0da0e58e8b 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -38,6 +38,7 @@ struct cpuidle_state_usage { u64 time_ns; unsigned long long above; /* Number of times it's been too deep */ unsigned long long below; /* Number of times it's been too shallow */ + unsigned long long rejected; /* Number of times idle entry was rejected */ #ifdef CONFIG_SUSPEND unsigned long long s2idle_usage; unsigned long long s2idle_time; /* in US */ -- cgit v1.2.3 From a297104aceeb312600b0efaf8a281ad0f17167d2 Mon Sep 17 00:00:00 2001 From: Sai Krishna Potthuri Date: Wed, 22 Jul 2020 12:46:04 +0530 Subject: dt-bindings: reset: Updated binding for Versal reset driver Added documentation and Versal reset indices to describe about Versal reset driver bindings. In Versal all reset indices includes Class, SubClass, Type, Index information whereas class refers to clock, reset, power etc., Underlying firmware in Versal have such classification and expects the ID to be this way. [13:0] - Index bits [19:14] - Type bits [25:20] - SubClass bits [31:26] - Class bits. Signed-off-by: Sai Krishna Potthuri Reviewed-by: Rob Herring Signed-off-by: Philipp Zabel --- include/dt-bindings/reset/xlnx-versal-resets.h | 105 +++++++++++++++++++++++++ 1 file changed, 105 insertions(+) create mode 100644 include/dt-bindings/reset/xlnx-versal-resets.h (limited to 'include') diff --git a/include/dt-bindings/reset/xlnx-versal-resets.h b/include/dt-bindings/reset/xlnx-versal-resets.h new file mode 100644 index 000000000000..895424e9b0e5 --- /dev/null +++ b/include/dt-bindings/reset/xlnx-versal-resets.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 Xilinx, Inc. + */ + +#ifndef _DT_BINDINGS_VERSAL_RESETS_H +#define _DT_BINDINGS_VERSAL_RESETS_H + +#define VERSAL_RST_PMC_POR (0xc30c001U) +#define VERSAL_RST_PMC (0xc410002U) +#define VERSAL_RST_PS_POR (0xc30c003U) +#define VERSAL_RST_PL_POR (0xc30c004U) +#define VERSAL_RST_NOC_POR (0xc30c005U) +#define VERSAL_RST_FPD_POR (0xc30c006U) +#define VERSAL_RST_ACPU_0_POR (0xc30c007U) +#define VERSAL_RST_ACPU_1_POR (0xc30c008U) +#define VERSAL_RST_OCM2_POR (0xc30c009U) +#define VERSAL_RST_PS_SRST (0xc41000aU) +#define VERSAL_RST_PL_SRST (0xc41000bU) +#define VERSAL_RST_NOC (0xc41000cU) +#define VERSAL_RST_NPI (0xc41000dU) +#define VERSAL_RST_SYS_RST_1 (0xc41000eU) +#define VERSAL_RST_SYS_RST_2 (0xc41000fU) +#define VERSAL_RST_SYS_RST_3 (0xc410010U) +#define VERSAL_RST_FPD (0xc410011U) +#define VERSAL_RST_PL0 (0xc410012U) +#define VERSAL_RST_PL1 (0xc410013U) +#define VERSAL_RST_PL2 (0xc410014U) +#define VERSAL_RST_PL3 (0xc410015U) +#define VERSAL_RST_APU (0xc410016U) +#define VERSAL_RST_ACPU_0 (0xc410017U) +#define VERSAL_RST_ACPU_1 (0xc410018U) +#define VERSAL_RST_ACPU_L2 (0xc410019U) +#define VERSAL_RST_ACPU_GIC (0xc41001aU) +#define VERSAL_RST_RPU_ISLAND (0xc41001bU) +#define VERSAL_RST_RPU_AMBA (0xc41001cU) +#define VERSAL_RST_R5_0 (0xc41001dU) +#define VERSAL_RST_R5_1 (0xc41001eU) +#define VERSAL_RST_SYSMON_PMC_SEQ_RST (0xc41001fU) +#define VERSAL_RST_SYSMON_PMC_CFG_RST (0xc410020U) +#define VERSAL_RST_SYSMON_FPD_CFG_RST (0xc410021U) +#define VERSAL_RST_SYSMON_FPD_SEQ_RST (0xc410022U) +#define VERSAL_RST_SYSMON_LPD (0xc410023U) +#define VERSAL_RST_PDMA_RST1 (0xc410024U) +#define VERSAL_RST_PDMA_RST0 (0xc410025U) +#define VERSAL_RST_ADMA (0xc410026U) +#define VERSAL_RST_TIMESTAMP (0xc410027U) +#define VERSAL_RST_OCM (0xc410028U) +#define VERSAL_RST_OCM2_RST (0xc410029U) +#define VERSAL_RST_IPI (0xc41002aU) +#define VERSAL_RST_SBI (0xc41002bU) +#define VERSAL_RST_LPD (0xc41002cU) +#define VERSAL_RST_QSPI (0xc10402dU) +#define VERSAL_RST_OSPI (0xc10402eU) +#define VERSAL_RST_SDIO_0 (0xc10402fU) +#define VERSAL_RST_SDIO_1 (0xc104030U) +#define VERSAL_RST_I2C_PMC (0xc104031U) +#define VERSAL_RST_GPIO_PMC (0xc104032U) +#define VERSAL_RST_GEM_0 (0xc104033U) +#define VERSAL_RST_GEM_1 (0xc104034U) +#define VERSAL_RST_SPARE (0xc104035U) +#define VERSAL_RST_USB_0 (0xc104036U) +#define VERSAL_RST_UART_0 (0xc104037U) +#define VERSAL_RST_UART_1 (0xc104038U) +#define VERSAL_RST_SPI_0 (0xc104039U) +#define VERSAL_RST_SPI_1 (0xc10403aU) +#define VERSAL_RST_CAN_FD_0 (0xc10403bU) +#define VERSAL_RST_CAN_FD_1 (0xc10403cU) +#define VERSAL_RST_I2C_0 (0xc10403dU) +#define VERSAL_RST_I2C_1 (0xc10403eU) +#define VERSAL_RST_GPIO_LPD (0xc10403fU) +#define VERSAL_RST_TTC_0 (0xc104040U) +#define VERSAL_RST_TTC_1 (0xc104041U) +#define VERSAL_RST_TTC_2 (0xc104042U) +#define VERSAL_RST_TTC_3 (0xc104043U) +#define VERSAL_RST_SWDT_FPD (0xc104044U) +#define VERSAL_RST_SWDT_LPD (0xc104045U) +#define VERSAL_RST_USB (0xc104046U) +#define VERSAL_RST_DPC (0xc208047U) +#define VERSAL_RST_PMCDBG (0xc208048U) +#define VERSAL_RST_DBG_TRACE (0xc208049U) +#define VERSAL_RST_DBG_FPD (0xc20804aU) +#define VERSAL_RST_DBG_TSTMP (0xc20804bU) +#define VERSAL_RST_RPU0_DBG (0xc20804cU) +#define VERSAL_RST_RPU1_DBG (0xc20804dU) +#define VERSAL_RST_HSDP (0xc20804eU) +#define VERSAL_RST_DBG_LPD (0xc20804fU) +#define VERSAL_RST_CPM_POR (0xc30c050U) +#define VERSAL_RST_CPM (0xc410051U) +#define VERSAL_RST_CPMDBG (0xc208052U) +#define VERSAL_RST_PCIE_CFG (0xc410053U) +#define VERSAL_RST_PCIE_CORE0 (0xc410054U) +#define VERSAL_RST_PCIE_CORE1 (0xc410055U) +#define VERSAL_RST_PCIE_DMA (0xc410056U) +#define VERSAL_RST_CMN (0xc410057U) +#define VERSAL_RST_L2_0 (0xc410058U) +#define VERSAL_RST_L2_1 (0xc410059U) +#define VERSAL_RST_ADDR_REMAP (0xc41005aU) +#define VERSAL_RST_CPI0 (0xc41005bU) +#define VERSAL_RST_CPI1 (0xc41005cU) +#define VERSAL_RST_XRAM (0xc30c05dU) +#define VERSAL_RST_AIE_ARRAY (0xc10405eU) +#define VERSAL_RST_AIE_SHIM (0xc10405fU) + +#endif -- cgit v1.2.3 From cbc111d1552ee1364a16cfd1162dd9e8f969101e Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 30 Jul 2020 14:46:08 +0800 Subject: dt-bindings: reset: imx8mq: add m4 reset Add the m4 reset used by the remoteproc driver Signed-off-by: Peng Fan Acked-by: Rob Herring Signed-off-by: Philipp Zabel --- include/dt-bindings/reset/imx8mq-reset.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/reset/imx8mq-reset.h b/include/dt-bindings/reset/imx8mq-reset.h index a5b570737582..705870693ec2 100644 --- a/include/dt-bindings/reset/imx8mq-reset.h +++ b/include/dt-bindings/reset/imx8mq-reset.h @@ -58,7 +58,10 @@ #define IMX8MQ_RESET_DDRC2_PRST 47 /* i.MX8MM/i.MX8MN does NOT support */ #define IMX8MQ_RESET_DDRC2_CORE_RESET 48 /* i.MX8MM/i.MX8MN does NOT support */ #define IMX8MQ_RESET_DDRC2_PHY_RESET 49 /* i.MX8MM/i.MX8MN does NOT support */ +#define IMX8MQ_RESET_SW_M4C_RST 50 +#define IMX8MQ_RESET_SW_M4P_RST 51 +#define IMX8MQ_RESET_M4_ENABLE 52 -#define IMX8MQ_RESET_NUM 50 +#define IMX8MQ_RESET_NUM 53 #endif -- cgit v1.2.3 From 07d098e6bbad04030dab5b3e64149601fcb063ce Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 21 Sep 2020 22:32:49 -0400 Subject: block: allow 'chunk_sectors' to be non-power-of-2 It is possible, albeit more unlikely, for a block device to have a non power-of-2 for chunk_sectors (e.g. 10+2 RAID6 with 128K chunk_sectors, which results in a full-stripe size of 1280K. This causes the RAID6's io_opt to be advertised as 1280K, and a stacked device _could_ then be made to use a blocksize, aka chunk_sectors, that matches non power-of-2 io_opt of underlying RAID6 -- resulting in stacked device's chunk_sectors being a non power-of-2). Update blk_queue_chunk_sectors() and blk_max_size_offset() to accommodate drivers that need a non power-of-2 chunk_sectors. Reviewed-by: Ming Lei Reviewed-by: Martin K. Petersen Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5bd96fbab9b4..6e19a7aa1672 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1063,11 +1063,17 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset) { - if (!q->limits.chunk_sectors) + unsigned int chunk_sectors = q->limits.chunk_sectors; + + if (!chunk_sectors) return q->limits.max_sectors; - return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors - - (offset & (q->limits.chunk_sectors - 1)))); + if (likely(is_power_of_2(chunk_sectors))) + chunk_sectors -= offset & (chunk_sectors - 1); + else + chunk_sectors -= sector_div(offset, chunk_sectors); + + return min(q->limits.max_sectors, chunk_sectors); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, -- cgit v1.2.3 From 1967f712677429f52ac3e8896b5ecfecc2372d95 Mon Sep 17 00:00:00 2001 From: Zbigniew Lukwinski Date: Fri, 31 Jul 2020 21:37:16 +0200 Subject: hwmon: (core) Add support for rated attributes Adding implementation for new attributes (rated_min/rated_max) for currentX, inX, powerX, tempX and humidityX. Tested with OpenBMC stack and simple hwmon driver using rated_min/rated_max for the following types of sensors: hwmon_temp, hwmon_in, hwmon_curr, hwmon_power, hwmon_humidity. For each sensor rated attributes were available and returned expected values. Signed-off-by: Zbigniew Lukwinski Link: https://lore.kernel.org/r/1596224237-32280-3-git-send-email-zbigniew.lukwinski@linux.intel.com Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 363d4a814aa1..1e8d6ea8992e 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -85,6 +85,8 @@ enum hwmon_temp_attributes { hwmon_temp_lowest, hwmon_temp_highest, hwmon_temp_reset_history, + hwmon_temp_rated_min, + hwmon_temp_rated_max, }; #define HWMON_T_ENABLE BIT(hwmon_temp_enable) @@ -112,6 +114,8 @@ enum hwmon_temp_attributes { #define HWMON_T_LOWEST BIT(hwmon_temp_lowest) #define HWMON_T_HIGHEST BIT(hwmon_temp_highest) #define HWMON_T_RESET_HISTORY BIT(hwmon_temp_reset_history) +#define HWMON_T_RATED_MIN BIT(hwmon_temp_rated_min) +#define HWMON_T_RATED_MAX BIT(hwmon_temp_rated_max) enum hwmon_in_attributes { hwmon_in_enable, @@ -130,6 +134,8 @@ enum hwmon_in_attributes { hwmon_in_max_alarm, hwmon_in_lcrit_alarm, hwmon_in_crit_alarm, + hwmon_in_rated_min, + hwmon_in_rated_max, }; #define HWMON_I_ENABLE BIT(hwmon_in_enable) @@ -148,6 +154,8 @@ enum hwmon_in_attributes { #define HWMON_I_MAX_ALARM BIT(hwmon_in_max_alarm) #define HWMON_I_LCRIT_ALARM BIT(hwmon_in_lcrit_alarm) #define HWMON_I_CRIT_ALARM BIT(hwmon_in_crit_alarm) +#define HWMON_I_RATED_MIN BIT(hwmon_in_rated_min) +#define HWMON_I_RATED_MAX BIT(hwmon_in_rated_max) enum hwmon_curr_attributes { hwmon_curr_enable, @@ -166,6 +174,8 @@ enum hwmon_curr_attributes { hwmon_curr_max_alarm, hwmon_curr_lcrit_alarm, hwmon_curr_crit_alarm, + hwmon_curr_rated_min, + hwmon_curr_rated_max, }; #define HWMON_C_ENABLE BIT(hwmon_curr_enable) @@ -184,6 +194,8 @@ enum hwmon_curr_attributes { #define HWMON_C_MAX_ALARM BIT(hwmon_curr_max_alarm) #define HWMON_C_LCRIT_ALARM BIT(hwmon_curr_lcrit_alarm) #define HWMON_C_CRIT_ALARM BIT(hwmon_curr_crit_alarm) +#define HWMON_C_RATED_MIN BIT(hwmon_curr_rated_min) +#define HWMON_C_RATED_MAX BIT(hwmon_curr_rated_max) enum hwmon_power_attributes { hwmon_power_enable, @@ -215,6 +227,8 @@ enum hwmon_power_attributes { hwmon_power_max_alarm, hwmon_power_lcrit_alarm, hwmon_power_crit_alarm, + hwmon_power_rated_min, + hwmon_power_rated_max, }; #define HWMON_P_ENABLE BIT(hwmon_power_enable) @@ -246,6 +260,8 @@ enum hwmon_power_attributes { #define HWMON_P_MAX_ALARM BIT(hwmon_power_max_alarm) #define HWMON_P_LCRIT_ALARM BIT(hwmon_power_lcrit_alarm) #define HWMON_P_CRIT_ALARM BIT(hwmon_power_crit_alarm) +#define HWMON_P_RATED_MIN BIT(hwmon_power_rated_min) +#define HWMON_P_RATED_MAX BIT(hwmon_power_rated_max) enum hwmon_energy_attributes { hwmon_energy_enable, @@ -267,6 +283,8 @@ enum hwmon_humidity_attributes { hwmon_humidity_max_hyst, hwmon_humidity_alarm, hwmon_humidity_fault, + hwmon_humidity_rated_min, + hwmon_humidity_rated_max, }; #define HWMON_H_ENABLE BIT(hwmon_humidity_enable) @@ -278,6 +296,8 @@ enum hwmon_humidity_attributes { #define HWMON_H_MAX_HYST BIT(hwmon_humidity_max_hyst) #define HWMON_H_ALARM BIT(hwmon_humidity_alarm) #define HWMON_H_FAULT BIT(hwmon_humidity_fault) +#define HWMON_H_RATED_MIN BIT(hwmon_humidity_rated_min) +#define HWMON_H_RATED_MAX BIT(hwmon_humidity_rated_max) enum hwmon_fan_attributes { hwmon_fan_enable, -- cgit v1.2.3 From 7497d4a66c596fc8312cafe1b8d1e76ad2bc34c3 Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Thu, 27 Aug 2020 13:04:54 -0700 Subject: hwmon: (gsc-hwmon) add fan sensor Add a fan sensor to report RPM's from a fan tach input. Signed-off-by: Tim Harvey Signed-off-by: Guenter Roeck --- include/linux/platform_data/gsc_hwmon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h index 37a8f554da00..281f499eda97 100644 --- a/include/linux/platform_data/gsc_hwmon.h +++ b/include/linux/platform_data/gsc_hwmon.h @@ -7,6 +7,7 @@ enum gsc_hwmon_mode { mode_voltage_24bit, mode_voltage_raw, mode_voltage_16bit, + mode_fan, mode_max, }; -- cgit v1.2.3 From 38430f0876fa8b9549ec434f569dce03e057c076 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:45 +0200 Subject: block: move the NEED_PART_SCAN flag to struct gendisk We can only scan for partitions on the whole disk, so move the flag from struct block_device to struct gendisk. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 +--- include/linux/genhd.h | 2 ++ 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6ffa783e1633..eb20e28184ab 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -19,8 +19,6 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; -#define BDEV_NEED_PART_SCAN 0 - struct block_device { dev_t bd_dev; int bd_openers; @@ -39,7 +37,7 @@ struct block_device { struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; - unsigned long bd_flags; + spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 1c97cf84f011..38f23d757013 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -191,6 +191,8 @@ struct gendisk { void *private_data; int flags; + unsigned long state; +#define GD_NEED_PART_SCAN 0 struct rw_semaphore lookup_sem; struct kobject *slave_dir; -- cgit v1.2.3 From bb3247a399801ebba20bef101c89e563f5fe7f02 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:55 +0200 Subject: PM: rewrite is_hibernate_resume_dev to not require an inode Just check the dev_t to help simplifying the code. Signed-off-by: Christoph Hellwig Acked-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Jens Axboe --- include/linux/suspend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index cb9afad82a90..8af13ba60c7e 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -473,9 +473,9 @@ static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) { #endif /* CONFIG_HIBERNATION */ #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV -int is_hibernate_resume_dev(const struct inode *); +int is_hibernate_resume_dev(dev_t dev); #else -static inline int is_hibernate_resume_dev(const struct inode *i) { return 0; } +static inline int is_hibernate_resume_dev(dev_t dev) { return 0; } #endif /* Hibernation and suspend events */ -- cgit v1.2.3 From 21bd900572f3708e281ea25f051fc92462eb1193 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:56 +0200 Subject: mm: split swap_type_of swap_type_of is used for two entirely different purposes: (1) check what swap type a given device/offset corresponds to (2) find the first available swap device that can be written to Mixing both in a single function creates an unreadable mess. Create two separate functions instead, and switch both to pass a dev_t instead of a struct block_device to further simplify the code. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/swap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 661046994db4..4340a7b6e7a1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -467,7 +467,8 @@ extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern int free_swap_and_cache(swp_entry_t); -extern int swap_type_of(dev_t, sector_t, struct block_device **); +int swap_type_of(dev_t device, sector_t offset); +int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); -- cgit v1.2.3 From 1fb1a2ad75e33e646d33e42b9ed17d879d472859 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:58 +0200 Subject: block: mark blkdev_get static There are no users outside the core block code left now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6e19a7aa1672..be5ef6f4ba19 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1981,7 +1981,6 @@ void blkdev_show(struct seq_file *seqf, off_t offset); #define BLKDEV_MAJOR_MAX 0 #endif -int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -- cgit v1.2.3 From f93808308aab34071259fa8cffbda273bc346ea7 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 23 Sep 2020 11:05:11 +0300 Subject: ASoC: Intel: add codec name prefix to ACPI machine description The current SOF machine driver adds a name prefix for each codec, mainly to differentiate ALSA controls for left and right amplifiers. This is a good idea, but the machine driver duplicates some of the information that already exists in ACPI descriptors, so add those prefixes there. Follow-up patches will make use of the information encoded in these tables and remove duplication. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Guennadi Liakhovetski Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20200923080514.3242858-4-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index b77b05c413a3..b16a844d16ef 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -93,11 +93,13 @@ struct snd_soc_acpi_endpoint { * @adr: 64 bit ACPI _ADR value * @num_endpoints: number of endpoints for this device * @endpoints: array of endpoints + * @name_prefix: string used for codec controls */ struct snd_soc_acpi_adr_device { const u64 adr; const u8 num_endpoints; const struct snd_soc_acpi_endpoint *endpoints; + const char *name_prefix; }; /** -- cgit v1.2.3 From e1ac11859a057ddcf7d6219bd090c7483541767d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 22 Sep 2020 10:30:15 +0300 Subject: net: bridge: add src field to br_ip Add a new src field to struct br_ip which will be used to lookup S, G entries. When SSM option is added we will enable full br_ip lookups. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 6479a38e52fa..4fb9c4954f3a 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -18,6 +18,12 @@ struct br_ip { __be32 ip4; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ip6; +#endif + } src; + union { + __be32 ip4; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr ip6; #endif } u; __be16 proto; -- cgit v1.2.3 From eab3227b1240bdcc06c0a01a3fc5bfd2bc12f406 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 22 Sep 2020 10:30:17 +0300 Subject: net: bridge: mcast: rename br_ip's u member to dst Since now we have src in br_ip, u no longer makes sense so rename it to dst. No functional changes. v2: fix build with CONFIG_BATMAN_ADV_MCAST CC: Marek Lindner CC: Simon Wunderlich CC: Antonio Quartulli CC: Sven Eckelmann CC: b.a.t.m.a.n@lists.open-mesh.org Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 4fb9c4954f3a..556caed00258 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -25,7 +25,7 @@ struct br_ip { #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ip6; #endif - } u; + } dst; __be16 proto; __u16 vid; }; -- cgit v1.2.3 From 9c4258c78a2a7624c79b797f40ae2dbfd2555e26 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 22 Sep 2020 10:30:18 +0300 Subject: net: bridge: mdb: add support to extend add/del commands Since the MDB add/del code expects an exact struct br_mdb_entry we can't really add any extensions, thus add a new nested attribute at the level of MDBA_SET_ENTRY called MDBA_SET_ENTRY_ATTRS which will be used to pass all new options via netlink attributes. This patch doesn't change anything functionally since the new attribute is not used yet, only parsed. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 75a2ac479247..dc52f8cffa0d 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -530,10 +530,22 @@ struct br_mdb_entry { enum { MDBA_SET_ENTRY_UNSPEC, MDBA_SET_ENTRY, + MDBA_SET_ENTRY_ATTRS, __MDBA_SET_ENTRY_MAX, }; #define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1) +/* [MDBA_SET_ENTRY_ATTRS] = { + * [MDBE_ATTR_xxx] + * ... + * } + */ +enum { + MDBE_ATTR_UNSPEC, + __MDBE_ATTR_MAX, +}; +#define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) + /* Embedded inside LINK_XSTATS_TYPE_BRIDGE */ enum { BRIDGE_XSTATS_UNSPEC, -- cgit v1.2.3 From 88d4bd180419a7cde3947f191dc4e26fbb19f80b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 22 Sep 2020 10:30:19 +0300 Subject: net: bridge: mdb: add support for add/del/dump of entries with source Add new mdb attributes (MDBE_ATTR_SOURCE for setting, MDBA_MDB_EATTR_SOURCE for dumping) to allow add/del and dump of mdb entries with a source address (S,G). New S,G entries are created with filter mode of MCAST_INCLUDE. The same attributes are used for IPv4 and IPv6, they're validated and parsed based on their protocol. S,G host joined entries which are added by user are not allowed yet. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index dc52f8cffa0d..3e6377c865eb 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -457,6 +457,7 @@ enum { MDBA_MDB_EATTR_TIMER, MDBA_MDB_EATTR_SRC_LIST, MDBA_MDB_EATTR_GROUP_MODE, + MDBA_MDB_EATTR_SOURCE, __MDBA_MDB_EATTR_MAX }; #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1) @@ -542,6 +543,7 @@ enum { */ enum { MDBE_ATTR_UNSPEC, + MDBE_ATTR_SOURCE, __MDBE_ATTR_MAX, }; #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) -- cgit v1.2.3 From 8f8cb77e0b22d9044d8d57ab3bb18ea8d0474752 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 22 Sep 2020 10:30:21 +0300 Subject: net: bridge: mcast: add rt_protocol field to the port group struct We need to be able to differentiate between pg entries created by user-space and the kernel when we start generating S,G entries for IGMPv3/MLDv2's fast path. User-space entries are created by default as RTPROT_STATIC and the kernel entries are RTPROT_KERNEL. Later we can allow user-space to provide the entry rt_protocol so we can differentiate between who added the entries specifically (e.g. clag, admin, frr etc). Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 3e6377c865eb..1054f151078d 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -458,6 +458,7 @@ enum { MDBA_MDB_EATTR_SRC_LIST, MDBA_MDB_EATTR_GROUP_MODE, MDBA_MDB_EATTR_SOURCE, + MDBA_MDB_EATTR_RTPROT, __MDBA_MDB_EATTR_MAX }; #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1) -- cgit v1.2.3 From 8266a0491e92d39dc9af739e8380a0daa9b8836b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 22 Sep 2020 10:30:24 +0300 Subject: net: bridge: mcast: handle port group filter modes We need to handle group filter mode transitions and initial state. To change a port group's INCLUDE -> EXCLUDE mode (or when we have added a new port group in EXCLUDE mode) we need to add that port to all of *,G ports' S,G entries for proper replication. When the EXCLUDE state is changed from IGMPv3 report, br_multicast_fwd_filter_exclude() must be called after the source list processing because the assumption is that all of the group's S,G entries will be created before transitioning to EXCLUDE mode, i.e. most importantly its blocked entries will already be added so it will not get automatically added to them. The transition EXCLUDE -> INCLUDE happens only when a port group timer expires, it requires us to remove that port from all of *,G ports' S,G entries where it was automatically added previously. Finally when we are adding a new S,G entry we must add all of *,G's EXCLUDE ports to it. In order to distinguish automatically added *,G EXCLUDE ports we have a new port group flag - MDB_PG_FLAGS_STAR_EXCL. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 1054f151078d..e4bd30a25f6b 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -518,6 +518,7 @@ struct br_mdb_entry { __u8 state; #define MDB_FLAGS_OFFLOAD (1 << 0) #define MDB_FLAGS_FAST_LEAVE (1 << 1) +#define MDB_FLAGS_STAR_EXCL (1 << 2) __u8 flags; __u16 vid; struct { -- cgit v1.2.3 From 9116ffbf1dd71f953ffda4198d01f82d3ca16df8 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 22 Sep 2020 10:30:25 +0300 Subject: net: bridge: mcast: add support for blocked port groups When excluding S,G entries we need a way to block a particular S,G,port. The new port group flag is managed based on the source's timer as per RFCs 3376 and 3810. When a source expires and its port group is in EXCLUDE mode, it will be blocked. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index e4bd30a25f6b..4c687686aa8f 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -519,6 +519,7 @@ struct br_mdb_entry { #define MDB_FLAGS_OFFLOAD (1 << 0) #define MDB_FLAGS_FAST_LEAVE (1 << 1) #define MDB_FLAGS_STAR_EXCL (1 << 2) +#define MDB_FLAGS_BLOCKED (1 << 3) __u8 flags; __u16 vid; struct { -- cgit v1.2.3 From 39097ab66dbe89b16438dd6d178d49e75cb922ed Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 23 Sep 2020 00:29:02 +0200 Subject: net: phy: Fixup kernel doc Add missing parameter documentation, or fixup wrong parameter names. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mdio.h | 3 ++- include/linux/phy.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 3a88b699b758..dbd69b3d170b 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -306,7 +306,7 @@ static inline u32 linkmode_adv_to_mii_10gbt_adv_t(unsigned long *advertising) /** * mii_10gbt_stat_mod_linkmode_lpa_t * @advertising: target the linkmode advertisement settings - * @adv: value of the C45 10GBASE-T AN STATUS register + * @lpa: value of the C45 10GBASE-T AN STATUS register * * A small helper function that translates C45 10GBASE-T AN STATUS register bits * to linkmode advertisement settings. Other bits in advertising aren't changed. @@ -371,6 +371,7 @@ struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr); /** * mdio_module_driver() - Helper macro for registering mdio drivers + * @_mdio_driver: driver to register * * Helper macro for MDIO drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it diff --git a/include/linux/phy.h b/include/linux/phy.h index 3a09d2bf69ea..4901b2637059 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1566,8 +1566,9 @@ static inline int mdiobus_register_board_info(const struct mdio_board_info *i, /** - * module_phy_driver() - Helper macro for registering PHY drivers + * phy_module_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register + * @__count: Numbers of members in array * * Helper macro for PHY drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it -- cgit v1.2.3 From 4069a572d423b73919ae40a500dfc4b10f8a6f32 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 23 Sep 2020 00:29:03 +0200 Subject: net: phy: Document core PHY structures Add kerneldoc for the core PHY data structures, a few inline functions and exported functions which are not already documented. v2 Typos g/phy/PHY/s Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 423 ++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 292 insertions(+), 131 deletions(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4901b2637059..eb3cb1a98b45 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -82,7 +82,39 @@ extern const int phy_10gbit_features_array[1]; #define PHY_POLL_CABLE_TEST 0x00000004 #define MDIO_DEVICE_IS_PHY 0x80000000 -/* Interface Mode definitions */ +/** + * enum phy_interface_t - Interface Mode definitions + * + * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch + * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined + * @PHY_INTERFACE_MODE_MII: Median-independent interface + * @PHY_INTERFACE_MODE_GMII: Gigabit median-independent interface + * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface + * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface + * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface + * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface + * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface + * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay + * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay + * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay + * @PHY_INTERFACE_MODE_RTBI: Reduced TBI + * @PHY_INTERFACE_MODE_SMII: ??? MII + * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface + * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface + * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax + * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII + * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII + * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX + * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX + * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI + * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface + * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR + * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII + * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN + * @PHY_INTERFACE_MODE_MAX: Book keeping + * + * Describes the interface between the MAC and PHY. + */ typedef enum { PHY_INTERFACE_MODE_NA, PHY_INTERFACE_MODE_INTERNAL, @@ -116,8 +148,8 @@ typedef enum { } phy_interface_t; /** - * phy_supported_speeds - return all speeds currently supported by a phy device - * @phy: The phy device to return supported speeds of. + * phy_supported_speeds - return all speeds currently supported by a PHY device + * @phy: The PHY device to return supported speeds of. * @speeds: buffer to store supported speeds in. * @size: size of speeds buffer. * @@ -134,9 +166,9 @@ unsigned int phy_supported_speeds(struct phy_device *phy, * phy_modes - map phy_interface_t enum to device tree binding of phy-mode * @interface: enum phy_interface_t value * - * Description: maps 'enum phy_interface_t' defined in this file + * Description: maps enum &phy_interface_t defined in this file * into the device tree binding of 'phy-mode', so that Ethernet - * device driver can get phy interface from device tree. + * device driver can get PHY interface from device tree. */ static inline const char *phy_modes(phy_interface_t interface) { @@ -215,6 +247,14 @@ struct sfp_bus; struct sfp_upstream_ops; struct sk_buff; +/** + * struct mdio_bus_stats - Statistics counters for MDIO busses + * @transfers: Total number of transfers, i.e. @writes + @reads + * @errors: Number of MDIO transfers that returned an error + * @writes: Number of write transfers + * @reads: Number of read transfers + * @syncp: Synchronisation for incrementing statistics + */ struct mdio_bus_stats { u64_stats_t transfers; u64_stats_t errors; @@ -224,7 +264,15 @@ struct mdio_bus_stats { struct u64_stats_sync syncp; }; -/* Represents a shared structure between different phydev's in the same +/** + * struct phy_package_shared - Shared information in PHY packages + * @addr: Common PHY address used to combine PHYs in one package + * @refcnt: Number of PHYs connected to this shared data + * @flags: Initialization of PHY package + * @priv_size: Size of the shared private data @priv + * @priv: Driver private data shared across a PHY package + * + * Represents a shared structure between different phydev's in the same * package, for example a quad PHY. See phy_package_join() and * phy_package_leave(). */ @@ -247,7 +295,14 @@ struct phy_package_shared { #define PHY_SHARED_F_INIT_DONE 0 #define PHY_SHARED_F_PROBE_DONE 1 -/* +/** + * struct mii_bus - Represents an MDIO bus + * + * @owner: Who owns this device + * @name: User friendly name for this MDIO device, or driver name + * @id: Unique identifier for this bus, typical from bus hierarchy + * @priv: Driver private data + * * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure */ @@ -256,49 +311,58 @@ struct mii_bus { const char *name; char id[MII_BUS_ID_SIZE]; void *priv; + /** @read: Perform a read transfer on the bus */ int (*read)(struct mii_bus *bus, int addr, int regnum); + /** @write: Perform a write transfer on the bus */ int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); + /** @reset: Perform a reset of the bus */ int (*reset)(struct mii_bus *bus); + + /** @stats: Statistic counters per device on the bus */ struct mdio_bus_stats stats[PHY_MAX_ADDR]; - /* - * A lock to ensure that only one thing can read/write + /** + * @mdio_lock: A lock to ensure that only one thing can read/write * the MDIO bus at a time */ struct mutex mdio_lock; + /** @parent: Parent device of this bus */ struct device *parent; + /** @state: State of bus structure */ enum { MDIOBUS_ALLOCATED = 1, MDIOBUS_REGISTERED, MDIOBUS_UNREGISTERED, MDIOBUS_RELEASED, } state; + + /** @dev: Kernel device representation */ struct device dev; - /* list of all PHYs on bus */ + /** @mdio_map: list of all MDIO devices on bus */ struct mdio_device *mdio_map[PHY_MAX_ADDR]; - /* PHY addresses to be ignored when probing */ + /** @phy_mask: PHY addresses to be ignored when probing */ u32 phy_mask; - /* PHY addresses to ignore the TA/read failure */ + /** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */ u32 phy_ignore_ta_mask; - /* - * An array of interrupts, each PHY's interrupt at the index + /** + * @irq: An array of interrupts, each PHY's interrupt at the index * matching its address */ int irq[PHY_MAX_ADDR]; - /* GPIO reset pulse width in microseconds */ + /** @reset_delay_us: GPIO reset pulse width in microseconds */ int reset_delay_us; - /* GPIO reset deassert delay in microseconds */ + /** @reset_post_delay_us: GPIO reset deassert delay in microseconds */ int reset_post_delay_us; - /* RESET GPIO descriptor pointer */ + /** @reset_gpiod: Reset GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; - /* bus capabilities, used for probing */ + /** @probe_capabilities: bus capabilities, used for probing */ enum { MDIOBUS_NO_CAP = 0, MDIOBUS_C22, @@ -306,15 +370,22 @@ struct mii_bus { MDIOBUS_C22_C45, } probe_capabilities; - /* protect access to the shared element */ + /** @shared_lock: protect access to the shared element */ struct mutex shared_lock; - /* shared state across different PHYs */ + /** @shared: shared state across different PHYs */ struct phy_package_shared *shared[PHY_MAX_ADDR]; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) -struct mii_bus *mdiobus_alloc_size(size_t); +struct mii_bus *mdiobus_alloc_size(size_t size); + +/** + * mdiobus_alloc - Allocate an MDIO bus structure + * + * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready + * for the driver to register the bus. + */ static inline struct mii_bus *mdiobus_alloc(void) { return mdiobus_alloc_size(0); @@ -341,40 +412,41 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false #define PHY_INTERRUPT_ENABLED true -/* PHY state machine states: +/** + * enum phy_state - PHY state machine states: * - * DOWN: PHY device and driver are not ready for anything. probe + * @PHY_DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. - * - PHY driver probe function will set the state to READY + * - PHY driver probe function will set the state to @PHY_READY * - * READY: PHY is ready to send and receive packets, but the + * @PHY_READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement * probe will be set to this state by phy_probe(). * - start will set the state to UP * - * UP: The PHY and attached device are ready to do work. + * @PHY_UP: The PHY and attached device are ready to do work. * Interrupts should be started here. - * - timer moves to NOLINK or RUNNING + * - timer moves to @PHY_NOLINK or @PHY_RUNNING * - * NOLINK: PHY is up, but not currently plugged in. - * - irq or timer will set RUNNING if link comes back - * - phy_stop moves to HALTED + * @PHY_NOLINK: PHY is up, but not currently plugged in. + * - irq or timer will set @PHY_RUNNING if link comes back + * - phy_stop moves to @PHY_HALTED * - * RUNNING: PHY is currently up, running, and possibly sending + * @PHY_RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets - * - irq or timer will set NOLINK if link goes down - * - phy_stop moves to HALTED + * - irq or timer will set @PHY_NOLINK if link goes down + * - phy_stop moves to @PHY_HALTED * - * CABLETEST: PHY is performing a cable test. Packet reception/sending + * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending * is not expected to work, carrier will be indicated as down. PHY will be * poll once per second, or on interrupt for it current state. * Once complete, move to UP to restart the PHY. - * - phy_stop aborts the running test and moves to HALTED + * - phy_stop aborts the running test and moves to @PHY_HALTED * - * HALTED: PHY is up, but no polling or interrupts are done. Or + * @PHY_HALTED: PHY is up, but no polling or interrupts are done. Or * PHY is in an error state. - * - phy_start moves to UP + * - phy_start moves to @PHY_UP */ enum phy_state { PHY_DOWN = 0, @@ -403,34 +475,67 @@ struct phy_c45_device_ids { struct macsec_context; struct macsec_ops; -/* phy_device: An instance of a PHY +/** + * struct phy_device - An instance of a PHY * - * drv: Pointer to the driver for this PHY instance - * phy_id: UID for this device found during discovery - * c45_ids: 802.3-c45 Device Identifers if is_c45. - * is_c45: Set to true if this phy uses clause 45 addressing. - * is_internal: Set to true if this phy is internal to a MAC. - * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. - * is_gigabit_capable: Set to true if PHY supports 1000Mbps - * has_fixups: Set to true if this phy has fixups/quirks. - * suspended: Set to true if this phy has been suspended successfully. - * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus. - * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. - * loopback_enabled: Set true if this phy has been loopbacked successfully. - * downshifted_rate: Set true if link speed has been downshifted. - * state: state of the PHY for management purposes - * dev_flags: Device-specific flags used by the PHY driver. - * irq: IRQ number of the PHY's interrupt (-1 if none) - * phy_timer: The timer for handling the state machine - * sfp_bus_attached: flag indicating whether the SFP bus has been attached - * sfp_bus: SFP bus attached to this PHY's fiber port - * attached_dev: The attached enet driver's device instance ptr - * adjust_link: Callback for the enet controller to respond to - * changes in the link state. - * macsec_ops: MACsec offloading ops. + * @mdio: MDIO bus this PHY is on + * @drv: Pointer to the driver for this PHY instance + * @phy_id: UID for this device found during discovery + * @c45_ids: 802.3-c45 Device Identifiers if is_c45. + * @is_c45: Set to true if this PHY uses clause 45 addressing. + * @is_internal: Set to true if this PHY is internal to a MAC. + * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc. + * @is_gigabit_capable: Set to true if PHY supports 1000Mbps + * @has_fixups: Set to true if this PHY has fixups/quirks. + * @suspended: Set to true if this PHY has been suspended successfully. + * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus. + * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. + * @loopback_enabled: Set true if this PHY has been loopbacked successfully. + * @downshifted_rate: Set true if link speed has been downshifted. + * @state: State of the PHY for management purposes + * @dev_flags: Device-specific flags used by the PHY driver. + * @irq: IRQ number of the PHY's interrupt (-1 if none) + * @phy_timer: The timer for handling the state machine + * @phylink: Pointer to phylink instance for this PHY + * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached + * @sfp_bus: SFP bus attached to this PHY's fiber port + * @attached_dev: The attached enet driver's device instance ptr + * @adjust_link: Callback for the enet controller to respond to changes: in the + * link state. + * @phy_link_change: Callback for phylink for notification of link change + * @macsec_ops: MACsec offloading ops. * - * speed, duplex, pause, supported, advertising, lp_advertising, - * and autoneg are used like in mii_if_info + * @speed: Current link speed + * @duplex: Current duplex + * @pause: Current pause + * @asym_pause: Current asymmetric pause + * @supported: Combined MAC/PHY supported linkmodes + * @advertising: Currently advertised linkmodes + * @adv_old: Saved advertised while power saving for WoL + * @lp_advertising: Current link partner advertised linkmodes + * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited + * @autoneg: Flag autoneg being used + * @link: Current link state + * @autoneg_complete: Flag auto negotiation of the link has completed + * @mdix: Current crossover + * @mdix_ctrl: User setting of crossover + * @interrupts: Flag interrupts have been enabled + * @interface: enum phy_interface_t value + * @skb: Netlink message for cable diagnostics + * @nest: Netlink nest used for cable diagnostics + * @ehdr: nNtlink header for cable diagnostics + * @phy_led_triggers: Array of LED triggers + * @phy_num_led_triggers: Number of triggers in @phy_led_triggers + * @led_link_trigger: LED trigger for link up/down + * @last_triggered: last LED trigger for link speed + * @master_slave_set: User requested master/slave configuration + * @master_slave_get: Current master/slave advertisement + * @master_slave_state: Current master/slave configuration + * @mii_ts: Pointer to time stamper callbacks + * @lock: Mutex for serialization access to PHY + * @state_queue: Work queue for state machine + * @shared: Pointer to private data shared by phys in one package + * @priv: Pointer to driver private data * * interrupts currently only supports enabled or disabled, * but could be changed in the future to support enabling @@ -550,9 +655,18 @@ struct phy_device { #define to_phy_device(d) container_of(to_mdio_device(d), \ struct phy_device, mdio) -/* A structure containing possible configuration parameters +/** + * struct phy_tdr_config - Configuration of a TDR raw test + * + * @first: Distance for first data collection point + * @last: Distance for last data collection point + * @step: Step between data collection points + * @pair: Bitmap of cable pairs to collect data for + * + * A structure containing possible configuration parameters * for a TDR cable test. The driver does not need to implement * all the parameters, but should report what is actually used. + * All distances are in centimeters. */ struct phy_tdr_config { u32 first; @@ -562,18 +676,20 @@ struct phy_tdr_config { }; #define PHY_PAIR_ALL -1 -/* struct phy_driver: Driver structure for a particular PHY type +/** + * struct phy_driver - Driver structure for a particular PHY type * - * driver_data: static driver data - * phy_id: The result of reading the UID registers of this PHY + * @mdiodrv: Data common to all MDIO devices + * @phy_id: The result of reading the UID registers of this PHY * type, and ANDing them with the phy_id_mask. This driver * only works for PHYs with IDs which match this field - * name: The friendly name of this PHY type - * phy_id_mask: Defines the important bits of the phy_id - * features: A mandatory list of features (speed, duplex, etc) + * @name: The friendly name of this PHY type + * @phy_id_mask: Defines the important bits of the phy_id + * @features: A mandatory list of features (speed, duplex, etc) * supported by this PHY - * flags: A bitfield defining certain other features this PHY + * @flags: A bitfield defining certain other features this PHY * supports (like interrupts) + * @driver_data: Static driver data * * All functions are optional. If config_aneg or read_status * are not implemented, the phy core uses the genphy versions. @@ -592,151 +708,178 @@ struct phy_driver { u32 flags; const void *driver_data; - /* - * Called to issue a PHY software reset + /** + * @soft_reset: Called to issue a PHY software reset */ int (*soft_reset)(struct phy_device *phydev); - /* - * Called to initialize the PHY, + /** + * @config_init: Called to initialize the PHY, * including after a reset */ int (*config_init)(struct phy_device *phydev); - /* - * Called during discovery. Used to set + /** + * @probe: Called during discovery. Used to set * up device-specific structures, if any */ int (*probe)(struct phy_device *phydev); - /* - * Probe the hardware to determine what abilities it has. - * Should only set phydev->supported. + /** + * @get_features: Probe the hardware to determine what + * abilities it has. Should only set phydev->supported. */ int (*get_features)(struct phy_device *phydev); /* PHY Power Management */ + /** @suspend: Suspend the hardware, saving state if needed */ int (*suspend)(struct phy_device *phydev); + /** @resume: Resume the hardware, restoring state if needed */ int (*resume)(struct phy_device *phydev); - /* - * Configures the advertisement and resets + /** + * @config_aneg: Configures the advertisement and resets * autonegotiation if phydev->autoneg is on, * forces the speed to the current settings in phydev * if phydev->autoneg is off */ int (*config_aneg)(struct phy_device *phydev); - /* Determines the auto negotiation result */ + /** @aneg_done: Determines the auto negotiation result */ int (*aneg_done)(struct phy_device *phydev); - /* Determines the negotiated speed and duplex */ + /** @read_status: Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); - /* Clears any pending interrupts */ + /** @ack_interrupt: Clears any pending interrupts */ int (*ack_interrupt)(struct phy_device *phydev); - /* Enables or disables interrupts */ + /** @config_intr: Enables or disables interrupts */ int (*config_intr)(struct phy_device *phydev); - /* - * Checks if the PHY generated an interrupt. + /** + * @did_interrupt: Checks if the PHY generated an interrupt. * For multi-PHY devices with shared PHY interrupt pin * Set interrupt bits have to be cleared. */ int (*did_interrupt)(struct phy_device *phydev); - /* Override default interrupt handling */ + /** @handle_interrupt: Override default interrupt handling */ irqreturn_t (*handle_interrupt)(struct phy_device *phydev); - /* Clears up any memory if needed */ + /** @remove: Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); - /* Returns true if this is a suitable driver for the given - * phydev. If NULL, matching is based on phy_id and - * phy_id_mask. + /** + * @match_phy_device: Returns true if this is a suitable + * driver for the given phydev. If NULL, matching is based on + * phy_id and phy_id_mask. */ int (*match_phy_device)(struct phy_device *phydev); - /* Some devices (e.g. qnap TS-119P II) require PHY register changes to - * enable Wake on LAN, so set_wol is provided to be called in the - * ethernet driver's set_wol function. */ + /** + * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY + * register changes to enable Wake on LAN, so set_wol is + * provided to be called in the ethernet driver's set_wol + * function. + */ int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); - /* See set_wol, but for checking whether Wake on LAN is enabled. */ + /** + * @get_wol: See set_wol, but for checking whether Wake on LAN + * is enabled. + */ void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); - /* - * Called to inform a PHY device driver when the core is about to - * change the link state. This callback is supposed to be used as - * fixup hook for drivers that need to take action when the link - * state changes. Drivers are by no means allowed to mess with the + /** + * @link_change_notify: Called to inform a PHY device driver + * when the core is about to change the link state. This + * callback is supposed to be used as fixup hook for drivers + * that need to take action when the link state + * changes. Drivers are by no means allowed to mess with the * PHY device structure in their implementations. */ void (*link_change_notify)(struct phy_device *dev); - /* - * Phy specific driver override for reading a MMD register. - * This function is optional for PHY specific drivers. When - * not provided, the default MMD read function will be used - * by phy_read_mmd(), which will use either a direct read for - * Clause 45 PHYs or an indirect read for Clause 22 PHYs. - * devnum is the MMD device number within the PHY device, - * regnum is the register within the selected MMD device. + /** + * @read_mmd: PHY specific driver override for reading a MMD + * register. This function is optional for PHY specific + * drivers. When not provided, the default MMD read function + * will be used by phy_read_mmd(), which will use either a + * direct read for Clause 45 PHYs or an indirect read for + * Clause 22 PHYs. devnum is the MMD device number within the + * PHY device, regnum is the register within the selected MMD + * device. */ int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum); - /* - * Phy specific driver override for writing a MMD register. - * This function is optional for PHY specific drivers. When - * not provided, the default MMD write function will be used - * by phy_write_mmd(), which will use either a direct write for - * Clause 45 PHYs, or an indirect write for Clause 22 PHYs. - * devnum is the MMD device number within the PHY device, - * regnum is the register within the selected MMD device. - * val is the value to be written. + /** + * @write_mmd: PHY specific driver override for writing a MMD + * register. This function is optional for PHY specific + * drivers. When not provided, the default MMD write function + * will be used by phy_write_mmd(), which will use either a + * direct write for Clause 45 PHYs, or an indirect write for + * Clause 22 PHYs. devnum is the MMD device number within the + * PHY device, regnum is the register within the selected MMD + * device. val is the value to be written. */ int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, u16 val); + /** @read_page: Return the current PHY register page number */ int (*read_page)(struct phy_device *dev); + /** @write_page: Set the current PHY register page number */ int (*write_page)(struct phy_device *dev, int page); - /* Get the size and type of the eeprom contained within a plug-in - * module */ + /** + * @module_info: Get the size and type of the eeprom contained + * within a plug-in module + */ int (*module_info)(struct phy_device *dev, struct ethtool_modinfo *modinfo); - /* Get the eeprom information from the plug-in module */ + /** + * @module_eeprom: Get the eeprom information from the plug-in + * module + */ int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); - /* Start a cable test */ + /** @cable_test_start: Start a cable test */ int (*cable_test_start)(struct phy_device *dev); - /* Start a raw TDR cable test */ + /** @cable_test_tdr_start: Start a raw TDR cable test */ int (*cable_test_tdr_start)(struct phy_device *dev, const struct phy_tdr_config *config); - /* Once per second, or on interrupt, request the status of the - * test. + /** + * @cable_test_get_status: Once per second, or on interrupt, + * request the status of the test. */ int (*cable_test_get_status)(struct phy_device *dev, bool *finished); - /* Get statistics from the phy using ethtool */ + /* Get statistics from the PHY using ethtool */ + /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); + /** @get_strings: Names of the statistic counters */ void (*get_strings)(struct phy_device *dev, u8 *data); + /** @get_stats: Return the statistic counter values */ void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); /* Get and Set PHY tunables */ + /** @get_tunable: Return the value of a tunable */ int (*get_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, void *data); + /** @set_tunable: Set the value of a tunable */ int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); + /** @set_loopback: Set the loopback mood of the PHY */ int (*set_loopback)(struct phy_device *dev, bool enable); + /** @get_sqi: Get the signal quality indication */ int (*get_sqi)(struct phy_device *dev); + /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ @@ -890,6 +1033,24 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); +/** + * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a + * condition is met or a timeout occurs + * + * @phydev: The phy_device struct + * @devaddr: The MMD to read from + * @regnum: The register on the MMD to read + * @val: Variable to read the register into + * @cond: Break condition (usually involving @val) + * @sleep_us: Maximum time to sleep between reads in us (0 + * tight-loops). Should be less than ~20ms since usleep_range + * is used (see Documentation/timers/timers-howto.rst). + * @timeout_us: Timeout in us, 0 means never timeout + * @sleep_before_read: if it is true, sleep @sleep_us before read. + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. + */ #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \ sleep_us, timeout_us, sleep_before_read) \ ({ \ @@ -1161,7 +1322,7 @@ static inline bool phy_is_internal(struct phy_device *phydev) /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) - * @mode: the phy_interface_t enum + * @mode: the &phy_interface_t enum */ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) { @@ -1170,11 +1331,11 @@ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) }; /** - * phy_interface_mode_is_8023z() - does the phy interface mode use 802.3z + * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z * negotiation * @mode: one of &enum phy_interface_t * - * Returns true if the phy interface mode uses the 16-bit negotiation + * Returns true if the PHY interface mode uses the 16-bit negotiation * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding) */ static inline bool phy_interface_mode_is_8023z(phy_interface_t mode) @@ -1193,7 +1354,7 @@ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) return phy_interface_mode_is_rgmii(phydev->interface); }; -/* +/** * phy_is_pseudo_fixed_link - Convenience function for testing if this * PHY is the CPU port facing side of an Ethernet switch, or similar. * @phydev: the phy_device struct -- cgit v1.2.3 From 70fb2612aab62d47e03f82eaa7384a8d30ca175d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Sep 2020 21:26:23 -0700 Subject: fscrypt: don't call no-key names "ciphertext names" Currently we're using the term "ciphertext name" ambiguously because it can mean either the actual ciphertext filename, or the encoded filename that is shown when an encrypted directory is listed without its key. The latter we're now usually calling the "no-key name"; and while it's derived from the ciphertext name, it's not the same thing. To avoid this ambiguity, rename fscrypt_name::is_ciphertext_name to fscrypt_name::is_nokey_name, and update comments that say "ciphertext name" (or "encrypted name") to say "no-key name" instead when warranted. Link: https://lore.kernel.org/r/20200924042624.98439-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index fc67c4cbaa96..bc9ec727e993 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -35,7 +35,7 @@ struct fscrypt_name { u32 hash; u32 minor_hash; struct fscrypt_str crypto_buf; - bool is_ciphertext_name; + bool is_nokey_name; }; #define FSTR_INIT(n, l) { .name = n, .len = l } @@ -730,17 +730,16 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir, * @fname: (output) the name to use to search the on-disk directory * * Prepare for ->lookup() in a directory which may be encrypted by determining - * the name that will actually be used to search the directory on-disk. Lookups - * can be done with or without the directory's encryption key; without the key, - * filenames are presented in encrypted form. Therefore, we'll try to set up - * the directory's encryption key, but even without it the lookup can continue. + * the name that will actually be used to search the directory on-disk. If the + * directory's encryption key is available, then the lookup is assumed to be by + * plaintext name; otherwise, it is assumed to be by no-key name. * * This also installs a custom ->d_revalidate() method which will invalidate the * dentry if it was created without the key and the key is later added. * - * Return: 0 on success; -ENOENT if key is unavailable but the filename isn't a - * correctly formed encoded ciphertext name, so a negative dentry should be - * created; or another -errno code. + * Return: 0 on success; -ENOENT if the directory's key is unavailable but the + * filename isn't a valid no-key name, so a negative dentry should be created; + * or another -errno code. */ static inline int fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, -- cgit v1.2.3 From 501e43fbea468fa93c1dff0ee744e69303ef5a43 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Sep 2020 21:26:24 -0700 Subject: fscrypt: rename DCACHE_ENCRYPTED_NAME to DCACHE_NOKEY_NAME Originally we used the term "encrypted name" or "ciphertext name" to mean the encoded filename that is shown when an encrypted directory is listed without its key. But these terms are ambiguous since they also mean the filename stored on-disk. "Encrypted name" is especially ambiguous since it could also be understood to mean "this filename is encrypted on-disk", similar to "encrypted file". So we've started calling these encoded names "no-key names" instead. Therefore, rename DCACHE_ENCRYPTED_NAME to DCACHE_NOKEY_NAME to avoid confusion about what this flag means. Link: https://lore.kernel.org/r/20200924042624.98439-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/dcache.h | 2 +- include/linux/fscrypt.h | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 65d975bf9390..6f95c3300cbb 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -213,7 +213,7 @@ struct dentry_operations { #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ -#define DCACHE_ENCRYPTED_NAME 0x02000000 /* Encrypted name (dir key was unavailable) */ +#define DCACHE_NOKEY_NAME 0x02000000 /* Encrypted name encoded without key */ #define DCACHE_OP_REAL 0x04000000 #define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index bc9ec727e993..f1757e73162d 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -100,15 +100,15 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) } /* - * When d_splice_alias() moves a directory's encrypted alias to its decrypted - * alias as a result of the encryption key being added, DCACHE_ENCRYPTED_NAME - * must be cleared. Note that we don't have to support arbitrary moves of this - * flag because fscrypt doesn't allow encrypted aliases to be the source or - * target of a rename(). + * When d_splice_alias() moves a directory's no-key alias to its plaintext alias + * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be + * cleared. Note that we don't have to support arbitrary moves of this flag + * because fscrypt doesn't allow no-key names to be the source or target of a + * rename(). */ static inline void fscrypt_handle_d_move(struct dentry *dentry) { - dentry->d_flags &= ~DCACHE_ENCRYPTED_NAME; + dentry->d_flags &= ~DCACHE_NOKEY_NAME; } /* crypto.c */ -- cgit v1.2.3 From c9e7c76d70fa50582ca96759829c93d0dd024662 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 21 Sep 2020 15:36:51 +0100 Subject: xfrm: Provide API to register translator module Add a skeleton for xfrm_compat module and provide API to register it in xfrm_state.ko. struct xfrm_translator will have function pointers to translate messages received from 32-bit userspace or to be sent to it from 64-bit kernel. module_get()/module_put() are used instead of rcu_read_lock() as the module will vmalloc() memory for translation. The new API is registered with xfrm_state module, not with xfrm_user as the former needs translator for user_policy set by setsockopt() and xfrm_user already uses functions from xfrm_state. Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2737d24ec244..fe2e3717da14 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -2000,6 +2000,25 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, return 0; } +struct xfrm_translator { + struct module *owner; +}; + +#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) +extern int xfrm_register_translator(struct xfrm_translator *xtr); +extern int xfrm_unregister_translator(struct xfrm_translator *xtr); +extern struct xfrm_translator *xfrm_get_translator(void); +extern void xfrm_put_translator(struct xfrm_translator *xtr); +#else +static inline struct xfrm_translator *xfrm_get_translator(void) +{ + return NULL; +} +static inline void xfrm_put_translator(struct xfrm_translator *xtr) +{ +} +#endif + #if IS_ENABLED(CONFIG_IPV6) static inline bool xfrm6_local_dontfrag(const struct sock *sk) { -- cgit v1.2.3 From 5461fc0c8d9f23956b99f5907f69726a293ccb67 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 21 Sep 2020 15:36:52 +0100 Subject: xfrm/compat: Add 64=>32-bit messages translator Provide the kernel-to-user translator under XFRM_USER_COMPAT, that creates for 64-bit xfrm-user message a 32-bit translation and puts it in skb's frag_list. net/compat.c layer provides MSG_CMSG_COMPAT to decide if the message should be taken from skb or frag_list. (used by wext-core which has also an ABI difference) Kernel sends 64-bit xfrm messages to the userspace for: - multicast (monitor events) - netlink dumps Wire up the translator to xfrm_nlmsg_multicast(). Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fe2e3717da14..5b6cc62c9354 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -2000,7 +2000,12 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, return 0; } +extern const int xfrm_msg_min[XFRM_NR_MSGTYPES]; + struct xfrm_translator { + /* Allocate frag_list and put compat translation there */ + int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src); + struct module *owner; }; -- cgit v1.2.3 From 5106f4a8acff480e244300bc5097c0ad7048c3a2 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 21 Sep 2020 15:36:55 +0100 Subject: xfrm/compat: Add 32=>64-bit messages translator Provide the user-to-kernel translator under XFRM_USER_COMPAT, that creates for 32-bit xfrm-user message a 64-bit translation. The translation is afterwards reused by xfrm_user code just as if userspace had sent 64-bit message. Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 5b6cc62c9354..fa18cb6bb3f7 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -2001,11 +2001,17 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, } extern const int xfrm_msg_min[XFRM_NR_MSGTYPES]; +extern const struct nla_policy xfrma_policy[XFRMA_MAX+1]; struct xfrm_translator { /* Allocate frag_list and put compat translation there */ int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src); + /* Allocate nlmsg with 64-bit translaton of received 32-bit message */ + struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh, + int maxtype, const struct nla_policy *policy, + struct netlink_ext_ack *extack); + struct module *owner; }; -- cgit v1.2.3 From 96392ee5a13b992563cfe07d23ee30d333b89126 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 21 Sep 2020 15:36:56 +0100 Subject: xfrm/compat: Translate 32-bit user_policy from sockptr Provide compat_xfrm_userpolicy_info translation for xfrm setsocketopt(). Reallocate buffer and put the missing padding for 64-bit message. Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fa18cb6bb3f7..53618a31634b 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -2012,6 +2012,9 @@ struct xfrm_translator { int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack); + /* Translate 32-bit user_policy from sockptr */ + int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen); + struct module *owner; }; -- cgit v1.2.3 From 65f4d7ddc7b681001246f60c22a3cf650864da35 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Fri, 18 Sep 2020 21:22:30 +0800 Subject: clocksource/drivers/sp804: Remove unused sp804_timer_disable() and timer-sp804.h Since commit 7484c727b636 ("ARM: realview: delete the RealView board files") and commit 16956fed35fe ("ARM: versatile: switch to DT only booting and remove legacy code"), there's no one to use the functions defined or declared in include/clocksource/timer-sp804.h. Delete it. Signed-off-by: Zhen Lei Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200918132237.3552-3-thunder.leizhen@huawei.com --- include/clocksource/timer-sp804.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/clocksource/timer-sp804.h (limited to 'include') diff --git a/include/clocksource/timer-sp804.h b/include/clocksource/timer-sp804.h deleted file mode 100644 index a5b41f31a1c2..000000000000 --- a/include/clocksource/timer-sp804.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __CLKSOURCE_TIMER_SP804_H -#define __CLKSOURCE_TIMER_SP804_H - -struct clk; - -int __sp804_clocksource_and_sched_clock_init(void __iomem *, - const char *, struct clk *, int); -int __sp804_clockevents_init(void __iomem *, unsigned int, - struct clk *, const char *); -void sp804_timer_disable(void __iomem *); - -static inline void sp804_clocksource_init(void __iomem *base, const char *name) -{ - __sp804_clocksource_and_sched_clock_init(base, name, NULL, 0); -} - -static inline void sp804_clocksource_and_sched_clock_init(void __iomem *base, - const char *name) -{ - __sp804_clocksource_and_sched_clock_init(base, name, NULL, 1); -} - -static inline void sp804_clockevents_init(void __iomem *base, unsigned int irq, const char *name) -{ - __sp804_clockevents_init(base, irq, NULL, name); - -} -#endif -- cgit v1.2.3 From fe205d984e7730f4d21f6f8ebc60f0698404ac31 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 18 Aug 2020 22:24:27 +0800 Subject: ACPI: Remove side effect of partly creating a node in acpi_map_pxm_to_online_node() While this function will only return an online node, it can have the side effect of partially creating a new node. The existing comments suggest this is intentional, but the usecases of this function are related to NFIT and HMAT parsing, neither of which should be able to define new nodes. One route by which the existing behaviour would cause a crash is to have a _PXM entry in ACPI DSDT attempt to place a device within this partly created proximity domain. A subsequent call to devm_kzalloc() or similar would result in an attempt to allocate memory on a node for which zone lists have not been set up and a NULL pointer dereference. Prevent such cases by switching to pxm_to_node() within acpi_map_pxm_to_online_node() which cannot cause a new node to be partly created. If one would previously have been created we now return NO_NUMA_NODE. Documentation updated to reflect this change. Signed-off-by: Jonathan Cameron Reviewed-by: Hanjun Guo Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1e4cdc6c7ae2..a9fd122ae878 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -430,13 +430,12 @@ int acpi_get_node(acpi_handle handle); * ACPI device drivers, which are called after the NUMA initialization has * completed in the kernel, can call this interface to obtain their device * NUMA topology from ACPI tables. Such drivers do not have to deal with - * offline nodes. A node may be offline when a device proximity ID is - * unique, SRAT memory entry does not exist, or NUMA is disabled, ex. - * "numa=off" on x86. + * offline nodes. A node may be offline when SRAT memory entry does not exist, + * or NUMA is disabled, ex. "numa=off" on x86. */ static inline int acpi_map_pxm_to_online_node(int pxm) { - int node = acpi_map_pxm_to_node(pxm); + int node = pxm_to_node(pxm); return numa_map_to_online_node(node); } -- cgit v1.2.3 From 4eb3723f18e9ba4d4b13d82b6f7e68dd50a852ea Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 18 Aug 2020 22:24:28 +0800 Subject: ACPI: Rename acpi_map_pxm_to_online_node() to pxm_to_online_node() As this function is no longer allowed to create new mappings let us rename it to reflect this. Note all nodes should already exist before any of the users of this function are called. Signed-off-by: Jonathan Cameron Reviewed-by: Hanjun Guo Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a9fd122ae878..e9f6cd67943e 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -420,10 +420,10 @@ int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); /** - * acpi_map_pxm_to_online_node - Map proximity ID to online node + * pxm_to_online_node - Map proximity ID to online node * @pxm: ACPI proximity ID * - * This is similar to acpi_map_pxm_to_node(), but always returns an online + * This is similar to pxm_to_node(), but always returns an online * node. When the mapped node from a given proximity ID is offline, it * looks up the node distance table and returns the nearest online node. * @@ -433,14 +433,14 @@ int acpi_get_node(acpi_handle handle); * offline nodes. A node may be offline when SRAT memory entry does not exist, * or NUMA is disabled, ex. "numa=off" on x86. */ -static inline int acpi_map_pxm_to_online_node(int pxm) +static inline int pxm_to_online_node(int pxm) { int node = pxm_to_node(pxm); return numa_map_to_online_node(node); } #else -static inline int acpi_map_pxm_to_online_node(int pxm) +static inline int pxm_to_online_node(int pxm) { return 0; } -- cgit v1.2.3 From fce55cc8b7ade3c583f47eab5885e2f541ede1ee Mon Sep 17 00:00:00 2001 From: Ed Wildgoose Date: Sun, 20 Sep 2020 21:32:06 +0100 Subject: platform/x86: pcengines-apuv2: Fix typo on define of AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 Schematics show that the GPIO number is 55 (not 59). Trivial typo. Signed-off-by: Ed Wildgoose Signed-off-by: Andy Shevchenko --- include/linux/platform_data/gpio/gpio-amd-fch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/gpio/gpio-amd-fch.h b/include/linux/platform_data/gpio/gpio-amd-fch.h index 9e46678edb2a..255d51c9d36d 100644 --- a/include/linux/platform_data/gpio/gpio-amd-fch.h +++ b/include/linux/platform_data/gpio/gpio-amd-fch.h @@ -19,7 +19,7 @@ #define AMD_FCH_GPIO_REG_GPIO49 0x40 #define AMD_FCH_GPIO_REG_GPIO50 0x41 #define AMD_FCH_GPIO_REG_GPIO51 0x42 -#define AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 0x43 +#define AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 0x43 #define AMD_FCH_GPIO_REG_GPIO57 0x44 #define AMD_FCH_GPIO_REG_GPIO58 0x45 #define AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 0x46 -- cgit v1.2.3 From 76bd5c016ef49683d626a48748ef1764aaf8ba63 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 14 Sep 2020 17:05:08 -0400 Subject: NFSv4: make cache consistency bitmask dynamic Client uses static bitmask for GETATTR on CLOSE/WRITE/DELEGRETURN and ignores the fact that it might have some attributes marked invalid in its cache. Compared to v3 where all attributes are retrieved in postop attributes, v4's cache is frequently out of sync and leads to standalone GETATTRs being sent to the server. Instead, in addition to the minimum cache consistency attributes also check cache_validity and adjust the GETATTR request accordingly. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 69cb46f7b8d2..0599efd57eb9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -525,7 +525,7 @@ struct nfs_closeargs { struct nfs_seqid * seqid; fmode_t fmode; u32 share_access; - const u32 * bitmask; + u32 * bitmask; struct nfs4_layoutreturn_args *lr_args; }; @@ -608,7 +608,7 @@ struct nfs4_delegreturnargs { struct nfs4_sequence_args seq_args; const struct nfs_fh *fhandle; const nfs4_stateid *stateid; - const u32 * bitmask; + u32 * bitmask; struct nfs4_layoutreturn_args *lr_args; }; @@ -648,7 +648,7 @@ struct nfs_pgio_args { union { unsigned int replen; /* used by read */ struct { - const u32 * bitmask; /* used by write */ + u32 * bitmask; /* used by write */ enum nfs3_stable_how stable; /* used by write */ }; }; -- cgit v1.2.3 From 596b0474d3d9b1242eab713f84d8873f9887d980 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 8 Sep 2020 13:27:08 +0900 Subject: kbuild: preprocess module linker script There was a request to preprocess the module linker script like we do for the vmlinux one. (https://lkml.org/lkml/2020/8/21/512) The difference between vmlinux.lds and module.lds is that the latter is needed for external module builds, thus must be cleaned up by 'make mrproper' instead of 'make clean'. Also, it must be created by 'make modules_prepare'. You cannot put it in arch/$(SRCARCH)/kernel/, which is cleaned up by 'make clean'. I moved arch/$(SRCARCH)/kernel/module.lds to arch/$(SRCARCH)/include/asm/module.lds.h, which is included from scripts/module.lds.S. scripts/module.lds is fine because 'make clean' keeps all the build artifacts under scripts/. You can add arch-specific sections in . Signed-off-by: Masahiro Yamada Tested-by: Jessica Yu Acked-by: Will Deacon Acked-by: Geert Uytterhoeven Acked-by: Palmer Dabbelt Reviewed-by: Kees Cook Acked-by: Jessica Yu --- include/asm-generic/Kbuild | 1 + include/asm-generic/module.lds.h | 10 ++++++++++ 2 files changed, 11 insertions(+) create mode 100644 include/asm-generic/module.lds.h (limited to 'include') diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 74b0612601dd..7cd4e627e00e 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -40,6 +40,7 @@ mandatory-y += mmiowb.h mandatory-y += mmu.h mandatory-y += mmu_context.h mandatory-y += module.h +mandatory-y += module.lds.h mandatory-y += msi.h mandatory-y += pci.h mandatory-y += percpu.h diff --git a/include/asm-generic/module.lds.h b/include/asm-generic/module.lds.h new file mode 100644 index 000000000000..f210d5c1b78b --- /dev/null +++ b/include/asm-generic/module.lds.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_GENERIC_MODULE_LDS_H +#define __ASM_GENERIC_MODULE_LDS_H + +/* + * can specify arch-specific sections for linking modules. + * Empty for the asm-generic header. + */ + +#endif /* __ASM_GENERIC_MODULE_LDS_H */ -- cgit v1.2.3 From 09a5f210f67eea4a2176820c3bc398747a564705 Mon Sep 17 00:00:00 2001 From: Wenpeng Liang Date: Wed, 16 Sep 2020 16:43:24 +0800 Subject: RDMA/hns: Add support for CQE in size of 64 Bytes The new version of RoCEE supports using CQE in size of 32B or 64B. The performance of bus can be improved by using larger size of CQE. Link: https://lore.kernel.org/r/1600245806-56321-3-git-send-email-liweihang@huawei.com Signed-off-by: Wenpeng Liang Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/hns-abi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index eb76b38a00d4..9ec85f76e9ac 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -39,6 +39,8 @@ struct hns_roce_ib_create_cq { __aligned_u64 buf_addr; __aligned_u64 db_addr; + __u32 cqe_size; + __u32 reserved; }; struct hns_roce_ib_create_cq_resp { @@ -73,7 +75,7 @@ struct hns_roce_ib_create_qp_resp { struct hns_roce_ib_alloc_ucontext_resp { __u32 qp_tab_size; - __u32 reserved; + __u32 cqe_size; }; struct hns_roce_ib_alloc_pd_resp { -- cgit v1.2.3 From 402dd2cf46b177be5bcb138b7d7fd8f38aa130e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:28 +0200 Subject: fs: remove the unused SB_I_MULTIROOT flag The last user of SB_I_MULTIROOT is disappeared with commit f2aedb713c28 ("NFS: Add fs_context support.") Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a08..fbd74df5ce5f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1385,7 +1385,6 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ -#define SB_I_MULTIROOT 0x00000008 /* Multiple roots to the dentry tree */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -- cgit v1.2.3 From c2e4cd57cfa1f627b786c764d185fff85fd12be9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:34 +0200 Subject: block: lift setting the readahead size into the block layer Drivers shouldn't really mess with the readahead size, as that is a VM concept. Instead set it based on the optimal I/O size by lifting the algorithm from the md driver when registering the disk. Also set bdi->io_pages there as well by applying the same scheme based on max_sectors. To ensure the limits work well for stacking drivers a new helper is added to update the readahead limits from the block limits, which is also called from disk_stack_limits. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Jan Kara Reviewed-by: Mike Snitzer Reviewed-by: Martin K. Petersen Acked-by: Coly Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index be5ef6f4ba19..282f5ca424f1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1140,6 +1140,7 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q, extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); +void blk_queue_update_readahead(struct request_queue *q); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); -- cgit v1.2.3 From ed7b6b4f6e915cb0bc52d0000bcc63168867b6ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:35 +0200 Subject: bdi: remove BDI_CAP_CGROUP_WRITEBACK Just checking SB_I_CGROUPWB for cgroup writeback support is enough. Either the file system allocates its own bdi (e.g. btrfs), in which case it is known to support cgroup writeback, or the bdi comes from the block layer, which always supports cgroup writeback. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0b06b2d26c9a..52583b6f2ea0 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -123,7 +123,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. * - * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be * inefficient. */ @@ -233,9 +232,9 @@ int inode_congested(struct inode *inode, int cong_bits); * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * - * cgroup writeback requires support from both the bdi and filesystem. - * Also, both memcg and iocg have to be on the default hierarchy. Test - * whether all conditions are met. + * Cgroup writeback requires support from the filesystem. Also, both memcg and + * iocg have to be on the default hierarchy. Test whether all conditions are + * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. @@ -247,7 +246,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode) return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && bdi_cap_account_dirty(bdi) && - (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } -- cgit v1.2.3 From a8b456d01cd6b37191f14248f3e2bdbe5ce3a89e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:36 +0200 Subject: bdi: remove BDI_CAP_SYNCHRONOUS_IO BDI_CAP_SYNCHRONOUS_IO is only checked in the swap code, and used to decided if ->rw_page can be used on a block device. Just check up for the method instead. The only complication is that zram needs a second set of block_device_operations as it can switch between modes that actually support ->rw_page and those who don't. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 52583b6f2ea0..860ea33571bc 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -122,9 +122,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. - * - * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be - * inefficient. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 @@ -132,7 +129,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 -#define BDI_CAP_SYNCHRONOUS_IO 0x00000040 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) @@ -174,11 +170,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); -static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi) -{ - return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO; -} - static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) { return bdi->capabilities & BDI_CAP_STABLE_WRITES; -- cgit v1.2.3 From 1cb039f3dc1619eb795c54aad0a98fdb379b4237 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:38 +0200 Subject: bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag The BDI_CAP_STABLE_WRITES is one of the few bits of information in the backing_dev_info shared between the block drivers and the writeback code. To help untangling the dependency replace it with a queue flag and a superblock flag derived from it. This also helps with the case of e.g. a file system requiring stable writes due to its own checksumming, but not forcing it on other users of the block device like the swap code. One downside is that we an't support the stable_pages_required bdi attribute in sysfs anymore. It is replaced with a queue attribute which also is writable for easier testing. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 ------ include/linux/blkdev.h | 3 +++ include/linux/fs.h | 1 + 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 860ea33571bc..5da4ea3dd0cc 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -126,7 +126,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 #define BDI_CAP_NO_ACCT_WB 0x00000004 -#define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 @@ -170,11 +169,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); -static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) -{ - return bdi->capabilities & BDI_CAP_STABLE_WRITES; -} - static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 282f5ca424f1..8e77f12de522 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -606,6 +606,7 @@ struct request_queue { #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ +#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ @@ -635,6 +636,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) +#define blk_queue_stable_writes(q) \ + test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) diff --git a/include/linux/fs.h b/include/linux/fs.h index fbd74df5ce5f..222465b7cf41 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1385,6 +1385,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ +#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -- cgit v1.2.3 From 823423ef55f4d9c470b1edc9c5b5c93d06abfaae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:39 +0200 Subject: bdi: invert BDI_CAP_NO_ACCT_WB Replace BDI_CAP_NO_ACCT_WB with a positive BDI_CAP_WRITEBACK_ACCT to make the checks more obvious. Also remove the pointless bdi_cap_account_writeback wrapper that just obsfucates the check. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5da4ea3dd0cc..b217344a2c63 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -120,17 +120,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting * BDI_CAP_NO_WRITEBACK: Don't write pages back - * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages + * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 -#define BDI_CAP_NO_ACCT_WB 0x00000004 +#define BDI_CAP_WRITEBACK_ACCT 0x00000004 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ - (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) + (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY) extern struct backing_dev_info noop_backing_dev_info; @@ -179,13 +179,6 @@ static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi) return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY); } -static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) -{ - /* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */ - return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB | - BDI_CAP_NO_WRITEBACK)); -} - static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); -- cgit v1.2.3 From f56753ac2a90810726334df04d735e9f8f5a32d9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:40 +0200 Subject: bdi: replace BDI_CAP_NO_{WRITEBACK,ACCT_DIRTY} with a single flag Replace the two negative flags that are always used together with a single positive flag that indicates the writeback capability instead of two related non-capabilities. Also remove the pointless wrappers to just check the flag. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 48 ++++++++++----------------------------------- 1 file changed, 10 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index b217344a2c63..44df4fcef65c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -110,27 +110,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); /* * Flags in backing_dev_info::capability * - * The first three flags control whether dirty pages will contribute to the - * VM's accounting and whether writepages() should be called for dirty pages - * (something that would not, for example, be appropriate for ramfs) - * - * WARNING: these flags are closely related and should not normally be - * used separately. The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these - * three flags into a single convenience macro. - * - * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting - * BDI_CAP_NO_WRITEBACK: Don't write pages back - * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages - * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. + * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages + * should contribute to accounting + * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages + * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ -#define BDI_CAP_NO_ACCT_DIRTY 0x00000001 -#define BDI_CAP_NO_WRITEBACK 0x00000002 -#define BDI_CAP_WRITEBACK_ACCT 0x00000004 -#define BDI_CAP_STRICTLIMIT 0x00000010 -#define BDI_CAP_CGROUP_WRITEBACK 0x00000020 - -#define BDI_CAP_NO_ACCT_AND_WRITEBACK \ - (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY) +#define BDI_CAP_WRITEBACK (1 << 0) +#define BDI_CAP_WRITEBACK_ACCT (1 << 1) +#define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; @@ -169,24 +156,9 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); -static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) -{ - return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK); -} - -static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi) -{ - return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY); -} - -static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) -{ - return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); -} - -static inline bool mapping_cap_account_dirty(struct address_space *mapping) +static inline bool mapping_can_writeback(struct address_space *mapping) { - return bdi_cap_account_dirty(inode_to_bdi(mapping->host)); + return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } static inline int bdi_sched_wait(void *word) @@ -223,7 +195,7 @@ static inline bool inode_cgwb_enabled(struct inode *inode) return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && - bdi_cap_account_dirty(bdi) && + (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } -- cgit v1.2.3 From aedcade6f4fa9a1e65f327fc42de3fb47660646c Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 14 Aug 2020 17:40:26 -0700 Subject: debugobjects: Allow debug_obj_descr to be const The debugobject core could be slightly harder to corrupt if the debug_obj_descr would be a pointer to const memory. Depending on the architecture, const data structures are placed into read-only memory and thus are harder to corrupt or hijack. This descriptor is used to fix up stuff like timers and workqueues when core kernel data structures are busted, so moving the descriptors to read-only memory will make debugobjects more resilient to something going wrong and then corrupting the function pointers inside struct debug_obj_descr. Signed-off-by: Stephen Boyd Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20200815004027.2046113-2-swboyd@chromium.org --- include/linux/debugobjects.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index afc416e5dcab..8d2dde23e9fb 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -30,7 +30,7 @@ struct debug_obj { enum debug_obj_state state; unsigned int astate; void *object; - struct debug_obj_descr *descr; + const struct debug_obj_descr *descr; }; /** @@ -64,14 +64,14 @@ struct debug_obj_descr { }; #ifdef CONFIG_DEBUG_OBJECTS -extern void debug_object_init (void *addr, struct debug_obj_descr *descr); +extern void debug_object_init (void *addr, const struct debug_obj_descr *descr); extern void -debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr); -extern int debug_object_activate (void *addr, struct debug_obj_descr *descr); -extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr); -extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr); -extern void debug_object_free (void *addr, struct debug_obj_descr *descr); -extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr); +debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr); +extern int debug_object_activate (void *addr, const struct debug_obj_descr *descr); +extern void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr); +extern void debug_object_destroy (void *addr, const struct debug_obj_descr *descr); +extern void debug_object_free (void *addr, const struct debug_obj_descr *descr); +extern void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr); /* * Active state: @@ -79,26 +79,26 @@ extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr); * - Must return to 0 before deactivation. */ extern void -debug_object_active_state(void *addr, struct debug_obj_descr *descr, +debug_object_active_state(void *addr, const struct debug_obj_descr *descr, unsigned int expect, unsigned int next); extern void debug_objects_early_init(void); extern void debug_objects_mem_init(void); #else static inline void -debug_object_init (void *addr, struct debug_obj_descr *descr) { } +debug_object_init (void *addr, const struct debug_obj_descr *descr) { } static inline void -debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { } +debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr) { } static inline int -debug_object_activate (void *addr, struct debug_obj_descr *descr) { return 0; } +debug_object_activate (void *addr, const struct debug_obj_descr *descr) { return 0; } static inline void -debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { } +debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) { } static inline void -debug_object_destroy (void *addr, struct debug_obj_descr *descr) { } +debug_object_destroy (void *addr, const struct debug_obj_descr *descr) { } static inline void -debug_object_free (void *addr, struct debug_obj_descr *descr) { } +debug_object_free (void *addr, const struct debug_obj_descr *descr) { } static inline void -debug_object_assert_init(void *addr, struct debug_obj_descr *descr) { } +debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) { } static inline void debug_objects_early_init(void) { } static inline void debug_objects_mem_init(void) { } -- cgit v1.2.3 From b952caf2d5ca898cc10d63be7722ae7a5daca696 Mon Sep 17 00:00:00 2001 From: Qianli Zhao Date: Thu, 13 Aug 2020 23:03:14 +0800 Subject: timers: Mask invalid flags in do_init_timer() do_init_timer() accepts any combination of timer flags handed in by the caller without a sanity check, but only TIMER_DEFFERABLE, TIMER_PINNED and TIMER_IRQSAFE are valid. If the supplied flags have other bits set, this could result in malfunction. If bits are set in TIMER_CPUMASK the first timer usage could deference a cpu base which is outside the range of possible CPUs. If TIMER_MIGRATION is set, then the switch_timer_base() will live lock. Prevent that with a sanity check which warns when invalid flags are supplied and masks them out. [ tglx: Made it WARN_ON_ONCE() and added context to the changelog ] Signed-off-by: Qianli Zhao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/9d79a8aa4eb56713af7379f99f062dedabcde140.1597326756.git.zhaoqianli@xiaomi.com --- include/linux/timer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index 07910ae5ddd9..d10bc7e73b41 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -67,6 +67,7 @@ struct timer_list { #define TIMER_DEFERRABLE 0x00080000 #define TIMER_PINNED 0x00100000 #define TIMER_IRQSAFE 0x00200000 +#define TIMER_INIT_FLAGS (TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) #define TIMER_ARRAYSHIFT 22 #define TIMER_ARRAYMASK 0xFFC00000 -- cgit v1.2.3 From 29bcff787a2593b2126cfaff612c0b4e560022e9 Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Thu, 20 Aug 2020 09:22:08 -0400 Subject: md/raid5: add new xor function to support different page offset raid5 will call async_xor() and async_xor_val() to compute xor. For now, both of them require the common src/dst page offset. But, we want them to support different src/dst page offset for following shared page. Here, adding two new function async_xor_offs() and async_xor_val_offs() respectively for async_xor() and async_xor_val(). Signed-off-by: Yufen Yu Signed-off-by: Song Liu --- include/linux/async_tx.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 4c328fef403c..8901f3c801ee 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -162,11 +162,22 @@ struct dma_async_tx_descriptor * async_xor(struct page *dest, struct page **src_list, unsigned int offset, int src_cnt, size_t len, struct async_submit_ctl *submit); +struct dma_async_tx_descriptor * +async_xor_offs(struct page *dest, unsigned int offset, + struct page **src_list, unsigned int *src_offset, + int src_cnt, size_t len, struct async_submit_ctl *submit); + struct dma_async_tx_descriptor * async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, int src_cnt, size_t len, enum sum_check_flags *result, struct async_submit_ctl *submit); +struct dma_async_tx_descriptor * +async_xor_val_offs(struct page *dest, unsigned int offset, + struct page **src_list, unsigned int *src_offset, + int src_cnt, size_t len, enum sum_check_flags *result, + struct async_submit_ctl *submit); + struct dma_async_tx_descriptor * async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, unsigned int src_offset, size_t len, -- cgit v1.2.3 From d69454bc9fdfb63e84152e0533454079ea3e38a3 Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Thu, 20 Aug 2020 09:22:10 -0400 Subject: md/raid6: let syndrome computor support different page offset For now, syndrome compute functions require common offset in the pages array. However, we expect them to support different offset when try to use shared page in the following. Simplily covert them by adding page offset where each page address are referred. Since the only caller of async_gen_syndrome() and async_syndrome_val() are in raid6, we don't want to reserve the old interface but modify the interface directly. After that, replacing old interfaces with new ones for raid6 and raid6test. Signed-off-by: Yufen Yu Signed-off-by: Song Liu --- include/linux/async_tx.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 8901f3c801ee..efc5510f7d11 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -186,13 +186,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit); struct dma_async_tx_descriptor * -async_gen_syndrome(struct page **blocks, unsigned int offset, int src_cnt, +async_gen_syndrome(struct page **blocks, unsigned int *offsets, int src_cnt, size_t len, struct async_submit_ctl *submit); struct dma_async_tx_descriptor * -async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt, +async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt, size_t len, enum sum_check_flags *pqres, struct page *spare, - struct async_submit_ctl *submit); + unsigned int s_off, struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb, -- cgit v1.2.3 From 4f86ff5580fa692f850f37f948c73814a24a722b Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Thu, 20 Aug 2020 09:22:11 -0400 Subject: md/raid6: let async recovery function support different page offset For now, asynchronous raid6 recovery calculate functions are require common offset for pages. But, we expect them to support different page offset after introducing stripe shared page. Do that by simplily adding page offset where each page address are referred. Then, replace the old interface with the new ones in raid6 and raid6test. Signed-off-by: Yufen Yu Signed-off-by: Song Liu --- include/linux/async_tx.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index efc5510f7d11..5cc73d7e5b52 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -196,11 +196,13 @@ async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt, struct dma_async_tx_descriptor * async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb, - struct page **ptrs, struct async_submit_ctl *submit); + struct page **ptrs, unsigned int *offs, + struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_raid6_datap_recov(int src_num, size_t bytes, int faila, - struct page **ptrs, struct async_submit_ctl *submit); + struct page **ptrs, unsigned int *offs, + struct async_submit_ctl *submit); void async_tx_quiesce(struct dma_async_tx_descriptor **tx); #endif /* _ASYNC_TX_H_ */ -- cgit v1.2.3 From e49d8c22f1261c43a986a7fdbf677ac309682a07 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 22 Sep 2020 20:56:23 -0700 Subject: net_sched: defer tcf_idr_insert() in tcf_action_init_1() All TC actions call tcf_idr_insert() for new action at the end of their ->init(), so we can actually move it to a central place in tcf_action_init_1(). And once the action is inserted into the global IDR, other parallel process could free it immediately as its refcnt is still 1, so we can not fail after this, we need to move it after the goto action validation to avoid handling the failure case after insertion. This is found during code review, is not directly triggered by syzbot. And this prepares for the next patch. Cc: Vlad Buslov Cc: Jamal Hadi Salim Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/act_api.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index cb382a89ea58..87214927314a 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -166,8 +166,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a); - void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); -- cgit v1.2.3 From e2f9a8fe73d3a29edfdb4215e7596c95b6db362d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 23 Sep 2020 14:24:20 +0300 Subject: net: mscc: ocelot: always pass skb clone to ocelot_port_add_txtstamp_skb Currently, ocelot switchdev passes the skb directly to the function that enqueues it to the list of skb's awaiting a TX timestamp. Whereas the felix DSA driver first clones the skb, then passes the clone to this queue. This matters because in the case of felix, the common IRQ handler, which is ocelot_get_txtstamp(), currently clones the clone, and frees the original clone. This is useless and can be simplified by using skb_complete_tx_timestamp() instead of skb_tstamp_tx(). Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 0ac4e7fba086..3105bbb6cdcf 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -710,8 +710,8 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid); int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr); int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr); -int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port, - struct sk_buff *skb); +void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port, + struct sk_buff *clone); void ocelot_get_txtstamp(struct ocelot *ocelot); void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu); int ocelot_get_max_mtu(struct ocelot *ocelot, int port); -- cgit v1.2.3 From b5b6775d72e8662b5ea7f892bf06db4831e2c1aa Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 23 Sep 2020 18:41:22 +0300 Subject: of: add of_mdio_find_device() api Add a helper function which finds the mdio_device structure given a device tree node. This is helpful for finding the PCS device based on a DTS node but managing it as a mdio_device instead of a phy_device. Signed-off-by: Russell King Signed-off-by: Ioana Ciornei Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 1efb88d9f892..cfe8c607a628 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -17,6 +17,7 @@ bool of_mdiobus_child_is_phy(struct device_node *child); int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, struct device_node *np); +struct mdio_device *of_mdio_find_device(struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * of_phy_connect(struct net_device *dev, struct device_node *phy_np, @@ -74,6 +75,11 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node * return mdiobus_register(mdio); } +static inline struct mdio_device *of_mdio_find_device(struct device_node *np) +{ + return NULL; +} + static inline struct phy_device *of_phy_find_device(struct device_node *phy_np) { return NULL; -- cgit v1.2.3 From 02a1b175b0e92d9e0fa5df3957ade8d733ceb6a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Wed, 23 Sep 2020 13:18:15 -0700 Subject: net/ipv4: always honour route mtu during forwarding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Documentation/networking/ip-sysctl.txt:46 says: ip_forward_use_pmtu - BOOLEAN By default we don't trust protocol path MTUs while forwarding because they could be easily forged and can lead to unwanted fragmentation by the router. You only need to enable this if you have user-space software which tries to discover path mtus by itself and depends on the kernel honoring this information. This is normally not the case. Default: 0 (disabled) Possible values: 0 - disabled 1 - enabled Which makes it pretty clear that setting it to 1 is a potential security/safety/DoS issue, and yet it is entirely reasonable to want forwarded traffic to honour explicitly administrator configured route mtus (instead of defaulting to device mtu). Indeed, I can't think of a single reason why you wouldn't want to. Since you configured a route mtu you probably know better... It is pretty common to have a higher device mtu to allow receiving large (jumbo) frames, while having some routes via that interface (potentially including the default route to the internet) specify a lower mtu. Note that ipv6 forwarding uses device mtu unless the route is locked (in which case it will use the route mtu). This approach is not usable for IPv4 where an 'mtu lock' on a route also has the side effect of disabling TCP path mtu discovery via disabling the IPv4 DF (don't frag) bit on all outgoing frames. I'm not aware of a way to lock a route from an IPv6 RA, so that also potentially seems wrong. Signed-off-by: Maciej Żenczykowski Cc: Eric Dumazet Cc: Willem de Bruijn Cc: Lorenzo Colitti Cc: Sunmeet Gill (Sunny) Cc: Vinay Paradkar Cc: Tyler Wear Cc: David Ahern Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index b09c48d862cc..2a52787db64a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -436,12 +436,18 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct net *net = dev_net(dst->dev); + unsigned int mtu; if (net->ipv4.sysctl_ip_fwd_use_pmtu || ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); + /* 'forwarding = true' case should always honour route mtu */ + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); } -- cgit v1.2.3 From 08b81d873126b413cda511b1ea1cbb0e99938bbd Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 24 Sep 2020 08:30:01 +0800 Subject: mptcp: add sk_stop_timer_sync helper This patch added a new helper sk_stop_timer_sync, it deactivates a timer like sk_stop_timer, but waits for the handler to finish. Acked-by: Paolo Abeni Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: David S. Miller --- include/net/sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index eaa5cac5e836..a5c6ae78df77 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2195,6 +2195,8 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); +void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); + int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, -- cgit v1.2.3 From 4ab810a4e04ab6c851007033d39c13e6d3f55110 Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Thu, 24 Sep 2020 10:11:13 +0800 Subject: net: mscc: ocelot: fix fields offset in SG_CONFIG_REG_3 INIT_IPS and GATE_ENABLE fields have a wrong offset in SG_CONFIG_REG_3. This register is used by stream gate control of PSFP, and it has not been used before, because PSFP is not implemented in ocelot driver. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_ana.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_ana.h b/include/soc/mscc/ocelot_ana.h index 841c6ec22b64..1669481d9779 100644 --- a/include/soc/mscc/ocelot_ana.h +++ b/include/soc/mscc/ocelot_ana.h @@ -252,10 +252,10 @@ #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_M GENMASK(18, 16) #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_X(x) (((x) & GENMASK(18, 16)) >> 16) #define ANA_SG_CONFIG_REG_3_GATE_ENABLE BIT(20) -#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 24) & GENMASK(27, 24)) -#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(27, 24) -#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(27, 24)) >> 24) -#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(28) +#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 21) & GENMASK(24, 21)) +#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(24, 21) +#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(24, 21)) >> 21) +#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(25) #define ANA_SG_GCL_GS_CONFIG_RSZ 0x4 -- cgit v1.2.3 From ad2b9b0f8d0107602bdc1f3b1ab90719842ace11 Mon Sep 17 00:00:00 2001 From: Priyaranjan Jha Date: Thu, 24 Sep 2020 15:23:14 -0700 Subject: tcp: skip DSACKs with dubious sequence ranges Currently, we use length of DSACKed range to compute number of delivered packets. And if sequence range in DSACK is corrupted, we can get bogus dsacked/acked count, and bogus cwnd. This patch put bounds on DSACKed range to skip update of data delivery and spurious retransmission information, if the DSACK is unlikely caused by sender's action: - DSACKed range shouldn't be greater than maximum advertised rwnd. - Total no. of DSACKed segments shouldn't be greater than total no. of retransmitted segs. Unlike spurious retransmits, network duplicates or corrupted DSACKs shouldn't be counted as delivery. Signed-off-by: Priyaranjan Jha Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index cee9f8e6fce3..f84e7bcad6de 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -288,6 +288,7 @@ enum LINUX_MIB_TCPTIMEOUTREHASH, /* TCPTimeoutRehash */ LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */ LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */ + LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ __LINUX_MIB_MAX }; -- cgit v1.2.3 From 77d0cab93909edf1e5740643d788ac2e458b8187 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 25 Sep 2020 01:23:02 +0200 Subject: net: tcp: drop unused function argument from mptcp_incoming_options Since commit cfde141ea3faa30e ("mptcp: move option parsing into mptcp_incoming_options()"), the 3rd function argument is no longer used. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/mptcp.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 3525d2822abe..753ba7e755d6 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -85,8 +85,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts); -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, - struct tcp_options_received *opt_rx); +void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts); @@ -185,8 +184,7 @@ static inline bool mptcp_established_options(struct sock *sk, } static inline void mptcp_incoming_options(struct sock *sk, - struct sk_buff *skb, - struct tcp_options_received *opt_rx) + struct sk_buff *skb) { } -- cgit v1.2.3 From 7ae10eb903d6ed9b3069fe1dc175b36d86667d09 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 09:29:50 +0200 Subject: dma-mapping: remove DMA_MASK_NONE This value is only used by a PCMCIA driver and not very useful. Signed-off-by: Christoph Hellwig Acked-by: Dominik Brodowski --- include/linux/dma-mapping.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index bb138ac6f5e6..e074588d753f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -138,8 +138,6 @@ extern const struct dma_map_ops dma_dummy_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) -#define DMA_MASK_NONE 0x0ULL - static inline int valid_dma_direction(int dma_direction) { return ((dma_direction == DMA_BIDIRECTIONAL) || -- cgit v1.2.3 From db4268f8c575617bacdeff862c7de674dbf65075 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 09:31:32 +0200 Subject: dma-mapping: move valid_dma_direction to dma-direction.h Move the valid_dma_direction helper to a more suitable header, and clean it up to use the proper enum as well as removing pointless braces. Signed-off-by: Christoph Hellwig --- include/linux/dma-direction.h | 8 +++++++- include/linux/dma-mapping.h | 7 ------- 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h index 9c96e30e6a0b..a2fe4571bc92 100644 --- a/include/linux/dma-direction.h +++ b/include/linux/dma-direction.h @@ -9,4 +9,10 @@ enum dma_data_direction { DMA_NONE = 3, }; -#endif +static inline int valid_dma_direction(enum dma_data_direction dir) +{ + return dir == DMA_BIDIRECTIONAL || dir == DMA_TO_DEVICE || + dir == DMA_FROM_DEVICE; +} + +#endif /* _LINUX_DMA_DIRECTION_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index e074588d753f..51e93d44b826 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -138,13 +138,6 @@ extern const struct dma_map_ops dma_dummy_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) -static inline int valid_dma_direction(int dma_direction) -{ - return ((dma_direction == DMA_BIDIRECTIONAL) || - (dma_direction == DMA_TO_DEVICE) || - (dma_direction == DMA_FROM_DEVICE)); -} - #ifdef CONFIG_DMA_DECLARE_COHERENT /* * These three functions are only for dma allocator. -- cgit v1.2.3 From eba304c6861613a649ba46cfab835b1eddeacd8e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 09:33:42 +0200 Subject: dma-mapping: better document dma_addr_t and DMA_MAPPING_ERROR Move the comment documenting dma_addr_t away from the dma_map_ops definition which isn't very related to it, and toward DMA_MAPPING_ERROR, which is somewhat related. Add a little blurb about DMA_MAPPING_ERROR as well. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 51e93d44b826..943479fb77f6 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -67,12 +67,6 @@ */ #define DMA_ATTR_PRIVILEGED (1UL << 9) -/* - * A dma_addr_t can hold any valid DMA or bus address for the platform. - * It can be given to a device to use as a DMA source or target. A CPU cannot - * reference a dma_addr_t directly because there may be translation between - * its physical address space and the bus address space. - */ struct dma_map_ops { void* (*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, @@ -131,6 +125,16 @@ struct dma_map_ops { unsigned long (*get_merge_boundary)(struct device *dev); }; +/* + * A dma_addr_t can hold any valid DMA or bus address for the platform. It can + * be given to a device to use as a DMA source or target. It is specific to a + * given device and there may be a translation between the CPU physical address + * space and the bus address space. + * + * DMA_MAPPING_ERROR is the magic error code if a mapping failed. It should not + * be used directly in drivers, but checked for using dma_mapping_error() + * instead. + */ #define DMA_MAPPING_ERROR (~(dma_addr_t)0) extern const struct dma_map_ops dma_virt_ops; -- cgit v1.2.3 From 43ee5b6daa6c45246098493dab2c229d196c9cf6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 17 Aug 2020 19:17:20 +0200 Subject: mm: turn alloc_pages into an inline function To prevent a compiler error when a method call alloc_pages is added (which I plan to for the dma_map_ops). Signed-off-by: Christoph Hellwig --- include/linux/gfp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 67a0774e080b..dd2577c54071 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -550,8 +550,10 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else -#define alloc_pages(gfp_mask, order) \ - alloc_pages_node(numa_node_id(), gfp_mask, order) +static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) +{ + return alloc_pages_node(numa_node_id(), gfp_mask, order); +} #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ -- cgit v1.2.3 From 0d71675f87dc406d4c284729b8d36be050ad0d15 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 13:31:30 +0200 Subject: dma-mapping: add a new dma_alloc_noncoherent API Add a new API to allocate and free memory that is guaranteed to be addressable by a device, but which potentially is not cache coherent for DMA. To transfer ownership to and from the device, the existing streaming DMA API calls dma_sync_single_for_device and dma_sync_single_for_cpu must be used. For now the new calls are implemented on top of dma_alloc_attrs just like the old-noncoherent API, but once all drivers are switched to the new API it will be replaced with a better working implementation that is available on all architectures. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 943479fb77f6..cb607b381adf 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -384,6 +384,18 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev) } #endif /* CONFIG_HAS_DMA */ +static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + return dma_alloc_attrs(dev, size, dma_handle, gfp, + DMA_ATTR_NON_CONSISTENT); +} +static inline void dma_free_noncoherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir) +{ + dma_free_attrs(dev, size, vaddr, dma_handle, DMA_ATTR_NON_CONSISTENT); +} + static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) { -- cgit v1.2.3 From 5a84292271402cffe0717bc58e2ad9a0c7977272 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 13:28:13 +0200 Subject: dma-mapping: remove dma_cache_sync All users are gone now, remove the API. Signed-off-by: Christoph Hellwig Acked-by: Thomas Bogendoerfer (MIPS part) --- include/linux/dma-mapping.h | 8 -------- include/linux/dma-noncoherent.h | 10 ---------- 2 files changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index cb607b381adf..233bb8dcbe02 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -117,8 +117,6 @@ struct dma_map_ops { void (*sync_sg_for_device)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir); - void (*cache_sync)(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction direction); int (*dma_supported)(struct device *dev, u64 mask); u64 (*get_required_mask)(struct device *dev); size_t (*max_mapping_size)(struct device *dev); @@ -249,8 +247,6 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle); -void dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction dir); int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); @@ -334,10 +330,6 @@ static inline void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle) { } -static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction dir) -{ -} static inline int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index b9bc6c557ea4..0888656369a4 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -62,16 +62,6 @@ static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, } #endif /* CONFIG_MMU */ -#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC -void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction direction); -#else -static inline void arch_dma_cache_sync(struct device *dev, void *vaddr, - size_t size, enum dma_data_direction direction) -{ -} -#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */ - #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir); -- cgit v1.2.3 From efa70f2fdc842e63a0a13223e0e83cedcc2117f1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 13:34:33 +0200 Subject: dma-mapping: add a new dma_alloc_pages API This API is the equivalent of alloc_pages, except that the returned memory is guaranteed to be DMA addressable by the passed in device. The implementation will also be used to provide a more sensible replacement for DMA_ATTR_NON_CONSISTENT flag. Additionally dma_alloc_noncoherent is switched over to use dma_alloc_pages as its backend. Signed-off-by: Christoph Hellwig Acked-by: Thomas Bogendoerfer (MIPS part) --- include/linux/dma-direct.h | 5 +++++ include/linux/dma-mapping.h | 34 +++++++++++++++++----------------- include/linux/dma-noncoherent.h | 3 --- 3 files changed, 22 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 83f797e0cb78..38ed3b55034d 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -115,6 +115,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); +struct page *dma_direct_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); +void dma_direct_free_pages(struct device *dev, size_t size, + struct page *page, dma_addr_t dma_addr, + enum dma_data_direction dir); int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 233bb8dcbe02..4b9b1d64f5ec 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -27,11 +27,6 @@ * buffered to improve performance. */ #define DMA_ATTR_WRITE_COMBINE (1UL << 2) -/* - * DMA_ATTR_NON_CONSISTENT: Lets the platform to choose to return either - * consistent or non-consistent memory as it sees fit. - */ -#define DMA_ATTR_NON_CONSISTENT (1UL << 3) /* * DMA_ATTR_NO_KERNEL_MAPPING: Lets the platform to avoid creating a kernel * virtual mapping for the allocated buffer. @@ -74,6 +69,11 @@ struct dma_map_ops { void (*free)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs); + struct page *(*alloc_pages)(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, + gfp_t gfp); + void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, + dma_addr_t dma_handle, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); @@ -376,17 +376,14 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev) } #endif /* CONFIG_HAS_DMA */ -static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) -{ - return dma_alloc_attrs(dev, size, dma_handle, gfp, - DMA_ATTR_NON_CONSISTENT); -} -static inline void dma_free_noncoherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir) -{ - dma_free_attrs(dev, size, vaddr, dma_handle, DMA_ATTR_NON_CONSISTENT); -} +struct page *dma_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); +void dma_free_pages(struct device *dev, size_t size, struct page *page, + dma_addr_t dma_handle, enum dma_data_direction dir); +void *dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); +void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, enum dma_data_direction dir); static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -512,7 +509,10 @@ static inline void dma_sync_sgtable_for_device(struct device *dev, extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); - +struct page *dma_common_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); +void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr, + dma_addr_t dma_handle, enum dma_data_direction dir); struct page **dma_common_find_pages(void *cpu_addr); void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot, const void *caller); diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 0888656369a4..e61283e06576 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -31,9 +31,6 @@ static __always_inline bool dma_alloc_need_uncached(struct device *dev, return false; if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) return false; - if (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) && - (attrs & DMA_ATTR_NON_CONSISTENT)) - return false; return true; } -- cgit v1.2.3 From de7cf917768f438aae6d2f4e9bced3739f15f5b6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 13:59:45 +0200 Subject: dma-mapping: add new {alloc,free}_noncoherent dma_map_ops methods This will allow IOMMU drivers to allocate non-contigous memory and return a vmapped virtual address. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4b9b1d64f5ec..7c77cd6f3604 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -74,6 +74,11 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); + void* (*alloc_noncoherent)(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, + gfp_t gfp); + void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); -- cgit v1.2.3 From 77ebdabe8de7c02f43c6de3357f79ff96f9f0579 Mon Sep 17 00:00:00 2001 From: Elena Petrova Date: Fri, 18 Sep 2020 16:42:16 +0100 Subject: crypto: af_alg - add extra parameters for DRBG interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extend the user-space RNG interface: 1. Add entropy input via ALG_SET_DRBG_ENTROPY setsockopt option; 2. Add additional data input via sendmsg syscall. This allows DRBG to be tested with test vectors, for example for the purpose of CAVP testing, which otherwise isn't possible. To prevent erroneous use of entropy input, it is hidden under CRYPTO_USER_API_RNG_CAVP config option and requires CAP_SYS_ADMIN to succeed. Signed-off-by: Elena Petrova Acked-by: Stephan Müller Reviewed-by: Eric Biggers Signed-off-by: Herbert Xu --- include/crypto/if_alg.h | 1 + include/uapi/linux/if_alg.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index ee6412314f8f..a5db86670bdf 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -46,6 +46,7 @@ struct af_alg_type { void *(*bind)(const char *name, u32 type, u32 mask); void (*release)(void *private); int (*setkey)(void *private, const u8 *key, unsigned int keylen); + int (*setentropy)(void *private, sockptr_t entropy, unsigned int len); int (*accept)(void *private, struct sock *sk); int (*accept_nokey)(void *private, struct sock *sk); int (*setauthsize)(void *private, unsigned int authsize); diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h index bc2bcdec377b..60b7c2efd921 100644 --- a/include/uapi/linux/if_alg.h +++ b/include/uapi/linux/if_alg.h @@ -35,6 +35,7 @@ struct af_alg_iv { #define ALG_SET_OP 3 #define ALG_SET_AEAD_ASSOCLEN 4 #define ALG_SET_AEAD_AUTHSIZE 5 +#define ALG_SET_DRBG_ENTROPY 6 /* Operations */ #define ALG_OP_DECRYPT 0 -- cgit v1.2.3 From f49282870fb039e3c2e5c3341bd27875282609d7 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Mon, 21 Sep 2020 00:20:54 +0800 Subject: crypto: sm3 - export crypto_sm3_final function Both crypto_sm3_update and crypto_sm3_finup have been exported, exporting crypto_sm3_final, to avoid having to use crypto_sm3_finup(desc, NULL, 0, dgst) to calculate the hash in some cases. Signed-off-by: Tianjia Zhang Tested-by: Xufeng Zhang Signed-off-by: Herbert Xu --- include/crypto/sm3.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/crypto/sm3.h b/include/crypto/sm3.h index 1438942dc773..42ea21289ba9 100644 --- a/include/crypto/sm3.h +++ b/include/crypto/sm3.h @@ -35,6 +35,8 @@ struct shash_desc; extern int crypto_sm3_update(struct shash_desc *desc, const u8 *data, unsigned int len); +extern int crypto_sm3_final(struct shash_desc *desc, u8 *out); + extern int crypto_sm3_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *hash); #endif -- cgit v1.2.3 From a8ea8bdd9df92a0e5db5b43900abb7a288b8a53e Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Mon, 21 Sep 2020 00:20:55 +0800 Subject: lib/mpi: Extend the MPI library Expand the mpi library based on libgcrypt, and the ECC algorithm of mpi based on libgcrypt requires these functions. Some other algorithms will be developed based on mpi ecc, such as SM2. Signed-off-by: Tianjia Zhang Tested-by: Xufeng Zhang Signed-off-by: Herbert Xu --- include/linux/mpi.h | 87 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) (limited to 'include') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 5d906dfbf3ed..3c9e41603cf6 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -40,21 +40,79 @@ struct gcry_mpi { typedef struct gcry_mpi *MPI; #define mpi_get_nlimbs(a) ((a)->nlimbs) +#define mpi_has_sign(a) ((a)->sign) /*-- mpiutil.c --*/ MPI mpi_alloc(unsigned nlimbs); +void mpi_clear(MPI a); void mpi_free(MPI a); int mpi_resize(MPI a, unsigned nlimbs); +static inline MPI mpi_new(unsigned int nbits) +{ + return mpi_alloc((nbits + BITS_PER_MPI_LIMB - 1) / BITS_PER_MPI_LIMB); +} + +MPI mpi_copy(MPI a); +MPI mpi_alloc_like(MPI a); +void mpi_snatch(MPI w, MPI u); +MPI mpi_set(MPI w, MPI u); +MPI mpi_set_ui(MPI w, unsigned long u); +MPI mpi_alloc_set_ui(unsigned long u); +void mpi_swap_cond(MPI a, MPI b, unsigned long swap); + +/* Constants used to return constant MPIs. See mpi_init if you + * want to add more constants. + */ +#define MPI_NUMBER_OF_CONSTANTS 6 +enum gcry_mpi_constants { + MPI_C_ZERO, + MPI_C_ONE, + MPI_C_TWO, + MPI_C_THREE, + MPI_C_FOUR, + MPI_C_EIGHT +}; + +MPI mpi_const(enum gcry_mpi_constants no); + /*-- mpicoder.c --*/ + +/* Different formats of external big integer representation. */ +enum gcry_mpi_format { + GCRYMPI_FMT_NONE = 0, + GCRYMPI_FMT_STD = 1, /* Twos complement stored without length. */ + GCRYMPI_FMT_PGP = 2, /* As used by OpenPGP (unsigned only). */ + GCRYMPI_FMT_SSH = 3, /* As used by SSH (like STD but with length). */ + GCRYMPI_FMT_HEX = 4, /* Hex format. */ + GCRYMPI_FMT_USG = 5, /* Like STD but unsigned. */ + GCRYMPI_FMT_OPAQUE = 8 /* Opaque format (some functions only). */ +}; + MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes); MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread); +int mpi_fromstr(MPI val, const char *str); +MPI mpi_scanval(const char *string); MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len); void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, int *sign); int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes, int *sign); +int mpi_print(enum gcry_mpi_format format, unsigned char *buffer, + size_t buflen, size_t *nwritten, MPI a); + +/*-- mpi-mod.c --*/ +void mpi_mod(MPI rem, MPI dividend, MPI divisor); + +/* Context used with Barrett reduction. */ +struct barrett_ctx_s; +typedef struct barrett_ctx_s *mpi_barrett_t; + +mpi_barrett_t mpi_barrett_init(MPI m, int copy); +void mpi_barrett_free(mpi_barrett_t ctx); +void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx); +void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx); /*-- mpi-pow.c --*/ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); @@ -62,6 +120,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); /*-- mpi-cmp.c --*/ int mpi_cmp_ui(MPI u, ulong v); int mpi_cmp(MPI u, MPI v); +int mpi_cmpabs(MPI u, MPI v); /*-- mpi-sub-ui.c --*/ int mpi_sub_ui(MPI w, MPI u, unsigned long vval); @@ -69,6 +128,34 @@ int mpi_sub_ui(MPI w, MPI u, unsigned long vval); /*-- mpi-bit.c --*/ void mpi_normalize(MPI a); unsigned mpi_get_nbits(MPI a); +int mpi_test_bit(MPI a, unsigned int n); +void mpi_set_bit(MPI a, unsigned int n); +void mpi_set_highbit(MPI a, unsigned int n); +void mpi_clear_highbit(MPI a, unsigned int n); +void mpi_clear_bit(MPI a, unsigned int n); +void mpi_rshift_limbs(MPI a, unsigned int count); +void mpi_rshift(MPI x, MPI a, unsigned int n); +void mpi_lshift_limbs(MPI a, unsigned int count); +void mpi_lshift(MPI x, MPI a, unsigned int n); + +/*-- mpi-add.c --*/ +void mpi_add_ui(MPI w, MPI u, unsigned long v); +void mpi_add(MPI w, MPI u, MPI v); +void mpi_sub(MPI w, MPI u, MPI v); +void mpi_addm(MPI w, MPI u, MPI v, MPI m); +void mpi_subm(MPI w, MPI u, MPI v, MPI m); + +/*-- mpi-mul.c --*/ +void mpi_mul(MPI w, MPI u, MPI v); +void mpi_mulm(MPI w, MPI u, MPI v, MPI m); + +/*-- mpi-div.c --*/ +void mpi_tdiv_r(MPI rem, MPI num, MPI den); +void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor); +void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor); + +/*-- mpi-inv.c --*/ +int mpi_invm(MPI x, MPI a, MPI n); /* inline functions */ -- cgit v1.2.3 From d58bb7e55a8a65894cc02f27c3e2bf9403e7c40f Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Mon, 21 Sep 2020 00:20:56 +0800 Subject: lib/mpi: Introduce ec implementation to MPI library The implementation of EC is introduced from libgcrypt as the basic algorithm of elliptic curve, which can be more perfectly integrated with MPI implementation. Some other algorithms will be developed based on mpi ecc, such as SM2. Signed-off-by: Tianjia Zhang Tested-by: Xufeng Zhang Signed-off-by: Herbert Xu --- include/linux/mpi.h | 105 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 105 insertions(+) (limited to 'include') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 3c9e41603cf6..3e5358f4de2f 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -157,6 +157,111 @@ void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor); /*-- mpi-inv.c --*/ int mpi_invm(MPI x, MPI a, MPI n); +/*-- ec.c --*/ + +/* Object to represent a point in projective coordinates */ +struct gcry_mpi_point { + MPI x; + MPI y; + MPI z; +}; + +typedef struct gcry_mpi_point *MPI_POINT; + +/* Models describing an elliptic curve */ +enum gcry_mpi_ec_models { + /* The Short Weierstrass equation is + * y^2 = x^3 + ax + b + */ + MPI_EC_WEIERSTRASS = 0, + /* The Montgomery equation is + * by^2 = x^3 + ax^2 + x + */ + MPI_EC_MONTGOMERY, + /* The Twisted Edwards equation is + * ax^2 + y^2 = 1 + bx^2y^2 + * Note that we use 'b' instead of the commonly used 'd'. + */ + MPI_EC_EDWARDS +}; + +/* Dialects used with elliptic curves */ +enum ecc_dialects { + ECC_DIALECT_STANDARD = 0, + ECC_DIALECT_ED25519, + ECC_DIALECT_SAFECURVE +}; + +/* This context is used with all our EC functions. */ +struct mpi_ec_ctx { + enum gcry_mpi_ec_models model; /* The model describing this curve. */ + enum ecc_dialects dialect; /* The ECC dialect used with the curve. */ + int flags; /* Public key flags (not always used). */ + unsigned int nbits; /* Number of bits. */ + + /* Domain parameters. Note that they may not all be set and if set + * the MPIs may be flaged as constant. + */ + MPI p; /* Prime specifying the field GF(p). */ + MPI a; /* First coefficient of the Weierstrass equation. */ + MPI b; /* Second coefficient of the Weierstrass equation. */ + MPI_POINT G; /* Base point (generator). */ + MPI n; /* Order of G. */ + unsigned int h; /* Cofactor. */ + + /* The actual key. May not be set. */ + MPI_POINT Q; /* Public key. */ + MPI d; /* Private key. */ + + const char *name; /* Name of the curve. */ + + /* This structure is private to mpi/ec.c! */ + struct { + struct { + unsigned int a_is_pminus3:1; + unsigned int two_inv_p:1; + } valid; /* Flags to help setting the helper vars below. */ + + int a_is_pminus3; /* True if A = P - 3. */ + + MPI two_inv_p; + + mpi_barrett_t p_barrett; + + /* Scratch variables. */ + MPI scratch[11]; + + /* Helper for fast reduction. */ + /* int nist_nbits; /\* If this is a NIST curve, the # of bits. *\/ */ + /* MPI s[10]; */ + /* MPI c; */ + } t; + + /* Curve specific computation routines for the field. */ + void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); + void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec); + void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); + void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx); + void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx); +}; + +void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, + enum ecc_dialects dialect, + int flags, MPI p, MPI a, MPI b); +void mpi_ec_deinit(struct mpi_ec_ctx *ctx); +MPI_POINT mpi_point_new(unsigned int nbits); +void mpi_point_release(MPI_POINT p); +void mpi_point_init(MPI_POINT p); +void mpi_point_free_parts(MPI_POINT p); +int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx); +void mpi_ec_add_points(MPI_POINT result, + MPI_POINT p1, MPI_POINT p2, + struct mpi_ec_ctx *ctx); +void mpi_ec_mul_point(MPI_POINT result, + MPI scalar, MPI_POINT point, + struct mpi_ec_ctx *ctx); +int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx); + /* inline functions */ /** -- cgit v1.2.3 From ea7ecb66440b37c035e899c60ceaf7a03d364930 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Mon, 21 Sep 2020 00:20:57 +0800 Subject: crypto: sm2 - introduce OSCCA SM2 asymmetric cipher algorithm This new module implement the SM2 public key algorithm. It was published by State Encryption Management Bureau, China. List of specifications for SM2 elliptic curve public key cryptography: * GM/T 0003.1-2012 * GM/T 0003.2-2012 * GM/T 0003.3-2012 * GM/T 0003.4-2012 * GM/T 0003.5-2012 IETF: https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02 oscca: http://www.oscca.gov.cn/sca/xxgk/2010-12/17/content_1002386.shtml scctc: http://www.gmbz.org.cn/main/bzlb.html Signed-off-by: Tianjia Zhang Tested-by: Xufeng Zhang Signed-off-by: Herbert Xu --- include/crypto/sm2.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/crypto/sm2.h (limited to 'include') diff --git a/include/crypto/sm2.h b/include/crypto/sm2.h new file mode 100644 index 000000000000..af452556dcd4 --- /dev/null +++ b/include/crypto/sm2.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * sm2.h - SM2 asymmetric public-key algorithm + * as specified by OSCCA GM/T 0003.1-2012 -- 0003.5-2012 SM2 and + * described at https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02 + * + * Copyright (c) 2020, Alibaba Group. + * Written by Tianjia Zhang + */ + +#ifndef _CRYPTO_SM2_H +#define _CRYPTO_SM2_H + +#include +#include + +/* The default user id as specified in GM/T 0009-2012 */ +#define SM2_DEFAULT_USERID "1234567812345678" +#define SM2_DEFAULT_USERID_LEN 16 + +extern int sm2_compute_z_digest(struct crypto_akcipher *tfm, + const unsigned char *id, size_t id_len, + unsigned char dgst[SM3_DIGEST_SIZE]); + +#endif /* _CRYPTO_SM2_H */ -- cgit v1.2.3 From 254f84f559039b6d6f6e1035fd7645b42671ab48 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Mon, 21 Sep 2020 00:21:01 +0800 Subject: X.509: support OSCCA certificate parse The digital certificate format based on SM2 crypto algorithm as specified in GM/T 0015-2012. It was published by State Encryption Management Bureau, China. This patch adds the OID object identifier defined by OSCCA. The x509 certificate supports SM2-with-SM3 type certificate parsing. It uses the standard elliptic curve public key, and the sm2 algorithm signs the hash generated by sm3. Signed-off-by: Tianjia Zhang Tested-by: Xufeng Zhang Reviewed-by: Vitaly Chikunov Signed-off-by: Herbert Xu --- include/linux/oid_registry.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 657d6bf2c064..4462ed2c18cd 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -107,6 +107,12 @@ enum OID { OID_gostTC26Sign512B, /* 1.2.643.7.1.2.1.2.2 */ OID_gostTC26Sign512C, /* 1.2.643.7.1.2.1.2.3 */ + /* OSCCA */ + OID_sm2, /* 1.2.156.10197.1.301 */ + OID_sm3, /* 1.2.156.10197.1.401 */ + OID_SM2_with_SM3, /* 1.2.156.10197.1.501 */ + OID_sm3WithRSAEncryption, /* 1.2.156.10197.1.504 */ + OID__NR }; -- cgit v1.2.3 From 215525639631ade1d67e879fe2c3d7195daa9f59 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Mon, 21 Sep 2020 00:21:02 +0800 Subject: X.509: support OSCCA SM2-with-SM3 certificate verification The digital certificate format based on SM2 crypto algorithm as specified in GM/T 0015-2012. It was published by State Encryption Management Bureau, China. The method of generating Other User Information is defined as ZA=H256(ENTLA || IDA || a || b || xG || yG || xA || yA), it also specified in https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02. The x509 certificate supports SM2-with-SM3 type certificate verification. Because certificate verification requires ZA in addition to tbs data, ZA also depends on elliptic curve parameters and public key data, so you need to access tbs in sig and calculate ZA. Finally calculate the digest of the signature and complete the verification work. The calculation process of ZA is declared in specifications GM/T 0009-2012 and GM/T 0003.2-2012. Signed-off-by: Tianjia Zhang Tested-by: Xufeng Zhang Reviewed-by: Gilad Ben-Yossef Signed-off-by: Herbert Xu --- include/crypto/public_key.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h index 11f535cfb810..02a6dbe5c366 100644 --- a/include/crypto/public_key.h +++ b/include/crypto/public_key.h @@ -12,6 +12,7 @@ #include #include +#include /* * Cryptographic data for the public-key subtype of the asymmetric key type. @@ -44,6 +45,8 @@ struct public_key_signature { const char *pkey_algo; const char *hash_algo; const char *encoding; + const void *data; + unsigned int data_size; }; extern void public_key_signature_free(struct public_key_signature *sig); @@ -81,4 +84,16 @@ extern int verify_signature(const struct key *, int public_key_verify_signature(const struct public_key *pkey, const struct public_key_signature *sig); +#if IS_REACHABLE(CONFIG_CRYPTO_SM2) +int cert_sig_digest_update(const struct public_key_signature *sig, + struct crypto_akcipher *tfm_pkey); +#else +static inline +int cert_sig_digest_update(const struct public_key_signature *sig, + struct crypto_akcipher *tfm_pkey) +{ + return -ENOTSUPP; +} +#endif + #endif /* _LINUX_PUBLIC_KEY_H */ -- cgit v1.2.3 From bb0890b4cd7f8203e3aa99c6d0f062d6acdaad27 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 24 Sep 2020 09:40:53 -0400 Subject: fbdev, newport_con: Move FONT_EXTRA_WORDS macros into linux/font.h drivers/video/console/newport_con.c is borrowing FONT_EXTRA_WORDS macros from drivers/video/fbdev/core/fbcon.h. To keep things simple, move all definitions into . Since newport_con now uses four extra words, initialize the fourth word in newport_set_font() properly. Cc: stable@vger.kernel.org Signed-off-by: Peilin Ye Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/7fb8bc9b0abc676ada6b7ac0e0bd443499357267.1600953813.git.yepeilin.cs@gmail.com --- include/linux/font.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/font.h b/include/linux/font.h index 51b91c8b69d5..40ed008d7dad 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -59,4 +59,12 @@ extern const struct font_desc *get_default_font(int xres, int yres, /* Max. length for the name of a predefined font */ #define MAX_FONT_NAME 32 +/* Extra word getters */ +#define REFCOUNT(fd) (((int *)(fd))[-1]) +#define FNTSIZE(fd) (((int *)(fd))[-2]) +#define FNTCHARCNT(fd) (((int *)(fd))[-3]) +#define FNTSUM(fd) (((int *)(fd))[-4]) + +#define FONT_EXTRA_WORDS 4 + #endif /* _VIDEO_FONT_H */ -- cgit v1.2.3 From 6735b4632def0640dbdf4eb9f99816aca18c4f16 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 24 Sep 2020 09:42:22 -0400 Subject: Fonts: Support FONT_EXTRA_WORDS macros for built-in fonts syzbot has reported an issue in the framebuffer layer, where a malicious user may overflow our built-in font data buffers. In order to perform a reliable range check, subsystems need to know `FONTDATAMAX` for each built-in font. Unfortunately, our font descriptor, `struct console_font` does not contain `FONTDATAMAX`, and is part of the UAPI, making it infeasible to modify it. For user-provided fonts, the framebuffer layer resolves this issue by reserving four extra words at the beginning of data buffers. Later, whenever a function needs to access them, it simply uses the following macros: Recently we have gathered all the above macros to . Let us do the same thing for built-in fonts, prepend four extra words (including `FONTDATAMAX`) to their data buffers, so that subsystems can use these macros for all fonts, no matter built-in or user-provided. This patch depends on patch "fbdev, newport_con: Move FONT_EXTRA_WORDS macros into linux/font.h". Cc: stable@vger.kernel.org Link: https://syzkaller.appspot.com/bug?id=08b8be45afea11888776f897895aef9ad1c3ecfd Signed-off-by: Peilin Ye Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/ef18af00c35fb3cc826048a5f70924ed6ddce95b.1600953813.git.yepeilin.cs@gmail.com --- include/linux/font.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/font.h b/include/linux/font.h index 40ed008d7dad..59faa80f586d 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -67,4 +67,9 @@ extern const struct font_desc *get_default_font(int xres, int yres, #define FONT_EXTRA_WORDS 4 +struct font_data { + unsigned int extra[FONT_EXTRA_WORDS]; + const unsigned char data[]; +} __packed; + #endif /* _VIDEO_FONT_H */ -- cgit v1.2.3 From 749626fa099085ca77f3ff05a8efcb3b87721724 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 1 Sep 2020 14:47:16 +0800 Subject: ACPI: Remove three unused inline functions There is no callers in tree. Signed-off-by: YueHaibing [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1e4cdc6c7ae2..7ce2235f99f9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -977,8 +977,6 @@ int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); #else -static inline int acpi_dev_runtime_suspend(struct device *dev) { return 0; } -static inline int acpi_dev_runtime_resume(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) @@ -1216,13 +1214,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, return -ENXIO; } -static inline int acpi_dev_prop_get(const struct acpi_device *adev, - const char *propname, - void **valptr) -{ - return -ENXIO; -} - static inline int acpi_dev_prop_read_single(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, -- cgit v1.2.3 From 2a36ab717e8fe678d98f81c14a0b124712719840 Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Wed, 23 Sep 2020 16:36:16 -0700 Subject: rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ This patchset is based on Google-internal RSEQ work done by Paul Turner and Andrew Hunter. When working with per-CPU RSEQ-based memory allocations, it is sometimes important to make sure that a global memory location is no longer accessed from RSEQ critical sections. For example, there can be two per-CPU lists, one is "active" and accessed per-CPU, while another one is inactive and worked on asynchronously "off CPU" (e.g. garbage collection is performed). Then at some point the two lists are swapped, and a fast RCU-like mechanism is required to make sure that the previously active list is no longer accessed. This patch introduces such a mechanism: in short, membarrier() syscall issues an IPI to a CPU, restarting a potentially active RSEQ critical section on the CPU. Signed-off-by: Peter Oskolkov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mathieu Desnoyers Link: https://lkml.kernel.org/r/20200923233618.2572849-1-posk@google.com --- include/linux/sched/mm.h | 3 +++ include/linux/syscalls.h | 2 +- include/uapi/linux/membarrier.h | 26 ++++++++++++++++++++++++++ 3 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index f889e332912f..15bfb06f2884 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -348,10 +348,13 @@ enum { MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), + MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 75ac7f8ae93c..06db09875aa4 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -974,7 +974,7 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); asmlinkage long sys_userfaultfd(int flags); -asmlinkage long sys_membarrier(int cmd, int flags); +asmlinkage long sys_membarrier(int cmd, unsigned int flags, int cpu_id); asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in, int fd_out, loff_t __user *off_out, diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 5891d7614c8c..737605897f36 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -114,6 +114,26 @@ * If this command is not implemented by an * architecture, -EINVAL is returned. * Returns 0 on success. + * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: + * Ensure the caller thread, upon return from + * system call, that all its running thread + * siblings have any currently running rseq + * critical sections restarted if @flags + * parameter is 0; if @flags parameter is + * MEMBARRIER_CMD_FLAG_CPU, + * then this operation is performed only + * on CPU indicated by @cpu_id. If this command is + * not implemented by an architecture, -EINVAL + * is returned. A process needs to register its + * intent to use the private expedited rseq + * command prior to using it, otherwise + * this command returns -EPERM. + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ: + * Register the process intent to use + * MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ. + * If this command is not implemented by an + * architecture, -EINVAL is returned. + * Returns 0 on success. * @MEMBARRIER_CMD_SHARED: * Alias to MEMBARRIER_CMD_GLOBAL. Provided for * header backward compatibility. @@ -131,9 +151,15 @@ enum membarrier_cmd { MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 5), MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 6), + MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ = (1 << 7), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ = (1 << 8), /* Alias for header backward compatibility. */ MEMBARRIER_CMD_SHARED = MEMBARRIER_CMD_GLOBAL, }; +enum membarrier_cmd_flag { + MEMBARRIER_CMD_FLAG_CPU = (1 << 0), +}; + #endif /* _UAPI_LINUX_MEMBARRIER_H */ -- cgit v1.2.3 From 3aab91774bbd8e571cfaddaf839aafd07718333c Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Fri, 25 Sep 2020 14:00:31 +0800 Subject: block: remove unused BLK_QC_T_EAGAIN flag commit 7b6620d7db56 ("block: remove REQ_NOWAIT_INLINE") removed the REQ_NOWAIT_INLINE related code, but the diff wasn't applied to blk_types.h somehow. Then commit 2771cefeac49 ("block: remove the REQ_NOWAIT_INLINE flag") removed the REQ_NOWAIT_INLINE flag while the BLK_QC_T_EAGAIN flag still remains. Fixes: 7b6620d7db56 ("block: remove REQ_NOWAIT_INLINE") Signed-off-by: Jeffle Xu Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4ecf4fed171f..b3fc5d3dd8ea 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -497,13 +497,12 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U -#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; + return cookie != BLK_QC_T_NONE; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) -- cgit v1.2.3 From fa01b1e9733fd59ecb8b5b6d85dfb481d2025fbf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Sep 2020 07:40:57 +0200 Subject: block: add a bdev_is_partition helper Add a littler helper to make the somewhat arcane bd_contains checks a little more obvious. Signed-off-by: Christoph Hellwig Acked-by: Ulf Hansson Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8e77f12de522..33f283885ba5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1353,6 +1353,11 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, extern int blk_verify_command(unsigned char *cmd, fmode_t mode); +static inline bool bdev_is_partition(struct block_device *bdev) +{ + return bdev->bd_partno; +} + enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, @@ -1469,7 +1474,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev) if (q->limits.misaligned) return -1; - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_part->start_sect); return q->limits.alignment_offset; @@ -1510,7 +1515,7 @@ static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_part->start_sect); return q->limits.discard_alignment; -- cgit v1.2.3 From 021a24460dc28e7412aecfae89f60e1847e685c0 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 23 Sep 2020 16:06:51 -0400 Subject: block: add QUEUE_FLAG_NOWAIT Add QUEUE_FLAG_NOWAIT to allow a block device to advertise support for REQ_NOWAIT. Bio-based devices may set QUEUE_FLAG_NOWAIT where applicable. Update QUEUE_FLAG_MQ_DEFAULT to include QUEUE_FLAG_NOWAIT. Also update submit_bio_checks() to verify it is set for REQ_NOWAIT bios. Reported-by: Konstantin Khlebnikov Suggested-by: Christoph Hellwig Signed-off-by: Mike Snitzer Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 33f283885ba5..d5a3e1a4c2f7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -619,10 +619,12 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ -#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ +#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ +#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); @@ -664,6 +666,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) +#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -- cgit v1.2.3 From 6abc49468eeaad2dd481779906aaa29605139087 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 23 Sep 2020 16:06:52 -0400 Subject: dm: add support for REQ_NOWAIT and enable it for linear target Add DM target feature flag DM_TARGET_NOWAIT which advertises that target works with REQ_NOWAIT bios. Add dm_table_supports_nowait() and update dm_table_set_restrictions() to set/clear QUEUE_FLAG_NOWAIT accordingly. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/device-mapper.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 93096e524e43..d6f8d4ba8d48 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -252,6 +252,12 @@ struct target_type { #define DM_TARGET_ZONED_HM 0x00000040 #define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM) +/* + * A target handles REQ_NOWAIT + */ +#define DM_TARGET_NOWAIT 0x00000080 +#define dm_target_supports_nowait(type) ((type)->features & DM_TARGET_NOWAIT) + struct dm_target { struct dm_table *table; struct target_type *type; -- cgit v1.2.3 From 34d8f7a4627ca59ba915c7ea44fe9d9123875712 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 21 Sep 2020 14:13:35 +0800 Subject: iopoll: update kerneldoc of read_poll_timeout_atomic() Arguments description of read_poll_timeout_atomic() is out of date, update it. Cc: Alan Stern Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/1600668815-12135-11-git-send-email-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- include/linux/iopoll.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index bc89ac625f26..2c8860e406bd 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -60,8 +60,7 @@ /** * read_poll_timeout_atomic - Periodically poll an address until a condition is * met or a timeout occurs - * @op: accessor function (takes @addr as its only argument) - * @addr: Address to poll + * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) * @delay_us: Time to udelay between reads in us (0 tight-loops). Should @@ -69,6 +68,7 @@ * Documentation/timers/timers-howto.rst). * @timeout_us: Timeout in us, 0 means never timeout * @delay_before_read: if it is true, delay @delay_us before read. + * @args: arguments for @op poll * * Returns 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. -- cgit v1.2.3 From ddd1198e3e0935066d6e309180d49f64ef4fa702 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 23 Sep 2020 15:43:42 +0200 Subject: USB: correct API of usb_control_msg_send/recv They need to specify how memory is to be allocated, as control messages need to work in contexts that require GFP_NOIO. Signed-off-by: Oliver Neukum Link: https://lore.kernel.org/r/20200923134348.23862-9-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index a5460f08126e..7d72c4e0713c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1804,10 +1804,12 @@ extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, /* wrappers around usb_control_msg() for the most common standard requests */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, __u8 requesttype, __u16 value, __u16 index, - const void *data, __u16 size, int timeout); + const void *data, __u16 size, int timeout, + gfp_t memflags); int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request, __u8 requesttype, __u16 value, __u16 index, - void *data, __u16 size, int timeout); + void *data, __u16 size, int timeout, + gfp_t memflags); extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype, unsigned char descindex, void *buf, int size); extern int usb_get_status(struct usb_device *dev, -- cgit v1.2.3 From c5a6561b8d99ea7d8df21308249ce05bce3dd466 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 17 Sep 2020 20:44:56 -0400 Subject: iocost: add iocg_forgive_debt tracepoint Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/trace/events/iocost.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include') diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index b350860d2e71..0b6869980ba2 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -164,6 +164,47 @@ TRACE_EVENT(iocost_ioc_vrate_adj, ) ); +TRACE_EVENT(iocost_iocg_forgive_debt, + + TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, + u32 usage_pct, u64 old_debt, u64 new_debt, + u64 old_delay, u64 new_delay), + + TP_ARGS(iocg, path, now, usage_pct, + old_debt, new_debt, old_delay, new_delay), + + TP_STRUCT__entry ( + __string(devname, ioc_name(iocg->ioc)) + __string(cgroup, path) + __field(u64, now) + __field(u64, vnow) + __field(u32, usage_pct) + __field(u64, old_debt) + __field(u64, new_debt) + __field(u64, old_delay) + __field(u64, new_delay) + ), + + TP_fast_assign( + __assign_str(devname, ioc_name(iocg->ioc)); + __assign_str(cgroup, path); + __entry->now = now->now; + __entry->vnow = now->vnow; + __entry->usage_pct = usage_pct; + __entry->old_debt = old_debt; + __entry->new_debt = new_debt; + __entry->old_delay = old_delay; + __entry->new_delay = new_delay; + ), + + TP_printk("[%s:%s] now=%llu:%llu usage=%u debt=%llu->%llu delay=%llu->%llu", + __get_str(devname), __get_str(cgroup), + __entry->now, __entry->vnow, __entry->usage_pct, + __entry->old_debt, __entry->new_debt, + __entry->old_delay, __entry->new_delay + ) +); + #endif /* _TRACE_BLK_IOCOST_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 5f6e560c2dd5be3ae446f20ae97263cbfa309630 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Tue, 7 Jul 2020 23:45:07 +0800 Subject: soc: mediatek: cmdq: add write_s function add write_s function in cmdq helper functions which writes value contains in internal register to address with large dma access support. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1594136714-11650-3-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + include/linux/soc/mediatek/mtk-cmdq.h | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 05eea1aef5aa..1f76cfedb16d 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -60,6 +60,7 @@ enum cmdq_code { CMDQ_CODE_JUMP = 0x10, CMDQ_CODE_WFE = 0x20, CMDQ_CODE_EOC = 0x40, + CMDQ_CODE_WRITE_S = 0x90, CMDQ_CODE_LOGIC = 0xa0, }; diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 2249ecaf77e4..9b0c57a0063d 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -12,6 +12,8 @@ #include #define CMDQ_NO_TIMEOUT 0xffffffffu +#define CMDQ_ADDR_HIGH(addr) ((u32)(((addr) >> 16) & GENMASK(31, 0))) +#define CMDQ_ADDR_LOW(addr) ((u16)(addr) | BIT(1)) struct cmdq_pkt; @@ -102,6 +104,23 @@ int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value); int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value, u32 mask); +/** + * cmdq_pkt_write_s() - append write_s command to the CMDQ packet + * @pkt: the CMDQ packet + * @high_addr_reg_idx: internal register ID which contains high address of pa + * @addr_low: low address of pa + * @src_reg_idx: the CMDQ internal register ID which cache source value + * + * Return: 0 for success; else the error code is returned + * + * Support write value to physical address without subsys. Use CMDQ_ADDR_HIGH() + * to get high address and call cmdq_pkt_assign() to assign value into internal + * reg. Also use CMDQ_ADDR_LOW() to get low address for addr_low parameter when + * call to this function. + */ +int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 src_reg_idx); + /** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet -- cgit v1.2.3 From 11c7842d41c82eb3551a0606ccba89ac33318b62 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Tue, 7 Jul 2020 23:45:08 +0800 Subject: soc: mediatek: cmdq: add write_s_mask function add write_s_mask function in cmdq helper functions which writes value contains in internal register to address with mask and large dma access support. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1594136714-11650-4-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + include/linux/soc/mediatek/mtk-cmdq.h | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 1f76cfedb16d..90d1d8e64412 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -61,6 +61,7 @@ enum cmdq_code { CMDQ_CODE_WFE = 0x20, CMDQ_CODE_EOC = 0x40, CMDQ_CODE_WRITE_S = 0x90, + CMDQ_CODE_WRITE_S_MASK = 0x91, CMDQ_CODE_LOGIC = 0xa0, }; diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 9b0c57a0063d..53230341bf94 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -121,6 +121,24 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, u16 addr_low, u16 src_reg_idx); +/** + * cmdq_pkt_write_s_mask() - append write_s with mask command to the CMDQ packet + * @pkt: the CMDQ packet + * @high_addr_reg_idx: internal register ID which contains high address of pa + * @addr_low: low address of pa + * @src_reg_idx: the CMDQ internal register ID which cache source value + * @mask: the specified target address mask, use U32_MAX if no need + * + * Return: 0 for success; else the error code is returned + * + * Support write value to physical address without subsys. Use CMDQ_ADDR_HIGH() + * to get high address and call cmdq_pkt_assign() to assign value into internal + * reg. Also use CMDQ_ADDR_LOW() to get low address for addr_low parameter when + * call to this function. + */ +int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 src_reg_idx, u32 mask); + /** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet -- cgit v1.2.3 From d3b04aab06fbc33ddea15725f3ff1667c9717929 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Tue, 7 Jul 2020 23:45:09 +0800 Subject: soc: mediatek: cmdq: add read_s function Add read_s function in cmdq helper functions which support read value from register or dma physical address into gce internal register. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1594136714-11650-5-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + include/linux/soc/mediatek/mtk-cmdq.h | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 90d1d8e64412..efbd8a9eb2d1 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -60,6 +60,7 @@ enum cmdq_code { CMDQ_CODE_JUMP = 0x10, CMDQ_CODE_WFE = 0x20, CMDQ_CODE_EOC = 0x40, + CMDQ_CODE_READ_S = 0x80, CMDQ_CODE_WRITE_S = 0x90, CMDQ_CODE_WRITE_S_MASK = 0x91, CMDQ_CODE_LOGIC = 0xa0, diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 53230341bf94..cd7ec714344e 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -104,6 +104,18 @@ int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value); int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value, u32 mask); +/* + * cmdq_pkt_read_s() - append read_s command to the CMDQ packet + * @pkt: the CMDQ packet + * @high_addr_reg_idx: internal register ID which contains high address of pa + * @addr_low: low address of pa + * @reg_idx: the CMDQ internal register ID to cache read data + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_read_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, u16 addr_low, + u16 reg_idx); + /** * cmdq_pkt_write_s() - append write_s command to the CMDQ packet * @pkt: the CMDQ packet -- cgit v1.2.3 From 1af43fce813ebd74c76d080beb261603bd0853e1 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Tue, 7 Jul 2020 23:45:10 +0800 Subject: soc: mediatek: cmdq: add write_s value function add write_s function in cmdq helper functions which writes a constant value to address with large dma access support. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1594136714-11650-6-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index cd7ec714344e..ae73e10da274 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -151,6 +151,19 @@ int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, u16 addr_low, u16 src_reg_idx, u32 mask); +/** + * cmdq_pkt_write_s_value() - append write_s command to the CMDQ packet which + * write value to a physical address + * @pkt: the CMDQ packet + * @high_addr_reg_idx: internal register ID which contains high address of pa + * @addr_low: low address of pa + * @value: the specified target value + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, + u16 addr_low, u32 value); + /** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet -- cgit v1.2.3 From 88a2ffc48d5bc85119ef7961df12369dcd53b4d2 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Tue, 7 Jul 2020 23:45:11 +0800 Subject: soc: mediatek: cmdq: add write_s_mask value function add write_s_mask_value function in cmdq helper functions which writes a constant value to address with mask and large dma access support. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1594136714-11650-7-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index ae73e10da274..d9390d76ee14 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -164,6 +164,21 @@ int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, u16 addr_low, u32 value); +/** + * cmdq_pkt_write_s_mask_value() - append write_s command with mask to the CMDQ + * packet which write value to a physical + * address + * @pkt: the CMDQ packet + * @high_addr_reg_idx: internal register ID which contains high address of pa + * @addr_low: low address of pa + * @value: the specified target value + * @mask: the specified target mask + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, + u16 addr_low, u32 value, u32 mask); + /** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet -- cgit v1.2.3 From 946f1792d3d7942acfbc6afa9a733f608f4622d6 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Tue, 7 Jul 2020 23:45:12 +0800 Subject: soc: mediatek: cmdq: add jump function Add jump function so that client can jump to any address which contains instruction. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1594136714-11650-8-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index d9390d76ee14..34354e952f60 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -252,6 +252,17 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, */ int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value); +/** + * cmdq_pkt_jump() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread PC to + * a physical address which should contains more instruction. + * @pkt: the CMDQ packet + * @addr: physical address of target instruction buffer + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr); + /** * cmdq_pkt_finalize() - Append EOC and jump command to pkt. * @pkt: the CMDQ packet -- cgit v1.2.3 From 23c22299cd290409c6b78f57c42b64f8dfb6dd92 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Tue, 7 Jul 2020 23:45:13 +0800 Subject: soc: mediatek: cmdq: add clear option in cmdq_pkt_wfe api Add clear parameter to let client decide if event should be clear to 0 after GCE receive it. Signed-off-by: Dennis YC Hsieh Acked-by: Chun-Kuang Hu Link: https://lore.kernel.org/r/1594136714-11650-9-git-send-email-dennis-yc.hsieh@mediatek.com [mb: fix commit message] Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 3 +-- include/linux/soc/mediatek/mtk-cmdq.h | 5 +++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index efbd8a9eb2d1..d5a983d65f05 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -28,8 +28,7 @@ * bit 16-27: update value * bit 31: 1 - update, 0 - no update */ -#define CMDQ_WFE_OPTION (CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | \ - CMDQ_WFE_WAIT_VALUE) +#define CMDQ_WFE_OPTION (CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE) /** cmdq event maximum */ #define CMDQ_MAX_EVENT 0x3ff diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 34354e952f60..960704d75994 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -182,11 +182,12 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, /** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet - * @event: the desired event type to "wait and CLEAR" + * @event: the desired event type to wait + * @clear: clear event or not after event arrive * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event); +int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear); /** * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet -- cgit v1.2.3 From ea0c80d1764449acf2f70fdb25aec33800cd0348 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Thu, 24 Sep 2020 15:17:49 +0800 Subject: genirq: Add stub for set_handle_irq() when !GENERIC_IRQ_MULTI_HANDLER In order to avoid compilation errors when a driver references set_handle_irq(), but that the architecture doesn't select GENERIC_IRQ_MULTI_HANDLER, add a stub function that will just WARN_ON_ONCE() if ever used. Signed-off-by: Zhen Lei [maz: commit message] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20200924071754.4509-2-thunder.leizhen@huawei.com --- include/linux/irq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 1b7f4dfee35b..b167baef88c0 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1252,6 +1252,12 @@ int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)); * top-level IRQ handler. */ extern void (*handle_arch_irq)(struct pt_regs *) __ro_after_init; +#else +#define set_handle_irq(handle_irq) \ + do { \ + (void)handle_irq; \ + WARN_ON(1); \ + } while (0) #endif #endif /* _LINUX_IRQ_H */ -- cgit v1.2.3 From 576d0703a81217f04e3a29ce3403231062ef2877 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 06:51:38 +0200 Subject: compat.h: fix a spelling error in There is no compat_sys_readv64v2 syscall, only a compat_sys_preadv64v2 one. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index d38c4d7e83bd..790be5ffc12c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -812,7 +812,7 @@ asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 -asmlinkage long compat_sys_readv64v2(unsigned long fd, +asmlinkage long compat_sys_preadv64v2(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif -- cgit v1.2.3 From 7d1eb2d8f05014a4970df4aeed8c096bfb5e1dcd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20P=C5=91cze?= Date: Fri, 25 Sep 2020 09:37:47 +0000 Subject: ACPI: battery: include linux/power_supply.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit acpi/battery.h uses 'struct power_supply *', but fails to include/create any declaration of the type. Include linux/ power_supply.h to fix that. Signed-off-by: Barnabás Pőcze [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- include/acpi/battery.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/acpi/battery.h b/include/acpi/battery.h index 5d8f5d910c82..b8d56b702c7a 100644 --- a/include/acpi/battery.h +++ b/include/acpi/battery.h @@ -2,6 +2,8 @@ #ifndef __ACPI_BATTERY_H #define __ACPI_BATTERY_H +#include + #define ACPI_BATTERY_CLASS "battery" #define ACPI_BATTERY_NOTIFY_STATUS 0x80 -- cgit v1.2.3 From f19425641cb2572a33cb074d5e30283720bd4d22 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 6 Aug 2020 11:17:12 -0700 Subject: Bluetooth: L2CAP: Fix calling sk_filter on non-socket based channel Only sockets will have the chan->data set to an actual sk, channels like A2MP would have its own data which would likely cause a crash when calling sk_filter, in order to fix this a new callback has been introduced so channels can implement their own filtering if necessary. Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 8f1e6a7a2df8..1d1232917de7 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -665,6 +665,8 @@ struct l2cap_ops { struct sk_buff *(*alloc_skb) (struct l2cap_chan *chan, unsigned long hdr_len, unsigned long len, int nb); + int (*filter) (struct l2cap_chan * chan, + struct sk_buff *skb); }; struct l2cap_conn { -- cgit v1.2.3 From 1df8f55a37bd286a3d40192980050bc3d7d78887 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:03:50 -0700 Subject: bpf: Enable bpf_skc_to_* sock casting helper to networking prog type There is a constant need to add more fields into the bpf_tcp_sock for the bpf programs running at tc, sock_ops...etc. A current workaround could be to use bpf_probe_read_kernel(). However, other than making another helper call for reading each field and missing CO-RE, it is also not as intuitive to use as directly reading "tp->lsndtime" for example. While already having perfmon cap to do bpf_probe_read_kernel(), it will be much easier if the bpf prog can directly read from the tcp_sock. This patch tries to do that by using the existing casting-helpers bpf_skc_to_*() whose func_proto returns a btf_id. For example, the func_proto of bpf_skc_to_tcp_sock returns the btf_id of the kernel "struct tcp_sock". These helpers are also added to is_ptr_cast_function(). It ensures the returning reg (BPF_REF_0) will also carries the ref_obj_id. That will keep the ref-tracking works properly. The bpf_skc_to_* helpers are made available to most of the bpf prog types in filter.c. The bpf_skc_to_* helpers will be limited by perfmon cap. This patch adds a ARG_PTR_TO_BTF_ID_SOCK_COMMON. The helper accepting this arg can accept a btf-id-ptr (PTR_TO_BTF_ID + &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON]) or a legacy-ctx-convert-skc-ptr (PTR_TO_SOCK_COMMON). The bpf_skc_to_*() helpers are changed to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will accept pointer obtained from skb->sk. Instead of specifying both arg_type and arg_btf_id in the same func_proto which is how the current ARG_PTR_TO_BTF_ID does, the arg_btf_id of the new ARG_PTR_TO_BTF_ID_SOCK_COMMON is specified in the compatible_reg_types[] in verifier.c. The reason is the arg_btf_id is always the same. Discussion in this thread: https://lore.kernel.org/bpf/20200922070422.1917351-1-kafai@fb.com/ The ARG_PTR_TO_BTF_ID_ part gives a clear expectation that the helper is expecting a PTR_TO_BTF_ID which could be NULL. This is the same behavior as the existing helper taking ARG_PTR_TO_BTF_ID. The _SOCK_COMMON part means the helper is also expecting the legacy SOCK_COMMON pointer. By excluding the _OR_NULL part, the bpf prog cannot call helper with a literal NULL which doesn't make sense in most cases. e.g. bpf_skc_to_tcp_sock(NULL) will be rejected. All PTR_TO_*_OR_NULL reg has to do a NULL check first before passing into the helper or else the bpf prog will be rejected. This behavior is nothing new and consistent with the current expectation during bpf-prog-load. [ ARG_PTR_TO_BTF_ID_SOCK_COMMON will be used to replace ARG_PTR_TO_SOCK* of other existing helpers later such that those existing helpers can take the PTR_TO_BTF_ID returned by the bpf_skc_to_*() helpers. The only special case is bpf_sk_lookup_assign() which can accept a literal NULL ptr. It has to be handled specially in another follow up patch if there is a need (e.g. by renaming ARG_PTR_TO_SOCKET_OR_NULL to ARG_PTR_TO_BTF_ID_SOCK_COMMON_OR_NULL). ] [ When converting the older helpers that take ARG_PTR_TO_SOCK* in the later patch, if the kernel does not support BTF, ARG_PTR_TO_BTF_ID_SOCK_COMMON will behave like ARG_PTR_TO_SOCK_COMMON because no reg->type could have PTR_TO_BTF_ID in this case. It is not a concern for the newer-btf-only helper like the bpf_skc_to_*() here though because these helpers must require BTF vmlinux to begin with. ] Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200925000350.3855720-1-kafai@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fc5c901c7542..d0937f1d2980 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -292,6 +292,7 @@ enum bpf_arg_type { ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ + ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ __BPF_ARG_TYPE_MAX, }; -- cgit v1.2.3 From a5fa25adf03d4b063aece74ba70ccbb3a71af122 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:03:56 -0700 Subject: bpf: Change bpf_sk_release and bpf_sk_*cgroup_id to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON The previous patch allows the networking bpf prog to use the bpf_skc_to_*() helpers to get a PTR_TO_BTF_ID socket pointer, e.g. "struct tcp_sock *". It allows the bpf prog to read all the fields of the tcp_sock. This patch changes the bpf_sk_release() and bpf_sk_*cgroup_id() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. For example, the following will work: sk = bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); if (!sk) return; tp = bpf_skc_to_tcp_sock(sk); if (!tp) { bpf_sk_release(sk); return; } lsndtime = tp->lsndtime; /* Pass tp to bpf_sk_release() will also work */ bpf_sk_release(tp); Since PTR_TO_BTF_ID could be NULL, the helper taking ARG_PTR_TO_BTF_ID_SOCK_COMMON has to check for NULL at runtime. A btf_id of "struct sock" may not always mean a fullsock. Regardless the helper's running context may get a non-fullsock or not, considering fullsock check/handling is pretty cheap, it is better to keep the same verifier expectation on helper that takes ARG_PTR_TO_BTF_ID* will be able to handle the minisock situation. In the bpf_sk_*cgroup_id() case, it will try to get a fullsock by using sk_to_full_sk() as its skb variant bpf_sk"b"_*cgroup_id() has already been doing. bpf_sk_release can already handle minisock, so nothing special has to be done. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200925000356.3856047-1-kafai@fb.com --- include/uapi/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a22812561064..c96a56d9c3be 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2512,7 +2512,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * long bpf_sk_release(struct bpf_sock *sock) + * long bpf_sk_release(void *sock) * Description * Release the reference held by *sock*. *sock* must be a * non-**NULL** pointer that was returned from @@ -3234,11 +3234,11 @@ union bpf_attr { * * **-EOVERFLOW** if an overflow happened: The same object will be tried again. * - * u64 bpf_sk_cgroup_id(struct bpf_sock *sk) + * u64 bpf_sk_cgroup_id(void *sk) * Description * Return the cgroup v2 id of the socket *sk*. * - * *sk* must be a non-**NULL** pointer to a full socket, e.g. one + * *sk* must be a non-**NULL** pointer to a socket, e.g. one * returned from **bpf_sk_lookup_xxx**\ (), * **bpf_sk_fullsock**\ (), etc. The format of returned id is * same as in **bpf_skb_cgroup_id**\ (). @@ -3248,7 +3248,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level) + * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level) * Description * Return id of cgroup v2 that is ancestor of cgroup associated * with the *sk* at the *ancestor_level*. The root cgroup is at -- cgit v1.2.3 From 592a3498648af000e93dff2d36229ab11cd8c7f6 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:04:02 -0700 Subject: bpf: Change bpf_sk_storage_*() to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON This patch changes the bpf_sk_storage_*() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. A micro benchmark has been done on a "cgroup_skb/egress" bpf program which does a bpf_sk_storage_get(). It was driven by netperf doing a 4096 connected UDP_STREAM test with 64bytes packet. The stats from "kernel.bpf_stats_enabled" shows no meaningful difference. The sk_storage_get_btf_proto, sk_storage_delete_btf_proto, btf_sk_storage_get_proto, and btf_sk_storage_delete_proto are no longer needed, so they are removed. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20200925000402.3856307-1-kafai@fb.com --- include/net/bpf_sk_storage.h | 2 -- include/uapi/linux/bpf.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 119f4c9c3a9c..3c516dd07caf 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -20,8 +20,6 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; -extern const struct bpf_func_proto sk_storage_get_btf_proto; -extern const struct bpf_func_proto sk_storage_delete_btf_proto; struct bpf_local_storage_elem; struct bpf_sk_storage_diag; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c96a56d9c3be..0ec6dbeb17a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2861,6 +2861,7 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * **-EINVAL** if sk is not a fullsock (e.g. a request_sock). * * long bpf_send_signal(u32 sig) * Description -- cgit v1.2.3 From c0df236e1394970f3503a8fb103de95d000014ca Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:04:09 -0700 Subject: bpf: Change bpf_tcp_*_syncookie to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON This patch changes the bpf_tcp_*_syncookie() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20200925000409.3856725-1-kafai@fb.com --- include/uapi/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0ec6dbeb17a5..69b9e30375bc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2692,7 +2692,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Check whether *iph* and *th* contain a valid SYN cookie ACK for * the listening socket in *sk*. @@ -2878,7 +2878,7 @@ union bpf_attr { * * **-EAGAIN** if bpf program can try again. * - * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Try to issue a SYN cookie for the packet with corresponding * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. -- cgit v1.2.3 From 27e5203bd9c5cc6d54dcac48c3027f3f04522b8b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:04:15 -0700 Subject: bpf: Change bpf_sk_assign to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON This patch changes the bpf_sk_assign() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. The bpf_sk_lookup_assign() is taking ARG_PTR_TO_SOCKET_"OR_NULL". Meaning it specifically takes a literal NULL. ARG_PTR_TO_BTF_ID_SOCK_COMMON does not allow a literal NULL, so another ARG type is required for this purpose and another follow-up patch can be used if there is such need. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200925000415.3857374-1-kafai@fb.com --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 69b9e30375bc..2d6519a2ed77 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3107,7 +3107,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This * description applies to **BPF_PROG_TYPE_SCHED_CLS** and -- cgit v1.2.3 From 6277e374b0b07c1a93c829f0a27e38739b3b7a1b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 24 Sep 2020 13:52:24 +0200 Subject: efi: Add definition of EFI_MEMORY_CPU_CRYPTO and ability to report it Incorporate the definition of EFI_MEMORY_CPU_CRYPTO from the UEFI specification v2.8, and wire it into our memory map dumping routine as well. To make a bit of space in the output buffer, which is provided by the various callers, shorten the descriptive names of the memory types. Reviewed-by: Laszlo Ersek Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 73db1ae04cef..f216c029a77b 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -122,6 +122,7 @@ typedef struct { ((u64)0x0000000000010000ULL) /* higher reliability */ #define EFI_MEMORY_RO ((u64)0x0000000000020000ULL) /* read-only */ #define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ +#define EFI_MEMORY_CPU_CRYPTO ((u64)0x0000000000080000ULL) /* supports encryption */ #define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */ #define EFI_MEMORY_DESCRIPTOR_VERSION 1 -- cgit v1.2.3 From 403217f30418c808600e3e8e345413ba5cc15676 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Mon, 17 Aug 2020 12:53:06 -0400 Subject: SUNRPC/NFSD: Implement xdr_reserve_space_vec() Reserving space for a large READ payload requires special handling when reserving space in the xdr buffer pages. One problem we can have is use of the scratch buffer, which is used to get a pointer to a contiguous region of data up to PAGE_SIZE. When using the scratch buffer, calls to xdr_commit_encode() shift the data to it's proper alignment in the xdr buffer. If we've reserved several pages in a vector, then this could potentially invalidate earlier pointers and result in incorrect READ data being sent to the client. I get around this by looking at the amount of space left in the current page, and never reserve more than that for each entry in the read vector. This lets us place data directly where it needs to go in the buffer pages. Signed-off-by: Anna Schumaker Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 5a6a81b7cd9f..6613d96a3029 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -234,6 +234,8 @@ typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); +extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, + size_t nbytes); extern void xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); -- cgit v1.2.3 From afbe7973173a7ce0a68af8b33e44c967582297be Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 24 Sep 2020 12:30:20 -0400 Subject: tracepoints: Add helper to test if tracepoint is enabled in a header As tracepoints are discouraged from being added in a header because it can cause side effects if other tracepoints are in headers, as well as bloat the kernel as the trace_() function is not a small inline, the common workaround is to add a function call that calls a wrapper function in a C file that then calls the tracepoint. But as function calls add overhead, this function should only be called when the tracepoint in question is enabled. To get around this overhead, a static_branch can be used to only have the tracepoint wrapper get called when the tracepoint is enabled. Add a tracepoint_enabled(tp) macro that gets passed the name of the tracepoint, and this becomes a static_branch that is enabled when the tracepoint is enabled and is a nop when the tracepoint is disabled. Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint-defs.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index b29950a19205..60625973faaf 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -48,4 +48,38 @@ struct bpf_raw_event_map { u32 writable_size; } __aligned(32); +/* + * If a tracepoint needs to be called from a header file, it is not + * recommended to call it directly, as tracepoints in header files + * may cause side-effects and bloat the kernel. Instead, use + * tracepoint_enabled() to test if the tracepoint is enabled, then if + * it is, call a wrapper function defined in a C file that will then + * call the tracepoint. + * + * For "trace_foo_bar()", you would need to create a wrapper function + * in a C file to call trace_foo_bar(): + * void do_trace_foo_bar(args) { trace_foo_bar(args); } + * Then in the header file, declare the tracepoint: + * DECLARE_TRACEPOINT(foo_bar); + * And call your wrapper: + * static inline void some_inlined_function() { + * [..] + * if (tracepoint_enabled(foo_bar)) + * do_trace_foo_bar(args); + * [..] + * } + * + * Note: tracepoint_enabled(foo_bar) is equivalent to trace_foo_bar_enabled() + * but is safe to have in headers, where trace_foo_bar_enabled() is not. + */ +#define DECLARE_TRACEPOINT(tp) \ + extern struct tracepoint __tracepoint_##tp + +#ifdef CONFIG_TRACEPOINTS +# define tracepoint_enabled(tp) \ + static_key_false(&(__tracepoint_##tp).key) +#else +# define tracepoint_enabled(tracepoint) false +#endif + #endif -- cgit v1.2.3 From c65fc2276f0f022f5ad4a84658add2b28cff7227 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 24 Sep 2020 12:43:46 -0400 Subject: mm/page_ref: Convert the open coded tracepoint enabled to the new helper As more use cases of checking if a tracepoint is enabled in a header are coming to fruition, a helper macro, tracepoint_enabled(), has been added to check if a tracepoint is enabled or not, and can be used with minimal header requirements (avoid "include hell"). Convert the page_ref logic over to the new helper macro. Cc: Joonsoo Kim Cc: Michal Nazarewicz Cc: Vlastimil Babka Cc: Minchan Kim Cc: Mel Gorman Cc: "Kirill A. Shutemov" Cc: Sergey Senozhatsky Cc: Arnd Bergmann Signed-off-by: Steven Rostedt (VMware) --- include/linux/page_ref.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index d27701199a4d..f3318f34fc54 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -7,13 +7,13 @@ #include #include -extern struct tracepoint __tracepoint_page_ref_set; -extern struct tracepoint __tracepoint_page_ref_mod; -extern struct tracepoint __tracepoint_page_ref_mod_and_test; -extern struct tracepoint __tracepoint_page_ref_mod_and_return; -extern struct tracepoint __tracepoint_page_ref_mod_unless; -extern struct tracepoint __tracepoint_page_ref_freeze; -extern struct tracepoint __tracepoint_page_ref_unfreeze; +DECLARE_TRACEPOINT(page_ref_set); +DECLARE_TRACEPOINT(page_ref_mod); +DECLARE_TRACEPOINT(page_ref_mod_and_test); +DECLARE_TRACEPOINT(page_ref_mod_and_return); +DECLARE_TRACEPOINT(page_ref_mod_unless); +DECLARE_TRACEPOINT(page_ref_freeze); +DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF @@ -24,7 +24,7 @@ extern struct tracepoint __tracepoint_page_ref_unfreeze; * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ -#define page_ref_tracepoint_active(t) static_key_false(&(t).key) +#define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); @@ -75,7 +75,7 @@ static inline int page_count(struct page *page) static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); - if (page_ref_tracepoint_active(__tracepoint_page_ref_set)) + if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } @@ -91,14 +91,14 @@ static inline void init_page_count(struct page *page) static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } @@ -106,7 +106,7 @@ static inline int page_ref_sub_return(struct page *page, int nr) { int ret = atomic_sub_return(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -nr, ret); return ret; } @@ -114,14 +114,14 @@ static inline int page_ref_sub_return(struct page *page, int nr) static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } @@ -129,7 +129,7 @@ static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) + if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } @@ -138,7 +138,7 @@ static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } @@ -147,7 +147,7 @@ static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) + if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } @@ -156,7 +156,7 @@ static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } @@ -165,7 +165,7 @@ static inline int page_ref_add_unless(struct page *page, int nr, int u) { int ret = atomic_add_unless(&page->_refcount, nr, u); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless)) + if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } @@ -174,7 +174,7 @@ static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); - if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze)) + if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } @@ -185,7 +185,7 @@ static inline void page_ref_unfreeze(struct page *page, int count) VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); - if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) + if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } -- cgit v1.2.3 From e0f9956a3862b32ad73869a8e52a33c84aafa46f Mon Sep 17 00:00:00 2001 From: "Chuah, Kim Tatt" Date: Fri, 25 Sep 2020 17:40:41 +0800 Subject: net: stmmac: Add option for VLAN filter fail queue enable Add option in plat_stmmacenet_data struct to enable VLAN Filter Fail Queuing. This option allows packets that fail VLAN filter to be routed to a specific Rx queue when Receive All is also set. When this option is enabled: - Enable VFFQ only when entering promiscuous mode, because Receive All will pass up all rx packets that failed address filtering (similar to promiscuous mode). - VLAN-promiscuous mode is never entered to allow rx packet to fail VLAN filters and get routed to selected VFFQ Rx queue. Reviewed-by: Voon Weifeng Reviewed-by: Ong Boon Leong Signed-off-by: Chuah, Kim Tatt Signed-off-by: Ong Boon Leong Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index bd964c31d333..00e83c877496 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -198,5 +198,7 @@ struct plat_stmmacenet_data { int mac_port_sel_speed; bool en_tx_lpi_clockgating; int has_xgmac; + bool vlan_fail_q_en; + u8 vlan_fail_q; }; #endif -- cgit v1.2.3 From ba5f4cfeac77fca981b199ec7f2396a3616e5216 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 24 Sep 2020 12:58:40 -0700 Subject: bpf: Add comment to document BTF type PTR_TO_BTF_ID_OR_NULL The meaning of PTR_TO_BTF_ID_OR_NULL differs slightly from other types denoted with the *_OR_NULL type. For example the types PTR_TO_SOCKET and PTR_TO_SOCKET_OR_NULL can be used for branch analysis because the type PTR_TO_SOCKET is guaranteed to _not_ have a null value. In contrast PTR_TO_BTF_ID and BTF_TO_BTF_ID_OR_NULL have slightly different meanings. A PTR_TO_BTF_TO_ID may be a pointer to NULL value, but it is safe to read this pointer in the program context because the program context will handle any faults. The fallout is for PTR_TO_BTF_ID the verifier can assume reads are safe, but can not use the type in branch analysis. Additionally, authors need to be extra careful when passing PTR_TO_BTF_ID into helpers. In general helpers consuming type PTR_TO_BTF_ID will need to assume it may be null. Seeing the above is not obvious to readers without the back knowledge lets add a comment in the type definition. Editorial comment, as networking and tracing programs get closer and more tightly merged we may need to consider a new type that we can ensure is non-null for branch analysis and also passing into helpers. Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Acked-by: Lorenz Bauer --- include/linux/bpf.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d0937f1d2980..79902325bef8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -383,8 +383,22 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ - PTR_TO_BTF_ID, /* reg points to kernel struct */ - PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ + /* PTR_TO_BTF_ID points to a kernel struct that does not need + * to be null checked by the BPF program. This does not imply the + * pointer is _not_ null and in practice this can easily be a null + * pointer when reading pointer chains. The assumption is program + * context will handle null pointer dereference typically via fault + * handling. The verifier must keep this in mind and can make no + * assumptions about null or non-null when doing branch analysis. + * Further, when passed into helpers the helpers can not, without + * additional context, assume the value is non-null. + */ + PTR_TO_BTF_ID, + /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not + * been checked for null. Used primarily to inform the verifier + * an explicit null check is required for this struct. + */ + PTR_TO_BTF_ID_OR_NULL, PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ -- cgit v1.2.3 From 22ec3d232f8511b21355fcdb6fb2a4eced3decd8 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 25 Sep 2020 13:46:05 -0700 Subject: devlink: check flash_update parameter support in net core When implementing .flash_update, drivers which do not support per-component update are manually checking the component parameter to verify that it is NULL. Without this check, the driver might accept an update request with a component specified even though it will not honor such a request. Instead of having each driver check this, move the logic into net/core/devlink.c, and use a new `supported_flash_update_params` field in the devlink_ops. Drivers which will support per-component update must now specify this by setting DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT in the supported_flash_update_params in their devlink_ops. This helps ensure that drivers do not forget to check for a NULL component if they do not support per-component update. This also enables a slightly better error message by enabling the core stack to set the netlink bad attribute message to indicate precisely the unsupported attribute in the message. Going forward, any new additional parameter to flash update will require a bit in the supported_flash_update_params bitfield. Signed-off-by: Jacob Keller Reviewed-by: Jakub Kicinski Cc: Jiri Pirko Cc: Jonathan Corbet Cc: Michael Chan Cc: Bin Luo Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: Ido Schimmel Cc: Danielle Ratson Cc: Shannon Nelson Signed-off-by: David S. Miller --- include/net/devlink.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 4883dbae7faf..cec6b4f109fa 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -550,6 +550,8 @@ enum devlink_param_generic_id { /* Firmware bundle identifier */ #define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID "fw.bundle_id" +#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT BIT(0) + struct devlink_region; struct devlink_info_req; @@ -1037,6 +1039,12 @@ enum devlink_trap_group_generic_id { } struct devlink_ops { + /** + * @supported_flash_update_params: + * mask of parameters supported by the driver's .flash_update + * implemementation. + */ + u32 supported_flash_update_params; int (*reload_down)(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack); int (*reload_up)(struct devlink *devlink, @@ -1097,6 +1105,13 @@ struct devlink_ops { struct netlink_ext_ack *extack); int (*info_get)(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack); + /** + * @flash_update: Device flash update function + * + * Used to perform a flash update for the device. The set of + * parameters supported by the driver should be set in + * supported_flash_update_params. + */ int (*flash_update)(struct devlink *devlink, const char *file_name, const char *component, struct netlink_ext_ack *extack); -- cgit v1.2.3 From bc75c054f04048517e0b153ab38d973bbcdcef59 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 25 Sep 2020 13:46:06 -0700 Subject: devlink: convert flash_update to use params structure The devlink core recently gained support for checking whether the driver supports a flash_update parameter, via `supported_flash_update_params`. However, parameters are specified as function arguments. Adding a new parameter still requires modifying the signature of the .flash_update callback in all drivers. Convert the .flash_update function to take a new `struct devlink_flash_update_params` instead. By using this structure, and the `supported_flash_update_params` bit field, a new parameter to flash_update can be added without requiring modification to existing drivers. As before, all parameters except file_name will require driver opt-in. Because file_name is a necessary field to for the flash_update to make sense, no "SUPPORTED" bitflag is provided and it is always considered valid. All future additional parameters will require a new bit in the supported_flash_update_params bitfield. Signed-off-by: Jacob Keller Reviewed-by: Jakub Kicinski Cc: Jiri Pirko Cc: Jakub Kicinski Cc: Jonathan Corbet Cc: Michael Chan Cc: Bin Luo Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: Ido Schimmel Cc: Danielle Ratson Signed-off-by: David S. Miller --- include/net/devlink.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index cec6b4f109fa..7794e1601772 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -550,6 +550,20 @@ enum devlink_param_generic_id { /* Firmware bundle identifier */ #define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID "fw.bundle_id" +/** + * struct devlink_flash_update_params - Flash Update parameters + * @file_name: the name of the flash firmware file to update from + * @component: the flash component to update + * + * With the exception of file_name, drivers must opt-in to parameters by + * setting the appropriate bit in the supported_flash_update_params field in + * their devlink_ops structure. + */ +struct devlink_flash_update_params { + const char *file_name; + const char *component; +}; + #define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT BIT(0) struct devlink_region; @@ -1112,8 +1126,8 @@ struct devlink_ops { * parameters supported by the driver should be set in * supported_flash_update_params. */ - int (*flash_update)(struct devlink *devlink, const char *file_name, - const char *component, + int (*flash_update)(struct devlink *devlink, + struct devlink_flash_update_params *params, struct netlink_ext_ack *extack); /** * @trap_init: Trap initialization function. -- cgit v1.2.3 From 5d5b4128c4caae34ddcd9b2dc30ac4d6155617a3 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 25 Sep 2020 13:46:07 -0700 Subject: devlink: introduce flash update overwrite mask Sections of device flash may contain settings or device identifying information. When performing a flash update, it is generally expected that these settings and identifiers are not overwritten. However, it may sometimes be useful to allow overwriting these fields when performing a flash update. Some examples include, 1) customizing the initial device config on first programming, such as overwriting default device identifying information, or 2) reverting a device configuration to known good state provided in the new firmware image, or 3) in case it is suspected that current firmware logic for managing the preservation of fields during an update is broken. Although some devices are able to completely separate these types of settings and fields into separate components, this is not true for all hardware. To support controlling this behavior, a new DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK is defined. This is an nla_bitfield32 which will define what subset of fields in a component should be overwritten during an update. If no bits are specified, or of the overwrite mask is not provided, then an update should not overwrite anything, and should maintain the settings and identifiers as they are in the previous image. If the overwrite mask has the DEVLINK_FLASH_OVERWRITE_SETTINGS bit set, then the device should be configured to overwrite any of the settings in the requested component with settings found in the provided image. Similarly, if the DEVLINK_FLASH_OVERWRITE_IDENTIFIERS bit is set, the device should be configured to overwrite any device identifiers in the requested component with the identifiers from the image. Multiple overwrite modes may be combined to indicate that a combination of the set of fields that should be overwritten. Drivers which support the new overwrite mask must set the DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK in the supported_flash_update_params field of their devlink_ops. Signed-off-by: Jacob Keller Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/devlink.h | 4 +++- include/uapi/linux/devlink.h | 23 +++++++++++++++++++++++ 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7794e1601772..7339bf9ba6b4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -562,9 +562,11 @@ enum devlink_param_generic_id { struct devlink_flash_update_params { const char *file_name; const char *component; + u32 overwrite_mask; }; -#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT BIT(0) +#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT BIT(0) +#define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1) struct devlink_region; struct devlink_info_req; diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index a2ecc8b00611..7b0face1bad5 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -230,6 +230,28 @@ enum { DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1 }; +/* Specify what sections of a flash component can be overwritten when + * performing an update. Overwriting of firmware binary sections is always + * implicitly assumed to be allowed. + * + * Each section must be documented in + * Documentation/networking/devlink/devlink-flash.rst + * + */ +enum { + DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT, + DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT, + + __DEVLINK_FLASH_OVERWRITE_MAX_BIT, + DEVLINK_FLASH_OVERWRITE_MAX_BIT = __DEVLINK_FLASH_OVERWRITE_MAX_BIT - 1 +}; + +#define DEVLINK_FLASH_OVERWRITE_SETTINGS _BITUL(DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT) +#define DEVLINK_FLASH_OVERWRITE_IDENTIFIERS _BITUL(DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT) + +#define DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS \ + (_BITUL(__DEVLINK_FLASH_OVERWRITE_MAX_BIT) - 1) + /** * enum devlink_trap_action - Packet trap action. * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not @@ -464,6 +486,7 @@ enum devlink_attr { DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, /* u32 */ DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, /* u64 */ + DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, /* bitfield32 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From b38c73ca1c213bbf8a872b334a6bb835becfaba5 Mon Sep 17 00:00:00 2001 From: Dafna Hirschfeld Date: Thu, 27 Aug 2020 21:46:08 +0200 Subject: media: v4l2: add support for colorspace conversion API (CSC) for video capture For video capture it is the driver that reports the colorspace, transfer function, Y'CbCr/HSV encoding and quantization range used by the video, and there is no way to request something different, even though many HDTV receivers have some sort of colorspace conversion capabilities. For output video this feature already exists since the application specifies this information for the video format it will send out, and the transmitter will enable any available CSC if a format conversion has to be performed in order to match the capabilities of the sink. For video capture we propose adding new v4l2_pix_format flag: V4L2_PIX_FMT_FLAG_SET_CSC. The flag is set by the application, the driver will interpret the colorspace, xfer_func, ycbcr_enc/hsv_enc and quantization fields as the requested colorspace information and will attempt to do the conversion it supports. Drivers set the flags V4L2_FMT_FLAG_CSC_COLORSPACE, V4L2_FMT_FLAG_CSC_XFER_FUNC, V4L2_FMT_FLAG_CSC_YCBCR_ENC/V4L2_FMT_FLAG_CSC_HSV_ENC, V4L2_FMT_FLAG_CSC_QUANTIZATION, in the flags field of the struct v4l2_fmtdesc during enumeration to indicate that they support colorspace conversion for the respective field. Drivers do not have to actually look at the flags. If the flags are not set, then the fields 'colorspace', 'xfer_func', 'ycbcr_enc/hsv_enc', and 'quantization' are set to the default values by the core, i.e. just pass on the received format without conversion. Signed-off-by: Hans Verkuil Signed-off-by: Philipp Zabel Signed-off-by: Dafna Hirschfeld Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 4769628790da..b2bc83f37024 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -777,6 +777,7 @@ struct v4l2_pix_format { /* Flags */ #define V4L2_PIX_FMT_FLAG_PREMUL_ALPHA 0x00000001 +#define V4L2_PIX_FMT_FLAG_SET_CSC 0x00000002 /* * F O R M A T E N U M E R A T I O N @@ -796,6 +797,11 @@ struct v4l2_fmtdesc { #define V4L2_FMT_FLAG_CONTINUOUS_BYTESTREAM 0x0004 #define V4L2_FMT_FLAG_DYN_RESOLUTION 0x0008 #define V4L2_FMT_FLAG_ENC_CAP_FRAME_INTERVAL 0x0010 +#define V4L2_FMT_FLAG_CSC_COLORSPACE 0x0020 +#define V4L2_FMT_FLAG_CSC_XFER_FUNC 0x0040 +#define V4L2_FMT_FLAG_CSC_YCBCR_ENC 0x0080 +#define V4L2_FMT_FLAG_CSC_HSV_ENC V4L2_FMT_FLAG_CSC_YCBCR_ENC +#define V4L2_FMT_FLAG_CSC_QUANTIZATION 0x0100 /* Frame Size and frame rate enumeration */ /* -- cgit v1.2.3 From 2f491463497ad43bc06968a334747c6b6b20fc74 Mon Sep 17 00:00:00 2001 From: Dafna Hirschfeld Date: Thu, 27 Aug 2020 21:46:09 +0200 Subject: media: vivid: Add support to the CSC API The CSC API (Colorspace conversion) allows userspace to try to configure the colorspace, transfer function, Y'CbCr/HSV encoding and the quantization for capture devices. This patch adds support to the CSC API in vivid. Using the CSC API, userspace is allowed to do the following: - Set the colorspace. - Set the xfer_func. - Set the ycbcr_enc function for YUV formats. - Set the hsv_enc function for HSV formats - Set the quantization for YUV and RGB formats. Signed-off-by: Dafna Hirschfeld Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-common.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index 150ee16ebd81..a3083529b698 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -539,4 +539,33 @@ static inline void v4l2_buffer_set_timestamp(struct v4l2_buffer *buf, buf->timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC; } +static inline bool v4l2_is_colorspace_valid(__u32 colorspace) +{ + return colorspace > V4L2_COLORSPACE_DEFAULT && + colorspace <= V4L2_COLORSPACE_DCI_P3; +} + +static inline bool v4l2_is_xfer_func_valid(__u32 xfer_func) +{ + return xfer_func > V4L2_XFER_FUNC_DEFAULT && + xfer_func <= V4L2_XFER_FUNC_SMPTE2084; +} + +static inline bool v4l2_is_ycbcr_enc_valid(__u8 ycbcr_enc) +{ + return ycbcr_enc > V4L2_YCBCR_ENC_DEFAULT && + ycbcr_enc <= V4L2_YCBCR_ENC_SMPTE240M; +} + +static inline bool v4l2_is_hsv_enc_valid(__u8 hsv_enc) +{ + return hsv_enc == V4L2_HSV_ENC_180 || hsv_enc == V4L2_HSV_ENC_256; +} + +static inline bool v4l2_is_quant_valid(__u8 quantization) +{ + return quantization == V4L2_QUANTIZATION_FULL_RANGE || + quantization == V4L2_QUANTIZATION_LIM_RANGE; +} + #endif /* V4L2_COMMON_H_ */ -- cgit v1.2.3 From 62aacfa9bf93f94f6949338e0c7a2ed4c4bd2c2a Mon Sep 17 00:00:00 2001 From: Dafna Hirschfeld Date: Thu, 27 Aug 2020 21:46:10 +0200 Subject: media: v4l2: extend the CSC API to subdevice. This patch extends the CSC API in video devices to be supported also on sub-devices. The flag V4L2_MBUS_FRAMEFMT_SET_CSC set by the application when calling VIDIOC_SUBDEV_S_FMT ioctl. The flags: V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE, V4L2_SUBDEV_MBUS_CODE_CSC_XFER_FUNC, V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC/V4L2_SUBDEV_MBUS_CODE_CSC_HSV_ENC V4L2_SUBDEV_MBUS_CODE_CSC_QUANTIZATION are set by the driver in the VIDIOC_SUBDEV_ENUM_MBUS_CODE ioctl. New 'flags' fields were added to the structs v4l2_subdev_mbus_code_enum, v4l2_mbus_framefmt which are borrowed from the 'reserved' field The patch also replaces the 'ycbcr_enc' field in 'struct v4l2_mbus_framefmt' with a union that includes 'hsv_enc' Signed-off-by: Dafna Hirschfeld Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-mediabus.h | 15 +++++++++++++-- include/uapi/linux/v4l2-subdev.h | 10 +++++++++- 2 files changed, 22 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h index 123a231001a8..903e67b16711 100644 --- a/include/uapi/linux/v4l2-mediabus.h +++ b/include/uapi/linux/v4l2-mediabus.h @@ -16,6 +16,8 @@ #include #include +#define V4L2_MBUS_FRAMEFMT_SET_CSC 0x0001 + /** * struct v4l2_mbus_framefmt - frame format on the media bus * @width: image width @@ -24,8 +26,11 @@ * @field: used interlacing type (from enum v4l2_field) * @colorspace: colorspace of the data (from enum v4l2_colorspace) * @ycbcr_enc: YCbCr encoding of the data (from enum v4l2_ycbcr_encoding) + * @hsv_enc: HSV encoding of the data (from enum v4l2_hsv_encoding) * @quantization: quantization of the data (from enum v4l2_quantization) * @xfer_func: transfer function of the data (from enum v4l2_xfer_func) + * @flags: flags (V4L2_MBUS_FRAMEFMT_*) + * @reserved: reserved bytes that can be later used */ struct v4l2_mbus_framefmt { __u32 width; @@ -33,10 +38,16 @@ struct v4l2_mbus_framefmt { __u32 code; __u32 field; __u32 colorspace; - __u16 ycbcr_enc; + union { + /* enum v4l2_ycbcr_encoding */ + __u16 ycbcr_enc; + /* enum v4l2_hsv_encoding */ + __u16 hsv_enc; + }; __u16 quantization; __u16 xfer_func; - __u16 reserved[11]; + __u16 flags; + __u16 reserved[10]; }; #ifndef __KERNEL__ diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 5d2a1dab7911..00850b98078a 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -65,19 +65,27 @@ struct v4l2_subdev_crop { __u32 reserved[8]; }; +#define V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE 0x00000001 +#define V4L2_SUBDEV_MBUS_CODE_CSC_XFER_FUNC 0x00000002 +#define V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC 0x00000004 +#define V4L2_SUBDEV_MBUS_CODE_CSC_HSV_ENC V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC +#define V4L2_SUBDEV_MBUS_CODE_CSC_QUANTIZATION 0x00000008 + /** * struct v4l2_subdev_mbus_code_enum - Media bus format enumeration * @pad: pad number, as reported by the media API * @index: format index during enumeration * @code: format code (MEDIA_BUS_FMT_ definitions) * @which: format type (from enum v4l2_subdev_format_whence) + * @flags: flags set by the driver, (V4L2_SUBDEV_MBUS_CODE_*) */ struct v4l2_subdev_mbus_code_enum { __u32 pad; __u32 index; __u32 code; __u32 which; - __u32 reserved[8]; + __u32 flags; + __u32 reserved[7]; }; /** -- cgit v1.2.3 From d3f7b1bb204099f2f7306318896223e8599bb6a2 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 25 Sep 2020 21:19:10 -0700 Subject: mm/gup: fix gup_fast with dynamic page table folding Currently to make sure that every page table entry is read just once gup_fast walks perform READ_ONCE and pass pXd value down to the next gup_pXd_range function by value e.g.: static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) ... pudp = pud_offset(&p4d, addr); This function passes a reference on that local value copy to pXd_offset, and might get the very same pointer in return. This happens when the level is folded (on most arches), and that pointer should not be iterated. On s390 due to the fact that each task might have different 5,4 or 3-level address translation and hence different levels folded the logic is more complex and non-iteratable pointer to a local copy leads to severe problems. Here is an example of what happens with gup_fast on s390, for a task with 3-level paging, crossing a 2 GB pud boundary: // addr = 0x1007ffff000, end = 0x10080001000 static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; // pud_offset returns &p4d itself (a pointer to a value on stack) pudp = pud_offset(&p4d, addr); do { // on second iteratation reading "random" stack value pud_t pud = READ_ONCE(*pudp); // next = 0x10080000000, due to PUD_SIZE/MASK != PGDIR_SIZE/MASK on s390 next = pud_addr_end(addr, end); ... } while (pudp++, addr = next, addr != end); // pudp++ iterating over stack return 1; } This happens since s390 moved to common gup code with commit d1874a0c2805 ("s390/mm: make the pxd_offset functions more robust") and commit 1a42010cdc26 ("s390/mm: convert to the generic get_user_pages_fast code"). s390 tried to mimic static level folding by changing pXd_offset primitives to always calculate top level page table offset in pgd_offset and just return the value passed when pXd_offset has to act as folded. What is crucial for gup_fast and what has been overlooked is that PxD_SIZE/MASK and thus pXd_addr_end should also change correspondingly. And the latter is not possible with dynamic folding. To fix the issue in addition to pXd values pass original pXdp pointers down to gup_pXd_range functions. And introduce pXd_offset_lockless helpers, which take an additional pXd entry value parameter. This has already been discussed in https://lkml.kernel.org/r/20190418100218.0a4afd51@mschwideX1 Fixes: 1a42010cdc26 ("s390/mm: convert to the generic get_user_pages_fast code") Signed-off-by: Vasily Gorbik Signed-off-by: Andrew Morton Reviewed-by: Gerald Schaefer Reviewed-by: Alexander Gordeev Reviewed-by: Jason Gunthorpe Reviewed-by: Mike Rapoport Reviewed-by: John Hubbard Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Dave Hansen Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Jeff Dike Cc: Richard Weinberger Cc: Dave Hansen Cc: Andy Lutomirski Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Arnd Bergmann Cc: Andrey Ryabinin Cc: Heiko Carstens Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: [5.2+] Link: https://lkml.kernel.org/r/patch.git-943f1e5dcff2.your-ad-here.call-01599856292-ext-8676@work.hours Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e8cbc2e795d5..90654cb63e9e 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,6 +1427,16 @@ typedef unsigned int pgtbl_mod_mask; #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif +#ifndef p4d_offset_lockless +#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) +#endif +#ifndef pud_offset_lockless +#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) +#endif +#ifndef pmd_offset_lockless +#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) +#endif + /* * p?d_leaf() - true if this entry is a final mapping to a physical address. * This differs from p?d_huge() by the fact that they are always available (if -- cgit v1.2.3 From c1d0da83358a2316d9be7f229f26126dbaa07468 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Fri, 25 Sep 2020 21:19:28 -0700 Subject: mm: replace memmap_context by meminit_context Patch series "mm: fix memory to node bad links in sysfs", v3. Sometimes, firmware may expose interleaved memory layout like this: Early memory node ranges node 1: [mem 0x0000000000000000-0x000000011fffffff] node 2: [mem 0x0000000120000000-0x000000014fffffff] node 1: [mem 0x0000000150000000-0x00000001ffffffff] node 0: [mem 0x0000000200000000-0x000000048fffffff] node 2: [mem 0x0000000490000000-0x00000007ffffffff] In that case, we can see memory blocks assigned to multiple nodes in sysfs: $ ls -l /sys/devices/system/memory/memory21 total 0 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2 -rw-r--r-- 1 root root 65536 Aug 24 05:27 online -r--r--r-- 1 root root 65536 Aug 24 05:27 phys_device -r--r--r-- 1 root root 65536 Aug 24 05:27 phys_index drwxr-xr-x 2 root root 0 Aug 24 05:27 power -r--r--r-- 1 root root 65536 Aug 24 05:27 removable -rw-r--r-- 1 root root 65536 Aug 24 05:27 state lrwxrwxrwx 1 root root 0 Aug 24 05:25 subsystem -> ../../../../bus/memory -rw-r--r-- 1 root root 65536 Aug 24 05:25 uevent -r--r--r-- 1 root root 65536 Aug 24 05:27 valid_zones The same applies in the node's directory with a memory21 link in both the node1 and node2's directory. This is wrong but doesn't prevent the system to run. However when later, one of these memory blocks is hot-unplugged and then hot-plugged, the system is detecting an inconsistency in the sysfs layout and a BUG_ON() is raised: kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084! LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4 CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25 Call Trace: add_memory_resource+0x23c/0x340 (unreliable) __add_memory+0x5c/0xf0 dlpar_add_lmb+0x1b4/0x500 dlpar_memory+0x1f8/0xb80 handle_dlpar_errorlog+0xc0/0x190 dlpar_store+0x198/0x4a0 kobj_attr_store+0x30/0x50 sysfs_kf_write+0x64/0x90 kernfs_fop_write+0x1b0/0x290 vfs_write+0xe8/0x290 ksys_write+0xdc/0x130 system_call_exception+0x160/0x270 system_call_common+0xf0/0x27c This has been seen on PowerPC LPAR. The root cause of this issue is that when node's memory is registered, the range used can overlap another node's range, thus the memory block is registered to multiple nodes in sysfs. There are two issues here: (a) The sysfs memory and node's layouts are broken due to these multiple links (b) The link errors in link_mem_sections() should not lead to a system panic. To address (a) register_mem_sect_under_node should not rely on the system state to detect whether the link operation is triggered by a hot plug operation or not. This is addressed by the patches 1 and 2 of this series. Issue (b) will be addressed separately. This patch (of 2): The memmap_context enum is used to detect whether a memory operation is due to a hot-add operation or happening at boot time. Make it general to the hotplug operation and rename it as meminit_context. There is no functional change introduced by this patch Suggested-by: David Hildenbrand Signed-off-by: Laurent Dufour Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J . Wysocki" Cc: Nathan Lynch Cc: Scott Cheloha Cc: Tony Luck Cc: Fenghua Yu Cc: Link: https://lkml.kernel.org/r/20200915094143.79181-1-ldufour@linux.ibm.com Link: https://lkml.kernel.org/r/20200915132624.9723-1-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- include/linux/mmzone.h | 11 ++++++++--- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index b2f370f0b420..48614513eb66 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2416,7 +2416,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, - enum memmap_context, struct vmem_altmap *); + enum meminit_context, struct vmem_altmap *); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8379432f4f2f..0f7a4ff4b059 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -824,10 +824,15 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); -enum memmap_context { - MEMMAP_EARLY, - MEMMAP_HOTPLUG, +/* + * Memory initialization context, use to differentiate memory added by + * the platform statically or via memory hotplug interface. + */ +enum meminit_context { + MEMINIT_EARLY, + MEMINIT_HOTPLUG, }; + extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); -- cgit v1.2.3 From f85086f95fa36194eb0db5cd5c12e56801b98523 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Fri, 25 Sep 2020 21:19:31 -0700 Subject: mm: don't rely on system state to detect hot-plug operations In register_mem_sect_under_node() the system_state's value is checked to detect whether the call is made during boot time or during an hot-plug operation. Unfortunately, that check against SYSTEM_BOOTING is wrong because regular memory is registered at SYSTEM_SCHEDULING state. In addition, memory hot-plug operation can be triggered at this system state by the ACPI [1]. So checking against the system state is not enough. The consequence is that on system with interleaved node's ranges like this: Early memory node ranges node 1: [mem 0x0000000000000000-0x000000011fffffff] node 2: [mem 0x0000000120000000-0x000000014fffffff] node 1: [mem 0x0000000150000000-0x00000001ffffffff] node 0: [mem 0x0000000200000000-0x000000048fffffff] node 2: [mem 0x0000000490000000-0x00000007ffffffff] This can be seen on PowerPC LPAR after multiple memory hot-plug and hot-unplug operations are done. At the next reboot the node's memory ranges can be interleaved and since the call to link_mem_sections() is made in topology_init() while the system is in the SYSTEM_SCHEDULING state, the node's id is not checked, and the sections registered to multiple nodes: $ ls -l /sys/devices/system/memory/memory21/node* total 0 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2 In that case, the system is able to boot but if later one of theses memory blocks is hot-unplugged and then hot-plugged, the sysfs inconsistency is detected and this is triggering a BUG_ON(): kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084! Oops: Exception in kernel mode, sig: 5 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4 CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25 Call Trace: add_memory_resource+0x23c/0x340 (unreliable) __add_memory+0x5c/0xf0 dlpar_add_lmb+0x1b4/0x500 dlpar_memory+0x1f8/0xb80 handle_dlpar_errorlog+0xc0/0x190 dlpar_store+0x198/0x4a0 kobj_attr_store+0x30/0x50 sysfs_kf_write+0x64/0x90 kernfs_fop_write+0x1b0/0x290 vfs_write+0xe8/0x290 ksys_write+0xdc/0x130 system_call_exception+0x160/0x270 system_call_common+0xf0/0x27c This patch addresses the root cause by not relying on the system_state value to detect whether the call is due to a hot-plug operation. An extra parameter is added to link_mem_sections() detailing whether the operation is due to a hot-plug operation. [1] According to Oscar Salvador, using this qemu command line, ACPI memory hotplug operations are raised at SYSTEM_SCHEDULING state: $QEMU -enable-kvm -machine pc -smp 4,sockets=4,cores=1,threads=1 -cpu host -monitor pty \ -m size=$MEM,slots=255,maxmem=4294967296k \ -numa node,nodeid=0,cpus=0-3,mem=512 -numa node,nodeid=1,mem=512 \ -object memory-backend-ram,id=memdimm0,size=134217728 -device pc-dimm,node=0,memdev=memdimm0,id=dimm0,slot=0 \ -object memory-backend-ram,id=memdimm1,size=134217728 -device pc-dimm,node=0,memdev=memdimm1,id=dimm1,slot=1 \ -object memory-backend-ram,id=memdimm2,size=134217728 -device pc-dimm,node=0,memdev=memdimm2,id=dimm2,slot=2 \ -object memory-backend-ram,id=memdimm3,size=134217728 -device pc-dimm,node=0,memdev=memdimm3,id=dimm3,slot=3 \ -object memory-backend-ram,id=memdimm4,size=134217728 -device pc-dimm,node=1,memdev=memdimm4,id=dimm4,slot=4 \ -object memory-backend-ram,id=memdimm5,size=134217728 -device pc-dimm,node=1,memdev=memdimm5,id=dimm5,slot=5 \ -object memory-backend-ram,id=memdimm6,size=134217728 -device pc-dimm,node=1,memdev=memdimm6,id=dimm6,slot=6 \ Fixes: 4fbce633910e ("mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range()") Signed-off-by: Laurent Dufour Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Fenghua Yu Cc: Nathan Lynch Cc: Scott Cheloha Cc: Tony Luck Cc: Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds --- include/linux/node.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/node.h b/include/linux/node.h index 4866f32a02d8..014ba3ab2efd 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,11 +99,13 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -extern int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn); +int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else static inline int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn) + unsigned long end_pfn, + enum meminit_context context) { return 0; } @@ -128,7 +130,8 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, start_pfn, end_pfn); + error = link_mem_sections(nid, start_pfn, end_pfn, + MEMINIT_EARLY); } return error; -- cgit v1.2.3 From 2d44b097bbb9d0af0f3b94304fee4b639ab14171 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 26 Sep 2020 22:32:01 +0300 Subject: net: mscc: ocelot: move NPI port configuration to DSA Remove the ocelot_configure_cpu() function, which was in fact bringing up 2 ports: the CPU port module, which both switchdev and DSA have, and the NPI port, which only DSA has. The (non-Ethernet) CPU port module is at a fixed index in the analyzer, whereas the NPI port is selected through the "ethernet" property in the device tree. Therefore, the function to set up an NPI port is DSA-specific, so we move it there, simplifying the ocelot switch library a little bit. Cc: Horatiu Vultur Cc: Alexandre Belloni Cc: UNGLinuxDriver Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 3105bbb6cdcf..349e839c4c18 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -672,9 +672,6 @@ void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, int ocelot_regfields_init(struct ocelot *ocelot, const struct reg_field *const regfields); struct regmap *ocelot_regmap_init(struct ocelot *ocelot, struct resource *res); -void ocelot_configure_cpu(struct ocelot *ocelot, int npi, - enum ocelot_tag_prefix injection, - enum ocelot_tag_prefix extraction); int ocelot_init(struct ocelot *ocelot); void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); -- cgit v1.2.3 From c3975400c8014e39f7f272808377c97c906c8cee Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 26 Sep 2020 22:32:02 +0300 Subject: net: dsa: allow drivers to request promiscuous mode on master Currently DSA assumes that taggers don't mess with the destination MAC address of the frames on RX. That is not always the case. Some DSA headers are placed before the Ethernet header (ocelot), and others simply mangle random bytes from the destination MAC address (sja1105 with its incl_srcpt option). Currently the DSA master goes to promiscuous mode automatically when the slave devices go too (such as when enslaved to a bridge), but in standalone mode this is a problem that needs to be dealt with. So give drivers the possibility to signal that their tagging protocol will get randomly dropped otherwise, and let DSA deal with fixing that. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index d16057c5987a..46019edc32cb 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -84,6 +84,12 @@ struct dsa_device_ops { unsigned int overhead; const char *name; enum dsa_tag_protocol proto; + /* Some tagging protocols either mangle or shift the destination MAC + * address, in which case the DSA master would drop packets on ingress + * if what it understands out of the destination MAC address is not in + * its RX filter. + */ + bool promisc_on_master; }; /* This structure defines the control interfaces that are overlayed by the -- cgit v1.2.3 From 5124197ce58b5706bb60c2ecb3b79f4dfabab6e1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 26 Sep 2020 22:32:04 +0300 Subject: net: dsa: tag_ocelot: use a short prefix on both ingress and egress There are 2 goals that we follow: - Reduce the header size - Make the header size equal between RX and TX The issue that required long prefix on RX was the fact that the ocelot DSA tag, being put before Ethernet as it is, would overlap with the area that a DSA master uses for RX filtering (destination MAC address mainly). Now that we can ask DSA to put the master in promiscuous mode, in theory we could remove the prefix altogether and call it a day, but it looks like we can't. Using no prefix on ingress, some packets (such as ICMP) would be received, while others (such as PTP) would not be received. This is because the DSA master we use (enetc) triggers parse errors ("MAC rx frame errors") presumably because it sees Ethernet frames with a bad length. And indeed, when using no prefix, the EtherType (bytes 12-13 of the frame, bits 96-111) falls over the REW_VAL field from the extraction header, aka the PTP timestamp. When turning the short (32-bit) prefix on, the EtherType overlaps with bits 64-79 of the extraction header, which are a reserved area transmitted as zero by the switch. The packets are not dropped by the DSA master with a short prefix. Actually, the frames look like this in tcpdump (below is a PTP frame, with an extra dsa_8021q tag - dadb 0482 - added by a downstream sja1105). 89:0c:a9:f2:01:00 > 88:80:00:0a:00:1d, 802.3, length 0: LLC, \ dsap Unknown (0x10) Individual, ssap ProWay NM (0x0e) Response, \ ctrl 0x0004: Information, send seq 2, rcv seq 0, \ Flags [Response], length 78 0x0000: 8880 000a 001d 890c a9f2 0100 0000 100f ................ 0x0010: 0400 0000 0180 c200 000e 001f 7b63 0248 ............{c.H 0x0020: dadb 0482 88f7 1202 0036 0000 0000 0000 .........6...... 0x0030: 0000 0000 0000 0000 0000 001f 7bff fe63 ............{..c 0x0040: 0248 0001 1f81 0500 0000 0000 0000 0000 .H.............. 0x0050: 0000 0000 0000 0000 0000 0000 ............ So the short prefix is our new default: we've shortened our RX frames by 12 octets, increased TX by 4, and headers are now equal between RX and TX. Note that we still need promiscuous mode for the DSA master to not drop it. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 349e839c4c18..3093385f6147 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -101,6 +101,7 @@ #define OCELOT_TAG_LEN 16 #define OCELOT_SHORT_PREFIX_LEN 4 #define OCELOT_LONG_PREFIX_LEN 16 +#define OCELOT_TOTAL_TAG_LEN (OCELOT_SHORT_PREFIX_LEN + OCELOT_TAG_LEN) #define OCELOT_SPEED_2500 0 #define OCELOT_SPEED_1000 1 -- cgit v1.2.3 From 2e8cb1b3db384382c84cc5f765c821454640aac1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 26 Sep 2020 22:32:05 +0300 Subject: net: dsa: make the .flow_dissect tagger callback return void There is no tagger that returns anything other than zero, so just change the return type appropriately. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 46019edc32cb..98d339311898 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -74,8 +74,8 @@ struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt); - int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, - int *offset); + void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, + int *offset); /* Used to determine which traffic should match the DSA filter in * eth_type_trans, and which, if any, should bypass it and be processed * as regular on the master net device. -- cgit v1.2.3 From 9790cf20a8c4bb8d774797c238fa3643f4336e46 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 26 Sep 2020 22:32:06 +0300 Subject: net: dsa: add a generic procedure for the flow dissector For all DSA formats that don't use tail tags, it looks like behind the obscure number crunching they're all doing the same thing: locating the real EtherType behind the DSA tag. Nonetheless, this is not immediately obvious, so create a generic helper for those DSA taggers that put the header before the EtherType. Another assumption for the generic function is that the DSA tags are of equal length on RX and on TX. Prior to the previous patch, this was not true for ocelot and for gswip. The problem was resolved for ocelot, but for gswip it still remains, so that can't use this helper yet. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 98d339311898..817fab5e2c21 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -711,6 +711,32 @@ static inline bool dsa_can_decode(const struct sk_buff *skb, return false; } +/* All DSA tags that push the EtherType to the right (basically all except tail + * tags, which don't break dissection) can be treated the same from the + * perspective of the flow dissector. + * + * We need to return: + * - offset: the (B - A) difference between: + * A. the position of the real EtherType and + * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes + * after the normal EtherType was supposed to be) + * The offset in bytes is exactly equal to the tagger overhead (and half of + * that, in __be16 shorts). + * + * - proto: the value of the real EtherType. + */ +static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, + __be16 *proto, int *offset) +{ +#if IS_ENABLED(CONFIG_NET_DSA) + const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; + int tag_len = ops->overhead; + + *offset = tag_len; + *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; +#endif +} + #if IS_ENABLED(CONFIG_NET_DSA) static inline int __dsa_netdevice_ops_check(struct net_device *dev) { -- cgit v1.2.3 From 7a6ffe764be35af0527d8cfd047945e8f8797ddf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 26 Sep 2020 22:32:07 +0300 Subject: net: dsa: point out the tail taggers The Marvell 88E6060 uses tag_trailer.c and the KSZ8795, KSZ9477 and KSZ9893 switches also use tail tags. Tell that to the DSA core, since this makes a difference for the flow dissector. Most switches break the parsing of frame headers, but these ones don't, so no flow dissector adjustment needs to be done for them. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 817fab5e2c21..b502a63d196e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -90,6 +90,7 @@ struct dsa_device_ops { * its RX filter. */ bool promisc_on_master; + bool tail_tag; }; /* This structure defines the control interfaces that are overlayed by the -- cgit v1.2.3 From da9aa5d96bfe49e903ce2bc01cfb8a776c2619e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 26 Sep 2020 09:03:57 +0200 Subject: fs: remove vfs_statx_fd vfs_statx_fd is only used to implement vfs_fstat. Remove vfs_statx_fd and just implement vfs_fstat directly. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e019ea2f1347..f100d9f711a3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3163,7 +3163,7 @@ extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); extern int vfs_statx(int, const char __user *, int, struct kstat *, u32); -extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int); +int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { @@ -3181,11 +3181,6 @@ static inline int vfs_fstatat(int dfd, const char __user *filename, return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, stat, STATX_BASIC_STATS); } -static inline int vfs_fstat(int fd, struct kstat *stat) -{ - return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0); -} - extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); -- cgit v1.2.3 From 0b2c6693b4220595e9cff95d829d5d5bc5d544dc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 26 Sep 2020 09:03:58 +0200 Subject: fs: implement vfs_stat and vfs_lstat in terms of vfs_fstatat Go through vfs_fstatat instead of duplicating the *stat to statx mapping three times. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f100d9f711a3..b43c9ad7c3c2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3165,21 +3165,19 @@ extern int iterate_dir(struct file *, struct dir_context *); extern int vfs_statx(int, const char __user *, int, struct kstat *, u32); int vfs_fstat(int fd, struct kstat *stat); -static inline int vfs_stat(const char __user *filename, struct kstat *stat) +static inline int vfs_fstatat(int dfd, const char __user *filename, + struct kstat *stat, int flags) { - return vfs_statx(AT_FDCWD, filename, AT_NO_AUTOMOUNT, + return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, stat, STATX_BASIC_STATS); } -static inline int vfs_lstat(const char __user *name, struct kstat *stat) +static inline int vfs_stat(const char __user *filename, struct kstat *stat) { - return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); + return vfs_fstatat(AT_FDCWD, filename, stat, 0); } -static inline int vfs_fstatat(int dfd, const char __user *filename, - struct kstat *stat, int flags) +static inline int vfs_lstat(const char __user *name, struct kstat *stat) { - return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); + return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); -- cgit v1.2.3 From 09f1bde4017e9c34749da2918b3926799c77bce8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 26 Sep 2020 09:03:59 +0200 Subject: fs: move vfs_fstatat out of line This allows to keep vfs_statx static in fs/stat.c to prepare for the following changes. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b43c9ad7c3c2..1ac68236bc09 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3162,15 +3162,10 @@ extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); -extern int vfs_statx(int, const char __user *, int, struct kstat *, u32); +int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, + int flags); int vfs_fstat(int fd, struct kstat *stat); -static inline int vfs_fstatat(int dfd, const char __user *filename, - struct kstat *stat, int flags) -{ - return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); -} static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); -- cgit v1.2.3 From f2d077ff1b5c17008cff5dc27e7356a694e55462 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 26 Sep 2020 09:04:01 +0200 Subject: fs: remove KSTAT_QUERY_FLAGS KSTAT_QUERY_FLAGS expands to AT_STATX_SYNC_TYPE, which itself already is a mask. Remove the double name, especially given that the prefix is a little confusing vs the normal AT_* flags. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/stat.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/stat.h b/include/linux/stat.h index 56614af83d4a..fff27e603814 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -19,8 +19,6 @@ #include #include -#define KSTAT_QUERY_FLAGS (AT_STATX_SYNC_TYPE) - struct kstat { u32 result_mask; /* What fields the user got */ umode_t mode; -- cgit v1.2.3 From 008cfe4418b3dbda2ff820cdd7b1a5ce458ae444 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 25 Sep 2020 18:25:57 -0400 Subject: mm: Introduce mm_struct.has_pinned (Commit message majorly collected from Jason Gunthorpe) Reduce the chance of false positive from page_maybe_dma_pinned() by keeping track if the mm_struct has ever been used with pin_user_pages(). This allows cases that might drive up the page ref_count to avoid any penalty from handling dma_pinned pages. Future work is planned, to provide a more sophisticated solution, likely to turn it into a real counter. For now, make it atomic_t but use it as a boolean for simplicity. Suggested-by: Jason Gunthorpe Signed-off-by: Peter Xu Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 496c3ff97cce..ed028af3cb19 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -436,6 +436,16 @@ struct mm_struct { */ atomic_t mm_count; + /** + * @has_pinned: Whether this mm has pinned any pages. This can + * be either replaced in the future by @pinned_vm when it + * becomes stable, or grow into a counter on its own. We're + * aggresive on this bit now - even if the pinned pages were + * unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm just for simplicity. + */ + atomic_t has_pinned; + #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif -- cgit v1.2.3 From 7a4830c380f3a8b3425f6383deff58e65b2557b5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 25 Sep 2020 18:25:58 -0400 Subject: mm/fork: Pass new vma pointer into copy_page_range() This prepares for the future work to trigger early cow on pinned pages during fork(). No functional change intended. Signed-off-by: Peter Xu Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 48614513eb66..16b799a0522c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1646,7 +1646,7 @@ struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma); + struct vm_area_struct *vma, struct vm_area_struct *new); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); -- cgit v1.2.3 From e622129569963fa3bab976685443756e5da70da9 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Sun, 27 Sep 2020 16:01:50 +0800 Subject: ptp: add stub function for ptp_get_msgtype() Added the missing stub function for ptp_get_msgtype(). Fixes: 036c508ba95e ("ptp: Add generic ptp message type function") Reported-by: Randy Dunlap Signed-off-by: Yangbo Lu Acked-by: Randy Dunlap # build-tested Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 8437307cca8c..c6487b7ab026 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -134,5 +134,13 @@ static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb, { return NULL; } +static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, + unsigned int type) +{ + /* The return is meaningless. The stub function would not be + * executed since no available header from ptp_parse_header. + */ + return 0; +} #endif #endif /* _PTP_CLASSIFY_H_ */ -- cgit v1.2.3 From c1135c7fd0e95740cd4619ce389f43ffce043140 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Wed, 16 Sep 2020 11:48:09 +0800 Subject: Drivers: hv: vmbus: Introduce types of GPADL This patch introduces two types of GPADL: HV_GPADL_{BUFFER, RING}. The types of GPADL are purely the concept in the guest, IOW the hypervisor treat them as the same. The reason of introducing the types for GPADL is to support guests whose page size is not 4k (the page size of Hyper-V hypervisor). In these guests, both the headers and the data parts of the ringbuffers need to be aligned to the PAGE_SIZE, because 1) some of the ringbuffers will be mapped into userspace and 2) we use "double mapping" mechanism to support fast wrap-around, and "double mapping" relies on ringbuffers being page-aligned. However, the Hyper-V hypervisor only uses 4k (HV_HYP_PAGE_SIZE) headers. Our solution to this is that we always make the headers of ringbuffers take one guest page and when GPADL is established between the guest and hypervisor, the only first 4k of header is used. To handle this special case, we need the types of GPADL to differ different guest memory usage for GPADL. Type enum is introduced along with several general interfaces to describe the differences between normal buffer GPADL and ringbuffer GPADL. Signed-off-by: Boqun Feng Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20200916034817.30282-4-boqun.feng@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 38100e80360a..9c19149c0e1a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -29,6 +29,48 @@ #pragma pack(push, 1) +/* + * Types for GPADL, decides is how GPADL header is created. + * + * It doesn't make much difference between BUFFER and RING if PAGE_SIZE is the + * same as HV_HYP_PAGE_SIZE. + * + * If PAGE_SIZE is bigger than HV_HYP_PAGE_SIZE, the headers of ring buffers + * will be of PAGE_SIZE, however, only the first HV_HYP_PAGE will be put + * into gpadl, therefore the number for HV_HYP_PAGE and the indexes of each + * HV_HYP_PAGE will be different between different types of GPADL, for example + * if PAGE_SIZE is 64K: + * + * BUFFER: + * + * gva: |-- 64k --|-- 64k --| ... | + * gpa: | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k | + * index: 0 1 2 15 16 17 18 .. 31 32 ... + * | | ... | | | ... | ... + * v V V V V V + * gpadl: | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k | ... | + * index: 0 1 2 ... 15 16 17 18 .. 31 32 ... + * + * RING: + * + * | header | data | header | data | + * gva: |-- 64k --|-- 64k --| ... |-- 64k --|-- 64k --| ... | + * gpa: | 4k | .. | 4k | 4k | ... | 4k | ... | 4k | .. | 4k | .. | ... | + * index: 0 1 16 17 18 31 ... n n+1 n+16 ... 2n + * | / / / | / / + * | / / / | / / + * | / / ... / ... | / ... / + * | / / / | / / + * | / / / | / / + * V V V V V V v + * gpadl: | 4k | 4k | ... | ... | 4k | 4k | ... | + * index: 0 1 2 ... 16 ... n-15 n-14 n-13 ... 2n-30 + */ +enum hv_gpadl_type { + HV_GPADL_BUFFER, + HV_GPADL_RING +}; + /* Single-page buffer */ struct hv_page_buffer { u32 len; @@ -111,7 +153,7 @@ struct hv_ring_buffer { } feature_bits; /* Pad it to PAGE_SIZE so that data starts on page boundary */ - u8 reserved2[4028]; + u8 reserved2[PAGE_SIZE - 68]; /* * Ring data starts here + RingDataStartOffset @@ -120,6 +162,10 @@ struct hv_ring_buffer { u8 buffer[]; } __packed; +/* Calculate the proper size of a ringbuffer, it must be page-aligned */ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \ + (payload_sz)) + struct hv_ring_buffer_info { struct hv_ring_buffer *ring_buffer; u32 ring_size; /* Include the shared header */ -- cgit v1.2.3 From bca6b91dfdd4347d8fe0bb97377dda0cacd51d82 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Wed, 16 Sep 2020 11:48:11 +0800 Subject: Drivers: hv: vmbus: Move virt_to_hvpfn() to hyperv header There will be more places other than vmbus where we need to calculate the Hyper-V page PFN from a virtual address, so move virt_to_hvpfn() to hyperv generic header. Signed-off-by: Boqun Feng Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20200916034817.30282-6-boqun.feng@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 9c19149c0e1a..83456dc181a8 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -14,6 +14,7 @@ #include +#include #include #include #include @@ -23,6 +24,7 @@ #include #include #include +#include #define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ @@ -1676,4 +1678,17 @@ struct hyperv_pci_block_ops { extern struct hyperv_pci_block_ops hvpci_block_ops; +static inline unsigned long virt_to_hvpfn(void *addr) +{ + phys_addr_t paddr; + + if (is_vmalloc_addr(addr)) + paddr = page_to_phys(vmalloc_to_page(addr)) + + offset_in_page(addr); + else + paddr = __pa(addr); + + return paddr >> HV_HYP_PAGE_SHIFT; +} + #endif /* _HYPERV_H */ -- cgit v1.2.3 From 106dee08408118c5b50387817e74419436e8b651 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Wed, 16 Sep 2020 11:48:12 +0800 Subject: hv: hyperv.h: Introduce some hvpfn helper functions When a guest communicate with the hypervisor, it must use HV_HYP_PAGE to calculate PFN, so introduce a few hvpfn helper functions as the counterpart of the page helper functions. This is the preparation for supporting guest whose PAGE_SIZE is not 4k. Signed-off-by: Boqun Feng Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20200916034817.30282-7-boqun.feng@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 83456dc181a8..1ce131f29f3b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1691,4 +1691,9 @@ static inline unsigned long virt_to_hvpfn(void *addr) return paddr >> HV_HYP_PAGE_SHIFT; } +#define NR_HV_HYP_PAGES_IN_PAGE (PAGE_SIZE / HV_HYP_PAGE_SIZE) +#define offset_in_hvpage(ptr) ((unsigned long)(ptr) & ~HV_HYP_PAGE_MASK) +#define HVPFN_UP(x) (((x) + HV_HYP_PAGE_SIZE-1) >> HV_HYP_PAGE_SHIFT) +#define page_to_hvpfn(page) (page_to_pfn(page) * NR_HV_HYP_PAGES_IN_PAGE) + #endif /* _HYPERV_H */ -- cgit v1.2.3 From 62c59a8786e6bb75569cee91dab66e9da3ff4b68 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 25 Sep 2020 16:49:51 +0800 Subject: memstick: Skip allocating card when removing host After commit 6827ca573c03 ("memstick: rtsx_usb_ms: Support runtime power management"), removing module rtsx_usb_ms will be stuck. The deadlock is caused by powering on and powering off at the same time, the former one is when memstick_check() is flushed, and the later is called by memstick_remove_host(). Soe let's skip allocating card to prevent this issue. Fixes: 6827ca573c03 ("memstick: rtsx_usb_ms: Support runtime power management") Signed-off-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20200925084952.13220-1-kai.heng.feng@canonical.com Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- include/linux/memstick.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index da4c65f9435f..ebf73d4ee969 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -281,6 +281,7 @@ struct memstick_host { struct memstick_dev *card; unsigned int retries; + bool removing; /* Notify the host that some requests are pending. */ void (*request)(struct memstick_host *host); -- cgit v1.2.3 From f2d10ff4a903813df767a4b56b651a26b938df06 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Sun, 27 Sep 2020 22:15:29 +0100 Subject: kgdb: Honour the kprobe blocklist when setting breakpoints Currently kgdb has absolutely no safety rails in place to discourage or prevent a user from placing a breakpoint in dangerous places such as the debugger's own trap entry/exit and other places where it is not safe to take synchronous traps. Introduce a new config symbol KGDB_HONOUR_BLOCKLIST and modify the default implementation of kgdb_validate_break_address() so that we use the kprobe blocklist to prohibit instrumentation of critical functions if the config symbol is set. The config symbol dependencies are set to ensure that the blocklist will be enabled by default if we enable KGDB and are compiling for an architecture where we HAVE_KPROBES. Suggested-by: Peter Zijlstra Reviewed-by: Douglas Anderson Reviewed-by: Masami Hiramatsu Link: https://lore.kernel.org/r/20200927211531.1380577-2-daniel.thompson@linaro.org Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 477b8b7c908f..0d6cf64c8bb1 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -16,6 +16,7 @@ #include #include #include +#include #ifdef CONFIG_HAVE_ARCH_KGDB #include #endif @@ -335,6 +336,23 @@ extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code, atomic_t *snd_rdy); extern void gdbstub_exit(int status); +/* + * kgdb and kprobes both use the same (kprobe) blocklist (which makes sense + * given they are both typically hooked up to the same trap meaning on most + * architectures one cannot be used to debug the other) + * + * However on architectures where kprobes is not (yet) implemented we permit + * breakpoints everywhere rather than blocking everything by default. + */ +static inline bool kgdb_within_blocklist(unsigned long addr) +{ +#ifdef CONFIG_KGDB_HONOUR_BLOCKLIST + return within_kprobe_blacklist(addr); +#else + return false; +#endif +} + extern int kgdb_single_step; extern atomic_t kgdb_active; #define in_dbg_master() \ -- cgit v1.2.3 From c8cb5b854b40f2ce52ccd032fa19750f4181d5fc Mon Sep 17 00:00:00 2001 From: Tova Mussai Date: Fri, 18 Sep 2020 11:33:13 +0200 Subject: nl80211/cfg80211: support 6 GHz scanning Support 6 GHz scanning, by * a new scan flag to scan for colocated BSSes advertised by (and found) APs on 2.4 & 5 GHz * doing the necessary reduced neighbor report parsing for this, to find them * adding the ability to split the scan request in case the device by itself cannot support this. Also add some necessary bits in mac80211 to not break with these changes. Signed-off-by: Tova Mussai Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20200918113313.232917c93af9.Ida22f0212f9122f47094d81659e879a50434a6a2@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 32 +++++++++++++++++++++++++++++++- include/uapi/linux/nl80211.h | 3 +++ 2 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 10c2cc8f0efc..11eb81676e95 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2095,6 +2095,27 @@ struct cfg80211_scan_info { bool aborted; }; +/** + * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only + * + * @short_bssid: short ssid to scan for + * @bssid: bssid to scan for + * @channel_idx: idx of the channel in the channel array in the scan request + * which the above info relvant to + * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU + * @short_ssid_valid: short_ssid is valid and can be used + * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait + * 20 TUs before starting to send probe requests. + */ +struct cfg80211_scan_6ghz_params { + u32 short_ssid; + u32 channel_idx; + u8 bssid[ETH_ALEN]; + bool unsolicited_probe; + bool short_ssid_valid; + bool psc_no_listen; +}; + /** * struct cfg80211_scan_request - scan request description * @@ -2122,6 +2143,10 @@ struct cfg80211_scan_info { * @mac_addr_mask: MAC address mask used with randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr + * @scan_6ghz: relevant for split scan request only, + * true if this is the second scan request + * @n_6ghz_params: number of 6 GHz params + * @scan_6ghz_params: 6 GHz params * @bssid: BSSID to scan for (most commonly, the wildcard BSSID) */ struct cfg80211_scan_request { @@ -2149,6 +2174,9 @@ struct cfg80211_scan_request { struct cfg80211_scan_info info; bool notified; bool no_cck; + bool scan_6ghz; + u32 n_6ghz_params; + struct cfg80211_scan_6ghz_params *scan_6ghz_params; /* keep last */ struct ieee80211_channel *channels[]; @@ -4217,6 +4245,8 @@ struct cfg80211_ops { /** * enum wiphy_flags - wiphy capability flags * + * @WIPHY_FLAG_SPLIT_SCAN_6GHZ: if set to true, the scan request will be split + * into two, first for legacy bands and second for UHB. * @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this * wiphy at all * @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled @@ -4260,7 +4290,7 @@ struct cfg80211_ops { enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), /* use hole at 1 */ - /* use hole at 2 */ + WIPHY_FLAG_SPLIT_SCAN_6GHZ = BIT(2), WIPHY_FLAG_NETNS_OK = BIT(3), WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), WIPHY_FLAG_4ADDR_AP = BIT(5), diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index bdc90b8dfd24..c74ceaddb909 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -6059,6 +6059,8 @@ enum nl80211_timeout_reason { * @NL80211_SCAN_FLAG_FREQ_KHZ: report scan results with * %NL80211_ATTR_SCAN_FREQ_KHZ. This also means * %NL80211_ATTR_SCAN_FREQUENCIES will not be included. + * @NL80211_SCAN_FLAG_COLOCATED_6GHZ: scan for colocated APs reported by + * 2.4/5 GHz APs */ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, @@ -6075,6 +6077,7 @@ enum nl80211_scan_flags { NL80211_SCAN_FLAG_RANDOM_SN = 1<<11, NL80211_SCAN_FLAG_MIN_PREQ_CONTENT = 1<<12, NL80211_SCAN_FLAG_FREQ_KHZ = 1<<13, + NL80211_SCAN_FLAG_COLOCATED_6GHZ = 1<<14, }; /** -- cgit v1.2.3 From d2b7588a47de8322891de38ec14d15105d66cb1e Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 21 Sep 2020 19:28:04 -0700 Subject: nl80211: support S1G capability overrides in assoc NL80211_ATTR_S1G_CAPABILITY can be passed along with NL80211_ATTR_S1G_CAPABILITY_MASK to NL80211_CMD_ASSOCIATE to indicate S1G capabilities which should override the hardware capabilities in eg. the association request. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200922022818.15855-4-thomas@adapt-ip.com [johannes: always require both attributes together, commit message] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ include/net/cfg80211.h | 3 +++ include/uapi/linux/nl80211.h | 9 +++++++++ 3 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 53fba39d4ba6..f71cffa18176 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2330,6 +2330,8 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) } /* S1G Capabilities Information field */ +#define IEEE80211_S1G_CAPABILITY_LEN 15 + #define S1G_CAP0_S1G_LONG BIT(0) #define S1G_CAP0_SGI_1MHZ BIT(1) #define S1G_CAP0_SGI_2MHZ BIT(2) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 11eb81676e95..bead4b9afeca 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2556,6 +2556,8 @@ enum cfg80211_assoc_req_flags { * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association * Request/Response frame or %NULL if FILS is not used. This field starts * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. + * @s1g_capa: S1G capability override + * @s1g_capa_mask: S1G capability override mask */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -2570,6 +2572,7 @@ struct cfg80211_assoc_request { const u8 *fils_kek; size_t fils_kek_len; const u8 *fils_nonces; + struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c74ceaddb909..05db40b4c56f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2521,6 +2521,12 @@ enum nl80211_commands { * unsolicited broadcast probe response. It is a nested attribute, see * &enum nl80211_unsol_bcast_probe_resp_attributes. * + * @NL80211_ATTR_S1G_CAPABILITY: S1G Capability information element (from + * association request when used with NL80211_CMD_NEW_STATION) + * @NL80211_ATTR_S1G_CAPABILITY_MASK: S1G Capability Information element + * override mask. Used with NL80211_ATTR_S1G_CAPABILITY in + * NL80211_CMD_ASSOCIATE or NL80211_CMD_CONNECT. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3007,6 +3013,9 @@ enum nl80211_attrs { NL80211_ATTR_UNSOL_BCAST_PROBE_RESP, + NL80211_ATTR_S1G_CAPABILITY, + NL80211_ATTR_S1G_CAPABILITY_MASK, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 9eaffe5078ca0808603cdd15c4eaf0106a996f3a Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 21 Sep 2020 19:28:06 -0700 Subject: cfg80211: convert S1G beacon to scan results The S1G beacon is an extension frame as opposed to management frame for the regular beacon. This means we may have to occasionally cast the frame buffer to a different header type. Luckily this isn't too bad as scan results mostly only care about the IEs. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200922022818.15855-6-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f71cffa18176..1ce0b37441b9 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -151,6 +151,9 @@ #define IEEE80211_ANO_NETTYPE_WILD 15 +/* bits unique to S1G beacon */ +#define IEEE80211_S1G_BCN_NEXT_TBTT 0x100 + /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */ #define IEEE80211_CTL_EXT_POLL 0x2000 #define IEEE80211_CTL_EXT_SPR 0x3000 @@ -553,6 +556,28 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON); } +/** + * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT && + * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_next_tbtt_present(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) && + fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT); +} + +/** + * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only + * true for S1G beacons when they're short. + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_is_s1g_short_beacon(__le16 fc) +{ + return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc); +} + /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder @@ -1034,6 +1059,13 @@ struct ieee80211_ext { u8 change_seq; u8 variable[0]; } __packed s1g_beacon; + struct { + u8 sa[ETH_ALEN]; + __le32 timestamp; + u8 change_seq; + u8 next_tbtt[3]; + u8 variable[0]; + } __packed s1g_short_beacon; } u; } __packed __aligned(2); -- cgit v1.2.3 From 80ca25711380c8eabe51eed875ca9432b4f8939e Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 21 Sep 2020 19:28:09 -0700 Subject: cfg80211: handle Association Response from S1G STA The sending STA type is implicit based on beacon or probe response content. If sending STA was an S1G STA, adjust the Information Element location accordingly. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200922022818.15855-9-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 1ce0b37441b9..d0fda8424118 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1100,6 +1100,11 @@ struct ieee80211_mgmt { /* followed by Supported rates */ u8 variable[0]; } __packed assoc_resp, reassoc_resp; + struct { + __le16 capab_info; + __le16 status_code; + u8 variable[0]; + } __packed s1g_assoc_resp, s1g_reassoc_resp; struct { __le16 capab_info; __le16 listen_interval; -- cgit v1.2.3 From 05d109576a36fd498e5db2d905eb50c7dd844b83 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 21 Sep 2020 19:28:10 -0700 Subject: mac80211: encode listen interval for S1G S1G allows listen interval up to 2^14 * 10000 beacon intervals. In order to do this listen interval needs a scaling factor applied to the lower 14 bits. Calculate this and properly encode the listen interval for S1G STAs. See IEEE802.11ah-2016 Table 9-44a for reference. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200922022818.15855-10-thomas@adapt-ip.com [move listen_int_usf into function using it] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d0fda8424118..7b6af47dd279 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2448,6 +2448,13 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) #define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) + +#define LISTEN_INT_USF GENMASK(15, 14) +#define LISTEN_INT_UI GENMASK(13, 0) + +#define IEEE80211_MAX_USF FIELD_MAX(LISTEN_INT_USF) +#define IEEE80211_MAX_UI FIELD_MAX(LISTEN_INT_UI) + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 -- cgit v1.2.3 From 1821f8b36f112be9e3071779da82e14384fc6989 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 21 Sep 2020 19:28:12 -0700 Subject: mac80211: handle S1G low rates S1G doesn't have legacy (sband->bitrates) rates, only MCS. For now, just send a frame at MCS 0 if a low rate is requested. Note we also redefine (since we're out of TX flags) TX_RC_VHT_MCS as TX_RC_S1G_MCS to indicate an S1G MCS. This is probably OK as VHT MCS is not valid on S1G band and vice versa. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200922022818.15855-12-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e90089d104b0..de22524e9270 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -833,6 +833,8 @@ enum mac80211_tx_info_flags { #define IEEE80211_TX_CTL_STBC_SHIFT 23 +#define IEEE80211_TX_RC_S1G_MCS IEEE80211_TX_RC_VHT_MCS + /** * enum mac80211_tx_control_flags - flags to describe transmit control * -- cgit v1.2.3 From 1ae099540e8c7f1ee066b3ad45cc91f582bb1ce8 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 25 Sep 2020 16:34:16 +0200 Subject: KVM: x86: Allow deflecting unknown MSR accesses to user space MSRs are weird. Some of them are normal control registers, such as EFER. Some however are registers that really are model specific, not very interesting to virtualization workloads, and not performance critical. Others again are really just windows into package configuration. Out of these MSRs, only the first category is necessary to implement in kernel space. Rarely accessed MSRs, MSRs that should be fine tunes against certain CPU models and MSRs that contain information on the package level are much better suited for user space to process. However, over time we have accumulated a lot of MSRs that are not the first category, but still handled by in-kernel KVM code. This patch adds a generic interface to handle WRMSR and RDMSR from user space. With this, any future MSR that is part of the latter categories can be handled in user space. Furthermore, it allows us to replace the existing "ignore_msrs" logic with something that applies per-VM rather than on the full system. That way you can run productive VMs in parallel to experimental ones where you don't care about proper MSR handling. Signed-off-by: Alexander Graf Reviewed-by: Jim Mattson Message-Id: <20200925143422.21718-3-graf@amazon.com> Signed-off-by: Paolo Bonzini --- include/trace/events/kvm.h | 2 +- include/uapi/linux/kvm.h | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 9417a34aad08..26cfb0fa8e7e 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -17,7 +17,7 @@ ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL), \ ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\ ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI), \ - ERSN(HYPERV), ERSN(ARM_NISV) + ERSN(HYPERV), ERSN(ARM_NISV), ERSN(X86_RDMSR), ERSN(X86_WRMSR) TRACE_EVENT(kvm_userspace_exit, TP_PROTO(__u32 reason, int errno), diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7d8eced6f459..31292a3cdfc2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -248,6 +248,8 @@ struct kvm_hyperv_exit { #define KVM_EXIT_IOAPIC_EOI 26 #define KVM_EXIT_HYPERV 27 #define KVM_EXIT_ARM_NISV 28 +#define KVM_EXIT_X86_RDMSR 29 +#define KVM_EXIT_X86_WRMSR 30 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -413,6 +415,16 @@ struct kvm_run { __u64 esr_iss; __u64 fault_ipa; } arm_nisv; + /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */ + struct { + __u8 error; /* user -> kernel */ + __u8 pad[7]; +#define KVM_MSR_EXIT_REASON_INVAL (1 << 0) +#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1) + __u32 reason; /* kernel -> user */ + __u32 index; /* kernel -> user */ + __u64 data; /* kernel <-> user */ + } msr; /* Fix the size of the union. */ char padding[256]; }; @@ -1037,6 +1049,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SMALLER_MAXPHYADDR 185 #define KVM_CAP_S390_DIAG318 186 #define KVM_CAP_STEAL_TIME 187 +#define KVM_CAP_X86_USER_SPACE_MSR 188 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 1a155254ff937ac92cf9940d273ea597b2c667a2 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 25 Sep 2020 16:34:21 +0200 Subject: KVM: x86: Introduce MSR filtering It's not desireable to have all MSRs always handled by KVM kernel space. Some MSRs would be useful to handle in user space to either emulate behavior (like uCode updates) or differentiate whether they are valid based on the CPU model. To allow user space to specify which MSRs it wants to see handled by KVM, this patch introduces a new ioctl to push filter rules with bitmaps into KVM. Based on these bitmaps, KVM can then decide whether to reject MSR access. With the addition of KVM_CAP_X86_USER_SPACE_MSR it can also deflect the denied MSR events to user space to operate on. If no filter is populated, MSR handling stays identical to before. Signed-off-by: Alexander Graf Message-Id: <20200925143422.21718-8-graf@amazon.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 31292a3cdfc2..58f43aa1fc21 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -421,6 +421,7 @@ struct kvm_run { __u8 pad[7]; #define KVM_MSR_EXIT_REASON_INVAL (1 << 0) #define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1) +#define KVM_MSR_EXIT_REASON_FILTER (1 << 2) __u32 reason; /* kernel -> user */ __u32 index; /* kernel -> user */ __u64 data; /* kernel <-> user */ @@ -1050,6 +1051,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_DIAG318 186 #define KVM_CAP_STEAL_TIME 187 #define KVM_CAP_X86_USER_SPACE_MSR 188 +#define KVM_CAP_X86_MSR_FILTER 189 #ifdef KVM_CAP_IRQ_ROUTING @@ -1551,6 +1553,9 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) +/* Available with KVM_CAP_X86_MSR_FILTER */ +#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From 1d00ce807efaa0ee3a96de7801be042a06d35873 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 21 Sep 2020 19:28:15 -0700 Subject: mac80211: support S1G association The changes required for associating in S1G are: - apply S1G BSS channel info before assoc - mark all S1G STAs as QoS STAs - include and parse AID request element - handle new Association Response format - don't fail assoc if supported rates element is missing Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200922022818.15855-15-thomas@adapt-ip.com [pass skb to ieee80211_add_aid_request_ie(), remove unused variable 'bss'] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 21 +++++++++++++++++++++ include/net/mac80211.h | 2 ++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7b6af47dd279..f2f56b287aed 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -987,6 +987,25 @@ enum ieee80211_vht_opmode_bits { IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, }; +/** + * enum ieee80211_s1g_chanwidth + * These are defined in IEEE802.11-2016ah Table 10-20 + * as BSS Channel Width + * + * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel + */ +enum ieee80211_s1g_chanwidth { + IEEE80211_S1G_CHANWIDTH_1MHZ = 0, + IEEE80211_S1G_CHANWIDTH_2MHZ = 1, + IEEE80211_S1G_CHANWIDTH_4MHZ = 3, + IEEE80211_S1G_CHANWIDTH_8MHZ = 7, + IEEE80211_S1G_CHANWIDTH_16MHZ = 15, +}; + #define WLAN_SA_QUERY_TR_ID_LEN 2 #define WLAN_MEMBERSHIP_LEN 8 #define WLAN_USER_POSITION_LEN 16 @@ -2854,6 +2873,8 @@ enum ieee80211_eid { WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201, + WLAN_EID_AID_REQUEST = 210, + WLAN_EID_AID_RESPONSE = 211, WLAN_EID_S1G_BCN_COMPAT = 213, WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, WLAN_EID_S1G_CAPABILITIES = 217, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index de22524e9270..72bc877d2c22 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -627,6 +627,7 @@ struct ieee80211_fils_discovery { * @fils_discovery: FILS discovery configuration * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response * interval. + * @s1g: BSS is S1G BSS (affects Association Request format). */ struct ieee80211_bss_conf { const u8 *bssid; @@ -696,6 +697,7 @@ struct ieee80211_bss_conf { struct cfg80211_he_bss_color he_bss_color; struct ieee80211_fils_discovery fils_discovery; u32 unsol_bcast_probe_resp_interval; + bool s1g; }; /** -- cgit v1.2.3 From 58ef7c1b555e0e605da24b76cb2821dd3fcd6bc6 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 21 Sep 2020 19:28:16 -0700 Subject: nl80211: include frequency offset in survey info Recently channels gained a potential frequency offset, so include this in the per-channel survey info. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200922022818.15855-16-thomas@adapt-ip.com [add the offset only if non-zero] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 05db40b4c56f..1e51445f81cd 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4097,6 +4097,7 @@ enum nl80211_user_reg_hint_type { * receiving frames destined to the local BSS * @NL80211_SURVEY_INFO_MAX: highest survey info attribute number * currently defined + * @NL80211_SURVEY_INFO_FREQUENCY_OFFSET: center frequency offset in KHz * @__NL80211_SURVEY_INFO_AFTER_LAST: internal use */ enum nl80211_survey_info { @@ -4112,6 +4113,7 @@ enum nl80211_survey_info { NL80211_SURVEY_INFO_TIME_SCAN, NL80211_SURVEY_INFO_PAD, NL80211_SURVEY_INFO_TIME_BSS_RX, + NL80211_SURVEY_INFO_FREQUENCY_OFFSET, /* keep last */ __NL80211_SURVEY_INFO_AFTER_LAST, -- cgit v1.2.3 From 265a0708339daeb71848169f52b91066cc2984fd Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Tue, 22 Sep 2020 12:19:56 -0700 Subject: mac80211: Support not iterating over not-sdata-in-driver ifaces Allow drivers to request that interface-iterator does NOT iterate over interfaces that are not sdata-in-driver. This will allow us to fix crashes in ath10k (and possibly other drivers). To summarize Johannes' explanation: Consider add interface wlan0 add interface wlan1 iterate active interfaces -> wlan0 wlan1 add interface wlan2 iterate active interfaces -> wlan0 wlan1 wlan2 If you apply this scenario to a restart, which ought to be functionally equivalent to the normal startup, just compressed in time, you're basically saying that today you get add interface wlan0 add interface wlan1 iterate active interfaces -> wlan0 wlan1 wlan2 << problem here add interface wlan2 iterate active interfaces -> wlan0 wlan1 wlan2 which yeah, totally seems wrong. But fixing that to be add interface wlan0 add interface wlan1 iterate active interfaces -> add interface wlan2 iterate active interfaces -> (or maybe -> wlan0 wlan1 wlan2 if the reconfig already completed) This is also at least somewhat wrong, but better to not iterate over something that exists in the driver than iterate over something that does not. Originally the first issue was causing crashes in testing with lots of station vdevs on an ath10k radio, combined with firmware crashing. I ran with a similar patch for years with no obvious bad results, including significant testing with ath9k and ath10k. Signed-off-by: Ben Greear Link: https://lore.kernel.org/r/20200922191957.25257-1-greearb@candelatech.com Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 72bc877d2c22..4747d446179a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5407,11 +5407,15 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw); * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all * interfaces, even if they haven't been re-added to the driver yet. * @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up). + * @IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER: Skip any interfaces where SDATA + * is not in the driver. This may fix crashes during firmware recovery + * for instance. */ enum ieee80211_interface_iteration_flags { IEEE80211_IFACE_ITER_NORMAL = 0, IEEE80211_IFACE_ITER_RESUME_ALL = BIT(0), IEEE80211_IFACE_ITER_ACTIVE = BIT(1), + IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER = BIT(2), }; /** -- cgit v1.2.3 From f5bec330e3010450daeb5cb6a94a4a7c54afa306 Mon Sep 17 00:00:00 2001 From: Rajkumar Manoharan Date: Mon, 28 Sep 2020 00:28:11 -0700 Subject: nl80211: extend support to config spatial reuse parameter set Allow the user to configure below Spatial Reuse Parameter Set element. * Non-SRG OBSS PD Max Offset * SRG BSS Color Bitmap * SRG Partial BSSID Bitmap Signed-off-by: Rajkumar Manoharan Link: https://lore.kernel.org/r/1601278091-20313-2-git-send-email-rmanohar@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 +++++-- include/net/cfg80211.h | 10 ++++++++++ include/uapi/linux/nl80211.h | 11 +++++++++++ 3 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f2f56b287aed..770408b2fdaf 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2350,8 +2350,11 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) } /* HE Spatial Reuse defines */ -#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT 0x4 -#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT 0x8 +#define IEEE80211_HE_SPR_PSR_DISALLOWED BIT(0) +#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED BIT(1) +#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT BIT(2) +#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT BIT(3) +#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED BIT(4) /* * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index bead4b9afeca..aee47f2b5709 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -269,13 +269,23 @@ struct ieee80211_rate { * struct ieee80211_he_obss_pd - AP settings for spatial reuse * * @enable: is the feature enabled. + * @sr_ctrl: The SR Control field of SRP element. + * @non_srg_max_offset: non-SRG maximum tx power offset * @min_offset: minimal tx power offset an associated station shall use * @max_offset: maximum tx power offset an associated station shall use + * @bss_color_bitmap: bitmap that indicates the BSS color values used by + * members of the SRG + * @partial_bssid_bitmap: bitmap that indicates the partial BSSID values + * used by members of the SRG */ struct ieee80211_he_obss_pd { bool enable; + u8 sr_ctrl; + u8 non_srg_max_offset; u8 min_offset; u8 max_offset; + u8 bss_color_bitmap[8]; + u8 partial_bssid_bitmap[8]; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1e51445f81cd..47700a2b9af9 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -6991,6 +6991,13 @@ enum nl80211_peer_measurement_ftm_resp { * * @NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET: the OBSS PD minimum tx power offset. * @NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET: the OBSS PD maximum tx power offset. + * @NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET: the non-SRG OBSS PD maximum + * tx power offset. + * @NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP: bitmap that indicates the BSS color + * values used by members of the SRG. + * @NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP: bitmap that indicates the partial + * BSSID values used by members of the SRG. + * @NL80211_HE_OBSS_PD_ATTR_SR_CTRL: The SR Control field of SRP element. * * @__NL80211_HE_OBSS_PD_ATTR_LAST: Internal * @NL80211_HE_OBSS_PD_ATTR_MAX: highest OBSS PD attribute. @@ -7000,6 +7007,10 @@ enum nl80211_obss_pd_attributes { NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET, NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET, + NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET, + NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP, + NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP, + NL80211_HE_OBSS_PD_ATTR_SR_CTRL, /* keep last */ __NL80211_HE_OBSS_PD_ATTR_LAST, -- cgit v1.2.3 From f5be3a61fdb5dd11ef60173e2783ccf62685f892 Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Tue, 22 Sep 2020 13:53:45 +0800 Subject: arm64: perf: Add support caps under sysfs ARMv8.4-PMU introduces the PMMIR_EL1 registers and some new PMU events, like STALL_SLOT etc, are related to it. Let's add a caps directory to /sys/bus/event_source/devices/armv8_pmuv3_0/ and support slots from PMMIR_EL1 registers in this entry. The user programs can get the slots from sysfs directly. /sys/bus/event_source/devices/armv8_pmuv3_0/caps/slots is exposed under sysfs. Both ARMv8.4-PMU and STALL_SLOT event are implemented, it returns the slots from PMMIR_EL1, otherwise it will return 0. Signed-off-by: Shaokun Zhang Cc: Will Deacon Cc: Mark Rutland Link: https://lore.kernel.org/r/1600754025-53535-1-git-send-email-zhangshaokun@hisilicon.com Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 5b616dde9a4c..505480217cf1 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -73,6 +73,7 @@ enum armpmu_attr_groups { ARMPMU_ATTR_GROUP_COMMON, ARMPMU_ATTR_GROUP_EVENTS, ARMPMU_ATTR_GROUP_FORMATS, + ARMPMU_ATTR_GROUP_CAPS, ARMPMU_NR_ATTR_GROUPS }; @@ -109,6 +110,8 @@ struct arm_pmu { struct notifier_block cpu_pm_nb; /* the attr_groups array must be NULL-terminated */ const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1]; + /* store the PMMIR_EL1 to expose slots */ + u64 reg_pmmir; /* Only to be used by ACPI probing code */ unsigned long acpi_cpuid; -- cgit v1.2.3 From ef24f97daac4d9450c956ab165d8337c2feca0e9 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:57 +0200 Subject: mtd: rawnand: Separate the ECC engine type and the ECC byte placement The use of "syndrome" placement should not be encoded in the ECC engine mode/type. Create a "placement" field in NAND chip and change all occurrences of the NAND_ECC_HW_SYNDROME enumeration to be just NAND_ECC_HW and possibly a placement entry like NAND_ECC_PLACEMENT_INTERLEAVED. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-10-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 6 ++++-- include/linux/platform_data/mtd-davinci.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 10bbfbf4ad7f..cfd75a12f802 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -304,6 +304,7 @@ static const struct nand_ecc_caps __name = { \ /** * struct nand_ecc_ctrl - Control structure for ECC * @mode: ECC mode + * @placement: OOB bytes placement * @algo: ECC algorithm * @steps: number of ECC steps per page * @size: data bytes per ECC step @@ -331,7 +332,7 @@ static const struct nand_ecc_caps __name = { \ * controller and always return contiguous in-band and * out-of-band data even if they're not stored * contiguously on the NAND chip (e.g. - * NAND_ECC_HW_SYNDROME interleaves in-band and + * NAND_ECC_PLACEMENT_INTERLEAVED interleaves in-band and * out-of-band data). * @write_page_raw: function to write a raw page without ECC. This function * should hide the specific layout used by the ECC @@ -339,7 +340,7 @@ static const struct nand_ecc_caps __name = { \ * in-band and out-of-band data. ECC controller is * responsible for doing the appropriate transformations * to adapt to its specific layout (e.g. - * NAND_ECC_HW_SYNDROME interleaves in-band and + * NAND_ECC_PLACEMENT_INTERLEAVED interleaves in-band and * out-of-band data). * @read_page: function to read a page according to the ECC generator * requirements; returns maximum number of bitflips corrected in @@ -356,6 +357,7 @@ static const struct nand_ecc_caps __name = { \ */ struct nand_ecc_ctrl { enum nand_ecc_mode mode; + enum nand_ecc_placement placement; enum nand_ecc_algo algo; int steps; int size; diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index 03e92c71b3fa..6e2b252a4ce6 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -69,6 +69,7 @@ struct davinci_nand_pdata { /* platform_data */ * using it with large page chips. */ enum nand_ecc_mode ecc_mode; + enum nand_ecc_placement ecc_placement; u8 ecc_bits; /* e.g. NAND_BUSWIDTH_16 */ -- cgit v1.2.3 From bace41f80f65dc4ba13c892bac783e7e81847379 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:58 +0200 Subject: mtd: rawnand: Use the new ECC engine type enumeration Mechanical switch from the legacy "mode" enumeration to the new "engine type" enumeration in drivers and board files. The device tree parsing is also updated to return the new enumeration from the old strings. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-11-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 ++-- include/linux/platform_data/mtd-davinci.h | 8 ++++---- include/linux/platform_data/mtd-nand-s3c2410.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index cfd75a12f802..967b616c50df 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -303,7 +303,7 @@ static const struct nand_ecc_caps __name = { \ /** * struct nand_ecc_ctrl - Control structure for ECC - * @mode: ECC mode + * @engine_type: ECC engine type * @placement: OOB bytes placement * @algo: ECC algorithm * @steps: number of ECC steps per page @@ -356,7 +356,7 @@ static const struct nand_ecc_caps __name = { \ * @write_oob: function to write chip OOB data */ struct nand_ecc_ctrl { - enum nand_ecc_mode mode; + enum nand_ecc_engine_type engine_type; enum nand_ecc_placement placement; enum nand_ecc_algo algo; int steps; diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index 6e2b252a4ce6..dd474dd44848 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -60,15 +60,15 @@ struct davinci_nand_pdata { /* platform_data */ struct mtd_partition *parts; unsigned nr_parts; - /* none == NAND_ECC_NONE (strongly *not* advised!!) - * soft == NAND_ECC_SOFT - * else == NAND_ECC_HW, according to ecc_bits + /* none == NAND_ECC_ENGINE_TYPE_NONE (strongly *not* advised!!) + * soft == NAND_ECC_ENGINE_TYPE_SOFT + * else == NAND_ECC_ENGINE_TYPE_ON_HOST, according to ecc_bits * * All DaVinci-family chips support 1-bit hardware ECC. * Newer ones also support 4-bit ECC, but are awkward * using it with large page chips. */ - enum nand_ecc_mode ecc_mode; + enum nand_ecc_engine_type engine_type; enum nand_ecc_placement ecc_placement; u8 ecc_bits; diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index 08675b16f9e1..25390fc3e795 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -49,7 +49,7 @@ struct s3c2410_platform_nand { unsigned int ignore_unset_ecc:1; - enum nand_ecc_mode ecc_mode; + enum nand_ecc_engine_type engine_type; int nr_sets; struct s3c2410_nand_set *sets; -- cgit v1.2.3 From d193792a26c216cb7db3cf12300c9414990fa603 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:51:59 +0200 Subject: mtd: nand: Create a helper to extract the ECC configuration Despite its current name, the eccreq field actually encodes both the NAND requirements and the final ECC configuration. That works fine when using on-die ECC since those 2 concepts match perfectly, but it starts being a problem as soon as we use on-host ECC engines, where we're not guaranteed to have a perfect match. Let's hide the ECC configuration access behind a helper so we can later split those 2 concepts. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-12-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 8cf5bdbea782..9cbb41a5541c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -523,6 +523,16 @@ nanddev_get_memorg(struct nand_device *nand) return &nand->memorg; } +/** + * nanddev_get_ecc_conf() - Extract the ECC configuration from a NAND device + * @nand: NAND device + */ +static inline const struct nand_ecc_props * +nanddev_get_ecc_conf(struct nand_device *nand) +{ + return &nand->eccreq; +} + int nanddev_init(struct nand_device *nand, const struct nand_ops *ops, struct module *owner); void nanddev_cleanup(struct nand_device *nand); -- cgit v1.2.3 From 3316c8e3ad1fcaeefd4ffa93587dd78fb24e8afa Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:52:01 +0200 Subject: mtd: nand: Create helpers to set/extract the ECC requirements Despite its current name, the eccreq field actually encodes both the NAND requirements and the final ECC configuration. That works fine when using on-die ECC since those 2 concepts match perfectly, but it starts being a problem as soon as we use on-host ECC engines, where we're not guaranteed to have a perfect match. Let's hide the ECC requirements access behind helpers so we can later split those 2 concepts. As the structures have not been clarified yet, these helpers access the same internal variable as nanddev_get_ecc_conf() for now. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-14-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9cbb41a5541c..348fb2ad4d90 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -533,6 +533,30 @@ nanddev_get_ecc_conf(struct nand_device *nand) return &nand->eccreq; } +/** + * nanddev_get_ecc_requirements() - Extract the ECC requirements from a NAND + * device + * @nand: NAND device + */ +static inline const struct nand_ecc_props * +nanddev_get_ecc_requirements(struct nand_device *nand) +{ + return &nand->eccreq; +} + +/** + * nanddev_set_ecc_requirements() - Assign the ECC requirements of a NAND + * device + * @nand: NAND device + * @reqs: Requirements + */ +static inline void +nanddev_set_ecc_requirements(struct nand_device *nand, + const struct nand_ecc_props *reqs) +{ + nand->eccreq = *reqs; +} + int nanddev_init(struct nand_device *nand, const struct nand_ops *ops, struct module *owner); void nanddev_cleanup(struct nand_device *nand); -- cgit v1.2.3 From 93ef92f6f42275e3d6070b1c5020bfca0e614fff Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:52:03 +0200 Subject: mtd: nand: Use the new generic ECC object Embed a generic NAND ECC high-level object in the nand_device structure to carry all the ECC engine configuration/data. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-16-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 348fb2ad4d90..697ea2474a7c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -301,7 +301,7 @@ struct nand_ecc { * struct nand_device - NAND device * @mtd: MTD instance attached to the NAND device * @memorg: memory layout - * @eccreq: ECC requirements + * @ecc: NAND ECC object attached to the NAND device * @rowconv: position to row address converter * @bbt: bad block table info * @ops: NAND operations attached to the NAND device @@ -309,8 +309,8 @@ struct nand_ecc { * Generic NAND object. Specialized NAND layers (raw NAND, SPI NAND, OneNAND) * should declare their own NAND object embedding a nand_device struct (that's * how inheritance is done). - * struct_nand_device->memorg and struct_nand_device->eccreq should be filled - * at device detection time to reflect the NAND device + * struct_nand_device->memorg and struct_nand_device->ecc.requirements should + * be filled at device detection time to reflect the NAND device * capabilities/requirements. Once this is done nanddev_init() can be called. * It will take care of converting NAND information into MTD ones, which means * the specialized NAND layers should never manually tweak @@ -319,7 +319,7 @@ struct nand_ecc { struct nand_device { struct mtd_info mtd; struct nand_memory_organization memorg; - struct nand_ecc_props eccreq; + struct nand_ecc ecc; struct nand_row_converter rowconv; struct nand_bbt bbt; const struct nand_ops *ops; @@ -530,7 +530,7 @@ nanddev_get_memorg(struct nand_device *nand) static inline const struct nand_ecc_props * nanddev_get_ecc_conf(struct nand_device *nand) { - return &nand->eccreq; + return &nand->ecc.ctx.conf; } /** @@ -541,7 +541,7 @@ nanddev_get_ecc_conf(struct nand_device *nand) static inline const struct nand_ecc_props * nanddev_get_ecc_requirements(struct nand_device *nand) { - return &nand->eccreq; + return &nand->ecc.requirements; } /** @@ -554,7 +554,7 @@ static inline void nanddev_set_ecc_requirements(struct nand_device *nand, const struct nand_ecc_props *reqs) { - nand->eccreq = *reqs; + nand->ecc.requirements = *reqs; } int nanddev_init(struct nand_device *nand, const struct nand_ops *ops, -- cgit v1.2.3 From 6b61d49a55796dbbc479eeb4465e59fd656c719c Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 18 Sep 2020 19:55:18 +0300 Subject: PM: runtime: Fix timer_expires data type on 32-bit arches Commit 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers") switched PM runtime autosuspend to use hrtimers and all related time accounting in ns, but missed to update the timer_expires data type in struct dev_pm_info to u64. This causes the timer_expires value to be truncated on 32-bit architectures when assignment is done from u64 values: rpm_suspend() |- dev->power.timer_expires = expires; Fix it by changing the timer_expires type to u64. Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers") Signed-off-by: Grygorii Strashko Acked-by: Pavel Machek Acked-by: Vincent Guittot Cc: 5.0+ # 5.0+ [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index a30a4b54df52..47aca6bac1d6 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -590,7 +590,7 @@ struct dev_pm_info { #endif #ifdef CONFIG_PM struct hrtimer suspend_timer; - unsigned long timer_expires; + u64 timer_expires; struct work_struct work; wait_queue_head_t wait_queue; struct wake_irq *wakeirq; -- cgit v1.2.3 From c3d4ed1abecfcfc801199cfadb71f5b80e025d9e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 28 Sep 2020 08:51:08 -0700 Subject: iomap: Allow filesystem to call iomap_dio_complete without i_rwsem This is to avoid the deadlock caused in btrfs because of O_DIRECT | O_DSYNC. Filesystems such as btrfs require i_rwsem while performing sync on a file. iomap_dio_rw() is called under i_rw_sem. This leads to a deadlock because of: iomap_dio_complete() generic_write_sync() btrfs_sync_file() Separate out iomap_dio_complete() from iomap_dio_rw(), so filesystems can call iomap_dio_complete() after unlocking i_rwsem. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Signed-off-by: Goldwyn Rodrigues Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 4d1d3c3469e9..172b3397a1a3 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -13,6 +13,7 @@ struct address_space; struct fiemap_extent_info; struct inode; +struct iomap_dio; struct iomap_writepage_ctx; struct iov_iter; struct kiocb; @@ -258,6 +259,10 @@ struct iomap_dio_ops { ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, bool wait_for_completion); +struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, + const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + bool wait_for_completion); +ssize_t iomap_dio_complete(struct iomap_dio *dio); int iomap_dio_iopoll(struct kiocb *kiocb, bool spin); #ifdef CONFIG_SWAP -- cgit v1.2.3 From 00a0b46c99e26b30ea27c1fb4f4dbdfc6f8b1c49 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 28 Sep 2020 09:00:40 +0900 Subject: ASoC: soc-dai: add mark for snd_soc_dai_startup/shutdown() soc_pcm_open() does rollback when failed (A), but, it is almost same as soc_pcm_close(). static int soc_pcm_open(xxx) { ... if (ret < 0) goto xxx_err; ... return 0; ^ config_err: | ... | rtd_startup_err: (A) ... | component_err: | ... v return ret; } The difference is soc_pcm_close() is for all dai/component/substream, rollback is for succeeded part only. This kind of duplicated code can be a hotbed of bugs, thus, we want to share soc_pcm_close() and rollback. Now, soc_pcm_open/close() are handling => 1) snd_soc_dai_startup/shutdown() 2) snd_soc_link_startup/shutdown() 3) snd_soc_component_module_get/put() 4) snd_soc_component_open/close() 5) pm_runtime_put/get() This patch is for 1) snd_soc_dai_startup/shutdown(). The idea of having bit-flag or counter is not enough for this purpose. For example if one DAI is used for 2xPlaybacks for some reasons, and if 1st Playback was succeeded but 2nd Playback was failed, 2nd Playback rollback doesn't need to call shutdown. But it has succeeded bit-flag or counter via 1st Playback, thus, 2nd Playback rollback will call unneeded shutdown. And 1st Playback's necessary shutdown will not be called, because bit-flag or counter was cleared by wrong 2nd Playback rollback. To avoid such case, this patch marks substream pointer when startup() was succeeded. If rollback needed, it will check rollback flag and marked substream pointer. One note here is that it cares *current* startup() only now. but we might want to check *whole* marked substream in the future. This patch is using macro named "push/pop", so that it can be easily update. Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87lfgubwoc.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown --- include/sound/soc-dai.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 8b693dade9c6..2150bd4c7a05 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -153,7 +153,7 @@ void snd_soc_dai_hw_free(struct snd_soc_dai *dai, int snd_soc_dai_startup(struct snd_soc_dai *dai, struct snd_pcm_substream *substream); void snd_soc_dai_shutdown(struct snd_soc_dai *dai, - struct snd_pcm_substream *substream); + struct snd_pcm_substream *substream, int rollback); snd_pcm_sframes_t snd_soc_dai_delay(struct snd_soc_dai *dai, struct snd_pcm_substream *substream); void snd_soc_dai_suspend(struct snd_soc_dai *dai); @@ -388,6 +388,9 @@ struct snd_soc_dai { struct list_head list; + /* function mark */ + struct snd_pcm_substream *mark_startup; + /* bit field */ unsigned int probed:1; }; -- cgit v1.2.3 From 6064ed73cd2405d13c252b190ac64c03ab40e4b9 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 28 Sep 2020 09:00:57 +0900 Subject: ASoC: soc-link: add mark for snd_soc_link_startup/shutdown() soc_pcm_open() does rollback when failed (A), but, it is almost same as soc_pcm_close(). static int soc_pcm_open(xxx) { ... if (ret < 0) goto xxx_err; ... return 0; ^ config_err: | ... | rtd_startup_err: (A) ... | component_err: | ... v return ret; } The difference is soc_pcm_close() is for all dai/component/substream, rollback is for succeeded part only. This kind of duplicated code can be a hotbed of bugs, thus, we want to share soc_pcm_close() and rollback. Now, soc_pcm_open/close() are handling 1) snd_soc_dai_startup/shutdown() => 2) snd_soc_link_startup/shutdown() 3) snd_soc_component_module_get/put() 4) snd_soc_component_open/close() 5) pm_runtime_put/get() This patch is for 2) snd_soc_link_startup/shutdown(). The idea of having bit-flag or counter is not enough for this purpose. For example if one DAI is used for 2xPlaybacks for some reasons, and if 1st Playback was succeeded but 2nd Playback was failed, 2nd Playback rollback doesn't need to call shutdown. But it has succeeded bit-flag or counter via 1st Playback, thus, 2nd Playback rollback will call unneeded shutdown. And 1st Playback's necessary shutdown will not be called, because bit-flag or counter was cleared by wrong 2nd Playback rollback. To avoid such case, this patch marks substream pointer when startup() was succeeded. If rollback needed, it will check rollback flag and marked substream pointer. One note here is that it cares *current* startup() only now. but we might want to check *whole* marked substream in the future. This patch is using macro named "push/pop", so that it can be easily update. Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87k0webwnv.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown --- include/sound/soc-link.h | 3 ++- include/sound/soc.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-link.h b/include/sound/soc-link.h index 337ac5666757..dac6c0ce6ede 100644 --- a/include/sound/soc-link.h +++ b/include/sound/soc-link.h @@ -14,7 +14,8 @@ int snd_soc_link_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, struct snd_pcm_hw_params *params); int snd_soc_link_startup(struct snd_pcm_substream *substream); -void snd_soc_link_shutdown(struct snd_pcm_substream *substream); +void snd_soc_link_shutdown(struct snd_pcm_substream *substream, + int rollback); int snd_soc_link_prepare(struct snd_pcm_substream *substream); int snd_soc_link_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params); diff --git a/include/sound/soc.h b/include/sound/soc.h index 09a7d8409ade..3b038c563ae1 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1159,6 +1159,9 @@ struct snd_soc_pcm_runtime { unsigned int num; /* 0-based and monotonic increasing */ struct list_head list; /* rtd list of the soc card */ + /* function mark */ + struct snd_pcm_substream *mark_startup; + /* bit field */ unsigned int pop_wait:1; unsigned int fe_compr:1; /* for Dynamic PCM */ -- cgit v1.2.3 From 51aff91ad123e03d1461ec1d980efd1814dca69e Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 28 Sep 2020 09:01:04 +0900 Subject: ASoC: soc-component: add mark for soc_pcm_components_open/close() soc_pcm_open() does rollback when failed (A), but, it is almost same as soc_pcm_close(). static int soc_pcm_open(xxx) { ... if (ret < 0) goto xxx_err; ... return 0; ^ config_err: | ... | rtd_startup_err: (A) ... | component_err: | ... v return ret; } The difference is soc_pcm_close() is for all dai/component/substream, rollback is for succeeded part only. This kind of duplicated code can be a hotbed of bugs, thus, we want to share soc_pcm_close() and rollback. Now, soc_pcm_open/close() are handling 1) snd_soc_dai_startup/shutdown() 2) snd_soc_link_startup/shutdown() => 3) snd_soc_component_module_get/put() => 4) snd_soc_component_open/close() 5) pm_runtime_put/get() This patch is for 3) snd_soc_component_module_get/put() 4) snd_soc_component_open/close(). The idea of having bit-flag or counter is not enough for this purpose. For example if one DAI is used for 2xPlaybacks for some reasons, and if 1st Playback was succeeded but 2nd Playback was failed, 2nd Playback rollback doesn't need to call shutdown. But it has succeeded bit-flag or counter via 1st Playback, thus, 2nd Playback rollback will call unneeded shutdown. And 1st Playback's necessary shutdown will not be called, because bit-flag or counter was cleared by wrong 2nd Playback rollback. To avoid such case, this patch marks substream pointer when open() was succeeded. If rollback needed, it will check rollback flag and marked substream pointer. One note here is that it cares *current* open() only now. but we might want to check *whole* marked substream in the future. This patch is using macro named "push/pop", so that it can be easily update. Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87imbybwno.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown --- include/sound/soc-component.h | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index 089ea9441fd1..a812202ec595 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -217,6 +217,10 @@ struct snd_soc_component { /* machine specific init */ int (*init)(struct snd_soc_component *component); + /* function mark */ + struct snd_pcm_substream *mark_module; + struct snd_pcm_substream *mark_open; + #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_root; const char *debugfs_prefix; @@ -370,17 +374,19 @@ void snd_soc_component_exit_regmap(struct snd_soc_component *component); #endif #define snd_soc_component_module_get_when_probe(component)\ - snd_soc_component_module_get(component, 0) -#define snd_soc_component_module_get_when_open(component) \ - snd_soc_component_module_get(component, 1) + snd_soc_component_module_get(component, NULL, 0) +#define snd_soc_component_module_get_when_open(component, substream) \ + snd_soc_component_module_get(component, substream, 1) int snd_soc_component_module_get(struct snd_soc_component *component, + struct snd_pcm_substream *substream, int upon_open); #define snd_soc_component_module_put_when_remove(component) \ - snd_soc_component_module_put(component, 0) -#define snd_soc_component_module_put_when_close(component) \ - snd_soc_component_module_put(component, 1) + snd_soc_component_module_put(component, NULL, 0, 0) +#define snd_soc_component_module_put_when_close(component, substream, rollback) \ + snd_soc_component_module_put(component, substream, 1, rollback) void snd_soc_component_module_put(struct snd_soc_component *component, - int upon_open); + struct snd_pcm_substream *substream, + int upon_open, int rollback); static inline void snd_soc_component_set_drvdata(struct snd_soc_component *c, void *data) @@ -424,7 +430,8 @@ int snd_soc_component_force_enable_pin_unlocked( int snd_soc_component_open(struct snd_soc_component *component, struct snd_pcm_substream *substream); int snd_soc_component_close(struct snd_soc_component *component, - struct snd_pcm_substream *substream); + struct snd_pcm_substream *substream, + int rollback); void snd_soc_component_suspend(struct snd_soc_component *component); void snd_soc_component_resume(struct snd_soc_component *component); int snd_soc_component_is_suspended(struct snd_soc_component *component); -- cgit v1.2.3 From 939a5cfb2a5609d2d6f996b5cd853397a82a92b9 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 28 Sep 2020 09:01:17 +0900 Subject: ASoC: soc-component: add mark for snd_soc_pcm_component_pm_runtime_get/put() soc_pcm_open() does rollback when failed (A), but, it is almost same as soc_pcm_close(). static int soc_pcm_open(xxx) { ... if (ret < 0) goto xxx_err; ... return 0; ^ config_err: | ... | rtd_startup_err: (A) ... | component_err: | ... v return ret; } The difference is soc_pcm_close() is for all dai/component/substream, rollback is for succeeded part only. This kind of duplicated code can be a hotbed of bugs, thus, we want to share soc_pcm_close() and rollback. Now, soc_pcm_open/close() are handling 1) snd_soc_dai_startup/shutdown() 2) snd_soc_link_startup/shutdown() 3) snd_soc_component_module_get/put() 4) snd_soc_component_open/close() => 5) pm_runtime_put/get() This patch is for 5) pm_runtime_put/get(). The idea of having bit-flag or counter is not enough for this purpose. For example if one DAI is used for 2xPlaybacks for some reasons, and if 1st Playback was succeeded but 2nd Playback was failed, 2nd Playback rollback doesn't need to call shutdown. But it has succeeded bit-flag or counter via 1st Playback, thus, 2nd Playback rollback will call unneeded shutdown. And 1st Playback's necessary shutdown will not be called, because bit-flag or counter was cleared by wrong 2nd Playback rollback. To avoid such case, this patch marks substream pointer when get() was succeeded. If rollback needed, it will check rollback flag and marked substream pointer. One note here is that it cares *current* get() only now. but we might want to check *whole* marked substream in the future. This patch is using macro named "push/pop", so that it can be easily update. Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87h7ribwnb.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown --- include/sound/soc-component.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index a812202ec595..2c790ce95259 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -220,6 +220,7 @@ struct snd_soc_component { /* function mark */ struct snd_pcm_substream *mark_module; struct snd_pcm_substream *mark_open; + void *mark_pm; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_root; @@ -464,5 +465,9 @@ void snd_soc_pcm_component_hw_free(struct snd_pcm_substream *substream, struct snd_soc_component *last); int snd_soc_pcm_component_trigger(struct snd_pcm_substream *substream, int cmd); +int snd_soc_pcm_component_pm_runtime_get(struct snd_soc_pcm_runtime *rtd, + void *stream); +void snd_soc_pcm_component_pm_runtime_put(struct snd_soc_pcm_runtime *rtd, + void *stream, int rollback); #endif /* __SOC_COMPONENT_H */ -- cgit v1.2.3 From b8127113d01e53adba15b41aefd37b90ed83d631 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Mon, 28 Sep 2020 10:34:51 -0600 Subject: coresight: Use IS_ENABLED for CONFIGs that may be modules Checking for ifdef CONFIG_x fails if CONFIG_x=m. Use IS_ENABLED that is true for both built-ins and modules, instead. Required when building coresight components as modules. Cc: Mathieu Poirier Cc: Leo Yan Cc: Alexander Shishkin Cc: Randy Dunlap Cc: Suzuki K Poulose Cc: Greg Kroah-Hartman Cc: Russell King Reviewed-by: Suzuki K Poulose Signed-off-by: Kim Phillips Signed-off-by: Tingwei Zhang Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200928163513.70169-4-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 58fffdecdbfd..3bb738f9a326 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -324,7 +324,7 @@ struct coresight_ops { const struct coresight_ops_ect *ect_ops; }; -#ifdef CONFIG_CORESIGHT +#if IS_ENABLED(CONFIG_CORESIGHT) extern struct coresight_device * coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); -- cgit v1.2.3 From f2ccc7b7bfa91b5cad5a4d57b269f6d7bbafd67d Mon Sep 17 00:00:00 2001 From: Tingwei Zhang Date: Mon, 28 Sep 2020 10:35:07 -0600 Subject: coresight: cti: Don't disable ect device if it's not enabled If associated ect device is not enabled at first place, disable routine should not be called. Add ect_enabled flag to check whether ect device is enabled. Fix the issue in below case. Ect device is not available when associated coresight device enabled and the association is established after coresight device is enabled. Signed-off-by: Mike Leach Signed-off-by: Tingwei Zhang Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200928163513.70169-20-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 3bb738f9a326..7d3c87e5b97c 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -208,6 +208,7 @@ struct coresight_device { /* sysfs links between components */ int nr_links; bool has_conns_grp; + bool ect_enabled; /* true only if associated ect device is enabled */ }; /* -- cgit v1.2.3 From 95e92e45a454a10a8114294d0f7aec930fb85891 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Thu, 24 Sep 2020 12:07:04 +0100 Subject: KVM: arm64: pmu: Make overflow handler NMI safe kvm_vcpu_kick() is not NMI safe. When the overflow handler is called from NMI context, defer waking the vcpu to an irq_work queue. A vcpu can be freed while it's not running by kvm_destroy_vm(). Prevent running the irq_work for a non-existent vcpu by calling irq_work_sync() on the PMU destroy path. [Alexandru E.: Added irq_work_sync()] Signed-off-by: Julien Thierry Signed-off-by: Alexandru Elisei Tested-by: Sumit Garg (Developerbox) Cc: Julien Thierry Cc: Marc Zyngier Cc: Will Deacon Cc: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Suzuki K Pouloze Cc: kvm@vger.kernel.org Cc: kvmarm@lists.cs.columbia.edu Link: https://lore.kernel.org/r/20200924110706.254996-6-alexandru.elisei@arm.com Signed-off-by: Will Deacon --- include/kvm/arm_pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 6db030439e29..dbf4f08d42e5 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -27,6 +27,7 @@ struct kvm_pmu { bool ready; bool created; bool irq_level; + struct irq_work overflow_work; }; #define kvm_arm_pmu_v3_ready(v) ((v)->arch.pmu.ready) -- cgit v1.2.3 From ea470b82f205fc1b0b5276575da519bb7d86db25 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 25 Sep 2020 17:48:55 +0100 Subject: regmap: add support to regmap_field_bulk_alloc/free apis Usage of regmap_field_alloc becomes much overhead when number of fields exceed more than 3. QCOM LPASS driver has extensively converted to use regmap_fields. Using new bulk api to allocate fields makes it much more cleaner code to read! Signed-off-by: Srinivas Kandagatla Tested-by: Srinivasa Rao Mandadapu Link: https://lore.kernel.org/r/20200925164856.10315-2-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- include/linux/regmap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 1970ed59d49f..eafe833f0103 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1150,6 +1150,17 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev, struct regmap *regmap, struct reg_field reg_field); void devm_regmap_field_free(struct device *dev, struct regmap_field *field); +int regmap_field_bulk_alloc(struct regmap *regmap, + struct regmap_field **rm_field, + struct reg_field *reg_field, + int num_fields); +void regmap_field_bulk_free(struct regmap_field *field); +int devm_regmap_field_bulk_alloc(struct device *dev, struct regmap *regmap, + struct regmap_field **field, + struct reg_field *reg_field, int num_fields); +void devm_regmap_field_bulk_free(struct device *dev, + struct regmap_field *field); + int regmap_field_read(struct regmap_field *field, unsigned int *val); int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, -- cgit v1.2.3 From 74cc6d182d038cbba6c6d91beb1b2bab926b618b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 25 Sep 2020 17:56:40 -0700 Subject: udp_tunnel: add the ability to share port tables Unfortunately recent Intel NIC designs share the UDP port table across netdevs. So far the UDP tunnel port state was maintained per netdev, we need to extend that to cater to Intel NICs. Expect NICs to allocate the info structure dynamically and link to the state from there. All the shared NICs will record port offload information in the one instance of the table so we need to make sure that the use count can accommodate larger numbers. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/udp_tunnel.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 94bb7a882250..2ea453dac876 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -200,11 +200,27 @@ enum udp_tunnel_nic_info_flags { UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; +struct udp_tunnel_nic; + +#define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) + +struct udp_tunnel_nic_shared { + struct udp_tunnel_nic *udp_tunnel_nic_info; + + struct list_head devices; +}; + +struct udp_tunnel_nic_shared_node { + struct net_device *dev; + struct list_head list; +}; + /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once + * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table @@ -213,6 +229,12 @@ enum udp_tunnel_nic_info_flags { * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * + * Devices which (misguidedly) share the UDP tunnel port table across multiple + * netdevs should allocate an instance of struct udp_tunnel_nic_shared and + * point @shared at it. + * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices + * sharing a table. + * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, @@ -234,6 +256,8 @@ struct udp_tunnel_nic_info { /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); + struct udp_tunnel_nic_shared *shared; + unsigned int flags; struct udp_tunnel_nic_table_info { -- cgit v1.2.3 From 1b4d60ec162f82ea29a2e7a907b5c6cc9f926321 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 25 Sep 2020 13:54:29 -0700 Subject: bpf: Enable BPF_PROG_TEST_RUN for raw_tracepoint Add .test_run for raw_tracepoint. Also, introduce a new feature that runs the target program on a specific CPU. This is achieved by a new flag in bpf_attr.test, BPF_F_TEST_RUN_ON_CPU. When this flag is set, the program is triggered on cpu with id bpf_attr.test.cpu. This feature is needed for BPF programs that handle perf_event and other percpu resources, as the program can access these resource locally. Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200925205432.1777-2-songliubraving@fb.com --- include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 79902325bef8..db6dcdee7933 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1396,6 +1396,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2d6519a2ed77..82522f05c021 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -424,6 +424,11 @@ enum { */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) +/* Flags for BPF_PROG_TEST_RUN */ + +/* If set, run the test on the cpu specified by bpf_attr.test.cpu */ +#define BPF_F_TEST_RUN_ON_CPU (1U << 0) + /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { /* enabled run_time_ns and run_cnt */ @@ -566,6 +571,8 @@ union bpf_attr { */ __aligned_u64 ctx_in; __aligned_u64 ctx_out; + __u32 flags; + __u32 cpu; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ -- cgit v1.2.3 From 5b2a828b98ec1872799b1b4d82113c76a12d594f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Sep 2020 22:47:21 -0700 Subject: fscrypt: export fscrypt_d_revalidate() Dentries that represent no-key names must have a dentry_operations that includes fscrypt_d_revalidate(). Currently, this is handled by fscrypt_prepare_lookup() installing fscrypt_d_ops. However, ceph support for encryption (https://lore.kernel.org/r/20200914191707.380444-1-jlayton@kernel.org) can't use fscrypt_d_ops, since ceph already has its own dentry_operations. Similarly, ext4 and f2fs support for directories that are both encrypted and casefolded (https://lore.kernel.org/r/20200923010151.69506-1-drosen@google.com) can't use fscrypt_d_ops either, since casefolding requires some dentry operations too. To satisfy both users, we need to move the responsibility of installing the dentry_operations to filesystems. In preparation for this, export fscrypt_d_revalidate() and give it a !CONFIG_FS_ENCRYPTION stub. Reviewed-by: Jeff Layton Link: https://lore.kernel.org/r/20200924054721.187797-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index f1757e73162d..a8f7a43f031b 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -197,6 +197,7 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode, bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len); u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); +int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); /* bio.c */ void fscrypt_decrypt_bio(struct bio *bio); @@ -454,6 +455,12 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir, return 0; } +static inline int fscrypt_d_revalidate(struct dentry *dentry, + unsigned int flags) +{ + return 1; +} + /* bio.c */ static inline void fscrypt_decrypt_bio(struct bio *bio) { -- cgit v1.2.3 From eff7423365a6938d2d34dbce989febed2ae1f957 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 25 Sep 2020 18:13:12 +0000 Subject: net: core: introduce struct netdev_nested_priv for nested interface infrastructure Functions related to nested interface infrastructure such as netdev_walk_all_{ upper | lower }_dev() pass both private functions and "data" pointer to handle their own things. At this point, the data pointer type is void *. In order to make it easier to expand common variables and functions, this new netdev_nested_priv structure is added. In the following patch, a new member variable will be added into this struct to fix the lockdep issue. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7bd4fcdd0738..313803d6c781 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4455,6 +4455,10 @@ extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; +struct netdev_nested_priv { + void *data; +}; + bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); @@ -4470,8 +4474,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); @@ -4508,12 +4512,12 @@ struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); -- cgit v1.2.3 From 1fc70edb7d7b5ce1ae32b0cf90183f4879ad421a Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 25 Sep 2020 18:13:29 +0000 Subject: net: core: add nested_level variable in net_device This patch is to add a new variable 'nested_level' into the net_device structure. This variable will be used as a parameter of spin_lock_nested() of dev->addr_list_lock. netif_addr_lock() can be called recursively so spin_lock_nested() is used instead of spin_lock() and dev->lower_level is used as a parameter of spin_lock_nested(). But, dev->lower_level value can be updated while it is being used. So, lockdep would warn a possible deadlock scenario. When a stacked interface is deleted, netif_{uc | mc}_sync() is called recursively. So, spin_lock_nested() is called recursively too. At this moment, the dev->lower_level variable is used as a parameter of it. dev->lower_level value is updated when interfaces are being unlinked/linked immediately. Thus, After unlinking, dev->lower_level shouldn't be a parameter of spin_lock_nested(). A (macvlan) | B (vlan) | C (bridge) | D (macvlan) | E (vlan) | F (bridge) A->lower_level : 6 B->lower_level : 5 C->lower_level : 4 D->lower_level : 3 E->lower_level : 2 F->lower_level : 1 When an interface 'A' is removed, it releases resources. At this moment, netif_addr_lock() would be called. Then, netdev_upper_dev_unlink() is called recursively. Then dev->lower_level is updated. There is no problem. But, when the bridge module is removed, 'C' and 'F' interfaces are removed at once. If 'F' is removed first, a lower_level value is like below. A->lower_level : 5 B->lower_level : 4 C->lower_level : 3 D->lower_level : 2 E->lower_level : 1 F->lower_level : 1 Then, 'C' is removed. at this moment, netif_addr_lock() is called recursively. The ordering is like this. C(3)->D(2)->E(1)->F(1) At this moment, the lower_level value of 'E' and 'F' are the same. So, lockdep warns a possible deadlock scenario. In order to avoid this problem, a new variable 'nested_level' is added. This value is the same as dev->lower_level - 1. But this value is updated in rtnl_unlock(). So, this variable can be used as a parameter of spin_lock_nested() safely in the rtnl context. Test commands: ip link add br0 type bridge vlan_filtering 1 ip link add vlan1 link br0 type vlan id 10 ip link add macvlan2 link vlan1 type macvlan ip link add br3 type bridge vlan_filtering 1 ip link set macvlan2 master br3 ip link add vlan4 link br3 type vlan id 10 ip link add macvlan5 link vlan4 type macvlan ip link add br6 type bridge vlan_filtering 1 ip link set macvlan5 master br6 ip link add vlan7 link br6 type vlan id 10 ip link add macvlan8 link vlan7 type macvlan ip link set br0 up ip link set vlan1 up ip link set macvlan2 up ip link set br3 up ip link set vlan4 up ip link set macvlan5 up ip link set br6 up ip link set vlan7 up ip link set macvlan8 up modprobe -rv bridge Splat looks like: [ 36.057436][ T744] WARNING: possible recursive locking detected [ 36.058848][ T744] 5.9.0-rc6+ #728 Not tainted [ 36.059959][ T744] -------------------------------------------- [ 36.061391][ T744] ip/744 is trying to acquire lock: [ 36.062590][ T744] ffff8c4767509280 (&vlan_netdev_addr_lock_key){+...}-{2:2}, at: dev_set_rx_mode+0x19/0x30 [ 36.064922][ T744] [ 36.064922][ T744] but task is already holding lock: [ 36.066626][ T744] ffff8c4767769280 (&vlan_netdev_addr_lock_key){+...}-{2:2}, at: dev_uc_add+0x1e/0x60 [ 36.068851][ T744] [ 36.068851][ T744] other info that might help us debug this: [ 36.070731][ T744] Possible unsafe locking scenario: [ 36.070731][ T744] [ 36.072497][ T744] CPU0 [ 36.073238][ T744] ---- [ 36.074007][ T744] lock(&vlan_netdev_addr_lock_key); [ 36.075290][ T744] lock(&vlan_netdev_addr_lock_key); [ 36.076590][ T744] [ 36.076590][ T744] *** DEADLOCK *** [ 36.076590][ T744] [ 36.078515][ T744] May be due to missing lock nesting notation [ 36.078515][ T744] [ 36.080491][ T744] 3 locks held by ip/744: [ 36.081471][ T744] #0: ffffffff98571df0 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x236/0x490 [ 36.083614][ T744] #1: ffff8c4767769280 (&vlan_netdev_addr_lock_key){+...}-{2:2}, at: dev_uc_add+0x1e/0x60 [ 36.085942][ T744] #2: ffff8c476c8da280 (&bridge_netdev_addr_lock_key/4){+...}-{2:2}, at: dev_uc_sync+0x39/0x80 [ 36.088400][ T744] [ 36.088400][ T744] stack backtrace: [ 36.089772][ T744] CPU: 6 PID: 744 Comm: ip Not tainted 5.9.0-rc6+ #728 [ 36.091364][ T744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 36.093630][ T744] Call Trace: [ 36.094416][ T744] dump_stack+0x77/0x9b [ 36.095385][ T744] __lock_acquire+0xbc3/0x1f40 [ 36.096522][ T744] lock_acquire+0xb4/0x3b0 [ 36.097540][ T744] ? dev_set_rx_mode+0x19/0x30 [ 36.098657][ T744] ? rtmsg_ifinfo+0x1f/0x30 [ 36.099711][ T744] ? __dev_notify_flags+0xa5/0xf0 [ 36.100874][ T744] ? rtnl_is_locked+0x11/0x20 [ 36.101967][ T744] ? __dev_set_promiscuity+0x7b/0x1a0 [ 36.103230][ T744] _raw_spin_lock_bh+0x38/0x70 [ 36.104348][ T744] ? dev_set_rx_mode+0x19/0x30 [ 36.105461][ T744] dev_set_rx_mode+0x19/0x30 [ 36.106532][ T744] dev_set_promiscuity+0x36/0x50 [ 36.107692][ T744] __dev_set_promiscuity+0x123/0x1a0 [ 36.108929][ T744] dev_set_promiscuity+0x1e/0x50 [ 36.110093][ T744] br_port_set_promisc+0x1f/0x40 [bridge] [ 36.111415][ T744] br_manage_promisc+0x8b/0xe0 [bridge] [ 36.112728][ T744] __dev_set_promiscuity+0x123/0x1a0 [ 36.113967][ T744] ? __hw_addr_sync_one+0x23/0x50 [ 36.115135][ T744] __dev_set_rx_mode+0x68/0x90 [ 36.116249][ T744] dev_uc_sync+0x70/0x80 [ 36.117244][ T744] dev_uc_add+0x50/0x60 [ 36.118223][ T744] macvlan_open+0x18e/0x1f0 [macvlan] [ 36.119470][ T744] __dev_open+0xd6/0x170 [ 36.120470][ T744] __dev_change_flags+0x181/0x1d0 [ 36.121644][ T744] dev_change_flags+0x23/0x60 [ 36.122741][ T744] do_setlink+0x30a/0x11e0 [ 36.123778][ T744] ? __lock_acquire+0x92c/0x1f40 [ 36.124929][ T744] ? __nla_validate_parse.part.6+0x45/0x8e0 [ 36.126309][ T744] ? __lock_acquire+0x92c/0x1f40 [ 36.127457][ T744] __rtnl_newlink+0x546/0x8e0 [ 36.128560][ T744] ? lock_acquire+0xb4/0x3b0 [ 36.129623][ T744] ? deactivate_slab.isra.85+0x6a1/0x850 [ 36.130946][ T744] ? __lock_acquire+0x92c/0x1f40 [ 36.132102][ T744] ? lock_acquire+0xb4/0x3b0 [ 36.133176][ T744] ? is_bpf_text_address+0x5/0xe0 [ 36.134364][ T744] ? rtnl_newlink+0x2e/0x70 [ 36.135445][ T744] ? rcu_read_lock_sched_held+0x32/0x60 [ 36.136771][ T744] ? kmem_cache_alloc_trace+0x2d8/0x380 [ 36.138070][ T744] ? rtnl_newlink+0x2e/0x70 [ 36.139164][ T744] rtnl_newlink+0x47/0x70 [ ... ] Fixes: 845e0ebb4408 ("net: change addr_list_lock back to static key") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 52 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 44 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 313803d6c781..9fdb3ebef306 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1955,6 +1955,7 @@ struct net_device { unsigned short type; unsigned short hard_header_len; unsigned char min_header_len; + unsigned char name_assign_type; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -1965,21 +1966,28 @@ struct net_device { unsigned char addr_len; unsigned char upper_level; unsigned char lower_level; + unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; spinlock_t addr_list_lock; - unsigned char name_assign_type; - bool uc_promisc; + struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; #ifdef CONFIG_SYSFS struct kset *queues_kset; +#endif +#ifdef CONFIG_LOCKDEP + struct list_head unlink_list; #endif unsigned int promiscuity; unsigned int allmulti; + bool uc_promisc; +#ifdef CONFIG_LOCKDEP + unsigned char nested_level; +#endif /* Protocol-specific pointers */ @@ -4260,17 +4268,23 @@ static inline void netif_tx_disable(struct net_device *dev) static inline void netif_addr_lock(struct net_device *dev) { - spin_lock(&dev->addr_list_lock); -} + unsigned char nest_level = 0; -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - spin_lock_nested(&dev->addr_list_lock, dev->lower_level); +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_lock_bh(struct net_device *dev) { - spin_lock_bh(&dev->addr_list_lock); + unsigned char nest_level = 0; + +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + local_bh_disable(); + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_unlock(struct net_device *dev) @@ -4455,7 +4469,19 @@ extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; +enum { + NESTED_SYNC_IMM_BIT, + NESTED_SYNC_TODO_BIT, +}; + +#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit)) +#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT) + +#define NESTED_SYNC_IMM __NESTED_SYNC(IMM) +#define NESTED_SYNC_TODO __NESTED_SYNC(TODO) + struct netdev_nested_priv { + unsigned char flags; void *data; }; @@ -4465,6 +4491,16 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); +#ifdef CONFIG_LOCKDEP +static LIST_HEAD(net_unlink_list); + +static inline void net_unlink_todo(struct net_device *dev) +{ + if (list_empty(&dev->unlink_list)) + list_add_tail(&dev->unlink_list, &net_unlink_list); +} +#endif + /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ -- cgit v1.2.3 From 201091ebb2a161a0e10aab36186690b332941f6a Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Sat, 26 Sep 2020 12:44:24 +0200 Subject: net/smc: introduce System Enterprise ID (SEID) SMCD version 2 defines a System Enterprise ID (short SEID). This patch contains the SEID creation and adds the callback to retrieve the created SEID. Signed-off-by: Ursula Braun Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- include/net/smc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/smc.h b/include/net/smc.h index 646feb4bc75f..b28b384d0625 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -37,6 +37,8 @@ struct smcd_dmb { #define ISM_EVENT_GID 1 #define ISM_EVENT_SWR 2 +#define ISM_RESERVED_VLANID 0x1FFF + #define ISM_ERROR 0xFFFF struct smcd_event { @@ -63,6 +65,7 @@ struct smcd_ops { int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); + void (*get_system_eid)(struct smcd_dev *dev, u8 **eid); }; struct smcd_dev { -- cgit v1.2.3 From 8caaccf521c160d231587091f1f5e8aef2dd0a5e Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Sat, 26 Sep 2020 12:44:25 +0200 Subject: net/smc: introduce CHID callback for ISM devices With SMCD version 2 the CHIDs of ISM devices are needed for the CLC handshake. This patch provides the new callback to retrieve the CHID of an ISM device. Signed-off-by: Ursula Braun Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- include/net/smc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/smc.h b/include/net/smc.h index b28b384d0625..e441aa97ad61 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -66,6 +66,7 @@ struct smcd_ops { bool sf, unsigned int offset, void *data, unsigned int size); void (*get_system_eid)(struct smcd_dev *dev, u8 **eid); + u16 (*get_chid)(struct smcd_dev *dev); }; struct smcd_dev { -- cgit v1.2.3 From efc68158c429f37d87fd02ee9a26913c78546fc9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 25 Sep 2020 23:25:01 +0200 Subject: bpf: change logging calls from verbose() to bpf_log() and use log pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation for moving code around, change a bunch of references to env->log (and the verbose() logging helper) to use bpf_log() and a direct pointer to struct bpf_verifier_log. While we're touching the function signature, mark the 'prog' argument to bpf_check_type_match() as const. Also enhance the bpf_verifier_log_needed() check to handle NULL pointers for the log struct so we can re-use the code with logging disabled. Acked-by: Andrii Nakryiko Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- include/linux/bpf_verifier.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index db6dcdee7933..5176726f4f03 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1420,7 +1420,7 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); -int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, +int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); struct bpf_prog *bpf_prog_by_id(u32 id); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 2bb48a2c4d08..7bc9276c4ef4 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -347,8 +347,9 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return (log->level && log->ubuf && !bpf_verifier_log_full(log)) || - log->level == BPF_LOG_KERNEL; + return log && + ((log->level && log->ubuf && !bpf_verifier_log_full(log)) || + log->level == BPF_LOG_KERNEL); } #define BPF_MAX_SUBPROGS 256 -- cgit v1.2.3 From f7b12b6fea00988496b7606d4964cd77beef46a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 25 Sep 2020 23:25:02 +0200 Subject: bpf: verifier: refactor check_attach_btf_id() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The check_attach_btf_id() function really does three things: 1. It performs a bunch of checks on the program to ensure that the attachment is valid. 2. It stores a bunch of state about the attachment being requested in the verifier environment and struct bpf_prog objects. 3. It allocates a trampoline for the attachment. This patch splits out (1.) and (3.) into separate functions which will perform the checks, but return the computed values instead of directly modifying the environment. This is done in preparation for reusing the checks when the actual attachment is happening, which will allow tracing programs to have multiple (compatible) attachments. This also fixes a bug where a bunch of checks were skipped if a trampoline already existed for the tracing target. Fixes: 6ba43b761c41 ("bpf: Attachment verification for BPF_MODIFY_RETURN") Fixes: 1e6c62a88215 ("bpf: Introduce sleepable BPF programs") Acked-by: Andrii Nakryiko Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 19 ++++++++++++++----- include/linux/bpf_verifier.h | 13 +++++++++++++ 2 files changed, 27 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5176726f4f03..b89a30764069 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -606,6 +606,13 @@ struct bpf_trampoline { struct bpf_ksym ksym; }; +struct bpf_attach_target_info { + struct btf_func_model fmodel; + long tgt_addr; + const char *tgt_name; + const struct btf_type *tgt_type; +}; + #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ struct bpf_dispatcher_prog { @@ -633,9 +640,10 @@ static __always_inline unsigned int bpf_dispatcher_nop_func( return bpf_func(ctx, insnsi); } #ifdef CONFIG_BPF_JIT -struct bpf_trampoline *bpf_trampoline_lookup(u64 key); int bpf_trampoline_link_prog(struct bpf_prog *prog); int bpf_trampoline_unlink_prog(struct bpf_prog *prog); +struct bpf_trampoline *bpf_trampoline_get(u64 key, + struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ @@ -680,10 +688,6 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); #else -static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) -{ - return NULL; -} static inline int bpf_trampoline_link_prog(struct bpf_prog *prog) { return -ENOTSUPP; @@ -692,6 +696,11 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) { return -ENOTSUPP; } +static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, + struct bpf_attach_target_info *tgt_info) +{ + return ERR_PTR(-EOPNOTSUPP); +} static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7bc9276c4ef4..363b4f1c562a 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -450,4 +450,17 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ctx_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +/* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ +static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, + u32 btf_id) +{ + return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id; +} + +int bpf_check_attach_target(struct bpf_verifier_log *log, + const struct bpf_prog *prog, + const struct bpf_prog *tgt_prog, + u32 btf_id, + struct bpf_attach_target_info *tgt_info); + #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From 76654e67f3a01c50dc13dd6dea75e58943413956 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Mon, 28 Sep 2020 12:31:03 +0100 Subject: bpf: Provide function to get vmlinux BTF information It will be used later for BPF structure display support Signed-off-by: Alan Maguire Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/1601292670-1616-2-git-send-email-alan.maguire@oracle.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b89a30764069..e620a4b1290f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1364,6 +1364,8 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, union bpf_attr __user *uattr); void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); +struct btf *bpf_get_btf_vmlinux(void); + /* Map specifics */ struct xdp_buff; struct sk_buff; -- cgit v1.2.3 From 31d0bc81637d8d974a6dad9827b765b4b70c89d7 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Mon, 28 Sep 2020 12:31:04 +0100 Subject: bpf: Move to generic BTF show support, apply it to seq files/strings generalize the "seq_show" seq file support in btf.c to support a generic show callback of which we support two instances; the current seq file show, and a show with snprintf() behaviour which instead writes the type data to a supplied string. Both classes of show function call btf_type_show() with different targets; the seq file or the string to be written. In the string case we need to track additional data - length left in string to write and length to return that we would have written (a la snprintf). By default show will display type information, field members and their types and values etc, and the information is indented based upon structure depth. Zeroed fields are omitted. Show however supports flags which modify its behaviour: BTF_SHOW_COMPACT - suppress newline/indent. BTF_SHOW_NONAME - suppress show of type and member names. BTF_SHOW_PTR_RAW - do not obfuscate pointer values. BTF_SHOW_UNSAFE - do not copy data to safe buffer before display. BTF_SHOW_ZERO - show zeroed values (by default they are not shown). Signed-off-by: Alan Maguire Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/1601292670-1616-3-git-send-email-alan.maguire@oracle.com --- include/linux/btf.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index a9af5e7a7ece..d0f5d3c9ec3d 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -13,6 +13,7 @@ struct btf; struct btf_member; struct btf_type; union bpf_attr; +struct btf_show; extern const struct file_operations btf_fops; @@ -46,8 +47,43 @@ int btf_get_info_by_fd(const struct btf *btf, const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *type_id, u32 *ret_size); + +/* + * Options to control show behaviour. + * - BTF_SHOW_COMPACT: no formatting around type information + * - BTF_SHOW_NONAME: no struct/union member names/types + * - BTF_SHOW_PTR_RAW: show raw (unobfuscated) pointer values; + * equivalent to %px. + * - BTF_SHOW_ZERO: show zero-valued struct/union members; they + * are not displayed by default + * - BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read + * data before displaying it. + */ +#define BTF_SHOW_COMPACT (1ULL << 0) +#define BTF_SHOW_NONAME (1ULL << 1) +#define BTF_SHOW_PTR_RAW (1ULL << 2) +#define BTF_SHOW_ZERO (1ULL << 3) +#define BTF_SHOW_UNSAFE (1ULL << 4) + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); + +/* + * Copy len bytes of string representation of obj of BTF type_id into buf. + * + * @btf: struct btf object + * @type_id: type id of type obj points to + * @obj: pointer to typed data + * @buf: buffer to write to + * @len: maximum length to write to buf + * @flags: show options (see above) + * + * Return: length that would have been/was copied as per snprintf, or + * negative error. + */ +int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, + char *buf, int len, u64 flags); + int btf_get_fd_by_id(u32 id); u32 btf_id(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, -- cgit v1.2.3 From c4d0bfb45068d853a478b9067a95969b1886a30f Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Mon, 28 Sep 2020 12:31:05 +0100 Subject: bpf: Add bpf_snprintf_btf helper A helper is added to support tracing kernel type information in BPF using the BPF Type Format (BTF). Its signature is long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags); struct btf_ptr * specifies - a pointer to the data to be traced - the BTF id of the type of data pointed to - a flags field is provided for future use; these flags are not to be confused with the BTF_F_* flags below that control how the btf_ptr is displayed; the flags member of the struct btf_ptr may be used to disambiguate types in kernel versus module BTF, etc; the main distinction is the flags relate to the type and information needed in identifying it; not how it is displayed. For example a BPF program with a struct sk_buff *skb could do the following: static struct btf_ptr b = { }; b.ptr = skb; b.type_id = __builtin_btf_type_id(struct sk_buff, 1); bpf_snprintf_btf(str, sizeof(str), &b, sizeof(b), 0, 0); Default output looks like this: (struct sk_buff){ .transport_header = (__u16)65535, .mac_header = (__u16)65535, .end = (sk_buff_data_t)192, .head = (unsigned char *)0x000000007524fd8b, .data = (unsigned char *)0x000000007524fd8b, .truesize = (unsigned int)768, .users = (refcount_t){ .refs = (atomic_t){ .counter = (int)1, }, }, } Flags modifying display are as follows: - BTF_F_COMPACT: no formatting around type information - BTF_F_NONAME: no struct/union member names/types - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values; equivalent to %px. - BTF_F_ZERO: show zero-valued struct/union members; they are not displayed by default Signed-off-by: Alan Maguire Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/1601292670-1616-4-git-send-email-alan.maguire@oracle.com --- include/linux/bpf.h | 1 + include/linux/btf.h | 9 ++++--- include/uapi/linux/bpf.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 73 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e620a4b1290f..768b533ba48e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1822,6 +1822,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; +extern const struct bpf_func_proto bpf_snprintf_btf_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/btf.h b/include/linux/btf.h index d0f5d3c9ec3d..3e5cdc2ba963 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -6,6 +6,7 @@ #include #include +#include #define BTF_TYPE_EMIT(type) ((void)(type *)0) @@ -59,10 +60,10 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, * - BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read * data before displaying it. */ -#define BTF_SHOW_COMPACT (1ULL << 0) -#define BTF_SHOW_NONAME (1ULL << 1) -#define BTF_SHOW_PTR_RAW (1ULL << 2) -#define BTF_SHOW_ZERO (1ULL << 3) +#define BTF_SHOW_COMPACT BTF_F_COMPACT +#define BTF_SHOW_NONAME BTF_F_NONAME +#define BTF_SHOW_PTR_RAW BTF_F_PTR_RAW +#define BTF_SHOW_ZERO BTF_F_ZERO #define BTF_SHOW_UNSAFE (1ULL << 4) void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 82522f05c021..cca9eb1b13e5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3594,6 +3594,42 @@ union bpf_attr { * the data in *dst*. This is a wrapper of **copy_from_user**\ (). * Return * 0 on success, or a negative error in case of failure. + * + * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags) + * Description + * Use BTF to store a string representation of *ptr*->ptr in *str*, + * using *ptr*->type_id. This value should specify the type + * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1) + * can be used to look up vmlinux BTF type ids. Traversing the + * data structure using BTF, the type information and values are + * stored in the first *str_size* - 1 bytes of *str*. Safe copy of + * the pointer data is carried out to avoid kernel crashes during + * operation. Smaller types can use string space on the stack; + * larger programs can use map data to store the string + * representation. + * + * The string can be subsequently shared with userspace via + * bpf_perf_event_output() or ring buffer interfaces. + * bpf_trace_printk() is to be avoided as it places too small + * a limit on string size to be useful. + * + * *flags* is a combination of + * + * **BTF_F_COMPACT** + * no formatting around type information + * **BTF_F_NONAME** + * no struct/union member names/types + * **BTF_F_PTR_RAW** + * show raw (unobfuscated) pointer values; + * equivalent to printk specifier %px. + * **BTF_F_ZERO** + * show zero-valued struct/union members; they + * are not displayed by default + * + * Return + * The number of bytes that were written (or would have been + * written if output had to be truncated due to string size), + * or a negative error in cases of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3745,6 +3781,7 @@ union bpf_attr { FN(inode_storage_delete), \ FN(d_path), \ FN(copy_from_user), \ + FN(snprintf_btf), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4853,4 +4890,34 @@ struct bpf_sk_lookup { __u32 local_port; /* Host byte order */ }; +/* + * struct btf_ptr is used for typed pointer representation; the + * type id is used to render the pointer data as the appropriate type + * via the bpf_snprintf_btf() helper described above. A flags field - + * potentially to specify additional details about the BTF pointer + * (rather than its mode of display) - is included for future use. + * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately. + */ +struct btf_ptr { + void *ptr; + __u32 type_id; + __u32 flags; /* BTF ptr flags; unused at present. */ +}; + +/* + * Flags to control bpf_snprintf_btf() behaviour. + * - BTF_F_COMPACT: no formatting around type information + * - BTF_F_NONAME: no struct/union member names/types + * - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values; + * equivalent to %px. + * - BTF_F_ZERO: show zero-valued struct/union members; they + * are not displayed by default + */ +enum { + BTF_F_COMPACT = (1ULL << 0), + BTF_F_NONAME = (1ULL << 1), + BTF_F_PTR_RAW = (1ULL << 2), + BTF_F_ZERO = (1ULL << 3), +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From eb411377aed9e27835e77ee0710ee8f4649958f3 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Mon, 28 Sep 2020 12:31:09 +0100 Subject: bpf: Add bpf_seq_printf_btf helper A helper is added to allow seq file writing of kernel data structures using vmlinux BTF. Its signature is long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags); Flags and struct btf_ptr definitions/use are identical to the bpf_snprintf_btf helper, and the helper returns 0 on success or a negative error value. Suggested-by: Alexei Starovoitov Signed-off-by: Alan Maguire Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/1601292670-1616-8-git-send-email-alan.maguire@oracle.com --- include/linux/btf.h | 2 ++ include/uapi/linux/bpf.h | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 3e5cdc2ba963..024e16ff7dcc 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -68,6 +68,8 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); +int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj, + struct seq_file *m, u64 flags); /* * Copy len bytes of string representation of obj of BTF type_id into buf. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cca9eb1b13e5..96ddb00b91dc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3630,6 +3630,14 @@ union bpf_attr { * The number of bytes that were written (or would have been * written if output had to be truncated due to string size), * or a negative error in cases of failure. + * + * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags) + * Description + * Use BTF to write to seq_write a string representation of + * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf(). + * *flags* are identical to those used for bpf_snprintf_btf. + * Return + * 0 on success or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3782,6 +3790,7 @@ union bpf_attr { FN(d_path), \ FN(copy_from_user), \ FN(snprintf_btf), \ + FN(seq_printf_btf), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From b4c5f83ae3f3e2b3239751c304e424eace62448b Mon Sep 17 00:00:00 2001 From: Rusaimi Amira Ruslan Date: Mon, 28 Sep 2020 18:12:12 +0800 Subject: stmmac: intel: Adding ref clock 1us tic for LPI cntr Adding reference clock (1us tic) for all LPI timer on Intel platforms. The reference clock is derived from ptp clk. This also enables all LPI counter. Signed-off-by: Rusaimi Amira Ruslan Signed-off-by: Voon Weifeng Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 00e83c877496..628e28903b8b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -200,5 +200,6 @@ struct plat_stmmacenet_data { int has_xgmac; bool vlan_fail_q_en; u8 vlan_fail_q; + unsigned int eee_usecs_rate; }; #endif -- cgit v1.2.3 From 3ddf9b431b931544dc2f94e8f6a055ff501436fa Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 28 Sep 2020 17:53:29 -0700 Subject: genetlink: add missing kdoc for validation flags Validation flags are missing kdoc, add it. Fixes: ef6243acb478 ("genetlink: optionally validate strictly/dumps") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/genetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 6e5f1e1aa822..8899d7429ccb 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -138,6 +138,7 @@ genl_dumpit_info(struct netlink_callback *cb) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags + * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers -- cgit v1.2.3 From 7b38b7b0427df70237e3c9c73f2db6b99be2b4b9 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 8 Sep 2020 19:24:45 +0900 Subject: PM / devfreq: Add devfreq_get_devfreq_by_node function Split off part of devfreq_get_devfreq_by_phandle into a separate function. This allows callers to fetch devfreq instances by enumerating devicetree instead of explicit phandles. Acked-by: Krzysztof Kozlowski Reviewed-by: Lukasz Luba Signed-off-by: Leonard Crestez [cw00.choi: Export devfreq_get_devfreq_by_node function and add function to devfreq.h when CONFIG_PM_DEVFREQ is enabled.] Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 12782fbb4c25..eb971b8e5051 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -261,6 +261,7 @@ void devm_devfreq_unregister_notifier(struct device *dev, struct devfreq *devfreq, struct notifier_block *nb, unsigned int list); +struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node); struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index); #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) @@ -414,6 +415,11 @@ static inline void devm_devfreq_unregister_notifier(struct device *dev, { } +static inline struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node) +{ + return ERR_PTR(-ENODEV); +} + static inline struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index) { -- cgit v1.2.3 From 86d90fd95bbc3b3fdc2ef0507b7324cd1d0a358b Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Tue, 8 Sep 2020 19:24:46 +0900 Subject: PM / devfreq: Change prototype of devfreq_get_devfreq_by_phandle function Previously, devfreq core support 'devfreq' property in order to get the devfreq device by phandle. But, 'devfreq' property name is not proper on devicetree binding because this name doesn't mean the any h/w attribute. The devfreq core hand over the right to decide the property name for getting the devfreq device on devicetree. Each devfreq driver will decide the property name on devicetree binding and pass the their own property name to devfreq_get_devfreq_by_phandle function. Acked-by: Krzysztof Kozlowski Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index eb971b8e5051..2f4a74efa6be 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -262,7 +262,8 @@ void devm_devfreq_unregister_notifier(struct device *dev, struct notifier_block *nb, unsigned int list); struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node); -struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index); +struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, + const char *phandle_name, int index); #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** @@ -421,7 +422,7 @@ static inline struct devfreq *devfreq_get_devfreq_by_node(struct device_node *no } static inline struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, - int index) + const char *phandle_name, int index) { return ERR_PTR(-ENODEV); } -- cgit v1.2.3 From 02bdbf7d09c059b16047e3d4a05e6d584dd993b6 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Tue, 8 Sep 2020 19:24:47 +0900 Subject: PM / devfreq: event: Change prototype of devfreq_event_get_edev_by_phandle function Previously, devfreq core support 'devfreq-events' property in order to get the devfreq-event device by phandle. But, 'devfreq-events' property name is not proper on devicetree binding because this name doesn't mean the any h/w attribute. The devfreq-event core hand over the rights to decide the property name for getting the devfreq-event device on devicetree. Each devfreq-event driver will decide the property name on devicetree binding and then pass the their own property name to devfreq_event_get_edev_by_phandle function. And change the prototype of devfreq_event_get_edev_count function because of used deprecated 'devfreq-events' property. Acked-by: Krzysztof Kozlowski Signed-off-by: Chanwoo Choi --- include/linux/devfreq-event.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h index f14f17f8cb7f..4a50a5c71a5f 100644 --- a/include/linux/devfreq-event.h +++ b/include/linux/devfreq-event.h @@ -106,8 +106,11 @@ extern int devfreq_event_get_event(struct devfreq_event_dev *edev, struct devfreq_event_data *edata); extern int devfreq_event_reset_event(struct devfreq_event_dev *edev); extern struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( - struct device *dev, int index); -extern int devfreq_event_get_edev_count(struct device *dev); + struct device *dev, + const char *phandle_name, + int index); +extern int devfreq_event_get_edev_count(struct device *dev, + const char *phandle_name); extern struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, struct devfreq_event_desc *desc); extern int devfreq_event_remove_edev(struct devfreq_event_dev *edev); @@ -152,12 +155,15 @@ static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev) } static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( - struct device *dev, int index) + struct device *dev, + const char *phandle_name, + int index) { return ERR_PTR(-EINVAL); } -static inline int devfreq_event_get_edev_count(struct device *dev) +static inline int devfreq_event_get_edev_count(struct device *dev, + const char *phandle_name) { return -EINVAL; } -- cgit v1.2.3 From 48404cf57852224c052e2e40d4dc50dd398c7a58 Mon Sep 17 00:00:00 2001 From: Michael Auchter Date: Tue, 22 Sep 2020 09:44:20 -0500 Subject: iio: adc: ad7291: convert to device tree There are no in-tree users of the platform data for this driver, so remove it and convert the driver to use device tree instead. Signed-off-by: Michael Auchter Link: https://lore.kernel.org/r/20200922144422.542669-1-michael.auchter@ni.com Signed-off-by: Jonathan Cameron --- include/linux/platform_data/ad7291.h | 13 ------------- 1 file changed, 13 deletions(-) delete mode 100644 include/linux/platform_data/ad7291.h (limited to 'include') diff --git a/include/linux/platform_data/ad7291.h b/include/linux/platform_data/ad7291.h deleted file mode 100644 index b1fd1530c9a5..000000000000 --- a/include/linux/platform_data/ad7291.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IIO_AD7291_H__ -#define __IIO_AD7291_H__ - -/** - * struct ad7291_platform_data - AD7291 platform data - * @use_external_ref: Whether to use an external or internal reference voltage - */ -struct ad7291_platform_data { - bool use_external_ref; -}; - -#endif -- cgit v1.2.3 From 25918a9c641c3c73ae94354605860c06fd73a05e Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Wed, 23 Sep 2020 15:18:10 +0300 Subject: iio: buffer-dmaengine: remove non managed alloc/free This is to encourage the use of devm_iio_dmaengine_buffer_alloc(). Currently the managed version of the DMAEngine buffer alloc is the only function used from this part of the framework. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20200923121810.944075-1-alexandru.ardelean@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dmaengine.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index 0e503db71289..5b502291d6a4 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -10,10 +10,6 @@ struct iio_buffer; struct device; -struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, - const char *channel); -void iio_dmaengine_buffer_free(struct iio_buffer *buffer); - struct iio_buffer *devm_iio_dmaengine_buffer_alloc(struct device *dev, const char *channel); -- cgit v1.2.3 From 2e2366c2d14193d3b95bab1fb484a9377224962b Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Wed, 23 Sep 2020 16:03:39 +0300 Subject: iio: cros_ec: unify hw fifo attributes into the core file The intent here is to minimize the use of iio_buffer_set_attrs(). Since we are planning to add support for multiple IIO buffers per IIO device, the issue has to do with: 1. Accessing 'indio_dev->buffer' directly (as is done with 'iio_buffer_set_attrs(indio_dev->buffer, )'). 2. The way that the buffer attributes would get handled or expanded when there are more buffers per IIO device. Current a sysfs kobj_type expands into a 'device' object that expands into an 'iio_dev' object. We will need to change this, so that the sysfs attributes for IIO buffers expand into IIO buffers at some point. Right now, the current IIO framework works fine for the '1 IIO device == 1 IIO buffer' case (that is now). Signed-off-by: Alexandru Ardelean Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20200923130339.997902-1-alexandru.ardelean@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/common/cros_ec_sensors_core.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h index caa8bb279a34..c9b80be82440 100644 --- a/include/linux/iio/common/cros_ec_sensors_core.h +++ b/include/linux/iio/common/cros_ec_sensors_core.h @@ -96,7 +96,8 @@ struct platform_device; int cros_ec_sensors_core_init(struct platform_device *pdev, struct iio_dev *indio_dev, bool physical_device, cros_ec_sensors_capture_t trigger_capture, - cros_ec_sensorhub_push_data_cb_t push_data); + cros_ec_sensorhub_push_data_cb_t push_data, + bool has_hw_fifo); irqreturn_t cros_ec_sensors_capture(int irq, void *p); int cros_ec_sensors_push_data(struct iio_dev *indio_dev, @@ -125,6 +126,5 @@ extern const struct dev_pm_ops cros_ec_sensors_pm_ops; /* List of extended channel specification for all sensors. */ extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[]; -extern const struct attribute *cros_ec_sensor_fifo_attributes[]; #endif /* __CROS_EC_SENSORS_CORE_H */ -- cgit v1.2.3 From 232f4eb6393f42f7f9418560ae9228e747fc6faf Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 23 Sep 2020 09:56:14 +0200 Subject: efi: pstore: disentangle from deprecated efivars module The EFI pstore implementation relies on the 'efivars' abstraction, which encapsulates the EFI variable store in a way that can be overridden by other backing stores, like the Google SMI one. On top of that, the EFI pstore implementation also relies on the efivars.ko module, which is a separate layer built on top of the 'efivars' abstraction that exposes the [deprecated] sysfs entries for each variable that exists in the backing store. Since the efivars.ko module is deprecated, and all users appear to have moved to the efivarfs file system instead, let's prepare for its removal, by removing EFI pstore's dependency on it. Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 4a2332f146eb..7066c11ab82f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -986,8 +986,6 @@ struct efivar_entry { bool deleting; }; -extern struct list_head efivar_sysfs_list; - static inline void efivar_unregister(struct efivar_entry *var) { @@ -1045,8 +1043,6 @@ void efivar_run_worker(void); #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) int efivars_sysfs_init(void); -#define EFIVARS_DATA_SIZE_MAX 1024 - #endif /* CONFIG_EFI_VARS */ extern bool efi_capsule_pending(int *reset_type); -- cgit v1.2.3 From c9b51a2dbfe7f47643e133bf48e1bf28f1b85d2a Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 23 Sep 2020 10:07:49 +0200 Subject: efi: pstore: move workqueue handling out of efivars The worker thread that gets kicked off to sync the state of the EFI variable list is only used by the EFI pstore implementation, and is defined in its source file. So let's move its scheduling there as well. Since our efivar_init() scan will bail on duplicate entries, there is no need to disable the workqueue like we did before, so we can run it unconditionally. Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 7066c11ab82f..ab8c80331217 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1037,9 +1037,6 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, size_t len); -extern struct work_struct efivar_work; -void efivar_run_worker(void); - #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) int efivars_sysfs_init(void); -- cgit v1.2.3 From 5d3c8617ccee6387ba73a5dba77fb9dc21cb85f4 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 23 Sep 2020 10:13:07 +0200 Subject: efi: efivars: un-export efivars_sysfs_init() efivars_sysfs_init() is only used locally in the source file that defines it, so make it static and unexport it. Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index ab8c80331217..4c8dae0b5c75 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1037,10 +1037,6 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, size_t len); -#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) -int efivars_sysfs_init(void); - -#endif /* CONFIG_EFI_VARS */ extern bool efi_capsule_pending(int *reset_type); extern int efi_capsule_supported(efi_guid_t guid, u32 flags, -- cgit v1.2.3 From a5d02e901e6dadd7dd60fafb6448a822a47430ff Mon Sep 17 00:00:00 2001 From: Vaibhav Gupta Date: Fri, 31 Jul 2020 01:14:16 +0530 Subject: PCI/PM: Remove unused pcibios_pm_ops The "struct dev_pm_ops pcibios_pm_ops", declared in include/linux/pci.h and defined in drivers/pci/pci-driver.c, provided arch-specific hooks when a PCI device was doing a hibernate transition. 394216275c7d ("s390: remove broken hibernate / power management support") removed the last use of pcibios_pm_ops, so remove it completely. [bhelgaas: drop unused "error"] Link: https://lore.kernel.org/r/20200730194416.1029509-1-vaibhavgupta40@gmail.com Reported-by: Bjorn Helgaas Signed-off-by: Vaibhav Gupta Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 835530605c0d..c9e169c4e216 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2034,10 +2034,6 @@ int pcibios_alloc_irq(struct pci_dev *dev); void pcibios_free_irq(struct pci_dev *dev); resource_size_t pcibios_default_alignment(void); -#ifdef CONFIG_HIBERNATE_CALLBACKS -extern struct dev_pm_ops pcibios_pm_ops; -#endif - #if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_MCFG) void __init pci_mmcfg_early_init(void); void __init pci_mmcfg_late_init(void); -- cgit v1.2.3 From 3789af9a13e5561738c0f2114e3a5e22c843ca3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Thu, 30 Jul 2020 21:08:48 +0000 Subject: PCI/PM: Rename pci_dev.d3_delay to d3hot_delay MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCI devices support two variants of the D3 power state: D3hot (main power present) D3cold (main power removed). Previously struct pci_dev contained: unsigned int d3_delay; /* D3->D0 transition time in ms */ unsigned int d3cold_delay; /* D3cold->D0 transition time in ms */ "d3_delay" refers specifically to the D3hot state. Rename it to "d3hot_delay" to avoid ambiguity and align with the ACPI "_DSM for Specifying Device Readiness Durations" in the PCI Firmware spec r3.2, sec 4.6.9. There is no change to the functionality. Link: https://lore.kernel.org/r/20200730210848.1578826-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- include/uapi/linux/pci_regs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index c9e169c4e216..bea1a03faab6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -373,7 +373,7 @@ struct pci_dev { user sysfs */ unsigned int clear_retrain_link:1; /* Need to clear Retrain Link bit manually */ - unsigned int d3_delay; /* D3->D0 transition time in ms */ + unsigned int d3hot_delay; /* D3hot->D0 transition time in ms */ unsigned int d3cold_delay; /* D3cold->D0 transition time in ms */ #ifdef CONFIG_PCIEASPM diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f9701410d3b5..49f15c37e771 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -246,7 +246,7 @@ #define PCI_PM_CAP_PME_D0 0x0800 /* PME# from D0 */ #define PCI_PM_CAP_PME_D1 0x1000 /* PME# from D1 */ #define PCI_PM_CAP_PME_D2 0x2000 /* PME# from D2 */ -#define PCI_PM_CAP_PME_D3 0x4000 /* PME# from D3 (hot) */ +#define PCI_PM_CAP_PME_D3hot 0x4000 /* PME# from D3 (hot) */ #define PCI_PM_CAP_PME_D3cold 0x8000 /* PME# from D3 (cold) */ #define PCI_PM_CAP_PME_SHIFT 11 /* Start of the PME Mask in PMC */ #define PCI_PM_CTRL 4 /* PM control and status register */ -- cgit v1.2.3 From 3aac1ead5eb6b76f3d2b8d111e6de1c2de23fb34 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 29 Sep 2020 14:45:50 +0200 Subject: bpf: Move prog->aux->linked_prog and trampoline into bpf_link on attach MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation for allowing multiple attachments of freplace programs, move the references to the target program and trampoline into the bpf_tracing_link structure when that is created. To do this atomically, introduce a new mutex in prog->aux to protect writing to the two pointers to target prog and trampoline, and rename the members to make it clear that they are related. With this change, it is no longer possible to attach the same tracing program multiple times (detaching in-between), since the reference from the tracing program to the target disappears on the first attach. However, since the next patch will let the caller supply an attach target, that will also make it possible to attach to the same place multiple times. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/160138355059.48470.2503076992210324984.stgit@toke.dk --- include/linux/bpf.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 768b533ba48e..839dd8670a7a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -640,8 +640,8 @@ static __always_inline unsigned int bpf_dispatcher_nop_func( return bpf_func(ctx, insnsi); } #ifdef CONFIG_BPF_JIT -int bpf_trampoline_link_prog(struct bpf_prog *prog); -int bpf_trampoline_unlink_prog(struct bpf_prog *prog); +int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); +int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); @@ -688,11 +688,13 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); #else -static inline int bpf_trampoline_link_prog(struct bpf_prog *prog) +static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, + struct bpf_trampoline *tr) { return -ENOTSUPP; } -static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) +static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog, + struct bpf_trampoline *tr) { return -ENOTSUPP; } @@ -763,7 +765,9 @@ struct bpf_prog_aux { u32 max_rdonly_access; u32 max_rdwr_access; const struct bpf_ctx_arg_aux *ctx_arg_info; - struct bpf_prog *linked_prog; + struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ + struct bpf_prog *dst_prog; + struct bpf_trampoline *dst_trampoline; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ @@ -771,7 +775,6 @@ struct bpf_prog_aux { bool sleepable; bool tail_call_reachable; enum bpf_tramp_prog_type trampoline_prog_type; - struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; -- cgit v1.2.3 From 4a1e7c0c63e02daad751842b7880f9bbcdfb6e89 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 29 Sep 2020 14:45:51 +0200 Subject: bpf: Support attaching freplace programs to multiple attach points MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This enables support for attaching freplace programs to multiple attach points. It does this by amending the UAPI for bpf_link_Create with a target btf ID that can be used to supply the new attachment point along with the target program fd. The target must be compatible with the target that was supplied at program load time. The implementation reuses the checks that were factored out of check_attach_btf_id() to ensure compatibility between the BTF types of the old and new attachment. If these match, a new bpf_tracing_link will be created for the new attach target, allowing multiple attachments to co-exist simultaneously. The code could theoretically support multiple-attach of other types of tracing programs as well, but since I don't have a use case for any of those, there is no API support for doing so. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/160138355169.48470.17165680973640685368.stgit@toke.dk --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 9 +++++++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 839dd8670a7a..50e5c4b52bd1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -768,6 +768,8 @@ struct bpf_prog_aux { struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; + enum bpf_prog_type saved_dst_prog_type; + enum bpf_attach_type saved_dst_attach_type; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 96ddb00b91dc..2b1d3f16cbd1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -639,8 +639,13 @@ union bpf_attr { }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ - __aligned_u64 iter_info; /* extra bpf_iter_link_info */ - __u32 iter_info_len; /* iter_info length */ + union { + __u32 target_btf_id; /* btf_id of target to attach to */ + struct { + __aligned_u64 iter_info; /* extra bpf_iter_link_info */ + __u32 iter_info_len; /* iter_info length */ + }; + }; } link_create; struct { /* struct used by BPF_LINK_UPDATE command */ -- cgit v1.2.3 From 3f47cb4c1cf3bceb2438ea962bfffc6665ee4a9f Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 29 Sep 2020 13:35:41 +0100 Subject: l2tp: report rx cookie discards in netlink get When an L2TPv3 session receives a data frame with an incorrect cookie l2tp_core logs a warning message and bumps a stats counter to reflect the fact that the packet has been dropped. However, the stats counter in question is missing from the l2tp_netlink get message for tunnel and session instances. Include the statistic in the netlink get response. Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- include/uapi/linux/l2tp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 88a0d32b8c07..30c80d5ba4bf 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -144,6 +144,7 @@ enum { L2TP_ATTR_RX_OOS_PACKETS, /* u64 */ L2TP_ATTR_RX_ERRORS, /* u64 */ L2TP_ATTR_STATS_PAD, + L2TP_ATTR_RX_COOKIE_DISCARDS, /* u64 */ __L2TP_ATTR_STATS_MAX, }; -- cgit v1.2.3 From 2ec13cbcfadbbeac499f3b63de0f7db490d45a7e Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 29 Sep 2020 11:08:59 -0700 Subject: devlink: include for _BITUL Commit 5d5b4128c4ca ("devlink: introduce flash update overwrite mask") added a usage of _BITUL to the UAPI header, but failed to include the header file where it was defined. It happens that this does not break any existing kernel include chains because it gets included through other sources. However, when including the UAPI headers in a userspace application (such as devlink in iproute2), _BITUL is not defined. Fixes: 5d5b4128c4ca ("devlink: introduce flash update overwrite mask") Signed-off-by: Jacob Keller Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 7b0face1bad5..ba467dc07852 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -13,6 +13,8 @@ #ifndef _UAPI_LINUX_DEVLINK_H_ #define _UAPI_LINUX_DEVLINK_H_ +#include + #define DEVLINK_GENL_NAME "devlink" #define DEVLINK_GENL_VERSION 0x1 #define DEVLINK_GENL_MCGRP_CONFIG_NAME "config" -- cgit v1.2.3 From f2bf88c4afc8c5ab92b40af24819933e57d0968c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 29 Sep 2020 22:25:11 +0200 Subject: net: caif: Remove unused caif SPI driver While chasing in_interrupt() (ab)use in drivers it turned out that the caif_spi driver has never been in use since the driver was merged 10 years ago. There never was any matching code which provides a platform device. The driver has not seen any update (asided of treewide changes and cleanups) since 8 years and the maintainers vanished from the planet. So analysing the potential contexts and the (in)correctness of in_interrupt() usage is just a pointless exercise. Remove the cruft. Signed-off-by: Thomas Gleixner Signed-off-by: David S. Miller --- include/net/caif/caif_spi.h | 155 -------------------------------------------- 1 file changed, 155 deletions(-) delete mode 100644 include/net/caif/caif_spi.h (limited to 'include') diff --git a/include/net/caif/caif_spi.h b/include/net/caif/caif_spi.h deleted file mode 100644 index a0bf4cbce71b..000000000000 --- a/include/net/caif/caif_spi.h +++ /dev/null @@ -1,155 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Daniel Martensson / Daniel.Martensson@stericsson.com - */ - -#ifndef CAIF_SPI_H_ -#define CAIF_SPI_H_ - -#include - -#define SPI_CMD_WR 0x00 -#define SPI_CMD_RD 0x01 -#define SPI_CMD_EOT 0x02 -#define SPI_CMD_IND 0x04 - -#define SPI_DMA_BUF_LEN 8192 - -#define WL_SZ 2 /* 16 bits. */ -#define SPI_CMD_SZ 4 /* 32 bits. */ -#define SPI_IND_SZ 4 /* 32 bits. */ - -#define SPI_XFER 0 -#define SPI_SS_ON 1 -#define SPI_SS_OFF 2 -#define SPI_TERMINATE 3 - -/* Minimum time between different levels is 50 microseconds. */ -#define MIN_TRANSITION_TIME_USEC 50 - -/* Defines for calculating duration of SPI transfers for a particular - * number of bytes. - */ -#define SPI_MASTER_CLK_MHZ 13 -#define SPI_XFER_TIME_USEC(bytes, clk) (((bytes) * 8) / clk) - -/* Normally this should be aligned on the modem in order to benefit from full - * duplex transfers. However a size of 8188 provokes errors when running with - * the modem. These errors occur when packet sizes approaches 4 kB of data. - */ -#define CAIF_MAX_SPI_FRAME 4092 - -/* Maximum number of uplink CAIF frames that can reside in the same SPI frame. - * This number should correspond with the modem setting. The application side - * CAIF accepts any number of embedded downlink CAIF frames. - */ -#define CAIF_MAX_SPI_PKTS 9 - -/* Decides if SPI buffers should be prefilled with 0xFF pattern for easier - * debugging. Both TX and RX buffers will be filled before the transfer. - */ -#define CFSPI_DBG_PREFILL 0 - -/* Structure describing a SPI transfer. */ -struct cfspi_xfer { - u16 tx_dma_len; - u16 rx_dma_len; - void *va_tx[2]; - dma_addr_t pa_tx[2]; - void *va_rx; - dma_addr_t pa_rx; -}; - -/* Structure implemented by the SPI interface. */ -struct cfspi_ifc { - void (*ss_cb) (bool assert, struct cfspi_ifc *ifc); - void (*xfer_done_cb) (struct cfspi_ifc *ifc); - void *priv; -}; - -/* Structure implemented by SPI clients. */ -struct cfspi_dev { - int (*init_xfer) (struct cfspi_xfer *xfer, struct cfspi_dev *dev); - void (*sig_xfer) (bool xfer, struct cfspi_dev *dev); - struct cfspi_ifc *ifc; - char *name; - u32 clk_mhz; - void *priv; -}; - -/* Enumeration describing the CAIF SPI state. */ -enum cfspi_state { - CFSPI_STATE_WAITING = 0, - CFSPI_STATE_AWAKE, - CFSPI_STATE_FETCH_PKT, - CFSPI_STATE_GET_NEXT, - CFSPI_STATE_INIT_XFER, - CFSPI_STATE_WAIT_ACTIVE, - CFSPI_STATE_SIG_ACTIVE, - CFSPI_STATE_WAIT_XFER_DONE, - CFSPI_STATE_XFER_DONE, - CFSPI_STATE_WAIT_INACTIVE, - CFSPI_STATE_SIG_INACTIVE, - CFSPI_STATE_DELIVER_PKT, - CFSPI_STATE_MAX, -}; - -/* Structure implemented by SPI physical interfaces. */ -struct cfspi { - struct caif_dev_common cfdev; - struct net_device *ndev; - struct platform_device *pdev; - struct sk_buff_head qhead; - struct sk_buff_head chead; - u16 cmd; - u16 tx_cpck_len; - u16 tx_npck_len; - u16 rx_cpck_len; - u16 rx_npck_len; - struct cfspi_ifc ifc; - struct cfspi_xfer xfer; - struct cfspi_dev *dev; - unsigned long state; - struct work_struct work; - struct workqueue_struct *wq; - struct list_head list; - int flow_off_sent; - u32 qd_low_mark; - u32 qd_high_mark; - struct completion comp; - wait_queue_head_t wait; - spinlock_t lock; - bool flow_stop; - bool slave; - bool slave_talked; -#ifdef CONFIG_DEBUG_FS - enum cfspi_state dbg_state; - u16 pcmd; - u16 tx_ppck_len; - u16 rx_ppck_len; - struct dentry *dbgfs_dir; - struct dentry *dbgfs_state; - struct dentry *dbgfs_frame; -#endif /* CONFIG_DEBUG_FS */ -}; - -extern int spi_frm_align; -extern int spi_up_head_align; -extern int spi_up_tail_align; -extern int spi_down_head_align; -extern int spi_down_tail_align; -extern struct platform_driver cfspi_spi_driver; - -void cfspi_dbg_state(struct cfspi *cfspi, int state); -int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len); -int cfspi_xmitlen(struct cfspi *cfspi); -int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len); -int cfspi_spi_remove(struct platform_device *pdev); -int cfspi_spi_probe(struct platform_device *pdev); -int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len); -int cfspi_xmitlen(struct cfspi *cfspi); -int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len); -void cfspi_xfer(struct work_struct *work); - -#endif /* CAIF_SPI_H_ */ -- cgit v1.2.3 From c11171a413385c1a72291cdb4a7435cb189762ab Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 29 Sep 2020 22:25:12 +0200 Subject: net: Add netif_rx_any_context() Quite some drivers make conditional decisions based on in_interrupt() to invoke either netif_rx() or netif_rx_ni(). Conditionals based on in_interrupt() or other variants of preempt count checks in drivers should not exist for various reasons and Linus clearly requested to either split the code pathes or pass an argument to the common functions which provides the context. This is obviously the correct solution, but for some of the affected drivers this needs a major rewrite due to their convoluted structure. As in_interrupt() usage in drivers needs to be phased out, provide netif_rx_any_context() as a stop gap for these drivers. This confines the in_interrupt() conditional to core code which in turn allows to remove the access to this check for driver code and provides one central place to do further modifications once the driver maze is cleaned up. Suggested-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a431c3229cbf..28cfa53daf72 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3785,6 +3785,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); +int netif_rx_any_context(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list(struct list_head *head); -- cgit v1.2.3 From 3c0e37a9e4021ccbf855dfcbc5aff1ca10487cd4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 30 Sep 2020 01:27:21 +0300 Subject: net: mscc: ocelot: introduce a new ocelot_target_{read,write} API There are some targets (register blocks) in the Ocelot switch that are instantiated more than once. For example, the VCAP IS1, IS2 and ES0 blocks all share the same register layout for interacting with the cache for the TCAM and the action RAM. For the VCAPs, the procedure for servicing them is actually common. We just need an API specifying which VCAP we are talking to, and we do that via these raw ocelot_target_read and ocelot_target_write accessors. In plain ocelot_read, the target is encoded into the register enum itself: u16 target = reg >> TARGET_OFFSET; For the VCAPs, the registers are currently defined like this: enum ocelot_reg { [...] S2_CORE_UPDATE_CTRL = S2 << TARGET_OFFSET, S2_CORE_MV_CFG, S2_CACHE_ENTRY_DAT, S2_CACHE_MASK_DAT, S2_CACHE_ACTION_DAT, S2_CACHE_CNT_DAT, S2_CACHE_TG_DAT, [...] }; which is precisely what we want to avoid, because we'd have to duplicate the same register map for S1 and for S0, and then figure out how to pass VCAP instance-specific registers to the ocelot_read calls (basically another lookup table that undoes the effect of shifting with TARGET_OFFSET). So for some targets, propose a more raw API, similar to what is currently done with ocelot_port_readl and ocelot_port_writel. Those targets can only be accessed with ocelot_target_{read,write} and not with ocelot_{read,write} after the conversion, which is fine. The VCAP registers are not actually modified to use this new API as of this patch. They will be modified in the next one. Signed-off-by: Vladimir Oltean Acked-by: Alexandre Belloni Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 3093385f6147..d459f4f25dc8 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -661,6 +661,24 @@ struct ocelot_policer { #define ocelot_fields_write(ocelot, id, reg, val) regmap_fields_write((ocelot)->regfields[(reg)], (id), (val)) #define ocelot_fields_read(ocelot, id, reg, val) regmap_fields_read((ocelot)->regfields[(reg)], (id), (val)) +#define ocelot_target_read_ix(ocelot, target, reg, gi, ri) \ + __ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_target_read_gix(ocelot, target, reg, gi) \ + __ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi)) +#define ocelot_target_read_rix(ocelot, target, reg, ri) \ + __ocelot_target_read_ix(ocelot, target, reg, reg##_RSZ * (ri)) +#define ocelot_target_read(ocelot, target, reg) \ + __ocelot_target_read_ix(ocelot, target, reg, 0) + +#define ocelot_target_write_ix(ocelot, target, val, reg, gi, ri) \ + __ocelot_target_write_ix(ocelot, target, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_target_write_gix(ocelot, target, val, reg, gi) \ + __ocelot_target_write_ix(ocelot, target, val, reg, reg##_GSZ * (gi)) +#define ocelot_target_write_rix(ocelot, target, val, reg, ri) \ + __ocelot_target_write_ix(ocelot, target, val, reg, reg##_RSZ * (ri)) +#define ocelot_target_write(ocelot, target, val, reg) \ + __ocelot_target_write_ix(ocelot, target, val, reg, 0) + /* I/O */ u32 ocelot_port_readl(struct ocelot_port *port, u32 reg); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg); @@ -668,6 +686,10 @@ u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset); void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset); void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, u32 offset); +u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target, + u32 reg, u32 offset); +void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, + u32 val, u32 reg, u32 offset); /* Hardware initialization */ int ocelot_regfields_init(struct ocelot *ocelot, -- cgit v1.2.3 From c1c3993edb7c8cfbe6b3991b4b4c9f673268770e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 30 Sep 2020 01:27:23 +0300 Subject: net: mscc: ocelot: generalize existing code for VCAP In the Ocelot switches there are 3 TCAMs: VCAP ES0, IS1 and IS2, which have the same configuration interface, but different sets of keys and actions. The driver currently only supports VCAP IS2. In preparation of VCAP IS1 and ES0 support, the existing code must be generalized to work with any VCAP. In that direction, we should move the structures that depend upon VCAP instantiation, like vcap_is2_keys and vcap_is2_actions, out of struct ocelot and into struct vcap_props .keys and .actions, a structure that is replicated 3 times, once per VCAP. We'll pass that structure as an argument to each function that does the key and action packing - only the control logic needs to distinguish between ocelot->vcap[VCAP_IS2] or IS1 or ES0. Another change is to make use of the newly introduced ocelot_target_read and ocelot_target_write API, since the 3 VCAPs have the same registers but put at different addresses. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 22 ++++++++------- include/soc/mscc/ocelot_vcap.h | 62 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index d459f4f25dc8..728b040e4e3e 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -393,13 +393,6 @@ enum ocelot_reg { SYS_CM_DATA_RD, SYS_CM_OP, SYS_CM_DATA, - S2_CORE_UPDATE_CTRL = S2 << TARGET_OFFSET, - S2_CORE_MV_CFG, - S2_CACHE_ENTRY_DAT, - S2_CACHE_MASK_DAT, - S2_CACHE_ACTION_DAT, - S2_CACHE_CNT_DAT, - S2_CACHE_TG_DAT, PTP_PIN_CFG = PTP << TARGET_OFFSET, PTP_PIN_TOD_SEC_MSB, PTP_PIN_TOD_SEC_LSB, @@ -518,6 +511,18 @@ enum ocelot_regfield { REGFIELD_MAX }; +enum { + /* VCAP_CORE_CFG */ + VCAP_CORE_UPDATE_CTRL, + VCAP_CORE_MV_CFG, + /* VCAP_CORE_CACHE */ + VCAP_CACHE_ENTRY_DAT, + VCAP_CACHE_MASK_DAT, + VCAP_CACHE_ACTION_DAT, + VCAP_CACHE_CNT_DAT, + VCAP_CACHE_TG_DAT, +}; + enum ocelot_ptp_pins { PTP_PIN_0, PTP_PIN_1, @@ -614,9 +619,6 @@ struct ocelot { struct list_head multicast; struct ocelot_vcap_block block; - - const struct vcap_field *vcap_is2_keys; - const struct vcap_field *vcap_is2_actions; const struct vcap_props *vcap; /* Workqueue to check statistics for overflow with its lock */ diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 5748373ab4d3..05466a1d7bd4 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -6,6 +6,8 @@ #ifndef _OCELOT_VCAP_H_ #define _OCELOT_VCAP_H_ +#include + /* ================================================================= * VCAP Common * ================================================================= @@ -33,6 +35,11 @@ struct vcap_props { } action_table[2]; u16 counter_words; /* Number of counter words */ u16 counter_width; /* Counter width (in bits) */ + + enum ocelot_target target; + + const struct vcap_field *keys; + const struct vcap_field *actions; }; /* VCAP Type-Group values */ @@ -41,6 +48,61 @@ struct vcap_props { #define VCAP_TG_HALF 2 /* Half entry */ #define VCAP_TG_QUARTER 3 /* Quarter entry */ +#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD(x) (((x) << 22) & GENMASK(24, 22)) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD_M GENMASK(24, 22) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD_X(x) (((x) & GENMASK(24, 22)) >> 22) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS BIT(21) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS BIT(20) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_CNT_DIS BIT(19) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR(x) (((x) << 3) & GENMASK(18, 3)) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR_M GENMASK(18, 3) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR_X(x) (((x) & GENMASK(18, 3)) >> 3) +#define VCAP_CORE_UPDATE_CTRL_UPDATE_SHOT BIT(2) +#define VCAP_CORE_UPDATE_CTRL_CLEAR_CACHE BIT(1) +#define VCAP_CORE_UPDATE_CTRL_MV_TRAFFIC_IGN BIT(0) + +#define VCAP_CORE_MV_CFG_MV_NUM_POS(x) (((x) << 16) & GENMASK(31, 16)) +#define VCAP_CORE_MV_CFG_MV_NUM_POS_M GENMASK(31, 16) +#define VCAP_CORE_MV_CFG_MV_NUM_POS_X(x) (((x) & GENMASK(31, 16)) >> 16) +#define VCAP_CORE_MV_CFG_MV_SIZE(x) ((x) & GENMASK(15, 0)) +#define VCAP_CORE_MV_CFG_MV_SIZE_M GENMASK(15, 0) + +#define VCAP_CACHE_ENTRY_DAT_RSZ 0x4 + +#define VCAP_CACHE_MASK_DAT_RSZ 0x4 + +#define VCAP_CACHE_ACTION_DAT_RSZ 0x4 + +#define VCAP_CACHE_CNT_DAT_RSZ 0x4 + +#define VCAP_STICKY_VCAP_ROW_DELETED_STICKY BIT(0) + +#define TCAM_BIST_CTRL_TCAM_BIST BIT(1) +#define TCAM_BIST_CTRL_TCAM_INIT BIT(0) + +#define TCAM_BIST_CFG_TCAM_BIST_SOE_ENA BIT(8) +#define TCAM_BIST_CFG_TCAM_HCG_DIS BIT(7) +#define TCAM_BIST_CFG_TCAM_CG_DIS BIT(6) +#define TCAM_BIST_CFG_TCAM_BIAS(x) ((x) & GENMASK(5, 0)) +#define TCAM_BIST_CFG_TCAM_BIAS_M GENMASK(5, 0) + +#define TCAM_BIST_STAT_BIST_RT_ERR BIT(15) +#define TCAM_BIST_STAT_BIST_PENC_ERR BIT(14) +#define TCAM_BIST_STAT_BIST_COMP_ERR BIT(13) +#define TCAM_BIST_STAT_BIST_ADDR_ERR BIT(12) +#define TCAM_BIST_STAT_BIST_BL1E_ERR BIT(11) +#define TCAM_BIST_STAT_BIST_BL1_ERR BIT(10) +#define TCAM_BIST_STAT_BIST_BL0E_ERR BIT(9) +#define TCAM_BIST_STAT_BIST_BL0_ERR BIT(8) +#define TCAM_BIST_STAT_BIST_PH1_ERR BIT(7) +#define TCAM_BIST_STAT_BIST_PH0_ERR BIT(6) +#define TCAM_BIST_STAT_BIST_PV1_ERR BIT(5) +#define TCAM_BIST_STAT_BIST_PV0_ERR BIT(4) +#define TCAM_BIST_STAT_BIST_RUN BIT(3) +#define TCAM_BIST_STAT_BIST_ERR BIT(2) +#define TCAM_BIST_STAT_BIST_BUSY BIT(1) +#define TCAM_BIST_STAT_TCAM_RDY BIT(0) + /* ================================================================= * VCAP IS2 * ================================================================= -- cgit v1.2.3 From a61e365d7c183c556717bbf36dcf00c941ec044e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 30 Sep 2020 01:27:24 +0300 Subject: net: mscc: ocelot: add definitions for VCAP IS1 keys, actions and target As a preparation step for the offloading to IS1, let's create the infrastructure for talking with this hardware block. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 + include/soc/mscc/ocelot_vcap.h | 93 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 93 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 728b040e4e3e..d0073c94e22a 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -123,6 +123,7 @@ enum ocelot_target { QSYS, REW, SYS, + S1, S2, HSIO, PTP, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 05466a1d7bd4..7ac184047292 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -14,7 +14,7 @@ */ enum { - /* VCAP_IS1, */ + VCAP_IS1, VCAP_IS2, /* VCAP_ES0, */ }; @@ -264,4 +264,95 @@ enum vcap_is2_action_field { VCAP_IS2_ACT_HIT_CNT, }; +/* ================================================================= + * VCAP IS1 + * ================================================================= + */ + +/* IS1 half key types */ +#define IS1_TYPE_S1_NORMAL 0 +#define IS1_TYPE_S1_5TUPLE_IP4 1 + +/* IS1 full key types */ +#define IS1_TYPE_S1_NORMAL_IP6 0 +#define IS1_TYPE_S1_7TUPLE 1 +#define IS2_TYPE_S1_5TUPLE_IP6 2 + +enum { + IS1_ACTION_TYPE_NORMAL, + IS1_ACTION_TYPE_MAX, +}; + +enum vcap_is1_half_key_field { + VCAP_IS1_HK_TYPE, + VCAP_IS1_HK_LOOKUP, + VCAP_IS1_HK_IGR_PORT_MASK, + VCAP_IS1_HK_RSV, + VCAP_IS1_HK_OAM_Y1731, + VCAP_IS1_HK_L2_MC, + VCAP_IS1_HK_L2_BC, + VCAP_IS1_HK_IP_MC, + VCAP_IS1_HK_VLAN_TAGGED, + VCAP_IS1_HK_VLAN_DBL_TAGGED, + VCAP_IS1_HK_TPID, + VCAP_IS1_HK_VID, + VCAP_IS1_HK_DEI, + VCAP_IS1_HK_PCP, + /* Specific Fields for IS1 Half Key S1_NORMAL */ + VCAP_IS1_HK_L2_SMAC, + VCAP_IS1_HK_ETYPE_LEN, + VCAP_IS1_HK_ETYPE, + VCAP_IS1_HK_IP_SNAP, + VCAP_IS1_HK_IP4, + VCAP_IS1_HK_L3_FRAGMENT, + VCAP_IS1_HK_L3_FRAG_OFS_GT0, + VCAP_IS1_HK_L3_OPTIONS, + VCAP_IS1_HK_L3_DSCP, + VCAP_IS1_HK_L3_IP4_SIP, + VCAP_IS1_HK_TCP_UDP, + VCAP_IS1_HK_TCP, + VCAP_IS1_HK_L4_SPORT, + VCAP_IS1_HK_L4_RNG, + /* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */ + VCAP_IS1_HK_IP4_INNER_TPID, + VCAP_IS1_HK_IP4_INNER_VID, + VCAP_IS1_HK_IP4_INNER_DEI, + VCAP_IS1_HK_IP4_INNER_PCP, + VCAP_IS1_HK_IP4_IP4, + VCAP_IS1_HK_IP4_L3_FRAGMENT, + VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0, + VCAP_IS1_HK_IP4_L3_OPTIONS, + VCAP_IS1_HK_IP4_L3_DSCP, + VCAP_IS1_HK_IP4_L3_IP4_DIP, + VCAP_IS1_HK_IP4_L3_IP4_SIP, + VCAP_IS1_HK_IP4_L3_PROTO, + VCAP_IS1_HK_IP4_TCP_UDP, + VCAP_IS1_HK_IP4_TCP, + VCAP_IS1_HK_IP4_L4_RNG, + VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE, +}; + +enum vcap_is1_action_field { + VCAP_IS1_ACT_DSCP_ENA, + VCAP_IS1_ACT_DSCP_VAL, + VCAP_IS1_ACT_QOS_ENA, + VCAP_IS1_ACT_QOS_VAL, + VCAP_IS1_ACT_DP_ENA, + VCAP_IS1_ACT_DP_VAL, + VCAP_IS1_ACT_PAG_OVERRIDE_MASK, + VCAP_IS1_ACT_PAG_VAL, + VCAP_IS1_ACT_RSV, + VCAP_IS1_ACT_VID_REPLACE_ENA, + VCAP_IS1_ACT_VID_ADD_VAL, + VCAP_IS1_ACT_FID_SEL, + VCAP_IS1_ACT_FID_VAL, + VCAP_IS1_ACT_PCP_DEI_ENA, + VCAP_IS1_ACT_PCP_VAL, + VCAP_IS1_ACT_DEI_VAL, + VCAP_IS1_ACT_VLAN_POP_CNT_ENA, + VCAP_IS1_ACT_VLAN_POP_CNT, + VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA, + VCAP_IS1_ACT_HIT_STICKY, +}; + #endif /* _OCELOT_VCAP_H_ */ -- cgit v1.2.3 From e3aea296d86f0f2166f4ddc5e1325217f847e722 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 30 Sep 2020 01:27:25 +0300 Subject: net: mscc: ocelot: add definitions for VCAP ES0 keys, actions and target As a preparation step for the offloading to ES0, let's create the infrastructure for talking with this hardware block. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 + include/soc/mscc/ocelot_vcap.h | 44 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index d0073c94e22a..b0a9efce8813 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -123,6 +123,7 @@ enum ocelot_target { QSYS, REW, SYS, + S0, S1, S2, HSIO, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 7ac184047292..707e609ec919 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -14,9 +14,9 @@ */ enum { + VCAP_ES0, VCAP_IS1, VCAP_IS2, - /* VCAP_ES0, */ }; struct vcap_props { @@ -355,4 +355,46 @@ enum vcap_is1_action_field { VCAP_IS1_ACT_HIT_STICKY, }; +/* ================================================================= + * VCAP ES0 + * ================================================================= + */ + +enum { + ES0_ACTION_TYPE_NORMAL, + ES0_ACTION_TYPE_MAX, +}; + +enum vcap_es0_key_field { + VCAP_ES0_EGR_PORT, + VCAP_ES0_IGR_PORT, + VCAP_ES0_RSV, + VCAP_ES0_L2_MC, + VCAP_ES0_L2_BC, + VCAP_ES0_VID, + VCAP_ES0_DP, + VCAP_ES0_PCP, +}; + +enum vcap_es0_action_field { + VCAP_ES0_ACT_PUSH_OUTER_TAG, + VCAP_ES0_ACT_PUSH_INNER_TAG, + VCAP_ES0_ACT_TAG_A_TPID_SEL, + VCAP_ES0_ACT_TAG_A_VID_SEL, + VCAP_ES0_ACT_TAG_A_PCP_SEL, + VCAP_ES0_ACT_TAG_A_DEI_SEL, + VCAP_ES0_ACT_TAG_B_TPID_SEL, + VCAP_ES0_ACT_TAG_B_VID_SEL, + VCAP_ES0_ACT_TAG_B_PCP_SEL, + VCAP_ES0_ACT_TAG_B_DEI_SEL, + VCAP_ES0_ACT_VID_A_VAL, + VCAP_ES0_ACT_PCP_A_VAL, + VCAP_ES0_ACT_DEI_A_VAL, + VCAP_ES0_ACT_VID_B_VAL, + VCAP_ES0_ACT_PCP_B_VAL, + VCAP_ES0_ACT_DEI_B_VAL, + VCAP_ES0_ACT_RSV, + VCAP_ES0_ACT_HIT_STICKY, +}; + #endif /* _OCELOT_VCAP_H_ */ -- cgit v1.2.3 From 2096805497e2bd21df3c26bd48c43ff0ce954316 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 30 Sep 2020 01:27:26 +0300 Subject: net: mscc: ocelot: automatically detect VCAP constants The numbers in struct vcap_props are not intuitive to derive, because they are not a straightforward copy-and-paste from the reference manual but instead rely on a fairly detailed level of understanding of the layout of an entry in the TCAM and in the action RAM. For this reason, bugs are very easy to introduce here. Ease the work of hardware porters and read from hardware the constants that were exported for this particular purpose. Note that this implies that struct vcap_props can no longer be const. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 13 ++++++++++++- include/soc/mscc/ocelot_vcap.h | 3 +++ 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index b0a9efce8813..0c40122dcb88 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -523,6 +523,17 @@ enum { VCAP_CACHE_ACTION_DAT, VCAP_CACHE_CNT_DAT, VCAP_CACHE_TG_DAT, + /* VCAP_CONST */ + VCAP_CONST_VCAP_VER, + VCAP_CONST_ENTRY_WIDTH, + VCAP_CONST_ENTRY_CNT, + VCAP_CONST_ENTRY_SWCNT, + VCAP_CONST_ENTRY_TG_WIDTH, + VCAP_CONST_ACTION_DEF_CNT, + VCAP_CONST_ACTION_WIDTH, + VCAP_CONST_CNT_WIDTH, + VCAP_CONST_CORE_CNT, + VCAP_CONST_IF_CNT, }; enum ocelot_ptp_pins { @@ -621,7 +632,7 @@ struct ocelot { struct list_head multicast; struct ocelot_vcap_block block; - const struct vcap_props *vcap; + struct vcap_props *vcap; /* Workqueue to check statistics for overflow with its lock */ struct mutex stats_lock; diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 707e609ec919..96300adf3648 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -17,8 +17,11 @@ enum { VCAP_ES0, VCAP_IS1, VCAP_IS2, + __VCAP_COUNT, }; +#define OCELOT_NUM_VCAP_BLOCKS __VCAP_COUNT + struct vcap_props { u16 tg_width; /* Type-group width (in bits) */ u16 sw_count; /* Sub word count */ -- cgit v1.2.3 From c9ca43d42ed8d5fd635d327a664ed1d8579eb2af Mon Sep 17 00:00:00 2001 From: Paras Sharma Date: Wed, 30 Sep 2020 11:35:26 +0530 Subject: serial: qcom_geni_serial: To correct QUP Version detection logic For QUP IP versions 2.5 and above the oversampling rate is halved from 32 to 16. Commit ce734600545f ("tty: serial: qcom_geni_serial: Update the oversampling rate") is pushed to handle this scenario. But the existing logic is failing to classify QUP Version 3.0 into the correct group ( 2.5 and above). As result Serial Engine clocks are not configured properly for baud rate and garbage data is sampled to FIFOs from the line. So, fix the logic to detect QUP with versions 2.5 and above. Fixes: ce734600545f ("tty: serial: qcom_geni_serial: Update the oversampling rate") Cc: stable Signed-off-by: Paras Sharma Reviewed-by: Akash Asthana Link: https://lore.kernel.org/r/1601445926-23673-1-git-send-email-parashar@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- include/linux/qcom-geni-se.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 8f385fbe5a0e..1c31f26ccc7a 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -248,6 +248,9 @@ struct geni_se { #define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) #define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) +/* QUP SE VERSION value for major number 2 and minor number 5 */ +#define QUP_SE_VERSION_2_5 0x20050000 + /* * Define bandwidth thresholds that cause the underlying Core 2X interconnect * clock to run at the named frequency. These baseline values are recommended -- cgit v1.2.3 From 714fb2fbe7379d0a413be217194f7af9814f2079 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Thu, 24 Sep 2020 13:42:11 +0530 Subject: mtd: hyperbus: Provide per device private pointer Provide per device private pointer that can be used by controller drivers to store device specific private data. Signed-off-by: Vignesh Raghavendra Link: https://lore.kernel.org/r/20200924081214.16934-2-vigneshr@ti.com --- include/linux/mtd/hyperbus.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h index 2129f7d3b6eb..d8cb1aec826d 100644 --- a/include/linux/mtd/hyperbus.h +++ b/include/linux/mtd/hyperbus.h @@ -20,6 +20,7 @@ enum hyperbus_memtype { * @mtd: pointer to MTD struct * @ctlr: pointer to HyperBus controller struct * @memtype: type of memory device: HyperFlash or HyperRAM + * @priv: pointer to controller specific per device private data */ struct hyperbus_device { @@ -28,6 +29,7 @@ struct hyperbus_device { struct mtd_info *mtd; struct hyperbus_ctlr *ctlr; enum hyperbus_memtype memtype; + void *priv; }; /** -- cgit v1.2.3 From 0fd16012adc0a994a7ce980a78e22e4de6220778 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 29 Sep 2020 12:09:55 +0200 Subject: lib: string_helpers: provide kfree_strarray() There's a common pattern of dynamically allocating an array of char pointers and then also dynamically allocating each string in this array. Provide a helper for freeing such a string array with one call. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko --- include/linux/string_helpers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 86f150c2a6b6..fa06dcdc481e 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -94,4 +94,6 @@ char *kstrdup_quotable(const char *src, gfp_t gfp); char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp); char *kstrdup_quotable_file(struct file *file, gfp_t gfp); +void kfree_strarray(char **array, size_t n); + #endif -- cgit v1.2.3 From 539430fbbcc4a8d02451c77fff1ecd1f3b5f8abf Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Mon, 28 Sep 2020 08:27:50 +0800 Subject: gpio: uapi: define GPIO_MAX_NAME_SIZE for array sizes Replace constant array sizes with a macro constant to clarify the source of array sizes, provide a place to document any constraints on the size, and to simplify array sizing in userspace if constructing structs from their composite fields. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 9c27cecf406f..285cc10355b2 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -14,6 +14,11 @@ #include #include +/* + * The maximum size of name and label arrays. + */ +#define GPIO_MAX_NAME_SIZE 32 + /** * struct gpiochip_info - Information about a certain GPIO chip * @name: the Linux kernel name of this GPIO chip @@ -22,8 +27,8 @@ * @lines: number of GPIO lines on this chip */ struct gpiochip_info { - char name[32]; - char label[32]; + char name[GPIO_MAX_NAME_SIZE]; + char label[GPIO_MAX_NAME_SIZE]; __u32 lines; }; @@ -52,8 +57,8 @@ struct gpiochip_info { struct gpioline_info { __u32 line_offset; __u32 flags; - char name[32]; - char consumer[32]; + char name[GPIO_MAX_NAME_SIZE]; + char consumer[GPIO_MAX_NAME_SIZE]; }; /* Maximum number of requested handles */ @@ -123,7 +128,7 @@ struct gpiohandle_request { __u32 lineoffsets[GPIOHANDLES_MAX]; __u32 flags; __u8 default_values[GPIOHANDLES_MAX]; - char consumer_label[32]; + char consumer_label[GPIO_MAX_NAME_SIZE]; __u32 lines; int fd; }; @@ -182,7 +187,7 @@ struct gpioevent_request { __u32 lineoffset; __u32 handleflags; __u32 eventflags; - char consumer_label[32]; + char consumer_label[GPIO_MAX_NAME_SIZE]; int fd; }; -- cgit v1.2.3 From b53911aa872db462be2e5f1dd611b25c4c2e663b Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Mon, 28 Sep 2020 08:27:51 +0800 Subject: gpio: uapi: define uAPI v2 Add a new version of the uAPI to address existing 32/64-bit alignment issues, add support for debounce and event sequence numbers, allow requested lines with different configurations, and provide some future proofing by adding padding reserved for future use. The alignment issue relates to the gpioevent_data, which packs to different sizes on 32-bit and 64-bit platforms. That creates problems for 32-bit apps running on 64-bit kernels. uAPI v2 addresses that particular issue, and the problem more generally, by adding pad fields that explicitly pad structs out to 64-bit boundaries, so they will pack to the same size now, and even if some of the reserved padding is used for __u64 fields in the future. The new structs have been analysed with pahole to ensure that they are sized as expected and contain no implicit padding. The lack of future proofing in v1 makes it impossible to, for example, add the debounce feature that is included in v2. The future proofing is addressed by providing configurable attributes in line config and reserved padding in all structs for future features. Specifically, the line request, config, info, info_changed and event structs receive updated versions and new ioctls. As the majority of the structs and ioctls were being replaced, it is opportune to rework some of the other aspects of the uAPI: v1 has three different flags fields, each with their own separate bit definitions. In v2 that is collapsed to one - gpio_v2_line_flag. The handle and event requests are merged into a single request, the line request, as the two requests were mostly the same other than the edge detection provided by event requests. As a byproduct, the v2 uAPI allows for multiple lines producing edge events on the same line handle. This is a new capability as v1 only supports a single line in an event request. As a consequence, there are now only two types of file handle to be concerned with, the chip and the line, and it is clearer which ioctls apply to which type of handle. There is also some minor renaming of fields for consistency compared to their v1 counterparts, e.g. offset rather than lineoffset or line_offset, and consumer rather than consumer_label. Additionally, v1 GPIOHANDLES_MAX becomes GPIO_V2_LINES_MAX in v2 for clarity, and the gpiohandle_data __u8 array becomes a bitmap in gpio_v2_line_values. The v2 uAPI is mostly a reorganisation and extension of v1, so userspace code, particularly libgpiod, should readily port to it. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 291 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 284 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 285cc10355b2..5904f49399de 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -11,11 +11,14 @@ #ifndef _UAPI_GPIO_H_ #define _UAPI_GPIO_H_ +#include #include #include /* * The maximum size of name and label arrays. + * + * Must be a multiple of 8 to ensure 32/64-bit alignment of structs. */ #define GPIO_MAX_NAME_SIZE 32 @@ -32,6 +35,265 @@ struct gpiochip_info { __u32 lines; }; +/* + * Maximum number of requested lines. + * + * Must be no greater than 64, as bitmaps are restricted here to 64-bits + * for simplicity, and a multiple of 2 to ensure 32/64-bit alignment of + * structs. + */ +#define GPIO_V2_LINES_MAX 64 + +/* + * The maximum number of configuration attributes associated with a line + * request. + */ +#define GPIO_V2_LINE_NUM_ATTRS_MAX 10 + +/** + * enum gpio_v2_line_flag - &struct gpio_v2_line_attribute.flags values + * @GPIO_V2_LINE_FLAG_USED: line is not available for request + * @GPIO_V2_LINE_FLAG_ACTIVE_LOW: line active state is physical low + * @GPIO_V2_LINE_FLAG_INPUT: line is an input + * @GPIO_V2_LINE_FLAG_OUTPUT: line is an output + * @GPIO_V2_LINE_FLAG_EDGE_RISING: line detects rising (inactive to active) + * edges + * @GPIO_V2_LINE_FLAG_EDGE_FALLING: line detects falling (active to + * inactive) edges + * @GPIO_V2_LINE_FLAG_OPEN_DRAIN: line is an open drain output + * @GPIO_V2_LINE_FLAG_OPEN_SOURCE: line is an open source output + * @GPIO_V2_LINE_FLAG_BIAS_PULL_UP: line has pull-up bias enabled + * @GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN: line has pull-down bias enabled + * @GPIO_V2_LINE_FLAG_BIAS_DISABLED: line has bias disabled + */ +enum gpio_v2_line_flag { + GPIO_V2_LINE_FLAG_USED = _BITULL(0), + GPIO_V2_LINE_FLAG_ACTIVE_LOW = _BITULL(1), + GPIO_V2_LINE_FLAG_INPUT = _BITULL(2), + GPIO_V2_LINE_FLAG_OUTPUT = _BITULL(3), + GPIO_V2_LINE_FLAG_EDGE_RISING = _BITULL(4), + GPIO_V2_LINE_FLAG_EDGE_FALLING = _BITULL(5), + GPIO_V2_LINE_FLAG_OPEN_DRAIN = _BITULL(6), + GPIO_V2_LINE_FLAG_OPEN_SOURCE = _BITULL(7), + GPIO_V2_LINE_FLAG_BIAS_PULL_UP = _BITULL(8), + GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN = _BITULL(9), + GPIO_V2_LINE_FLAG_BIAS_DISABLED = _BITULL(10), +}; + +/** + * struct gpio_v2_line_values - Values of GPIO lines + * @bits: a bitmap containing the value of the lines, set to 1 for active + * and 0 for inactive. + * @mask: a bitmap identifying the lines to get or set, with each bit + * number corresponding to the index into &struct + * gpio_v2_line_request.offsets. + */ +struct gpio_v2_line_values { + __aligned_u64 bits; + __aligned_u64 mask; +}; + +/** + * enum gpio_v2_line_attr_id - &struct gpio_v2_line_attribute.id values + * identifying which field of the attribute union is in use. + * @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use + * @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use + * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use + */ +enum gpio_v2_line_attr_id { + GPIO_V2_LINE_ATTR_ID_FLAGS = 1, + GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES = 2, + GPIO_V2_LINE_ATTR_ID_DEBOUNCE = 3, +}; + +/** + * struct gpio_v2_line_attribute - a configurable attribute of a line + * @id: attribute identifier with value from &enum gpio_v2_line_attr_id + * @padding: reserved for future use and must be zero filled + * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO + * line, with values from enum gpio_v2_line_flag, such as + * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed + * together. This overrides the default flags contained in the &struct + * gpio_v2_line_config for the associated line. + * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap + * containing the values to which the lines will be set, with each bit + * number corresponding to the index into &struct + * gpio_v2_line_request.offsets. + * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired + * debounce period, in microseconds + */ +struct gpio_v2_line_attribute { + __u32 id; + __u32 padding; + union { + __aligned_u64 flags; + __aligned_u64 values; + __u32 debounce_period_us; + }; +}; + +/** + * struct gpio_v2_line_config_attribute - a configuration attribute + * associated with one or more of the requested lines. + * @attr: the configurable attribute + * @mask: a bitmap identifying the lines to which the attribute applies, + * with each bit number corresponding to the index into &struct + * gpio_v2_line_request.offsets. + */ +struct gpio_v2_line_config_attribute { + struct gpio_v2_line_attribute attr; + __aligned_u64 mask; +}; + +/** + * struct gpio_v2_line_config - Configuration for GPIO lines + * @flags: flags for the GPIO lines, with values from enum + * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together. This is the default for + * all requested lines but may be overridden for particular lines using + * attrs. + * @num_attrs: the number of attributes in attrs + * @padding: reserved for future use and must be zero filled + * @attrs: the configuration attributes associated with the requested + * lines. Any attribute should only be associated with a particular line + * once. If an attribute is associated with a line multiple times then the + * first occurrence (i.e. lowest index) has precedence. + */ +struct gpio_v2_line_config { + __aligned_u64 flags; + __u32 num_attrs; + /* Pad to fill implicit padding and reserve space for future use. */ + __u32 padding[5]; + struct gpio_v2_line_config_attribute attrs[GPIO_V2_LINE_NUM_ATTRS_MAX]; +}; + +/** + * struct gpio_v2_line_request - Information about a request for GPIO lines + * @offsets: an array of desired lines, specified by offset index for the + * associated GPIO chip + * @consumer: a desired consumer label for the selected GPIO lines such as + * "my-bitbanged-relay" + * @config: requested configuration for the lines. + * @num_lines: number of lines requested in this request, i.e. the number + * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to + * request a single line + * @event_buffer_size: a suggested minimum number of line events that the + * kernel should buffer. This is only relevant if edge detection is + * enabled in the configuration. Note that this is only a suggested value + * and the kernel may allocate a larger buffer or cap the size of the + * buffer. If this field is zero then the buffer size defaults to a minimum + * of num_lines*16. + * @padding: reserved for future use and must be zero filled + * @fd: if successful this field will contain a valid anonymous file handle + * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means + * error + */ +struct gpio_v2_line_request { + __u32 offsets[GPIO_V2_LINES_MAX]; + char consumer[GPIO_MAX_NAME_SIZE]; + struct gpio_v2_line_config config; + __u32 num_lines; + __u32 event_buffer_size; + /* Pad to fill implicit padding and reserve space for future use. */ + __u32 padding[5]; + __s32 fd; +}; + +/** + * struct gpio_v2_line_info - Information about a certain GPIO line + * @name: the name of this GPIO line, such as the output pin of the line on + * the chip, a rail or a pin header name on a board, as specified by the + * GPIO chip, may be empty + * @consumer: a functional name for the consumer of this GPIO line as set + * by whatever is using it, will be empty if there is no current user but + * may also be empty if the consumer doesn't set this up + * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together + * @offset: the local offset on this GPIO chip, fill this in when + * requesting the line information from the kernel + * @num_attrs: the number of attributes in attrs + * @attrs: the configuration attributes associated with the line + * @padding: reserved for future use + */ +struct gpio_v2_line_info { + char name[GPIO_MAX_NAME_SIZE]; + char consumer[GPIO_MAX_NAME_SIZE]; + __u32 offset; + __u32 num_attrs; + __aligned_u64 flags; + struct gpio_v2_line_attribute attrs[GPIO_V2_LINE_NUM_ATTRS_MAX]; + /* Space reserved for future use. */ + __u32 padding[4]; +}; + +/** + * enum gpio_v2_line_changed_type - &struct gpio_v2_line_changed.event_type + * values + * @GPIO_V2_LINE_CHANGED_REQUESTED: line has been requested + * @GPIO_V2_LINE_CHANGED_RELEASED: line has been released + * @GPIO_V2_LINE_CHANGED_CONFIG: line has been reconfigured + */ +enum gpio_v2_line_changed_type { + GPIO_V2_LINE_CHANGED_REQUESTED = 1, + GPIO_V2_LINE_CHANGED_RELEASED = 2, + GPIO_V2_LINE_CHANGED_CONFIG = 3, +}; + +/** + * struct gpio_v2_line_info_changed - Information about a change in status + * of a GPIO line + * @info: updated line information + * @timestamp_ns: estimate of time of status change occurrence, in nanoseconds + * @event_type: the type of change with a value from enum + * gpio_v2_line_changed_type + * @padding: reserved for future use + */ +struct gpio_v2_line_info_changed { + struct gpio_v2_line_info info; + __aligned_u64 timestamp_ns; + __u32 event_type; + /* Pad struct to 64-bit boundary and reserve space for future use. */ + __u32 padding[5]; +}; + +/** + * enum gpio_v2_line_event_id - &struct gpio_v2_line_event.id values + * @GPIO_V2_LINE_EVENT_RISING_EDGE: event triggered by a rising edge + * @GPIO_V2_LINE_EVENT_FALLING_EDGE: event triggered by a falling edge + */ +enum gpio_v2_line_event_id { + GPIO_V2_LINE_EVENT_RISING_EDGE = 1, + GPIO_V2_LINE_EVENT_FALLING_EDGE = 2, +}; + +/** + * struct gpio_v2_line_event - The actual event being pushed to userspace + * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds. + * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the + * accurate measurement of the time between events. It does not provide + * the wall-clock time. + * @id: event identifier with value from enum gpio_v2_line_event_id + * @offset: the offset of the line that triggered the event + * @seqno: the sequence number for this event in the sequence of events for + * all the lines in this line request + * @line_seqno: the sequence number for this event in the sequence of + * events on this particular line + * @padding: reserved for future use + */ +struct gpio_v2_line_event { + __aligned_u64 timestamp_ns; + __u32 id; + __u32 offset; + __u32 seqno; + __u32 line_seqno; + /* Space reserved for future use. */ + __u32 padding[6]; +}; + +/* + * ABI v1 + */ + /* Informational flags */ #define GPIOLINE_FLAG_KERNEL (1UL << 0) /* Line used by the kernel */ #define GPIOLINE_FLAG_IS_OUT (1UL << 1) @@ -149,8 +411,6 @@ struct gpiohandle_config { __u32 padding[4]; /* padding for future use */ }; -#define GPIOHANDLE_SET_CONFIG_IOCTL _IOWR(0xB4, 0x0a, struct gpiohandle_config) - /** * struct gpiohandle_data - Information of values on a GPIO handle * @values: when getting the state of lines this contains the current @@ -161,9 +421,6 @@ struct gpiohandle_data { __u8 values[GPIOHANDLES_MAX]; }; -#define GPIOHANDLE_GET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x08, struct gpiohandle_data) -#define GPIOHANDLE_SET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x09, struct gpiohandle_data) - /* Eventrequest flags */ #define GPIOEVENT_REQUEST_RISING_EDGE (1UL << 0) #define GPIOEVENT_REQUEST_FALLING_EDGE (1UL << 1) @@ -207,11 +464,31 @@ struct gpioevent_data { __u32 id; }; +/* + * v1 and v2 ioctl()s + */ #define GPIO_GET_CHIPINFO_IOCTL _IOR(0xB4, 0x01, struct gpiochip_info) +#define GPIO_GET_LINEINFO_UNWATCH_IOCTL _IOWR(0xB4, 0x0C, __u32) + +/* + * v2 ioctl()s + */ +#define GPIO_V2_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x05, struct gpio_v2_line_info) +#define GPIO_V2_GET_LINEINFO_WATCH_IOCTL _IOWR(0xB4, 0x06, struct gpio_v2_line_info) +#define GPIO_V2_GET_LINE_IOCTL _IOWR(0xB4, 0x07, struct gpio_v2_line_request) +#define GPIO_V2_LINE_SET_CONFIG_IOCTL _IOWR(0xB4, 0x0D, struct gpio_v2_line_config) +#define GPIO_V2_LINE_GET_VALUES_IOCTL _IOWR(0xB4, 0x0E, struct gpio_v2_line_values) +#define GPIO_V2_LINE_SET_VALUES_IOCTL _IOWR(0xB4, 0x0F, struct gpio_v2_line_values) + +/* + * v1 ioctl()s + */ #define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info) -#define GPIO_GET_LINEINFO_WATCH_IOCTL _IOWR(0xB4, 0x0b, struct gpioline_info) -#define GPIO_GET_LINEINFO_UNWATCH_IOCTL _IOWR(0xB4, 0x0c, __u32) #define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request) #define GPIO_GET_LINEEVENT_IOCTL _IOWR(0xB4, 0x04, struct gpioevent_request) +#define GPIOHANDLE_GET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x08, struct gpiohandle_data) +#define GPIOHANDLE_SET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x09, struct gpiohandle_data) +#define GPIOHANDLE_SET_CONFIG_IOCTL _IOWR(0xB4, 0x0A, struct gpiohandle_config) +#define GPIO_GET_LINEINFO_WATCH_IOCTL _IOWR(0xB4, 0x0B, struct gpioline_info) #endif /* _UAPI_GPIO_H_ */ -- cgit v1.2.3 From b234d233fe30c63c4e461b03e2884a6765c8e5b0 Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Mon, 28 Sep 2020 08:28:00 +0800 Subject: gpio: uapi: document uAPI v1 as deprecated Update uAPI documentation to deprecate v1 structs and ioctls. Signed-off-by: Kent Gibson Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 5904f49399de..07865c601099 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -292,6 +292,9 @@ struct gpio_v2_line_event { /* * ABI v1 + * + * This version of the ABI is deprecated. + * Use the latest version of the ABI, defined above, instead. */ /* Informational flags */ @@ -315,6 +318,9 @@ struct gpio_v2_line_event { * @consumer: a functional name for the consumer of this GPIO line as set by * whatever is using it, will be empty if there is no current user but may * also be empty if the consumer doesn't set this up + * + * This struct is part of ABI v1 and is deprecated. + * Use struct gpio_v2_line_info instead. */ struct gpioline_info { __u32 line_offset; @@ -346,6 +352,9 @@ enum { * guarantee there are no implicit holes between it and subsequent members. * The 20-byte padding at the end makes sure we don't add any implicit padding * at the end of the structure on 64-bit architectures. + * + * This struct is part of ABI v1 and is deprecated. + * Use struct gpio_v2_line_info_changed instead. */ struct gpioline_info_changed { struct gpioline_info info; @@ -385,6 +394,9 @@ struct gpioline_info_changed { * @fd: if successful this field will contain a valid anonymous file handle * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value * means error + * + * This struct is part of ABI v1 and is deprecated. + * Use struct gpio_v2_line_request instead. */ struct gpiohandle_request { __u32 lineoffsets[GPIOHANDLES_MAX]; @@ -404,6 +416,9 @@ struct gpiohandle_request { * this specifies the default output value, should be 0 (low) or * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) * @padding: reserved for future use and should be zero filled + * + * This struct is part of ABI v1 and is deprecated. + * Use struct gpio_v2_line_config instead. */ struct gpiohandle_config { __u32 flags; @@ -416,6 +431,9 @@ struct gpiohandle_config { * @values: when getting the state of lines this contains the current * state of a line, when setting the state of lines these should contain * the desired target state + * + * This struct is part of ABI v1 and is deprecated. + * Use struct gpio_v2_line_values instead. */ struct gpiohandle_data { __u8 values[GPIOHANDLES_MAX]; @@ -439,6 +457,9 @@ struct gpiohandle_data { * @fd: if successful this field will contain a valid anonymous file handle * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value * means error + * + * This struct is part of ABI v1 and is deprecated. + * Use struct gpio_v2_line_request instead. */ struct gpioevent_request { __u32 lineoffset; @@ -458,6 +479,9 @@ struct gpioevent_request { * struct gpioevent_data - The actual event being pushed to userspace * @timestamp: best estimate of time of event occurrence, in nanoseconds * @id: event identifier + * + * This struct is part of ABI v1 and is deprecated. + * Use struct gpio_v2_line_event instead. */ struct gpioevent_data { __u64 timestamp; @@ -482,6 +506,8 @@ struct gpioevent_data { /* * v1 ioctl()s + * + * These ioctl()s are deprecated. Use the v2 equivalent instead. */ #define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info) #define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request) -- cgit v1.2.3 From 002f2176532093753cb6ced61e5ea7b8904c6cae Mon Sep 17 00:00:00 2001 From: "Jose M. Guisado Gomez" Date: Mon, 28 Sep 2020 14:27:10 +0200 Subject: netfilter: nf_tables: add userdata attributes to nft_chain Enables storing userdata for nft_chain. Field udata points to user data and udlen stores its length. Adds new attribute flag NFTA_CHAIN_USERDATA. Signed-off-by: Jose M. Guisado Gomez Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ include/uapi/linux/netfilter/nf_tables.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c4c526507ddb..0bd2a081ae39 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -945,6 +945,8 @@ struct nft_chain { bound:1, genmask:2; char *name; + u16 udlen; + u8 *udata; /* Only used during control plane commit phase: */ struct nft_rule **rules_next; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 3c2469b43742..352ee51707a1 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -208,6 +208,7 @@ enum nft_chain_flags { * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes) * @NFTA_CHAIN_FLAGS: chain flags * @NFTA_CHAIN_ID: uniquely identifies a chain in a transaction (NLA_U32) + * @NFTA_CHAIN_USERDATA: user data (NLA_BINARY) */ enum nft_chain_attributes { NFTA_CHAIN_UNSPEC, @@ -222,6 +223,7 @@ enum nft_chain_attributes { NFTA_CHAIN_PAD, NFTA_CHAIN_FLAGS, NFTA_CHAIN_ID, + NFTA_CHAIN_USERDATA, __NFTA_CHAIN_MAX }; #define NFTA_CHAIN_MAX (__NFTA_CHAIN_MAX - 1) -- cgit v1.2.3 From ba90e0c92666979298a2c42ca396ac56d00cf33e Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Wed, 30 Sep 2020 15:20:27 +0300 Subject: dt-bindings: ti-serdes-mux: Add defines for J7200 SoC There are 4 lanes in each J7200 SERDES. Each SERDES lane mux can select upto 4 different IPs. Define all the possible functions. Signed-off-by: Roger Quadros Signed-off-by: Nishanth Menon Reviewed-by: Vignesh Raghavendra Acked-by: Rob Herring Acked-by: Peter Rosin Cc: Peter Rosin Link: https://lore.kernel.org/r/20200930122032.23481-2-rogerq@ti.com --- include/dt-bindings/mux/ti-serdes.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/mux/ti-serdes.h b/include/dt-bindings/mux/ti-serdes.h index 146d0685a925..9047ec6bd3cf 100644 --- a/include/dt-bindings/mux/ti-serdes.h +++ b/include/dt-bindings/mux/ti-serdes.h @@ -68,4 +68,26 @@ #define J721E_SERDES4_LANE3_QSGMII_LANE8 0x2 #define J721E_SERDES4_LANE3_IP4_UNUSED 0x3 +/* J7200 */ + +#define J7200_SERDES0_LANE0_QSGMII_LANE3 0x0 +#define J7200_SERDES0_LANE0_PCIE1_LANE0 0x1 +#define J7200_SERDES0_LANE0_IP3_UNUSED 0x2 +#define J7200_SERDES0_LANE0_IP4_UNUSED 0x3 + +#define J7200_SERDES0_LANE1_QSGMII_LANE4 0x0 +#define J7200_SERDES0_LANE1_PCIE1_LANE1 0x1 +#define J7200_SERDES0_LANE1_IP3_UNUSED 0x2 +#define J7200_SERDES0_LANE1_IP4_UNUSED 0x3 + +#define J7200_SERDES0_LANE2_QSGMII_LANE1 0x0 +#define J7200_SERDES0_LANE2_PCIE1_LANE2 0x1 +#define J7200_SERDES0_LANE2_IP3_UNUSED 0x2 +#define J7200_SERDES0_LANE2_IP4_UNUSED 0x3 + +#define J7200_SERDES0_LANE3_QSGMII_LANE2 0x0 +#define J7200_SERDES0_LANE3_PCIE1_LANE3 0x1 +#define J7200_SERDES0_LANE3_USB 0x2 +#define J7200_SERDES0_LANE3_IP4_UNUSED 0x3 + #endif /* _DT_BINDINGS_MUX_TI_SERDES */ -- cgit v1.2.3 From 112c35237c726cb2c6eed32db660f285938fb666 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Tue, 29 Sep 2020 12:53:44 -0700 Subject: Partially revert "video: fbdev: amba-clcd: Retire elder CLCD driver" Also partially revert the follow-up change "drm: pl111: Absorb the external register header". This reverts the parts of commits 7e4e589db76a3cf4c1f534eb5a09cc6422766b93 and 0fb8125635e8eb5483fb095f98dcf0651206a7b8 that touch paths outside of drivers/gpu/drm/pl111. The fbdev driver is used by Android's FVP configuration. Using the DRM driver together with DRM's fbdev emulation results in a failure to boot Android. The root cause is that Android's generic fbdev userspace driver relies on the ability to set the pixel format via FBIOPUT_VSCREENINFO, which is not supported by fbdev emulation. There have been other less critical behavioral differences identified between the fbdev driver and the DRM driver with fbdev emulation. The DRM driver exposes different values for the panel's width, height and refresh rate, and the DRM driver fails a FBIOPUT_VSCREENINFO syscall with yres_virtual greater than the maximum supported value instead of letting the syscall succeed and setting yres_virtual based on yres. Signed-off-by: Peter Collingbourne Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200929195344.2219796-1-pcc@google.com --- include/linux/amba/clcd-regs.h | 87 +++++++++++++ include/linux/amba/clcd.h | 290 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 377 insertions(+) create mode 100644 include/linux/amba/clcd-regs.h create mode 100644 include/linux/amba/clcd.h (limited to 'include') diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h new file mode 100644 index 000000000000..421b0fa90d6a --- /dev/null +++ b/include/linux/amba/clcd-regs.h @@ -0,0 +1,87 @@ +/* + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#ifndef AMBA_CLCD_REGS_H +#define AMBA_CLCD_REGS_H + +/* + * CLCD Controller Internal Register addresses + */ +#define CLCD_TIM0 0x00000000 +#define CLCD_TIM1 0x00000004 +#define CLCD_TIM2 0x00000008 +#define CLCD_TIM3 0x0000000c +#define CLCD_UBAS 0x00000010 +#define CLCD_LBAS 0x00000014 + +#define CLCD_PL110_IENB 0x00000018 +#define CLCD_PL110_CNTL 0x0000001c +#define CLCD_PL110_STAT 0x00000020 +#define CLCD_PL110_INTR 0x00000024 +#define CLCD_PL110_UCUR 0x00000028 +#define CLCD_PL110_LCUR 0x0000002C + +#define CLCD_PL111_CNTL 0x00000018 +#define CLCD_PL111_IENB 0x0000001c +#define CLCD_PL111_RIS 0x00000020 +#define CLCD_PL111_MIS 0x00000024 +#define CLCD_PL111_ICR 0x00000028 +#define CLCD_PL111_UCUR 0x0000002c +#define CLCD_PL111_LCUR 0x00000030 + +#define CLCD_PALL 0x00000200 +#define CLCD_PALETTE 0x00000200 + +#define TIM2_PCD_LO_MASK GENMASK(4, 0) +#define TIM2_PCD_LO_BITS 5 +#define TIM2_CLKSEL (1 << 5) +#define TIM2_ACB_MASK GENMASK(10, 6) +#define TIM2_IVS (1 << 11) +#define TIM2_IHS (1 << 12) +#define TIM2_IPC (1 << 13) +#define TIM2_IOE (1 << 14) +#define TIM2_BCD (1 << 26) +#define TIM2_PCD_HI_MASK GENMASK(31, 27) +#define TIM2_PCD_HI_BITS 5 +#define TIM2_PCD_HI_SHIFT 27 + +#define CNTL_LCDEN (1 << 0) +#define CNTL_LCDBPP1 (0 << 1) +#define CNTL_LCDBPP2 (1 << 1) +#define CNTL_LCDBPP4 (2 << 1) +#define CNTL_LCDBPP8 (3 << 1) +#define CNTL_LCDBPP16 (4 << 1) +#define CNTL_LCDBPP16_565 (6 << 1) +#define CNTL_LCDBPP16_444 (7 << 1) +#define CNTL_LCDBPP24 (5 << 1) +#define CNTL_LCDBW (1 << 4) +#define CNTL_LCDTFT (1 << 5) +#define CNTL_LCDMONO8 (1 << 6) +#define CNTL_LCDDUAL (1 << 7) +#define CNTL_BGR (1 << 8) +#define CNTL_BEBO (1 << 9) +#define CNTL_BEPO (1 << 10) +#define CNTL_LCDPWR (1 << 11) +#define CNTL_LCDVCOMP(x) ((x) << 12) +#define CNTL_LDMAFIFOTIME (1 << 15) +#define CNTL_WATERMARK (1 << 16) + +/* ST Microelectronics variant bits */ +#define CNTL_ST_1XBPP_444 0x0 +#define CNTL_ST_1XBPP_5551 (1 << 17) +#define CNTL_ST_1XBPP_565 (1 << 18) +#define CNTL_ST_CDWID_12 0x0 +#define CNTL_ST_CDWID_16 (1 << 19) +#define CNTL_ST_CDWID_18 (1 << 20) +#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) +#define CNTL_ST_CEAEN (1 << 21) +#define CNTL_ST_LCDBPP24_PACKED (6 << 1) + +#endif /* AMBA_CLCD_REGS_H */ diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h new file mode 100644 index 000000000000..b6e0cbeaf533 --- /dev/null +++ b/include/linux/amba/clcd.h @@ -0,0 +1,290 @@ +/* + * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel. + * + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ +#include +#include + +enum { + /* individual formats */ + CLCD_CAP_RGB444 = (1 << 0), + CLCD_CAP_RGB5551 = (1 << 1), + CLCD_CAP_RGB565 = (1 << 2), + CLCD_CAP_RGB888 = (1 << 3), + CLCD_CAP_BGR444 = (1 << 4), + CLCD_CAP_BGR5551 = (1 << 5), + CLCD_CAP_BGR565 = (1 << 6), + CLCD_CAP_BGR888 = (1 << 7), + + /* connection layouts */ + CLCD_CAP_444 = CLCD_CAP_RGB444 | CLCD_CAP_BGR444, + CLCD_CAP_5551 = CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551, + CLCD_CAP_565 = CLCD_CAP_RGB565 | CLCD_CAP_BGR565, + CLCD_CAP_888 = CLCD_CAP_RGB888 | CLCD_CAP_BGR888, + + /* red/blue ordering */ + CLCD_CAP_RGB = CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 | + CLCD_CAP_RGB565 | CLCD_CAP_RGB888, + CLCD_CAP_BGR = CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 | + CLCD_CAP_BGR565 | CLCD_CAP_BGR888, + + CLCD_CAP_ALL = CLCD_CAP_BGR | CLCD_CAP_RGB, +}; + +struct backlight_device; + +struct clcd_panel { + struct fb_videomode mode; + signed short width; /* width in mm */ + signed short height; /* height in mm */ + u32 tim2; + u32 tim3; + u32 cntl; + u32 caps; + unsigned int bpp:8, + fixedtimings:1, + grayscale:1; + unsigned int connector; + struct backlight_device *backlight; + /* + * If the B/R lines are switched between the CLCD + * and the panel we need to know this and not try to + * compensate with the BGR bit in the control register. + */ + bool bgr_connection; +}; + +struct clcd_regs { + u32 tim0; + u32 tim1; + u32 tim2; + u32 tim3; + u32 cntl; + unsigned long pixclock; +}; + +struct clcd_fb; + +/* + * the board-type specific routines + */ +struct clcd_board { + const char *name; + + /* + * Optional. Hardware capability flags. + */ + u32 caps; + + /* + * Optional. Check whether the var structure is acceptable + * for this display. + */ + int (*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var); + + /* + * Compulsory. Decode fb->fb.var into regs->*. In the case of + * fixed timing, set regs->* to the register values required. + */ + void (*decode)(struct clcd_fb *fb, struct clcd_regs *regs); + + /* + * Optional. Disable any extra display hardware. + */ + void (*disable)(struct clcd_fb *); + + /* + * Optional. Enable any extra display hardware. + */ + void (*enable)(struct clcd_fb *); + + /* + * Setup platform specific parts of CLCD driver + */ + int (*setup)(struct clcd_fb *); + + /* + * mmap the framebuffer memory + */ + int (*mmap)(struct clcd_fb *, struct vm_area_struct *); + + /* + * Remove platform specific parts of CLCD driver + */ + void (*remove)(struct clcd_fb *); +}; + +struct amba_device; +struct clk; + +/* this data structure describes each frame buffer device we find */ +struct clcd_fb { + struct fb_info fb; + struct amba_device *dev; + struct clk *clk; + struct clcd_panel *panel; + struct clcd_board *board; + void *board_data; + void __iomem *regs; + u16 off_ienb; + u16 off_cntl; + u32 clcd_cntl; + u32 cmap[16]; + bool clk_enabled; +}; + +static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) +{ + struct fb_var_screeninfo *var = &fb->fb.var; + u32 val, cpl; + + /* + * Program the CLCD controller registers and start the CLCD + */ + val = ((var->xres / 16) - 1) << 2; + val |= (var->hsync_len - 1) << 8; + val |= (var->right_margin - 1) << 16; + val |= (var->left_margin - 1) << 24; + regs->tim0 = val; + + val = var->yres; + if (fb->panel->cntl & CNTL_LCDDUAL) + val /= 2; + val -= 1; + val |= (var->vsync_len - 1) << 10; + val |= var->lower_margin << 16; + val |= var->upper_margin << 24; + regs->tim1 = val; + + val = fb->panel->tim2; + val |= var->sync & FB_SYNC_HOR_HIGH_ACT ? 0 : TIM2_IHS; + val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS; + + cpl = var->xres_virtual; + if (fb->panel->cntl & CNTL_LCDTFT) /* TFT */ + /* / 1 */; + else if (!var->grayscale) /* STN color */ + cpl = cpl * 8 / 3; + else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */ + cpl /= 8; + else /* STN monochrome, 4bit */ + cpl /= 4; + + regs->tim2 = val | ((cpl - 1) << 16); + + regs->tim3 = fb->panel->tim3; + + val = fb->panel->cntl; + if (var->grayscale) + val |= CNTL_LCDBW; + + if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) { + /* + * if board and panel supply capabilities, we can support + * changing BGR/RGB depending on supplied parameters. Here + * we switch to what the framebuffer is providing if need + * be, so if the framebuffer is BGR but the display connection + * is RGB (first case) we switch it around. Vice versa mutatis + * mutandis if the framebuffer is RGB but the display connection + * is BGR, we flip it around. + */ + if (var->red.offset == 0) + val &= ~CNTL_BGR; + else + val |= CNTL_BGR; + if (fb->panel->bgr_connection) + val ^= CNTL_BGR; + } + + switch (var->bits_per_pixel) { + case 1: + val |= CNTL_LCDBPP1; + break; + case 2: + val |= CNTL_LCDBPP2; + break; + case 4: + val |= CNTL_LCDBPP4; + break; + case 8: + val |= CNTL_LCDBPP8; + break; + case 16: + /* + * PL110 cannot choose between 5551 and 565 modes in its + * control register. It is possible to use 565 with + * custom external wiring. + */ + if (amba_part(fb->dev) == 0x110 || + var->green.length == 5) + val |= CNTL_LCDBPP16; + else if (var->green.length == 6) + val |= CNTL_LCDBPP16_565; + else + val |= CNTL_LCDBPP16_444; + break; + case 32: + val |= CNTL_LCDBPP24; + break; + } + + regs->cntl = val; + regs->pixclock = var->pixclock; +} + +static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) +{ + var->xres_virtual = var->xres = (var->xres + 15) & ~15; + var->yres_virtual = var->yres = (var->yres + 1) & ~1; + +#define CHECK(e,l,h) (var->e < l || var->e > h) + if (CHECK(right_margin, (5+1), 256) || /* back porch */ + CHECK(left_margin, (5+1), 256) || /* front porch */ + CHECK(hsync_len, (5+1), 256) || + var->xres > 4096 || + var->lower_margin > 255 || /* back porch */ + var->upper_margin > 255 || /* front porch */ + var->vsync_len > 32 || + var->yres > 1024) + return -EINVAL; +#undef CHECK + + /* single panel mode: PCD = max(PCD, 1) */ + /* dual panel mode: PCD = max(PCD, 5) */ + + /* + * You can't change the grayscale setting, and + * we can only do non-interlaced video. + */ + if (var->grayscale != fb->fb.var.grayscale || + (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED) + return -EINVAL; + +#define CHECK(e) (var->e != fb->fb.var.e) + if (fb->panel->fixedtimings && + (CHECK(xres) || + CHECK(yres) || + CHECK(bits_per_pixel) || + CHECK(pixclock) || + CHECK(left_margin) || + CHECK(right_margin) || + CHECK(upper_margin) || + CHECK(lower_margin) || + CHECK(hsync_len) || + CHECK(vsync_len) || + CHECK(sync))) + return -EINVAL; +#undef CHECK + + var->nonstd = 0; + var->accel_flags = 0; + + return 0; +} -- cgit v1.2.3 From 27204b99b08289d0993cb77c22470034b5eb974d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 Sep 2020 15:24:43 +0200 Subject: drm: drm_dsc.h: fix a kernel-doc markup As warned by Sphinx: ./Documentation/gpu/drm-kms-helpers:305: ./include/drm/drm_dsc.h:587: WARNING: Unparseable C cross-reference: 'struct' Invalid C declaration: Expected identifier in nested name, got keyword: struct [error at 6] struct ------^ The markup for one struct is wrong, as struct is used twice. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/3d467022325e15bba8dcb13da8fb730099303266.1601467849.git.mchehab+huawei@kernel.org --- include/drm/drm_dsc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h index 887954cbfc60..732f32740c86 100644 --- a/include/drm/drm_dsc.h +++ b/include/drm/drm_dsc.h @@ -588,7 +588,7 @@ struct drm_dsc_picture_parameter_set { * This structure represents the DSC PPS infoframe required to send the Picture * Parameter Set metadata required before enabling VESA Display Stream * Compression. This is based on the DP Secondary Data Packet structure and - * comprises of SDP Header as defined &struct struct dp_sdp_header in drm_dp_helper.h + * comprises of SDP Header as defined &struct dp_sdp_header in drm_dp_helper.h * and PPS payload defined in &struct drm_dsc_picture_parameter_set. * * @pps_header: Header for PPS as per DP SDP header format of type -- cgit v1.2.3 From 1e3b37aab958861a9d0c01ff6dbec96a82743701 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:52:05 +0200 Subject: mtd: rawnand: Use the ECC framework OOB layouts No need to have our own in the raw NAND core. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-18-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 967b616c50df..1bbce6fa1b08 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -14,6 +14,7 @@ #define __LINUX_MTD_RAWNAND_H #include +#include #include #include #include @@ -1156,9 +1157,6 @@ struct nand_chip { void *priv; }; -extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; -extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops; - static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd) { return container_of(mtd, struct nand_chip, base.mtd); -- cgit v1.2.3 From d7157ff49a5b5845b37b8f2bf31607f0af295ef1 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:52:07 +0200 Subject: mtd: rawnand: Use the ECC framework user input parsing bits Many helpers are generic to all NAND chips, they should not be raw-NAND specific, so use the generic ones. To avoid moving all the raw NAND core "history" into the generic NAND layer, we keep a part of this parsing in the raw NAND core to ensure backward compatibility. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-20-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 1bbce6fa1b08..671e60948deb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -81,18 +81,6 @@ struct nand_chip; #define NAND_DATA_IFACE_CHECK_ONLY -1 -/* - * Constants for ECC_MODES - */ -enum nand_ecc_mode { - NAND_ECC_INVALID, - NAND_ECC_NONE, - NAND_ECC_SOFT, - NAND_ECC_HW, - NAND_ECC_HW_SYNDROME, - NAND_ECC_ON_DIE, -}; - /* * Constants for Hardware ECC */ -- cgit v1.2.3 From b5156335ac37f186812090795ed27884a76c3266 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Aug 2020 10:52:08 +0200 Subject: mtd: rawnand: Use the NAND framework user_conf object for ECC flags Instead of storing the ECC flags in chip->ecc.options, use nanddev->ecc.user_conf.flags. There is currently only one to save: NAND_ECC_MAXIMIZE. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-21-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 671e60948deb..aac07940de09 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -98,7 +98,6 @@ struct nand_chip; * pages and you want to rely on the default implementation. */ #define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) -#define NAND_ECC_MAXIMIZE BIT(1) /* * Option constants for bizarre disfunctionality and real -- cgit v1.2.3 From 4b6ec08fd21ee3179cbfccf3605ad13d9f38b623 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Wed, 2 Sep 2020 16:22:59 +0200 Subject: mfd: lp87565: Add LP87524-Q1 variant Add support for the LP87524B/J/P-Q1 Four 4-MHz Buck Converter. This is a variant of the LP87565 having 4 single-phase outputs and up to 10 A of total output current. Signed-off-by: Luca Ceresoli Signed-off-by: Lee Jones --- include/linux/mfd/lp87565.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h index 43716aca46fa..d44ddfb6bb63 100644 --- a/include/linux/mfd/lp87565.h +++ b/include/linux/mfd/lp87565.h @@ -14,6 +14,7 @@ enum lp87565_device_type { LP87565_DEVICE_TYPE_UNKNOWN = 0, + LP87565_DEVICE_TYPE_LP87524_Q1, LP87565_DEVICE_TYPE_LP87561_Q1, LP87565_DEVICE_TYPE_LP87565_Q1, }; -- cgit v1.2.3 From 4849bc777049b568a35d5d63ae326e93f0fff9de Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 28 Sep 2020 12:45:55 -0700 Subject: ACPI / NUMA: Add stub function for pxm_to_node() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit 01feba590cd6 ("ACPI: Do not create new NUMA domains from ACPI static tables that are not SRAT"): $ scripts/config --file arch/x86/configs/x86_64_defconfig -d NUMA -e ACPI_NFIT $ make -skj"$(nproc)" distclean defconfig drivers/acpi/nfit/ drivers/acpi/nfit/core.c: In function ‘acpi_nfit_register_region’: drivers/acpi/nfit/core.c:3010:27: error: implicit declaration of function ‘pxm_to_node’; did you mean ‘xa_to_node’? [-Werror=implicit-function-declaration] 3010 | ndr_desc->target_node = pxm_to_node(spa->proximity_domain); | ^~~~~~~~~~~ | xa_to_node cc1: some warnings being treated as errors ... Add a stub function like acpi_map_pxm_to_node() had so that the build continues to work. Fixes: 01feba590cd6 ("ACPI: Do not create new NUMA domains from ACPI static tables that are not SRAT") Signed-off-by: Nathan Chancellor Acked-by: Randy Dunlap # build-tested Acked-by: Jonathan Cameron Reviewed-by: Hanjun Guo Signed-off-by: Rafael J. Wysocki --- include/acpi/acpi_numa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h index fdebcfc6c8df..09eb3bc20ff5 100644 --- a/include/acpi/acpi_numa.h +++ b/include/acpi/acpi_numa.h @@ -22,5 +22,10 @@ extern int acpi_numa __initdata; extern void bad_srat(void); extern int srat_disabled(void); +#else /* CONFIG_ACPI_NUMA */ +static inline int pxm_to_node(int pxm) +{ + return 0; +} #endif /* CONFIG_ACPI_NUMA */ #endif /* __ACP_NUMA_H */ -- cgit v1.2.3 From 876611c493b10cbb59e0e2143d3e744d0442de63 Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Tue, 15 Sep 2020 11:44:21 +0800 Subject: mfd: intel-m10-bmc: Add Intel MAX 10 BMC chip support for Intel FPGA PAC This patch implements the basic functions of the BMC chip for some Intel FPGA PCIe Acceleration Cards (PAC). The BMC is implemented using the Intel MAX 10 CPLD. This BMC chip is connected to the FPGA by a SPI bus. To provide direct register access from the FPGA, the "SPI slave to Avalon Master Bridge" (spi-avmm) IP is integrated in the chip. It converts encoded streams of bytes from the host to the internal register read/write on the Avalon bus. So This driver uses the regmap-spi-avmm for register accessing. Signed-off-by: Xu Yilun Signed-off-by: Wu Hao Signed-off-by: Matthew Gerlach Signed-off-by: Russ Weight Reviewed-by: Tom Rix Signed-off-by: Lee Jones --- include/linux/mfd/intel-m10-bmc.h | 65 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/mfd/intel-m10-bmc.h (limited to 'include') diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h new file mode 100644 index 000000000000..c8ef2f1654a4 --- /dev/null +++ b/include/linux/mfd/intel-m10-bmc.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel MAX 10 Board Management Controller chip. + * + * Copyright (C) 2018-2020 Intel Corporation, Inc. + */ +#ifndef __MFD_INTEL_M10_BMC_H +#define __MFD_INTEL_M10_BMC_H + +#include + +#define M10BMC_LEGACY_SYS_BASE 0x300400 +#define M10BMC_SYS_BASE 0x300800 +#define M10BMC_MEM_END 0x200000fc + +/* Register offset of system registers */ +#define NIOS2_FW_VERSION 0x0 +#define M10BMC_TEST_REG 0x3c +#define M10BMC_BUILD_VER 0x68 +#define M10BMC_VER_MAJOR_MSK GENMASK(23, 16) +#define M10BMC_VER_PCB_INFO_MSK GENMASK(31, 24) +#define M10BMC_VER_LEGACY_INVALID 0xffffffff + +/** + * struct intel_m10bmc - Intel MAX 10 BMC parent driver data structure + * @dev: this device + * @regmap: the regmap used to access registers by m10bmc itself + */ +struct intel_m10bmc { + struct device *dev; + struct regmap *regmap; +}; + +/* + * register access helper functions. + * + * m10bmc_raw_read - read m10bmc register per addr + * m10bmc_sys_read - read m10bmc system register per offset + */ +static inline int +m10bmc_raw_read(struct intel_m10bmc *m10bmc, unsigned int addr, + unsigned int *val) +{ + int ret; + + ret = regmap_read(m10bmc->regmap, addr, val); + if (ret) + dev_err(m10bmc->dev, "fail to read raw reg %x: %d\n", + addr, ret); + + return ret; +} + +/* + * The base of the system registers could be configured by HW developers, and + * in HW SPEC, the base is not added to the addresses of the system registers. + * + * This macro helps to simplify the accessing of the system registers. And if + * the base is reconfigured in HW, SW developers could simply change the + * M10BMC_SYS_BASE accordingly. + */ +#define m10bmc_sys_read(m10bmc, offset, val) \ + m10bmc_raw_read(m10bmc, M10BMC_SYS_BASE + (offset), val) + +#endif /* __MFD_INTEL_M10_BMC_H */ -- cgit v1.2.3 From 8162a0b5a209b541e89336f53b96ea0c22b63945 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 29 Sep 2020 11:15:36 +0200 Subject: media: v4l2-subdev.h: fix a kernel-doc markup As reported by Sphinx: ./Documentation/driver-api/media/v4l2-subdev:490: ./include/media/v4l2-subdev.h:384: WARNING: Unparseable C cross-reference: 'struct' Invalid C declaration: Expected identifier in nested name, got keyword: struct [error at 6] struct ------^ The markup there is wrong: &struct &v4l2_input -> &struct v4l2_input Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 6f6795bab737..1de960bfcab9 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -381,7 +381,7 @@ struct v4l2_mbus_frame_desc { * OUTPUT device. This is ignored by video capture devices. * * @g_input_status: get input status. Same as the status field in the - * &struct &v4l2_input + * &struct v4l2_input * * @s_stream: used to notify the driver that a video stream will start or has * stopped. -- cgit v1.2.3 From 38b393fec298569c8ec154c750a107299bc8385d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Sun, 20 Sep 2020 00:15:36 +0200 Subject: leds: tca6507: Absorb platform data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only in-tree usage of this driver is via device-tree. No on else includes linux/leds-tca6507.h, so absorb the definition of platdata structure. Signed-off-by: Marek Behún Cc: NeilBrown Reviewed-by: Linus Walleij Tested-by: H. Nikolaus Schaller Signed-off-by: Pavel Machek --- include/linux/leds-tca6507.h | 21 --------------------- 1 file changed, 21 deletions(-) delete mode 100644 include/linux/leds-tca6507.h (limited to 'include') diff --git a/include/linux/leds-tca6507.h b/include/linux/leds-tca6507.h deleted file mode 100644 index 50d330ed1100..000000000000 --- a/include/linux/leds-tca6507.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * TCA6507 LED chip driver. - * - * Copyright (C) 2011 Neil Brown - */ - -#ifndef __LINUX_TCA6507_H -#define __LINUX_TCA6507_H -#include - -struct tca6507_platform_data { - struct led_platform_data leds; -#ifdef CONFIG_GPIOLIB - int gpio_base; - void (*setup)(unsigned gpio_base, unsigned ngpio); -#endif -}; - -#define TCA6507_MAKE_GPIO 1 -#endif /* __LINUX_TCA6507_H*/ -- cgit v1.2.3 From 85fc8efe85d405b80904f73e4e23184a84283753 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Sun, 20 Sep 2020 02:24:59 +0200 Subject: leds: pca963x: register LEDs immediately after parsing, get rid of platdata MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Register LEDs immediately after parsing their properties. This allows us to get rid of platdata, and since no one in tree uses header linux/platform_data/leds-pca963x.h, remove it. Signed-off-by: Marek Behún Cc: Peter Meerwald Cc: Ricardo Ribalda Cc: Zahari Petkov Signed-off-by: Pavel Machek --- include/linux/platform_data/leds-pca963x.h | 35 ------------------------------ 1 file changed, 35 deletions(-) delete mode 100644 include/linux/platform_data/leds-pca963x.h (limited to 'include') diff --git a/include/linux/platform_data/leds-pca963x.h b/include/linux/platform_data/leds-pca963x.h deleted file mode 100644 index 6091337ce4bf..000000000000 --- a/include/linux/platform_data/leds-pca963x.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * PCA963X LED chip driver. - * - * Copyright 2012 bct electronic GmbH - * Copyright 2013 Qtechnology A/S - */ - -#ifndef __LINUX_PCA963X_H -#define __LINUX_PCA963X_H -#include - -enum pca963x_outdrv { - PCA963X_OPEN_DRAIN, - PCA963X_TOTEM_POLE, /* aka push-pull */ -}; - -enum pca963x_blink_type { - PCA963X_SW_BLINK, - PCA963X_HW_BLINK, -}; - -enum pca963x_direction { - PCA963X_NORMAL, - PCA963X_INVERTED, -}; - -struct pca963x_platform_data { - struct led_platform_data leds; - enum pca963x_outdrv outdrv; - enum pca963x_blink_type blink_type; - enum pca963x_direction dir; -}; - -#endif /* __LINUX_PCA963X_H*/ -- cgit v1.2.3 From a6f0b08dbaf289c3c57284e16ac8043140f2139b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 29 Sep 2020 13:09:07 -0300 Subject: RDMA/core: Remove ucontext->closing Nothing reads this any more, and the reason for its existence has passed due to the deferred fput() scheme. Fixes: 8ea1f989aa07 ("drivers/IB,usnic: reduce scope of mmap_sem") Link: https://lore.kernel.org/r/0-v1-df64ff042436+42-uctx_closing_jgg@nvidia.com Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index f18502984e6f..5ad997346f7f 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1477,12 +1477,6 @@ struct ib_rdmacg_object { struct ib_ucontext { struct ib_device *device; struct ib_uverbs_file *ufile; - /* - * 'closing' can be read by the driver only during a destroy callback, - * it is set when we are closing the file descriptor and indicates - * that mm_sem may be locked. - */ - bool closing; bool cleanup_retryable; -- cgit v1.2.3 From b426ce83baa7dff947fb354118d3133f2953aac8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2020 17:18:15 +0200 Subject: bpf: Add classid helper only based on skb->sk Similarly to 5a52ae4e32a6 ("bpf: Allow to retrieve cgroup v1 classid from v2 hooks"), add a helper to retrieve cgroup v1 classid solely based on the skb->sk, so it can be used as key as part of BPF map lookups out of tc from host ns, in particular given the skb->sk is retained these days when crossing net ns thanks to 9c4c325252c5 ("skbuff: preserve sock reference when scrubbing the skb."). This is similar to bpf_skb_cgroup_id() which implements the same for v2. Kubernetes ecosystem is still operating on v1 however, hence net_cls needs to be used there until this can be dropped in with the v2 helper of bpf_skb_cgroup_id(). Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/ed633cf27a1c620e901c5aa99ebdefb028dce600.1601477936.git.daniel@iogearbox.net --- include/uapi/linux/bpf.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2b1d3f16cbd1..6116a7f54c8f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3643,6 +3643,15 @@ union bpf_attr { * *flags* are identical to those used for bpf_snprintf_btf. * Return * 0 on success or a negative error in case of failure. + * + * u64 bpf_skb_cgroup_classid(struct sk_buff *skb) + * Description + * See **bpf_get_cgroup_classid**\ () for the main description. + * This helper differs from **bpf_get_cgroup_classid**\ () in that + * the cgroup v1 net_cls class is retrieved only from the *skb*'s + * associated socket instead of the current process. + * Return + * The id is returned or 0 in case the id could not be retrieved. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3796,6 +3805,7 @@ union bpf_attr { FN(copy_from_user), \ FN(snprintf_btf), \ FN(seq_printf_btf), \ + FN(skb_cgroup_classid), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 92acdc58ab11af66fcaef485433fde61b5e32fac Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2020 17:18:16 +0200 Subject: bpf, net: Rework cookie generator as per-cpu one With its use in BPF, the cookie generator can be called very frequently in particular when used out of cgroup v2 hooks (e.g. connect / sendmsg) and attached to the root cgroup, for example, when used in v1/v2 mixed environments. In particular, when there's a high churn on sockets in the system there can be many parallel requests to the bpf_get_socket_cookie() and bpf_get_netns_cookie() helpers which then cause contention on the atomic counter. As similarly done in f991bd2e1421 ("fs: introduce a per-cpu last_ino allocator"), add a small helper library that both can use for the 64 bit counters. Given this can be called from different contexts, we also need to deal with potential nested calls even though in practice they are considered extremely rare. One idea as suggested by Eric Dumazet was to use a reverse counter for this situation since we don't expect 64 bit overflows anyways; that way, we can avoid bigger gaps in the 64 bit counter space compared to just batch-wise increase. Even on machines with small number of cores (e.g. 4) the cookie generation shrinks from min/max/med/avg (ns) of 22/50/40/38.9 down to 10/35/14/17.3 when run in parallel from multiple CPUs. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Reviewed-by: Eric Dumazet Acked-by: Martin KaFai Lau Cc: Eric Dumazet Link: https://lore.kernel.org/bpf/8a80b8d27d3c49f9a14e1d5213c19d8be87d1dc8.1601477936.git.daniel@iogearbox.net --- include/linux/cookie.h | 51 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/sock_diag.h | 14 ++++++++++++- include/net/net_namespace.h | 2 +- 3 files changed, 65 insertions(+), 2 deletions(-) create mode 100644 include/linux/cookie.h (limited to 'include') diff --git a/include/linux/cookie.h b/include/linux/cookie.h new file mode 100644 index 000000000000..0c159f585109 --- /dev/null +++ b/include/linux/cookie.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_COOKIE_H +#define __LINUX_COOKIE_H + +#include +#include +#include + +struct pcpu_gen_cookie { + local_t nesting; + u64 last; +} __aligned(16); + +struct gen_cookie { + struct pcpu_gen_cookie __percpu *local; + atomic64_t forward_last ____cacheline_aligned_in_smp; + atomic64_t reverse_last; +}; + +#define COOKIE_LOCAL_BATCH 4096 + +#define DEFINE_COOKIE(name) \ + static DEFINE_PER_CPU(struct pcpu_gen_cookie, __##name); \ + static struct gen_cookie name = { \ + .local = &__##name, \ + .forward_last = ATOMIC64_INIT(0), \ + .reverse_last = ATOMIC64_INIT(0), \ + } + +static __always_inline u64 gen_cookie_next(struct gen_cookie *gc) +{ + struct pcpu_gen_cookie *local = this_cpu_ptr(gc->local); + u64 val; + + if (likely(local_inc_return(&local->nesting) == 1)) { + val = local->last; + if (__is_defined(CONFIG_SMP) && + unlikely((val & (COOKIE_LOCAL_BATCH - 1)) == 0)) { + s64 next = atomic64_add_return(COOKIE_LOCAL_BATCH, + &gc->forward_last); + val = next - COOKIE_LOCAL_BATCH; + } + local->last = ++val; + } else { + val = atomic64_dec_return(&gc->reverse_last); + } + local_dec(&local->nesting); + return val; +} + +#endif /* __LINUX_COOKIE_H */ diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 15fe980a27ea..0b9ecd8cf979 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -25,7 +25,19 @@ void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); -u64 sock_gen_cookie(struct sock *sk); +u64 __sock_gen_cookie(struct sock *sk); + +static inline u64 sock_gen_cookie(struct sock *sk) +{ + u64 cookie; + + preempt_disable(); + cookie = __sock_gen_cookie(sk); + preempt_enable(); + + return cookie; +} + int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 2ee5901bec7a..22bc07f4b043 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -230,7 +230,7 @@ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); struct net *get_net_ns_by_fd(int fd); -u64 net_gen_cookie(struct net *net); +u64 __net_gen_cookie(struct net *net); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); -- cgit v1.2.3 From b4ab31414970a7a03a5d55d75083f2c101a30592 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2020 17:18:17 +0200 Subject: bpf: Add redirect_neigh helper as redirect drop-in Add a redirect_neigh() helper as redirect() drop-in replacement for the xmit side. Main idea for the helper is to be very similar in semantics to the latter just that the skb gets injected into the neighboring subsystem in order to let the stack do the work it knows best anyway to populate the L2 addresses of the packet and then hand over to dev_queue_xmit() as redirect() does. This solves two bigger items: i) skbs don't need to go up to the stack on the host facing veth ingress side for traffic egressing the container to achieve the same for populating L2 which also has the huge advantage that ii) the skb->sk won't get orphaned in ip_rcv_core() when entering the IP routing layer on the host stack. Given that skb->sk neither gets orphaned when crossing the netns as per 9c4c325252c5 ("skbuff: preserve sock reference when scrubbing the skb.") the helper can then push the skbs directly to the phys device where FQ scheduler can do its work and TCP stack gets proper backpressure given we hold on to skb->sk as long as skb is still residing in queues. With the helper used in BPF data path to then push the skb to the phys device, I observed a stable/consistent TCP_STREAM improvement on veth devices for traffic going container -> host -> host -> container from ~10Gbps to ~15Gbps for a single stream in my test environment. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Reviewed-by: David Ahern Acked-by: Martin KaFai Lau Cc: David Ahern Link: https://lore.kernel.org/bpf/f207de81629e1724899b73b8112e0013be782d35.1601477936.git.daniel@iogearbox.net --- include/linux/skbuff.h | 5 +++++ include/uapi/linux/bpf.h | 14 ++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 04a18e01b362..3d0cf3722bb4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2548,6 +2548,11 @@ static inline int skb_mac_header_was_set(const struct sk_buff *skb) return skb->mac_header != (typeof(skb->mac_header))~0U; } +static inline void skb_unset_mac_header(struct sk_buff *skb) +{ + skb->mac_header = (typeof(skb->mac_header))~0U; +} + static inline void skb_reset_mac_header(struct sk_buff *skb) { skb->mac_header = skb->data - skb->head; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6116a7f54c8f..1f17c6752deb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3652,6 +3652,19 @@ union bpf_attr { * associated socket instead of the current process. * Return * The id is returned or 0 in case the id could not be retrieved. + * + * long bpf_redirect_neigh(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex* + * and fill in L2 addresses from neighboring subsystem. This helper + * is somewhat similar to **bpf_redirect**\ (), except that it + * fills in e.g. MAC addresses based on the L3 information from + * the packet. This helper is supported for IPv4 and IPv6 protocols. + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3806,6 +3819,7 @@ union bpf_attr { FN(snprintf_btf), \ FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ + FN(redirect_neigh), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 14c9c014babedc6098bf4cd83c622997867bc0df Mon Sep 17 00:00:00 2001 From: Sean O'Brien Date: Wed, 9 Sep 2020 15:03:04 -0700 Subject: HID: add vivaldi HID driver Add vivaldi HID driver. This driver allows us to read and report the top row layout of keyboards which provide a vendor-defined (Google) HID usage. Signed-off-by: Sean O'Brien Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index c7044a14200e..58684657960b 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -163,6 +163,7 @@ struct hid_item { #define HID_UP_LNVENDOR 0xffa00000 #define HID_UP_SENSOR 0x00200000 #define HID_UP_ASUSVENDOR 0xff310000 +#define HID_UP_GOOGLEVENDOR 0xffd10000 #define HID_USAGE 0x0000ffff @@ -371,6 +372,7 @@ struct hid_item { #define HID_GROUP_LOGITECH_DJ_DEVICE 0x0102 #define HID_GROUP_STEAM 0x0103 #define HID_GROUP_LOGITECH_27MHZ_DEVICE 0x0104 +#define HID_GROUP_VIVALDI 0x0105 /* * HID protocol status -- cgit v1.2.3 From 20c168be684a97b084525906eb7ed017b7f9c0b8 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 30 Sep 2020 12:50:59 +0200 Subject: net: macb: move pdata to private header struct macb_platform_data is only used by macb_pci to register the platform device, move its definition to cadence/macb.h and remove platform_data/macb.h Signed-off-by: Alexandre Belloni Signed-off-by: David S. Miller --- include/linux/platform_data/macb.h | 20 -------------------- 1 file changed, 20 deletions(-) delete mode 100644 include/linux/platform_data/macb.h (limited to 'include') diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h deleted file mode 100644 index aa5b5562d6f7..000000000000 --- a/include/linux/platform_data/macb.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2004-2006 Atmel Corporation - */ -#ifndef __MACB_PDATA_H__ -#define __MACB_PDATA_H__ - -#include - -/** - * struct macb_platform_data - platform data for MACB Ethernet - * @pclk: platform clock - * @hclk: AHB clock - */ -struct macb_platform_data { - struct clk *pclk; - struct clk *hclk; -}; - -#endif /* __MACB_PDATA_H__ */ -- cgit v1.2.3 From b6b6d6533a14b5ddcf9f9c5239fc3721fc6beda0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Sep 2020 05:54:56 -0700 Subject: inet: remove icsk_ack.blocked TCP has been using it to work around the possibility of tcp_delack_timer() finding the socket owned by user. After commit 6f458dfb4092 ("tcp: improve latencies of timer triggered events") we added TCP_DELACK_TIMER_DEFERRED atomic bit for more immediate recovery, so we can get rid of icsk_ack.blocked This frees space that following patch will reuse. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index dc763ca9413c..79875f976190 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -110,7 +110,7 @@ struct inet_connection_sock { __u8 pending; /* ACK is pending */ __u8 quick; /* Scheduled number of quick acks */ __u8 pingpong; /* The session is interactive */ - __u8 blocked; /* Delayed ACK was blocked by socket lock */ + /* one byte hole. */ __u32 ato; /* Predicted tick of soft clock */ unsigned long timeout; /* Currently scheduled timeout */ __u32 lrcvtime; /* timestamp of last received data packet */ @@ -198,7 +198,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) sk_stop_timer(sk, &icsk->icsk_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { - icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0; + icsk->icsk_ack.pending = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif -- cgit v1.2.3 From a37c2134bed6f28c6d6aefa2699331e6e4e9c4f1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Sep 2020 05:54:57 -0700 Subject: tcp: add exponential backoff in __tcp_send_ack() Whenever host is under very high memory pressure, __tcp_send_ack() skb allocation fails, and we setup a 200 ms (TCP_DELACK_MAX) timer before retrying. On hosts with high number of TCP sockets, we can spend considerable amount of cpu cycles in these attempts, add high pressure on various spinlocks in mm-layer, ultimately blocking threads attempting to free space from making any progress. This patch adds standard exponential backoff to avoid adding fuel to the fire. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 79875f976190..7338b3865a2a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -110,7 +110,7 @@ struct inet_connection_sock { __u8 pending; /* ACK is pending */ __u8 quick; /* Scheduled number of quick acks */ __u8 pingpong; /* The session is interactive */ - /* one byte hole. */ + __u8 retry; /* Number of attempts */ __u32 ato; /* Predicted tick of soft clock */ unsigned long timeout; /* Currently scheduled timeout */ __u32 lrcvtime; /* timestamp of last received data packet */ @@ -199,6 +199,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) #endif } else if (what == ICSK_TIME_DACK) { icsk->icsk_ack.pending = 0; + icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif -- cgit v1.2.3 From a509a66a9d0d4f4e304d58fad38c078d0336c445 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 29 Sep 2020 15:25:22 +0200 Subject: arm64: permit ACPI core to map kernel memory used for table overrides Jonathan reports that the strict policy for memory mapped by the ACPI core breaks the use case of passing ACPI table overrides via initramfs. This is due to the fact that the memory type used for loading the initramfs in memory is not recognized as a memory type that is typically used by firmware to pass firmware tables. Since the purpose of the strict policy is to ensure that no AML or other ACPI code can manipulate any memory that is used by the kernel to keep its internal state or the state of user tasks, we can relax the permission check, and allow mappings of memory that is reserved and marked as NOMAP via memblock, and therefore not covered by the linear mapping to begin with. Fixes: 1583052d111f ("arm64/acpi: disallow AML memory opregions to access kernel memory") Fixes: 325f5585ec36 ("arm64/acpi: disallow writeable AML opregion mapping for EFI code regions") Reported-by: Jonathan Cameron Signed-off-by: Ard Biesheuvel Tested-by: Jonathan Cameron Cc: Sudeep Holla Cc: Lorenzo Pieralisi Link: https://lore.kernel.org/r/20200929132522.18067-1-ardb@kernel.org Signed-off-by: Catalin Marinas --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1e4cdc6c7ae2..64ae25c59d55 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -958,7 +958,7 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); -#ifdef CONFIG_X86 +#ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else static inline void arch_reserve_mem_area(acpi_physical_address addr, -- cgit v1.2.3 From 5b88823bfe0875b327cc041017b5dcbec9dcbcc8 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 29 Sep 2020 11:15:50 +0300 Subject: devlink: Add a tracepoint for trap reports Add a tracepoint for trap reports so that drop monitor could register its probe on it. Use trace_devlink_trap_report_enabled() to avoid wasting cycles setting the trap metadata if the tracepoint is not enabled. Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 14 ++++++++++++++ include/trace/events/devlink.h | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7339bf9ba6b4..1014294ba6a0 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -624,6 +624,20 @@ struct devlink_health_reporter_ops { struct netlink_ext_ack *extack); }; +/** + * struct devlink_trap_metadata - Packet trap metadata. + * @trap_name: Trap name. + * @trap_group_name: Trap group name. + * @input_dev: Input netdevice. + * @fa_cookie: Flow action user cookie. + */ +struct devlink_trap_metadata { + const char *trap_name; + const char *trap_group_name; + struct net_device *input_dev; + const struct flow_action_cookie *fa_cookie; +}; + /** * struct devlink_trap_policer - Immutable packet trap policer attributes. * @id: Policer identifier. diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 6f60a78d9a7e..44d8e2981065 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -171,6 +171,43 @@ TRACE_EVENT(devlink_health_reporter_state_update, __entry->new_state) ); +/* + * Tracepoint for devlink packet trap: + */ +TRACE_EVENT(devlink_trap_report, + TP_PROTO(const struct devlink *devlink, struct sk_buff *skb, + const struct devlink_trap_metadata *metadata), + + TP_ARGS(devlink, skb, metadata), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __string(trap_name, metadata->trap_name) + __string(trap_group_name, metadata->trap_group_name) + __dynamic_array(char, input_dev_name, IFNAMSIZ) + ), + + TP_fast_assign( + struct net_device *input_dev = metadata->input_dev; + + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(trap_name, metadata->trap_name); + __assign_str(trap_group_name, metadata->trap_group_name); + __assign_str(input_dev_name, + (input_dev ? input_dev->name : "NULL")); + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s trap_name=%s " + "trap_group_name=%s input_dev_name=%s", __get_str(bus_name), + __get_str(dev_name), __get_str(driver_name), + __get_str(trap_name), __get_str(trap_group_name), + __get_str(input_dev_name)) +); + #endif /* _TRACE_DEVLINK_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 8ee2267ad33e0ba021e9dd9b437f773906cd99d6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 29 Sep 2020 11:15:52 +0300 Subject: drop_monitor: Convert to using devlink tracepoint Convert drop monitor to use the recently introduced 'devlink_trap_report' tracepoint instead of having devlink call into drop monitor. This is both consistent with software originated drops ('kfree_skb' tracepoint) and also allows drop monitor to be built as a module and still report hardware originated drops. Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/drop_monitor.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) delete mode 100644 include/net/drop_monitor.h (limited to 'include') diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h deleted file mode 100644 index 3f5b6ddb3179..000000000000 --- a/include/net/drop_monitor.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ - -#ifndef _NET_DROP_MONITOR_H_ -#define _NET_DROP_MONITOR_H_ - -#include -#include -#include -#include - -/** - * struct net_dm_hw_metadata - Hardware-supplied packet metadata. - * @trap_group_name: Hardware trap group name. - * @trap_name: Hardware trap name. - * @input_dev: Input netdevice. - * @fa_cookie: Flow action user cookie. - */ -struct net_dm_hw_metadata { - const char *trap_group_name; - const char *trap_name; - struct net_device *input_dev; - const struct flow_action_cookie *fa_cookie; -}; - -#if IS_REACHABLE(CONFIG_NET_DROP_MONITOR) -void net_dm_hw_report(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata); -#else -static inline void -net_dm_hw_report(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) -{ -} -#endif - -#endif /* _NET_DROP_MONITOR_H_ */ -- cgit v1.2.3 From 93e155967ccc053b71d408edf8c0142199df5c8c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 29 Sep 2020 11:15:55 +0300 Subject: drop_monitor: Filter control packets in drop monitor Previously, devlink called into drop monitor in order to report hardware originated drops / exceptions. devlink intentionally filtered control packets and did not pass them to drop monitor as they were not dropped by the underlying hardware. Now drop monitor registers its probe on a generic 'devlink_trap_report' tracepoint and should therefore perform this filtering itself instead of having devlink do that. Add the trap type as metadata and have drop monitor ignore control packets. Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 1014294ba6a0..1c286e9a3590 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -630,12 +630,14 @@ struct devlink_health_reporter_ops { * @trap_group_name: Trap group name. * @input_dev: Input netdevice. * @fa_cookie: Flow action user cookie. + * @trap_type: Trap type. */ struct devlink_trap_metadata { const char *trap_name; const char *trap_group_name; struct net_device *input_dev; const struct flow_action_cookie *fa_cookie; + enum devlink_trap_type trap_type; }; /** -- cgit v1.2.3 From 0f2122045b946241a9e549c2a76cea54fa58a7ff Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 13 Sep 2020 13:09:39 -0600 Subject: io_uring: don't rely on weak ->files references Grab actual references to the files_struct. To avoid circular references issues due to this, we add a per-task note that keeps track of what io_uring contexts a task has used. When the tasks execs or exits its assigned files, we cancel requests based on this tracking. With that, we can grab proper references to the files table, and no longer need to rely on stashing away ring_fd and ring_file to check if the ring_fd may have been closed. Cc: stable@vger.kernel.org # v5.5+ Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 5 +++++ 2 files changed, 58 insertions(+) create mode 100644 include/linux/io_uring.h (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h new file mode 100644 index 000000000000..c09135a1ef13 --- /dev/null +++ b/include/linux/io_uring.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_H +#define _LINUX_IO_URING_H + +#include +#include +#include + +struct io_uring_task { + /* submission side */ + struct xarray xa; + struct wait_queue_head wait; + struct file *last; + atomic_long_t req_issue; + + /* completion side */ + bool in_idle ____cacheline_aligned_in_smp; + atomic_long_t req_complete; +}; + +#if defined(CONFIG_IO_URING) +void __io_uring_task_cancel(void); +void __io_uring_files_cancel(struct files_struct *files); +void __io_uring_free(struct task_struct *tsk); + +static inline void io_uring_task_cancel(void) +{ + if (current->io_uring && !xa_empty(¤t->io_uring->xa)) + __io_uring_task_cancel(); +} +static inline void io_uring_files_cancel(struct files_struct *files) +{ + if (current->io_uring && !xa_empty(¤t->io_uring->xa)) + __io_uring_files_cancel(files); +} +static inline void io_uring_free(struct task_struct *tsk) +{ + if (tsk->io_uring) + __io_uring_free(tsk); +} +#else +static inline void io_uring_task_cancel(void) +{ +} +static inline void io_uring_files_cancel(struct files_struct *files) +{ +} +static inline void io_uring_free(struct task_struct *tsk) +{ +} +#endif + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index afe01e232935..8bf2295ebee4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -63,6 +63,7 @@ struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; +struct io_uring_task; /* * Task state bitmask. NOTE! These bits are also @@ -935,6 +936,10 @@ struct task_struct { /* Open file information: */ struct files_struct *files; +#ifdef CONFIG_IO_URING + struct io_uring_task *io_uring; +#endif + /* Namespaces: */ struct nsproxy *nsproxy; -- cgit v1.2.3 From a3ec60054082ca2c2145ba487f9fc4de904e2b03 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 18 Sep 2020 20:41:00 -0600 Subject: io_uring: move io_uring_get_socket() into io_uring.h Now we have a io_uring kernel header, move this definition out of fs.h and into io_uring.h where it belongs. Signed-off-by: Jens Axboe --- include/linux/fs.h | 9 --------- include/linux/io_uring.h | 5 +++++ 2 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a08..1c4068428461 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3514,15 +3514,6 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); -#if defined(CONFIG_IO_URING) -extern struct sock *io_uring_get_socket(struct file *file); -#else -static inline struct sock *io_uring_get_socket(struct file *file) -{ - return NULL; -} -#endif - int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, unsigned int flags); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index c09135a1ef13..96315cfaf6d1 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -19,6 +19,7 @@ struct io_uring_task { }; #if defined(CONFIG_IO_URING) +struct sock *io_uring_get_socket(struct file *file); void __io_uring_task_cancel(void); void __io_uring_files_cancel(struct files_struct *files); void __io_uring_free(struct task_struct *tsk); @@ -39,6 +40,10 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline struct sock *io_uring_get_socket(struct file *file) +{ + return NULL; +} static inline void io_uring_task_cancel(void) { } -- cgit v1.2.3 From 9d4a75efa200a31deabe9ba1c941aef697e6bb30 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 27 Aug 2020 16:58:29 +0200 Subject: io_uring: use an enumeration for io_uring_register(2) opcodes The enumeration allows us to keep track of the last io_uring_register(2) opcode available. Behaviour and opcodes names don't change. Signed-off-by: Stefano Garzarella Reviewed-by: Kees Cook Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d65fde732518..5f12ae6a415c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -255,17 +255,22 @@ struct io_uring_params { /* * io_uring_register(2) opcodes and arguments */ -#define IORING_REGISTER_BUFFERS 0 -#define IORING_UNREGISTER_BUFFERS 1 -#define IORING_REGISTER_FILES 2 -#define IORING_UNREGISTER_FILES 3 -#define IORING_REGISTER_EVENTFD 4 -#define IORING_UNREGISTER_EVENTFD 5 -#define IORING_REGISTER_FILES_UPDATE 6 -#define IORING_REGISTER_EVENTFD_ASYNC 7 -#define IORING_REGISTER_PROBE 8 -#define IORING_REGISTER_PERSONALITY 9 -#define IORING_UNREGISTER_PERSONALITY 10 +enum { + IORING_REGISTER_BUFFERS = 0, + IORING_UNREGISTER_BUFFERS = 1, + IORING_REGISTER_FILES = 2, + IORING_UNREGISTER_FILES = 3, + IORING_REGISTER_EVENTFD = 4, + IORING_UNREGISTER_EVENTFD = 5, + IORING_REGISTER_FILES_UPDATE = 6, + IORING_REGISTER_EVENTFD_ASYNC = 7, + IORING_REGISTER_PROBE = 8, + IORING_REGISTER_PERSONALITY = 9, + IORING_UNREGISTER_PERSONALITY = 10, + + /* this goes last */ + IORING_REGISTER_LAST +}; struct io_uring_files_update { __u32 offset; -- cgit v1.2.3 From 21b55dbc0653018b8cd4513c37cbca303b0f0d50 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 27 Aug 2020 16:58:30 +0200 Subject: io_uring: add IOURING_REGISTER_RESTRICTIONS opcode The new io_uring_register(2) IOURING_REGISTER_RESTRICTIONS opcode permanently installs a feature allowlist on an io_ring_ctx. The io_ring_ctx can then be passed to untrusted code with the knowledge that only operations present in the allowlist can be executed. The allowlist approach ensures that new features added to io_uring do not accidentally become available when an existing application is launched on a newer kernel version. Currently is it possible to restrict sqe opcodes, sqe flags, and register opcodes. IOURING_REGISTER_RESTRICTIONS can only be made once. Afterwards it is not possible to change restrictions anymore. This prevents untrusted code from removing restrictions. Suggested-by: Stefan Hajnoczi Signed-off-by: Stefano Garzarella Reviewed-by: Kees Cook Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 5f12ae6a415c..6e7f2e5e917b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -267,6 +267,7 @@ enum { IORING_REGISTER_PROBE = 8, IORING_REGISTER_PERSONALITY = 9, IORING_UNREGISTER_PERSONALITY = 10, + IORING_REGISTER_RESTRICTIONS = 11, /* this goes last */ IORING_REGISTER_LAST @@ -295,4 +296,34 @@ struct io_uring_probe { struct io_uring_probe_op ops[0]; }; +struct io_uring_restriction { + __u16 opcode; + union { + __u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */ + __u8 sqe_op; /* IORING_RESTRICTION_SQE_OP */ + __u8 sqe_flags; /* IORING_RESTRICTION_SQE_FLAGS_* */ + }; + __u8 resv; + __u32 resv2[3]; +}; + +/* + * io_uring_restriction->opcode values + */ +enum { + /* Allow an io_uring_register(2) opcode */ + IORING_RESTRICTION_REGISTER_OP = 0, + + /* Allow an sqe opcode */ + IORING_RESTRICTION_SQE_OP = 1, + + /* Allow sqe flags */ + IORING_RESTRICTION_SQE_FLAGS_ALLOWED = 2, + + /* Require sqe flags (these flags must be set on each submission) */ + IORING_RESTRICTION_SQE_FLAGS_REQUIRED = 3, + + IORING_RESTRICTION_LAST +}; + #endif -- cgit v1.2.3 From 7e84e1c7566a1df470a9e1f49d3db2ce311261a4 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 27 Aug 2020 16:58:31 +0200 Subject: io_uring: allow disabling rings during the creation This patch adds a new IORING_SETUP_R_DISABLED flag to start the rings disabled, allowing the user to register restrictions, buffers, files, before to start processing SQEs. When IORING_SETUP_R_DISABLED is set, SQE are not processed and SQPOLL kthread is not started. The restrictions registration are allowed only when the rings are disable to prevent concurrency issue while processing SQEs. The rings can be enabled using IORING_REGISTER_ENABLE_RINGS opcode with io_uring_register(2). Suggested-by: Jens Axboe Signed-off-by: Stefano Garzarella Reviewed-by: Kees Cook Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6e7f2e5e917b..a0c85e0e9016 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -95,6 +95,7 @@ enum { #define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */ #define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */ #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ +#define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ enum { IORING_OP_NOP, @@ -268,6 +269,7 @@ enum { IORING_REGISTER_PERSONALITY = 9, IORING_UNREGISTER_PERSONALITY = 10, IORING_REGISTER_RESTRICTIONS = 11, + IORING_REGISTER_ENABLE_RINGS = 12, /* this goes last */ IORING_REGISTER_LAST -- cgit v1.2.3 From ce71bfea207b4d7c21d36f24ec37618ffcea1da8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 31 Aug 2020 12:08:10 -0600 Subject: fs: align IOCB_* flags with RWF_* flags We have a set of flags that are shared between the two and inherired in kiocb_set_rw_flags(), but we check and set these individually. Reorder the IOCB flags so that the bottom part of the space is synced with the RWF flag space, and then we can do them all in one mask and set operation. The only exception is RWF_SYNC, which needs to mark IOCB_SYNC and IOCB_DSYNC. Do that one separately. This shaves 15 bytes of text from kiocb_set_rw_flags() for me. Suggested-by: Matthew Wilcox (Oracle) Signed-off-by: Jens Axboe --- include/linux/fs.h | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1c4068428461..4ebc14dee421 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -310,17 +310,20 @@ enum rw_hint { WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, }; -#define IOCB_EVENTFD (1 << 0) -#define IOCB_APPEND (1 << 1) -#define IOCB_DIRECT (1 << 2) -#define IOCB_HIPRI (1 << 3) -#define IOCB_DSYNC (1 << 4) -#define IOCB_SYNC (1 << 5) -#define IOCB_WRITE (1 << 6) -#define IOCB_NOWAIT (1 << 7) +/* Match RWF_* bits to IOCB bits */ +#define IOCB_HIPRI (__force int) RWF_HIPRI +#define IOCB_DSYNC (__force int) RWF_DSYNC +#define IOCB_SYNC (__force int) RWF_SYNC +#define IOCB_NOWAIT (__force int) RWF_NOWAIT +#define IOCB_APPEND (__force int) RWF_APPEND + +/* non-RWF related bits - start at 16 */ +#define IOCB_EVENTFD (1 << 16) +#define IOCB_DIRECT (1 << 17) +#define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ -#define IOCB_WAITQ (1 << 8) -#define IOCB_NOIO (1 << 9) +#define IOCB_WAITQ (1 << 19) +#define IOCB_NOIO (1 << 20) struct kiocb { struct file *ki_filp; @@ -3317,6 +3320,9 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { int kiocb_flags = 0; + /* make sure there's no overlap between RWF and private IOCB flags */ + BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); + if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) @@ -3325,16 +3331,11 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; - kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO; + kiocb_flags |= IOCB_NOIO; } - if (flags & RWF_HIPRI) - kiocb_flags |= IOCB_HIPRI; - if (flags & RWF_DSYNC) - kiocb_flags |= IOCB_DSYNC; + kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) - kiocb_flags |= (IOCB_DSYNC | IOCB_SYNC); - if (flags & RWF_APPEND) - kiocb_flags |= IOCB_APPEND; + kiocb_flags |= IOCB_DSYNC; ki->ki_flags |= kiocb_flags; return 0; -- cgit v1.2.3 From 90554200724d5b280439dc361fe7ee92fe459ea7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 3 Sep 2020 12:12:41 -0600 Subject: io_uring: provide IORING_ENTER_SQ_WAIT for SQPOLL SQ ring waits When using SQPOLL, applications can run into the issue of running out of SQ ring entries because the thread hasn't consumed them yet. The only option for dealing with that is checking later, or busy checking for the condition. Provide IORING_ENTER_SQ_WAIT if applications want to wait on this condition. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a0c85e0e9016..98d8e06dea22 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -225,6 +225,7 @@ struct io_cqring_offsets { */ #define IORING_ENTER_GETEVENTS (1U << 0) #define IORING_ENTER_SQ_WAKEUP (1U << 1) +#define IORING_ENTER_SQ_WAIT (1U << 2) /* * Passed in for io_uring_setup(2). Copied back with updated info on success -- cgit v1.2.3 From 7cd7becdddb00620fb8deb74e6fe4e5a1522ae5a Mon Sep 17 00:00:00 2001 From: sunils Date: Fri, 11 Sep 2020 00:13:26 +0300 Subject: net/mlx5: E-switch, Use PF num in metadata reg c0 Currently only 256 vports can be supported as only 8 bits are reserved for them and 8 bits are reserved for vhca_ids in metadata reg c0. To support more than 256 vports, replace vhca_id with a unique shorter 4-bit PF number which covers upto 16 PF's. Use remaining 12 bits for vports ranging 1-4095. This will continue to generate unique metadata even if multiple PCI devices have same switch_id. Signed-off-by: sunils Reviewed-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index c16827eeba9c..b0ae8020f13e 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -74,15 +74,16 @@ bool mlx5_eswitch_reg_c1_loopback_enabled(const struct mlx5_eswitch *esw); bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw); /* Reg C0 usage: - * Reg C0 = < ESW_VHCA_ID_BITS(8) | ESW_VPORT BITS(8) | ESW_CHAIN_TAG(16) > + * Reg C0 = < ESW_PFNUM_BITS(4) | ESW_VPORT BITS(12) | ESW_CHAIN_TAG(16) > * - * Highest 8 bits of the reg c0 is the vhca_id, next 8 bits is vport_num, - * the rest (lowest 16 bits) is left for tc chain tag restoration. - * VHCA_ID + VPORT comprise the SOURCE_PORT matching. + * Highest 4 bits of the reg c0 is the PF_NUM (range 0-15), 12 bits of + * unique non-zero vport id (range 1-4095). The rest (lowest 16 bits) is left + * for tc chain tag restoration. + * PFNUM + VPORT comprise the SOURCE_PORT matching. */ -#define ESW_VHCA_ID_BITS 8 -#define ESW_VPORT_BITS 8 -#define ESW_SOURCE_PORT_METADATA_BITS (ESW_VHCA_ID_BITS + ESW_VPORT_BITS) +#define ESW_VPORT_BITS 12 +#define ESW_PFNUM_BITS 4 +#define ESW_SOURCE_PORT_METADATA_BITS (ESW_PFNUM_BITS + ESW_VPORT_BITS) #define ESW_SOURCE_PORT_METADATA_OFFSET (32 - ESW_SOURCE_PORT_METADATA_BITS) #define ESW_CHAIN_TAG_METADATA_BITS (32 - ESW_SOURCE_PORT_METADATA_BITS) #define ESW_CHAIN_TAG_METADATA_MASK GENMASK(ESW_CHAIN_TAG_METADATA_BITS - 1,\ -- cgit v1.2.3 From 792caccc4526bb489e054f9ab61d7c024b15dea2 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 30 Sep 2020 15:49:26 -0700 Subject: bpf: Introduce BPF_F_PRESERVE_ELEMS for perf event array Currently, perf event in perf event array is removed from the array when the map fd used to add the event is closed. This behavior makes it difficult to the share perf events with perf event array. Introduce perf event map that keeps the perf event open with a new flag BPF_F_PRESERVE_ELEMS. With this flag set, perf events in the array are not removed when the original map fd is closed. Instead, the perf event will stay in the map until 1) it is explicitly removed from the array; or 2) the array is freed. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200930224927.1936644-2-songliubraving@fb.com --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1f17c6752deb..4f556cfcbfbe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -414,6 +414,9 @@ enum { /* Enable memory-mapping BPF map */ BPF_F_MMAPABLE = (1U << 10), + +/* Share perf_event among processes */ + BPF_F_PRESERVE_ELEMS = (1U << 11), }; /* Flags for BPF_PROG_QUERY. */ -- cgit v1.2.3 From 1e6aaae93e9ddb9dc664993eb949b1da94cab3a5 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:43 -0700 Subject: iommu/uapi: Add argsz for user filled data As IOMMU UAPI gets extended, user data size may increase. To support backward compatibiliy, this patch introduces a size field to each UAPI data structures. It is *always* the responsibility for the user to fill in the correct size. Padding fields are adjusted to ensure 8 byte alignment. Specific scenarios for user data handling are documented in: Documentation/userspace-api/iommu.rst As there is no current users of the API, struct version is not incremented. Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-3-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/uapi/linux/iommu.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index c2b2caf9ed41..b42acc8fe007 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -139,6 +139,7 @@ enum iommu_page_response_code { /** * struct iommu_page_response - Generic page response information + * @argsz: User filled size of this data * @version: API version of this structure * @flags: encodes whether the corresponding fields are valid * (IOMMU_FAULT_PAGE_RESPONSE_* values) @@ -147,6 +148,7 @@ enum iommu_page_response_code { * @code: response code from &enum iommu_page_response_code */ struct iommu_page_response { + __u32 argsz; #define IOMMU_PAGE_RESP_VERSION_1 1 __u32 version; #define IOMMU_PAGE_RESP_PASID_VALID (1 << 0) @@ -222,6 +224,7 @@ struct iommu_inv_pasid_info { /** * struct iommu_cache_invalidate_info - First level/stage invalidation * information + * @argsz: User filled size of this data * @version: API version of this structure * @cache: bitfield that allows to select which caches to invalidate * @granularity: defines the lowest granularity used for the invalidation: @@ -250,6 +253,7 @@ struct iommu_inv_pasid_info { * must support the used granularity. */ struct iommu_cache_invalidate_info { + __u32 argsz; #define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1 __u32 version; /* IOMMU paging structure cache */ @@ -259,7 +263,7 @@ struct iommu_cache_invalidate_info { #define IOMMU_CACHE_INV_TYPE_NR (3) __u8 cache; __u8 granularity; - __u8 padding[2]; + __u8 padding[6]; union { struct iommu_inv_pasid_info pasid_info; struct iommu_inv_addr_info addr_info; @@ -296,6 +300,7 @@ struct iommu_gpasid_bind_data_vtd { /** * struct iommu_gpasid_bind_data - Information about device and guest PASID binding + * @argsz: User filled size of this data * @version: Version of this data structure * @format: PASID table entry format * @flags: Additional information on guest bind request @@ -313,17 +318,18 @@ struct iommu_gpasid_bind_data_vtd { * PASID to host PASID based on this bind data. */ struct iommu_gpasid_bind_data { + __u32 argsz; #define IOMMU_GPASID_BIND_VERSION_1 1 __u32 version; #define IOMMU_PASID_FORMAT_INTEL_VTD 1 __u32 format; + __u32 addr_width; #define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */ __u64 flags; __u64 gpgd; __u64 hpasid; __u64 gpasid; - __u32 addr_width; - __u8 padding[12]; + __u8 padding[8]; /* Vendor specific data */ union { struct iommu_gpasid_bind_data_vtd vtd; -- cgit v1.2.3 From 8d3bb3b8cbf2ffb3ef73720a48b3445518dcdb55 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:44 -0700 Subject: iommu/uapi: Use named union for user data IOMMU UAPI data size is filled by the user space which must be validated by the kernel. To ensure backward compatibility, user data can only be extended by either re-purpose padding bytes or extend the variable sized union at the end. No size change is allowed before the union. Therefore, the minimum size is the offset of the union. To use offsetof() on the union, we must make it named. Signed-off-by: Jacob Pan Reviewed-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/linux-iommu/20200611145518.0c2817d6@x1.home/ Link: https://lore.kernel.org/r/1601051567-54787-4-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/uapi/linux/iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index b42acc8fe007..5946779ac1f9 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -267,7 +267,7 @@ struct iommu_cache_invalidate_info { union { struct iommu_inv_pasid_info pasid_info; struct iommu_inv_addr_info addr_info; - }; + } granu; }; /** @@ -333,7 +333,7 @@ struct iommu_gpasid_bind_data { /* Vendor specific data */ union { struct iommu_gpasid_bind_data_vtd vtd; - }; + } vendor; }; #endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3 From 23cc3493b5e107b8deb697cf3157a07276b5eff7 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:45 -0700 Subject: iommu/uapi: Rename uapi functions User APIs such as iommu_sva_unbind_gpasid() may also be used by the kernel. Since we introduced user pointer to the UAPI functions, in-kernel callers cannot share the same APIs. In-kernel callers are also trusted, there is no need to validate the data. We plan to have two flavors of the same API functions, one called through ioctls, carrying a user pointer and one called directly with valid IOMMU UAPI structs. To differentiate both, let's rename existing functions with an iommu_uapi_ prefix. Suggested-by: Alex Williamson Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-5-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2ad26d8b4ab9..d18de2afa6fb 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -424,13 +424,13 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info); -extern int iommu_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); +extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info); +extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data); +extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1032,21 +1032,22 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } -static inline int -iommu_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info) +static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info) { return -ENODEV; } -static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data) + +static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, + struct iommu_gpasid_bind_data *data) { return -ENODEV; } -static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, int pasid) +static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, int pasid) { return -ENODEV; } -- cgit v1.2.3 From d90573812eea63c6bc8ab8a38f661b4c27c3cdc0 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:46 -0700 Subject: iommu/uapi: Handle data and argsz filled by users IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality. IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags. User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking. This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-6-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 28 +++++++++++++++++++--------- include/uapi/linux/iommu.h | 1 + 2 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d18de2afa6fb..82876f682367 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -426,11 +426,14 @@ extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev, - struct iommu_cache_invalidate_info *inv_info); + void __user *uinfo); + extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data); + struct device *dev, void __user *udata); extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); + struct device *dev, void __user *udata); +extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1032,22 +1035,29 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } -static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info) +static inline int +iommu_uapi_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info) { return -ENODEV; } static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, - struct iommu_gpasid_bind_data *data) + struct device *dev, void __user *udata) { return -ENODEV; } static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, int pasid) + struct device *dev, void __user *udata) +{ + return -ENODEV; +} + +static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, + ioasid_t pasid) { return -ENODEV; } diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index 5946779ac1f9..66d4ca40b40f 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -322,6 +322,7 @@ struct iommu_gpasid_bind_data { #define IOMMU_GPASID_BIND_VERSION_1 1 __u32 version; #define IOMMU_PASID_FORMAT_INTEL_VTD 1 +#define IOMMU_PASID_FORMAT_LAST 2 __u32 format; __u32 addr_width; #define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */ -- cgit v1.2.3 From 6278eecba31f3983fe2743fc01b198433aa18247 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:47 -0700 Subject: iommu/vt-d: Check UAPI data processed by IOMMU core IOMMU generic layer already does sanity checks on UAPI data for version match and argsz range based on generic information. This patch adjusts the following data checking responsibilities: - removes the redundant version check from VT-d driver - removes the check for vendor specific data size - adds check for the use of reserved/undefined flags Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-7-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/uapi/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index 66d4ca40b40f..e1d9e75f2c94 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -288,6 +288,7 @@ struct iommu_gpasid_bind_data_vtd { #define IOMMU_SVA_VTD_GPASID_PWT (1 << 3) /* page-level write through */ #define IOMMU_SVA_VTD_GPASID_EMTE (1 << 4) /* extended mem type enable */ #define IOMMU_SVA_VTD_GPASID_CD (1 << 5) /* PASID-level cache disable */ +#define IOMMU_SVA_VTD_GPASID_LAST (1 << 6) __u64 flags; __u32 pat; __u32 emt; -- cgit v1.2.3 From 8a018eb55e3ac033592afbcb476b0ffe64465b12 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 1 Oct 2020 08:50:55 -0400 Subject: pipe: Fix memory leaks in create_pipe_files() Calling pipe2() with O_NOTIFICATION_PIPE could results in memory leaks unless watch_queue_init() is successful. In case of watch_queue_init() failure in pipe2() we are left with inode and pipe_inode_info instances that need to be freed. That failure exit has been introduced in commit c73be61cede5 ("pipe: Add general notification queue support") and its handling should've been identical to nearby treatment of alloc_file_pseudo() failures - it is dealing with the same situation. As it is, the mainline kernel leaks in that case. Another problem is that CONFIG_WATCH_QUEUE and !CONFIG_WATCH_QUEUE cases are treated differently (and the former leaks just pipe_inode_info, the latter - both pipe_inode_info and inode). Fixed by providing a dummy wacth_queue_init() in !CONFIG_WATCH_QUEUE case and by having failures of wacth_queue_init() handled the same way we handle alloc_file_pseudo() ones. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Signed-off-by: Qian Cai Signed-off-by: Al Viro --- include/linux/watch_queue.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index 5e08db2adc31..c994d1b2cdba 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -122,6 +122,12 @@ static inline void remove_watch_list(struct watch_list *wlist, u64 id) */ #define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT) +#else +static inline int watch_queue_init(struct pipe_inode_info *pipe) +{ + return -ENOPKG; +} + #endif #endif /* _LINUX_WATCH_QUEUE_H */ -- cgit v1.2.3 From 88451f2cd3cec2abc30debdf129422d2699d1eba Mon Sep 17 00:00:00 2001 From: Zqiang Date: Tue, 8 Sep 2020 14:27:09 +0800 Subject: debugobjects: Free per CPU pool after CPU unplug If a CPU is offlined the debug objects per CPU pool is not cleaned up. If the CPU is never onlined again then the objects in the pool are wasted. Add a CPU hotplug callback which is invoked after the CPU is dead to free the pool. [ tglx: Massaged changelog and added comment about remote access safety ] Signed-off-by: Zqiang Signed-off-by: Thomas Gleixner Cc: Waiman Long Link: https://lore.kernel.org/r/20200908062709.11441-1-qiang.zhang@windriver.com --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index bf9181cef444..6f524bbf71a2 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -36,6 +36,7 @@ enum cpuhp_state { CPUHP_X86_MCE_DEAD, CPUHP_VIRT_NET_DEAD, CPUHP_SLUB_DEAD, + CPUHP_DEBUG_OBJ_DEAD, CPUHP_MM_WRITEBACK_DEAD, CPUHP_MM_VMSTAT_DEAD, CPUHP_SOFTIRQ_DEAD, -- cgit v1.2.3 From 61931c0ee9cf5da575996b977a2358b598ef84bb Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 1 Oct 2020 15:00:56 -0400 Subject: dm: export dm_copy_name_and_uuid Allow DM targets to access the configured name and uuid. Also, bump DM ioctl version. Signed-off-by: Mike Snitzer --- include/uapi/linux/dm-ioctl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 6622912c2342..4933b6b67b85 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -272,9 +272,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 42 +#define DM_VERSION_MINOR 43 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2020-02-27)" +#define DM_VERSION_EXTRA "-ioctl (2020-10-01)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 36f30e486dce22345c2dd3a3ba439c12cd67f6ba Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 30 Sep 2020 19:38:25 +0300 Subject: IB/core: Improve ODP to use hmm_range_fault() Move to use hmm_range_fault() instead of get_user_pags_remote() to improve performance in a few aspects: This includes: - Dropping the need to allocate and free memory to hold its output - No need any more to use put_page() to unpin the pages - The logic to detect contiguous pages is done based on the returned order, no need to run per page and evaluate. In addition, moving to use hmm_range_fault() enables to reduce page faults in the system with it's snapshot mode, this will be introduced in next patches from this series. As part of this, cleanup some flows and use the required data structures to work with hmm_range_fault(). Link: https://lore.kernel.org/r/20200930163828.1336747-2-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_umem_odp.h | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h index d16d2c17e733..a53b62ac8a9d 100644 --- a/include/rdma/ib_umem_odp.h +++ b/include/rdma/ib_umem_odp.h @@ -14,17 +14,13 @@ struct ib_umem_odp { struct mmu_interval_notifier notifier; struct pid *tgid; + /* An array of the pfns included in the on-demand paging umem. */ + unsigned long *pfn_list; + /* - * An array of the pages included in the on-demand paging umem. - * Indices of pages that are currently not mapped into the device will - * contain NULL. - */ - struct page **page_list; - /* - * An array of the same size as page_list, with DMA addresses mapped - * for pages the pages in page_list. The lower two bits designate - * access permissions. See ODP_READ_ALLOWED_BIT and - * ODP_WRITE_ALLOWED_BIT. + * An array with DMA addresses mapped for pfns in pfn_list. + * The lower two bits designate access permissions. + * See ODP_READ_ALLOWED_BIT and ODP_WRITE_ALLOWED_BIT. */ dma_addr_t *dma_list; /* @@ -97,9 +93,8 @@ ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr, const struct mmu_interval_notifier_ops *ops); void ib_umem_odp_release(struct ib_umem_odp *umem_odp); -int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset, - u64 bcnt, u64 access_mask, - unsigned long current_seq); +int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 start_offset, + u64 bcnt, u64 access_mask); void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset, u64 bound); -- cgit v1.2.3 From 8bfafde08693cc2e740134c3e32b40254f5d82ae Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 30 Sep 2020 19:38:26 +0300 Subject: IB/core: Enable ODP sync without faulting Enable ODP sync without faulting, this improves performance by reducing the number of page faults in the system. The gain from this option is that the device page table can be aligned with the presented pages in the CPU page table without causing page faults. As of that, the overhead on data path from hardware point of view to trigger a fault which end-up by calling the driver to bring the pages will be dropped. Link: https://lore.kernel.org/r/20200930163828.1336747-3-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_umem_odp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h index a53b62ac8a9d..0844c1d05ac6 100644 --- a/include/rdma/ib_umem_odp.h +++ b/include/rdma/ib_umem_odp.h @@ -94,7 +94,7 @@ ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr, void ib_umem_odp_release(struct ib_umem_odp *umem_odp); int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 start_offset, - u64 bcnt, u64 access_mask); + u64 bcnt, u64 access_mask, bool fault); void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset, u64 bound); -- cgit v1.2.3 From 677cf51f71c97bcf98852aa2077d7289bc73e3b3 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 30 Sep 2020 19:38:27 +0300 Subject: RDMA/mlx5: Extend advice MR to support non faulting mode Extend advice MR to support non faulting mode, this can improve performance by increasing the populated page tables in the device. Link: https://lore.kernel.org/r/20200930163828.1336747-4-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/ib_user_ioctl_verbs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h index 5debab45ebcb..fb8cdb38198b 100644 --- a/include/uapi/rdma/ib_user_ioctl_verbs.h +++ b/include/uapi/rdma/ib_user_ioctl_verbs.h @@ -208,6 +208,7 @@ enum ib_uverbs_read_counters_flags { enum ib_uverbs_advise_mr_advice { IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH, IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE, + IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT, }; enum ib_uverbs_advise_mr_flag { -- cgit v1.2.3 From 6d849653b00f2336efcd371fe85a7eb31bb094e9 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Sat, 26 Sep 2020 14:55:47 +0200 Subject: regulator: qcom_smd: Add PM660/PM660L regulator support The PM660 and PM660L are a very very common PMIC combo, found on boards using the SDM630, SDM636, SDM660 (and SDA variants) SoC. PM660 provides 6 SMPS and 19 LDOs (of which one is unaccesible), while PM660L provides 5 SMPS (of which S3 and S4 are combined), 10 LDOs and a Buck-or-Boost (BoB) regulator. The PM660L IC also provides other regulators that are very specialized (for example, for the display) and will be managed in the other appropriate drivers (for example, labibb). Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20200926125549.13191-6-kholk11@gmail.com Signed-off-by: Mark Brown --- include/linux/soc/qcom/smd-rpm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h index da304ce8c8f7..f2645ec52520 100644 --- a/include/linux/soc/qcom/smd-rpm.h +++ b/include/linux/soc/qcom/smd-rpm.h @@ -19,6 +19,10 @@ struct qcom_smd_rpm; #define QCOM_SMD_RPM_CLK_BUF_A 0x616B6C63 #define QCOM_SMD_RPM_LDOA 0x616f646c #define QCOM_SMD_RPM_LDOB 0x626F646C +#define QCOM_SMD_RPM_RWCX 0x78637772 +#define QCOM_SMD_RPM_RWMX 0x786d7772 +#define QCOM_SMD_RPM_RWLC 0x636c7772 +#define QCOM_SMD_RPM_RWLM 0x6d6c7772 #define QCOM_SMD_RPM_MEM_CLK 0x326b6c63 #define QCOM_SMD_RPM_MISC_CLK 0x306b6c63 #define QCOM_SMD_RPM_NCPA 0x6170636E -- cgit v1.2.3 From 41a7431dbaa37533c3b732cdea425a7b8f2d4162 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 19 Sep 2020 16:04:18 +0200 Subject: power: supply: bq27xxx: add support for TI bq34z100 Add support for new device: the TI bq34z100-G1, a Wide Range Fuel Gauge for Li-Ion, PbA, NiMH, and NiCd batteries. The device shares a lot with other models, although it has its own differences requiring new quirks. This patch was tested on a system equipped with NiMH batteries. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 987d9652aa4e..111a40d0d3d5 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -32,6 +32,7 @@ enum bq27xxx_chip { BQ27621, BQ27Z561, BQ28Z610, + BQ34Z100, }; struct bq27xxx_device_info; -- cgit v1.2.3 From 8f2242b91501f4510f63f400cf7dae61912c6fef Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Tue, 25 Aug 2020 22:17:43 +0200 Subject: spi: pxa2xx: Add SSC2 and SSPSP2 SSP registers Update list of SSP registers with SSC2 and SSPSP2. These registers are utilized by LPT/WPT AudioDSP architecture. While SSC2 shares the same offset (0x40) as SSACDD, description of this register for SSP device present on mentioned AudioDSP is different so define separate constant to avoid any ambiguity. Cc: Andy Shevchenko Signed-off-by: Cezary Rojewski Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200825201743.4926-1-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 6facf27865f9..1608c760fe91 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -186,6 +186,10 @@ #define SSIRF 0x48 /* RX FIFO trigger level */ #define SSIRF_RxThresh(x) ((x) - 1) +/* LPT/WPT SSP */ +#define SSCR2 (0x40) /* SSP Command / Status 2 */ +#define SSPSP2 (0x44) /* SSP Programmable Serial Protocol 2 */ + enum pxa_ssp_type { SSP_UNDEFINED = 0, PXA25x_SSP, /* pxa 210, 250, 255, 26x */ -- cgit v1.2.3 From a4947e84f23474803b62a2759b5808147e4e15f9 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 13 Sep 2020 13:29:28 +0300 Subject: overflow: Include header file with SIZE_MAX declaration The various array_size functions use SIZE_MAX define, but missed limits.h causes to failure to compile code that needs overflow.h. In file included from drivers/infiniband/core/uverbs_std_types_device.c:6: ./include/linux/overflow.h: In function 'array_size': ./include/linux/overflow.h:258:10: error: 'SIZE_MAX' undeclared (first use in this function) 258 | return SIZE_MAX; | ^~~~~~~~ Fixes: 610b15c50e86 ("overflow.h: Add allocation size calculation helpers") Link: https://lore.kernel.org/r/20200913102928.134985-1-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/overflow.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 93fcef105061..ff3c48f0abc5 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -3,6 +3,7 @@ #define __LINUX_OVERFLOW_H #include +#include /* * In the fallback code below, we need to compute the minimum and -- cgit v1.2.3 From 1c15b4f2a42ff6697767c22c8ff5f9bcc22fdbe5 Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Wed, 23 Sep 2020 19:50:13 +0300 Subject: RDMA/core: Modify enum ib_gid_type and enum rdma_network_type Separate IB_GID_TYPE_IB and IB_GID_TYPE_ROCE to two different values, so enum ib_gid_type will match the gid types of the new query GID table API which will be introduced in the following patches. This change in enum ib_gid_type requires to change also enum rdma_network_type by separating RDMA_NETWORK_IB and RDMA_NETWORK_ROCE_V1 values. Link: https://lore.kernel.org/r/20200923165015.2491894-3-leon@kernel.org Signed-off-by: Avihai Horon Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 5ad997346f7f..3b61fba531d0 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -138,10 +138,9 @@ union ib_gid { extern union ib_gid zgid; enum ib_gid_type { - /* If link layer is Ethernet, this is RoCE V1 */ IB_GID_TYPE_IB = 0, - IB_GID_TYPE_ROCE = 0, - IB_GID_TYPE_ROCE_UDP_ENCAP = 1, + IB_GID_TYPE_ROCE = 1, + IB_GID_TYPE_ROCE_UDP_ENCAP = 2, IB_GID_TYPE_SIZE }; @@ -180,7 +179,7 @@ rdma_node_get_transport(unsigned int node_type); enum rdma_network_type { RDMA_NETWORK_IB, - RDMA_NETWORK_ROCE_V1 = RDMA_NETWORK_IB, + RDMA_NETWORK_ROCE_V1, RDMA_NETWORK_IPV4, RDMA_NETWORK_IPV6 }; @@ -190,9 +189,10 @@ static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type net if (network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) return IB_GID_TYPE_ROCE_UDP_ENCAP; - - /* IB_GID_TYPE_IB same as RDMA_NETWORK_ROCE_V1 */ - return IB_GID_TYPE_IB; + else if (network_type == RDMA_NETWORK_ROCE_V1) + return IB_GID_TYPE_ROCE; + else + return IB_GID_TYPE_IB; } static inline enum rdma_network_type @@ -201,6 +201,9 @@ rdma_gid_attr_network_type(const struct ib_gid_attr *attr) if (attr->gid_type == IB_GID_TYPE_IB) return RDMA_NETWORK_IB; + if (attr->gid_type == IB_GID_TYPE_ROCE) + return RDMA_NETWORK_ROCE_V1; + if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid)) return RDMA_NETWORK_IPV4; else -- cgit v1.2.3 From c4b4d548fabc15b9c5db9f61204dd0c608414d2d Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Wed, 23 Sep 2020 19:50:14 +0300 Subject: RDMA/core: Introduce new GID table query API Introduce rdma_query_gid_table which enables querying all the GID tables of a given device and copying the attributes of all valid GID entries to a provided buffer. This API provides a faster way to query a GID table using single call and will be used in libibverbs to improve current approach that requires multiple calls to open, close and read multiple sysfs files for a single GID table entry. Link: https://lore.kernel.org/r/20200923165015.2491894-4-leon@kernel.org Signed-off-by: Avihai Horon Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_cache.h | 3 +++ include/uapi/rdma/ib_user_ioctl_verbs.h | 8 ++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h index 66a8f369a2fa..bae29f50adff 100644 --- a/include/rdma/ib_cache.h +++ b/include/rdma/ib_cache.h @@ -110,5 +110,8 @@ const struct ib_gid_attr *rdma_get_gid_attr(struct ib_device *device, u8 port_num, int index); void rdma_put_gid_attr(const struct ib_gid_attr *attr); void rdma_hold_gid_attr(const struct ib_gid_attr *attr); +ssize_t rdma_query_gid_table(struct ib_device *device, + struct ib_uverbs_gid_entry *entries, + size_t max_entries); #endif /* _IB_CACHE_H */ diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h index fb8cdb38198b..14820082de5e 100644 --- a/include/uapi/rdma/ib_user_ioctl_verbs.h +++ b/include/uapi/rdma/ib_user_ioctl_verbs.h @@ -251,4 +251,12 @@ enum rdma_driver_id { RDMA_DRIVER_SIW, }; +struct ib_uverbs_gid_entry { + __aligned_u64 gid[2]; + __u32 gid_index; + __u32 port_num; + __u32 gid_type; + __u32 netdev_ifindex; /* It is 0 if there is no netdev associated with it */ +}; + #endif -- cgit v1.2.3 From 9f85cbe50aa044a46f0a22fda323fa27b80c82da Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Wed, 23 Sep 2020 19:50:15 +0300 Subject: RDMA/uverbs: Expose the new GID query API to user space Expose the query GID table and entry API to user space by adding two new methods and method handlers to the device object. This API provides a faster way to query a GID table using single call and will be used in libibverbs to improve current approach that requires multiple calls to open, close and read multiple sysfs files for a single GID table entry. Link: https://lore.kernel.org/r/20200923165015.2491894-5-leon@kernel.org Signed-off-by: Avihai Horon Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 6 +++--- include/uapi/rdma/ib_user_ioctl_cmds.h | 16 ++++++++++++++++ include/uapi/rdma/ib_user_ioctl_verbs.h | 6 ++++++ 3 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 3b61fba531d0..ce935d70fdc8 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -138,9 +138,9 @@ union ib_gid { extern union ib_gid zgid; enum ib_gid_type { - IB_GID_TYPE_IB = 0, - IB_GID_TYPE_ROCE = 1, - IB_GID_TYPE_ROCE_UDP_ENCAP = 2, + IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB, + IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1, + IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2, IB_GID_TYPE_SIZE }; diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h index 99dcabf61a71..7968a1845355 100644 --- a/include/uapi/rdma/ib_user_ioctl_cmds.h +++ b/include/uapi/rdma/ib_user_ioctl_cmds.h @@ -70,6 +70,8 @@ enum uverbs_methods_device { UVERBS_METHOD_QUERY_PORT, UVERBS_METHOD_GET_CONTEXT, UVERBS_METHOD_QUERY_CONTEXT, + UVERBS_METHOD_QUERY_GID_TABLE, + UVERBS_METHOD_QUERY_GID_ENTRY, }; enum uverbs_attrs_invoke_write_cmd_attr_ids { @@ -352,4 +354,18 @@ enum uverbs_attrs_async_event_create { UVERBS_ATTR_ASYNC_EVENT_ALLOC_FD_HANDLE, }; +enum uverbs_attrs_query_gid_table_cmd_attr_ids { + UVERBS_ATTR_QUERY_GID_TABLE_ENTRY_SIZE, + UVERBS_ATTR_QUERY_GID_TABLE_FLAGS, + UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES, + UVERBS_ATTR_QUERY_GID_TABLE_RESP_NUM_ENTRIES, +}; + +enum uverbs_attrs_query_gid_entry_cmd_attr_ids { + UVERBS_ATTR_QUERY_GID_ENTRY_PORT, + UVERBS_ATTR_QUERY_GID_ENTRY_GID_INDEX, + UVERBS_ATTR_QUERY_GID_ENTRY_FLAGS, + UVERBS_ATTR_QUERY_GID_ENTRY_RESP_ENTRY, +}; + #endif diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h index 14820082de5e..22483799cd07 100644 --- a/include/uapi/rdma/ib_user_ioctl_verbs.h +++ b/include/uapi/rdma/ib_user_ioctl_verbs.h @@ -251,6 +251,12 @@ enum rdma_driver_id { RDMA_DRIVER_SIW, }; +enum ib_uverbs_gid_type { + IB_UVERBS_GID_TYPE_IB, + IB_UVERBS_GID_TYPE_ROCE_V1, + IB_UVERBS_GID_TYPE_ROCE_V2, +}; + struct ib_uverbs_gid_entry { __aligned_u64 gid[2]; __u32 gid_index; -- cgit v1.2.3 From 472e5b056f000a778abb41f1e443de58eb259783 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 1 Oct 2020 19:14:36 -0700 Subject: pipe: remove pipe_wait() and fix wakeup race with splice The pipe splice code still used the old model of waiting for pipe IO by using a non-specific "pipe_wait()" that waited for any pipe event to happen, which depended on all pipe IO being entirely serialized by the pipe lock. So by checking the state you were waiting for, and then adding yourself to the wait queue before dropping the lock, you were guaranteed to see all the wakeups. Strictly speaking, the actual wakeups were not done under the lock, but the pipe_wait() model still worked, because since the waiter held the lock when checking whether it should sleep, it would always see the current state, and the wakeup was always done after updating the state. However, commit 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing") split the single wait-queue into two, and in the process also made the "wait for event" code wait for _two_ wait queues, and that then showed a race with the wakers that were not serialized by the pipe lock. It's only splice that used that "pipe_wait()" model, so the problem wasn't obvious, but Josef Bacik reports: "I hit a hang with fstest btrfs/187, which does a btrfs send into /dev/null. This works by creating a pipe, the write side is given to the kernel to write into, and the read side is handed to a thread that splices into a file, in this case /dev/null. The box that was hung had the write side stuck here [pipe_write] and the read side stuck here [splice_from_pipe_next -> pipe_wait]. [ more details about pipe_wait() scenario ] The problem is we're doing the prepare_to_wait, which sets our state each time, however we can be woken up either with reads or writes. In the case above we race with the WRITER waking us up, and re-set our state to INTERRUPTIBLE, and thus never break out of schedule" Josef had a patch that avoided the issue in pipe_wait() by just making it set the state only once, but the deeper problem is that pipe_wait() depends on a level of synchonization by the pipe mutex that it really shouldn't. And the whole "wait for any pipe state change" model really isn't very good to begin with. So rather than trying to work around things in pipe_wait(), remove that legacy model of "wait for arbitrary pipe event" entirely, and actually create functions that wait for the pipe actually being readable or writable, and can do so without depending on the pipe lock serializing everything. Fixes: 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing") Link: https://lore.kernel.org/linux-fsdevel/bfa88b5ad6f069b2b679316b9e495a970130416c.1601567868.git.josef@toxicpanda.com/ Reported-by: Josef Bacik Reviewed-and-tested-by: Josef Bacik Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 50afd0d0084c..5d2705f1d01c 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -240,8 +240,9 @@ extern unsigned int pipe_max_size; extern unsigned long pipe_user_pages_hard; extern unsigned long pipe_user_pages_soft; -/* Drop the inode semaphore and wait for a pipe event, atomically */ -void pipe_wait(struct pipe_inode_info *pipe); +/* Wait for a pipe to be readable/writable while dropping the pipe lock */ +void pipe_wait_readable(struct pipe_inode_info *); +void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); -- cgit v1.2.3 From 3301c215a2bb94b5a0afcb444bbe9bf2a395a65d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 21 Aug 2020 10:55:44 +0800 Subject: USB: UDC: Expand device model API interface The routines used by the UDC core to interface with the kernel's device model, namely usb_add_gadget_udc(), usb_add_gadget_udc_release(), and usb_del_gadget_udc(), provide access to only a subset of the device model's full API. They include functionality equivalent to device_register() and device_unregister() for gadgets, but they omit device_initialize(), device_add(), device_del(), get_device(), and put_device(). This patch expands the UDC API by adding usb_initialize_gadget(), usb_add_gadget(), usb_del_gadget(), usb_get_gadget(), and usb_put_gadget() to fill in the gap. It rewrites the existing routines to call the new ones. CC: Anton Vasilyev CC: Evgeny Novikov CC: Benjamin Herrenschmidt Reviewed-by: Greg Kroah-Hartman Signed-off-by: Alan Stern Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 52ce1f6b8f83..e7351d64f11f 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -436,6 +436,7 @@ struct usb_gadget { }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) +/* Interface to the device model */ static inline void set_gadget_data(struct usb_gadget *gadget, void *data) { dev_set_drvdata(&gadget->dev, data); } static inline void *get_gadget_data(struct usb_gadget *gadget) @@ -444,6 +445,26 @@ static inline struct usb_gadget *dev_to_usb_gadget(struct device *dev) { return container_of(dev, struct usb_gadget, dev); } +static inline struct usb_gadget *usb_get_gadget(struct usb_gadget *gadget) +{ + get_device(&gadget->dev); + return gadget; +} +static inline void usb_put_gadget(struct usb_gadget *gadget) +{ + put_device(&gadget->dev); +} +extern void usb_initialize_gadget(struct device *parent, + struct usb_gadget *gadget, void (*release)(struct device *dev)); +extern int usb_add_gadget(struct usb_gadget *gadget); +extern void usb_del_gadget(struct usb_gadget *gadget); + +/* Legacy device-model interface */ +extern int usb_add_gadget_udc_release(struct device *parent, + struct usb_gadget *gadget, void (*release)(struct device *dev)); +extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget); +extern void usb_del_gadget_udc(struct usb_gadget *gadget); +extern char *usb_get_gadget_udc_name(void); /* iterates the non-control endpoints; 'tmp' is a struct usb_ep pointer */ #define gadget_for_each_ep(tmp, gadget) \ @@ -735,12 +756,6 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver); */ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver); -extern int usb_add_gadget_udc_release(struct device *parent, - struct usb_gadget *gadget, void (*release)(struct device *dev)); -extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget); -extern void usb_del_gadget_udc(struct usb_gadget *gadget); -extern char *usb_get_gadget_udc_name(void); - /*-------------------------------------------------------------------------*/ /* utility to simplify dealing with string descriptors */ -- cgit v1.2.3 From 4d12a897fa1276737724393331d1002962f62940 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 29 Sep 2020 23:22:00 +0530 Subject: bus: mhi: fix doubled words and struct image_info kernel-doc Drop doubled word "table" in kernel-doc. Fix syntax for the kernel-doc notation for struct image_info. Note that the bhi_vec field is private and not part of the kernel-doc. Drop doubled word "device" in a comment. Cc: Manivannan Sadhasivam Cc: Hemant Kumar Reviewed-by: Manivannan Sadhasivam [mani: Added bus: prefix to the commit subject] Signed-off-by: Randy Dunlap Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index c4a940d98912..0779bc689b3e 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -85,13 +85,15 @@ enum mhi_ch_type { }; /** - * struct image_info - Firmware and RDDM table table - * @mhi_buf - Buffer for firmware and RDDM table - * @entries - # of entries in table + * struct image_info - Firmware and RDDM table + * @mhi_buf: Buffer for firmware and RDDM table + * @entries: # of entries in table */ struct image_info { struct mhi_buf *mhi_buf; + /* private: from internal.h */ struct bhi_vec_entry *bhi_vec; + /* public: */ u32 entries; }; @@ -593,7 +595,7 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl); /** * mhi_sync_power_up - Start MHI power up sequence and wait till the device - * device enters valid EE state + * enters valid EE state * @mhi_cntrl: MHI controller */ int mhi_sync_power_up(struct mhi_controller *mhi_cntrl); -- cgit v1.2.3 From 5aa93f0576b4e7be60ffcccb674470c59789fd1b Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Tue, 29 Sep 2020 23:22:05 +0530 Subject: bus: mhi: core: Use generic name field for an MHI device An MHI device is not necessarily associated with only channels as we can have one associated with the controller itself. Hence, the chan_name field within the mhi_device structure should instead be replaced with a generic name to accurately reflect any type of MHI device. Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-7-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 0779bc689b3e..bb337d163dda 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -438,10 +438,10 @@ struct mhi_controller { }; /** - * struct mhi_device - Structure representing a MHI device which binds - * to channels + * struct mhi_device - Structure representing an MHI device which binds + * to channels or is associated with controllers * @id: Pointer to MHI device ID struct - * @chan_name: Name of the channel to which the device binds + * @name: Name of the associated MHI device * @mhi_cntrl: Controller the device belongs to * @ul_chan: UL channel for the device * @dl_chan: DL channel for the device @@ -453,7 +453,7 @@ struct mhi_controller { */ struct mhi_device { const struct mhi_device_id *id; - const char *chan_name; + const char *name; struct mhi_controller *mhi_cntrl; struct mhi_chan *ul_chan; struct mhi_chan *dl_chan; -- cgit v1.2.3 From 601455dae00a853d1d8d6d768b3b79a7d59a5853 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Tue, 29 Sep 2020 23:22:07 +0530 Subject: bus: mhi: core: Introduce counters to track MHI device state transitions Use counters to track MHI device state transitions such as those to M0, M2, or M3 states. This can help in better debug, allowing the user to see the number of transitions to a certain MHI state when queried using debugfs entries or via other mechanisms. Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-9-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index bb337d163dda..c56b4447a4e9 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -328,6 +328,7 @@ struct mhi_controller_config { * @dev_state: MHI device state * @dev_wake: Device wakeup count * @pending_pkts: Pending packets for the controller + * @M0, M2, M3: Counters to track number of device MHI state changes * @transition_list: List of MHI state transitions * @transition_lock: Lock for protecting MHI state transition list * @wlock: Lock for protecting device wakeup @@ -407,6 +408,7 @@ struct mhi_controller { enum mhi_state dev_state; atomic_t dev_wake; atomic_t pending_pkts; + u32 M0, M2, M3; struct list_head transition_list; spinlock_t transition_lock; spinlock_t wlock; -- cgit v1.2.3 From 8e3729bfa7be159d1f94d0caab9c1beff8268672 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Tue, 29 Sep 2020 23:22:08 +0530 Subject: bus: mhi: core: Read and save device hardware information from BHI Device hardware specific information such as serial number and the OEM PK hash can be read using BHI and saved on host to identify the endpoint. Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-10-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index c56b4447a4e9..0c97f4bc5fae 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -16,6 +16,8 @@ #include #include +#define MHI_MAX_OEM_PK_HASH_SEGMENTS 16 + struct mhi_chan; struct mhi_event; struct mhi_ctxt; @@ -316,6 +318,8 @@ struct mhi_controller_config { * @device_number: MHI controller device number * @major_version: MHI controller major revision number * @minor_version: MHI controller minor revision number + * @serial_number: MHI controller serial number obtained from BHI + * @oem_pk_hash: MHI controller OEM PK Hash obtained from BHI * @mhi_event: MHI event ring configurations table * @mhi_cmd: MHI command ring configurations table * @mhi_ctxt: MHI device context, shared memory between host and device @@ -394,6 +398,8 @@ struct mhi_controller { u32 device_number; u32 major_version; u32 minor_version; + u32 serial_number; + u32 oem_pk_hash[MHI_MAX_OEM_PK_HASH_SEGMENTS]; struct mhi_event *mhi_event; struct mhi_cmd *mhi_cmd; -- cgit v1.2.3 From f42dfbe8f712127031e7b9bc938a1c33cec2ff57 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Tue, 29 Sep 2020 23:22:09 +0530 Subject: bus: mhi: core: Introduce APIs to allocate and free the MHI controller Client devices should use the APIs provided to allocate and free the MHI controller structure. This will help ensure that the structure is zero-initialized and there are no false positives with respect to reading any values such as the serial number or the OEM PK hash. Suggested-by: Manivannan Sadhasivam Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-11-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 0c97f4bc5fae..6b987e8cc438 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -527,6 +527,18 @@ struct mhi_driver { #define to_mhi_driver(drv) container_of(drv, struct mhi_driver, driver) #define to_mhi_device(dev) container_of(dev, struct mhi_device, dev) +/** + * mhi_alloc_controller - Allocate the MHI Controller structure + * Allocate the mhi_controller structure using zero initialized memory + */ +struct mhi_controller *mhi_alloc_controller(void); + +/** + * mhi_free_controller - Free the MHI Controller structure + * Free the mhi_controller structure which was previously allocated + */ +void mhi_free_controller(struct mhi_controller *mhi_cntrl); + /** * mhi_register_controller - Register MHI controller * @mhi_cntrl: MHI controller to register -- cgit v1.2.3 From f38173a731cae380885e843dace21c8dc4198285 Mon Sep 17 00:00:00 2001 From: Hemant Kumar Date: Tue, 29 Sep 2020 23:22:10 +0530 Subject: bus: mhi: core: Add const qualifier to MHI config information MHI channel, event and controller config data needs to be treated read only information. Add const qualifier to make sure config information passed by MHI controller is not modified by MHI core driver. Suggested-by: Kalle Valo Reviewed-by: Manivannan Sadhasivam Signed-off-by: Hemant Kumar Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-12-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 6b987e8cc438..b2c0214bfbd6 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -280,9 +280,9 @@ struct mhi_controller_config { u32 timeout_ms; u32 buf_len; u32 num_channels; - struct mhi_channel_config *ch_cfg; + const struct mhi_channel_config *ch_cfg; u32 num_events; - struct mhi_event_config *event_cfg; + const struct mhi_event_config *event_cfg; bool use_bounce_buf; bool m2_no_db; }; @@ -545,7 +545,7 @@ void mhi_free_controller(struct mhi_controller *mhi_cntrl); * @config: Configuration to use for the controller */ int mhi_register_controller(struct mhi_controller *mhi_cntrl, - struct mhi_controller_config *config); + const struct mhi_controller_config *config); /** * mhi_unregister_controller - Unregister MHI controller -- cgit v1.2.3 From e1427f32b85010ca0c38104955e234ca89d4cee5 Mon Sep 17 00:00:00 2001 From: Clark Williams Date: Tue, 29 Sep 2020 23:22:11 +0530 Subject: bus: mhi: Remove include of rwlock_types.h rwlock.h should not be included directly. Instead linux/splinlock.h should be included. Including it directly will break the RT build. Also there is no point in including _types.h headers directly. There is no benefit in including the type without the accessor. Fixes: 0cbf260820fa7 ("bus: mhi: core: Add support for registering MHI controllers") Reviewed-by: Manivannan Sadhasivam Signed-off-by: Clark Williams Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-13-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index b2c0214bfbd6..008b8f6fa9ff 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -9,10 +9,9 @@ #include #include #include -#include #include #include -#include +#include #include #include -- cgit v1.2.3 From c7bd825e52b3d0b9ae519a006b80521d4587f864 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Tue, 29 Sep 2020 23:22:13 +0530 Subject: bus: mhi: core: Introduce debugfs entries for MHI Introduce debugfs entries to show state, register, channel, device, and event rings information. Allow the host to dump registers, issue device wake, and change the MHI timeout to help in debug. Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-15-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 008b8f6fa9ff..fb45a0ff9aa3 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -291,6 +291,7 @@ struct mhi_controller_config { * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI * controller (required) * @mhi_dev: MHI device instance for the controller + * @debugfs_dentry: MHI controller debugfs directory * @regs: Base address of MHI MMIO register space (required) * @bhi: Points to base of MHI BHI register space * @bhie: Points to base of MHI BHIe register space @@ -370,6 +371,7 @@ struct mhi_controller_config { struct mhi_controller { struct device *cntrl_dev; struct mhi_device *mhi_dev; + struct dentry *debugfs_dentry; void __iomem *regs; void __iomem *bhi; void __iomem *bhie; -- cgit v1.2.3 From 9654ab011e28ee756d231035c488509dc214fa6f Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 29 Sep 2020 23:22:16 +0530 Subject: bus: mhi: Remove unused nr_irqs_req variable nr_irqs_req is unused in MHI stack. Reviewed-by: Manivannan Sadhasivam Signed-off-by: Loic Poulain Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200929175218.8178-18-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index fb45a0ff9aa3..d4841e5a5f45 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -312,7 +312,6 @@ struct mhi_controller_config { * @total_ev_rings: Total # of event rings allocated * @hw_ev_rings: Number of hardware event rings * @sw_ev_rings: Number of software event rings - * @nr_irqs_req: Number of IRQs required to operate (optional) * @nr_irqs: Number of IRQ allocated by bus master (required) * @family_number: MHI controller family number * @device_number: MHI controller device number @@ -393,7 +392,6 @@ struct mhi_controller { u32 total_ev_rings; u32 hw_ev_rings; u32 sw_ev_rings; - u32 nr_irqs_req; u32 nr_irqs; u32 family_number; u32 device_number; -- cgit v1.2.3 From 2efc459d06f1630001e3984854848a5647086232 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 16 Sep 2020 13:40:38 -0700 Subject: sysfs: Add sysfs_emit and sysfs_emit_at to format sysfs output Output defects can exist in sysfs content using sprintf and snprintf. sprintf does not know the PAGE_SIZE maximum of the temporary buffer used for outputting sysfs content and it's possible to overrun the PAGE_SIZE buffer length. Add a generic sysfs_emit function that knows that the size of the temporary buffer and ensures that no overrun is done. Add a generic sysfs_emit_at function that can be used in multiple call situations that also ensures that no overrun is done. Validate the output buffer argument to be page aligned. Validate the offset len argument to be within the PAGE_SIZE buf. Signed-off-by: Joe Perches Link: https://lore.kernel.org/r/884235202216d464d61ee975f7465332c86f76b2.1600285923.git.joe@perches.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 34e84122f635..2caa34c1ca1a 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -329,6 +329,10 @@ int sysfs_groups_change_owner(struct kobject *kobj, int sysfs_group_change_owner(struct kobject *kobj, const struct attribute_group *groups, kuid_t kuid, kgid_t kgid); +__printf(2, 3) +int sysfs_emit(char *buf, const char *fmt, ...); +__printf(3, 4) +int sysfs_emit_at(char *buf, int at, const char *fmt, ...); #else /* CONFIG_SYSFS */ @@ -576,6 +580,17 @@ static inline int sysfs_group_change_owner(struct kobject *kobj, return 0; } +__printf(2, 3) +static inline int sysfs_emit(char *buf, const char *fmt, ...) +{ + return 0; +} + +__printf(3, 4) +static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...) +{ + return 0; +} #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, -- cgit v1.2.3 From 7981593bf083801035b1f1377661849805acb216 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 16 Sep 2020 13:40:43 -0700 Subject: mm: and drivers core: Convert hugetlb_report_node_meminfo to sysfs_emit Convert the unbound sprintf in hugetlb_report_node_meminfo to use sysfs_emit_at so that no possible overrun of a PAGE_SIZE buf can occur. Signed-off-by: Joe Perches Acked-by: Mike Kravetz Link: https://lore.kernel.org/r/894b351b82da6013cde7f36ff4b5493cd0ec30d0.1600285923.git.joe@perches.com Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d5cc5f802dd4..ebca2ef02212 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -129,7 +129,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page); void hugetlb_report_meminfo(struct seq_file *); -int hugetlb_report_node_meminfo(int, char *); +int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, @@ -245,7 +245,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) { } -static inline int hugetlb_report_node_meminfo(int nid, char *buf) +static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } -- cgit v1.2.3 From 12f3467b0d28369d3add7a0deb65fdac9b503c90 Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Thu, 24 Sep 2020 11:00:45 +0200 Subject: usb: typec: add typec_find_pwr_opmode This patch adds a function that converts power operation mode string into power operation mode value. It is useful to configure power operation mode through device tree property, as power capabilities may be linked to hardware design. Acked-by: Heikki Krogerus Signed-off-by: Amelie Delaunay Link: https://lore.kernel.org/r/20200924090049.9041-3-amelie.delaunay@st.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 9cb1bec94b71..6be558045942 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -268,6 +268,7 @@ int typec_set_mode(struct typec_port *port, int mode); void *typec_get_drvdata(struct typec_port *port); +int typec_find_pwr_opmode(const char *name); int typec_find_orientation(const char *name); int typec_find_port_power_role(const char *name); int typec_find_power_role(const char *name); -- cgit v1.2.3 From ba1df797e5bbba68ddd1a29bd658b1c11f9a60b6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 1 Oct 2020 18:59:07 -0400 Subject: NFSACL: Replace PROC() macro with open code Clean up: Follow-up on ten-year-old commit b9081d90f5b9 ("NFS: kill off complicated macro 'PROC'") by performing the same conversion in the NFSACL code. To reduce the chance of error, I copied the original C preprocessor output and then made some minor edits. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/uapi/linux/nfsacl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nfsacl.h b/include/uapi/linux/nfsacl.h index ca9a8501ff30..2c2ad204d3b0 100644 --- a/include/uapi/linux/nfsacl.h +++ b/include/uapi/linux/nfsacl.h @@ -9,11 +9,13 @@ #define NFS_ACL_PROGRAM 100227 +#define ACLPROC2_NULL 0 #define ACLPROC2_GETACL 1 #define ACLPROC2_SETACL 2 #define ACLPROC2_GETATTR 3 #define ACLPROC2_ACCESS 4 +#define ACLPROC3_NULL 0 #define ACLPROC3_GETACL 1 #define ACLPROC3_SETACL 2 -- cgit v1.2.3 From 1f86a00c1159fd77e66b1bd6ff1a183f4d46f34d Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Tue, 29 Sep 2020 11:54:31 +0300 Subject: bus/fsl-mc: add support for 'driver_override' in the mc-bus This patch is required for vfio-fsl-mc meta driver to successfully bind layerscape container devices for device passthrough. This patch adds a mechanism to allow a layerscape device to specify a driver rather than a layerscape driver provide a device match. Example to allow a device (dprc.1) to specifically bind with driver (vfio-fsl-mc):- - echo vfio-fsl-mc > /sys/bus/fsl-mc/devices/dprc.1/driver_override - echo dprc.1 > /sys/bus/fsl-mc/drivers/fsl_mc_dprc/unbind - echo dprc.1 > /sys/bus/fsl-mc/drivers/vfio-fsl-mc/bind Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Bharat Bhushan Signed-off-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-4-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index a428c61ead6e..3b5f0c98636d 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -161,6 +161,7 @@ struct fsl_mc_obj_desc { * @regions: pointer to array of MMIO region entries * @irqs: pointer to array of pointers to interrupts allocated to this device * @resource: generic resource associated with this MC object device, if any. + * @driver_override: driver name to force a match * * Generic device object for MC object devices that are "attached" to a * MC bus. @@ -194,6 +195,7 @@ struct fsl_mc_device { struct fsl_mc_device_irq **irqs; struct fsl_mc_resource *resource; struct device_link *consumer_link; + char *driver_override; }; #define to_fsl_mc_device(_dev) \ -- cgit v1.2.3 From e0c171d5537f45185c2e8f97b9ab2e2fdea56fa9 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Tue, 29 Sep 2020 11:54:32 +0300 Subject: bus/fsl-mc: Set the QMAN/BMAN region flags The QMAN region is memory mapped, so it should be of type IORESOURCE_MEM. The region flags bits were wrongly used to pass additional information. Use the bus specific bits for this purpose. Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-5-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 3b5f0c98636d..03a5d16dde73 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -3,6 +3,7 @@ * Freescale Management Complex (MC) bus public interface * * Copyright (C) 2014-2016 Freescale Semiconductor, Inc. + * Copyright 2019-2020 NXP * Author: German Rivera * */ @@ -148,6 +149,13 @@ struct fsl_mc_obj_desc { */ #define FSL_MC_IS_DPRC 0x0001 +/* Region flags */ +/* Indicates that region can be mapped as cacheable */ +#define FSL_MC_REGION_CACHEABLE 0x00000001 + +/* Indicates that region can be mapped as shareable */ +#define FSL_MC_REGION_SHAREABLE 0x00000002 + /** * struct fsl_mc_device - MC object device object * @dev: Linux driver model device object -- cgit v1.2.3 From 715b02ce8968bd560d295945520bae6d73707a73 Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Tue, 29 Sep 2020 11:54:34 +0300 Subject: bus/fsl-mc: Add dprc-reset-container support DPRC reset is required by VFIO-mc in order to stop a device to further generate DMA transactions. Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Bharat Bhushan Signed-off-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-7-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 03a5d16dde73..1d8800acf21f 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -524,6 +524,13 @@ static inline bool is_fsl_mc_bus_dpdmai(const struct fsl_mc_device *mc_dev) return mc_dev->dev.type == &fsl_mc_bus_dpdmai_type; } +#define DPRC_RESET_OPTION_NON_RECURSIVE 0x00000001 +int dprc_reset_container(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + int child_container_id, + u32 options); + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From 5d781fabe64244ccf8a954617ea8b28737517b1c Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Tue, 29 Sep 2020 11:54:35 +0300 Subject: bus/fsl-mc: Export dprc_scan/dprc_remove functions to be used by multiple entities Currently the DPRC scan function is used only by the bus driver. But the same functionality will be needed by the VFIO driver. To support this, the dprc scan function was exported and a little bit adjusted to fit both scenarios. Also the scan mutex initialization is done when the bus object is created, not in dprc_probe in order to be used by both VFIO and bus driver. Similarily dprc_remove_devices is exported to be used by VFIO. Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-8-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 1d8800acf21f..da11171bc38f 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -531,6 +531,13 @@ int dprc_reset_container(struct fsl_mc_io *mc_io, int child_container_id, u32 options); +int dprc_scan_container(struct fsl_mc_device *mc_bus_dev, + bool alloc_interrupts); + +void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev, + struct fsl_mc_obj_desc *obj_desc_array, + int num_child_objects_in_mc); + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From 46f35b5fbbbb22896839e5dbcc24d020926dca36 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Tue, 29 Sep 2020 11:54:36 +0300 Subject: bus/fsl-mc: Export a cleanup function for DPRC Create and export a cleanup function for DPRC. The function is used by the DPRC driver, but it will be used by the VFIO driver as well. Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-9-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index da11171bc38f..5519a510b8c9 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -538,6 +538,8 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev, struct fsl_mc_obj_desc *obj_desc_array, int num_child_objects_in_mc); +int dprc_cleanup(struct fsl_mc_device *mc_dev); + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From 17eaf21320da965c2571a5f029a2becaffe8313f Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Tue, 29 Sep 2020 11:54:37 +0300 Subject: bus/fsl-mc: Add a container setup function Both DPRC driver and VFIO driver use the same initialization code for the DPRC. Introduced a new function which groups this initialization code. The function is exported and may be used by VFIO as well. Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-10-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 5519a510b8c9..e99d181ee4cd 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -540,6 +540,8 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev, int dprc_cleanup(struct fsl_mc_device *mc_dev); +int dprc_setup(struct fsl_mc_device *mc_dev); + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From 0dadd95216d56cec01cef066eebe6354f069ff34 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Tue, 29 Sep 2020 11:54:39 +0300 Subject: bus/fsl-mc: Export IRQ pool handling functions to be used by VFIO The IRQ pool handling functions can be used by both DPRC driver and VFIO. Adapt and export those functions. Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-12-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index e99d181ee4cd..f791fe38c251 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -542,6 +542,17 @@ int dprc_cleanup(struct fsl_mc_device *mc_dev); int dprc_setup(struct fsl_mc_device *mc_dev); +/** + * Maximum number of total IRQs that can be pre-allocated for an MC bus' + * IRQ pool + */ +#define FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS 256 + +int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev, + unsigned int irq_count); + +void fsl_mc_cleanup_irq_pool(struct fsl_mc_device *mc_bus_dev); + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From 273ee53ddf2e7d79565aff0ddc009ea2114d763b Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Tue, 29 Sep 2020 11:54:40 +0300 Subject: bus/fsl-mc: Extend ICID size from 16bit to 32bit In virtual machines the device-id range is defined between 0x10000-0x20000. The reason for using such a large range is to avoid overlapping with the PCI range. Reviewed-by: Laurentiu Tudor Acked-by: Laurentiu Tudor Signed-off-by: Bharat Bhushan Signed-off-by: Laurentiu Tudor Signed-off-by: Diana Craciun Link: https://lore.kernel.org/r/20200929085441.17448-13-diana.craciun@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index f791fe38c251..db244874e834 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -195,7 +195,7 @@ struct fsl_mc_device { struct device dev; u64 dma_mask; u16 flags; - u16 icid; + u32 icid; u16 mc_handle; struct fsl_mc_io *mc_io; struct fsl_mc_obj_desc obj_desc; -- cgit v1.2.3 From be458311cdbb5d94820ffc4e40c5906085c0a507 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 1 Oct 2020 13:07:49 -0700 Subject: mm: memcg/slab: fix slab statistics in !SMP configuration Since commit ea426c2a7de8 ("mm: memcg: prepare for byte-sized vmstat items") the write side of slab counters accepts a value in bytes and converts it to pages. It happens in __mod_node_page_state(). However a non-SMP version of __mod_node_page_state() doesn't perform this conversion. It leads to incorrect (unrealistically high) slab counters values. Fix this by adding a similar conversion to the non-SMP version of __mod_node_page_state(). Signed-off-by: Roman Gushchin Reported-and-tested-by: Bastian Bittorf Fixes: ea426c2a7de8 ("mm: memcg: prepare for byte-sized vmstat items") Acked-by: Vlastimil Babka Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 91220ace31da..7557c1070fd7 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -312,6 +312,11 @@ static inline void __mod_zone_page_state(struct zone *zone, static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { + if (vmstat_item_in_bytes(item)) { + VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); + delta >>= PAGE_SHIFT; + } + node_page_state_add(delta, pgdat, item); } -- cgit v1.2.3 From 894c26a1c274b8eafbb4b1dad67e70e51a106061 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 30 Sep 2020 22:05:42 +0800 Subject: ACPI: Support Generic Initiator only domains Generic Initiators are a new ACPI concept that allows for the description of proximity domains that contain a device which performs memory access (such as a network card) but neither host CPU nor Memory. This patch has the parsing code and provides the infrastructure for an architecture to associate these new domains with their nearest memory processing node. Signed-off-by: Jonathan Cameron Signed-off-by: Rafael J. Wysocki --- include/linux/nodemask.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 27e7fa36f707..3334ce056335 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -399,6 +399,7 @@ enum node_states { #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ + N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; -- cgit v1.2.3 From 01aabca2fd545554905321029e6c4c5b2fedb345 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 30 Sep 2020 22:05:44 +0800 Subject: ACPI: Let ACPI know we support Generic Initiator Affinity Structures Until we tell ACPI that we support generic initiators, it will have to operate in fall back domain mode and all _PXM entries should be on existing non GI domains. This patch sets the relevant OSC bit to make that happen. Signed-off-by: Jonathan Cameron Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e9f6cd67943e..edbf3c4116b4 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -545,6 +545,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 +#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; -- cgit v1.2.3 From 1e0cb59d5f0a41d1a2b7a1e7d45024fbac62d6e7 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 30 Sep 2020 13:43:50 +0100 Subject: ACPI: Make acpi_evaluate_dsm() prototype consistent MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When compiling a driver which includes both include/linux/acpi.h and include/acpi/acpi_bus.h for when CONFIG_ACPI=n for i386, I get this: /include/acpi/acpi_bus.h:53:20: error: conflicting types for ‘acpi_evaluate_dsm’ union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, ^~~~~~~~~~~~~~~~~ In file included from drivers/scsi/hisi_sas/hisi_sas.h:10:0, from drivers/scsi/hisi_sas/hisi_sas_main.c:7: ./include/linux/acpi.h:866:34: note: previous definition of ‘acpi_evaluate_dsm’ was here static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, ^~~~~~~~~~~~~~~~~ Fix by making prototype in include/linux/acpi.h consistent. Signed-off-by: John Garry [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 7ce2235f99f9..49dbb105084f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -865,7 +865,7 @@ static inline bool acpi_driver_match_device(struct device *dev, static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, - int rev, int func, + u64 rev, u64 func, union acpi_object *argv4) { return NULL; -- cgit v1.2.3 From 49f618e1b669ef0e26a8d8d7f8fafc7b8fd31531 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 24 Sep 2020 13:04:47 +0200 Subject: PM: domains: Rename power state enums for genpd To clarify the code a bit, let's rename GPD_STATE_ACTIVE into GENPD_STATE_ON and GPD_STATE_POWER_OFF to GENPD_STATE_OFF. Signed-off-by: Ulf Hansson [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index ee11502a575b..66f3c5d64d81 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -64,8 +64,8 @@ #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5) enum gpd_status { - GPD_STATE_ACTIVE = 0, /* PM domain is active */ - GPD_STATE_POWER_OFF, /* PM domain is off */ + GENPD_STATE_ON = 0, /* PM domain is on */ + GENPD_STATE_OFF, /* PM domain is off */ }; struct dev_power_governor { -- cgit v1.2.3 From 50b2412b7e7862c5af0cbf4b10d93bc5c712d021 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Tue, 4 Aug 2020 10:40:21 +0300 Subject: net/mlx5: Avoid possible free of command entry while timeout comp handler Upon command completion timeout, driver simulates a forced command completion. In a rare case where real interrupt for that command arrives simultaneously, it might release the command entry while the forced handler might still access it. Fix that by adding an entry refcount, to track current amount of allowed handlers. Command entry to be released only when this refcount is decremented to zero. Command refcount is always initialized to one. For callback commands, command completion handler is the symmetric flow to decrement it. For non-callback commands, it is wait_func(). Before ringing the doorbell, increment the refcount for the real completion handler. Once the real completion handler is called, it will decrement it. For callback commands, once the delayed work is scheduled, increment the refcount. Upon callback command completion handler, we will try to cancel the timeout callback. In case of success, we need to decrement the callback refcount as it will never run. In addition, gather the entry index free and the entry free into a one flow for all command types release. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c145de0473bc..897156822f0d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -767,6 +767,8 @@ struct mlx5_cmd_work_ent { u64 ts2; u16 op; bool polling; + /* Track the max comp handlers */ + refcount_t refcnt; }; struct mlx5_pas { -- cgit v1.2.3 From b898ce7bccf13087719c021d829dab607c175246 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 11 Sep 2020 11:48:55 -0700 Subject: net/mlx5: cmdif, Avoid skipping reclaim pages if FW is not accessible In case of pci is offline reclaim_pages_cmd() will still try to call the FW to release FW pages, cmd_exec() in this case will return a silent success without actually calling the FW. This is wrong and will cause page leaks, what we should do is to detect pci offline or command interface un-available before tying to access the FW and manually release the FW pages in the driver. In this patch we share the code to check for FW command interface availability and we call it in sensitive places e.g. reclaim_pages_cmd(). Alternative fix: 1. Remove MLX5_CMD_OP_MANAGE_PAGES form mlx5_internal_err_ret_value, command success simulation list. 2. Always Release FW pages even if cmd_exec fails in reclaim_pages_cmd(). Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 897156822f0d..372100c755e7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -935,6 +935,7 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); +bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); -- cgit v1.2.3 From 82f45c6c4a70622cc0585e3f4372e192a6491d26 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Oct 2020 18:34:48 -0700 Subject: bpf: tcp: Do not limit cb_flags when creating child sk from listen sk The commit 0813a841566f ("bpf: tcp: Allow bpf prog to write and parse TCP header option") unnecessarily introduced bpf_skops_init_child() which limited the child sk from inheriting all bpf_sock_ops_cb_flags of the listen sk. That breaks existing user expectation. This patch removes the bpf_skops_init_child() and just allows sock_copy() to do its job to copy everything from listen sk to the child sk. Fixes: 0813a841566f ("bpf: tcp: Allow bpf prog to write and parse TCP header option") Reported-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201002013448.2542025-1-kafai@fb.com --- include/net/tcp.h | 33 --------------------------------- 1 file changed, 33 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 3601dea931a6..d4ef5bf94168 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2228,34 +2228,6 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, #endif /* CONFIG_NET_SOCK_MSG */ #ifdef CONFIG_CGROUP_BPF -/* Copy the listen sk's HDR_OPT_CB flags to its child. - * - * During 3-Way-HandShake, the synack is usually sent from - * the listen sk with the HDR_OPT_CB flags set so that - * bpf-prog will be called to write the BPF hdr option. - * - * In fastopen, the child sk is used to send synack instead - * of the listen sk. Thus, inheriting the HDR_OPT_CB flags - * from the listen sk gives the bpf-prog a chance to write - * BPF hdr option in the synack pkt during fastopen. - * - * Both fastopen and non-fastopen child will inherit the - * HDR_OPT_CB flags to keep the bpf-prog having a consistent - * behavior when deciding to clear this cb flags (or not) - * during the PASSIVE_ESTABLISHED_CB. - * - * In the future, other cb flags could be inherited here also. - */ -static inline void bpf_skops_init_child(const struct sock *sk, - struct sock *child) -{ - tcp_sk(child)->bpf_sock_ops_cb_flags = - tcp_sk(sk)->bpf_sock_ops_cb_flags & - (BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG | - BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | - BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); -} - static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) @@ -2264,11 +2236,6 @@ static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, skops->skb_data_end = skb->data + end_offset; } #else -static inline void bpf_skops_init_child(const struct sock *sk, - struct sock *child) -{ -} - static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) -- cgit v1.2.3 From 69e0ad37c9f32d5aa1beb02aab4ec0cd055be013 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 28 Sep 2020 16:09:39 -0700 Subject: static_call: Fix return type of static_call_init Functions that are passed to early_initcall should be of type initcall_t, which expects a return type of int. This is not currently an error but a patch in the Clang LTO series could change that in the future. Fixes: 9183c3f9ed71 ("static_call: Add inline static call infrastructure") Signed-off-by: Nathan Chancellor Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Sami Tolvanen Link: https://lore.kernel.org/lkml/20200903203053.3411268-17-samitolvanen@google.com/ --- include/linux/static_call.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index bfa2ba39be57..695da4c9b338 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -136,7 +136,7 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE -extern void __init static_call_init(void); +extern int __init static_call_init(void); struct static_call_mod { struct static_call_mod *next; @@ -187,7 +187,7 @@ extern int static_call_text_reserved(void *start, void *end); #elif defined(CONFIG_HAVE_STATIC_CALL) -static inline void static_call_init(void) { } +static inline int static_call_init(void) { return 0; } struct static_call_key { void *func; @@ -234,7 +234,7 @@ static inline int static_call_text_reserved(void *start, void *end) #else /* Generic implementation */ -static inline void static_call_init(void) { } +static inline int static_call_init(void) { return 0; } struct static_call_key { void *func; -- cgit v1.2.3 From a95bc734e60449e7b073ff7ff70c35083b290ae9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 2 Oct 2020 09:46:04 +0200 Subject: netlink: fix policy dump leak If userspace doesn't complete the policy dump, we leak the allocated state. Fix this. Fixes: d07dcf9aadd6 ("netlink: add infrastructure to expose policies to userspace") Signed-off-by: Johannes Berg Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/netlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 8e0eb2c9c528..271620f6bc7f 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1934,7 +1934,8 @@ void nla_get_range_signed(const struct nla_policy *pt, int netlink_policy_dump_start(const struct nla_policy *policy, unsigned int maxtype, unsigned long *state); -bool netlink_policy_dump_loop(unsigned long *state); +bool netlink_policy_dump_loop(unsigned long state); int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); +void netlink_policy_dump_free(unsigned long state); #endif -- cgit v1.2.3 From 949ca6b82e43b342dba153a9fd643fb1b5e9f034 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 2 Oct 2020 09:46:04 +0200 Subject: netlink: fix policy dump leak [ Upstream commit a95bc734e60449e7b073ff7ff70c35083b290ae9 ] If userspace doesn't complete the policy dump, we leak the allocated state. Fix this. Fixes: d07dcf9aadd6 ("netlink: add infrastructure to expose policies to userspace") Signed-off-by: Johannes Berg Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/netlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index b2cf34f53e55..9e7eca961a98 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1938,7 +1938,8 @@ void nla_get_range_signed(const struct nla_policy *pt, int netlink_policy_dump_start(const struct nla_policy *policy, unsigned int maxtype, unsigned long *state); -bool netlink_policy_dump_loop(unsigned long *state); +bool netlink_policy_dump_loop(unsigned long state); int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); +void netlink_policy_dump_free(unsigned long state); #endif -- cgit v1.2.3 From 1132e56e78e3c8f4deaf68ed760c78456a9c61f4 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Thu, 1 Oct 2020 14:50:48 +0800 Subject: bcache: add set_uuid in struct cache_set This patch adds a separated set_uuid[16] in struct cache_set, to store the uuid of the cache set. This is the preparation to remove the embedded struct cache_sb from struct cache_set. Signed-off-by: Coly Li Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/trace/events/bcache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index 0bddea663b3b..e41c611d6d3b 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -164,7 +164,7 @@ TRACE_EVENT(bcache_write, ), TP_fast_assign( - memcpy(__entry->uuid, c->sb.set_uuid, 16); + memcpy(__entry->uuid, c->set_uuid, 16); __entry->inode = inode; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; @@ -200,7 +200,7 @@ DECLARE_EVENT_CLASS(cache_set, ), TP_fast_assign( - memcpy(__entry->uuid, c->sb.set_uuid, 16); + memcpy(__entry->uuid, c->set_uuid, 16); ), TP_printk("%pU", __entry->uuid) -- cgit v1.2.3 From 1dc0408cdf3caf3a8b8ad97c831ae52d2ab5b953 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 1 Oct 2020 19:42:12 -0700 Subject: net: dsa: Call dsa_untag_bridge_pvid() from dsa_switch_rcv() When a DSA switch driver needs to call dsa_untag_bridge_pvid(), it can set dsa_switch::untag_brige_pvid to indicate this is necessary. This is a pre-requisite to making sure that we are always calling dsa_untag_bridge_pvid() after eth_type_trans() has been called. Signed-off-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b502a63d196e..8b0696e08cac 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -308,6 +308,14 @@ struct dsa_switch { */ bool configure_vlan_while_not_filtering; + /* If the switch driver always programs the CPU port as egress tagged + * despite the VLAN configuration indicating otherwise, then setting + * @untag_bridge_pvid will force the DSA receive path to pop the bridge's + * default_pvid VLAN tagged frames to offer a consistent behavior + * between a vlan_filtering=0 and vlan_filtering=1 bridge device. + */ + bool untag_bridge_pvid; + /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ -- cgit v1.2.3 From 4976b718c3551faba2c0616ef55ebeb74db1c5ca Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 29 Sep 2020 16:50:44 -0700 Subject: bpf: Introduce pseudo_btf_id Pseudo_btf_id is a type of ld_imm insn that associates a btf_id to a ksym so that further dereferences on the ksym can use the BTF info to validate accesses. Internally, when seeing a pseudo_btf_id ld insn, the verifier reads the btf_id stored in the insn[0]'s imm field and marks the dst_reg as PTR_TO_BTF_ID. The btf_id points to a VAR_KIND, which is encoded in btf_vminux by pahole. If the VAR is not of a struct type, the dst reg will be marked as PTR_TO_MEM instead of PTR_TO_BTF_ID and the mem_size is resolved to the size of the VAR's type. >From the VAR btf_id, the verifier can also read the address of the ksym's corresponding kernel var from kallsyms and use that to fill dst_reg. Therefore, the proper functionality of pseudo_btf_id depends on (1) kallsyms and (2) the encoding of kernel global VARs in pahole, which should be available since pahole v1.18. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200929235049.2533242-2-haoluo@google.com --- include/linux/bpf_verifier.h | 7 +++++++ include/linux/btf.h | 15 +++++++++++++++ include/uapi/linux/bpf.h | 36 +++++++++++++++++++++++++++--------- 3 files changed, 49 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 363b4f1c562a..e83ef6f6bf43 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -308,6 +308,13 @@ struct bpf_insn_aux_data { u32 map_index; /* index into used_maps[] */ u32 map_off; /* offset from value base address */ }; + struct { + enum bpf_reg_type reg_type; /* type of pseudo_btf_id */ + union { + u32 btf_id; /* btf_id for struct typed var */ + u32 mem_size; /* mem_size for non-struct typed var */ + }; + } btf_var; }; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 024e16ff7dcc..af1244180588 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -145,6 +145,21 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; } +static inline bool btf_type_is_var(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; +} + +/* union is only a special case of struct: + * all its offsetof(member) == 0 + */ +static inline bool btf_type_is_struct(const struct btf_type *t) +{ + u8 kind = BTF_INFO_KIND(t->info); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + static inline u16 btf_type_vlen(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4f556cfcbfbe..2aa156af24d6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -356,18 +356,36 @@ enum bpf_link_type { #define BPF_F_SLEEPABLE (1U << 4) /* When BPF ldimm64's insn[0].src_reg != 0 then this can have - * two extensions: - * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd map fd - * insn[1].imm: 0 offset into value - * insn[0].off: 0 0 - * insn[1].off: 0 0 - * ldimm64 rewrite: address of map address of map[0]+offset - * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE + * the following extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_FD + * insn[0].imm: map fd + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of map + * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 +/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE + * insn[0].imm: map fd + * insn[1].imm: offset into value + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of map[0]+offset + * verifier type: PTR_TO_MAP_VALUE + */ #define BPF_PSEUDO_MAP_VALUE 2 +/* insn[0].src_reg: BPF_PSEUDO_BTF_ID + * insn[0].imm: kernel btd id of VAR + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of the kernel variable + * verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var + * is struct/union. + */ +#define BPF_PSEUDO_BTF_ID 3 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function -- cgit v1.2.3 From eaa6bcb71ef6ed3dc18fc525ee7e293b06b4882b Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 29 Sep 2020 16:50:47 -0700 Subject: bpf: Introduce bpf_per_cpu_ptr() Add bpf_per_cpu_ptr() to help bpf programs access percpu vars. bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the kernel except that it may return NULL. This happens when the cpu parameter is out of range. So the caller must check the returned value. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200929235049.2533242-5-haoluo@google.com --- include/linux/bpf.h | 4 ++++ include/linux/btf.h | 11 +++++++++++ include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 3 files changed, 33 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 50e5c4b52bd1..9dde15b2479d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -293,6 +293,7 @@ enum bpf_arg_type { ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ + ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ __BPF_ARG_TYPE_MAX, }; @@ -307,6 +308,7 @@ enum bpf_return_type { RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ + RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -405,6 +407,7 @@ enum bpf_reg_type { PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ + PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ }; /* The information passed from prog-specific *_is_valid_access @@ -1828,6 +1831,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; +extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/btf.h b/include/linux/btf.h index af1244180588..2bf641829664 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -110,6 +110,11 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type, i < btf_type_vlen(struct_type); \ i++, member++) +#define for_each_vsi(i, datasec_type, member) \ + for (i = 0, member = btf_type_var_secinfo(datasec_type); \ + i < btf_type_vlen(datasec_type); \ + i++, member++) + static inline bool btf_type_is_ptr(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; @@ -194,6 +199,12 @@ static inline const struct btf_member *btf_type_member(const struct btf_type *t) return (const struct btf_member *)(t + 1); } +static inline const struct btf_var_secinfo *btf_type_var_secinfo( + const struct btf_type *t) +{ + return (const struct btf_var_secinfo *)(t + 1); +} + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2aa156af24d6..f3c1b637ab39 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3686,6 +3686,23 @@ union bpf_attr { * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. + * + * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on *cpu*. A ksym is an + * extern variable decorated with '__ksym'. For ksym, there is a + * global var (either static or global) defined of the same name + * in the kernel. The ksym is percpu if the global var is percpu. + * The returned pointer points to the global percpu var on *cpu*. + * + * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the + * kernel, except that bpf_per_cpu_ptr() may return NULL. This + * happens if *cpu* is larger than nr_cpu_ids. The caller of + * bpf_per_cpu_ptr() must check the returned value. + * Return + * A pointer pointing to the kernel percpu variable on *cpu*, or + * NULL, if *cpu* is invalid. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3841,6 +3858,7 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ + FN(bpf_per_cpu_ptr), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 63d9b80dcf2c67bc5ade61cbbaa09d7af21f43f1 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 29 Sep 2020 16:50:48 -0700 Subject: bpf: Introducte bpf_this_cpu_ptr() Add bpf_this_cpu_ptr() to help access percpu var on this cpu. This helper always returns a valid pointer, therefore no need to check returned value for NULL. Also note that all programs run with preemption disabled, which means that the returned pointer is stable during all the execution of the program. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200929235049.2533242-6-haoluo@google.com --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 13 +++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9dde15b2479d..dc63eeed4fd9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -309,6 +309,7 @@ enum bpf_return_type { RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */ + RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -1832,6 +1833,7 @@ extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; +extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f3c1b637ab39..c446394135be 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3703,6 +3703,18 @@ union bpf_attr { * Return * A pointer pointing to the kernel percpu variable on *cpu*, or * NULL, if *cpu* is invalid. + * + * void *bpf_this_cpu_ptr(const void *percpu_ptr) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on this cpu. See the + * description of 'ksym' in **bpf_per_cpu_ptr**\ (). + * + * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in + * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would + * never return NULL. + * Return + * A pointer pointing to the kernel percpu variable on this cpu. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3859,6 +3871,7 @@ union bpf_attr { FN(skb_cgroup_classid), \ FN(redirect_neigh), \ FN(bpf_per_cpu_ptr), \ + FN(bpf_this_cpu_ptr), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From a93bdcb94a0b3ca72046151412c2389dca681d2a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 2 Oct 2020 07:49:45 +0200 Subject: net: core: document two new elements of struct net_device As warned by "make htmldocs", there are two new struct elements that aren't documented: ../include/linux/netdevice.h:2159: warning: Function parameter or member 'unlink_list' not described in 'net_device' ../include/linux/netdevice.h:2159: warning: Function parameter or member 'nested_level' not described in 'net_device' Fixes: 1fc70edb7d7b ("net: core: add nested_level variable in net_device") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9fdb3ebef306..18dec08439f9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1851,6 +1851,11 @@ enum netdev_priv_flags { * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * + * @nested_level: Used as as a parameter of spin_lock_nested() of + * dev->addr_list_lock. + * @unlink_list: As netif_addr_lock() can be called recursively, + * keep a list of interfaces to be deleted. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ -- cgit v1.2.3 From c381b07941adc2274ce552daf86c94701c5e265a Mon Sep 17 00:00:00 2001 From: Coly Li Date: Fri, 2 Oct 2020 16:27:28 +0800 Subject: net: introduce helper sendpage_ok() in include/linux/net.h The original problem was from nvme-over-tcp code, who mistakenly uses kernel_sendpage() to send pages allocated by __get_free_pages() without __GFP_COMP flag. Such pages don't have refcount (page_count is 0) on tail pages, sending them by kernel_sendpage() may trigger a kernel panic from a corrupted kernel heap, because these pages are incorrectly freed in network stack as page_count 0 pages. This patch introduces a helper sendpage_ok(), it returns true if the checking page, - is not slab page: PageSlab(page) is false. - has page refcount: page_count(page) is not zero All drivers who want to send page to remote end by kernel_sendpage() may use this helper to check whether the page is OK. If the helper does not return true, the driver should try other non sendpage method (e.g. sock_no_sendpage()) to handle the page. Signed-off-by: Coly Li Cc: Chaitanya Kulkarni Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Jan Kara Cc: Jens Axboe Cc: Mikhail Skorzhinskii Cc: Philipp Reisner Cc: Sagi Grimberg Cc: Vlastimil Babka Cc: stable@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/net.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..ae713c851342 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -286,6 +287,21 @@ do { \ #define net_get_random_once_wait(buf, nbytes) \ get_random_once_wait((buf), (nbytes)) +/* + * E.g. XFS meta- & log-data is in slab pages, or bcache meta + * data pages, or other high order pages allocated by + * __get_free_pages() without __GFP_COMP, which have a page_count + * of 0 and/or have PageSlab() set. We cannot use send_page for + * those, as that does get_page(); put_page(); and would cause + * either a VM_BUG directly, or __page_cache_release a page that + * would actually still be referenced by someone, leading to some + * obscure delayed Oops somewhere else. + */ +static inline bool sendpage_ok(struct page *page) +{ + return !PageSlab(page) && page_count(page) >= 1; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, -- cgit v1.2.3 From 7010645ba7256992818b518163f46bd4cdf8002a Mon Sep 17 00:00:00 2001 From: Roman Bolshakov Date: Tue, 29 Sep 2020 15:59:57 +0300 Subject: scsi: target: core: Add CONTROL field for trace events trace-cmd report doesn't show events from target subsystem because scsi_command_size() leaks through event format string: [target:target_sequencer_start] function scsi_command_size not defined [target:target_cmd_complete] function scsi_command_size not defined Addition of scsi_command_size() to plugin_scsi.c in trace-cmd doesn't help because an expression is used inside TP_printk(). trace-cmd event parser doesn't understand minus sign inside [ ]: Error: expected ']' but read '-' Rather than duplicating kernel code in plugin_scsi.c, provide a dedicated field for CONTROL byte. Link: https://lore.kernel.org/r/20200929125957.83069-1-r.bolshakov@yadro.com Reviewed-by: Mike Christie Signed-off-by: Roman Bolshakov Signed-off-by: Martin K. Petersen --- include/scsi/scsi_common.h | 7 +++++++ include/trace/events/target.h | 12 ++++++------ 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_common.h b/include/scsi/scsi_common.h index 731ac09ed231..5b567b43e1b1 100644 --- a/include/scsi/scsi_common.h +++ b/include/scsi/scsi_common.h @@ -25,6 +25,13 @@ scsi_command_size(const unsigned char *cmnd) scsi_varlen_cdb_length(cmnd) : COMMAND_SIZE(cmnd[0]); } +static inline unsigned char +scsi_command_control(const unsigned char *cmnd) +{ + return (cmnd[0] == VARIABLE_LENGTH_CMD) ? + cmnd[1] : cmnd[COMMAND_SIZE(cmnd[0]) - 1]; +} + /* Returns a human-readable name for the device */ extern const char *scsi_device_type(unsigned type); diff --git a/include/trace/events/target.h b/include/trace/events/target.h index 77408edd29d2..67fad2677ed5 100644 --- a/include/trace/events/target.h +++ b/include/trace/events/target.h @@ -141,6 +141,7 @@ TRACE_EVENT(target_sequencer_start, __field( unsigned int, opcode ) __field( unsigned int, data_length ) __field( unsigned int, task_attribute ) + __field( unsigned char, control ) __array( unsigned char, cdb, TCM_MAX_COMMAND_SIZE ) __string( initiator, cmd->se_sess->se_node_acl->initiatorname ) ), @@ -151,6 +152,7 @@ TRACE_EVENT(target_sequencer_start, __entry->opcode = cmd->t_task_cdb[0]; __entry->data_length = cmd->data_length; __entry->task_attribute = cmd->sam_task_attr; + __entry->control = scsi_command_control(cmd->t_task_cdb); memcpy(__entry->cdb, cmd->t_task_cdb, TCM_MAX_COMMAND_SIZE); __assign_str(initiator, cmd->se_sess->se_node_acl->initiatorname); ), @@ -160,9 +162,7 @@ TRACE_EVENT(target_sequencer_start, __entry->tag, show_opcode_name(__entry->opcode), __entry->data_length, __print_hex(__entry->cdb, 16), show_task_attribute_name(__entry->task_attribute), - scsi_command_size(__entry->cdb) <= 16 ? - __entry->cdb[scsi_command_size(__entry->cdb) - 1] : - __entry->cdb[1] + __entry->control ) ); @@ -178,6 +178,7 @@ TRACE_EVENT(target_cmd_complete, __field( unsigned int, opcode ) __field( unsigned int, data_length ) __field( unsigned int, task_attribute ) + __field( unsigned char, control ) __field( unsigned char, scsi_status ) __field( unsigned char, sense_length ) __array( unsigned char, cdb, TCM_MAX_COMMAND_SIZE ) @@ -191,6 +192,7 @@ TRACE_EVENT(target_cmd_complete, __entry->opcode = cmd->t_task_cdb[0]; __entry->data_length = cmd->data_length; __entry->task_attribute = cmd->sam_task_attr; + __entry->control = scsi_command_control(cmd->t_task_cdb); __entry->scsi_status = cmd->scsi_status; __entry->sense_length = cmd->scsi_status == SAM_STAT_CHECK_CONDITION ? min(18, ((u8 *) cmd->sense_buffer)[SPC_ADD_SENSE_LEN_OFFSET] + 8) : 0; @@ -208,9 +210,7 @@ TRACE_EVENT(target_cmd_complete, show_opcode_name(__entry->opcode), __entry->data_length, __print_hex(__entry->cdb, 16), show_task_attribute_name(__entry->task_attribute), - scsi_command_size(__entry->cdb) <= 16 ? - __entry->cdb[scsi_command_size(__entry->cdb) - 1] : - __entry->cdb[1] + __entry->control ) ); -- cgit v1.2.3 From 319e4dd11a207bac2eaa9b96060145cd0d4c12d2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 2 Oct 2020 15:02:21 +0300 Subject: net: mscc: ocelot: introduce conversion helpers between port and netdev Since the mscc_ocelot_switch_lib is common between a pure switchdev and a DSA driver, the procedure of retrieving a net_device for a certain port index differs, as those are registered by their individual front-ends. Up to now that has been dealt with by always passing the port index to the switch library, but now, we're going to need to work with net_device pointers from the tc-flower offload, for things like indev, or mirred. It is not desirable to refactor that, so let's make sure that the flower offload core has the ability to translate between a net_device and a port index properly. Signed-off-by: Vladimir Oltean Acked-by: Alexandre Belloni Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 0c40122dcb88..424256fa531b 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -559,6 +559,8 @@ enum ocelot_tag_prefix { struct ocelot; struct ocelot_ops { + struct net_device *(*port_to_netdev)(struct ocelot *ocelot, int port); + int (*netdev_to_port)(struct net_device *dev); int (*reset)(struct ocelot *ocelot); u16 (*wm_enc)(u16 value); }; -- cgit v1.2.3 From 1397a2eb52e20e20363cc0a1cb707d5eb473dbb7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 2 Oct 2020 15:02:22 +0300 Subject: net: mscc: ocelot: create TCAM skeleton from tc filter chains For Ocelot switches, there are 2 ingress pipelines for flow offload rules: VCAP IS1 (Ingress Classification) and IS2 (Security Enforcement). IS1 and IS2 support different sets of actions. The pipeline order for a packet on ingress is: Basic classification -> VCAP IS1 -> VCAP IS2 Furthermore, IS1 is looked up 3 times, and IS2 is looked up twice (each TCAM entry can be configured to match only on the first lookup, or only on the second, or on both etc). Because the TCAMs are completely independent in hardware, and because of the fixed pipeline, we actually have very limited options when it comes to offloading complex rules to them while still maintaining the same semantics with the software data path. This patch maps flow offload rules to ingress TCAMs according to a predefined chain index number. There is going to be a script in selftests that clarifies the usage model. There is also an egress TCAM (VCAP ES0, the Egress Rewriter), which is modeled on top of the default chain 0 of the egress qdisc, because it doesn't have multiple lookups. Suggested-by: Allan W. Nielsen Co-developed-by: Xiaoliang Yang Signed-off-by: Xiaoliang Yang Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 424256fa531b..46608494616f 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -633,7 +633,8 @@ struct ocelot { struct list_head multicast; - struct ocelot_vcap_block block; + struct list_head dummy_rules; + struct ocelot_vcap_block block[3]; struct vcap_props *vcap; /* Workqueue to check statistics for overflow with its lock */ -- cgit v1.2.3 From 10c24eb23da0dc67934fcc9b5b0f201750ff8cd8 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 1 Oct 2020 18:11:45 +0300 Subject: devlink: add parser error drop packet traps Add parser error drop packet traps, so that capable device driver could register them with devlink. The new packet trap group holds any drops of packets which were marked by the device as erroneous during header parsing. Add documentation for every added packet trap and packet trap group. Signed-off-by: Ioana Ciornei Signed-off-by: David S. Miller --- include/net/devlink.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 1c286e9a3590..1f5004a5c9f9 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -784,6 +784,22 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_SAMPLE, DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_TRAP, DEVLINK_TRAP_GENERIC_ID_EARLY_DROP, + DEVLINK_TRAP_GENERIC_ID_VXLAN_PARSING, + DEVLINK_TRAP_GENERIC_ID_LLC_SNAP_PARSING, + DEVLINK_TRAP_GENERIC_ID_VLAN_PARSING, + DEVLINK_TRAP_GENERIC_ID_PPPOE_PPP_PARSING, + DEVLINK_TRAP_GENERIC_ID_MPLS_PARSING, + DEVLINK_TRAP_GENERIC_ID_ARP_PARSING, + DEVLINK_TRAP_GENERIC_ID_IP_1_PARSING, + DEVLINK_TRAP_GENERIC_ID_IP_N_PARSING, + DEVLINK_TRAP_GENERIC_ID_GRE_PARSING, + DEVLINK_TRAP_GENERIC_ID_UDP_PARSING, + DEVLINK_TRAP_GENERIC_ID_TCP_PARSING, + DEVLINK_TRAP_GENERIC_ID_IPSEC_PARSING, + DEVLINK_TRAP_GENERIC_ID_SCTP_PARSING, + DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING, + DEVLINK_TRAP_GENERIC_ID_GTP_PARSING, + DEVLINK_TRAP_GENERIC_ID_ESP_PARSING, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -819,6 +835,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL, DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE, DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP, + DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS, /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, @@ -974,6 +991,39 @@ enum devlink_trap_group_generic_id { "flow_action_trap" #define DEVLINK_TRAP_GENERIC_NAME_EARLY_DROP \ "early_drop" +#define DEVLINK_TRAP_GENERIC_NAME_VXLAN_PARSING \ + "vxlan_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_LLC_SNAP_PARSING \ + "llc_snap_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_VLAN_PARSING \ + "vlan_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_PPPOE_PPP_PARSING \ + "pppoe_ppp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_MPLS_PARSING \ + "mpls_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_ARP_PARSING \ + "arp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_IP_1_PARSING \ + "ip_1_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_IP_N_PARSING \ + "ip_n_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_GRE_PARSING \ + "gre_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_UDP_PARSING \ + "udp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_TCP_PARSING \ + "tcp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_IPSEC_PARSING \ + "ipsec_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_SCTP_PARSING \ + "sctp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_DCCP_PARSING \ + "dccp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_GTP_PARSING \ + "gtp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_ESP_PARSING \ + "esp_parsing" + #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -1025,6 +1075,8 @@ enum devlink_trap_group_generic_id { "acl_sample" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_TRAP \ "acl_trap" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PARSER_ERROR_DROPS \ + "parser_error_drops" #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id, \ _metadata_cap) \ -- cgit v1.2.3 From c50bf2be7306cd37e4a8228acfe0fee36b9097dc Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 1 Oct 2020 18:11:46 +0300 Subject: devlink: add .trap_group_action_set() callback Add a new devlink callback, .trap_group_action_set(), which can be used by device drivers which do not support controlling the action (drop, trap) on each trap but rather on the entire group trap. If this new callback is populated, it will take precedence over the .trap_action_set() callback when the user requests a change of all the traps in a group. Signed-off-by: Ioana Ciornei Signed-off-by: David S. Miller --- include/net/devlink.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 1f5004a5c9f9..89ede1ce3a3a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1242,6 +1242,16 @@ struct devlink_ops { const struct devlink_trap_group *group, const struct devlink_trap_policer *policer, struct netlink_ext_ack *extack); + /** + * @trap_group_action_set: Trap group action set function. + * + * If this callback is populated, it will take precedence over looping + * over all traps in a group and calling .trap_action_set(). + */ + int (*trap_group_action_set)(struct devlink *devlink, + const struct devlink_trap_group *group, + enum devlink_trap_action action, + struct netlink_ext_ack *extack); /** * @trap_policer_init: Trap policer initialization function. * -- cgit v1.2.3 From f5ace5ef37b1e1de49882248656f35c45e041585 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 2 Oct 2020 18:10:33 -0500 Subject: block: scsi_ioctl: Avoid the use of one-element arrays One-element arrays are being deprecated[1]. Replace the one-element array with a simple object of type compat_caddr_t: 'compat_caddr_t unused'[2], once it seems this field is actually never used. Also, update struct cdrom_generic_command in UAPI by adding an anonimous union to avoid using the one-element array _reserved_. [1] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays [2] https://github.com/KSPP/linux/issues/86 Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/lkml/5f76f5d0.qJ4t%2FHWuRzSW7bTa%25lkp@intel.com/ Build-tested-by: kernel test robot Signed-off-by: Jens Axboe --- include/uapi/linux/cdrom.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 2817230148fd..6c34f6e2f1f7 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -289,7 +289,10 @@ struct cdrom_generic_command unsigned char data_direction; int quiet; int timeout; - void __user *reserved[1]; /* unused, actually */ + union { + void __user *reserved[1]; /* unused, actually */ + void __user *unused; + }; }; /* -- cgit v1.2.3 From e5086736969880478abb2ac85ef8757ac6ce45bf Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 2 Oct 2020 14:49:52 -0700 Subject: genetlink: reorg struct genl_family There are holes and oversized members in struct genl_family. Before: /* size: 104, cachelines: 2, members: 16 */ After: /* size: 88, cachelines: 2, members: 16 */ The command field in struct genlmsghdr is a u8, so no point in the operation count being 32 bit. Also operation 0 is usually undefined, so we only need 255 entries. netnsok and parallel_ops are only ever initialized to true. We can grow the fields as needed, compiler should warn us if someone tries to assign larger constants. Signed-off-by: Jakub Kicinski Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index b9eb92f3fe86..5cd9ab0c6bd9 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -48,8 +48,11 @@ struct genl_family { char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; - bool netnsok; - bool parallel_ops; + unsigned int mcgrp_offset; /* private */ + u8 netnsok:1; + u8 parallel_ops:1; + u8 n_ops; + u8 n_mcgrps; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, @@ -59,9 +62,6 @@ struct genl_family { struct genl_info *info); const struct genl_ops * ops; const struct genl_multicast_group *mcgrps; - unsigned int n_ops; - unsigned int n_mcgrps; - unsigned int mcgrp_offset; /* private */ struct module *module; }; -- cgit v1.2.3 From 0b588afdd16f9e0b63128dc4bcd002e7f2725fe0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 2 Oct 2020 14:49:53 -0700 Subject: genetlink: add small version of ops We want to add maxattr and policy back to genl_ops, to enable dumping per command policy to user space. This, however, would cause bloat for all the families with global policies. Introduce smaller version of ops (half the size of genl_ops). Translate these smaller ops into a full blown struct before use in the core. v1: - use struct assignment - put a full copy of the op in struct genl_dumpit_info - s/light/small/ Signed-off-by: Jakub Kicinski Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 53 ++++++++++++++++++++++++++++++++++++------------- 1 file changed, 39 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 5cd9ab0c6bd9..8ea1fc1ed1c7 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -41,6 +41,8 @@ struct genl_info; * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family + * @small_ops: the small-struct operations supported by this family + * @n_small_ops: number of small-struct operations supported by this family */ struct genl_family { int id; /* private */ @@ -52,6 +54,7 @@ struct genl_family { u8 netnsok:1; u8 parallel_ops:1; u8 n_ops; + u8 n_small_ops; u8 n_mcgrps; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, @@ -61,6 +64,7 @@ struct genl_family { struct sk_buff *skb, struct genl_info *info); const struct genl_ops * ops; + const struct genl_small_ops *small_ops; const struct genl_multicast_group *mcgrps; struct module *module; }; @@ -108,23 +112,26 @@ enum genl_validate_flags { }; /** - * struct genl_info - info that is available during dumpit op call - * @family: generic netlink family - for internal genl code usage - * @ops: generic netlink ops - for internal genl code usage - * @attrs: netlink attributes + * struct genl_small_ops - generic netlink operations (small version) + * @cmd: command identifier + * @internal_flags: flags used by the family + * @flags: flags + * @validate: validation flags from enum genl_validate_flags + * @doit: standard command callback + * @dumpit: callback for dumpers + * + * This is a cut-down version of struct genl_ops for users who don't need + * most of the ancillary infra and want to save space. */ -struct genl_dumpit_info { - const struct genl_family *family; - const struct genl_ops *ops; - struct nlattr **attrs; +struct genl_small_ops { + int (*doit)(struct sk_buff *skb, struct genl_info *info); + int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); + u8 cmd; + u8 internal_flags; + u8 flags; + u8 validate; }; -static inline const struct genl_dumpit_info * -genl_dumpit_info(struct netlink_callback *cb) -{ - return cb->data; -} - /** * struct genl_ops - generic netlink operations * @cmd: command identifier @@ -148,6 +155,24 @@ struct genl_ops { u8 validate; }; +/** + * struct genl_info - info that is available during dumpit op call + * @family: generic netlink family - for internal genl code usage + * @ops: generic netlink ops - for internal genl code usage + * @attrs: netlink attributes + */ +struct genl_dumpit_info { + const struct genl_family *family; + struct genl_ops op; + struct nlattr **attrs; +}; + +static inline const struct genl_dumpit_info * +genl_dumpit_info(struct netlink_callback *cb) +{ + return cb->data; +} + int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, -- cgit v1.2.3 From adc848450ff84e961cf7966b8a475889a92a9fd3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 2 Oct 2020 14:49:55 -0700 Subject: genetlink: add a structure for dump state Whenever netlink dump uses more than 2 cb->args[] entries code gets hard to read. We're about to add more state to ctrl_dumppolicy() so create a structure. Since the structure is typed and clearly named we can remove the local fam_id variable and use ctx->fam_id directly. v3: - rebase onto explicit free fix v1: - s/nl_policy_dump/netlink_policy_dump_state/ - forward declare struct netlink_policy_dump_state, and move from passing unsigned long to actual pointer type - add build bug on - u16 fam_id - s/args/ctx/ Signed-off-by: Jakub Kicinski Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/netlink.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 9e7eca961a98..00258590f2cb 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1935,11 +1935,14 @@ void nla_get_range_unsigned(const struct nla_policy *pt, void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range); +struct netlink_policy_dump_state; + int netlink_policy_dump_start(const struct nla_policy *policy, unsigned int maxtype, - unsigned long *state); -bool netlink_policy_dump_loop(unsigned long state); -int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); -void netlink_policy_dump_free(unsigned long state); + struct netlink_policy_dump_state **state); +bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state); +int netlink_policy_dump_write(struct sk_buff *skb, + struct netlink_policy_dump_state *state); +void netlink_policy_dump_free(struct netlink_policy_dump_state *state); #endif -- cgit v1.2.3 From 48526a0f4ca2b484cab4318dc0b2c2be1d8685b7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 2 Oct 2020 14:49:57 -0700 Subject: genetlink: bring back per op policy Add policy to the struct genl_ops structure, this time with maxattr, so it can be used properly. Propagate .policy and .maxattr from the family in genl_get_cmd() if needed, this way the rest of the code does not have to worry if the policy is per op or global. Signed-off-by: Jakub Kicinski Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8ea1fc1ed1c7..cb35625d001e 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -137,6 +137,8 @@ struct genl_small_ops { * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags + * @maxattr: maximum number of attributes supported + * @policy: netlink policy (takes precedence over family policy) * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers @@ -149,6 +151,8 @@ struct genl_ops { int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); + const struct nla_policy *policy; + unsigned int maxattr; u8 cmd; u8 internal_flags; u8 flags; -- cgit v1.2.3 From bfdc59701d6d100c99c3b987bcffd1c204e393c8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 06:51:40 +0200 Subject: iov_iter: refactor rw_copy_check_uvector and import_iovec Split rw_copy_check_uvector into two new helpers with more sensible calling conventions: - iovec_from_user copies a iovec from userspace either into the provided stack buffer if it fits, or allocates a new buffer for it. Returns the actually used iovec. It also verifies that iov_len does fit a signed type, and handles compat iovecs if the compat flag is set. - __import_iovec consolidates the native and compat versions of import_iovec. It calls iovec_from_user, then validates each iovec actually points to user addresses, and ensures the total length doesn't overflow. This has two major implications: - the access_process_vm case loses the total lenght checking, which wasn't required anyway, given that each call receives two iovecs for the local and remote side of the operation, and it verifies the total length on the local side already. - instead of a single loop there now are two loops over the iovecs. Given that the iovecs are cache hot this doesn't make a major difference Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 16 +++++----------- include/linux/fs.h | 13 ------------- include/linux/uio.h | 12 +++++++++--- 3 files changed, 14 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 790be5ffc12c..cebcaac68aec 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -91,6 +91,11 @@ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ +struct compat_iovec { + compat_uptr_t iov_base; + compat_size_t iov_len; +}; + #ifdef CONFIG_COMPAT #ifndef compat_user_stack_pointer @@ -248,11 +253,6 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; -struct compat_iovec { - compat_uptr_t iov_base; - compat_size_t iov_len; -}; - struct compat_rlimit { compat_ulong_t rlim_cur; compat_ulong_t rlim_max; @@ -451,12 +451,6 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, struct epoll_event; /* fortunately, this one is fixed-layout */ -extern ssize_t compat_rw_copy_check_uvector(int type, - const struct compat_iovec __user *uvector, - unsigned long nr_segs, - unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer); - extern void __user *compat_alloc_user_space(unsigned long len); int compat_restore_altstack(const compat_stack_t __user *uss); diff --git a/include/linux/fs.h b/include/linux/fs.h index e019ea2f1347..b9fdac75ba06 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -178,14 +178,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File supports async buffered reads */ #define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) -/* - * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector - * that indicates that they should check the contents of the iovec are - * valid, but not check the memory that the iovec elements - * points too. - */ -#define CHECK_IOVEC_ONLY -1 - /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -1887,11 +1879,6 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma) return file->f_op->mmap(file, vma); } -ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, - unsigned long nr_segs, unsigned long fast_segs, - struct iovec *fast_pointer, - struct iovec **ret_pointer); - extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, diff --git a/include/linux/uio.h b/include/linux/uio.h index 3835a8a8e9ea..92c11fe41c62 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -266,9 +266,15 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); -ssize_t import_iovec(int type, const struct iovec __user * uvector, - unsigned nr_segs, unsigned fast_segs, - struct iovec **iov, struct iov_iter *i); +struct iovec *iovec_from_user(const struct iovec __user *uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_iov, bool compat); +ssize_t import_iovec(int type, const struct iovec __user *uvec, + unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, + struct iov_iter *i); +ssize_t __import_iovec(int type, const struct iovec __user *uvec, + unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, + struct iov_iter *i, bool compat); #ifdef CONFIG_COMPAT struct compat_iovec; -- cgit v1.2.3 From 89cd35c58bc2e36bfdc23dde67a429b08cf4ae03 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 06:51:41 +0200 Subject: iov_iter: transparently handle compat iovecs in import_iovec Use in compat_syscall to import either native or the compat iovecs, and remove the now superflous compat_import_iovec. This removes the need for special compat logic in most callers, and the remaining ones can still be simplified by using __import_iovec with a bool compat parameter. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/uio.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/uio.h b/include/linux/uio.h index 92c11fe41c62..daedc61ad370 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -275,14 +275,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec, ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); - -#ifdef CONFIG_COMPAT -struct compat_iovec; -ssize_t compat_import_iovec(int type, const struct compat_iovec __user * uvector, - unsigned nr_segs, unsigned fast_segs, - struct iovec **iov, struct iov_iter *i); -#endif - int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); -- cgit v1.2.3 From 3523a9d45478984169d7f4416a00c83afc964e2a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 06:51:42 +0200 Subject: fs: remove various compat readv/writev helpers Now that import_iovec handles compat iovecs as well, all the duplicated code in the compat readv/writev helpers is not needed. Remove them and switch the compat syscall handlers to use the native helpers. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index cebcaac68aec..36b5842162c7 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -546,25 +546,25 @@ asmlinkage long compat_sys_getdents(unsigned int fd, /* fs/read_write.c */ asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd, - const struct compat_iovec __user *vec, compat_ulong_t vlen); + const struct iovec __user *vec, compat_ulong_t vlen); asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd, - const struct compat_iovec __user *vec, compat_ulong_t vlen); + const struct iovec __user *vec, compat_ulong_t vlen); /* No generic prototype for pread64 and pwrite64 */ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 asmlinkage long compat_sys_pwritev64(unsigned long fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif @@ -800,20 +800,20 @@ asmlinkage long compat_sys_execveat(int dfd, const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp, int flags); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 asmlinkage long compat_sys_preadv64v2(unsigned long fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 asmlinkage long compat_sys_pwritev64v2(unsigned long fd, - const struct compat_iovec __user *vec, + const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif -- cgit v1.2.3 From 5f764d624a89d4d00d282157077878d4e7c69869 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 06:51:43 +0200 Subject: fs: remove the compat readv/writev syscalls Now that import_iovec handles compat iovecs, the native readv and writev syscalls can be used for the compat case as well. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 4 ---- include/uapi/asm-generic/unistd.h | 4 ++-- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 36b5842162c7..07268fc8082b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -545,10 +545,6 @@ asmlinkage long compat_sys_getdents(unsigned int fd, /* fs/read_write.c */ asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); -asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd, - const struct iovec __user *vec, compat_ulong_t vlen); -asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd, - const struct iovec __user *vec, compat_ulong_t vlen); /* No generic prototype for pread64 and pwrite64 */ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, const struct iovec __user *vec, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 995b36c2ea7d..211c9eacbda6 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -207,9 +207,9 @@ __SYSCALL(__NR_read, sys_read) #define __NR_write 64 __SYSCALL(__NR_write, sys_write) #define __NR_readv 65 -__SC_COMP(__NR_readv, sys_readv, compat_sys_readv) +__SC_COMP(__NR_readv, sys_readv, sys_readv) #define __NR_writev 66 -__SC_COMP(__NR_writev, sys_writev, compat_sys_writev) +__SC_COMP(__NR_writev, sys_writev, sys_writev) #define __NR_pread64 67 __SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64) #define __NR_pwrite64 68 -- cgit v1.2.3 From 598b3cec831fd6ccb3cbe4919a722e868c6364a8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 06:51:44 +0200 Subject: fs: remove compat_sys_vmsplice Now that import_iovec handles compat iovecs, the native vmsplice syscall can be used for the compat case as well. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 4 ---- include/uapi/asm-generic/unistd.h | 2 +- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 07268fc8082b..7c3e876703cf 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -597,10 +597,6 @@ asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); -/* fs/splice.c */ -asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *, - unsigned int nr_segs, unsigned int flags); - /* fs/stat.c */ asmlinkage long compat_sys_newfstatat(unsigned int dfd, const char __user *filename, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 211c9eacbda6..f2dcb0d57030 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -237,7 +237,7 @@ __SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4) /* fs/splice.c */ #define __NR_vmsplice 75 -__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice) +__SYSCALL(__NR_vmsplice, sys_vmsplice) #define __NR_splice 76 __SYSCALL(__NR_splice, sys_splice) #define __NR_tee 77 -- cgit v1.2.3 From c3973b401ef2b0b8005f8074a10e96e3ea093823 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 06:51:45 +0200 Subject: mm: remove compat_process_vm_{readv,writev} Now that import_iovec handles compat iovecs, the native syscalls can be used for the compat case as well. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 8 -------- include/uapi/asm-generic/unistd.h | 6 ++---- 2 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 7c3e876703cf..3e3d2beafed3 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -780,14 +780,6 @@ asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, int flags); asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags); -asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid, - const struct compat_iovec __user *lvec, - compat_ulong_t liovcnt, const struct compat_iovec __user *rvec, - compat_ulong_t riovcnt, compat_ulong_t flags); -asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, - const struct compat_iovec __user *lvec, - compat_ulong_t liovcnt, const struct compat_iovec __user *rvec, - compat_ulong_t riovcnt, compat_ulong_t flags); asmlinkage long compat_sys_execveat(int dfd, const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp, int flags); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index f2dcb0d57030..c1dfe99c9c3f 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -727,11 +727,9 @@ __SYSCALL(__NR_setns, sys_setns) #define __NR_sendmmsg 269 __SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg) #define __NR_process_vm_readv 270 -__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \ - compat_sys_process_vm_readv) +__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv) #define __NR_process_vm_writev 271 -__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \ - compat_sys_process_vm_writev) +__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev) #define __NR_kcmp 272 __SYSCALL(__NR_kcmp, sys_kcmp) #define __NR_finit_module 273 -- cgit v1.2.3 From 51cf18c90ca1b51d1cb4af3064e85fcf8610b5d2 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 28 Aug 2020 10:00:49 +0100 Subject: sched/debug: Add new tracepoint to track cpu_capacity rq->cpu_capacity is a key element in several scheduler parts, such as EAS task placement and load balancing. Tracking this value enables testing and/or debugging by a toolkit. Signed-off-by: Vincent Donnefort Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1598605249-72651-1-git-send-email-vincent.donnefort@arm.com --- include/linux/sched.h | 1 + include/trace/events/sched.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2bf0af19a62a..f516c18eeb20 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2044,6 +2044,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); int sched_trace_rq_cpu(struct rq *rq); +int sched_trace_rq_cpu_capacity(struct rq *rq); int sched_trace_rq_nr_running(struct rq *rq); const struct cpumask *sched_trace_rd_span(struct root_domain *rd); diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index fec25b9cfbaf..c96a4337afe6 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -630,6 +630,10 @@ DECLARE_TRACE(pelt_se_tp, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); +DECLARE_TRACE(sched_cpu_capacity_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + DECLARE_TRACE(sched_overutilized_tp, TP_PROTO(struct root_domain *rd, bool overutilized), TP_ARGS(rd, overutilized)); -- cgit v1.2.3 From 04a351a62bd4be1dbcc88fae69b990362d88ffe5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 3 Oct 2020 10:44:43 +0200 Subject: netlink: rework policy dump to support multiple policies Rework the policy dump code a bit to support adding multiple policies to a single dump, in order to e.g. support per-op policies in generic netlink. v2: - move kernel-doc to implementation [Jakub] - squash the first patch to not flip-flop on the prototype [Jakub] - merge netlink_policy_dump_get_policy_idx() with the old get_policy_idx() we already had - rebase without Jakub's patch to have per-op dump Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/netlink.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 00258590f2cb..5a5ff97cc596 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1937,9 +1937,12 @@ void nla_get_range_signed(const struct nla_policy *pt, struct netlink_policy_dump_state; -int netlink_policy_dump_start(const struct nla_policy *policy, - unsigned int maxtype, - struct netlink_policy_dump_state **state); +int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, + const struct nla_policy *policy, + unsigned int maxtype); +int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state, + const struct nla_policy *policy, + unsigned int maxtype); bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state); int netlink_policy_dump_write(struct sk_buff *skb, struct netlink_policy_dump_state *state); -- cgit v1.2.3 From 50a896cf2d6f34e884a00139d6e6012c9833ace3 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 3 Oct 2020 10:44:45 +0200 Subject: genetlink: properly support per-op policy dumping Add support for per-op policy dumping. The data is pretty much as before, except that now the assumption that the policy with index 0 is "the" policy no longer holds - you now need to look at the new CTRL_ATTR_OP_POLICY attribute which is a nested attr (indexed by op) containing attributes for do and dump policies. When a single op is requested, the CTRL_ATTR_OP_POLICY will be added in the same way, since do and dump policies may differ. v2: - conditionally advertise per-command policies only if there actually is a policy being used for the do/dump and it's present at all Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/uapi/linux/genetlink.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index 9c0636ec2286..bc9c98e84828 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -64,6 +64,7 @@ enum { CTRL_ATTR_OPS, CTRL_ATTR_MCAST_GROUPS, CTRL_ATTR_POLICY, + CTRL_ATTR_OP_POLICY, __CTRL_ATTR_MAX, }; @@ -85,6 +86,15 @@ enum { __CTRL_ATTR_MCAST_GRP_MAX, }; +enum { + CTRL_ATTR_POLICY_UNSPEC, + CTRL_ATTR_POLICY_DO, + CTRL_ATTR_POLICY_DUMP, + + __CTRL_ATTR_POLICY_DUMP_MAX, + CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1 +}; + #define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1) -- cgit v1.2.3 From e992a6eda9a1eeeab73a8d2792464e4a2b1ebc3b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 3 Oct 2020 10:44:46 +0200 Subject: genetlink: allow dumping command-specific policy Right now CTRL_CMD_GETPOLICY can only dump the family-wide policy. Support dumping policy of a specific op. v3: - rebase after per-op policy export and handle that v2: - make cmd U32, just in case. v1: - don't echo op in the output in a naive way, this should make it cleaner to extend the output format for dumping policies for all the commands at once in the future. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20201001225933.1373426-11-kuba@kernel.org Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/uapi/linux/genetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index bc9c98e84828..d83f214b4134 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -65,6 +65,7 @@ enum { CTRL_ATTR_MCAST_GROUPS, CTRL_ATTR_POLICY, CTRL_ATTR_OP_POLICY, + CTRL_ATTR_OP, __CTRL_ATTR_MAX, }; -- cgit v1.2.3 From 8e1b3884eed7d96d4f1210b668611ee6a1803ea5 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Thu, 1 Oct 2020 17:12:50 +0000 Subject: net: remove NETDEV_HW_ADDR_T_SLAVE NETDEV_HW_ADDR_T_SLAVE is not used anymore, remove it. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 28cfa53daf72..0c79d9e56a5e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -212,9 +212,8 @@ struct netdev_hw_addr { unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 #define NETDEV_HW_ADDR_T_SAN 2 -#define NETDEV_HW_ADDR_T_SLAVE 3 -#define NETDEV_HW_ADDR_T_UNICAST 4 -#define NETDEV_HW_ADDR_T_MULTICAST 5 +#define NETDEV_HW_ADDR_T_UNICAST 3 +#define NETDEV_HW_ADDR_T_MULTICAST 4 bool global_use; int sync_cnt; int refcount; -- cgit v1.2.3 From 19fbcb36a39eefbe8912a13ccc02e937b1c418d6 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sat, 3 Oct 2020 00:44:28 +0200 Subject: net/sched: act_vlan: Add {POP,PUSH}_ETH actions Implement TCA_VLAN_ACT_POP_ETH and TCA_VLAN_ACT_PUSH_ETH, to respectively pop and push a base Ethernet header at the beginning of a frame. POP_ETH is just a matter of pulling ETH_HLEN bytes. VLAN tags, if any, must be stripped before calling POP_ETH. PUSH_ETH is restricted to skbs with no mac_header, and only the MAC addresses can be configured. The Ethertype is automatically set from skb->protocol. These restrictions ensure that all skb's fields remain consistent, so that this action can't confuse other part of the networking stack (like GSO). Since openvswitch already had these actions, consolidate the code in skbuff.c (like for vlan and mpls push/pop). Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/net/tc_act/tc_vlan.h | 2 ++ include/uapi/linux/tc_act/tc_vlan.h | 4 ++++ 3 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3d0cf3722bb4..42131e325e27 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3573,6 +3573,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); +int skb_eth_pop(struct sk_buff *skb); +int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, + const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index 4e2502408c31..f051046ba034 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -11,6 +11,8 @@ struct tcf_vlan_params { int tcfv_action; + unsigned char tcfv_push_dst[ETH_ALEN]; + unsigned char tcfv_push_src[ETH_ALEN]; u16 tcfv_push_vid; __be16 tcfv_push_proto; u8 tcfv_push_prio; diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h index 168995b54a70..5b306fe815cc 100644 --- a/include/uapi/linux/tc_act/tc_vlan.h +++ b/include/uapi/linux/tc_act/tc_vlan.h @@ -16,6 +16,8 @@ #define TCA_VLAN_ACT_POP 1 #define TCA_VLAN_ACT_PUSH 2 #define TCA_VLAN_ACT_MODIFY 3 +#define TCA_VLAN_ACT_POP_ETH 4 +#define TCA_VLAN_ACT_PUSH_ETH 5 struct tc_vlan { tc_gen; @@ -30,6 +32,8 @@ enum { TCA_VLAN_PUSH_VLAN_PROTOCOL, TCA_VLAN_PAD, TCA_VLAN_PUSH_VLAN_PRIORITY, + TCA_VLAN_PUSH_ETH_DST, + TCA_VLAN_PUSH_ETH_SRC, __TCA_VLAN_MAX, }; #define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1) -- cgit v1.2.3 From a45294af9e96a3e060b6272fa7cd2c4b196de335 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sat, 3 Oct 2020 00:44:31 +0200 Subject: net/sched: act_mpls: Add action to push MPLS LSE before Ethernet header Define the MAC_PUSH action which pushes an MPLS LSE before the mac header (instead of between the mac and the network headers as the plain PUSH action does). The only special case is when the skb has an offloaded VLAN. In that case, it has to be inlined before pushing the MPLS header. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_mpls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/tc_act/tc_mpls.h b/include/uapi/linux/tc_act/tc_mpls.h index 9360e95273c7..9e4e8f52a779 100644 --- a/include/uapi/linux/tc_act/tc_mpls.h +++ b/include/uapi/linux/tc_act/tc_mpls.h @@ -10,6 +10,7 @@ #define TCA_MPLS_ACT_PUSH 2 #define TCA_MPLS_ACT_MODIFY 3 #define TCA_MPLS_ACT_DEC_TTL 4 +#define TCA_MPLS_ACT_MAC_PUSH 5 struct tc_mpls { tc_gen; /* generic TC action fields. */ -- cgit v1.2.3 From 24ce66c04a06a678f156cf575128246f3d214b4a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Sep 2020 07:58:18 +0200 Subject: uaccess: provide a generic TASK_SIZE_MAX definition Define TASK_SIZE_MAX as TASK_SIZE if not otherwise defined. Signed-off-by: Christoph Hellwig Signed-off-by: Palmer Dabbelt --- include/linux/uaccess.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 70073c802b48..d0e43761c708 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -31,6 +31,10 @@ typedef struct { /* empty dummy */ } mm_segment_t; +#ifndef TASK_SIZE_MAX +#define TASK_SIZE_MAX TASK_SIZE +#endif + #define uaccess_kernel() (false) #define user_addr_max() (TASK_SIZE_MAX) -- cgit v1.2.3 From 931de11f5a374748f1d620ee17810dedf13c9f69 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Sep 2020 07:58:19 +0200 Subject: asm-generic: improve the nommu {get,put}_user handling Instead of reusing raw_{copy,to}_from_user implement separate handlers using {get,put}_unaligned. This ensures unaligned access is handled correctly, and avoid the need for the small constant size optimization in raw_{copy,to}_from_user. Signed-off-by: Christoph Hellwig Acked-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/uaccess.h | 91 ++++++++++++++++++++++++------------------- 1 file changed, 51 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index ba68ee4dabfa..6de5f524e9e6 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -10,28 +10,60 @@ #include #ifdef CONFIG_UACCESS_MEMCPY -static inline __must_check unsigned long -raw_copy_from_user(void *to, const void __user * from, unsigned long n) +#include + +static inline int __get_user_fn(size_t size, const void __user *from, void *to) { - if (__builtin_constant_p(n)) { - switch(n) { - case 1: - *(u8 *)to = *(u8 __force *)from; - return 0; - case 2: - *(u16 *)to = *(u16 __force *)from; - return 0; - case 4: - *(u32 *)to = *(u32 __force *)from; - return 0; -#ifdef CONFIG_64BIT - case 8: - *(u64 *)to = *(u64 __force *)from; - return 0; -#endif - } + BUILD_BUG_ON(!__builtin_constant_p(size)); + + switch (size) { + case 1: + *(u8 *)to = get_unaligned((u8 __force *)from); + return 0; + case 2: + *(u16 *)to = get_unaligned((u16 __force *)from); + return 0; + case 4: + *(u32 *)to = get_unaligned((u32 __force *)from); + return 0; + case 8: + *(u64 *)to = get_unaligned((u64 __force *)from); + return 0; + default: + BUILD_BUG(); + return 0; + } + +} +#define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k) + +static inline int __put_user_fn(size_t size, void __user *to, void *from) +{ + BUILD_BUG_ON(!__builtin_constant_p(size)); + + switch (size) { + case 1: + put_unaligned(*(u8 *)from, (u8 __force *)to); + return 0; + case 2: + put_unaligned(*(u16 *)from, (u16 __force *)to); + return 0; + case 4: + put_unaligned(*(u32 *)from, (u32 __force *)to); + return 0; + case 8: + put_unaligned(*(u64 *)from, (u64 __force *)to); + return 0; + default: + BUILD_BUG(); + return 0; } +} +#define __put_user_fn(sz, u, k) __put_user_fn(sz, u, k) +static inline __must_check unsigned long +raw_copy_from_user(void *to, const void __user * from, unsigned long n) +{ memcpy(to, (const void __force *)from, n); return 0; } @@ -39,27 +71,6 @@ raw_copy_from_user(void *to, const void __user * from, unsigned long n) static inline __must_check unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - if (__builtin_constant_p(n)) { - switch(n) { - case 1: - *(u8 __force *)to = *(u8 *)from; - return 0; - case 2: - *(u16 __force *)to = *(u16 *)from; - return 0; - case 4: - *(u32 __force *)to = *(u32 *)from; - return 0; -#ifdef CONFIG_64BIT - case 8: - *(u64 __force *)to = *(u64 *)from; - return 0; -#endif - default: - break; - } - } - memcpy((void __force *)to, from, n); return 0; } -- cgit v1.2.3 From 2d2d255467d4ea927fbf606c8b584512edee0f7b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Sep 2020 07:58:20 +0200 Subject: asm-generic: add nommu implementations of __{get,put}_kernel_nofault Add native implementations of __{get,put}_kernel_nofault using {get,put}_unaligned, just like the {get,put}_user implementations. Signed-off-by: Christoph Hellwig Acked-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/uaccess.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 6de5f524e9e6..b367f339be1a 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -61,6 +61,22 @@ static inline int __put_user_fn(size_t size, void __user *to, void *from) } #define __put_user_fn(sz, u, k) __put_user_fn(sz, u, k) +#define __get_kernel_nofault(dst, src, type, err_label) \ +do { \ + *((type *)dst) = get_unaligned((type *)(src)); \ + if (0) /* make sure the label looks used to the compiler */ \ + goto err_label; \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, err_label) \ +do { \ + put_unaligned(*((type *)src), (type *)(dst)); \ + if (0) /* make sure the label looks used to the compiler */ \ + goto err_label; \ +} while (0) + +#define HAVE_GET_KERNEL_NOFAULT 1 + static inline __must_check unsigned long raw_copy_from_user(void *to, const void __user * from, unsigned long n) { -- cgit v1.2.3 From 3c57fa13f6bf3906643034c57736c778ce63fa55 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Sep 2020 07:58:21 +0200 Subject: asm-generic: make the set_fs implementation optional Put all the set_fs related code under CONFIG_SET_FS so that asm-generic/uaccess.h can be used for set_fs-less builds. Signed-off-by: Christoph Hellwig Acked-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/uaccess.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index b367f339be1a..45f9872fd747 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -94,6 +94,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) #define INLINE_COPY_TO_USER #endif /* CONFIG_UACCESS_MEMCPY */ +#ifdef CONFIG_SET_FS #define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) #ifndef KERNEL_DS @@ -116,6 +117,7 @@ static inline void set_fs(mm_segment_t fs) #ifndef uaccess_kernel #define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #endif +#endif /* CONFIG_SET_FS */ #define access_ok(addr, size) __access_ok((unsigned long)(addr),(size)) -- cgit v1.2.3 From 5f48846daf3321f8a1f8aa99cd6173e3980b7a29 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 2 Oct 2020 15:50:56 +0200 Subject: netfilter: nf_tables: Enable fast nft_cmp for inverted matches Add a boolean indicating NFT_CMP_NEQ. To include it into the match decision, it is sufficient to XOR it with the data comparison's result. While being at it, store the mask that is calculated during expression init and free the eval routine from having to recalculate it each time. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 78516de14d31..df2d91c814cb 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -25,8 +25,10 @@ void nf_tables_core_module_exit(void); struct nft_cmp_fast_expr { u32 data; + u32 mask; enum nft_registers sreg:8; u8 len; + bool inv; }; struct nft_immediate_expr { -- cgit v1.2.3 From 10fdd6d80e4c21ad48f3860d723f5b3b5965477b Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 1 Oct 2020 18:57:44 +0200 Subject: netfilter: nf_tables: Implement fast bitwise expression A typical use of bitwise expression is to mask out parts of an IP address when matching on the network part only. Optimize for this common use with a fast variant for NFT_BITWISE_BOOL-type expressions operating on 32bit-sized values. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index df2d91c814cb..8657e6815b07 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -23,6 +23,13 @@ extern struct nft_object_type nft_secmark_obj_type; int nf_tables_core_module_init(void); void nf_tables_core_module_exit(void); +struct nft_bitwise_fast_expr { + u32 mask; + u32 xor; + enum nft_registers sreg:8; + enum nft_registers dreg:8; +}; + struct nft_cmp_fast_expr { u32 data; u32 mask; @@ -68,6 +75,8 @@ struct nft_payload_set { extern const struct nft_expr_ops nft_payload_fast_ops; +extern const struct nft_expr_ops nft_bitwise_fast_ops; + extern struct static_key_false nft_counters_enabled; extern struct static_key_false nft_trace_enabled; -- cgit v1.2.3 From cf1166349c68816f4259d32559f54972b0d5c1a4 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 4 Oct 2020 18:12:51 +0200 Subject: net: devlink: Add unused port flavour Not all ports of a switch need to be used, particularly in embedded systems. Add a port flavour for ports which physically exist in the switch, but are not connected to the front panel etc, and so are unused. By having unused ports present in devlink, it gives a more accurate representation of the hardware. It also allows regions to be associated to such ports, so allowing, for example, to determine unused ports are correctly powered off, or to compare probable reset defaults of unused ports to used ports experiences issues. Actually registering unused ports and setting the flavour to unused is optional. The DSA core will register all such switch ports, but such ports are expected to be limited in number. Bigger ASICs may decide not to list unused ports. v2: Expand the description about why it is useful Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ba467dc07852..5f1d6c327670 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -197,6 +197,9 @@ enum devlink_port_flavour { * port that faces the PCI VF. */ DEVLINK_PORT_FLAVOUR_VIRTUAL, /* Any virtual port facing the user. */ + DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but + * is not used in any way. + */ }; enum devlink_param_cmode { -- cgit v1.2.3 From 3122433eb533aac7d08302ee4b3bd3adfcd280d3 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 4 Oct 2020 18:12:53 +0200 Subject: net: dsa: Register devlink ports before calling DSA driver setup() DSA drivers want to create regions on devlink ports as well as the devlink device instance, in order to export registers and other tables per port. To keep all this code together in the drivers, have the devlink ports registered early, so the setup() method can setup both device and port devlink regions. v3: Remove dp->setup Move common code out of switch statement. Fix wrong goto Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 8b0696e08cac..049140b2f593 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -215,6 +215,7 @@ struct dsa_port { u8 stp_state; struct net_device *bridge_dev; struct devlink_port devlink_port; + bool devlink_port_setup; struct phylink *pl; struct phylink_config pl_config; -- cgit v1.2.3 From 544e7c33ec2f8077685c254f5e3b03a85c0e62eb Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 4 Oct 2020 18:12:54 +0200 Subject: net: devlink: Add support for port regions Allow regions to be registered to a devlink port. The same netlink API is used, but the port index is provided to indicate when a region is a port region as opposed to a device region. Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/devlink.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 89ede1ce3a3a..237ba5e29a3b 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -110,6 +110,7 @@ struct devlink_port_attrs { struct devlink_port { struct list_head list; struct list_head param_list; + struct list_head region_list; struct devlink *devlink; unsigned int index; bool registered; @@ -591,6 +592,26 @@ struct devlink_region_ops { void *priv; }; +/** + * struct devlink_port_region_ops - Region operations for a port + * @name: region name + * @destructor: callback used to free snapshot memory when deleting + * @snapshot: callback to request an immediate snapshot. On success, + * the data variable must be updated to point to the snapshot data. + * The function will be called while the devlink instance lock is + * held. + * @priv: Pointer to driver private data for the region operation + */ +struct devlink_port_region_ops { + const char *name; + void (*destructor)(const void *data); + int (*snapshot)(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + struct netlink_ext_ack *extack, + u8 **data); + void *priv; +}; + struct devlink_fmsg; struct devlink_health_reporter; @@ -1445,7 +1466,13 @@ struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); +struct devlink_region * +devlink_port_region_create(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size); void devlink_region_destroy(struct devlink_region *region); +void devlink_port_region_destroy(struct devlink_region *region); + int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id); void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id); int devlink_region_snapshot_create(struct devlink_region *region, -- cgit v1.2.3 From 08156ba430b412bd9c23fe6155a58c7cb166045c Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 4 Oct 2020 18:12:55 +0200 Subject: net: dsa: Add devlink port regions support to DSA Allow DSA drivers to make use of devlink port regions, via simple wrappers. Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 049140b2f593..ca426cf9927b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -681,6 +681,11 @@ struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); +struct devlink_region * +dsa_devlink_port_region_create(struct dsa_switch *ds, + int port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); -- cgit v1.2.3 From 7d1e2a10681d3b6eeaace68885ef5de88ce03efe Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 4 Oct 2020 18:12:56 +0200 Subject: net: dsa: Add helper for converting devlink port to ds and port Hide away from DSA drivers how devlink works. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index ca426cf9927b..c0185660881c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -701,6 +701,20 @@ static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) return dl_priv->ds; } +static inline +struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) +{ + struct devlink *dl = port->devlink; + struct dsa_devlink_priv *dl_priv = devlink_priv(dl); + + return dl_priv->ds; +} + +static inline int dsa_devlink_port_to_port(struct devlink_port *port) +{ + return port->index; +} + struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; -- cgit v1.2.3 From 261bfb3328b89c63ca410ae30a0c87cd3955344c Mon Sep 17 00:00:00 2001 From: Vincent Huang Date: Sun, 4 Oct 2020 19:42:47 -0700 Subject: Input: synaptics-rmi4 - rename f30_data to gpio_data f30_data in rmi_device_platform_data could be also referenced by RMI function 3A, so rename it and the structure name to avoid confusion. Signed-off-by: Vincent Huang Reviewed-by: Hans de Goede Tested-by: Hans de Goede Reviewed-by: Andrew Duggan Link: https://lore.kernel.org/r/20200930094147.635556-2-vincent.huang@tw.synaptics.com Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 8ed37f93f3c8..ab7eea01ab42 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -102,15 +102,16 @@ struct rmi_2d_sensor_platform_data { }; /** - * struct rmi_f30_data - overrides defaults for a single F30 GPIOs/LED chip. + * struct rmi_gpio_data - overrides defaults for a single F30/F3A GPIOs/LED + * chip. * @buttonpad - the touchpad is a buttonpad, so enable only the first actual * button that is found. - * @trackstick_buttons - Set when the function 30 is handling the physical + * @trackstick_buttons - Set when the function 30 or 3a is handling the physical * buttons of the trackstick (as a PS/2 passthrough device). - * @disable - the touchpad incorrectly reports F30 and it should be ignored. + * @disable - the touchpad incorrectly reports F30/F3A and it should be ignored. * This is a special case which is due to misconfigured firmware. */ -struct rmi_f30_data { +struct rmi_gpio_data { bool buttonpad; bool trackstick_buttons; bool disable; @@ -218,7 +219,7 @@ struct rmi_device_platform_data { /* function handler pdata */ struct rmi_2d_sensor_platform_data sensor_pdata; struct rmi_f01_power_management power_management; - struct rmi_f30_data f30_data; + struct rmi_gpio_data gpio_data; }; /** -- cgit v1.2.3 From f5810e5c329238b8553ebd98b914bdbefd8e6737 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Wed, 16 Sep 2020 12:06:58 +0100 Subject: asm-generic/io.h: Fix !CONFIG_GENERIC_IOMAP pci_iounmap() implementation For arches that do not select CONFIG_GENERIC_IOMAP, the current pci_iounmap() function does nothing causing obvious memory leaks for mapped regions that are backed by MMIO physical space. In order to detect if a mapped pointer is IO vs MMIO, a check must made available to the pci_iounmap() function so that it can actually detect whether the pointer has to be unmapped. In configurations where CONFIG_HAS_IOPORT_MAP && !CONFIG_GENERIC_IOMAP, a mapped port is detected using an ioport_map() stub defined in asm-generic/io.h. Use the same logic to implement a stub (ie __pci_ioport_unmap()) that detects if the passed in pointer in pci_iounmap() is IO vs MMIO to iounmap conditionally and call it in pci_iounmap() fixing the issue. Leave __pci_ioport_unmap() as a NOP for all other config options. Tested-by: George Cherian Link: https://lore.kernel.org/lkml/20200905024811.74701-1-yangyingliang@huawei.com Link: https://lore.kernel.org/lkml/20200824132046.3114383-1-george.cherian@marvell.com Link: https://lore.kernel.org/r/a9daf8d8444d0ebd00bc6d64e336ec49dbb50784.1600254147.git.lorenzo.pieralisi@arm.com Reported-by: George Cherian Signed-off-by: Lorenzo Pieralisi Signed-off-by: Lorenzo Pieralisi Reviewed-by: Catalin Marinas Cc: Arnd Bergmann Cc: George Cherian Cc: Will Deacon Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: Yang Yingliang --- include/asm-generic/io.h | 39 +++++++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index dabf8cb7203b..9ea83d80eb6f 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -911,18 +911,6 @@ static inline void iowrite64_rep(volatile void __iomem *addr, #include #define __io_virt(x) ((void __force *)(x)) -#ifndef CONFIG_GENERIC_IOMAP -struct pci_dev; -extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); - -#ifndef pci_iounmap -#define pci_iounmap pci_iounmap -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) -{ -} -#endif -#endif /* CONFIG_GENERIC_IOMAP */ - /* * Change virtual addresses to physical addresses and vv. * These are pretty trivial @@ -1016,6 +1004,16 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) port &= IO_SPACE_LIMIT; return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } +#define __pci_ioport_unmap __pci_ioport_unmap +static inline void __pci_ioport_unmap(void __iomem *p) +{ + uintptr_t start = (uintptr_t) PCI_IOBASE; + uintptr_t addr = (uintptr_t) p; + + if (addr >= start && addr < start + IO_SPACE_LIMIT) + return; + iounmap(p); +} #endif #ifndef ioport_unmap @@ -1030,6 +1028,23 @@ extern void ioport_unmap(void __iomem *p); #endif /* CONFIG_GENERIC_IOMAP */ #endif /* CONFIG_HAS_IOPORT_MAP */ +#ifndef CONFIG_GENERIC_IOMAP +struct pci_dev; +extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); + +#ifndef __pci_ioport_unmap +static inline void __pci_ioport_unmap(void __iomem *p) {} +#endif + +#ifndef pci_iounmap +#define pci_iounmap pci_iounmap +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) +{ + __pci_ioport_unmap(p); +} +#endif +#endif /* CONFIG_GENERIC_IOMAP */ + /* * Convert a virtual cached pointer to an uncached pointer */ -- cgit v1.2.3 From 8438f5211479e4b8433f641634362264bc3bbd9e Mon Sep 17 00:00:00 2001 From: Tingwei Zhang Date: Mon, 5 Oct 2020 10:13:13 +0300 Subject: tracing: Add flag to control different traces More traces like event trace or trace marker will be supported. Add flag for difference traces, so that they can be controlled separately. Move current function trace to it's own flag instead of global ftrace enable flag. Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Alexander Shishkin Signed-off-by: Tingwei Zhang Signed-off-by: Alexander Shishkin Link: https://lore.kernel.org/r/20201005071319.78508-3-alexander.shishkin@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/trace.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/trace.h b/include/linux/trace.h index 36d255d66f88..c115a5d2269f 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -3,6 +3,9 @@ #define _LINUX_TRACE_H #ifdef CONFIG_TRACING + +#define TRACE_EXPORT_FUNCTION BIT(0) + /* * The trace export - an export of Ftrace output. The trace_export * can process traces and export them to a registered destination as @@ -15,10 +18,12 @@ * next - pointer to the next trace_export * write - copy traces which have been delt with ->commit() to * the destination + * flags - which ftrace to be exported */ struct trace_export { struct trace_export __rcu *next; void (*write)(struct trace_export *, const void *, unsigned int); + int flags; }; int register_ftrace_export(struct trace_export *export); -- cgit v1.2.3 From 8ab7a2b7055c88c3da5e4684dfa015c6a8987c28 Mon Sep 17 00:00:00 2001 From: Tingwei Zhang Date: Mon, 5 Oct 2020 10:13:14 +0300 Subject: tracing: Add trace_export support for event trace Only function traces can be exported to other destinations currently. This patch exports event trace as well. Move trace export related function to the beginning of file so other trace can call trace_process_export() to export. Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Alexander Shishkin Signed-off-by: Tingwei Zhang Signed-off-by: Alexander Shishkin Link: https://lore.kernel.org/r/20201005071319.78508-4-alexander.shishkin@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/trace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/trace.h b/include/linux/trace.h index c115a5d2269f..86033d214972 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -5,6 +5,7 @@ #ifdef CONFIG_TRACING #define TRACE_EXPORT_FUNCTION BIT(0) +#define TRACE_EXPORT_EVENT BIT(1) /* * The trace export - an export of Ftrace output. The trace_export -- cgit v1.2.3 From 458999c6f67b0ffcc704a4892041dd700adf7d83 Mon Sep 17 00:00:00 2001 From: Tingwei Zhang Date: Mon, 5 Oct 2020 10:13:15 +0300 Subject: tracing: Add trace_export support for trace_marker Add the support to route trace_marker buffer to other destination via trace_export. Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Alexander Shishkin Signed-off-by: Tingwei Zhang Signed-off-by: Alexander Shishkin Link: https://lore.kernel.org/r/20201005071319.78508-5-alexander.shishkin@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/trace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/trace.h b/include/linux/trace.h index 86033d214972..886a4ffd9d45 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -6,6 +6,7 @@ #define TRACE_EXPORT_FUNCTION BIT(0) #define TRACE_EXPORT_EVENT BIT(1) +#define TRACE_EXPORT_MARKER BIT(2) /* * The trace export - an export of Ftrace output. The trace_export -- cgit v1.2.3 From 07f8569fbe44f35e53c7a5946fbb348432c68377 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Sun, 4 Oct 2020 21:32:00 +0200 Subject: w1: Constify struct w1_family_ops The fops field in the w1_family struct is never modified. Make it const to indicate that. Constifying the pointer makes it possible for drivers to declare static w1_family_ops structs const, which in turn will allow the compiler to put it in read-only memory. Reviewed-by: Sebastian Reichel Signed-off-by: Rikard Falkeborn Link: https://lore.kernel.org/r/20201004193202.4044-2-rikard.falkeborn@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/w1.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/w1.h b/include/linux/w1.h index cebf3464bc03..949d3b10e531 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -269,7 +269,7 @@ struct w1_family { struct list_head family_entry; u8 fid; - struct w1_family_ops *fops; + const struct w1_family_ops *fops; const struct of_device_id *of_match_table; -- cgit v1.2.3 From c307459b9d1fcb8bbf3ea5a4162979532322ef77 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:13 -0700 Subject: fs/kernel_read_file: Remove FIRMWARE_PREALLOC_BUFFER enum FIRMWARE_PREALLOC_BUFFER is a "how", not a "what", and confuses the LSMs that are interested in filtering between types of things. The "how" should be an internal detail made uninteresting to the LSMs. Fixes: a098ecd2fa7d ("firmware: support loading into a pre-allocated buffer") Fixes: fd90bc559bfb ("ima: based on policy verify firmware signatures (pre-allocated buffer)") Fixes: 4f0496d8ffa3 ("ima: based on policy warn about loading firmware (pre-allocated buffer)") Signed-off-by: Kees Cook Reviewed-by: Mimi Zohar Reviewed-by: Luis Chamberlain Acked-by: Scott Branden Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201002173828.2099543-2-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a08..7336e22d0c5d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2858,10 +2858,10 @@ static inline void i_readcount_inc(struct inode *inode) #endif extern int do_pipe_flags(int *, int); +/* This is a list of *what* is being read, not *how*. */ #define __kernel_read_file_id(id) \ id(UNKNOWN, unknown) \ id(FIRMWARE, firmware) \ - id(FIRMWARE_PREALLOC_BUFFER, firmware) \ id(FIRMWARE_EFI_EMBEDDED, firmware) \ id(MODULE, kernel-module) \ id(KEXEC_IMAGE, kexec-image) \ -- cgit v1.2.3 From 06e67b849ab910a49a629445f43edb074153d0eb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:14 -0700 Subject: fs/kernel_read_file: Remove FIRMWARE_EFI_EMBEDDED enum The "FIRMWARE_EFI_EMBEDDED" enum is a "where", not a "what". It should not be distinguished separately from just "FIRMWARE", as this confuses the LSMs about what is being loaded. Additionally, there was no actual validation of the firmware contents happening. Fixes: e4c2c0ff00ec ("firmware: Add new platform fallback mechanism and firmware_request_platform()") Signed-off-by: Kees Cook Reviewed-by: Luis Chamberlain Acked-by: Scott Branden Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201002173828.2099543-3-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7336e22d0c5d..3fb7af12d033 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2858,11 +2858,10 @@ static inline void i_readcount_inc(struct inode *inode) #endif extern int do_pipe_flags(int *, int); -/* This is a list of *what* is being read, not *how*. */ +/* This is a list of *what* is being read, not *how* nor *where*. */ #define __kernel_read_file_id(id) \ id(UNKNOWN, unknown) \ id(FIRMWARE, firmware) \ - id(FIRMWARE_EFI_EMBEDDED, firmware) \ id(MODULE, kernel-module) \ id(KEXEC_IMAGE, kexec-image) \ id(KEXEC_INITRAMFS, kexec-initramfs) \ -- cgit v1.2.3 From b89999d004931ab2e5123611ace7dab77328f8d6 Mon Sep 17 00:00:00 2001 From: Scott Branden Date: Fri, 2 Oct 2020 10:38:15 -0700 Subject: fs/kernel_read_file: Split into separate include file Move kernel_read_file* out of linux/fs.h to its own linux/kernel_read_file.h include file. That header gets pulled in just about everywhere and doesn't really need functions not related to the general fs interface. Suggested-by: Christoph Hellwig Signed-off-by: Scott Branden Signed-off-by: Kees Cook Reviewed-by: Christoph Hellwig Reviewed-by: Mimi Zohar Reviewed-by: Luis Chamberlain Acked-by: Greg Kroah-Hartman Acked-by: James Morris Link: https://lore.kernel.org/r/20200706232309.12010-2-scott.branden@broadcom.com Link: https://lore.kernel.org/r/20201002173828.2099543-4-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 38 ------------------------------ include/linux/ima.h | 1 + include/linux/kernel_read_file.h | 51 ++++++++++++++++++++++++++++++++++++++++ include/linux/security.h | 1 + 4 files changed, 53 insertions(+), 38 deletions(-) create mode 100644 include/linux/kernel_read_file.h (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3fb7af12d033..0885d53afb11 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2858,44 +2858,6 @@ static inline void i_readcount_inc(struct inode *inode) #endif extern int do_pipe_flags(int *, int); -/* This is a list of *what* is being read, not *how* nor *where*. */ -#define __kernel_read_file_id(id) \ - id(UNKNOWN, unknown) \ - id(FIRMWARE, firmware) \ - id(MODULE, kernel-module) \ - id(KEXEC_IMAGE, kexec-image) \ - id(KEXEC_INITRAMFS, kexec-initramfs) \ - id(POLICY, security-policy) \ - id(X509_CERTIFICATE, x509-certificate) \ - id(MAX_ID, ) - -#define __fid_enumify(ENUM, dummy) READING_ ## ENUM, -#define __fid_stringify(dummy, str) #str, - -enum kernel_read_file_id { - __kernel_read_file_id(__fid_enumify) -}; - -static const char * const kernel_read_file_str[] = { - __kernel_read_file_id(__fid_stringify) -}; - -static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) -{ - if ((unsigned)id >= READING_MAX_ID) - return kernel_read_file_str[READING_UNKNOWN]; - - return kernel_read_file_str[id]; -} - -extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, - enum kernel_read_file_id); -extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t, - enum kernel_read_file_id); -extern int kernel_read_file_from_path_initns(const char *, void **, loff_t *, loff_t, - enum kernel_read_file_id); -extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, - enum kernel_read_file_id); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); diff --git a/include/linux/ima.h b/include/linux/ima.h index d15100de6cdd..64804f78408b 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -7,6 +7,7 @@ #ifndef _LINUX_IMA_H #define _LINUX_IMA_H +#include #include #include #include diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h new file mode 100644 index 000000000000..78cf3d7dc835 --- /dev/null +++ b/include/linux/kernel_read_file.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KERNEL_READ_FILE_H +#define _LINUX_KERNEL_READ_FILE_H + +#include +#include + +/* This is a list of *what* is being read, not *how* nor *where*. */ +#define __kernel_read_file_id(id) \ + id(UNKNOWN, unknown) \ + id(FIRMWARE, firmware) \ + id(MODULE, kernel-module) \ + id(KEXEC_IMAGE, kexec-image) \ + id(KEXEC_INITRAMFS, kexec-initramfs) \ + id(POLICY, security-policy) \ + id(X509_CERTIFICATE, x509-certificate) \ + id(MAX_ID, ) + +#define __fid_enumify(ENUM, dummy) READING_ ## ENUM, +#define __fid_stringify(dummy, str) #str, + +enum kernel_read_file_id { + __kernel_read_file_id(__fid_enumify) +}; + +static const char * const kernel_read_file_str[] = { + __kernel_read_file_id(__fid_stringify) +}; + +static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) +{ + if ((unsigned int)id >= READING_MAX_ID) + return kernel_read_file_str[READING_UNKNOWN]; + + return kernel_read_file_str[id]; +} + +int kernel_read_file(struct file *file, + void **buf, loff_t *size, loff_t max_size, + enum kernel_read_file_id id); +int kernel_read_file_from_path(const char *path, + void **buf, loff_t *size, loff_t max_size, + enum kernel_read_file_id id); +int kernel_read_file_from_path_initns(const char *path, + void **buf, loff_t *size, loff_t max_size, + enum kernel_read_file_id id); +int kernel_read_file_from_fd(int fd, + void **buf, loff_t *size, loff_t max_size, + enum kernel_read_file_id id); + +#endif /* _LINUX_KERNEL_READ_FILE_H */ diff --git a/include/linux/security.h b/include/linux/security.h index 0a0a03b36a3b..42df0d9b4c37 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -23,6 +23,7 @@ #ifndef __LINUX_SECURITY_H #define __LINUX_SECURITY_H +#include #include #include #include -- cgit v1.2.3 From f7a4f689bca6072492626938aad6dd2f32c5bf97 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:17 -0700 Subject: fs/kernel_read_file: Remove redundant size argument In preparation for refactoring kernel_read_file*(), remove the redundant "size" argument which is not needed: it can be included in the return code, with callers adjusted. (VFS reads already cannot be larger than INT_MAX.) Signed-off-by: Kees Cook Reviewed-by: Mimi Zohar Reviewed-by: Luis Chamberlain Reviewed-by: James Morris Acked-by: Scott Branden Link: https://lore.kernel.org/r/20201002173828.2099543-6-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kernel_read_file.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h index 78cf3d7dc835..0ca0bdbed1bd 100644 --- a/include/linux/kernel_read_file.h +++ b/include/linux/kernel_read_file.h @@ -36,16 +36,16 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) } int kernel_read_file(struct file *file, - void **buf, loff_t *size, loff_t max_size, + void **buf, loff_t max_size, enum kernel_read_file_id id); int kernel_read_file_from_path(const char *path, - void **buf, loff_t *size, loff_t max_size, + void **buf, loff_t max_size, enum kernel_read_file_id id); int kernel_read_file_from_path_initns(const char *path, - void **buf, loff_t *size, loff_t max_size, + void **buf, loff_t max_size, enum kernel_read_file_id id); int kernel_read_file_from_fd(int fd, - void **buf, loff_t *size, loff_t max_size, + void **buf, loff_t max_size, enum kernel_read_file_id id); #endif /* _LINUX_KERNEL_READ_FILE_H */ -- cgit v1.2.3 From 113eeb517780add2b38932a61d4e4440a73eb72a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:18 -0700 Subject: fs/kernel_read_file: Switch buffer size arg to size_t In preparation for further refactoring of kernel_read_file*(), rename the "max_size" argument to the more accurate "buf_size", and correct its type to size_t. Add kerndoc to explain the specifics of how the arguments will be used. Note that with buf_size now size_t, it can no longer be negative (and was never called with a negative value). Adjust callers to use it as a "maximum size" when *buf is NULL. Signed-off-by: Kees Cook Reviewed-by: Mimi Zohar Reviewed-by: Luis Chamberlain Reviewed-by: James Morris Acked-by: Scott Branden Link: https://lore.kernel.org/r/20201002173828.2099543-7-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kernel_read_file.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h index 0ca0bdbed1bd..910039e7593e 100644 --- a/include/linux/kernel_read_file.h +++ b/include/linux/kernel_read_file.h @@ -36,16 +36,16 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) } int kernel_read_file(struct file *file, - void **buf, loff_t max_size, + void **buf, size_t buf_size, enum kernel_read_file_id id); int kernel_read_file_from_path(const char *path, - void **buf, loff_t max_size, + void **buf, size_t buf_size, enum kernel_read_file_id id); int kernel_read_file_from_path_initns(const char *path, - void **buf, loff_t max_size, + void **buf, size_t buf_size, enum kernel_read_file_id id); int kernel_read_file_from_fd(int fd, - void **buf, loff_t max_size, + void **buf, size_t buf_size, enum kernel_read_file_id id); #endif /* _LINUX_KERNEL_READ_FILE_H */ -- cgit v1.2.3 From 885352881f11f1f3113d8eb877786bcb6d720544 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:19 -0700 Subject: fs/kernel_read_file: Add file_size output argument In preparation for adding partial read support, add an optional output argument to kernel_read_file*() that reports the file size so callers can reason more easily about their reading progress. Signed-off-by: Kees Cook Reviewed-by: Mimi Zohar Reviewed-by: Luis Chamberlain Reviewed-by: James Morris Acked-by: Scott Branden Link: https://lore.kernel.org/r/20201002173828.2099543-8-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kernel_read_file.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h index 910039e7593e..023293eaf948 100644 --- a/include/linux/kernel_read_file.h +++ b/include/linux/kernel_read_file.h @@ -37,15 +37,19 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) int kernel_read_file(struct file *file, void **buf, size_t buf_size, + size_t *file_size, enum kernel_read_file_id id); int kernel_read_file_from_path(const char *path, void **buf, size_t buf_size, + size_t *file_size, enum kernel_read_file_id id); int kernel_read_file_from_path_initns(const char *path, void **buf, size_t buf_size, + size_t *file_size, enum kernel_read_file_id id); int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size, + size_t *file_size, enum kernel_read_file_id id); #endif /* _LINUX_KERNEL_READ_FILE_H */ -- cgit v1.2.3 From b64fcae74b6d6940d14243c963ab0089e8f0d82d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:20 -0700 Subject: LSM: Introduce kernel_post_load_data() hook There are a few places in the kernel where LSMs would like to have visibility into the contents of a kernel buffer that has been loaded or read. While security_kernel_post_read_file() (which includes the buffer) exists as a pairing for security_kernel_read_file(), no such hook exists to pair with security_kernel_load_data(). Earlier proposals for just using security_kernel_post_read_file() with a NULL file argument were rejected (i.e. "file" should always be valid for the security_..._file hooks, but it appears at least one case was left in the kernel during earlier refactoring. (This will be fixed in a subsequent patch.) Since not all cases of security_kernel_load_data() can have a single contiguous buffer made available to the LSM hook (e.g. kexec image segments are separately loaded), there needs to be a way for the LSM to reason about its expectations of the hook coverage. In order to handle this, add a "contents" argument to the "kernel_load_data" hook that indicates if the newly added "kernel_post_load_data" hook will be called with the full contents once loaded. That way, LSMs requiring full contents can choose to unilaterally reject "kernel_load_data" with contents=false (which is effectively the existing hook coverage), but when contents=true they can allow it and later evaluate the "kernel_post_load_data" hook once the buffer is loaded. With this change, LSMs can gain coverage over non-file-backed data loads (e.g. init_module(2) and firmware userspace helper), which will happen in subsequent patches. Additionally prepare IMA to start processing these cases. Signed-off-by: Kees Cook Reviewed-by: KP Singh Link: https://lore.kernel.org/r/20201002173828.2099543-9-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/ima.h | 13 +++++++++++-- include/linux/lsm_hook_defs.h | 4 +++- include/linux/lsm_hooks.h | 10 ++++++++++ include/linux/security.h | 14 ++++++++++++-- 4 files changed, 36 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ima.h b/include/linux/ima.h index 64804f78408b..af9fb8c5f16a 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -20,7 +20,9 @@ extern void ima_post_create_tmpfile(struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); -extern int ima_load_data(enum kernel_load_data_id id); +extern int ima_load_data(enum kernel_load_data_id id, bool contents); +extern int ima_post_load_data(char *buf, loff_t size, + enum kernel_load_data_id id, char *description); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); @@ -78,7 +80,14 @@ static inline int ima_file_mprotect(struct vm_area_struct *vma, return 0; } -static inline int ima_load_data(enum kernel_load_data_id id) +static inline int ima_load_data(enum kernel_load_data_id id, bool contents) +{ + return 0; +} + +static inline int ima_post_load_data(char *buf, loff_t size, + enum kernel_load_data_id id, + char *description) { return 0; } diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 2a8c74d99015..83c6f1f5cc1e 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -184,7 +184,9 @@ LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) -LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id) +LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents) +LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size, + enum kernel_read_file_id id, char *description) LSM_HOOK(int, 0, kernel_read_file, struct file *file, enum kernel_read_file_id id) LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9e2e3e63719d..6bb4f1a0158c 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -635,7 +635,17 @@ * @kernel_load_data: * Load data provided by userspace. * @id kernel load data identifier + * @contents if a subsequent @kernel_post_load_data will be called. * Return 0 if permission is granted. + * @kernel_post_load_data: + * Load data provided by a non-file source (usually userspace buffer). + * @buf pointer to buffer containing the data contents. + * @size length of the data contents. + * @id kernel load data identifier + * @description a text description of what was loaded, @id-specific + * Return 0 if permission is granted. + * This must be paired with a prior @kernel_load_data call that had + * @contents set to true. * @kernel_read_file: * Read a file specified by userspace. * @file contains the file structure pointing to the file being read diff --git a/include/linux/security.h b/include/linux/security.h index 42df0d9b4c37..51c8e4e6b7cc 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -387,7 +387,10 @@ void security_cred_getsecid(const struct cred *c, u32 *secid); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); -int security_kernel_load_data(enum kernel_load_data_id id); +int security_kernel_load_data(enum kernel_load_data_id id, bool contents); +int security_kernel_post_load_data(char *buf, loff_t size, + enum kernel_load_data_id id, + char *description); int security_kernel_read_file(struct file *file, enum kernel_read_file_id id); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); @@ -1014,7 +1017,14 @@ static inline int security_kernel_module_request(char *kmod_name) return 0; } -static inline int security_kernel_load_data(enum kernel_load_data_id id) +static inline int security_kernel_load_data(enum kernel_load_data_id id, bool contents) +{ + return 0; +} + +static inline int security_kernel_post_load_data(char *buf, loff_t size, + enum kernel_load_data_id id, + char *description) { return 0; } -- cgit v1.2.3 From 2039bda1fa8dad3f4275b29eeaffef545bcbc85d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:23 -0700 Subject: LSM: Add "contents" flag to kernel_read_file hook As with the kernel_load_data LSM hook, add a "contents" flag to the kernel_read_file LSM hook that indicates whether the LSM can expect a matching call to the kernel_post_read_file LSM hook with the full contents of the file. With the coming addition of partial file read support for kernel_read_file*() API, the LSM will no longer be able to always see the entire contents of a file during the read calls. For cases where the LSM must read examine the complete file contents, it will need to do so on its own every time the kernel_read_file hook is called with contents=false (or reject such cases). Adjust all existing LSMs to retain existing behavior. Signed-off-by: Kees Cook Reviewed-by: Mimi Zohar Link: https://lore.kernel.org/r/20201002173828.2099543-12-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/ima.h | 6 ++++-- include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 3 +++ include/linux/security.h | 6 ++++-- 4 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ima.h b/include/linux/ima.h index af9fb8c5f16a..8fa7bcfb2da2 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -23,7 +23,8 @@ extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); extern int ima_load_data(enum kernel_load_data_id id, bool contents); extern int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description); -extern int ima_read_file(struct file *file, enum kernel_read_file_id id); +extern int ima_read_file(struct file *file, enum kernel_read_file_id id, + bool contents); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); extern void ima_post_path_mknod(struct dentry *dentry); @@ -92,7 +93,8 @@ static inline int ima_post_load_data(char *buf, loff_t size, return 0; } -static inline int ima_read_file(struct file *file, enum kernel_read_file_id id) +static inline int ima_read_file(struct file *file, enum kernel_read_file_id id, + bool contents) { return 0; } diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 83c6f1f5cc1e..d67cb3502310 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -188,7 +188,7 @@ LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents) LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size, enum kernel_read_file_id id, char *description) LSM_HOOK(int, 0, kernel_read_file, struct file *file, - enum kernel_read_file_id id) + enum kernel_read_file_id id, bool contents) LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old, diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 6bb4f1a0158c..8814e3d5952d 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -651,6 +651,7 @@ * @file contains the file structure pointing to the file being read * by the kernel. * @id kernel read file identifier + * @contents if a subsequent @kernel_post_read_file will be called. * Return 0 if permission is granted. * @kernel_post_read_file: * Read a file specified by userspace. @@ -659,6 +660,8 @@ * @buf pointer to buffer containing the file contents. * @size length of the file contents. * @id kernel read file identifier + * This must be paired with a prior @kernel_read_file call that had + * @contents set to true. * Return 0 if permission is granted. * @task_fix_setuid: * Update the module's state after setting one or more of the user diff --git a/include/linux/security.h b/include/linux/security.h index 51c8e4e6b7cc..bc2725491560 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -391,7 +391,8 @@ int security_kernel_load_data(enum kernel_load_data_id id, bool contents); int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description); -int security_kernel_read_file(struct file *file, enum kernel_read_file_id id); +int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, + bool contents); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); int security_task_fix_setuid(struct cred *new, const struct cred *old, @@ -1030,7 +1031,8 @@ static inline int security_kernel_post_load_data(char *buf, loff_t size, } static inline int security_kernel_read_file(struct file *file, - enum kernel_read_file_id id) + enum kernel_read_file_id id, + bool contents) { return 0; } -- cgit v1.2.3 From 0fa8e084648779eeb8929ae004301b3acf3bad84 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 2 Oct 2020 10:38:25 -0700 Subject: fs/kernel_file_read: Add "offset" arg for partial reads To perform partial reads, callers of kernel_read_file*() must have a non-NULL file_size argument and a preallocated buffer. The new "offset" argument can then be used to seek to specific locations in the file to fill the buffer to, at most, "buf_size" per call. Where possible, the LSM hooks can report whether a full file has been read or not so that the contents can be reasoned about. Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201002173828.2099543-14-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kernel_read_file.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h index 023293eaf948..575ffa1031d3 100644 --- a/include/linux/kernel_read_file.h +++ b/include/linux/kernel_read_file.h @@ -35,19 +35,19 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) return kernel_read_file_str[id]; } -int kernel_read_file(struct file *file, +int kernel_read_file(struct file *file, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id); -int kernel_read_file_from_path(const char *path, +int kernel_read_file_from_path(const char *path, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id); -int kernel_read_file_from_path_initns(const char *path, +int kernel_read_file_from_path_initns(const char *path, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id); -int kernel_read_file_from_fd(int fd, +int kernel_read_file_from_fd(int fd, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id); -- cgit v1.2.3 From 59cdb23ca2dfef3b93411d1105409dfe9cd1f62f Mon Sep 17 00:00:00 2001 From: Scott Branden Date: Fri, 2 Oct 2020 10:38:27 -0700 Subject: firmware: Add request_partial_firmware_into_buf() Add request_partial_firmware_into_buf() to allow for portions of a firmware file to be read into a buffer. This is needed when large firmware must be loaded in portions from a file on memory constrained systems. Signed-off-by: Scott Branden Co-developed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201002173828.2099543-16-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index cb3e2c06ed8a..c15acadc6cf4 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -53,6 +53,9 @@ int request_firmware_direct(const struct firmware **fw, const char *name, struct device *device); int request_firmware_into_buf(const struct firmware **firmware_p, const char *name, struct device *device, void *buf, size_t size); +int request_partial_firmware_into_buf(const struct firmware **firmware_p, + const char *name, struct device *device, + void *buf, size_t size, size_t offset); void release_firmware(const struct firmware *fw); #else @@ -102,6 +105,15 @@ static inline int request_firmware_into_buf(const struct firmware **firmware_p, return -EINVAL; } +static inline int request_partial_firmware_into_buf + (const struct firmware **firmware_p, + const char *name, + struct device *device, + void *buf, size_t size, size_t offset) +{ + return -EINVAL; +} + #endif int firmware_request_cache(struct device *device, const char *name); -- cgit v1.2.3 From 2e554a7a5d8a8092ecb20c547734bb33fddd5046 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 3 Oct 2020 01:06:46 +0300 Subject: net: dsa: propagate switchdev vlan_filtering prepare phase to drivers A driver may refuse to enable VLAN filtering for any reason beyond what the DSA framework cares about, such as: - having tc-flower rules that rely on the switch being VLAN-aware - the particular switch does not support VLAN, even if the driver does (the DSA framework just checks for the presence of the .port_vlan_add and .port_vlan_del pointers) - simply not supporting this configuration to be toggled at runtime Currently, when a driver rejects a configuration it cannot support, it does this from the commit phase, which triggers various warnings in switchdev. So propagate the prepare phase to drivers, to give them the ability to refuse invalid configurations cleanly and avoid the warnings. Since we need to modify all function prototypes and check for the prepare phase from within the drivers, take that opportunity and move the existing driver restrictions within the prepare phase where that is possible and easy. Cc: Florian Fainelli Cc: Martin Blumenstingl Cc: Hauke Mehrtens Cc: Woojung Huh Cc: Microchip Linux Driver Support Cc: Sean Wang Cc: Landen Chao Cc: Andrew Lunn Cc: Vivien Didelot Cc: Jonathan McDowell Cc: Linus Walleij Cc: Alexandre Belloni Cc: Claudiu Manoil Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 3 ++- include/soc/mscc/ocelot.h | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index c0185660881c..35429a140dfa 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -552,7 +552,8 @@ struct dsa_switch_ops { * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, - bool vlan_filtering); + bool vlan_filtering, + struct switchdev_trans *trans); int (*port_vlan_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); void (*port_vlan_add)(struct dsa_switch *ds, int port, diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 46608494616f..1e9db9577441 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -730,8 +730,8 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); void ocelot_adjust_link(struct ocelot *ocelot, int port, struct phy_device *phydev); -void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, - bool vlan_aware); +int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled, + struct switchdev_trans *trans); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); int ocelot_port_bridge_join(struct ocelot *ocelot, int port, struct net_device *bridge); -- cgit v1.2.3 From 2d914c1bf079491d1113051a7232250267f3f2e4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 30 Sep 2020 21:27:18 +0100 Subject: rxrpc: Fix accept on a connection that need securing When a new incoming call arrives at an userspace rxrpc socket on a new connection that has a security class set, the code currently pushes it onto the accept queue to hold a ref on it for the socket. This doesn't work, however, as recvmsg() pops it off, notices that it's in the SERVER_SECURING state and discards the ref. This means that the call runs out of refs too early and the kernel oopses. By contrast, a kernel rxrpc socket manually pre-charges the incoming call pool with calls that already have user call IDs assigned, so they are ref'd by the call tree on the socket. Change the mode of operation for userspace rxrpc server sockets to work like this too. Although this is a UAPI change, server sockets aren't currently functional. Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code") Signed-off-by: David Howells --- include/uapi/linux/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 4accfa7e266d..8f8dc7a937a4 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -51,11 +51,11 @@ enum rxrpc_cmsg_type { RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ - RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ RXRPC_SET_CALL_TIMEOUT = 13, /* s-: Set one or more call timeouts */ + RXRPC_CHARGE_ACCEPT = 14, /* s-: Charge the accept pool with a user call ID */ RXRPC__SUPPORTED }; -- cgit v1.2.3 From 10ed16662da9e28a33b6c991c36c6b323b03dd5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 18:06:18 +0200 Subject: block: add a bdget_part helper All remaining callers of bdget() outside of fs/block_dev.c want to get a reference to the struct block_device for a given struct hd_struct. Add a helper just for that and then mark bdget static. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d5a3e1a4c2f7..cf80e61b4c5e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -2003,7 +2003,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void blkdev_put(struct block_device *bdev, fmode_t mode); struct block_device *I_BDEV(struct inode *inode); -struct block_device *bdget(dev_t); +struct block_device *bdget_part(struct hd_struct *part); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); -- cgit v1.2.3 From 07560151db960d26b425410d6fd778e6757a5da2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 15 Sep 2020 20:53:13 -0700 Subject: block: make bio_crypt_clone() able to fail bio_crypt_clone() assumes its gfp_mask argument always includes __GFP_DIRECT_RECLAIM, so that the mempool_alloc() will always succeed. However, bio_crypt_clone() might be called with GFP_ATOMIC via setup_clone() in drivers/md/dm-rq.c, or with GFP_NOWAIT via kcryptd_io_read() in drivers/md/dm-crypt.c. Neither case is currently reachable with a bio that actually has an encryption context. However, it's fragile to rely on this. Just make bio_crypt_clone() able to fail, analogous to bio_integrity_clone(). Reported-by: Miaohe Lin Signed-off-by: Eric Biggers Reviewed-by: Mike Snitzer Reviewed-by: Satya Tangirala Cc: Satya Tangirala Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index e82342907f2b..69b24fe92cbf 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -112,12 +112,24 @@ static inline bool bio_has_crypt_ctx(struct bio *bio) #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ -void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); -static inline void bio_crypt_clone(struct bio *dst, struct bio *src, - gfp_t gfp_mask) +int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); +/** + * bio_crypt_clone - clone bio encryption context + * @dst: destination bio + * @src: source bio + * @gfp_mask: memory allocation flags + * + * If @src has an encryption context, clone it to @dst. + * + * Return: 0 on success, -ENOMEM if out of memory. -ENOMEM is only possible if + * @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM. + */ +static inline int bio_crypt_clone(struct bio *dst, struct bio *src, + gfp_t gfp_mask) { if (bio_has_crypt_ctx(src)) - __bio_crypt_clone(dst, src, gfp_mask); + return __bio_crypt_clone(dst, src, gfp_mask); + return 0; } #endif /* __LINUX_BLK_CRYPTO_H */ -- cgit v1.2.3 From 3a6f0fb7b8eb5ef0447da1332225b8c87ee207d0 Mon Sep 17 00:00:00 2001 From: Laxminath Kasam Date: Mon, 5 Oct 2020 19:47:19 +0530 Subject: regmap: irq: Add support to clear ack registers For particular codec HWs have requirement to toggle interrupt clear register twice 0->1->0. To accommodate it, need to add one more field (clear_ack) in the regmap_irq struct and update regmap-irq driver to support it. Signed-off-by: Laxminath Kasam Link: https://lore.kernel.org/r/1601907440-13373-1-git-send-email-lkasam@codeaurora.org Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index a35ec0a0d6e0..e7834d98207f 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1355,6 +1355,7 @@ struct regmap_irq_sub_irq_map { * @mask_invert: Inverted mask register: cleared bits are masked out. * @use_ack: Use @ack register even if it is zero. * @ack_invert: Inverted ack register: cleared bits for ack. + * @clear_ack: Use this to set 1 and 0 or vice-versa to clear interrupts. * @wake_invert: Inverted wake register: cleared bits are wake enabled. * @type_invert: Invert the type flags. * @type_in_mask: Use the mask registers for controlling irq type. For @@ -1403,6 +1404,7 @@ struct regmap_irq_chip { bool mask_invert:1; bool use_ack:1; bool ack_invert:1; + bool clear_ack:1; bool wake_invert:1; bool runtime_pm:1; bool type_invert:1; -- cgit v1.2.3 From 07da1223ec939982497db3caccd6215b55acc35c Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 4 Oct 2020 18:43:37 +0300 Subject: lib/scatterlist: Add support in dynamic allocation of SG table from pages Extend __sg_alloc_table_from_pages to support dynamic allocation of SG table from pages. It should be used by drivers that can't supply all the pages at one time. This function returns the last populated SGE in the table. Users should pass it as an argument to the function from the second call and forward. As before, nents will be equal to the number of populated SGEs (chunks). With this new extension, drivers can benefit the optimization of merging contiguous pages without a need to allocate all pages in advance and hold them in a large buffer. E.g. with the Infiniband driver that allocates a single page for hold the pages. For 1TB memory registration, the temporary buffer would consume only 4KB, instead of 2GB. Link: https://lore.kernel.org/r/20201004154340.1080481-2-leon@kernel.org Signed-off-by: Maor Gottlieb Reviewed-by: Christoph Hellwig Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/scatterlist.h | 38 ++++++++++++++++++++++---------------- 1 file changed, 22 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 45cf7b69d852..36c47e7e66a2 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -165,6 +165,22 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, #define for_each_sgtable_dma_sg(sgt, sg, i) \ for_each_sg((sgt)->sgl, sg, (sgt)->nents, i) +static inline void __sg_chain(struct scatterlist *chain_sg, + struct scatterlist *sgl) +{ + /* + * offset and length are unused for chain entry. Clear them. + */ + chain_sg->offset = 0; + chain_sg->length = 0; + + /* + * Set lowest bit to indicate a link pointer, and make sure to clear + * the termination bit if it happens to be set. + */ + chain_sg->page_link = ((unsigned long) sgl | SG_CHAIN) & ~SG_END; +} + /** * sg_chain - Chain two sglists together * @prv: First scatterlist @@ -178,18 +194,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, struct scatterlist *sgl) { - /* - * offset and length are unused for chain entry. Clear them. - */ - prv[prv_nents - 1].offset = 0; - prv[prv_nents - 1].length = 0; - - /* - * Set lowest bit to indicate a link pointer, and make sure to clear - * the termination bit if it happens to be set. - */ - prv[prv_nents - 1].page_link = ((unsigned long) sgl | SG_CHAIN) - & ~SG_END; + __sg_chain(&prv[prv_nents - 1], sgl); } /** @@ -286,10 +291,11 @@ void sg_free_table(struct sg_table *); int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int, struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *); int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); -int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, - unsigned int n_pages, unsigned int offset, - unsigned long size, unsigned int max_segment, - gfp_t gfp_mask); +struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, + struct page **pages, unsigned int n_pages, unsigned int offset, + unsigned long size, unsigned int max_segment, + struct scatterlist *prv, unsigned int left_pages, + gfp_t gfp_mask); int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, gfp_t gfp_mask); -- cgit v1.2.3 From 0a0f0d8be76dcd4390ff538e7060fda34db79717 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 22 Sep 2020 15:31:03 +0200 Subject: dma-mapping: split Split out all the bits that are purely for dma_map_ops implementations and related code into a new header so that they don't get pulled into all the drivers. That also means the architecture specific is not pulled in by any more, which leads to a missing includes that were pulled in by the x86 or arm versions in a few not overly portable drivers. Signed-off-by: Christoph Hellwig --- include/linux/dma-map-ops.h | 158 +++++++++++++++++++++++++++++++++++++++++ include/linux/dma-mapping.h | 168 +------------------------------------------- 2 files changed, 160 insertions(+), 166 deletions(-) create mode 100644 include/linux/dma-map-ops.h (limited to 'include') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h new file mode 100644 index 000000000000..4b4ba5bdcf6a --- /dev/null +++ b/include/linux/dma-map-ops.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This header is for implementations of dma_map_ops and related code. + * It should not be included in drivers just using the DMA API. + */ +#ifndef _LINUX_DMA_MAP_OPS_H +#define _LINUX_DMA_MAP_OPS_H + +#include + +struct dma_map_ops { + void *(*alloc)(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + unsigned long attrs); + void (*free)(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs); + struct page *(*alloc_pages)(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, + gfp_t gfp); + void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, + dma_addr_t dma_handle, enum dma_data_direction dir); + void *(*alloc_noncoherent)(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, + gfp_t gfp); + void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, enum dma_data_direction dir); + int (*mmap)(struct device *, struct vm_area_struct *, + void *, dma_addr_t, size_t, unsigned long attrs); + + int (*get_sgtable)(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); + + dma_addr_t (*map_page)(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, unsigned long attrs); + void (*unmap_page)(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, + unsigned long attrs); + /* + * map_sg returns 0 on error and a value > 0 on success. + * It should never return a value < 0. + */ + int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs); + void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs); + dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr, + size_t size, enum dma_data_direction dir, + unsigned long attrs); + void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, + unsigned long attrs); + void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir); + void (*sync_single_for_device)(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir); + void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir); + void (*sync_sg_for_device)(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir); + void (*cache_sync)(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction direction); + int (*dma_supported)(struct device *dev, u64 mask); + u64 (*get_required_mask)(struct device *dev); + size_t (*max_mapping_size)(struct device *dev); + unsigned long (*get_merge_boundary)(struct device *dev); +}; + +#ifdef CONFIG_DMA_OPS +#include + +static inline const struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (dev->dma_ops) + return dev->dma_ops; + return get_arch_dma_ops(dev->bus); +} + +static inline void set_dma_ops(struct device *dev, + const struct dma_map_ops *dma_ops) +{ + dev->dma_ops = dma_ops; +} +#else /* CONFIG_DMA_OPS */ +static inline const struct dma_map_ops *get_dma_ops(struct device *dev) +{ + return NULL; +} +static inline void set_dma_ops(struct device *dev, + const struct dma_map_ops *dma_ops) +{ +} +#endif /* CONFIG_DMA_OPS */ + +#ifdef CONFIG_DMA_DECLARE_COHERENT +int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, + dma_addr_t device_addr, size_t size); +int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle, void **ret); +int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr); +int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, size_t size, int *ret); + +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle); +int dma_release_from_global_coherent(int order, void *vaddr); +int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, + size_t size, int *ret); + +#else +static inline int dma_declare_coherent_memory(struct device *dev, + phys_addr_t phys_addr, dma_addr_t device_addr, size_t size) +{ + return -ENOSYS; +} +#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0) +#define dma_release_from_dev_coherent(dev, order, vaddr) (0) +#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0) + +static inline void *dma_alloc_from_global_coherent(struct device *dev, + ssize_t size, dma_addr_t *dma_handle) +{ + return NULL; +} +static inline int dma_release_from_global_coherent(int order, void *vaddr) +{ + return 0; +} +static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, + void *cpu_addr, size_t size, int *ret) +{ + return 0; +} +#endif /* CONFIG_DMA_DECLARE_COHERENT */ + +#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent); +#else +static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, + u64 size, const struct iommu_ops *iommu, bool coherent) +{ +} +#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */ + +#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS +void arch_teardown_dma_ops(struct device *dev); +#else +static inline void arch_teardown_dma_ops(struct device *dev) +{ +} +#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */ + +extern const struct dma_map_ops dma_dummy_ops; + +#endif /* _LINUX_DMA_MAP_OPS_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 7c77cd6f3604..9591cd482d7c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -62,72 +62,6 @@ */ #define DMA_ATTR_PRIVILEGED (1UL << 9) -struct dma_map_ops { - void* (*alloc)(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, - unsigned long attrs); - void (*free)(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs); - struct page *(*alloc_pages)(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, - gfp_t gfp); - void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); - void* (*alloc_noncoherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, - gfp_t gfp); - void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); - int (*mmap)(struct device *, struct vm_area_struct *, - void *, dma_addr_t, size_t, - unsigned long attrs); - - int (*get_sgtable)(struct device *dev, struct sg_table *sgt, void *, - dma_addr_t, size_t, unsigned long attrs); - - dma_addr_t (*map_page)(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs); - void (*unmap_page)(struct device *dev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction dir, - unsigned long attrs); - /* - * map_sg returns 0 on error and a value > 0 on success. - * It should never return a value < 0. - */ - int (*map_sg)(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs); - void (*unmap_sg)(struct device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction dir, - unsigned long attrs); - dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs); - void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction dir, - unsigned long attrs); - void (*sync_single_for_cpu)(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction dir); - void (*sync_single_for_device)(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction dir); - void (*sync_sg_for_cpu)(struct device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction dir); - void (*sync_sg_for_device)(struct device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction dir); - int (*dma_supported)(struct device *dev, u64 mask); - u64 (*get_required_mask)(struct device *dev); - size_t (*max_mapping_size)(struct device *dev); - unsigned long (*get_merge_boundary)(struct device *dev); -}; - /* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can * be given to a device to use as a DMA source or target. It is specific to a @@ -140,79 +74,9 @@ struct dma_map_ops { */ #define DMA_MAPPING_ERROR (~(dma_addr_t)0) -extern const struct dma_map_ops dma_virt_ops; -extern const struct dma_map_ops dma_dummy_ops; - #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) -#ifdef CONFIG_DMA_DECLARE_COHERENT -/* - * These three functions are only for dma allocator. - * Don't use them in device drivers. - */ -int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, - dma_addr_t *dma_handle, void **ret); -int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr); - -int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, size_t size, int *ret); - -void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle); -int dma_release_from_global_coherent(int order, void *vaddr); -int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, - size_t size, int *ret); - -#else -#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0) -#define dma_release_from_dev_coherent(dev, order, vaddr) (0) -#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0) - -static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, - dma_addr_t *dma_handle) -{ - return NULL; -} - -static inline int dma_release_from_global_coherent(int order, void *vaddr) -{ - return 0; -} - -static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, - void *cpu_addr, size_t size, - int *ret) -{ - return 0; -} -#endif /* CONFIG_DMA_DECLARE_COHERENT */ - #ifdef CONFIG_HAS_DMA -#include - -#ifdef CONFIG_DMA_OPS -static inline const struct dma_map_ops *get_dma_ops(struct device *dev) -{ - if (dev->dma_ops) - return dev->dma_ops; - return get_arch_dma_ops(dev->bus); -} - -static inline void set_dma_ops(struct device *dev, - const struct dma_map_ops *dma_ops) -{ - dev->dma_ops = dma_ops; -} -#else /* CONFIG_DMA_OPS */ -static inline const struct dma_map_ops *get_dma_ops(struct device *dev) -{ - return NULL; -} -static inline void set_dma_ops(struct device *dev, - const struct dma_map_ops *dma_ops) -{ -} -#endif /* CONFIG_DMA_OPS */ - static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { debug_dma_mapping_error(dev, dma_addr); @@ -595,24 +459,6 @@ static inline bool dma_addressing_limited(struct device *dev) dma_get_required_mask(dev); } -#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS -void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent); -#else -static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, - u64 size, const struct iommu_ops *iommu, bool coherent) -{ -} -#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */ - -#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS -void arch_teardown_dma_ops(struct device *dev); -#else -static inline void arch_teardown_dma_ops(struct device *dev) -{ -} -#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */ - static inline unsigned int dma_get_max_seg_size(struct device *dev) { if (dev->dma_parms && dev->dma_parms->max_segment_size) @@ -672,18 +518,6 @@ static inline int dma_get_cache_alignment(void) return 1; } -#ifdef CONFIG_DMA_DECLARE_COHERENT -int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, - dma_addr_t device_addr, size_t size); -#else -static inline int -dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, - dma_addr_t device_addr, size_t size) -{ - return -ENOSYS; -} -#endif /* CONFIG_DMA_DECLARE_COHERENT */ - static inline void *dmam_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { @@ -741,4 +575,6 @@ static inline int dma_mmap_wc(struct device *dev, int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start, dma_addr_t dma_start, u64 size); +extern const struct dma_map_ops dma_virt_ops; + #endif /* _LINUX_DMA_MAPPING_H */ -- cgit v1.2.3 From 8df4051232152a0520ab3035c2d96f33083c2d6a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 10:29:47 +0200 Subject: dma-contiguous: remove dma_declare_contiguous dma_declare_contiguous is a trivial wrapper around dma_contiguous_reserve_area and just has a single caller. Signed-off-by: Christoph Hellwig --- include/linux/dma-contiguous.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index fe55e004f1f4..62fd55d07235 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -83,31 +83,6 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, phys_addr_t limit, struct cma **res_cma, bool fixed); -/** - * dma_declare_contiguous() - reserve area for contiguous memory handling - * for particular device - * @dev: Pointer to device structure. - * @size: Size of the reserved memory. - * @base: Start address of the reserved memory (optional, 0 for any). - * @limit: End address of the reserved memory (optional, 0 for any). - * - * This function reserves memory for specified device. It should be - * called by board specific code when early allocator (memblock or bootmem) - * is still activate. - */ - -static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, - phys_addr_t base, phys_addr_t limit) -{ - struct cma *cma; - int ret; - ret = dma_contiguous_reserve_area(size, base, limit, &cma, true); - if (ret == 0) - dev_set_cma_area(dev, cma); - - return ret; -} - struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, unsigned int order, bool no_warn); bool dma_release_from_contiguous(struct device *dev, struct page *pages, @@ -135,13 +110,6 @@ static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base return -ENOSYS; } -static inline -int dma_declare_contiguous(struct device *dev, phys_addr_t size, - phys_addr_t base, phys_addr_t limit) -{ - return -ENOSYS; -} - static inline struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, unsigned int order, bool no_warn) -- cgit v1.2.3 From 5af638931eb374aa0894d8343cee72f50307ef20 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 10:56:03 +0200 Subject: dma-contiguous: remove dev_set_cma_area dev_set_cma_area contains a trivial assignment. It has just three callers that all have a non-NULL device and depend on CONFIG_DMA_CMA, so remove the wrapper. Signed-off-by: Christoph Hellwig --- include/linux/dma-contiguous.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 62fd55d07235..41ec08d81bc3 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -66,12 +66,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev) return dma_contiguous_default_area; } -static inline void dev_set_cma_area(struct device *dev, struct cma *cma) -{ - if (dev) - dev->cma_area = cma; -} - static inline void dma_contiguous_set_default(struct cma *cma) { dma_contiguous_default_area = cma; @@ -97,8 +91,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev) return NULL; } -static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { } - static inline void dma_contiguous_set_default(struct cma *cma) { } static inline void dma_contiguous_reserve(phys_addr_t limit) { } -- cgit v1.2.3 From 580a0cc9c3f662e0b10136bc8af1e672e472806f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 10:56:40 +0200 Subject: dma-contiguous: remove dma_contiguous_set_default dma_contiguous_set_default contains a trivial assignment, and has a single caller that is compiled if CONFIG_CMA_DMA is enabled. Signed-off-by: Christoph Hellwig --- include/linux/dma-contiguous.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 41ec08d81bc3..f9ce1ee58d41 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -66,11 +66,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev) return dma_contiguous_default_area; } -static inline void dma_contiguous_set_default(struct cma *cma) -{ - dma_contiguous_default_area = cma; -} - void dma_contiguous_reserve(phys_addr_t addr_limit); int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, @@ -91,8 +86,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev) return NULL; } -static inline void dma_contiguous_set_default(struct cma *cma) { } - static inline void dma_contiguous_reserve(phys_addr_t limit) { } static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, -- cgit v1.2.3 From 0b1abd1fb7efafc25231c54a67c6fbb3d3127efd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 10:56:52 +0200 Subject: dma-mapping: merge into Merge dma-contiguous.h into dma-map-ops.h, after removing the comment describing the contiguous allocator into kernel/dma/contigous.c. Signed-off-by: Christoph Hellwig --- include/linux/dma-contiguous.h | 135 ----------------------------------------- include/linux/dma-map-ops.h | 65 ++++++++++++++++++++ 2 files changed, 65 insertions(+), 135 deletions(-) delete mode 100644 include/linux/dma-contiguous.h (limited to 'include') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h deleted file mode 100644 index f9ce1ee58d41..000000000000 --- a/include/linux/dma-contiguous.h +++ /dev/null @@ -1,135 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef __LINUX_CMA_H -#define __LINUX_CMA_H - -/* - * Contiguous Memory Allocator for DMA mapping framework - * Copyright (c) 2010-2011 by Samsung Electronics. - * Written by: - * Marek Szyprowski - * Michal Nazarewicz - */ - -/* - * Contiguous Memory Allocator - * - * The Contiguous Memory Allocator (CMA) makes it possible to - * allocate big contiguous chunks of memory after the system has - * booted. - * - * Why is it needed? - * - * Various devices on embedded systems have no scatter-getter and/or - * IO map support and require contiguous blocks of memory to - * operate. They include devices such as cameras, hardware video - * coders, etc. - * - * Such devices often require big memory buffers (a full HD frame - * is, for instance, more then 2 mega pixels large, i.e. more than 6 - * MB of memory), which makes mechanisms such as kmalloc() or - * alloc_page() ineffective. - * - * At the same time, a solution where a big memory region is - * reserved for a device is suboptimal since often more memory is - * reserved then strictly required and, moreover, the memory is - * inaccessible to page system even if device drivers don't use it. - * - * CMA tries to solve this issue by operating on memory regions - * where only movable pages can be allocated from. This way, kernel - * can use the memory for pagecache and when device driver requests - * it, allocated pages can be migrated. - * - * Driver usage - * - * CMA should not be used by the device drivers directly. It is - * only a helper framework for dma-mapping subsystem. - * - * For more information, see kernel-docs in kernel/dma/contiguous.c - */ - -#ifdef __KERNEL__ - -#include -#include - -struct cma; -struct page; - -#ifdef CONFIG_DMA_CMA - -extern struct cma *dma_contiguous_default_area; - -static inline struct cma *dev_get_cma_area(struct device *dev) -{ - if (dev && dev->cma_area) - return dev->cma_area; - return dma_contiguous_default_area; -} - -void dma_contiguous_reserve(phys_addr_t addr_limit); - -int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma, - bool fixed); - -struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, - unsigned int order, bool no_warn); -bool dma_release_from_contiguous(struct device *dev, struct page *pages, - int count); -struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp); -void dma_free_contiguous(struct device *dev, struct page *page, size_t size); - -#else - -static inline struct cma *dev_get_cma_area(struct device *dev) -{ - return NULL; -} - -static inline void dma_contiguous_reserve(phys_addr_t limit) { } - -static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma, - bool fixed) -{ - return -ENOSYS; -} - -static inline -struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, - unsigned int order, bool no_warn) -{ - return NULL; -} - -static inline -bool dma_release_from_contiguous(struct device *dev, struct page *pages, - int count) -{ - return false; -} - -/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */ -static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size, - gfp_t gfp) -{ - return NULL; -} - -static inline void dma_free_contiguous(struct device *dev, struct page *page, - size_t size) -{ - __free_pages(page, get_order(size)); -} - -#endif - -#ifdef CONFIG_DMA_PERNUMA_CMA -void dma_pernuma_cma_reserve(void); -#else -static inline void dma_pernuma_cma_reserve(void) { } -#endif - -#endif - -#endif diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4b4ba5bdcf6a..474fc81bd492 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -8,6 +8,8 @@ #include +struct cma; + struct dma_map_ops { void *(*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, @@ -94,6 +96,69 @@ static inline void set_dma_ops(struct device *dev, } #endif /* CONFIG_DMA_OPS */ +#ifdef CONFIG_DMA_CMA +extern struct cma *dma_contiguous_default_area; + +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + if (dev && dev->cma_area) + return dev->cma_area; + return dma_contiguous_default_area; +} + +void dma_contiguous_reserve(phys_addr_t addr_limit); +int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, + phys_addr_t limit, struct cma **res_cma, bool fixed); + +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, + unsigned int order, bool no_warn); +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count); +struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp); +void dma_free_contiguous(struct device *dev, struct page *page, size_t size); +#else /* CONFIG_DMA_CMA */ +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + return NULL; +} +static inline void dma_contiguous_reserve(phys_addr_t limit) +{ +} +static inline int dma_contiguous_reserve_area(phys_addr_t size, + phys_addr_t base, phys_addr_t limit, struct cma **res_cma, + bool fixed) +{ + return -ENOSYS; +} +static inline struct page *dma_alloc_from_contiguous(struct device *dev, + size_t count, unsigned int order, bool no_warn) +{ + return NULL; +} +static inline bool dma_release_from_contiguous(struct device *dev, + struct page *pages, int count) +{ + return false; +} +/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */ +static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size, + gfp_t gfp) +{ + return NULL; +} +static inline void dma_free_contiguous(struct device *dev, struct page *page, + size_t size) +{ + __free_pages(page, get_order(size)); +} +#endif /* CONFIG_DMA_CMA*/ + +#ifdef CONFIG_DMA_PERNUMA_CMA +void dma_pernuma_cma_reserve(void); +#else +static inline void dma_pernuma_cma_reserve(void) { } +#endif /* CONFIG_DMA_PERNUMA_CMA */ + #ifdef CONFIG_DMA_DECLARE_COHERENT int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size); -- cgit v1.2.3 From 5db5d93089880c3cc9e83ca8bba68a5502e92dfe Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 11:04:43 +0200 Subject: dma-mapping: remove Just provide a weak default definition of dma_contiguous_early_fixup and let arm override it. Signed-off-by: Christoph Hellwig --- include/asm-generic/Kbuild | 1 - include/asm-generic/dma-contiguous.h | 10 ---------- include/linux/dma-map-ops.h | 2 ++ 3 files changed, 2 insertions(+), 11 deletions(-) delete mode 100644 include/asm-generic/dma-contiguous.h (limited to 'include') diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 74b0612601dd..62ebdc731ee2 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -16,7 +16,6 @@ mandatory-y += current.h mandatory-y += delay.h mandatory-y += device.h mandatory-y += div64.h -mandatory-y += dma-contiguous.h mandatory-y += dma-mapping.h mandatory-y += dma.h mandatory-y += emergency-restart.h diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h deleted file mode 100644 index f24b0f9a4f05..000000000000 --- a/include/asm-generic/dma-contiguous.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H -#define _ASM_GENERIC_DMA_CONTIGUOUS_H - -#include - -static inline void -dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { } - -#endif diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 474fc81bd492..7912f5d00ed9 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -116,6 +116,8 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages, int count); struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp); void dma_free_contiguous(struct device *dev, struct page *page, size_t size); + +void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size); #else /* CONFIG_DMA_CMA */ static inline struct cma *dev_get_cma_area(struct device *dev) { -- cgit v1.2.3 From a1fd09e8e6ae35228ecc7c1e4bfff1fd725f78a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 11 Sep 2020 10:12:44 +0200 Subject: dma-mapping: move dma-debug.h to kernel/dma/ Most of dma-debug.h is not required by anything outside of kernel/dma. Move the four declarations needed by dma-mappin.h or dma-ops providers into dma-mapping.h and dma-map-ops.h, and move the remainder of the file to kernel/dma/debug.h. Signed-off-by: Christoph Hellwig --- include/linux/dma-debug.h | 160 -------------------------------------------- include/linux/dma-map-ops.h | 12 ++++ include/linux/dma-mapping.h | 16 ++++- 3 files changed, 27 insertions(+), 161 deletions(-) delete mode 100644 include/linux/dma-debug.h (limited to 'include') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h deleted file mode 100644 index 7b3b04ba60f3..000000000000 --- a/include/linux/dma-debug.h +++ /dev/null @@ -1,160 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2008 Advanced Micro Devices, Inc. - * - * Author: Joerg Roedel - */ - -#ifndef __DMA_DEBUG_H -#define __DMA_DEBUG_H - -#include - -struct device; -struct scatterlist; -struct bus_type; - -#ifdef CONFIG_DMA_API_DEBUG - -extern void dma_debug_add_bus(struct bus_type *bus); - -extern void debug_dma_map_single(struct device *dev, const void *addr, - unsigned long len); - -extern void debug_dma_map_page(struct device *dev, struct page *page, - size_t offset, size_t size, - int direction, dma_addr_t dma_addr); - -extern void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); - -extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction); - -extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, int mapped_ents, int direction); - -extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, - int nelems, int dir); - -extern void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt); - -extern void debug_dma_free_coherent(struct device *dev, size_t size, - void *virt, dma_addr_t addr); - -extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr, - size_t size, int direction, - dma_addr_t dma_addr); - -extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction); - -extern void debug_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, - int direction); - -extern void debug_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, - size_t size, int direction); - -extern void debug_dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sg, - int nelems, int direction); - -extern void debug_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, - int nelems, int direction); - -extern void debug_dma_dump_mappings(struct device *dev); - -#else /* CONFIG_DMA_API_DEBUG */ - -static inline void dma_debug_add_bus(struct bus_type *bus) -{ -} - -static inline void debug_dma_map_single(struct device *dev, const void *addr, - unsigned long len) -{ -} - -static inline void debug_dma_map_page(struct device *dev, struct page *page, - size_t offset, size_t size, - int direction, dma_addr_t dma_addr) -{ -} - -static inline void debug_dma_mapping_error(struct device *dev, - dma_addr_t dma_addr) -{ -} - -static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction) -{ -} - -static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, int mapped_ents, int direction) -{ -} - -static inline void debug_dma_unmap_sg(struct device *dev, - struct scatterlist *sglist, - int nelems, int dir) -{ -} - -static inline void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt) -{ -} - -static inline void debug_dma_free_coherent(struct device *dev, size_t size, - void *virt, dma_addr_t addr) -{ -} - -static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr, - size_t size, int direction, - dma_addr_t dma_addr) -{ -} - -static inline void debug_dma_unmap_resource(struct device *dev, - dma_addr_t dma_addr, size_t size, - int direction) -{ -} - -static inline void debug_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, - size_t size, int direction) -{ -} - -static inline void debug_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, - size_t size, int direction) -{ -} - -static inline void debug_dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sg, - int nelems, int direction) -{ -} - -static inline void debug_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, - int nelems, int direction) -{ -} - -static inline void debug_dma_dump_mappings(struct device *dev) -{ -} - -#endif /* CONFIG_DMA_API_DEBUG */ - -#endif /* __DMA_DEBUG_H */ diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 7912f5d00ed9..9891def42da7 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -220,6 +220,18 @@ static inline void arch_teardown_dma_ops(struct device *dev) } #endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */ +#ifdef CONFIG_DMA_API_DEBUG +void dma_debug_add_bus(struct bus_type *bus); +void debug_dma_dump_mappings(struct device *dev); +#else +static inline void dma_debug_add_bus(struct bus_type *bus) +{ +} +static inline void debug_dma_dump_mappings(struct device *dev) +{ +} +#endif /* CONFIG_DMA_API_DEBUG */ + extern const struct dma_map_ops dma_dummy_ops; #endif /* _LINUX_DMA_MAP_OPS_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 9591cd482d7c..3f029afdc9dc 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -6,7 +6,6 @@ #include #include #include -#include #include #include #include @@ -76,6 +75,21 @@ #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) +#ifdef CONFIG_DMA_API_DEBUG +void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); +void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len); +#else +static inline void debug_dma_mapping_error(struct device *dev, + dma_addr_t dma_addr) +{ +} +static inline void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len) +{ +} +#endif /* CONFIG_DMA_API_DEBUG */ + #ifdef CONFIG_HAS_DMA static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { -- cgit v1.2.3 From 19c65c3d30bb5a97170e425979d2e44ab2096c7d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 22 Sep 2020 15:34:22 +0200 Subject: dma-mapping: move large parts of to kernel/dma Most of the dma_direct symbols should only be used by direct.c and mapping.c, so move them to kernel/dma. In fact more of dma-direct.h should eventually move, but that will require more coordination with other subsystems. Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 106 --------------------------------------------- 1 file changed, 106 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 38ed3b55034d..a2d6640c42c0 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -120,114 +120,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, void dma_direct_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_addr, enum dma_data_direction dir); -int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); -bool dma_direct_can_mmap(struct device *dev); -int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); -bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); -int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, - enum dma_data_direction dir, unsigned long attrs); dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir, unsigned long attrs); -size_t dma_direct_max_mapping_size(struct device *dev); -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ - defined(CONFIG_SWIOTLB) -void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir); -#else -static inline void dma_direct_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ -} -#endif - -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ - defined(CONFIG_SWIOTLB) -void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs); -void dma_direct_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); -#else -static inline void dma_direct_unmap_sg(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir, - unsigned long attrs) -{ -} -static inline void dma_direct_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ -} -#endif - -static inline void dma_direct_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ - phys_addr_t paddr = dma_to_phys(dev, addr); - - if (unlikely(is_swiotlb_buffer(paddr))) - swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); - - if (!dev_is_dma_coherent(dev)) - arch_sync_dma_for_device(paddr, size, dir); -} - -static inline void dma_direct_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ - phys_addr_t paddr = dma_to_phys(dev, addr); - - if (!dev_is_dma_coherent(dev)) { - arch_sync_dma_for_cpu(paddr, size, dir); - arch_sync_dma_for_cpu_all(); - } - - if (unlikely(is_swiotlb_buffer(paddr))) - swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); - - if (dir == DMA_FROM_DEVICE) - arch_dma_mark_clean(paddr, size); -} - -static inline dma_addr_t dma_direct_map_page(struct device *dev, - struct page *page, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - phys_addr_t phys = page_to_phys(page) + offset; - dma_addr_t dma_addr = phys_to_dma(dev, phys); - - if (unlikely(swiotlb_force == SWIOTLB_FORCE)) - return swiotlb_map(dev, phys, size, dir, attrs); - - if (unlikely(!dma_capable(dev, dma_addr, size, true))) { - if (swiotlb_force != SWIOTLB_NO_FORCE) - return swiotlb_map(dev, phys, size, dir, attrs); - - dev_WARN_ONCE(dev, 1, - "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", - &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); - return DMA_MAPPING_ERROR; - } - - if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_device(phys, size, dir); - return dma_addr; -} - -static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - phys_addr_t phys = dma_to_phys(dev, addr); - - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_single_for_cpu(dev, addr, size, dir); - - if (unlikely(is_swiotlb_buffer(phys))) - swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs); -} #endif /* _LINUX_DMA_DIRECT_H */ -- cgit v1.2.3 From 9f4df96b8781e40d0cb0e32eb3d1f6d87375adf9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 22 Sep 2020 15:36:11 +0200 Subject: dma-mapping: merge into Move more nitty gritty DMA implementation details into the common internal header. Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 2 +- include/linux/dma-map-ops.h | 102 +++++++++++++++++++++++++++++++++++++ include/linux/dma-noncoherent.h | 109 ---------------------------------------- 3 files changed, 103 insertions(+), 110 deletions(-) delete mode 100644 include/linux/dma-noncoherent.h (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index a2d6640c42c0..18aade195884 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -7,7 +7,7 @@ #define _LINUX_DMA_DIRECT_H 1 #include -#include +#include #include /* for min_low_pfn */ #include #include diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 9891def42da7..33c6e24707a9 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -7,6 +7,7 @@ #define _LINUX_DMA_MAP_OPS_H #include +#include struct cma; @@ -202,6 +203,107 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_DECLARE_COHERENT */ +#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H +#include +#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) +static inline bool dev_is_dma_coherent(struct device *dev) +{ + return dev->dma_coherent; +} +#else +static inline bool dev_is_dma_coherent(struct device *dev) +{ + return true; +} +#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ + +/* + * Check if an allocation needs to be marked uncached to be coherent. + */ +static __always_inline bool dma_alloc_need_uncached(struct device *dev, + unsigned long attrs) +{ + if (dev_is_dma_coherent(dev)) + return false; + if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) + return false; + return true; +} + +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs); +void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_addr, unsigned long attrs); + +#ifdef CONFIG_MMU +/* + * Page protection so that devices that can't snoop CPU caches can use the + * memory coherently. We default to pgprot_noncached which is usually used + * for ioremap as a safe bet, but architectures can override this with less + * strict semantics if possible. + */ +#ifndef pgprot_dmacoherent +#define pgprot_dmacoherent(prot) pgprot_noncached(prot) +#endif + +pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); +#else +static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + return prot; /* no protection bits supported without page tables */ +} +#endif /* CONFIG_MMU */ + +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir); +#else +static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) +{ +} +#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */ + +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir); +#else +static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) +{ +} +#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */ + +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL +void arch_sync_dma_for_cpu_all(void); +#else +static inline void arch_sync_dma_for_cpu_all(void) +{ +} +#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ + +#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT +void arch_dma_prep_coherent(struct page *page, size_t size); +#else +static inline void arch_dma_prep_coherent(struct page *page, size_t size) +{ +} +#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */ + +#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN +void arch_dma_mark_clean(phys_addr_t paddr, size_t size); +#else +static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size) +{ +} +#endif /* ARCH_HAS_DMA_MARK_CLEAN */ + +void *arch_dma_set_uncached(void *addr, size_t size); +void arch_dma_clear_uncached(void *addr, size_t size); + #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent); diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h deleted file mode 100644 index e61283e06576..000000000000 --- a/include/linux/dma-noncoherent.h +++ /dev/null @@ -1,109 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_DMA_NONCOHERENT_H -#define _LINUX_DMA_NONCOHERENT_H 1 - -#include -#include - -#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H -#include -#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) -static inline bool dev_is_dma_coherent(struct device *dev) -{ - return dev->dma_coherent; -} -#else -static inline bool dev_is_dma_coherent(struct device *dev) -{ - return true; -} -#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ - -/* - * Check if an allocation needs to be marked uncached to be coherent. - */ -static __always_inline bool dma_alloc_need_uncached(struct device *dev, - unsigned long attrs) -{ - if (dev_is_dma_coherent(dev)) - return false; - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) - return false; - return true; -} - -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs); -void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_addr, unsigned long attrs); - -#ifdef CONFIG_MMU -/* - * Page protection so that devices that can't snoop CPU caches can use the - * memory coherently. We default to pgprot_noncached which is usually used - * for ioremap as a safe bet, but architectures can override this with less - * strict semantics if possible. - */ -#ifndef pgprot_dmacoherent -#define pgprot_dmacoherent(prot) pgprot_noncached(prot) -#endif - -pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); -#else -static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, - unsigned long attrs) -{ - return prot; /* no protection bits supported without page tables */ -} -#endif /* CONFIG_MMU */ - -#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE -void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, - enum dma_data_direction dir); -#else -static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, - enum dma_data_direction dir) -{ -} -#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */ - -#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU -void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, - enum dma_data_direction dir); -#else -static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, - enum dma_data_direction dir) -{ -} -#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */ - -#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL -void arch_sync_dma_for_cpu_all(void); -#else -static inline void arch_sync_dma_for_cpu_all(void) -{ -} -#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ - -#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT -void arch_dma_prep_coherent(struct page *page, size_t size); -#else -static inline void arch_dma_prep_coherent(struct page *page, size_t size) -{ -} -#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */ - -#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN -void arch_dma_mark_clean(phys_addr_t paddr, size_t size); -#else -static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size) -{ -} -#endif /* ARCH_HAS_DMA_MARK_CLEAN */ - -void *arch_dma_set_uncached(void *addr, size_t size); -void arch_dma_clear_uncached(void *addr, size_t size); - -#endif /* _LINUX_DMA_NONCOHERENT_H */ -- cgit v1.2.3 From 5de15b610f785f0e188fefb707f0b19de156968a Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sat, 3 Oct 2020 23:23:20 +0300 Subject: mtd: hyperbus: add Renesas RPC-IF driver Add the HyperFLash driver for the Renesas RPC-IF. It's the "front end" driver using the "back end" APIs in the main driver to talk to the real hardware. Signed-off-by: Sergei Shtylyov Signed-off-by: Vignesh Raghavendra Link: https://lore.kernel.org/r/78abb851-2beb-fe7d-87e5-ce58ee877d35@gmail.com --- include/linux/mtd/hyperbus.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h index d8cb1aec826d..0ce612428aea 100644 --- a/include/linux/mtd/hyperbus.h +++ b/include/linux/mtd/hyperbus.h @@ -8,6 +8,17 @@ #include +/* HyperBus command bits */ +#define HYPERBUS_RW 0x80 /* R/W# */ +#define HYPERBUS_RW_WRITE 0 +#define HYPERBUS_RW_READ 0x80 +#define HYPERBUS_AS 0x40 /* Address Space */ +#define HYPERBUS_AS_MEM 0 +#define HYPERBUS_AS_REG 0x40 +#define HYPERBUS_BT 0x20 /* Burst Type */ +#define HYPERBUS_BT_WRAPPED 0 +#define HYPERBUS_BT_LINEAR 0x20 + enum hyperbus_memtype { HYPERFLASH, HYPERRAM, -- cgit v1.2.3 From ec6347bb43395cb92126788a1a5b25302543f815 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 5 Oct 2020 20:40:16 -0700 Subject: x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}() In reaction to a proposal to introduce a memcpy_mcsafe_fast() implementation Linus points out that memcpy_mcsafe() is poorly named relative to communicating the scope of the interface. Specifically what addresses are valid to pass as source, destination, and what faults / exceptions are handled. Of particular concern is that even though x86 might be able to handle the semantics of copy_mc_to_user() with its common copy_user_generic() implementation other archs likely need / want an explicit path for this case: On Fri, May 1, 2020 at 11:28 AM Linus Torvalds wrote: > > On Thu, Apr 30, 2020 at 6:21 PM Dan Williams wrote: > > > > However now I see that copy_user_generic() works for the wrong reason. > > It works because the exception on the source address due to poison > > looks no different than a write fault on the user address to the > > caller, it's still just a short copy. So it makes copy_to_user() work > > for the wrong reason relative to the name. > > Right. > > And it won't work that way on other architectures. On x86, we have a > generic function that can take faults on either side, and we use it > for both cases (and for the "in_user" case too), but that's an > artifact of the architecture oddity. > > In fact, it's probably wrong even on x86 - because it can hide bugs - > but writing those things is painful enough that everybody prefers > having just one function. Replace a single top-level memcpy_mcsafe() with either copy_mc_to_user(), or copy_mc_to_kernel(). Introduce an x86 copy_mc_fragile() name as the rename for the low-level x86 implementation formerly named memcpy_mcsafe(). It is used as the slow / careful backend that is supplanted by a fast copy_mc_generic() in a follow-on patch. One side-effect of this reorganization is that separating copy_mc_64.S to its own file means that perf no longer needs to track dependencies for its memcpy_64.S benchmarks. [ bp: Massage a bit. ] Signed-off-by: Dan Williams Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Acked-by: Michael Ellerman Cc: Link: http://lore.kernel.org/r/CAHk-=wjSqtXAqfUJxFtWNwmguFASTgB0dz1dT3V-78Quiezqbg@mail.gmail.com Link: https://lkml.kernel.org/r/160195561680.2163339.11574962055305783722.stgit@dwillia2-desk3.amr.corp.intel.com --- include/linux/string.h | 9 +-------- include/linux/uaccess.h | 13 +++++++++++++ include/linux/uio.h | 10 +++++----- 3 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/string.h b/include/linux/string.h index 9b7a0632e87a..b1f3894a0a3e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -161,20 +161,13 @@ extern int bcmp(const void *,const void *,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif -#ifndef __HAVE_ARCH_MEMCPY_MCSAFE -static inline __must_check unsigned long memcpy_mcsafe(void *dst, - const void *src, size_t cnt) -{ - memcpy(dst, src, cnt); - return 0; -} -#endif #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); } #endif + void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *s, char old, char new); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 94b285411659..1ae36bc8db35 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -179,6 +179,19 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n) } #endif +#ifndef copy_mc_to_kernel +/* + * Without arch opt-in this generic copy_mc_to_kernel() will not handle + * #MC (or arch equivalent) during source read. + */ +static inline unsigned long __must_check +copy_mc_to_kernel(void *dst, const void *src, size_t cnt) +{ + memcpy(dst, src, cnt); + return 0; +} +#endif + static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; diff --git a/include/linux/uio.h b/include/linux/uio.h index 3835a8a8e9ea..f14410c678bd 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -185,10 +185,10 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif -#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE -size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i); +#ifdef CONFIG_ARCH_HAS_COPY_MC +size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else -#define _copy_to_iter_mcsafe _copy_to_iter +#define _copy_mc_to_iter _copy_to_iter #endif static __always_inline __must_check @@ -201,12 +201,12 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) } static __always_inline __must_check -size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) +size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else - return _copy_to_iter_mcsafe(addr, bytes, i); + return _copy_mc_to_iter(addr, bytes, i); } size_t iov_iter_zero(size_t bytes, struct iov_iter *); -- cgit v1.2.3 From 90428a8eb4947f9c7c905a178f3520dc7e2ee6d2 Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Mon, 28 Sep 2020 10:02:01 +0530 Subject: genirq/PM: Introduce IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND flag An interrupt that is disabled/masked but set for wakeup may still need to be able to wake up the system from sleep states like "suspend to RAM". To that effect, introduce the IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND flag. If the irqchip have this flag set, the irq PM code will enable/unmask the irqs that are marked for wakeup, but that are in a disabled state. On resume, such irqs will be restored back to their disabled state. Suggested-by: Thomas Gleixner Signed-off-by: Maulik Shah [maz: commit message fix-up] Signed-off-by: Marc Zyngier Tested-by: Stephen Boyd Reviewed-by: Thomas Gleixner Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/1601267524-20199-4-git-send-email-mkshah@codeaurora.org --- include/linux/irq.h | 49 ++++++++++++++++++++++++++++++------------------- 1 file changed, 30 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 1b7f4dfee35b..a8b84b88e673 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -215,6 +215,8 @@ struct irq_data { * from actual interrupt context. * IRQD_AFFINITY_ON_ACTIVATE - Affinity is set on activation. Don't call * irq_chip::irq_set_affinity() when deactivated. + * IRQD_IRQ_ENABLED_ON_SUSPEND - Interrupt is enabled on suspend by irq pm if + * irqchip have flag IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND set. */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -240,6 +242,7 @@ enum { IRQD_MSI_NOMASK_QUIRK = (1 << 27), IRQD_HANDLE_ENFORCE_IRQCTX = (1 << 28), IRQD_AFFINITY_ON_ACTIVATE = (1 << 29), + IRQD_IRQ_ENABLED_ON_SUSPEND = (1 << 30), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -319,6 +322,11 @@ static inline bool irqd_is_handle_enforce_irqctx(struct irq_data *d) return __irqd_to_state(d) & IRQD_HANDLE_ENFORCE_IRQCTX; } +static inline bool irqd_is_enabled_on_suspend(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_IRQ_ENABLED_ON_SUSPEND; +} + static inline bool irqd_is_wakeup_set(struct irq_data *d) { return __irqd_to_state(d) & IRQD_WAKEUP_STATE; @@ -545,27 +553,30 @@ struct irq_chip { /* * irq_chip specific flags * - * IRQCHIP_SET_TYPE_MASKED: Mask before calling chip.irq_set_type() - * IRQCHIP_EOI_IF_HANDLED: Only issue irq_eoi() when irq was handled - * IRQCHIP_MASK_ON_SUSPEND: Mask non wake irqs in the suspend path - * IRQCHIP_ONOFFLINE_ENABLED: Only call irq_on/off_line callbacks - * when irq enabled - * IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip - * IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask - * IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode - * IRQCHIP_SUPPORTS_LEVEL_MSI Chip can provide two doorbells for Level MSIs - * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips + * IRQCHIP_SET_TYPE_MASKED: Mask before calling chip.irq_set_type() + * IRQCHIP_EOI_IF_HANDLED: Only issue irq_eoi() when irq was handled + * IRQCHIP_MASK_ON_SUSPEND: Mask non wake irqs in the suspend path + * IRQCHIP_ONOFFLINE_ENABLED: Only call irq_on/off_line callbacks + * when irq enabled + * IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip + * IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask + * IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode + * IRQCHIP_SUPPORTS_LEVEL_MSI: Chip can provide two doorbells for Level MSIs + * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips + * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs + * in the suspend path if they are in disabled state */ enum { - IRQCHIP_SET_TYPE_MASKED = (1 << 0), - IRQCHIP_EOI_IF_HANDLED = (1 << 1), - IRQCHIP_MASK_ON_SUSPEND = (1 << 2), - IRQCHIP_ONOFFLINE_ENABLED = (1 << 3), - IRQCHIP_SKIP_SET_WAKE = (1 << 4), - IRQCHIP_ONESHOT_SAFE = (1 << 5), - IRQCHIP_EOI_THREADED = (1 << 6), - IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), - IRQCHIP_SUPPORTS_NMI = (1 << 8), + IRQCHIP_SET_TYPE_MASKED = (1 << 0), + IRQCHIP_EOI_IF_HANDLED = (1 << 1), + IRQCHIP_MASK_ON_SUSPEND = (1 << 2), + IRQCHIP_ONOFFLINE_ENABLED = (1 << 3), + IRQCHIP_SKIP_SET_WAKE = (1 << 4), + IRQCHIP_ONESHOT_SAFE = (1 << 5), + IRQCHIP_EOI_THREADED = (1 << 6), + IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), + IRQCHIP_SUPPORTS_NMI = (1 << 8), + IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), }; #include -- cgit v1.2.3 From c6db31ffe202c3120147e9f3455a4dbc90546d39 Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Mon, 5 Oct 2020 18:39:37 +0300 Subject: ethtool: allow netdev driver to define phy tunables Define get/set phy tunable callbacks in ethtool ops. This will allow MAC drivers with integrated PHY still to implement these tunables. Reviewed-by: Andrew Lunn Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 060b20f0b20f..6408b446051f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -505,6 +505,10 @@ struct ethtool_ops { struct ethtool_fecparam *); void (*get_ethtool_phy_stats)(struct net_device *, struct ethtool_stats *, u64 *); + int (*get_phy_tunable)(struct net_device *, + const struct ethtool_tunable *, void *); + int (*set_phy_tunable)(struct net_device *, + const struct ethtool_tunable *, const void *); }; int ethtool_check_ops(const struct ethtool_ops *ops); -- cgit v1.2.3 From 451b05f413d3fd89ee84ae99a5029f619ed3cb78 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Mon, 5 Oct 2020 22:34:18 +0200 Subject: net: netdevice.h: sw_netstats_rx_add helper some drivers/network protocols update rx bytes/packets under u64_stats_update_begin/end sequence. Add a specific helper like dev_lstats_add() Signed-off-by: Fabian Frederick Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d126e36580c9..a0df43b13839 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2543,6 +2543,16 @@ struct pcpu_lstats { void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); +static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len) +{ + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_bytes += len; + tstats->rx_packets++; + u64_stats_update_end(&tstats->syncp); +} + static inline void dev_lstats_add(struct net_device *dev, unsigned int len) { struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); -- cgit v1.2.3 From ddcf3b70c5ae8444e920d28e30e7ad4e866c8015 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 5 Oct 2020 15:07:37 -0700 Subject: netlink: create helpers for checking type is an int There's a number of policies which check if type is a uint or sint. Factor the checking against the list of value sizes to a helper for easier reuse. v2: - new patch Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/netlink.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 5a5ff97cc596..c5aa46f379bc 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -362,20 +362,21 @@ struct nla_policy { #define NLA_POLICY_BITFIELD32(valid) \ { .type = NLA_BITFIELD32, .bitfield32_valid = valid } +#define __NLA_IS_UINT_TYPE(tp) \ + (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64) +#define __NLA_IS_SINT_TYPE(tp) \ + (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) + #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ - (__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 || \ - tp == NLA_U32 || tp == NLA_U64 || \ + (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ - (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16 || \ - tp == NLA_S32 || tp == NLA_S64) + tp) + (__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp) #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ - (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ - tp == NLA_S16 || tp == NLA_U16 || \ - tp == NLA_S32 || tp == NLA_U32 || \ - tp == NLA_S64 || tp == NLA_U64 || \ + (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ + __NLA_IS_SINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ -- cgit v1.2.3 From bdbb4e29df8b790db50cb73ce25d23543329f05f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 5 Oct 2020 15:07:38 -0700 Subject: netlink: add mask validation We don't have good validation policy for existing unsigned int attrs which serve as flags (for new ones we could use NLA_BITFIELD32). With increased use of policy dumping having the validation be expressed as part of the policy is important. Add validation policy in form of a mask of supported/valid bits. Support u64 in the uAPI to be future-proof, but really for now the embedded mask member can only hold 32 bits, so anything with bit 32+ set will always fail validation. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/netlink.h | 10 ++++++++++ include/uapi/linux/netlink.h | 2 ++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index c5aa46f379bc..2b9e41075f19 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -200,6 +200,7 @@ enum nla_policy_validation { NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, + NLA_VALIDATE_MASK, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, }; @@ -317,6 +318,7 @@ struct nla_policy { u16 len; union { const u32 bitfield32_valid; + const u32 mask; const char *reject_message; const struct nla_policy *nested_policy; struct netlink_range_validation *range; @@ -368,6 +370,8 @@ struct nla_policy { (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) +#define NLA_ENSURE_UINT_TYPE(tp) \ + (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp) #define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ tp == NLA_MSECS || \ @@ -416,6 +420,12 @@ struct nla_policy { .max = _max, \ } +#define NLA_POLICY_MASK(tp, _mask) { \ + .type = NLA_ENSURE_UINT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_MASK, \ + .mask = _mask, \ +} + #define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \ .type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \ .validation_type = NLA_VALIDATE_FUNCTION, \ diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index eac8a6a648ea..d02e472ba54c 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -331,6 +331,7 @@ enum netlink_attribute_type { * the index, if limited inside the nesting (U32) * @NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: valid mask for the * bitfield32 type (U32) + * @NL_POLICY_TYPE_ATTR_MASK: mask of valid bits for unsigned integers (U64) * @NL_POLICY_TYPE_ATTR_PAD: pad attribute for 64-bit alignment */ enum netlink_policy_type_attr { @@ -346,6 +347,7 @@ enum netlink_policy_type_attr { NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE, NL_POLICY_TYPE_ATTR_BITFIELD32_MASK, NL_POLICY_TYPE_ATTR_PAD, + NL_POLICY_TYPE_ATTR_MASK, /* keep last */ __NL_POLICY_TYPE_ATTR_MAX, -- cgit v1.2.3 From 2b0d3d3e4fcfb19d10f9a82910b8f0f05c56ee3e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 1 Oct 2020 23:48:41 +0800 Subject: percpu_ref: reduce memory footprint of percpu_ref in fast path 'struct percpu_ref' is often embedded into one user structure, and the instance is usually referenced in fast path, however actually only 'percpu_count_ptr' is needed in fast path. So move other fields into one new structure of 'percpu_ref_data', and allocate it dynamically via kzalloc(), then memory footprint of 'percpu_ref' in fast path is reduced a lot and becomes suitable to put into hot cacheline of user structure. Signed-off-by: Ming Lei Tested-by: Veronika Kabatova Reviewed-by: Christoph Hellwig Acked-by: Tejun Heo Cc: Sagi Grimberg Cc: Tejun Heo Cc: Christoph Hellwig Cc: Jens Axboe Cc: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/percpu-refcount.h | 52 +++++++++++++++++++---------------------- 1 file changed, 24 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 87d8a38bdea1..16c35a728b4c 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -92,18 +92,30 @@ enum { PERCPU_REF_ALLOW_REINIT = 1 << 2, }; -struct percpu_ref { +struct percpu_ref_data { atomic_long_t count; - /* - * The low bit of the pointer indicates whether the ref is in percpu - * mode; if set, then get/put will manipulate the atomic_t. - */ - unsigned long percpu_count_ptr; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; + struct percpu_ref *ref; +}; + +struct percpu_ref { + /* + * The low bit of the pointer indicates whether the ref is in percpu + * mode; if set, then get/put will manipulate the atomic_t. + */ + unsigned long percpu_count_ptr; + + /* + * 'percpu_ref' is often embedded into user structure, and only + * 'percpu_count_ptr' is required in fast path, move other fields + * into 'percpu_ref_data', so we can reduce memory footprint in + * fast path. + */ + struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, @@ -118,6 +130,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); +bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref @@ -191,7 +204,7 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else - atomic_long_add(nr, &ref->count); + atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } @@ -231,7 +244,7 @@ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, this_cpu_add(*percpu_count, nr); ret = true; } else { - ret = atomic_long_add_unless(&ref->count, nr, 0); + ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); @@ -279,7 +292,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { - ret = atomic_long_inc_not_zero(&ref->count); + ret = atomic_long_inc_not_zero(&ref->data->count); } rcu_read_unlock(); @@ -305,8 +318,8 @@ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); - else if (unlikely(atomic_long_sub_and_test(nr, &ref->count))) - ref->release(ref); + else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) + ref->data->release(ref); rcu_read_unlock(); } @@ -339,21 +352,4 @@ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } -/** - * percpu_ref_is_zero - test whether a percpu refcount reached zero - * @ref: percpu_ref to test - * - * Returns %true if @ref reached zero. - * - * This function is safe to call as long as @ref is between init and exit. - */ -static inline bool percpu_ref_is_zero(struct percpu_ref *ref) -{ - unsigned long __percpu *percpu_count; - - if (__ref_is_percpu(ref, &percpu_count)) - return false; - return !atomic_long_read(&ref->count); -} - #endif -- cgit v1.2.3 From 0549e87c30ae0d43d7e10424f2222bcd8bbe986d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 1 Oct 2020 23:48:42 +0800 Subject: block: move 'q_usage_counter' into front of 'request_queue' The field of 'q_usage_counter' is always fetched in fast path of every block driver, and move it into front of 'request_queue', so it can be fetched into 1st cacheline of 'request_queue' instance. Signed-off-by: Ming Lei Tested-by: Veronika Kabatova Reviewed-by: Christoph Hellwig Cc: Sagi Grimberg Cc: Tejun Heo Cc: Christoph Hellwig Cc: Jens Axboe Cc: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cf80e61b4c5e..5fc940423e5a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -397,6 +397,8 @@ struct request_queue { struct request *last_merge; struct elevator_queue *elevator; + struct percpu_ref q_usage_counter; + struct blk_queue_stats *stats; struct rq_qos *rq_qos; @@ -569,7 +571,6 @@ struct request_queue { * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; - struct percpu_ref q_usage_counter; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; -- cgit v1.2.3 From 92cf2fd156b273879198bb1d7e58851f822c481f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Oct 2020 09:07:17 +0200 Subject: block: remove the unused blk_integrity_merge_rq export Also move the definition from the public blkdev.h to the private block/blk.h header. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5fc940423e5a..6a6d9ea7420a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -extern bool blk_integrity_merge_rq(struct request_queue *, struct request *, - struct request *); extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, struct bio *); @@ -1795,12 +1793,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q { return 0; } -static inline bool blk_integrity_merge_rq(struct request_queue *rq, - struct request *r1, - struct request *r2) -{ - return true; -} static inline bool blk_integrity_merge_bio(struct request_queue *rq, struct request *r, struct bio *b) -- cgit v1.2.3 From d59da41998bc794441d7c039a059ed6eb0c2dc4d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Oct 2020 09:07:18 +0200 Subject: block: remove the unused blk_integrity_merge_bio export Also move the definition from the public blkdev.h to the private block/blk.h header. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6a6d9ea7420a..cda786fa4341 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, - struct bio *); static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { @@ -1793,12 +1791,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q { return 0; } -static inline bool blk_integrity_merge_bio(struct request_queue *rq, - struct request *r, - struct bio *b) -{ - return true; -} static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) -- cgit v1.2.3 From ca756120d4bcf28dfde5e3df8882153303d4010f Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Tue, 6 Oct 2020 08:48:55 +0200 Subject: ASoC: Intel: Remove haswell solution Newly added catpt solution found in sound/soc/intel/catpt is a direct replacement to sound/soc/intel/haswell. It covers all features supported by it and more - by aligning to recommended flows and requirement list based on Windows driver equivalent. No harm is done to userspace as catpt - similarly to haswell - loads no extenal topology files while sharing the exact same ADSP firmware binary. Given the above, existing haswell code is redundant so remove it. Signed-off-by: Cezary Rojewski Reviewed-by: Andy Shevchenko Acked-by: Liam Girdwood Link: https://lore.kernel.org/r/20201006064907.16277-2-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/trace/events/hswadsp.h | 385 ----------------------------------------- 1 file changed, 385 deletions(-) delete mode 100644 include/trace/events/hswadsp.h (limited to 'include') diff --git a/include/trace/events/hswadsp.h b/include/trace/events/hswadsp.h deleted file mode 100644 index 939d7a09d73f..000000000000 --- a/include/trace/events/hswadsp.h +++ /dev/null @@ -1,385 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM hswadsp - -#if !defined(_TRACE_HSWADSP_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_HSWADSP_H - -#include -#include -#include - -struct sst_hsw; -struct sst_hsw_stream; -struct sst_hsw_ipc_stream_free_req; -struct sst_hsw_ipc_volume_req; -struct sst_hsw_ipc_stream_alloc_req; -struct sst_hsw_audio_data_format_ipc; -struct sst_hsw_ipc_stream_info_reply; -struct sst_hsw_ipc_device_config_req; - -DECLARE_EVENT_CLASS(sst_irq, - - TP_PROTO(uint32_t status, uint32_t mask), - - TP_ARGS(status, mask), - - TP_STRUCT__entry( - __field( unsigned int, status ) - __field( unsigned int, mask ) - ), - - TP_fast_assign( - __entry->status = status; - __entry->mask = mask; - ), - - TP_printk("status 0x%8.8x mask 0x%8.8x", - (unsigned int)__entry->status, (unsigned int)__entry->mask) -); - -DEFINE_EVENT(sst_irq, sst_irq_busy, - - TP_PROTO(unsigned int status, unsigned int mask), - - TP_ARGS(status, mask) - -); - -DEFINE_EVENT(sst_irq, sst_irq_done, - - TP_PROTO(unsigned int status, unsigned int mask), - - TP_ARGS(status, mask) - -); - -DECLARE_EVENT_CLASS(ipc, - - TP_PROTO(const char *name, int val), - - TP_ARGS(name, val), - - TP_STRUCT__entry( - __string( name, name ) - __field( unsigned int, val ) - ), - - TP_fast_assign( - __assign_str(name, name); - __entry->val = val; - ), - - TP_printk("%s 0x%8.8x", __get_str(name), (unsigned int)__entry->val) - -); - -DEFINE_EVENT(ipc, ipc_request, - - TP_PROTO(const char *name, int val), - - TP_ARGS(name, val) - -); - -DEFINE_EVENT(ipc, ipc_reply, - - TP_PROTO(const char *name, int val), - - TP_ARGS(name, val) - -); - -DEFINE_EVENT(ipc, ipc_pending_reply, - - TP_PROTO(const char *name, int val), - - TP_ARGS(name, val) - -); - -DEFINE_EVENT(ipc, ipc_notification, - - TP_PROTO(const char *name, int val), - - TP_ARGS(name, val) - -); - -DEFINE_EVENT(ipc, ipc_error, - - TP_PROTO(const char *name, int val), - - TP_ARGS(name, val) - -); - -DECLARE_EVENT_CLASS(stream_position, - - TP_PROTO(unsigned int id, unsigned int pos), - - TP_ARGS(id, pos), - - TP_STRUCT__entry( - __field( unsigned int, id ) - __field( unsigned int, pos ) - ), - - TP_fast_assign( - __entry->id = id; - __entry->pos = pos; - ), - - TP_printk("id %d position 0x%x", - (unsigned int)__entry->id, (unsigned int)__entry->pos) -); - -DEFINE_EVENT(stream_position, stream_read_position, - - TP_PROTO(unsigned int id, unsigned int pos), - - TP_ARGS(id, pos) - -); - -DEFINE_EVENT(stream_position, stream_write_position, - - TP_PROTO(unsigned int id, unsigned int pos), - - TP_ARGS(id, pos) - -); - -TRACE_EVENT(hsw_stream_buffer, - - TP_PROTO(struct sst_hsw_stream *stream), - - TP_ARGS(stream), - - TP_STRUCT__entry( - __field( int, id ) - __field( int, pt_addr ) - __field( int, num_pages ) - __field( int, ring_size ) - __field( int, ring_offset ) - __field( int, first_pfn ) - ), - - TP_fast_assign( - __entry->id = stream->host_id; - __entry->pt_addr = stream->request.ringinfo.ring_pt_address; - __entry->num_pages = stream->request.ringinfo.num_pages; - __entry->ring_size = stream->request.ringinfo.ring_size; - __entry->ring_offset = stream->request.ringinfo.ring_offset; - __entry->first_pfn = stream->request.ringinfo.ring_first_pfn; - ), - - TP_printk("stream %d ring addr 0x%x pages %d size 0x%x offset 0x%x PFN 0x%x", - (int) __entry->id, (int)__entry->pt_addr, - (int)__entry->num_pages, (int)__entry->ring_size, - (int)__entry->ring_offset, (int)__entry->first_pfn) -); - -TRACE_EVENT(hsw_stream_alloc_reply, - - TP_PROTO(struct sst_hsw_stream *stream), - - TP_ARGS(stream), - - TP_STRUCT__entry( - __field( int, id ) - __field( int, stream_id ) - __field( int, mixer_id ) - __field( int, peak0 ) - __field( int, peak1 ) - __field( int, vol0 ) - __field( int, vol1 ) - ), - - TP_fast_assign( - __entry->id = stream->host_id; - __entry->stream_id = stream->reply.stream_hw_id; - __entry->mixer_id = stream->reply.mixer_hw_id; - __entry->peak0 = stream->reply.peak_meter_register_address[0]; - __entry->peak1 = stream->reply.peak_meter_register_address[1]; - __entry->vol0 = stream->reply.volume_register_address[0]; - __entry->vol1 = stream->reply.volume_register_address[1]; - ), - - TP_printk("stream %d hw id %d mixer %d peak 0x%x:0x%x vol 0x%x,0x%x", - (int) __entry->id, (int) __entry->stream_id, (int)__entry->mixer_id, - (int)__entry->peak0, (int)__entry->peak1, - (int)__entry->vol0, (int)__entry->vol1) -); - -TRACE_EVENT(hsw_mixer_info_reply, - - TP_PROTO(struct sst_hsw_ipc_stream_info_reply *reply), - - TP_ARGS(reply), - - TP_STRUCT__entry( - __field( int, mixer_id ) - __field( int, peak0 ) - __field( int, peak1 ) - __field( int, vol0 ) - __field( int, vol1 ) - ), - - TP_fast_assign( - __entry->mixer_id = reply->mixer_hw_id; - __entry->peak0 = reply->peak_meter_register_address[0]; - __entry->peak1 = reply->peak_meter_register_address[1]; - __entry->vol0 = reply->volume_register_address[0]; - __entry->vol1 = reply->volume_register_address[1]; - ), - - TP_printk("mixer id %d peak 0x%x:0x%x vol 0x%x,0x%x", - (int)__entry->mixer_id, - (int)__entry->peak0, (int)__entry->peak1, - (int)__entry->vol0, (int)__entry->vol1) -); - -TRACE_EVENT(hsw_stream_data_format, - - TP_PROTO(struct sst_hsw_stream *stream, - struct sst_hsw_audio_data_format_ipc *req), - - TP_ARGS(stream, req), - - TP_STRUCT__entry( - __field( uint32_t, id ) - __field( uint32_t, frequency ) - __field( uint32_t, bitdepth ) - __field( uint32_t, map ) - __field( uint32_t, config ) - __field( uint32_t, style ) - __field( uint8_t, ch_num ) - __field( uint8_t, valid_bit ) - ), - - TP_fast_assign( - __entry->id = stream->host_id; - __entry->frequency = req->frequency; - __entry->bitdepth = req->bitdepth; - __entry->map = req->map; - __entry->config = req->config; - __entry->style = req->style; - __entry->ch_num = req->ch_num; - __entry->valid_bit = req->valid_bit; - ), - - TP_printk("stream %d freq %d depth %d map 0x%x config 0x%x style 0x%x ch %d bits %d", - (int) __entry->id, (uint32_t)__entry->frequency, - (uint32_t)__entry->bitdepth, (uint32_t)__entry->map, - (uint32_t)__entry->config, (uint32_t)__entry->style, - (uint8_t)__entry->ch_num, (uint8_t)__entry->valid_bit) -); - -TRACE_EVENT(hsw_stream_alloc_request, - - TP_PROTO(struct sst_hsw_stream *stream, - struct sst_hsw_ipc_stream_alloc_req *req), - - TP_ARGS(stream, req), - - TP_STRUCT__entry( - __field( uint32_t, id ) - __field( uint8_t, path_id ) - __field( uint8_t, stream_type ) - __field( uint8_t, format_id ) - ), - - TP_fast_assign( - __entry->id = stream->host_id; - __entry->path_id = req->path_id; - __entry->stream_type = req->stream_type; - __entry->format_id = req->format_id; - ), - - TP_printk("stream %d path %d type %d format %d", - (int) __entry->id, (uint8_t)__entry->path_id, - (uint8_t)__entry->stream_type, (uint8_t)__entry->format_id) -); - -TRACE_EVENT(hsw_stream_free_req, - - TP_PROTO(struct sst_hsw_stream *stream, - struct sst_hsw_ipc_stream_free_req *req), - - TP_ARGS(stream, req), - - TP_STRUCT__entry( - __field( int, id ) - __field( int, stream_id ) - ), - - TP_fast_assign( - __entry->id = stream->host_id; - __entry->stream_id = req->stream_id; - ), - - TP_printk("stream %d hw id %d", - (int) __entry->id, (int) __entry->stream_id) -); - -TRACE_EVENT(hsw_volume_req, - - TP_PROTO(struct sst_hsw_stream *stream, - struct sst_hsw_ipc_volume_req *req), - - TP_ARGS(stream, req), - - TP_STRUCT__entry( - __field( int, id ) - __field( uint32_t, channel ) - __field( uint32_t, target_volume ) - __field( uint64_t, curve_duration ) - __field( uint32_t, curve_type ) - ), - - TP_fast_assign( - __entry->id = stream->host_id; - __entry->channel = req->channel; - __entry->target_volume = req->target_volume; - __entry->curve_duration = req->curve_duration; - __entry->curve_type = req->curve_type; - ), - - TP_printk("stream %d chan 0x%x vol %d duration %llu type %d", - (int) __entry->id, (uint32_t) __entry->channel, - (uint32_t)__entry->target_volume, - (uint64_t)__entry->curve_duration, - (uint32_t)__entry->curve_type) -); - -TRACE_EVENT(hsw_device_config_req, - - TP_PROTO(struct sst_hsw_ipc_device_config_req *req), - - TP_ARGS(req), - - TP_STRUCT__entry( - __field( uint32_t, ssp ) - __field( uint32_t, clock_freq ) - __field( uint32_t, mode ) - __field( uint16_t, clock_divider ) - ), - - TP_fast_assign( - __entry->ssp = req->ssp_interface; - __entry->clock_freq = req->clock_frequency; - __entry->mode = req->mode; - __entry->clock_divider = req->clock_divider; - ), - - TP_printk("SSP %d Freq %d mode %d div %d", - (uint32_t)__entry->ssp, - (uint32_t)__entry->clock_freq, (uint32_t)__entry->mode, - (uint32_t)__entry->clock_divider) -); - -#endif /* _TRACE_HSWADSP_H */ - -/* This part must be outside protection */ -#include -- cgit v1.2.3 From 3056cb0082feccee9a0012440ee5e4ca6a6e80ac Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Tue, 6 Oct 2020 08:48:57 +0200 Subject: ASoC: Intel: Remove rt5640 support for baytrail solution byt-rt5640 is deprecated in favor of bytcr_rt5640 used by sound/soc/intel/atom and SOF solutions both. Remove redundant machine board and all related code. Signed-off-by: Cezary Rojewski Reviewed-by: Andy Shevchenko Acked-by: Liam Girdwood Link: https://lore.kernel.org/r/20201006064907.16277-4-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi-intel-match.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h index ab6f75a86611..5c49e7d78002 100644 --- a/include/sound/soc-acpi-intel-match.h +++ b/include/sound/soc-acpi-intel-match.h @@ -16,7 +16,6 @@ */ extern struct snd_soc_acpi_mach snd_soc_acpi_intel_haswell_machines[]; extern struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[]; -extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_legacy_machines[]; extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_machines[]; extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cherrytrail_machines[]; extern struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[]; -- cgit v1.2.3 From bdb01301f3ea51a59eff252b06643fc1fe843e57 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 19 Aug 2020 23:20:30 +0800 Subject: scsi: Add host and host template flag 'host_tagset' Add Host and host template flag 'host_tagset' so hostwide tagset can be shared on multiple reply queues after the SCSI device's reply queue is converted to blk-mq hw queue. [jpg: Update comment on .can_queue and add Scsi_Host.host_tagset] Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/scsi/scsi_host.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 46ef8cccc982..701f178b20ae 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -436,6 +436,9 @@ struct scsi_host_template { /* True if the controller does not support WRITE SAME */ unsigned no_write_same:1; + /* True if the host uses host-wide tagspace */ + unsigned host_tagset:1; + /* * Countdown for host blocking with no commands outstanding. */ @@ -603,7 +606,8 @@ struct Scsi_Host { * * Note: it is assumed that each hardware queue has a queue depth of * can_queue. In other words, the total queue depth per host - * is nr_hw_queues * can_queue. + * is nr_hw_queues * can_queue. However, for when host_tagset is set, + * the total queue depth is can_queue. */ unsigned nr_hw_queues; unsigned active_mode:2; @@ -634,6 +638,9 @@ struct Scsi_Host { /* The controller does not support WRITE SAME */ unsigned no_write_same:1; + /* True if the host uses host-wide tagspace */ + unsigned host_tagset:1; + /* Host responded with short (<36 bytes) INQUIRY result */ unsigned short_inquiry:1; -- cgit v1.2.3 From eb88531bdbfaafb827192d1fc6c5a3fcc4fadd96 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sun, 27 Sep 2020 01:24:31 +0900 Subject: can: raw: add missing error queue support Error queue are not yet implemented in CAN-raw sockets. The problem: a userland call to recvmsg(soc, msg, MSG_ERRQUEUE) on a CAN-raw socket would unqueue messages from the normal queue without any kind of error or warning. As such, it prevented CAN drivers from using the functionalities that relies on the error queue such as skb_tx_timestamp(). SCM_CAN_RAW_ERRQUEUE is defined as the type for the CAN raw error queue. SCM stands for "Socket control messages". The name is inspired from SCM_J1939_ERRQUEUE of include/uapi/linux/can/j1939.h. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20200926162527.270030-1-mailhol.vincent@wanadoo.fr Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/raw.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h index 6a11d308eb5c..3386aa81fdf2 100644 --- a/include/uapi/linux/can/raw.h +++ b/include/uapi/linux/can/raw.h @@ -49,6 +49,9 @@ #include #define SOL_CAN_RAW (SOL_CAN_BASE + CAN_RAW) +enum { + SCM_CAN_RAW_ERRQUEUE = 1, +}; /* for socket options affecting the socket (not the global system) */ -- cgit v1.2.3 From f55a52bb2cdbc5a92ca209d0ada90a490a188f58 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 3 Oct 2020 00:41:46 +0900 Subject: can: dev: fix type of get_can_dlc() and get_canfd_dlc() macros The macros get_can_dlc() and get_canfd_dlc() are not visible in userland. As such, type u8 should be preferred over type __u8. Reference: https://lkml.org/lkml/2020/10/1/708 Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20201002154219.4887-3-mailhol.vincent@wanadoo.fr Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index ed0482b2f4b2..f8975d0b90bb 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -84,13 +84,13 @@ struct can_priv { /* * get_can_dlc(value) - helper macro to cast a given data length code (dlc) - * to __u8 and ensure the dlc value to be max. 8 bytes. + * to u8 and ensure the dlc value to be max. 8 bytes. * * To be used in the CAN netdriver receive path to ensure conformance with * ISO 11898-1 Chapter 8.4.2.3 (DLC field) */ -#define get_can_dlc(i) (min_t(__u8, (i), CAN_MAX_DLC)) -#define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) +#define get_can_dlc(i) (min_t(u8, (i), CAN_MAX_DLC)) +#define get_canfd_dlc(i) (min_t(u8, (i), CANFD_MAX_DLC)) /* Check for outgoing skbs that have not been created by the CAN subsystem */ static inline bool can_skb_headroom_valid(struct net_device *dev, -- cgit v1.2.3 From 5a0677110b73dd3e1766f89159701bfe8ac06808 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 6 Oct 2020 15:49:31 +0900 Subject: arm/arm64: xen: Fix to convert percpu address to gfn correctly Use per_cpu_ptr_to_phys() instead of virt_to_phys() for per-cpu address conversion. In xen_starting_cpu(), per-cpu xen_vcpu_info address is converted to gfn by virt_to_gfn() macro. However, since the virt_to_gfn(v) assumes the given virtual address is in linear mapped kernel memory area, it can not convert the per-cpu memory if it is allocated on vmalloc area. This depends on CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK. If it is enabled, the first chunk of percpu memory is linear mapped. In the other case, that is allocated from vmalloc area. Moreover, if the first chunk of percpu has run out until allocating xen_vcpu_info, it will be allocated on the 2nd chunk, which is based on kernel memory or vmalloc memory (depends on CONFIG_NEED_PER_CPU_KM). Without this fix and kernel configured to use vmalloc area for the percpu memory, the Dom0 kernel will fail to boot with following errors. [ 0.466172] Xen: initializing cpu0 [ 0.469601] ------------[ cut here ]------------ [ 0.474295] WARNING: CPU: 0 PID: 1 at arch/arm64/xen/../../arm/xen/enlighten.c:153 xen_starting_cpu+0x160/0x180 [ 0.484435] Modules linked in: [ 0.487565] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.9.0-rc4+ #4 [ 0.493895] Hardware name: Socionext Developer Box (DT) [ 0.499194] pstate: 00000005 (nzcv daif -PAN -UAO BTYPE=--) [ 0.504836] pc : xen_starting_cpu+0x160/0x180 [ 0.509263] lr : xen_starting_cpu+0xb0/0x180 [ 0.513599] sp : ffff8000116cbb60 [ 0.516984] x29: ffff8000116cbb60 x28: ffff80000abec000 [ 0.522366] x27: 0000000000000000 x26: 0000000000000000 [ 0.527754] x25: ffff80001156c000 x24: fffffdffbfcdb600 [ 0.533129] x23: 0000000000000000 x22: 0000000000000000 [ 0.538511] x21: ffff8000113a99c8 x20: ffff800010fe4f68 [ 0.543892] x19: ffff8000113a9988 x18: 0000000000000010 [ 0.549274] x17: 0000000094fe0f81 x16: 00000000deadbeef [ 0.554655] x15: ffffffffffffffff x14: 0720072007200720 [ 0.560037] x13: 0720072007200720 x12: 0720072007200720 [ 0.565418] x11: 0720072007200720 x10: 0720072007200720 [ 0.570801] x9 : ffff8000100fbdc0 x8 : ffff800010715208 [ 0.576182] x7 : 0000000000000054 x6 : ffff00001b790f00 [ 0.581564] x5 : ffff800010bbf880 x4 : 0000000000000000 [ 0.586945] x3 : 0000000000000000 x2 : ffff80000abec000 [ 0.592327] x1 : 000000000000002f x0 : 0000800000000000 [ 0.597716] Call trace: [ 0.600232] xen_starting_cpu+0x160/0x180 [ 0.604309] cpuhp_invoke_callback+0xac/0x640 [ 0.608736] cpuhp_issue_call+0xf4/0x150 [ 0.612728] __cpuhp_setup_state_cpuslocked+0x128/0x2c8 [ 0.618030] __cpuhp_setup_state+0x84/0xf8 [ 0.622192] xen_guest_init+0x324/0x364 [ 0.626097] do_one_initcall+0x54/0x250 [ 0.630003] kernel_init_freeable+0x12c/0x2c8 [ 0.634428] kernel_init+0x1c/0x128 [ 0.637988] ret_from_fork+0x10/0x18 [ 0.641635] ---[ end trace d95b5309a33f8b27 ]--- [ 0.646337] ------------[ cut here ]------------ [ 0.651005] kernel BUG at arch/arm64/xen/../../arm/xen/enlighten.c:158! [ 0.657697] Internal error: Oops - BUG: 0 [#1] SMP [ 0.662548] Modules linked in: [ 0.665676] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 5.9.0-rc4+ #4 [ 0.673398] Hardware name: Socionext Developer Box (DT) [ 0.678695] pstate: 00000005 (nzcv daif -PAN -UAO BTYPE=--) [ 0.684338] pc : xen_starting_cpu+0x178/0x180 [ 0.688765] lr : xen_starting_cpu+0x144/0x180 [ 0.693188] sp : ffff8000116cbb60 [ 0.696573] x29: ffff8000116cbb60 x28: ffff80000abec000 [ 0.701955] x27: 0000000000000000 x26: 0000000000000000 [ 0.707344] x25: ffff80001156c000 x24: fffffdffbfcdb600 [ 0.712718] x23: 0000000000000000 x22: 0000000000000000 [ 0.718107] x21: ffff8000113a99c8 x20: ffff800010fe4f68 [ 0.723481] x19: ffff8000113a9988 x18: 0000000000000010 [ 0.728863] x17: 0000000094fe0f81 x16: 00000000deadbeef [ 0.734245] x15: ffffffffffffffff x14: 0720072007200720 [ 0.739626] x13: 0720072007200720 x12: 0720072007200720 [ 0.745008] x11: 0720072007200720 x10: 0720072007200720 [ 0.750390] x9 : ffff8000100fbdc0 x8 : ffff800010715208 [ 0.755771] x7 : 0000000000000054 x6 : ffff00001b790f00 [ 0.761153] x5 : ffff800010bbf880 x4 : 0000000000000000 [ 0.766534] x3 : 0000000000000000 x2 : 00000000deadbeef [ 0.771916] x1 : 00000000deadbeef x0 : ffffffffffffffea [ 0.777304] Call trace: [ 0.779819] xen_starting_cpu+0x178/0x180 [ 0.783898] cpuhp_invoke_callback+0xac/0x640 [ 0.788325] cpuhp_issue_call+0xf4/0x150 [ 0.792317] __cpuhp_setup_state_cpuslocked+0x128/0x2c8 [ 0.797619] __cpuhp_setup_state+0x84/0xf8 [ 0.801779] xen_guest_init+0x324/0x364 [ 0.805683] do_one_initcall+0x54/0x250 [ 0.809590] kernel_init_freeable+0x12c/0x2c8 [ 0.814016] kernel_init+0x1c/0x128 [ 0.817583] ret_from_fork+0x10/0x18 [ 0.821226] Code: d0006980 f9427c00 cb000300 17ffffea (d4210000) [ 0.827415] ---[ end trace d95b5309a33f8b28 ]--- [ 0.832076] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 0.839815] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]--- Signed-off-by: Masami Hiramatsu Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/160196697165.60224.17470743378683334995.stgit@devnote2 Signed-off-by: Juergen Gross --- include/xen/arm/page.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index 39df751d0dc4..ac1b65470563 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -83,6 +83,9 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn) }) #define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) +#define percpu_to_gfn(v) \ + (pfn_to_gfn(per_cpu_ptr_to_phys(v) >> XEN_PAGE_SHIFT)) + /* Only used in PV code. But ARM guests are always HVM. */ static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr) { -- cgit v1.2.3 From 6fcd669514794da08ce6bfa272b6ec9b33cb543d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Aug 2020 09:56:58 +0200 Subject: block: optimize blk_queue_zoned_model for !CONFIG_BLK_DEV_ZONED Always return BLK_ZONED_NONE if zoned device support is not enabled. This allows various compiler optimizations including the dead code elimination that we so like for avoiding ifdefs. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Reviewed-by: Damien Le Moal --- include/linux/blkdev.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8e77f12de522..1b81b2766858 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -692,7 +692,9 @@ static inline bool queue_is_mq(struct request_queue *q) static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { - return q->limits.zoned; + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + return q->limits.zoned; + return BLK_ZONED_NONE; } static inline bool blk_queue_is_zoned(struct request_queue *q) -- cgit v1.2.3 From 200da27ab32d89ca43bd8ef010f84b205e5c780a Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 6 Oct 2020 13:11:15 -0700 Subject: LSM: Fix type of id parameter in kernel_post_load_data prototype Clang warns: security/security.c:1716:59: warning: implicit conversion from enumeration type 'enum kernel_load_data_id' to different enumeration type 'enum kernel_read_file_id' [-Wenum-conversion] ret = call_int_hook(kernel_post_load_data, 0, buf, size, id, ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~ security/security.c:715:22: note: expanded from macro 'call_int_hook' RC = P->hook.FUNC(__VA_ARGS__); \ ~ ^~~~~~~~~~~ 1 warning generated. There is a mismatch between the id parameter type in security_kernel_post_load_data and the function pointer prototype that is created by the LSM_HOOK macro in the security_list_options union. Fix the type in the LSM_HOOK macro as 'enum kernel_load_data_id' is what is expected. Fixes: b64fcae74b6d ("LSM: Introduce kernel_post_load_data() hook") Acked-by: Kees Cook Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20201006201115.716550-1-natechancellor@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/lsm_hook_defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index d67cb3502310..32a940117e7a 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -186,7 +186,7 @@ LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents) LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size, - enum kernel_read_file_id id, char *description) + enum kernel_load_data_id id, char *description) LSM_HOOK(int, 0, kernel_read_file, struct file *file, enum kernel_read_file_id id, bool contents) LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, -- cgit v1.2.3 From 849facea92fa68d9292f9b06d7c4ee9e7a06b8dc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 7 Oct 2020 11:04:08 +0200 Subject: dma-direct: simplify the DMA_ATTR_NO_KERNEL_MAPPING handling Use and entirely separate code path for the DMA_ATTR_NO_KERNEL_MAPPING path. This avoids any confusion about the ret type, and avoids lots of attr checks and helpers that can be significantly simplified now. It also ensures that common handling is applied to architetures still using the arch alloc/free hooks. Signed-off-by: Christoph Hellwig --- include/linux/dma-map-ops.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 33c6e24707a9..8029f7e04145 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -219,19 +219,6 @@ static inline bool dev_is_dma_coherent(struct device *dev) } #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ -/* - * Check if an allocation needs to be marked uncached to be coherent. - */ -static __always_inline bool dma_alloc_need_uncached(struct device *dev, - unsigned long attrs) -{ - if (dev_is_dma_coherent(dev)) - return false; - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) - return false; - return true; -} - void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, -- cgit v1.2.3 From c0ab7ffce275d3f83bd253c70889c28821d4a41d Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 6 Oct 2020 14:09:09 -0700 Subject: x86/mce: Recover from poison found while copying from user space Existing kernel code can only recover from a machine check on code that is tagged in the exception table with a fault handling recovery path. Add two new fields in the task structure to pass information from machine check handler to the "task_work" that is queued to run before the task returns to user mode: + mce_vaddr: will be initialized to the user virtual address of the fault in the case where the fault occurred in the kernel copying data from a user address. This is so that kill_me_maybe() can provide that information to the user SIGBUS handler. + mce_kflags: copy of the struct mce.kflags needed by kill_me_maybe() to determine if mce_vaddr is applicable to this error. Add code to recover from a machine check while copying data from user space to the kernel. Action for this case is the same as if the user touched the poison directly; unmap the page and send a SIGBUS to the task. Use a new helper function to share common code between the "fault in user mode" case and the "fault while copying from user" case. New code paths will be activated by the next patch which sets MCE_IN_KERNEL_COPYIN. Suggested-by: Borislav Petkov Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201006210910.21062-6-tony.luck@intel.com --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 93ecd930efd3..2cbba3e2b150 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1308,6 +1308,8 @@ struct task_struct { #endif #ifdef CONFIG_X86_MCE + void __user *mce_vaddr; + __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, -- cgit v1.2.3 From 437490fed3b0c9ae21af8f70e0f338d34560842b Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 28 Jul 2020 09:42:49 +0800 Subject: btrfs: tracepoints: output proper root owner for trace_find_free_extent() The current trace event always output result like this: find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=4(METADATA) find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=4(METADATA) find_free_extent: root=2(EXTENT_TREE) len=8192 empty_size=0 flags=1(DATA) find_free_extent: root=2(EXTENT_TREE) len=8192 empty_size=0 flags=1(DATA) find_free_extent: root=2(EXTENT_TREE) len=4096 empty_size=0 flags=1(DATA) find_free_extent: root=2(EXTENT_TREE) len=4096 empty_size=0 flags=1(DATA) T's saying we're allocating data extent for EXTENT tree, which is not even possible. It's because we always use EXTENT tree as the owner for trace_find_free_extent() without using the @root from btrfs_reserve_extent(). This patch will change the parameter to use proper @root for trace_find_free_extent(): Now it looks much better: find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP) find_free_extent: root=5(FS_TREE) len=8192 empty_size=0 flags=1(DATA) find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=1(DATA) find_free_extent: root=5(FS_TREE) len=4096 empty_size=0 flags=1(DATA) find_free_extent: root=5(FS_TREE) len=8192 empty_size=0 flags=1(DATA) find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP) find_free_extent: root=7(CSUM_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP) find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP) find_free_extent: root=1(ROOT_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP) Reported-by: Hans van Kranenburg CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 863335ecb7e8..b9241836d4f7 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1176,25 +1176,27 @@ DEFINE_EVENT(btrfs__reserved_extent, btrfs_reserved_extent_free, TRACE_EVENT(find_free_extent, - TP_PROTO(const struct btrfs_fs_info *fs_info, u64 num_bytes, + TP_PROTO(const struct btrfs_root *root, u64 num_bytes, u64 empty_size, u64 data), - TP_ARGS(fs_info, num_bytes, empty_size, data), + TP_ARGS(root, num_bytes, empty_size, data), TP_STRUCT__entry_btrfs( + __field( u64, root_objectid ) __field( u64, num_bytes ) __field( u64, empty_size ) __field( u64, data ) ), - TP_fast_assign_btrfs(fs_info, + TP_fast_assign_btrfs(root->fs_info, + __entry->root_objectid = root->root_key.objectid; __entry->num_bytes = num_bytes; __entry->empty_size = empty_size; __entry->data = data; ), TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s)", - show_root_type(BTRFS_EXTENT_TREE_OBJECTID), + show_root_type(__entry->root_objectid), __entry->num_bytes, __entry->empty_size, __entry->data, __print_flags((unsigned long)__entry->data, "|", BTRFS_GROUP_FLAGS)) -- cgit v1.2.3 From acbf1dd0fcbd10c67826a19958f55a053b32f532 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 31 Aug 2020 14:42:40 +0300 Subject: btrfs: make ordered extent tracepoint take btrfs_inode Reviewed-by: Johannes Thumshirn Reviewed-by: Josef Bacik Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index b9241836d4f7..8d311062d376 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -510,7 +510,7 @@ DEFINE_EVENT( DECLARE_EVENT_CLASS(btrfs__ordered_extent, - TP_PROTO(const struct inode *inode, + TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered), @@ -529,8 +529,8 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, __field( u64, truncated_len ) ), - TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), - __entry->ino = btrfs_ino(BTRFS_I(inode)); + TP_fast_assign_btrfs(inode->root->fs_info, + __entry->ino = btrfs_ino(inode); __entry->file_offset = ordered->file_offset; __entry->start = ordered->disk_bytenr; __entry->len = ordered->num_bytes; @@ -539,8 +539,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, __entry->flags = ordered->flags; __entry->compress_type = ordered->compress_type; __entry->refs = refcount_read(&ordered->refs); - __entry->root_objectid = - BTRFS_I(inode)->root->root_key.objectid; + __entry->root_objectid = inode->root->root_key.objectid; __entry->truncated_len = ordered->truncated_len; ), @@ -563,7 +562,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_add, - TP_PROTO(const struct inode *inode, + TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) @@ -571,7 +570,7 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_add, DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_remove, - TP_PROTO(const struct inode *inode, + TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) @@ -579,7 +578,7 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_remove, DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_start, - TP_PROTO(const struct inode *inode, + TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) @@ -587,7 +586,7 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_start, DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_put, - TP_PROTO(const struct inode *inode, + TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) -- cgit v1.2.3 From 2c53a14dd30124de9468316933715deaf7443096 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 15 Sep 2020 13:35:27 +0800 Subject: btrfs: use own btree inode io_tree owner id Btree inode is special compared to all other inode extent io_trees, although it has a btrfs inode, it doesn't have the track_uptodate bit at all. This means a lot of things like extent locking doesn't even need to be applied to btree io tree. Since it's so special, adds a new owner value for it to make debuging a little easier. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 8d311062d376..ecd24c719de4 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -79,6 +79,7 @@ struct btrfs_space_info; #define IO_TREE_OWNER \ EM( IO_TREE_FS_PINNED_EXTENTS, "PINNED_EXTENTS") \ EM( IO_TREE_FS_EXCLUDED_EXTENTS, "EXCLUDED_EXTENTS") \ + EM( IO_TREE_BTREE_INODE_IO, "BTREE_INODE_IO") \ EM( IO_TREE_INODE_IO, "INODE_IO") \ EM( IO_TREE_INODE_IO_FAILURE, "INODE_IO_FAILURE") \ EM( IO_TREE_RELOC_BLOCKS, "RELOC_BLOCKS") \ -- cgit v1.2.3 From 1465af12e254a68706e110846f59cf0f09683184 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 22 Sep 2020 10:37:01 +0800 Subject: btrfs: tree-checker: fix false alert caused by legacy btrfs root item Commit 259ee7754b67 ("btrfs: tree-checker: Add ROOT_ITEM check") introduced btrfs root item size check, however btrfs root item has two versions, the legacy one which just ends before generation_v2 member, is smaller than current btrfs root item size. This caused btrfs kernel to reject valid but old tree root leaves. Fix this problem by also allowing legacy root item, since kernel can already handle them pretty well and upgrade to newer root item format when needed. Reported-by: Martin Steigerwald Fixes: 259ee7754b67 ("btrfs: tree-checker: Add ROOT_ITEM check") CC: stable@vger.kernel.org # 5.4+ Tested-By: Martin Steigerwald Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 9ba64ca6b4ac..6b885982ece6 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -4,6 +4,11 @@ #include #include +#ifdef __KERNEL__ +#include +#else +#include +#endif /* * This header contains the structure definitions and constants used @@ -644,6 +649,15 @@ struct btrfs_root_item { __le64 reserved[8]; /* for future */ } __attribute__ ((__packed__)); +/* + * Btrfs root item used to be smaller than current size. The old format ends + * at where member generation_v2 is. + */ +static inline __u32 btrfs_legacy_root_item_size(void) +{ + return offsetof(struct btrfs_root_item, generation_v2); +} + /* * this is used for both forward and backward root refs */ -- cgit v1.2.3 From c33fe275b530f1ce1ab99923d50eb399f53ed545 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Thu, 24 Sep 2020 11:39:08 -0500 Subject: fs: remove no longer used dio_end_io() Since we removed the last user of dio_end_io() when btrfs got converted to iomap infrastructure ("btrfs: switch to iomap for direct IO"), remove the helper function dio_end_io(). Reviewed-by: Nikolay Borisov Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Josef Bacik Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a08..8e2842a9c0b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3079,8 +3079,6 @@ enum { DIO_SKIP_HOLES = 0x02, }; -void dio_end_io(struct bio *bio); - ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, -- cgit v1.2.3 From dcb5cdf60a1fbbdb3b4dd2abc562206481f09ef1 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Sat, 3 Oct 2020 13:19:42 +0530 Subject: powerpc/perf/hv-gpci: Add cpu hotplug support Patch here adds cpu hotplug functions to hv_gpci pmu. A new cpuhp_state "CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE" enum is added. The online callback function updates the cpumask only if its empty. As the primary intention of adding hotplug support is to designate a CPU to make HCALL to collect the counter data. The offline function test and clear corresponding cpu in a cpumask and update cpumask to any other active cpu. Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201003074943.338618-4-kjain@linux.ibm.com --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3215023d4852..5d08ed922510 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -183,6 +183,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE, + CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, -- cgit v1.2.3 From dd841a749d1ded8e2e5facc4242ee0b6779fc0cb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 14 Jun 2020 06:07:10 -0400 Subject: radix tree test suite: Fix compilation Introducing local_lock broke compilation; fix it all up. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/radix-tree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index c2a9f7c90727..5c85059a92ba 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From fe6f0cdc49263ae61cd3d33399662808c2398e86 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 7 Oct 2020 21:35:08 +0900 Subject: block: soft limit zone-append sectors as well Martin rightfully noted that for normal filesystem IO we have soft limits in place, to prevent them from getting too big and not lead to unpredictable latencies. For zone append we only have the hardware limit in place. Cap the max sectors we submit via zone-append to the maximal number of sectors if the second limit is lower. Reported-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/linux-btrfs/yq1k0w8g3rw.fsf@ca-mkp.ca.oracle.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cda786fa4341..6bd667c34777 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1407,7 +1407,10 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) { - return q->limits.max_zone_append_sectors; + + const struct queue_limits *l = &q->limits; + + return min(l->max_zone_append_sectors, l->max_sectors); } static inline unsigned queue_logical_block_size(const struct request_queue *q) -- cgit v1.2.3 From 24a1877286822293684ef3f7bada4ea48a6e129e Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 24 Sep 2020 17:48:51 +0200 Subject: locking/seqlock: Tweak DEFINE_SEQLOCK() kernel doc ctags creates a warning: |ctags: Warning: include/linux/seqlock.h:738: null expansion of name pattern "\2" The DEFINE_SEQLOCK() macro is passed to ctags and being told to expect an argument. Add a dummy argument to keep ctags quiet. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Link: https://lkml.kernel.org/r/20200924154851.skmswuyj322yuz4g@linutronix.de --- include/linux/seqlock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 76e44e6c0100..ac5b07f558b0 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -821,7 +821,7 @@ typedef struct { } while (0) /** - * DEFINE_SEQLOCK() - Define a statically allocated seqlock_t + * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ -- cgit v1.2.3 From 49f3d12b0f70ea867b891ad2a97f6e51bb564e18 Mon Sep 17 00:00:00 2001 From: Jakub Wilk Date: Wed, 7 Oct 2020 07:57:17 +0200 Subject: bpf: Fix typo in uapi/linux/bpf.h Reported-by: Samanta Navarro Signed-off-by: Jakub Wilk Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201007055717.7319-1-jwilk@jwilk.net --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c446394135be..d83561e8cd2c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2253,7 +2253,7 @@ union bpf_attr { * Description * This helper is used in programs implementing policies at the * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. - * if the verdeict eBPF program returns **SK_PASS**), redirect it + * if the verdict eBPF program returns **SK_PASS**), redirect it * to the socket referenced by *map* (of type * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and * egress interfaces can be used for redirection. The -- cgit v1.2.3 From cf1f08cac375630af6b6307907a3fc20fcf847c7 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 17 Apr 2020 11:00:24 -0400 Subject: SUNRPC: Implement a xdr_page_pos() function I'll need this for READ_PLUS to help figure out the offset where page data is stored at, but it might also be useful for other things. Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 5a6a81b7cd9f..25a68dd87ecf 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -240,6 +240,7 @@ extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len); extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr); +extern unsigned int xdr_page_pos(const struct xdr_stream *xdr); extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, -- cgit v1.2.3 From c567552612ece787b178e3b147b5854ad422a836 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 28 May 2014 13:41:22 -0400 Subject: NFS: Add READ_PLUS data segment support This patch adds client support for decoding a single NFS4_CONTENT_DATA segment returned by the server. This is the simplest implementation possible, since it does not account for any hole segments in the reply. Signed-off-by: Anna Schumaker --- include/linux/nfs4.h | 2 +- include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index b8360be141da..9dc7eeac924f 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -551,13 +551,13 @@ enum { NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LAYOUTERROR, - NFSPROC4_CLNT_COPY_NOTIFY, NFSPROC4_CLNT_GETXATTR, NFSPROC4_CLNT_SETXATTR, NFSPROC4_CLNT_LISTXATTRS, NFSPROC4_CLNT_REMOVEXATTR, + NFSPROC4_CLNT_READ_PLUS, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 7eae72a8762e..38e60ec742df 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -287,5 +287,6 @@ struct nfs_server { #define NFS_CAP_LAYOUTERROR (1U << 26) #define NFS_CAP_COPY_NOTIFY (1U << 27) #define NFS_CAP_XATTR (1U << 28) +#define NFS_CAP_READ_PLUS (1U << 29) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0599efd57eb9..d63cb862d58e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -657,7 +657,7 @@ struct nfs_pgio_args { struct nfs_pgio_res { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; - __u32 count; + __u64 count; __u32 op_status; union { struct { -- cgit v1.2.3 From 84ce182ab85b8ad5002fb1125ba572df99dd0d1c Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 28 May 2014 13:38:53 -0400 Subject: SUNRPC: Add the ability to expand holes in data pages This patch adds the ability to "read a hole" into a set of XDR data pages by taking the following steps: 1) Shift all data after the current xdr->p to the right, possibly into the tail, 2) Zero the specified range, and 3) Update xdr->p to point beyond the hole. Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 25a68dd87ecf..f9636d2a6d54 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); +extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t); /** * xdr_stream_remaining - Return the number of bytes remaining in the stream -- cgit v1.2.3 From e6ac0accb27c6892b7ebc7799e7ce56b3390a678 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Tue, 21 Apr 2020 11:27:00 -0400 Subject: SUNRPC: Add an xdr_align_data() function For now, this function simply aligns the data at the beginning of the pages. This can eventually be expanded to shift data to the correct offsets when we're ready. Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index f9636d2a6d54..fe7ff7f5b584 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); +extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t); extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t); /** -- cgit v1.2.3 From fb1ff4c1941573aea59e4cb575dc5a723303cd70 Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Mon, 5 Oct 2020 20:36:45 +0300 Subject: vfio/fsl-mc: Add VFIO framework skeleton for fsl-mc devices DPAA2 (Data Path Acceleration Architecture) consists in mechanisms for processing Ethernet packets, queue management, accelerators, etc. The Management Complex (mc) is a hardware entity that manages the DPAA2 hardware resources. It provides an object-based abstraction for software drivers to use the DPAA2 hardware. The MC mediates operations such as create, discover, destroy of DPAA2 objects. The MC provides memory-mapped I/O command interfaces (MC portals) which DPAA2 software drivers use to operate on DPAA2 objects. A DPRC is a container object that holds other types of DPAA2 objects. Each object in the DPRC is a Linux device and bound to a driver. The MC-bus driver is a platform driver (different from PCI or platform bus). The DPRC driver does runtime management of a bus instance. It performs the initial scan of the DPRC and handles changes in the DPRC configuration (adding/removing objects). All objects inside a container share the same hardware isolation context, meaning that only an entire DPRC can be assigned to a virtual machine. When a container is assigned to a virtual machine, all the objects within that container are assigned to that virtual machine. The DPRC container assigned to the virtual machine is not allowed to change contents (add/remove objects) by the guest. The restriction is set by the host and enforced by the mc hardware. The DPAA2 objects can be directly assigned to the guest. However the MC portals (the memory mapped command interface to the MC) need to be emulated because there are commands that configure the interrupts and the isolation IDs which are virtual in the guest. Example: echo vfio-fsl-mc > /sys/bus/fsl-mc/devices/dprc.2/driver_override echo dprc.2 > /sys/bus/fsl-mc/drivers/vfio-fsl-mc/bind The dprc.2 is bound to the VFIO driver and all the objects within dprc.2 are going to be bound to the VFIO driver. This patch adds the infrastructure for VFIO support for fsl-mc devices. Subsequent patches will add support for binding and secure assigning these devices using VFIO. More details about the DPAA2 objects can be found here: Documentation/networking/device_drivers/freescale/dpaa2/overview.rst Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 920470502329..95deac891378 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -201,6 +201,7 @@ struct vfio_device_info { #define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */ #define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */ #define VFIO_DEVICE_FLAGS_AP (1 << 5) /* vfio-ap device */ +#define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6) /* vfio-fsl-mc device */ __u32 num_regions; /* Max region index + 1 */ __u32 num_irqs; /* Max IRQ index + 1 */ }; -- cgit v1.2.3 From 0c633f0be1dc70a6db46d90dba4cdae82073350a Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Wed, 7 Oct 2020 14:56:22 -0400 Subject: vfio: Introduce capability definitions for VFIO_DEVICE_GET_INFO Allow the VFIO_DEVICE_GET_INFO ioctl to include a capability chain. Add a flag indicating capability chain support, and introduce the definitions for the first set of capabilities which are specified to s390 zPCI devices. Signed-off-by: Matthew Rosato Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 11 ++++++ include/uapi/linux/vfio_zdev.h | 78 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 89 insertions(+) create mode 100644 include/uapi/linux/vfio_zdev.h (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 920470502329..04fbe425ad0c 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -201,8 +201,10 @@ struct vfio_device_info { #define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */ #define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */ #define VFIO_DEVICE_FLAGS_AP (1 << 5) /* vfio-ap device */ +#define VFIO_DEVICE_FLAGS_CAPS (1 << 7) /* Info supports caps */ __u32 num_regions; /* Max region index + 1 */ __u32 num_irqs; /* Max IRQ index + 1 */ + __u32 cap_offset; /* Offset within info struct of first cap */ }; #define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7) @@ -218,6 +220,15 @@ struct vfio_device_info { #define VFIO_DEVICE_API_CCW_STRING "vfio-ccw" #define VFIO_DEVICE_API_AP_STRING "vfio-ap" +/* + * The following capabilities are unique to s390 zPCI devices. Their contents + * are further-defined in vfio_zdev.h + */ +#define VFIO_DEVICE_INFO_CAP_ZPCI_BASE 1 +#define VFIO_DEVICE_INFO_CAP_ZPCI_GROUP 2 +#define VFIO_DEVICE_INFO_CAP_ZPCI_UTIL 3 +#define VFIO_DEVICE_INFO_CAP_ZPCI_PFIP 4 + /** * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8, * struct vfio_region_info) diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h new file mode 100644 index 000000000000..b4309397b6b2 --- /dev/null +++ b/include/uapi/linux/vfio_zdev.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * VFIO Region definitions for ZPCI devices + * + * Copyright IBM Corp. 2020 + * + * Author(s): Pierre Morel + * Matthew Rosato + */ + +#ifndef _VFIO_ZDEV_H_ +#define _VFIO_ZDEV_H_ + +#include +#include + +/** + * VFIO_DEVICE_INFO_CAP_ZPCI_BASE - Base PCI Function information + * + * This capability provides a set of descriptive information about the + * associated PCI function. + */ +struct vfio_device_info_cap_zpci_base { + struct vfio_info_cap_header header; + __u64 start_dma; /* Start of available DMA addresses */ + __u64 end_dma; /* End of available DMA addresses */ + __u16 pchid; /* Physical Channel ID */ + __u16 vfn; /* Virtual function number */ + __u16 fmb_length; /* Measurement Block Length (in bytes) */ + __u8 pft; /* PCI Function Type */ + __u8 gid; /* PCI function group ID */ +}; + +/** + * VFIO_DEVICE_INFO_CAP_ZPCI_GROUP - Base PCI Function Group information + * + * This capability provides a set of descriptive information about the group of + * PCI functions that the associated device belongs to. + */ +struct vfio_device_info_cap_zpci_group { + struct vfio_info_cap_header header; + __u64 dasm; /* DMA Address space mask */ + __u64 msi_addr; /* MSI address */ + __u64 flags; +#define VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH 1 /* Program-specified TLB refresh */ + __u16 mui; /* Measurement Block Update Interval */ + __u16 noi; /* Maximum number of MSIs */ + __u16 maxstbl; /* Maximum Store Block Length */ + __u8 version; /* Supported PCI Version */ +}; + +/** + * VFIO_DEVICE_INFO_CAP_ZPCI_UTIL - Utility String + * + * This capability provides the utility string for the associated device, which + * is a device identifier string made up of EBCDID characters. 'size' specifies + * the length of 'util_str'. + */ +struct vfio_device_info_cap_zpci_util { + struct vfio_info_cap_header header; + __u32 size; + __u8 util_str[]; +}; + +/** + * VFIO_DEVICE_INFO_CAP_ZPCI_PFIP - PCI Function Path + * + * This capability provides the PCI function path string, which is an identifier + * that describes the internal hardware path of the device. 'size' specifies + * the length of 'pfip'. + */ +struct vfio_device_info_cap_zpci_pfip { + struct vfio_info_cap_header header; + __u32 size; + __u8 pfip[]; +}; + +#endif -- cgit v1.2.3 From 1c47fa6b31c2683f03bc2f9174902bb7dcd35d83 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 3 Oct 2020 00:41:49 +0900 Subject: can: dev: add a helper function to calculate the duration of one bit Rename macro CAN_CALC_SYNC_SEG to CAN_SYNC_SEG and make it available through include/linux/can/dev.h Add an helper function can_bit_time() which returns the duration (in time quanta) of one CAN bit. Rationale for this patch: the sync segment and the bit time are two concepts which are defined in the CAN ISO standard. Device drivers for CAN might need those. Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for additional information. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20201002154219.4887-6-mailhol.vincent@wanadoo.fr [mkl: Let can_bit_time() return an unsinged int, make argument const] Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index f8975d0b90bb..41ff31795320 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -82,6 +82,21 @@ struct can_priv { #endif }; +#define CAN_SYNC_SEG 1 + +/* + * can_bit_time() - Duration of one bit + * + * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for + * additional information. + * + * Return: the number of time quanta in one bit. + */ +static inline unsigned int can_bit_time(const struct can_bittiming *bt) +{ + return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2; +} + /* * get_can_dlc(value) - helper macro to cast a given data length code (dlc) * to u8 and ensure the dlc value to be max. 8 bytes. -- cgit v1.2.3 From e057dd3fc20ffb3d7f150af46542a51b59b90127 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 28 Sep 2020 22:04:04 +0200 Subject: can: add ISO 15765-2:2016 transport protocol CAN Transport Protocols offer support for segmented Point-to-Point communication between CAN nodes via two defined CAN Identifiers. As CAN frames can only transport a small amount of data bytes (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this segmentation is needed to transport longer PDUs as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic. This protocol driver implements data transfers according to ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types. Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20200928200404.82229-1-socketcan@hartkopp.net [mkl: Removed "WITH Linux-syscall-note" from isotp.c. Fixed indention, a checkpatch warning and typos. Replaced __u{8,32} by u{8,32}. Removed always false (optlen < 0) check in isotp_setsockopt().] Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 166 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 166 insertions(+) create mode 100644 include/uapi/linux/can/isotp.h (limited to 'include') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h new file mode 100644 index 000000000000..553006509f4e --- /dev/null +++ b/include/uapi/linux/can/isotp.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* + * linux/can/isotp.h + * + * Definitions for isotp CAN sockets (ISO 15765-2:2016) + * + * Copyright (c) 2020 Volkswagen Group Electronic Research + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of Volkswagen nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * The provided data structures and external interfaces from this code + * are not restricted to be used by modules with a GPL compatible license. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + */ + +#ifndef _UAPI_CAN_ISOTP_H +#define _UAPI_CAN_ISOTP_H + +#include +#include + +#define SOL_CAN_ISOTP (SOL_CAN_BASE + CAN_ISOTP) + +/* for socket options affecting the socket (not the global system) */ + +#define CAN_ISOTP_OPTS 1 /* pass struct can_isotp_options */ + +#define CAN_ISOTP_RECV_FC 2 /* pass struct can_isotp_fc_options */ + +/* sockopts to force stmin timer values for protocol regression tests */ + +#define CAN_ISOTP_TX_STMIN 3 /* pass __u32 value in nano secs */ + /* use this time instead of value */ + /* provided in FC from the receiver */ + +#define CAN_ISOTP_RX_STMIN 4 /* pass __u32 value in nano secs */ + /* ignore received CF frames which */ + /* timestamps differ less than val */ + +#define CAN_ISOTP_LL_OPTS 5 /* pass struct can_isotp_ll_options */ + +struct can_isotp_options { + + __u32 flags; /* set flags for isotp behaviour. */ + /* __u32 value : flags see below */ + + __u32 frame_txtime; /* frame transmission time (N_As/N_Ar) */ + /* __u32 value : time in nano secs */ + + __u8 ext_address; /* set address for extended addressing */ + /* __u8 value : extended address */ + + __u8 txpad_content; /* set content of padding byte (tx) */ + /* __u8 value : content on tx path */ + + __u8 rxpad_content; /* set content of padding byte (rx) */ + /* __u8 value : content on rx path */ + + __u8 rx_ext_address; /* set address for extended addressing */ + /* __u8 value : extended address (rx) */ +}; + +struct can_isotp_fc_options { + + __u8 bs; /* blocksize provided in FC frame */ + /* __u8 value : blocksize. 0 = off */ + + __u8 stmin; /* separation time provided in FC frame */ + /* __u8 value : */ + /* 0x00 - 0x7F : 0 - 127 ms */ + /* 0x80 - 0xF0 : reserved */ + /* 0xF1 - 0xF9 : 100 us - 900 us */ + /* 0xFA - 0xFF : reserved */ + + __u8 wftmax; /* max. number of wait frame transmiss. */ + /* __u8 value : 0 = omit FC N_PDU WT */ +}; + +struct can_isotp_ll_options { + + __u8 mtu; /* generated & accepted CAN frame type */ + /* __u8 value : */ + /* CAN_MTU (16) -> standard CAN 2.0 */ + /* CANFD_MTU (72) -> CAN FD frame */ + + __u8 tx_dl; /* tx link layer data length in bytes */ + /* (configured maximum payload length) */ + /* __u8 value : 8,12,16,20,24,32,48,64 */ + /* => rx path supports all LL_DL values */ + + __u8 tx_flags; /* set into struct canfd_frame.flags */ + /* at frame creation: e.g. CANFD_BRS */ + /* Obsolete when the BRS flag is fixed */ + /* by the CAN netdriver configuration */ +}; + +/* flags for isotp behaviour */ + +#define CAN_ISOTP_LISTEN_MODE 0x001 /* listen only (do not send FC) */ +#define CAN_ISOTP_EXTEND_ADDR 0x002 /* enable extended addressing */ +#define CAN_ISOTP_TX_PADDING 0x004 /* enable CAN frame padding tx path */ +#define CAN_ISOTP_RX_PADDING 0x008 /* enable CAN frame padding rx path */ +#define CAN_ISOTP_CHK_PAD_LEN 0x010 /* check received CAN frame padding */ +#define CAN_ISOTP_CHK_PAD_DATA 0x020 /* check received CAN frame padding */ +#define CAN_ISOTP_HALF_DUPLEX 0x040 /* half duplex error state handling */ +#define CAN_ISOTP_FORCE_TXSTMIN 0x080 /* ignore stmin from received FC */ +#define CAN_ISOTP_FORCE_RXSTMIN 0x100 /* ignore CFs depending on rx stmin */ +#define CAN_ISOTP_RX_EXT_ADDR 0x200 /* different rx extended addressing */ +#define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */ + + +/* default values */ + +#define CAN_ISOTP_DEFAULT_FLAGS 0 +#define CAN_ISOTP_DEFAULT_EXT_ADDRESS 0x00 +#define CAN_ISOTP_DEFAULT_PAD_CONTENT 0xCC /* prevent bit-stuffing */ +#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 0 +#define CAN_ISOTP_DEFAULT_RECV_BS 0 +#define CAN_ISOTP_DEFAULT_RECV_STMIN 0x00 +#define CAN_ISOTP_DEFAULT_RECV_WFTMAX 0 + +#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU +#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN +#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0 + +/* + * Remark on CAN_ISOTP_DEFAULT_RECV_* values: + * + * We can strongly assume, that the Linux Kernel implementation of + * CAN_ISOTP is capable to run with BS=0, STmin=0 and WFTmax=0. + * But as we like to be able to behave as a commonly available ECU, + * these default settings can be changed via sockopts. + * For that reason the STmin value is intentionally _not_ checked for + * consistency and copied directly into the flow control (FC) frame. + * + */ + +#endif /* !_UAPI_CAN_ISOTP_H */ -- cgit v1.2.3 From 638eae9bc7eb1012d1e0f5a8fd4db46447f822e9 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Wed, 23 Sep 2020 20:20:51 +0300 Subject: platform_data/mlxreg: Update module license Update license to SPDX-License. Signed-off-by: Vadim Pasternak Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20200923172053.26296-4-vadimp@nvidia.com Signed-off-by: Hans de Goede --- include/linux/platform_data/mlxreg.h | 32 ++------------------------------ 1 file changed, 2 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 1af9c01563f9..0a727d405a7a 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -1,34 +1,6 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ /* - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. - * Copyright (c) 2017 Vadim Pasternak - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. + * Copyright (C) 2017-2020 Mellanox Technologies Ltd. */ #ifndef __LINUX_PLATFORM_DATA_MLXREG_H -- cgit v1.2.3 From d2f3ab5b6b05f67817f3bd3f2fda5f0126e95a62 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Wed, 23 Sep 2020 20:20:52 +0300 Subject: platform_data/mlxreg: Extend core platform structure Add 'capability' field to structure 'mlxreg_core_platform_data'. The purpose of this filed to indicate the actual number of the components within the particular group. Such components could be, for example the number of the FAN drawers. Some systems are equipped with FAN drawers with one tachometer inside, others with FAN drawers with several tachometers inside. Signed-off-by: Vadim Pasternak Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20200923172053.26296-5-vadimp@nvidia.com Signed-off-by: Hans de Goede --- include/linux/platform_data/mlxreg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 0a727d405a7a..101333fe2b8d 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -109,6 +109,7 @@ struct mlxreg_core_item { * @features: supported features of device; * @version: implementation version; * @identity: device identity name; + * @capability: device capability register; */ struct mlxreg_core_platform_data { struct mlxreg_core_data *data; @@ -117,6 +118,7 @@ struct mlxreg_core_platform_data { u32 features; u32 version; char identity[MLXREG_CORE_LABEL_MAX_SIZE]; + u32 capability; }; /** -- cgit v1.2.3 From 9c37de297f6590937f95a28bec1b7ac68a38618f Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 7 Oct 2020 15:15:08 -0400 Subject: dm: remove special-casing of bio-based immutable singleton target on NVMe Since commit 5a6c35f9af416 ("block: remove direct_make_request") there is no benefit to DM special-casing NVMe. Remove all code used to establish DM_TYPE_NVME_BIO_BASED. Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index d6f8d4ba8d48..61a66fb8ebb3 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -29,7 +29,6 @@ enum dm_queue_mode { DM_TYPE_BIO_BASED = 1, DM_TYPE_REQUEST_BASED = 2, DM_TYPE_DAX_BIO_BASED = 3, - DM_TYPE_NVME_BIO_BASED = 4, }; typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; -- cgit v1.2.3 From 7007e9dd56767a95de0947b3f7599bcc2f21687f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 5 Oct 2020 10:41:28 +0200 Subject: scsi: core: Clean up allocation and freeing of sgtables Rename scsi_init_io() to scsi_alloc_sgtables(), and ensure callers call scsi_free_sgtables() to cleanup failures close to scsi_init_io() instead of leaking it down the generic I/O submission path. Link: https://lore.kernel.org/r/20201005084130.143273-9-hch@lst.de Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index e76bac4d14c5..69ade4fb71aa 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -165,7 +165,8 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, size_t *offset, size_t *len); extern void scsi_kunmap_atomic_sg(void *virt); -extern blk_status_t scsi_init_io(struct scsi_cmnd *cmd); +blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd); +void scsi_free_sgtables(struct scsi_cmnd *cmd); #ifdef CONFIG_SCSI_DMA extern int scsi_dma_map(struct scsi_cmnd *cmd); -- cgit v1.2.3 From 3093e7c16e12d729c325adb3c53dde7308cefbd8 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 7 Oct 2020 17:05:45 +1100 Subject: X.509: Fix modular build of public_key_sm2 The sm2 code was split out of public_key.c in a way that breaks modular builds. This patch moves the code back into the same file as the original motivation was to minimise ifdefs and that has nothing to do with splitting the code out. Fixes: 215525639631 ("X.509: support OSCCA SM2-with-SM3...") Reported-by: kernel test robot Signed-off-by: Herbert Xu --- include/crypto/public_key.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h index 02a6dbe5c366..948c5203ca9c 100644 --- a/include/crypto/public_key.h +++ b/include/crypto/public_key.h @@ -84,16 +84,4 @@ extern int verify_signature(const struct key *, int public_key_verify_signature(const struct public_key *pkey, const struct public_key_signature *sig); -#if IS_REACHABLE(CONFIG_CRYPTO_SM2) -int cert_sig_digest_update(const struct public_key_signature *sig, - struct crypto_akcipher *tfm_pkey); -#else -static inline -int cert_sig_digest_update(const struct public_key_signature *sig, - struct crypto_akcipher *tfm_pkey) -{ - return -ENOTSUPP; -} -#endif - #endif /* _LINUX_PUBLIC_KEY_H */ -- cgit v1.2.3 From 8dc4bd073663fa8aba2fae08b1c23ab41a2e97a2 Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Wed, 7 Oct 2020 23:15:47 -0700 Subject: usb: typec: tcpm: Add support for Sink Fast Role SWAP(FRS) PD 3.0 spec defines a new mechanism for power role swap called Fast role swap. This change enables TCPM to support FRS when acting as sink. Once the explicit contract is negotiated, sink port is expected to query the source port for sink caps to determine whether the source is FRS capable. Bits 23 & 24 of fixed pdo of the sink caps from the source, when set, indicates the current needed by the source when fast role swap is in progress(Implicit contract phasae). 0 indicates that the source does not support Fast Role Swap. Upon receiving the FRS signal from the source, TCPC(TCPM_FRS_EVENT) informs TCPM to start the Fast role swap sequence. 1. TCPM sends FRS PD message: FR_SWAP_SEND 2. If response is not received within the expiry of SenderResponseTimer, Error recovery is triggered.: FR_SWAP_SEND_TIMEOUT 3. Upon receipt of the accept message, TCPM waits for PSSourceOffTimer for PS_READY message from the partner: FR_SWAP_SNK_SRC_NEW_SINK_READY. TCPC is expected to autonomously turn on vbus once the FRS signal is received and vbus voltage falls below vsafe5v within tSrcFrSwap. This is different from traditional power role swap where the vbus sourcing is turned on by TCPM. 4. By this time, TCPC most likely would have started to source vbus, TCPM waits for tSrcFrSwap to see if the lower level TCPC driver signals TCPM_SOURCING_VBUS event: FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED. 5. When TCPC signals sourcing vbus, TCPM sends PS_READY msg and changes the CC pin from Rd to Rp. This is the end of fast role swap sequence and TCPM initiates the sequnce to negotiate explicit contract by transitioning into SRC_STARTUP after SwapSrcStart. The code is written based on the sequence described in "Figure 8-107: Dual-role Port in Sink to Source Fast Role Swap State Diagram" of USB Power Delivery Specification Revision 3.0, Version 1.2. Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20201008061556.1402293-7-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 19 +++++++++++-------- include/linux/usb/tcpm.h | 8 +++++++- 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index f842e4589bd2..3a805e2ecbc9 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -219,14 +219,16 @@ enum pd_pdo_type { #define PDO_CURR_MASK 0x3ff #define PDO_PWR_MASK 0x3ff -#define PDO_FIXED_DUAL_ROLE BIT(29) /* Power role swap supported */ -#define PDO_FIXED_SUSPEND BIT(28) /* USB Suspend supported (Source) */ -#define PDO_FIXED_HIGHER_CAP BIT(28) /* Requires more than vSafe5V (Sink) */ -#define PDO_FIXED_EXTPOWER BIT(27) /* Externally powered */ -#define PDO_FIXED_USB_COMM BIT(26) /* USB communications capable */ -#define PDO_FIXED_DATA_SWAP BIT(25) /* Data role swap supported */ -#define PDO_FIXED_VOLT_SHIFT 10 /* 50mV units */ -#define PDO_FIXED_CURR_SHIFT 0 /* 10mA units */ +#define PDO_FIXED_DUAL_ROLE BIT(29) /* Power role swap supported */ +#define PDO_FIXED_SUSPEND BIT(28) /* USB Suspend supported (Source) */ +#define PDO_FIXED_HIGHER_CAP BIT(28) /* Requires more than vSafe5V (Sink) */ +#define PDO_FIXED_EXTPOWER BIT(27) /* Externally powered */ +#define PDO_FIXED_USB_COMM BIT(26) /* USB communications capable */ +#define PDO_FIXED_DATA_SWAP BIT(25) /* Data role swap supported */ +#define PDO_FIXED_FRS_CURR_MASK (BIT(24) | BIT(23)) /* FR_Swap Current (Sink) */ +#define PDO_FIXED_FRS_CURR_SHIFT 23 +#define PDO_FIXED_VOLT_SHIFT 10 /* 50mV units */ +#define PDO_FIXED_CURR_SHIFT 0 /* 10mA units */ #define PDO_FIXED_VOLT(mv) ((((mv) / 50) & PDO_VOLT_MASK) << PDO_FIXED_VOLT_SHIFT) #define PDO_FIXED_CURR(ma) ((((ma) / 10) & PDO_CURR_MASK) << PDO_FIXED_CURR_SHIFT) @@ -454,6 +456,7 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_DB_DETECT 10000 /* 10 - 15 seconds */ #define PD_T_SEND_SOURCE_CAP 150 /* 100 - 200 ms */ #define PD_T_SENDER_RESPONSE 60 /* 24 - 30 ms, relaxed */ +#define PD_T_RECEIVER_RESPONSE 15 /* 15ms max */ #define PD_T_SOURCE_ACTIVITY 45 #define PD_T_SINK_ACTIVITY 135 #define PD_T_SINK_WAIT_CAP 240 diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 89f58760cf48..09762d26fa0c 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -78,8 +78,11 @@ enum tcpm_transmit_type { * automatically if a connection is established. * @try_role: Optional; called to set a preferred role * @pd_transmit:Called to transmit PD message - * @mux: Pointer to multiplexer data * @set_bist_data: Turn on/off bist data mode for compliance testing + * @enable_frs: + * Optional; Called to enable/disable PD 3.0 fast role swap. + * Enabling frs is accessory dependent as not all PD3.0 + * accessories support fast role swap. */ struct tcpc_dev { struct fwnode_handle *fwnode; @@ -105,6 +108,7 @@ struct tcpc_dev { int (*pd_transmit)(struct tcpc_dev *dev, enum tcpm_transmit_type type, const struct pd_message *msg); int (*set_bist_data)(struct tcpc_dev *dev, bool on); + int (*enable_frs)(struct tcpc_dev *dev, bool enable); }; struct tcpm_port; @@ -114,6 +118,8 @@ void tcpm_unregister_port(struct tcpm_port *port); void tcpm_vbus_change(struct tcpm_port *port); void tcpm_cc_change(struct tcpm_port *port); +void tcpm_sink_frs(struct tcpm_port *port); +void tcpm_sourcing_vbus(struct tcpm_port *port); void tcpm_pd_receive(struct tcpm_port *port, const struct pd_message *msg); void tcpm_pd_transmit_complete(struct tcpm_port *port, -- cgit v1.2.3 From ba6ff70a3bb76c1ff440d3a0044b82e97abb648f Mon Sep 17 00:00:00 2001 From: Rajkumar Manoharan Date: Sat, 3 Oct 2020 15:04:18 -0700 Subject: mac80211: copy configured beacon tx rate to driver The user is allowed to change beacon tx rate (HT/VHT/HE) from hostapd. This information needs to be passed to the driver when the rate control is offloaded to the firmware. The driver capability of allowing beacon rate is already validated in cfg80211, so simply passing the rate information to the driver is enough. Signed-off-by: Rajkumar Manoharan Link: https://lore.kernel.org/r/1601762658-15627-1-git-send-email-rmanohar@codeaurora.org [adjust commit message slightly] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 4747d446179a..e8e295dae744 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -628,6 +628,8 @@ struct ieee80211_fils_discovery { * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response * interval. * @s1g: BSS is S1G BSS (affects Association Request format). + * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed + * to driver when rate control is offloaded to firmware. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -698,6 +700,7 @@ struct ieee80211_bss_conf { struct ieee80211_fils_discovery fils_discovery; u32 unsol_bcast_probe_resp_interval; bool s1g; + struct cfg80211_bitrate_mask beacon_tx_rate; }; /** -- cgit v1.2.3 From 8446466c9dd645da4c1848f35ffd0fc1df3524ee Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 6 Aug 2020 10:07:24 -0400 Subject: XArray: Fix xas_for_each_conflict documentation At one point, xas_for_each_conflict() was going to work this way, and I forgot to update the documentation when I changed my mind. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index b4d70e7568b2..6b336098fca7 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1714,13 +1714,12 @@ enum { * @xas: XArray operation state. * @entry: Entry retrieved from the array. * - * The loop body will be executed for each entry in the XArray that lies - * within the range specified by @xas. If the loop completes successfully, - * any entries that lie in this range will be replaced by @entry. The caller - * may break out of the loop; if they do so, the contents of the XArray will - * be unchanged. The operation may fail due to an out of memory condition. - * The caller may also call xa_set_err() to exit the loop while setting an - * error to record the reason. + * The loop body will be executed for each entry in the XArray that + * lies within the range specified by @xas. If the loop terminates + * normally, @entry will be %NULL. The user may break out of the loop, + * which will leave @entry set to the conflicting entry. The caller + * may also call xa_set_err() to exit the loop while setting an error + * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) -- cgit v1.2.3 From a20b7053b5c47cd7de23288238ea4d23502f300a Mon Sep 17 00:00:00 2001 From: Ionela Voinescu Date: Thu, 24 Sep 2020 13:30:15 +0100 Subject: cpufreq,arm,arm64: restructure definitions of arch_set_freq_scale() Compared to other arch_* functions, arch_set_freq_scale() has an atypical weak definition that can be replaced by a strong architecture specific implementation. The more typical support for architectural functions involves defining an empty stub in a header file if the symbol is not already defined in architecture code. Some examples involve: - #define arch_scale_freq_capacity topology_get_freq_scale - #define arch_scale_freq_invariant topology_scale_freq_invariant - #define arch_scale_cpu_capacity topology_get_cpu_scale - #define arch_update_cpu_topology topology_update_cpu_topology - #define arch_scale_thermal_pressure topology_get_thermal_pressure - #define arch_set_thermal_pressure topology_set_thermal_pressure Bring arch_set_freq_scale() in line with these functions by renaming it to topology_set_freq_scale() in the arch topology driver, and by defining the arch_set_freq_scale symbol to point to the new function for arm and arm64. While there are other users of the arch_topology driver, this patch defines arch_set_freq_scale for arm and arm64 only, due to their existing definitions of arch_scale_freq_capacity. This is the getter function of the frequency invariance scale factor and without a getter function, the setter function - arch_set_freq_scale() has not purpose. Signed-off-by: Ionela Voinescu Acked-by: Viresh Kumar Acked-by: Catalin Marinas Acked-by: Sudeep Holla (BL_SWITCHER and topology parts) Signed-off-by: Rafael J. Wysocki --- include/linux/arch_topology.h | 2 ++ include/linux/cpufreq.h | 11 ++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 083df331a3c9..0f6cd6b73a61 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -30,6 +30,8 @@ static inline unsigned long topology_get_freq_scale(int cpu) return per_cpu(freq_scale, cpu); } +void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, + unsigned long max_freq); bool topology_scale_freq_invariant(void); bool arch_freq_counters_available(const struct cpumask *cpus); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9f779fbdbe7b..fa37b1c66443 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1011,9 +1011,14 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); -extern void arch_set_freq_scale(const struct cpumask *cpus, - unsigned long cur_freq, - unsigned long max_freq); +#ifndef arch_set_freq_scale +static __always_inline +void arch_set_freq_scale(const struct cpumask *cpus, + unsigned long cur_freq, + unsigned long max_freq) +{ +} +#endif /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; -- cgit v1.2.3 From 2ef0342530b0f487a65b5f6c94c85dce5f9b53b5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 8 Oct 2020 08:53:03 +0200 Subject: PNP: remove the now unused pnp_find_card() function All user of the pnp_find_card() compat wrapper are gone, so remove the function as well. Signed-off-by: Christoph Hellwig Signed-off-by: Rafael J. Wysocki --- include/linux/isapnp.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/isapnp.h b/include/linux/isapnp.h index 11edb2109a68..dba18c95844b 100644 --- a/include/linux/isapnp.h +++ b/include/linux/isapnp.h @@ -75,9 +75,6 @@ static inline int isapnp_proc_done(void) { return 0; } #endif /* compat */ -struct pnp_card *pnp_find_card(unsigned short vendor, - unsigned short device, - struct pnp_card *from); struct pnp_dev *pnp_find_dev(struct pnp_card *card, unsigned short vendor, unsigned short function, @@ -92,9 +89,6 @@ static inline int isapnp_cfg_end(void) { return -ENODEV; } static inline unsigned char isapnp_read_byte(unsigned char idx) { return 0xff; } static inline void isapnp_write_byte(unsigned char idx, unsigned char val) { ; } -static inline struct pnp_card *pnp_find_card(unsigned short vendor, - unsigned short device, - struct pnp_card *from) { return NULL; } static inline struct pnp_dev *pnp_find_dev(struct pnp_card *card, unsigned short vendor, unsigned short function, -- cgit v1.2.3 From 3d21044e5dbadf484232beb3c5d09f836cebb0ed Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 7 Oct 2020 19:53:55 -0700 Subject: ACPICA: Add support for 64 bit risc-v compilation ACPICA commit 0def627be286620c64a5d4d60ce2373f119169a9 Add 64 bit risc-v architecture. Useful for acpica tools and incorporating ACPICA into the Firmware Test Suite. Link: https://github.com/acpica/acpica/commit/0def627b Signed-off-by: Colin Ian King Signed-off-by: Bob Moore Signed-off-by: Erik Kaneda Signed-off-by: Rafael J. Wysocki --- include/acpi/platform/aclinux.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 987e2af7c335..4098ba1d6599 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -190,7 +190,8 @@ #if defined(__ia64__) || (defined(__x86_64__) && !defined(__ILP32__)) ||\ defined(__aarch64__) || defined(__PPC64__) ||\ - defined(__s390x__) + defined(__s390x__) ||\ + (defined(__riscv) && (defined(__LP64__) || defined(_LP64))) #define ACPI_MACHINE_WIDTH 64 #define COMPILER_DEPENDENT_INT64 long #define COMPILER_DEPENDENT_UINT64 unsigned long -- cgit v1.2.3 From ec360131ec27d611e5dc5e03a84d3dc47d4b9ea0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 7 Oct 2020 19:53:56 -0700 Subject: ACPICA: Drop the repeated word "an" in a comment ACPICA commit 9ed2c006444d1def55bc6f08164ed5d9e809c856 Link: https://github.com/acpica/acpica/commit/9ed2c006 Signed-off-by: Randy Dunlap Signed-off-by: Erik Kaneda Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actypes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index d50e61384f1f..647cb11d0a0a 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -824,7 +824,7 @@ typedef u8 acpi_adr_space_type; * * Note: A Data Table region is a special type of operation region * that has its own AML opcode. However, internally, the AML - * interpreter simply creates an operation region with an an address + * interpreter simply creates an operation region with an address * space type of ACPI_ADR_SPACE_DATA_TABLE. */ #define ACPI_ADR_SPACE_DATA_TABLE (acpi_adr_space_type) 0x7E /* Internal to ACPICA only */ -- cgit v1.2.3 From 465e490d290b9670c3eef7406915facd58946244 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 7 Oct 2020 19:53:57 -0700 Subject: ACPICA: Tree-wide: fix various typos and spelling mistakes ACPICA commit 6648a6ac8410813bcfedb5c8345259dd155ea851 Fix spelling issues found using the codespell checker Link: https://github.com/acpica/acpica/commit/6648a6ac Signed-off-by: Colin Ian King Signed-off-by: Bob Moore Signed-off-by: Erik Kaneda Signed-off-by: Rafael J. Wysocki --- include/acpi/acconfig.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 5940a3c68a96..a225eff499c8 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -121,7 +121,7 @@ * *****************************************************************************/ -/* Method info (in WALK_STATE), containing local variables and argumetns */ +/* Method info (in WALK_STATE), containing local variables and arguments */ #define ACPI_METHOD_NUM_LOCALS 8 #define ACPI_METHOD_MAX_LOCAL 7 -- cgit v1.2.3 From 18aaa02c9b32a281832f46b9b9b3a2111db0db54 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Wed, 7 Oct 2020 19:53:59 -0700 Subject: ACPICA: acpi_help: Update UUID list Added the following UUID's Memory Device Generic Buttons Device NVDIMM Root Device Control Method Battery Device Graphs for _DSD method Hierarchical Data Extension ARM core_sight Graph UUID This commit squashes the following ACPICA commits: 93e9aa864a7c5e10db876a9af3f2086e50cc6cf5 759aaf73942af4a1a0d13715ce5e6b054af351fa 24751ce4cf3089a7c1709e4986bc82dfb5cca7bc Link: https://github.com/acpica/acpica/commit/93e9aa86 Link: https://github.com/acpica/acpica/commit/759aaf73 Link: https://github.com/acpica/acpica/commit/24751ce4 Signed-off-by: Bob Moore Signed-off-by: Erik Kaneda Signed-off-by: Rafael J. Wysocki --- include/acpi/acuuid.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h index 9e1367b19069..10e30a5030ee 100644 --- a/include/acpi/acuuid.h +++ b/include/acpi/acuuid.h @@ -27,6 +27,10 @@ #define UUID_PCI_HOST_BRIDGE "33db4d5b-1ff7-401c-9657-7441c03dd766" #define UUID_I2C_DEVICE "3cdff6f7-4267-4555-ad05-b30a3d8938de" #define UUID_POWER_BUTTON "dfbcf3c5-e7a5-44e6-9c1f-29c76f6e059c" +#define UUID_MEMORY_DEVICE "03b19910-f473-11dd-87af-0800200c9a66" +#define UUID_GENERIC_BUTTONS_DEVICE "fa6bd625-9ce8-470d-a2c7-b3ca36c4282e" +#define UUID_NVDIMM_ROOT_DEVICE "2f10e7a4-9e91-11e4-89d3-123b93f75cba" +#define UUID_CONTROL_METHOD_BATTERY "f18fc78b-0f15-4978-b793-53f833a1d35b" /* Interfaces */ @@ -56,5 +60,8 @@ #define UUID_BATTERY_THERMAL_LIMIT "4c2067e3-887d-475c-9720-4af1d3ed602e" #define UUID_THERMAL_EXTENSIONS "14d399cd-7a27-4b18-8fb4-7cb7b9f4e500" #define UUID_DEVICE_PROPERTIES "daffd814-6eba-4d8c-8a91-bc9bbf4aa301" +#define UUID_DEVICE_GRAPHS "ab02a46b-74c7-45a2-bd68-f7d344ef2153" +#define UUID_HIERARCHICAL_DATA_EXTENSION "dbb8e3e6-5886-4ba6-8795-1319f52a966b" +#define UUID_CORESIGHT_GRAPH "3ecbc8b6-1d0e-4fb3-8107-e627f805c6cd" #endif /* __ACUUID_H__ */ -- cgit v1.2.3 From ef3efb439aef2ad4409cba5f3d865be87fa507c4 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Wed, 7 Oct 2020 19:54:00 -0700 Subject: ACPICA: iASL: Return exceptions for string-to-integer conversions This allows iASL to generate errors by passing exceptions that may be encountered during string-to-integer conversions. The exceptions point out invalid hex, decimal, and octal integers. ACPICA commit e98b8c0a3d96fdabb167c0ef18a809b32ade3228 Link: https://github.com/acpica/acpica/commit/e98b8c0a Signed-off-by: Bob Moore Signed-off-by: Erik Kaneda Signed-off-by: Rafael J. Wysocki --- include/acpi/acexcep.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index 436cd1411c3a..2fc624a61769 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -40,12 +40,12 @@ struct acpi_exception_info { char *name; -#ifdef ACPI_HELP_APP +#if defined (ACPI_HELP_APP) || defined (ACPI_ASL_COMPILER) char *description; #endif }; -#ifdef ACPI_HELP_APP +#if defined (ACPI_HELP_APP) || defined (ACPI_ASL_COMPILER) #define EXCEP_TXT(name,description) {name, description} #else #define EXCEP_TXT(name,description) {name} -- cgit v1.2.3 From 2bfdb7b3e95b3c11cf1d1233dac7cb9c4394ec32 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Wed, 7 Oct 2020 19:54:03 -0700 Subject: ACPICA: Update version to 20200925 Version 20200925 ACPICA commit 70add34a9a4729b5496d0695ad14d6a1dc435879 Link: https://github.com/acpica/acpica/commit/70add34a Signed-off-by: Bob Moore Signed-off-by: Erik Kaneda Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 9dc816641286..be7de305a622 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20200717 +#define ACPI_CA_VERSION 0x20200925 #include #include -- cgit v1.2.3 From 12fbfc4cabec65950bb0cc10eab0fc5c4c4d039f Mon Sep 17 00:00:00 2001 From: V Sujith Kumar Reddy Date: Thu, 8 Oct 2020 10:46:57 +0530 Subject: ASoC: Add sc7180-lpass binding header hdmi define Add header defining hdmi dai-id for SC7180 lpass soc in dt bindings. Signed-off-by: V Sujith Kumar Reddy Acked-by: Rob Herring Signed-off-by: Srinivasa Rao Tested-by: Srinivas Kandagatla Reviewed-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/1602134223-2562-2-git-send-email-srivasam@codeaurora.org Signed-off-by: Mark Brown --- include/dt-bindings/sound/sc7180-lpass.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/sound/sc7180-lpass.h b/include/dt-bindings/sound/sc7180-lpass.h index 7d988f6346a5..56ecaafd2dc6 100644 --- a/include/dt-bindings/sound/sc7180-lpass.h +++ b/include/dt-bindings/sound/sc7180-lpass.h @@ -4,6 +4,7 @@ #define MI2S_PRIMARY 0 #define MI2S_SECONDARY 1 +#define LPASS_DP_RX 2 #define LPASS_MCLK0 0 -- cgit v1.2.3 From 02dae28f0b542969e44cbc1e14ffc9944cd2975c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 31 Aug 2020 11:11:01 +0800 Subject: ftrace: Simplify the dyn_ftrace->flags macro All the three macro are defined to be used for ftrace_rec_count(). This can be achieved by (flags & FTRACE_REF_MAX) directly. Since no other places would use those macros, remove them for clarity. Also it fixes a typo in the comment. Link: https://lkml.kernel.org/r/20200831031104.23322-4-richard.weiyang@linux.alibaba.com Signed-off-by: Wei Yang Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5c2d5cc6e6a..b1f56e3410dc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -432,7 +432,7 @@ bool is_ftrace_trampoline(unsigned long addr); * DIRECT - there is a direct function to call * * When a new ftrace_ops is registered and wants a function to save - * pt_regs, the rec->flag REGS is set. When the function has been + * pt_regs, the rec->flags REGS is set. When the function has been * set up to save regs, the REG_EN flag is set. Once a function * starts saving regs it will do so until all ftrace_ops are removed * from tracing that function. @@ -450,12 +450,9 @@ enum { }; #define FTRACE_REF_MAX_SHIFT 23 -#define FTRACE_FL_BITS 9 -#define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1) -#define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT) #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) -#define ftrace_rec_count(rec) ((rec)->flags & ~FTRACE_FL_MASK) +#define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) struct dyn_ftrace { unsigned long ip; /* address of mcount call-site */ -- cgit v1.2.3 From 40dc4a42b97ef5a52ef34a73093a7992faaab15e Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 31 Aug 2020 11:11:04 +0800 Subject: ftrace: ftrace_global_list is renamed to ftrace_ops_list Fix the comment to comply with the code. Link: https://lkml.kernel.org/r/20200831031104.23322-7-richard.weiyang@linux.alibaba.com Signed-off-by: Wei Yang Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index b1f56e3410dc..1bd3a0356ae4 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -217,11 +217,11 @@ extern struct ftrace_ops __rcu *ftrace_ops_list; extern struct ftrace_ops ftrace_list_end; /* - * Traverse the ftrace_global_list, invoking all entries. The reason that we + * Traverse the ftrace_ops_list, invoking all entries. The reason that we * can use rcu_dereference_raw_check() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period * mechanism. The rcu_dereference_raw_check() calls are needed to handle - * concurrent insertions into the ftrace_global_list. + * concurrent insertions into the ftrace_ops_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -- cgit v1.2.3 From 2bb8945bcc1a768f2bc402a16c9610bba8d5187d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Sep 2020 11:49:37 +0200 Subject: lockdep: Fix usage_traceoverflow Basically print_lock_class_header()'s for loop is out of sync with the the size of of ->usage_traces[]. Also clean things up a bit while at it, to avoid such mishaps in the future. Fixes: 23870f122768 ("locking/lockdep: Fix "USED" <- "IN-NMI" inversions") Reported-by: Qian Cai Debugged-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Tested-by: Qian Cai Link: https://lkml.kernel.org/r/20200930094937.GE2651@hirez.programming.kicks-ass.net --- include/linux/lockdep_types.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index bb35b449f533..9a1fd49df17f 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -35,8 +35,12 @@ enum lockdep_wait_type { /* * We'd rather not expose kernel/lockdep_states.h this wide, but we do need * the total number of states... :-( + * + * XXX_LOCK_USAGE_STATES is the number of lines in lockdep_states.h, for each + * of those we generates 4 states, Additionally we report on USED and USED_READ. */ -#define XXX_LOCK_USAGE_STATES (1+2*4) +#define XXX_LOCK_USAGE_STATES 2 +#define LOCK_TRACE_STATES (XXX_LOCK_USAGE_STATES*4 + 2) /* * NR_LOCKDEP_CACHING_CLASSES ... Number of classes @@ -106,7 +110,7 @@ struct lock_class { * IRQ/softirq usage tracking bits: */ unsigned long usage_mask; - const struct lock_trace *usage_traces[XXX_LOCK_USAGE_STATES]; + const struct lock_trace *usage_traces[LOCK_TRACE_STATES]; /* * Generation counter, when doing certain classes of graph walking, -- cgit v1.2.3 From 4d004099a668c41522242aa146a38cc4eb59cb1e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 2 Oct 2020 11:04:21 +0200 Subject: lockdep: Fix lockdep recursion Steve reported that lockdep_assert*irq*(), when nested inside lockdep itself, will trigger a false-positive. One example is the stack-trace code, as called from inside lockdep, triggering tracing, which in turn calls RCU, which then uses lockdep_assert_irqs_disabled(). Fixes: a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context} to per-cpu variables") Reported-by: Steven Rostedt Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 6a584b3e5c74..b1227be47496 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -534,6 +534,7 @@ do { \ DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); +DECLARE_PER_CPU(unsigned int, lockdep_recursion); /* * The below lockdep_assert_*() macros use raw_cpu_read() to access the above @@ -543,25 +544,27 @@ DECLARE_PER_CPU(int, hardirq_context); * read the value from our previous CPU. */ +#define __lockdep_enabled (debug_locks && !raw_cpu_read(lockdep_recursion)) + #define lockdep_assert_irqs_enabled() \ do { \ - WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ - WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(__lockdep_enabled && raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ - WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context)); \ + WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ - debug_locks && \ + __lockdep_enabled && \ (preempt_count() != 0 || \ !raw_cpu_read(hardirqs_enabled))); \ } while (0) @@ -569,7 +572,7 @@ do { \ #define lockdep_assert_preemption_disabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ - debug_locks && \ + __lockdep_enabled && \ (preempt_count() == 0 && \ raw_cpu_read(hardirqs_enabled))); \ } while (0) -- cgit v1.2.3 From baffd723e44dc3d7f84f0b8f1fe1ece00ddd2710 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 5 Oct 2020 09:56:57 +0200 Subject: lockdep: Revert "lockdep: Use raw_cpu_*() for per-cpu variables" The thinking in commit: fddf9055a60d ("lockdep: Use raw_cpu_*() for per-cpu variables") is flawed. While it is true that when we're migratable both CPUs will have a 0 value, it doesn't hold that when we do get migrated in the middle of a raw_cpu_op(), the old CPU will still have 0 by the time we get around to reading it on the new CPU. Luckily, the reason for that commit (s390 using preempt_disable() instead of preempt_disable_notrace() in their percpu code), has since been fixed by commit: 1196f12a2c96 ("s390: don't trace preemption in percpu macros") An audit of arch/*/include/asm/percpu*.h shows there are no other architectures affected by this particular issue. Fixes: fddf9055a60d ("lockdep: Use raw_cpu_*() for per-cpu variables") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20201005095958.GJ2651@hirez.programming.kicks-ass.net --- include/linux/lockdep.h | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b1227be47496..1130f271de66 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -512,19 +512,19 @@ static inline void print_irqtrace_events(struct task_struct *curr) #define lock_map_release(l) lock_release(l, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING -# define might_lock(lock) \ +# define might_lock(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) -# define might_lock_read(lock) \ +# define might_lock_read(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) -# define might_lock_nested(lock, subclass) \ +# define might_lock_nested(lock, subclass) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL, \ @@ -536,29 +536,21 @@ DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); DECLARE_PER_CPU(unsigned int, lockdep_recursion); -/* - * The below lockdep_assert_*() macros use raw_cpu_read() to access the above - * per-cpu variables. This is required because this_cpu_read() will potentially - * call into preempt/irq-disable and that obviously isn't right. This is also - * correct because when IRQs are enabled, it doesn't matter if we accidentally - * read the value from our previous CPU. - */ - -#define __lockdep_enabled (debug_locks && !raw_cpu_read(lockdep_recursion)) +#define __lockdep_enabled (debug_locks && !this_cpu_read(lockdep_recursion)) #define lockdep_assert_irqs_enabled() \ do { \ - WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ - WARN_ON_ONCE(__lockdep_enabled && raw_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(__lockdep_enabled && this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ - WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirq_context)); \ + WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ @@ -566,7 +558,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() != 0 || \ - !raw_cpu_read(hardirqs_enabled))); \ + !this_cpu_read(hardirqs_enabled))); \ } while (0) #define lockdep_assert_preemption_disabled() \ @@ -574,7 +566,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() == 0 && \ - raw_cpu_read(hardirqs_enabled))); \ + this_cpu_read(hardirqs_enabled))); \ } while (0) #else -- cgit v1.2.3 From 96e503f9000f2ad17d550cd884a5e386eb7f532f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 6 Oct 2020 19:17:22 +0300 Subject: ALSA: hda/i915 - fix list corruption with concurrent probes Current hdac_i915 uses a static completion instance to wait for i915 driver to complete the component bind. This design is not safe if multiple HDA controllers are active and communicating with different i915 instances, and can lead to list corruption and failed audio driver probe. Fix the design by moving completion mechanism to common acomp code and remove the related code from hdac_i915. Fixes: 7b882fe3e3e8 ("ALSA: hda - handle multiple i915 device instances") Co-developed-by: Kai Vehmanen Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20201006161722.500256-1-kai.vehmanen@linux.intel.com Signed-off-by: Takashi Iwai --- include/drm/drm_audio_component.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/drm/drm_audio_component.h b/include/drm/drm_audio_component.h index a45f93487039..0d36bfd1a4cd 100644 --- a/include/drm/drm_audio_component.h +++ b/include/drm/drm_audio_component.h @@ -117,6 +117,10 @@ struct drm_audio_component { * @audio_ops: Ops implemented by hda driver, called by DRM driver */ const struct drm_audio_component_audio_ops *audio_ops; + /** + * @master_bind_complete: completion held during component master binding + */ + struct completion master_bind_complete; }; #endif /* _DRM_AUDIO_COMPONENT_H_ */ -- cgit v1.2.3 From 846e463a70e910f2a831aea19f9a361422a2ff5b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Oct 2020 09:51:11 -0700 Subject: net/sched: get rid of qdisc->padded kmalloc() of sufficiently big portion of memory is cache-aligned in regular conditions. If some debugging options are used, there is no reason qdisc structures would need 64-byte alignment if most other kernel structures are not aligned. This get rid of QDISC_ALIGN and QDISC_ALIGNTO. Addition of privdata field will help implementing the reverse of qdisc_priv() and documents where the private data is. Signed-off-by: Eric Dumazet Cc: Allen Pais Acked-by: Cong Wang Signed-off-by: Jakub Kicinski --- include/net/pkt_sched.h | 5 +---- include/net/sch_generic.h | 5 ++++- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index ac8c890a2657..4ed32e6b0201 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -19,12 +19,9 @@ struct qdisc_walker { int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *); }; -#define QDISC_ALIGNTO 64 -#define QDISC_ALIGN(len) (((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1)) - static inline void *qdisc_priv(struct Qdisc *q) { - return (char *) q + QDISC_ALIGN(sizeof(struct Qdisc)); + return &q->privdata; } /* diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6c762457122f..d8fd8676fc72 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -91,7 +91,7 @@ struct Qdisc { struct net_rate_estimator __rcu *rate_est; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; - int padded; + int pad; refcount_t refcnt; /* @@ -112,6 +112,9 @@ struct Qdisc { /* for NOLOCK qdisc, true if there are no enqueued skbs */ bool empty; struct rcu_head rcu; + + /* private data */ + long privdata[] ____cacheline_aligned; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) -- cgit v1.2.3 From eca43ee6c46db92dd850ce659316b0680d70e137 Mon Sep 17 00:00:00 2001 From: "Nikita V. Shirokov" Date: Fri, 9 Oct 2020 07:03:25 +0000 Subject: bpf: Add tcp_notsent_lowat bpf setsockopt Adding support for TCP_NOTSENT_LOWAT sockoption (https://lwn.net/Articles/560082/) in tcp bpf programs. Signed-off-by: Nikita V. Shirokov Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201009070325.226855-1-tehnerd@tehnerd.com --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d83561e8cd2c..42d2df799397 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1698,7 +1698,7 @@ union bpf_attr { * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return -- cgit v1.2.3 From 8858e8d98d5457ba23bcd0d99ce23e272b8b09a1 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 9 Oct 2020 18:07:14 +0900 Subject: block: fix uapi blkzoned.h comments Update the kdoc comments for struct blk_zone (capacity field description missing) and for struct blk_zone_report (flags field description missing). Signed-off-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 42c3366cc25f..656a326821a2 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -93,12 +93,15 @@ enum blk_zone_report_flags { * @non_seq: Flag indicating that the zone is using non-sequential resources * (for host-aware zoned block devices only). * @reset: Flag indicating that a zone reset is recommended. - * @reserved: Padding to 64 B to match the ZBC/ZAC defined zone descriptor size. + * @resv: Padding for 8B alignment. + * @capacity: Zone usable capacity in 512 B sector units + * @reserved: Padding to 64 B to match the ZBC, ZAC and ZNS defined zone + * descriptor size. * - * start, len and wp use the regular 512 B sector unit, regardless of the - * device logical block size. The overall structure size is 64 B to match the - * ZBC/ZAC defined zone descriptor and allow support for future additional - * zone information. + * start, len, capacity and wp use the regular 512 B sector unit, regardless + * of the device logical block size. The overall structure size is 64 B to + * match the ZBC, ZAC and ZNS defined zone descriptor and allow support for + * future additional zone information. */ struct blk_zone { __u64 start; /* Zone start sector */ @@ -118,7 +121,7 @@ struct blk_zone { * * @sector: starting sector of report * @nr_zones: IN maximum / OUT actual - * @reserved: padding to 16 byte alignment + * @flags: one or more flags as defined by enum blk_zone_report_flags. * @zones: Space to hold @nr_zones @zones entries on reply. * * The array of at most @nr_zones must follow this structure in memory. -- cgit v1.2.3 From ccdf07219da6bd1f43c6ddcde4c0e36993c7365a Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 7 Oct 2020 09:00:43 +0300 Subject: devlink: Add reload action option to devlink reload command Add devlink reload action to allow the user to request a specific reload action. The action parameter is optional, if not specified then devlink driver re-init action is used (backward compatible). Note that when required to do firmware activation some drivers may need to reload the driver. On the other hand some drivers may need to reset the firmware to reinitialize the driver entities. Therefore, the devlink reload command returns the actions which were actually performed. Reload actions supported are: driver_reinit: driver entities re-initialization, applying devlink-param and devlink-resource values. fw_activate: firmware activate. command examples: $devlink dev reload pci/0000:82:00.0 action driver_reinit reload_actions_performed: driver_reinit $devlink dev reload pci/0000:82:00.0 action fw_activate reload_actions_performed: driver_reinit fw_activate Signed-off-by: Moshe Shemesh Reviewed-by: Jakub Kicinski Reviewed-by: Jacob Keller Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 7 ++++--- include/uapi/linux/devlink.h | 13 +++++++++++++ 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 237ba5e29a3b..93c535ae5a4b 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1150,10 +1150,11 @@ struct devlink_ops { * implemementation. */ u32 supported_flash_update_params; + unsigned long reload_actions; int (*reload_down)(struct devlink *devlink, bool netns_change, - struct netlink_ext_ack *extack); - int (*reload_up)(struct devlink *devlink, - struct netlink_ext_ack *extack); + enum devlink_reload_action action, struct netlink_ext_ack *extack); + int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action, + u32 *actions_performed, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); int (*port_split)(struct devlink *devlink, unsigned int port_index, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 5f1d6c327670..74bdad252c36 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -301,6 +301,16 @@ enum { DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE, }; +enum devlink_reload_action { + DEVLINK_RELOAD_ACTION_UNSPEC, + DEVLINK_RELOAD_ACTION_DRIVER_REINIT, /* Driver entities re-instantiation */ + DEVLINK_RELOAD_ACTION_FW_ACTIVATE, /* FW activate */ + + /* Add new reload actions above */ + __DEVLINK_RELOAD_ACTION_MAX, + DEVLINK_RELOAD_ACTION_MAX = __DEVLINK_RELOAD_ACTION_MAX - 1 +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -493,6 +503,9 @@ enum devlink_attr { DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, /* u64 */ DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, /* bitfield32 */ + DEVLINK_ATTR_RELOAD_ACTION, /* u8 */ + DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, /* bitfield32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From dc64cc7c63102ac78bac3cfbc00ef3abd7a3fdf3 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 7 Oct 2020 09:00:44 +0300 Subject: devlink: Add devlink reload limit option Add reload limit to demand restrictions on reload actions. Reload limits supported: no_reset: No reset allowed, no down time allowed, no link flap and no configuration is lost. By default reload limit is unspecified and so no constraints on reload actions are required. Some combinations of action and limit are invalid. For example, driver can not reinitialize its entities without any downtime. The no_reset reload limit will have usecase in this patchset to implement restricted fw_activate on mlx5. Have the uapi parameter of reload limit ready for future support of multiselection. Signed-off-by: Moshe Shemesh Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 8 ++++++-- include/uapi/linux/devlink.h | 14 ++++++++++++++ 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 93c535ae5a4b..9f5c37c391f8 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1151,10 +1151,14 @@ struct devlink_ops { */ u32 supported_flash_update_params; unsigned long reload_actions; + unsigned long reload_limits; int (*reload_down)(struct devlink *devlink, bool netns_change, - enum devlink_reload_action action, struct netlink_ext_ack *extack); + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack); int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action, - u32 *actions_performed, struct netlink_ext_ack *extack); + enum devlink_reload_limit limit, u32 *actions_performed, + struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); int (*port_split)(struct devlink *devlink, unsigned int port_index, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 74bdad252c36..82a5e66c1518 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -311,6 +311,19 @@ enum devlink_reload_action { DEVLINK_RELOAD_ACTION_MAX = __DEVLINK_RELOAD_ACTION_MAX - 1 }; +enum devlink_reload_limit { + DEVLINK_RELOAD_LIMIT_UNSPEC, /* unspecified, no constraints */ + DEVLINK_RELOAD_LIMIT_NO_RESET, /* No reset allowed, no down time allowed, + * no link flap and no configuration is lost. + */ + + /* Add new reload limit above */ + __DEVLINK_RELOAD_LIMIT_MAX, + DEVLINK_RELOAD_LIMIT_MAX = __DEVLINK_RELOAD_LIMIT_MAX - 1 +}; + +#define DEVLINK_RELOAD_LIMITS_VALID_MASK (BIT(__DEVLINK_RELOAD_LIMIT_MAX) - 1) + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -505,6 +518,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_ACTION, /* u8 */ DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, /* bitfield32 */ + DEVLINK_ATTR_RELOAD_LIMITS, /* bitfield32 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From a254c264267e8746fb257806c166e54375cf9c06 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 7 Oct 2020 09:00:45 +0300 Subject: devlink: Add reload stats Add reload stats to hold the history per reload action type and limit. For example, the number of times fw_activate has been performed on this device since the driver module was added or if the firmware activation was performed with or without reset. Add devlink notification on stats update. Expose devlink reload stats to the user through devlink dev get command. Examples: $ devlink dev show pci/0000:82:00.0: stats: reload: driver_reinit 2 fw_activate 1 fw_activate_no_reset 0 pci/0000:82:00.1: stats: reload: driver_reinit 1 fw_activate 0 fw_activate_no_reset 0 $ devlink dev show -jp { "dev": { "pci/0000:82:00.0": { "stats": { "reload": { "driver_reinit": 2, "fw_activate": 1, "fw_activate_no_reset": 0 } } }, "pci/0000:82:00.1": { "stats": { "reload": { "driver_reinit": 1, "fw_activate": 0, "fw_activate_no_reset": 0 } } } } } Signed-off-by: Moshe Shemesh Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 8 ++++++++ include/uapi/linux/devlink.h | 6 ++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 9f5c37c391f8..d091c6ba82ce 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -20,6 +20,13 @@ #include #include +#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ + (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) + +struct devlink_dev_stats { + u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; +}; + struct devlink_ops; struct devlink { @@ -38,6 +45,7 @@ struct devlink { struct list_head trap_policer_list; const struct devlink_ops *ops; struct xarray snapshot_ids; + struct devlink_dev_stats stats; struct device *dev; possible_net_t _net; struct mutex lock; /* Serializes access to devlink instance specific objects such as diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 82a5e66c1518..ab15fc597b74 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -520,6 +520,12 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, /* bitfield32 */ DEVLINK_ATTR_RELOAD_LIMITS, /* bitfield32 */ + DEVLINK_ATTR_DEV_STATS, /* nested */ + DEVLINK_ATTR_RELOAD_STATS, /* nested */ + DEVLINK_ATTR_RELOAD_STATS_ENTRY, /* nested */ + DEVLINK_ATTR_RELOAD_STATS_LIMIT, /* u8 */ + DEVLINK_ATTR_RELOAD_STATS_VALUE, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From 77069ba2e3adf48c472fbbd9cbd7a4f5370b17df Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 7 Oct 2020 09:00:46 +0300 Subject: devlink: Add remote reload stats Add remote reload stats to hold the history of actions performed due devlink reload commands initiated by remote host. For example, in case firmware activation with reset finished successfully but was initiated by remote host. The function devlink_remote_reload_actions_performed() is exported to enable drivers update on remote reload actions performed as it was not initiated by their own devlink instance. Expose devlink remote reload stats to the user through devlink dev get command. Examples: $ devlink dev show pci/0000:82:00.0: stats: reload: driver_reinit 2 fw_activate 1 fw_activate_no_reset 0 remote_reload: driver_reinit 0 fw_activate 0 fw_activate_no_reset 0 pci/0000:82:00.1: stats: reload: driver_reinit 1 fw_activate 0 fw_activate_no_reset 0 remote_reload: driver_reinit 1 fw_activate 1 fw_activate_no_reset 0 $ devlink dev show -jp { "dev": { "pci/0000:82:00.0": { "stats": { "reload": { "driver_reinit": 2, "fw_activate": 1, "fw_activate_no_reset": 0 }, "remote_reload": { "driver_reinit": 0, "fw_activate": 0, "fw_activate_no_reset": 0 } } }, "pci/0000:82:00.1": { "stats": { "reload": { "driver_reinit": 1, "fw_activate": 0, "fw_activate_no_reset": 0 }, "remote_reload": { "driver_reinit": 1, "fw_activate": 1, "fw_activate_no_reset": 0 } } } } } Signed-off-by: Moshe Shemesh Reviewed-by: Jakub Kicinski Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 4 ++++ include/uapi/linux/devlink.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index d091c6ba82ce..d2771e57a278 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -25,6 +25,7 @@ struct devlink_dev_stats { u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; }; struct devlink_ops; @@ -1567,6 +1568,9 @@ void devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter); bool devlink_is_reload_failed(const struct devlink *devlink); +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed); void devlink_flash_update_begin_notify(struct devlink *devlink); void devlink_flash_update_end_notify(struct devlink *devlink); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ab15fc597b74..0113bc4db9f5 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -525,6 +525,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_STATS_ENTRY, /* nested */ DEVLINK_ATTR_RELOAD_STATS_LIMIT, /* u8 */ DEVLINK_ATTR_RELOAD_STATS_VALUE, /* u32 */ + DEVLINK_ATTR_REMOTE_RELOAD_STATS, /* nested */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From 38b9f903f22b9baa5c4b9bfb07c8bbc49f5efbba Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 7 Oct 2020 09:00:49 +0300 Subject: net/mlx5: Handle sync reset request event Once the driver gets sync_reset_request from firmware it prepares for the coming reset and sends acknowledge. After getting this event the driver expects device reset, either it will trigger PCI reset on sync_reset_now event or such PCI reset will be triggered by another PF of the same device. So it moves to reset requested mode and if it gets PCI reset triggered by the other PF it detect the reset and reloads. Signed-off-by: Moshe Shemesh Reviewed-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 239e5348ee09..add85094f9a5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -501,6 +501,7 @@ struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; struct mlx5_devcom; +struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; @@ -578,6 +579,7 @@ struct mlx5_priv { struct mlx5_core_sriov sriov; struct mlx5_lag *lag; struct mlx5_devcom *devcom; + struct mlx5_fw_reset *fw_reset; struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; -- cgit v1.2.3 From 195d9dece1686576ad1c7b45942b5cf9eacb3fbf Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 7 Oct 2020 09:00:53 +0300 Subject: devlink: Add enable_remote_dev_reset generic parameter The enable_remote_dev_reset devlink param flags that the host admin allows device resets that can be initiated by other hosts. This parameter is useful for setups where a device is shared by different hosts, such as multi-host setup. Once the user set this parameter to false, the driver should NACK any attempt to reset the device while the driver is loaded. Signed-off-by: Moshe Shemesh Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index d2771e57a278..b01bb9bca5a2 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -469,6 +469,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -506,6 +507,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce" #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME "enable_remote_dev_reset" +#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ -- cgit v1.2.3 From 2d69356752ff862dbb0c7e6725874740799d7708 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 7 Oct 2020 09:00:55 +0300 Subject: net/mlx5: Add support for fw live patch event Firmware live patch event notifies the driver that the firmware was just updated using live patch. In such case the driver should not reload or re-initiate entities, part to updating the firmware version and re-initiate the firmware tracer which can be updated by live patch with new strings database to help debugging an issue. Signed-off-by: Moshe Shemesh Reviewed-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 81ca5989009b..cf824366a7d1 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -366,6 +366,7 @@ enum { enum { MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5, + MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT = 0x7, MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT = 0x8, }; -- cgit v1.2.3 From 90a025a859a3ac4dfe3db62edf21070a90e98766 Mon Sep 17 00:00:00 2001 From: Brendan Higgins Date: Tue, 4 Aug 2020 13:47:41 -0700 Subject: vmlinux.lds.h: add linker section for KUnit test suites Add a linker section where KUnit can put references to its test suites. This patch is the first step in transitioning to dispatching all KUnit tests from a centralized executor rather than having each as its own separate late_initcall. Co-developed-by: Iurii Zaikin Signed-off-by: Iurii Zaikin Signed-off-by: Brendan Higgins Reviewed-by: Stephen Boyd Signed-off-by: Shuah Khan --- include/asm-generic/vmlinux.lds.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 5430febd34be..31e08674b542 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -717,7 +717,8 @@ THERMAL_TABLE(governor) \ EARLYCON_TABLE() \ LSM_TABLE() \ - EARLY_LSM_TABLE() + EARLY_LSM_TABLE() \ + KUNIT_TABLE() #define INIT_TEXT \ *(.init.text .init.text.*) \ @@ -909,6 +910,13 @@ KEEP(*(.con_initcall.init)) \ __con_initcall_end = .; +/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */ +#define KUNIT_TABLE() \ + . = ALIGN(8); \ + __kunit_suites_start = .; \ + KEEP(*(.kunit_test_suites)) \ + __kunit_suites_end = .; + #ifdef CONFIG_BLK_DEV_INITRD #define INIT_RAM_FS \ . = ALIGN(4); \ -- cgit v1.2.3 From aac35468ca20a3a0e75a24c13c0e31610727f120 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Tue, 4 Aug 2020 13:47:42 -0700 Subject: kunit: test: create a single centralized executor for all tests Add a centralized executor to dispatch tests rather than relying on late_initcall to schedule each test suite separately. Centralized execution is for built-in tests only; modules will execute tests when loaded. Signed-off-by: Alan Maguire Co-developed-by: Iurii Zaikin Signed-off-by: Iurii Zaikin Co-developed-by: Brendan Higgins Signed-off-by: Brendan Higgins Reviewed-by: Stephen Boyd Reviewed-by: Kees Cook Signed-off-by: Shuah Khan --- include/kunit/test.h | 67 +++++++++++++++++++++++++++++++++++----------------- 1 file changed, 45 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 59f3144f009a..d2d261f58259 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -233,7 +233,7 @@ size_t kunit_suite_num_test_cases(struct kunit_suite *suite); unsigned int kunit_test_case_num(struct kunit_suite *suite, struct kunit_case *test_case); -int __kunit_test_suites_init(struct kunit_suite **suites); +int __kunit_test_suites_init(struct kunit_suite * const * const suites); void __kunit_test_suites_exit(struct kunit_suite **suites); @@ -246,34 +246,57 @@ void __kunit_test_suites_exit(struct kunit_suite **suites); * Registers @suites_list with the test framework. See &struct kunit_suite for * more information. * - * When builtin, KUnit tests are all run as late_initcalls; this means - * that they cannot test anything where tests must run at a different init - * phase. One significant restriction resulting from this is that KUnit - * cannot reliably test anything that is initialize in the late_init phase; - * another is that KUnit is useless to test things that need to be run in - * an earlier init phase. - * - * An alternative is to build the tests as a module. Because modules - * do not support multiple late_initcall()s, we need to initialize an - * array of suites for a module. - * - * TODO(brendanhiggins@google.com): Don't run all KUnit tests as - * late_initcalls. I have some future work planned to dispatch all KUnit - * tests from the same place, and at the very least to do so after - * everything else is definitely initialized. + * If a test suite is built-in, module_init() gets translated into + * an initcall which we don't want as the idea is that for builtins + * the executor will manage execution. So ensure we do not define + * module_{init|exit} functions for the builtin case when registering + * suites via kunit_test_suites() below. */ -#define kunit_test_suites(suites_list...) \ - static struct kunit_suite *suites[] = {suites_list, NULL}; \ - static int kunit_test_suites_init(void) \ +#ifdef MODULE +#define kunit_test_suites_for_module(__suites) \ + static int __init kunit_test_suites_init(void) \ { \ - return __kunit_test_suites_init(suites); \ + return __kunit_test_suites_init(__suites); \ } \ - late_initcall(kunit_test_suites_init); \ + module_init(kunit_test_suites_init); \ + \ static void __exit kunit_test_suites_exit(void) \ { \ - return __kunit_test_suites_exit(suites); \ + return __kunit_test_suites_exit(__suites); \ } \ module_exit(kunit_test_suites_exit) +#else +#define kunit_test_suites_for_module(__suites) +#endif /* MODULE */ + +#define __kunit_test_suites(unique_array, unique_suites, ...) \ + static struct kunit_suite *unique_array[] = { __VA_ARGS__, NULL }; \ + kunit_test_suites_for_module(unique_array); \ + static struct kunit_suite **unique_suites \ + __used __section(.kunit_test_suites) = unique_array + +/** + * kunit_test_suites() - used to register one or more &struct kunit_suite + * with KUnit. + * + * @suites: a statically allocated list of &struct kunit_suite. + * + * Registers @suites with the test framework. See &struct kunit_suite for + * more information. + * + * When builtin, KUnit tests are all run via executor; this is done + * by placing the array of struct kunit_suite * in the .kunit_test_suites + * ELF section. + * + * An alternative is to build the tests as a module. Because modules do not + * support multiple initcall()s, we need to initialize an array of suites for a + * module. + * + */ +#define kunit_test_suites(...) \ + __kunit_test_suites(__UNIQUE_ID(array), \ + __UNIQUE_ID(suites), \ + __VA_ARGS__) #define kunit_test_suite(suite) kunit_test_suites(&suite) -- cgit v1.2.3 From 8c0d884986ba22f1020be9c02e41c030890ee8f2 Mon Sep 17 00:00:00 2001 From: Brendan Higgins Date: Tue, 4 Aug 2020 13:47:43 -0700 Subject: init: main: add KUnit to kernel init Although we have not seen any actual examples where KUnit doesn't work because it runs in the late init phase of the kernel, it has been a concern for some time that this could potentially be an issue in the future. So, remove KUnit from init calls entirely, instead call directly from kernel_init() so that KUnit runs after late init. Co-developed-by: Alan Maguire Signed-off-by: Alan Maguire Signed-off-by: Brendan Higgins Reviewed-by: Stephen Boyd Reviewed-by: Kees Cook Reviewed-by: Luis Chamberlain Signed-off-by: Shuah Khan --- include/kunit/test.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index d2d261f58259..7ea24466e49c 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -237,6 +237,15 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites); void __kunit_test_suites_exit(struct kunit_suite **suites); +#if IS_BUILTIN(CONFIG_KUNIT) +int kunit_run_all_tests(void); +#else +static inline int kunit_run_all_tests(void) +{ + return 0; +} +#endif /* IS_BUILTIN(CONFIG_KUNIT) */ + /** * kunit_test_suites() - used to register one or more &struct kunit_suite * with KUnit. -- cgit v1.2.3 From 923527dcb4d164925a2fed0b53c6a1625a60a472 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 8 Oct 2020 22:49:00 -0700 Subject: net/tls: remove a duplicate function prototype Remove one of the two instances of the function prototype for tls_validate_xmit_skb(). Signed-off-by: Randy Dunlap Cc: Boris Pismenny Cc: Aviad Yehezkel Cc: John Fastabend Cc: Daniel Borkmann Signed-off-by: Jakub Kicinski --- include/net/tls.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index e5dac7e74e79..baf1e99d8193 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -679,10 +679,6 @@ int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); -struct sk_buff *tls_validate_xmit_skb(struct sock *sk, - struct net_device *dev, - struct sk_buff *skb); - int tls_sw_fallback_init(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info); -- cgit v1.2.3 From 44f3625bc61653ea3bde9960298faf2f5518fda5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 8 Oct 2020 12:45:17 +0200 Subject: netlink: export policy in extended ACK Add a new attribute NLMSGERR_ATTR_POLICY to the extended ACK to advertise the policy, e.g. if an attribute was out of range, you'll know the range that's permissible. Add new NL_SET_ERR_MSG_ATTR_POL() and NL_SET_ERR_MSG_ATTR_POL() macros to set this, since realistically it's only useful to do this when the bad attribute (offset) is also returned. Use it in lib/nlattr.c which practically does all the policy validation. v2: - add and use netlink_policy_dump_attr_size_estimate() v3: - remove redundant break v4: - really remove redundant break ... sorry Reviewed-by: Jakub Kicinski Signed-off-by: Johannes Berg Signed-off-by: Jakub Kicinski --- include/linux/netlink.h | 30 ++++++++++++++++++++---------- include/net/netlink.h | 4 ++++ include/uapi/linux/netlink.h | 2 ++ 3 files changed, 26 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index e3e49f0e5c13..666cd0390699 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -68,12 +68,14 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) * @_msg: message string to report - don't access directly, use * %NL_SET_ERR_MSG * @bad_attr: attribute with error + * @policy: policy for a bad attribute * @cookie: cookie data to return to userspace (for success) * @cookie_len: actual cookie data length */ struct netlink_ext_ack { const char *_msg; const struct nlattr *bad_attr; + const struct nla_policy *policy; u8 cookie[NETLINK_MAX_COOKIE_LEN]; u8 cookie_len; }; @@ -95,21 +97,29 @@ struct netlink_ext_ack { #define NL_SET_ERR_MSG_MOD(extack, msg) \ NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg) -#define NL_SET_BAD_ATTR(extack, attr) do { \ - if ((extack)) \ +#define NL_SET_BAD_ATTR_POLICY(extack, attr, pol) do { \ + if ((extack)) { \ (extack)->bad_attr = (attr); \ + (extack)->policy = (pol); \ + } \ } while (0) -#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ - static const char __msg[] = msg; \ - struct netlink_ext_ack *__extack = (extack); \ - \ - if (__extack) { \ - __extack->_msg = __msg; \ - __extack->bad_attr = (attr); \ - } \ +#define NL_SET_BAD_ATTR(extack, attr) NL_SET_BAD_ATTR_POLICY(extack, attr, NULL) + +#define NL_SET_ERR_MSG_ATTR_POL(extack, attr, pol, msg) do { \ + static const char __msg[] = msg; \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) { \ + __extack->_msg = __msg; \ + __extack->bad_attr = (attr); \ + __extack->policy = (pol); \ + } \ } while (0) +#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) \ + NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg) + static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, u64 cookie) { diff --git a/include/net/netlink.h b/include/net/netlink.h index 2b9e41075f19..7356f41d23ba 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1957,6 +1957,10 @@ int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state, bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state); int netlink_policy_dump_write(struct sk_buff *skb, struct netlink_policy_dump_state *state); +int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt); +int netlink_policy_dump_write_attr(struct sk_buff *skb, + const struct nla_policy *pt, + int nestattr); void netlink_policy_dump_free(struct netlink_policy_dump_state *state); #endif diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index d02e472ba54c..c3816ff7bfc3 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -129,6 +129,7 @@ struct nlmsgerr { * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to * be used - in the success case - to identify a created * object or operation or similar (binary) + * @NLMSGERR_ATTR_POLICY: policy for a rejected attribute * @__NLMSGERR_ATTR_MAX: number of attributes * @NLMSGERR_ATTR_MAX: highest attribute number */ @@ -137,6 +138,7 @@ enum nlmsgerr_attrs { NLMSGERR_ATTR_MSG, NLMSGERR_ATTR_OFFS, NLMSGERR_ATTR_COOKIE, + NLMSGERR_ATTR_POLICY, __NLMSGERR_ATTR_MAX, NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1 -- cgit v1.2.3 From 55567976629e58fde28fb70612ca73228271eef2 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 6 Oct 2020 10:10:20 +0100 Subject: genirq/irqdomain: Allow partial trimming of irq_data hierarchy It appears that some HW is ugly enough that not all the interrupts connected to a particular interrupt controller end up with the same hierarchy depth (some of them are terminated early). This leaves the irqchip hacker with only two choices, both equally bad: - create discrete domain chains, one for each "hierarchy depth", which is very hard to maintain - create fake hierarchy levels for the shallow paths, leading to all kind of problems (what are the safe hwirq values for these fake levels?) Implement the ability to cut short a single interrupt hierarchy from a level marked as being disconnected by using the new irq_domain_disconnect_hierarchy() helper. The irqdomain allocation code will then perform the trimming Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b37350c4fe37..a52b095bd404 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -509,6 +509,9 @@ extern void irq_domain_free_irqs_parent(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs); +extern int irq_domain_disconnect_hierarchy(struct irq_domain *domain, + unsigned int virq); + static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) { return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY; -- cgit v1.2.3 From dd2ce6a5373c6f5c830be54be10775458a8bd312 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 11 Oct 2020 01:40:01 +0200 Subject: bpf: Improve bpf_redirect_neigh helper description Follow-up to address David's feedback that we should better describe internals of the bpf_redirect_neigh() helper. Suggested-by: David Ahern Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Reviewed-by: David Ahern Link: https://lore.kernel.org/bpf/20201010234006.7075-2-daniel@iogearbox.net --- include/uapi/linux/bpf.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 42d2df799397..4272cc53d478 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3679,10 +3679,14 @@ union bpf_attr { * Redirect the packet to another net device of index *ifindex* * and fill in L2 addresses from neighboring subsystem. This helper * is somewhat similar to **bpf_redirect**\ (), except that it - * fills in e.g. MAC addresses based on the L3 information from - * the packet. This helper is supported for IPv4 and IPv6 protocols. + * populates L2 addresses as well, meaning, internally, the helper + * performs a FIB lookup based on the skb's networking header to + * get the address of the next hop and then relies on the neighbor + * lookup for the L2 address of the nexthop. + * * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types. + * currently only supported for tc BPF program types, and enabled + * for IPv4 and IPv6 protocols. * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. -- cgit v1.2.3 From 9aa1206e8f48222f35a0c809f33b2f4aaa1e2661 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 11 Oct 2020 01:40:02 +0200 Subject: bpf: Add redirect_peer helper Add an efficient ingress to ingress netns switch that can be used out of tc BPF programs in order to redirect traffic from host ns ingress into a container veth device ingress without having to go via CPU backlog queue [0]. For local containers this can also be utilized and path via CPU backlog queue only needs to be taken once, not twice. On a high level this borrows from ipvlan which does similar switch in __netif_receive_skb_core() and then iterates via another_round. This helps to reduce latency for mentioned use cases. Pod to remote pod with redirect(), TCP_RR [1]: # percpu_netperf 10.217.1.33 RT_LATENCY: 122.450 (per CPU: 122.666 122.401 122.333 122.401 ) MEAN_LATENCY: 121.210 (per CPU: 121.100 121.260 121.320 121.160 ) STDDEV_LATENCY: 120.040 (per CPU: 119.420 119.910 125.460 115.370 ) MIN_LATENCY: 46.500 (per CPU: 47.000 47.000 47.000 45.000 ) P50_LATENCY: 118.500 (per CPU: 118.000 119.000 118.000 119.000 ) P90_LATENCY: 127.500 (per CPU: 127.000 128.000 127.000 128.000 ) P99_LATENCY: 130.750 (per CPU: 131.000 131.000 129.000 132.000 ) TRANSACTION_RATE: 32666.400 (per CPU: 8152.200 8169.842 8174.439 8169.897 ) Pod to remote pod with redirect_peer(), TCP_RR: # percpu_netperf 10.217.1.33 RT_LATENCY: 44.449 (per CPU: 43.767 43.127 45.279 45.622 ) MEAN_LATENCY: 45.065 (per CPU: 44.030 45.530 45.190 45.510 ) STDDEV_LATENCY: 84.823 (per CPU: 66.770 97.290 84.380 90.850 ) MIN_LATENCY: 33.500 (per CPU: 33.000 33.000 34.000 34.000 ) P50_LATENCY: 43.250 (per CPU: 43.000 43.000 43.000 44.000 ) P90_LATENCY: 46.750 (per CPU: 46.000 47.000 47.000 47.000 ) P99_LATENCY: 52.750 (per CPU: 51.000 54.000 53.000 53.000 ) TRANSACTION_RATE: 90039.500 (per CPU: 22848.186 23187.089 22085.077 21919.130 ) [0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf [1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net --- include/linux/netdevice.h | 4 ++++ include/uapi/linux/bpf.h | 17 +++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 28cfa53daf72..0533f86018dd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1277,6 +1277,9 @@ struct netdev_net_notifier { * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. + * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); + * If a device is paired with a peer device, return the peer instance. + * The caller must be under RCU read context. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1484,6 +1487,7 @@ struct net_device_ops { struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); + struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); }; /** diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4272cc53d478..b97bc5abb3b8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3719,6 +3719,22 @@ union bpf_attr { * never return NULL. * Return * A pointer pointing to the kernel percpu variable on this cpu. + * + * long bpf_redirect_peer(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_redirect**\ (), except + * that the redirection happens to the *ifindex*' peer device and + * the netns switch takes place from ingress to ingress without + * going through the CPU's backlog queue. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types at the ingress + * hook and for veth device types. The peer device must reside in a + * different network namespace. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3876,6 +3892,7 @@ union bpf_attr { FN(redirect_neigh), \ FN(bpf_per_cpu_ptr), \ FN(bpf_this_cpu_ptr), \ + FN(redirect_peer), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 4a8f87e60f6db40e640f1db555d063b2c4dea5f1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 11 Oct 2020 01:40:03 +0200 Subject: bpf: Allow for map-in-map with dynamic inner array map entries Recent work in f4d05259213f ("bpf: Add map_meta_equal map ops") and 134fede4eecf ("bpf: Relax max_entries check for most of the inner map types") added support for dynamic inner max elements for most map-in-map types. Exceptions were maps like array or prog array where the map_gen_lookup() callback uses the maps' max_entries field as a constant when emitting instructions. We recently implemented Maglev consistent hashing into Cilium's load balancer which uses map-in-map with an outer map being hash and inner being array holding the Maglev backend table for each service. This has been designed this way in order to reduce overall memory consumption given the outer hash map allows to avoid preallocating a large, flat memory area for all services. Also, the number of service mappings is not always known a-priori. The use case for dynamic inner array map entries is to further reduce memory overhead, for example, some services might just have a small number of back ends while others could have a large number. Right now the Maglev backend table for small and large number of backends would need to have the same inner array map entries which adds a lot of unneeded overhead. Dynamic inner array map entries can be realized by avoiding the inlined code generation for their lookup. The lookup will still be efficient since it will be calling into array_map_lookup_elem() directly and thus avoiding retpoline. The patch adds a BPF_F_INNER_MAP flag to map creation which therefore skips inline code generation and relaxes array_map_meta_equal() check to ignore both maps' max_entries. This also still allows to have faster lookups for map-in-map when BPF_F_INNER_MAP is not specified and hence dynamic max_entries not needed. Example code generation where inner map is dynamic sized array: # bpftool p d x i 125 int handle__sys_enter(void * ctx): ; int handle__sys_enter(void *ctx) 0: (b4) w1 = 0 ; int key = 0; 1: (63) *(u32 *)(r10 -4) = r1 2: (bf) r2 = r10 ; 3: (07) r2 += -4 ; inner_map = bpf_map_lookup_elem(&outer_arr_dyn, &key); 4: (18) r1 = map[id:468] 6: (07) r1 += 272 7: (61) r0 = *(u32 *)(r2 +0) 8: (35) if r0 >= 0x3 goto pc+5 9: (67) r0 <<= 3 10: (0f) r0 += r1 11: (79) r0 = *(u64 *)(r0 +0) 12: (15) if r0 == 0x0 goto pc+1 13: (05) goto pc+1 14: (b7) r0 = 0 15: (b4) w6 = -1 ; if (!inner_map) 16: (15) if r0 == 0x0 goto pc+6 17: (bf) r2 = r10 ; 18: (07) r2 += -4 ; val = bpf_map_lookup_elem(inner_map, &key); 19: (bf) r1 = r0 | No inlining but instead 20: (85) call array_map_lookup_elem#149280 | call to array_map_lookup_elem() ; return val ? *val : -1; | for inner array lookup. 21: (15) if r0 == 0x0 goto pc+1 ; return val ? *val : -1; 22: (61) r6 = *(u32 *)(r0 +0) ; } 23: (bc) w0 = w6 24: (95) exit Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201010234006.7075-4-daniel@iogearbox.net --- include/linux/bpf.h | 2 +- include/uapi/linux/bpf.h | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index dc63eeed4fd9..2b16bf48aab6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -82,7 +82,7 @@ struct bpf_map_ops { void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); void (*map_fd_put_ptr)(void *ptr); - u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); + int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b97bc5abb3b8..bf5a99d803e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -435,6 +435,9 @@ enum { /* Share perf_event among processes */ BPF_F_PRESERVE_ELEMS = (1U << 11), + +/* Create a map that is suitable to be an inner map with dynamic max entries */ + BPF_F_INNER_MAP = (1U << 12), }; /* Flags for BPF_PROG_QUERY. */ -- cgit v1.2.3 From 8b7b2eb131d3476062ffd34358785b44be25172f Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 10 Oct 2020 23:16:37 -0700 Subject: mm: validate inode in mapping_set_error() The swap address_space doesn't have host. Thus, it makes kernel crash once swap write meets error. Fix it. Fixes: 735e4ae5ba28 ("vfs: track per-sb writeback errors and report them to syncfs") Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Acked-by: Jeff Layton Cc: Jan Kara Cc: Andres Freund Cc: Matthew Wilcox Cc: Al Viro Cc: Christoph Hellwig Cc: Dave Chinner Cc: David Howells Cc: Link: https://lkml.kernel.org/r/20201010000650.750063-1-minchan@kernel.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7de11dcd534d..434c9c34aeb6 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -54,7 +54,8 @@ static inline void mapping_set_error(struct address_space *mapping, int error) __filemap_set_wb_err(mapping, error); /* Record it in superblock */ - errseq_set(&mapping->host->i_sb->s_wb_err, error); + if (mapping->host) + errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) -- cgit v1.2.3 From 4aab2be0983031a05cb4a19696c9da5749523426 Mon Sep 17 00:00:00 2001 From: Vijay Balakrishna Date: Sat, 10 Oct 2020 23:16:40 -0700 Subject: mm: khugepaged: recalculate min_free_kbytes after memory hotplug as expected by khugepaged When memory is hotplug added or removed the min_free_kbytes should be recalculated based on what is expected by khugepaged. Currently after hotplug, min_free_kbytes will be set to a lower default and higher default set when THP enabled is lost. This change restores min_free_kbytes as expected for THP consumers. [vijayb@linux.microsoft.com: v5] Link: https://lkml.kernel.org/r/1601398153-5517-1-git-send-email-vijayb@linux.microsoft.com Fixes: f000565adb77 ("thp: set recommended min free kbytes") Signed-off-by: Vijay Balakrishna Signed-off-by: Andrew Morton Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Allen Pais Cc: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Oleg Nesterov Cc: Song Liu Cc: Link: https://lkml.kernel.org/r/1600305709-2319-2-git-send-email-vijayb@linux.microsoft.com Link: https://lkml.kernel.org/r/1600204258-13683-1-git-send-email-vijayb@linux.microsoft.com Signed-off-by: Linus Torvalds --- include/linux/khugepaged.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index bc45ea1efbf7..c941b7377321 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -15,6 +15,7 @@ extern int __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, unsigned long vm_flags); +extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); #else @@ -85,6 +86,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) { } + +static inline void khugepaged_min_free_kbytes_update(void) +{ +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_KHUGEPAGED_H */ -- cgit v1.2.3 From 60a3815da702fd9e4759945f26cce5c47d3967ad Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 8 Oct 2020 01:14:47 +0200 Subject: netfilter: add inet ingress support This patch adds the NF_INET_INGRESS pseudohook for the NFPROTO_INET family. This is a mapping this new hook to the existing NFPROTO_NETDEV and NF_NETDEV_INGRESS hook. The hook does not guarantee that packets are inet only, users must filter out non-ip traffic explicitly. This infrastructure makes it easier to support this new hook in nf_tables. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index ca9e63d6e0e4..6a6179af0d7c 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -45,6 +45,7 @@ enum nf_inet_hooks { NF_INET_FORWARD, NF_INET_LOCAL_OUT, NF_INET_POST_ROUTING, + NF_INET_INGRESS, NF_INET_NUMHOOKS }; -- cgit v1.2.3 From d3519cb89f6d5949481afa5de3ee0fc6a051e231 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 8 Oct 2020 01:14:48 +0200 Subject: netfilter: nf_tables: add inet ingress support This patch adds a new ingress hook for the inet family. The inet ingress hook emulates the IP receive path code, therefore, unclean packets are drop before walking over the ruleset in this basechain. This patch also introduces the nft_base_chain_netdev() helper function to check if this hook is bound to one or more devices (through the hook list infrastructure). This check allows to perform the same handling for the inet ingress as it would be a netdev ingress chain from the control plane. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 +++++ include/net/netfilter/nf_tables_ipv4.h | 33 ++++++++++++++++++++++++ include/net/netfilter/nf_tables_ipv6.h | 46 ++++++++++++++++++++++++++++++++++ 3 files changed, 85 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0bd2a081ae39..3965ce18226f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1081,6 +1081,12 @@ struct nft_table { u8 *udata; }; +static inline bool nft_base_chain_netdev(int family, u32 hooknum) +{ + return family == NFPROTO_NETDEV || + (family == NFPROTO_INET && hooknum == NF_INET_INGRESS); +} + void nft_register_chain_type(const struct nft_chain_type *); void nft_unregister_chain_type(const struct nft_chain_type *); diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index ed7b511f0a59..1f7bea39ad1b 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -53,4 +53,37 @@ static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, nft_set_pktinfo_unspec(pkt, skb); } +static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt, + struct sk_buff *skb) +{ + struct iphdr *iph; + u32 len, thoff; + + if (!pskb_may_pull(skb, sizeof(*iph))) + return -1; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + goto inhdr_error; + + len = ntohs(iph->tot_len); + thoff = iph->ihl * 4; + if (skb->len < len) { + __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); + return -1; + } else if (len < thoff) { + goto inhdr_error; + } + + pkt->tprot_set = true; + pkt->tprot = iph->protocol; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; + + return 0; + +inhdr_error: + __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INHDRERRORS); + return -1; +} #endif diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index d0f1c537b017..867de29f3f7a 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -70,4 +70,50 @@ static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, nft_set_pktinfo_unspec(pkt, skb); } +static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, + struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_IPV6) + unsigned int flags = IP6_FH_F_AUTH; + unsigned short frag_off; + unsigned int thoff = 0; + struct inet6_dev *idev; + struct ipv6hdr *ip6h; + int protohdr; + u32 pkt_len; + + if (!pskb_may_pull(skb, sizeof(*ip6h))) + return -1; + + ip6h = ipv6_hdr(skb); + if (ip6h->version != 6) + goto inhdr_error; + + pkt_len = ntohs(ip6h->payload_len); + if (pkt_len + sizeof(*ip6h) > skb->len) { + idev = __in6_dev_get(nft_in(pkt)); + __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS); + return -1; + } + + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); + if (protohdr < 0) + goto inhdr_error; + + pkt->tprot_set = true; + pkt->tprot = protohdr; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = frag_off; + + return 0; + +inhdr_error: + idev = __in6_dev_get(nft_in(pkt)); + __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INHDRERRORS); + return -1; +#else + return -1; +#endif +} + #endif -- cgit v1.2.3 From ef5659280eb13e8ac31c296f58cfdfa1684ac06b Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 10 Oct 2020 22:09:38 -0700 Subject: bpf, sockmap: Allow skipping sk_skb parser program Currently, we often run with a nop parser namely one that just does this, 'return skb->len'. This happens when either our verdict program can handle streaming data or it is only looking at socket data such as IP addresses and other metadata associated with the flow. The second case is common for a L3/L4 proxy for instance. So lets allow loading programs without the parser then we can skip the stream parser logic and avoid having to add a BPF program that is effectively a nop. Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower --- include/linux/skmsg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 3119928fc103..fec0c5ac1c4f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -308,6 +308,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node); int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); +void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock); +void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); -- cgit v1.2.3 From ac911bfeb34b5d79fb4e23a08b8db0b89c529b53 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 12 Oct 2020 09:43:53 +0200 Subject: can: isotp: implement cleanups / improvements from review As pointed out by Jakub Kicinski here: http://lore.kernel.org/r/20201009175751.5c54097f@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com this patch addresses the remarked issues: - remove empty line in comment - remove default=y for CAN_ISOTP in Kconfig - make use of pr_notice_once() - use GFP_ATOMIC instead of gfp_any() in soft hrtimer context The version strings in the CAN subsystem are removed by a separate patch. Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20201012074354.25839-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 553006509f4e..7793b26aa154 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -160,7 +160,6 @@ struct can_isotp_ll_options { * these default settings can be changed via sockopts. * For that reason the STmin value is intentionally _not_ checked for * consistency and copied directly into the flow control (FC) frame. - * */ #endif /* !_UAPI_CAN_ISOTP_H */ -- cgit v1.2.3 From f726f3d37163f714034aa5fd1f92a1a73df4297f Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 12 Oct 2020 09:43:54 +0200 Subject: can: remove obsolete version strings As pointed out by Jakub Kicinski here: http://lore.kernel.org/r/20201009175751.5c54097f@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com this patch removes the obsolete version information of the different CAN protocols and the AF_CAN core module. Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20201012074354.25839-2-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 7 ------- include/net/netns/can.h | 1 - 2 files changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 7da9f1f82e8e..5fb8d0e3f9c1 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -18,13 +18,6 @@ #include #include -#define CAN_VERSION "20170425" - -/* increment this number each time you change some user-space interface */ -#define CAN_ABI_VERSION "9" - -#define CAN_VERSION_STRING "rev " CAN_VERSION " abi " CAN_ABI_VERSION - #define DNAME(dev) ((dev) ? (dev)->name : "any") /** diff --git a/include/net/netns/can.h b/include/net/netns/can.h index b6ab7d1530d7..52fbd8291a96 100644 --- a/include/net/netns/can.h +++ b/include/net/netns/can.h @@ -15,7 +15,6 @@ struct can_rcv_lists_stats; struct netns_can { #if IS_ENABLED(CONFIG_PROC_FS) struct proc_dir_entry *proc_dir; - struct proc_dir_entry *pde_version; struct proc_dir_entry *pde_stats; struct proc_dir_entry *pde_reset_stats; struct proc_dir_entry *pde_rcvlist_all; -- cgit v1.2.3 From 585834a5eeb38a9b290786b6d3ee55f22098c602 Mon Sep 17 00:00:00 2001 From: zhuguangqing Date: Thu, 17 Sep 2020 15:35:53 +0800 Subject: thermal/idle_inject: Fix comment of idle_duration_us and name of latency_ns The comment of idle_duration_us and the name of latency_ns can be misleading, so fix them. Signed-off-by: zhuguangqing Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200917073553.898-1-zhuguangqing83@gmail.com --- include/linux/idle_inject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h index 91a8612b8bf9..fb88e23a99d3 100644 --- a/include/linux/idle_inject.h +++ b/include/linux/idle_inject.h @@ -28,6 +28,6 @@ void idle_inject_get_duration(struct idle_inject_device *ii_dev, unsigned int *idle_duration_us); void idle_inject_set_latency(struct idle_inject_device *ii_dev, - unsigned int latency_ns); + unsigned int latency_us); #endif /* __IDLE_INJECT_H__ */ -- cgit v1.2.3 From 88052319620a35f827509d645e4c8063ded751c8 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 15 Sep 2020 15:36:49 -0700 Subject: thermal: core: Add new event for sending keep alive notifications This event is sent by the platform firmware to confirm that user space thermal solution is alive. The response to this event from the user space thermal solution is platform specific. Signed-off-by: Srinivas Pandruvada Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200915223650.406046-3-srinivas.pandruvada@linux.intel.com --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 42ef807e5d84..42b69d4072a4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -55,6 +55,7 @@ enum thermal_notify_event { THERMAL_DEVICE_UP, /* Thermal device is up after a down event */ THERMAL_DEVICE_POWER_CAPABILITY_CHANGED, /* power capability changed */ THERMAL_TABLE_CHANGED, /* Thermal table(s) changed */ + THERMAL_EVENT_KEEP_ALIVE, /* Request for user space handler to respond */ }; struct thermal_zone_device_ops { -- cgit v1.2.3 From ecd1d2a3e4f893584578a304d7bd1591e895a8e4 Mon Sep 17 00:00:00 2001 From: zhuguangqing Date: Mon, 14 Sep 2020 15:11:01 +0800 Subject: thermal: cooling: Remove unused variable *tz 1. devfreq_cooling.c: The variable *tz is not used in devfreq_cooling_get_requested_power(), devfreq_cooling_state2power() and devfreq_cooling_power2state(). 2. cpufreq_cooling.c: After 84fe2cab48590, the variable *tz is not used anymore in cpufreq_get_requested_power(), cpufreq_state2power() and cpufreq_power2state(). Remove the variable *tz. Signed-off-by: zhuguangqing Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200914071101.13575-1-zhuguangqing83@gmail.com --- include/linux/thermal.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 42b69d4072a4..d07ea27e72a9 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -85,12 +85,9 @@ struct thermal_cooling_device_ops { int (*get_max_state) (struct thermal_cooling_device *, unsigned long *); int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *); int (*set_cur_state) (struct thermal_cooling_device *, unsigned long); - int (*get_requested_power)(struct thermal_cooling_device *, - struct thermal_zone_device *, u32 *); - int (*state2power)(struct thermal_cooling_device *, - struct thermal_zone_device *, unsigned long, u32 *); - int (*power2state)(struct thermal_cooling_device *, - struct thermal_zone_device *, u32, unsigned long *); + int (*get_requested_power)(struct thermal_cooling_device *, u32 *); + int (*state2power)(struct thermal_cooling_device *, unsigned long, u32 *); + int (*power2state)(struct thermal_cooling_device *, u32, unsigned long *); }; struct thermal_cooling_device { -- cgit v1.2.3 From a6e7d0a4bdb02a7a3ffe0b44aaa8842b7efdd056 Mon Sep 17 00:00:00 2001 From: Kai Vehmanen Date: Mon, 12 Oct 2020 13:27:04 +0300 Subject: ALSA: hda: fix jack detection with Realtek codecs when in D3 In case HDA controller becomes active, but codec is runtime suspended, jack detection is not successful and no interrupt is raised. This has been observed with multiple Realtek codecs and HDA controllers from different vendors. Bug does not occur if both codec and controller are active, or both are in suspend. Bug can be easily hit on desktop systems with no built-in speaker. The problem can be fixed by powering up the codec once after every controller runtime resume. Even if codec goes back to suspend later, the jack detection will continue to work. Add a flag to 'hda_codec' to describe codecs that require this flow from the controller driver. Modify __azx_runtime_resume() to use pm_request_resume() to make the intent clearer. Mark all Realtek codecs with the new forced_resume flag. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=209379 Cc: Kailang Yang Co-developed-by: Kai-Heng Feng Signed-off-by: Kai-Heng Feng Signed-off-by: Kai Vehmanen Cc: Link: https://lore.kernel.org/r/20201012102704.794423-1-kai.vehmanen@linux.intel.com Signed-off-by: Takashi Iwai --- include/sound/hda_codec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 0fea49bfc5e8..73827b7d17e0 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -253,6 +253,7 @@ struct hda_codec { unsigned int force_pin_prefix:1; /* Add location prefix */ unsigned int link_down_at_suspend:1; /* link down at runtime suspend */ unsigned int relaxed_resume:1; /* don't resume forcibly for jack */ + unsigned int forced_resume:1; /* forced resume for jack */ unsigned int mst_no_extra_pcms:1; /* no backup PCMs for DP-MST */ #ifdef CONFIG_PM -- cgit v1.2.3 From 3986f9a42e993075af01c17dc8968cfb96a4fe53 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 17 Aug 2020 13:45:04 +0200 Subject: libceph: multiple workspaces for CRUSH computations Replace a global map->crush_workspace (protected by a global mutex) with a list of workspaces, up to the number of CPUs + 1. This is based on a patch from Robin Geuze . Robin and his team have observed a 10-20% increase in IOPS on all queue depths and lower CPU usage as well on a high-end all-NVMe 100GbE cluster. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osdmap.h | 14 ++++++++++++-- include/linux/crush/crush.h | 3 +++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 3f4498fef6ad..cad9acfbc320 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -137,6 +137,17 @@ int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp, const char *fmt, ...); void ceph_oid_destroy(struct ceph_object_id *oid); +struct workspace_manager { + struct list_head idle_ws; + spinlock_t ws_lock; + /* Number of free workspaces */ + int free_ws; + /* Total number of allocated workspaces */ + atomic_t total_ws; + /* Waiters for a free workspace */ + wait_queue_head_t ws_wait; +}; + struct ceph_pg_mapping { struct rb_node node; struct ceph_pg pgid; @@ -184,8 +195,7 @@ struct ceph_osdmap { * the list of osds that store+replicate them. */ struct crush_map *crush; - struct mutex crush_workspace_mutex; - void *crush_workspace; + struct workspace_manager crush_wsm; }; static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd) diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 2f811baf78d2..30dba392b730 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -346,6 +346,9 @@ struct crush_work_bucket { struct crush_work { struct crush_work_bucket **work; /* Per-bucket working store */ +#ifdef __KERNEL__ + struct list_head item; +#endif }; #ifdef __KERNEL__ -- cgit v1.2.3 From 0b98acd6188309333c3a8a6e16feadadd31e4523 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 14 Sep 2020 13:39:19 +0200 Subject: libceph, rbd, ceph: "blacklist" -> "blocklist" Signed-off-by: Ilya Dryomov --- include/linux/ceph/mon_client.h | 2 +- include/linux/ceph/rados.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index ce4ffeb384d7..b658961156a0 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -142,7 +142,7 @@ int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what, int ceph_monc_get_version_async(struct ceph_mon_client *monc, const char *what, ceph_monc_callback_t cb, u64 private_data); -int ceph_monc_blacklist_add(struct ceph_mon_client *monc, +int ceph_monc_blocklist_add(struct ceph_mon_client *monc, struct ceph_entity_addr *client_addr); extern int ceph_monc_open_session(struct ceph_mon_client *monc); diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 3a518fd0eaad..43a7a1573b51 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -424,7 +424,7 @@ enum { }; #define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ -#define EBLACKLISTED ESHUTDOWN /* blacklisted */ +#define EBLOCKLISTED ESHUTDOWN /* blocklisted */ /* xattr comparison */ enum { -- cgit v1.2.3 From b07720d0bd1e7c2251642010efb6075dbee23bb8 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 2 Oct 2020 14:38:08 +0200 Subject: libceph: fix ENTITY_NAME format suggestion Signed-off-by: Ilya Dryomov --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 76371aaae2d1..60b324efd1c4 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -54,7 +54,7 @@ struct ceph_connection_operations { int (*check_message_signature) (struct ceph_msg *msg); }; -/* use format string %s%d */ +/* use format string %s%lld */ #define ENTITY_NAME(n) ceph_entity_type_name((n).type), le64_to_cpu((n).num) struct ceph_messenger { -- cgit v1.2.3 From 9b80e4c4ddaca3501177ed41e49d0928ba2122a8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Aug 2020 14:47:03 -0700 Subject: overflow: Add __must_check attribute to check_*() helpers Since the destination variable of the check_*_overflow() helpers will contain a wrapped value on failure, it would be best to make sure callers really did check the return result of the helper. Adjust the macros to use a bool-wrapping static inline that is marked with __must_check. This means the macros can continue to have their type-agnostic behavior while gaining the function attribute (that cannot be applied directly to macros). Suggested-by: Rasmus Villemoes Link: https://lore.kernel.org/lkml/202008151007.EF679DF@keescook/ Signed-off-by: Kees Cook --- include/linux/overflow.h | 39 ++++++++++++++++++++++++--------------- 1 file changed, 24 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 93fcef105061..f1c4e7b56bd9 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -43,6 +43,16 @@ #define is_non_negative(a) ((a) > 0 || (a) == 0) #define is_negative(a) (!(is_non_negative(a))) +/* + * Allows for effectively applying __must_check to a macro so we can have + * both the type-agnostic benefits of the macros while also being able to + * enforce that the return value is, in fact, checked. + */ +static inline bool __must_check __must_check_overflow(bool overflow) +{ + return unlikely(overflow); +} + #ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on @@ -52,32 +62,32 @@ * alias for __builtin_add_overflow, but add type checks similar to * below. */ -#define check_add_overflow(a, b, d) ({ \ +#define check_add_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_add_overflow(__a, __b, __d); \ -}) +})) -#define check_sub_overflow(a, b, d) ({ \ +#define check_sub_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_sub_overflow(__a, __b, __d); \ -}) +})) -#define check_mul_overflow(a, b, d) ({ \ +#define check_mul_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_mul_overflow(__a, __b, __d); \ -}) +})) #else @@ -190,21 +200,20 @@ }) -#define check_add_overflow(a, b, d) \ +#define check_add_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d)) + __unsigned_add_overflow(a, b, d))) -#define check_sub_overflow(a, b, d) \ +#define check_sub_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d)) + __unsigned_sub_overflow(a, b, d))) -#define check_mul_overflow(a, b, d) \ +#define check_mul_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d)) - + __unsigned_mul_overflow(a, b, d))) #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ @@ -227,7 +236,7 @@ * '*d' will hold the results of the attempted shift, but is not * considered "safe for use" if false is returned. */ -#define check_shl_overflow(a, s, d) ({ \ +#define check_shl_overflow(a, s, d) __must_check_overflow(({ \ typeof(a) _a = a; \ typeof(s) _s = s; \ typeof(d) _d = d; \ @@ -237,7 +246,7 @@ *_d = (_a_full << _to_shift); \ (_to_shift != _s || is_negative(*_d) || is_negative(_a) || \ (*_d >> _to_shift) != _a); \ -}) +})) /** * array_size() - Calculate size of 2-dimensional array. -- cgit v1.2.3 From ee92e4f1f95eb7b8820299f10fc5fba16d85cece Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Wed, 8 Apr 2020 14:47:39 -0500 Subject: net/mlx5: Add NIC TX domain namespace Add new namespace that represents the NIC TX domain. Signed-off-by: Huy Nguyen Signed-off-by: Raed Salem Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 92d991d93757..846d94ad04bc 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -76,6 +76,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_SNIFFER_RX, MLX5_FLOW_NAMESPACE_SNIFFER_TX, MLX5_FLOW_NAMESPACE_EGRESS, + MLX5_FLOW_NAMESPACE_EGRESS_KERNEL, MLX5_FLOW_NAMESPACE_RDMA_RX, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, MLX5_FLOW_NAMESPACE_RDMA_TX, -- cgit v1.2.3 From 9b9d454ddbf0c41391ed68ea82bc3d8ff6a65074 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 5 Jun 2020 20:17:51 -0500 Subject: net/mlx5e: IPsec: Add TX steering rule per IPsec state Add new FTE in TX IPsec FT per IPsec state. It has the same matching criteria as the RX steering rule. The IPsec FT is created/destroyed when the first/last rule is added/deleted respectively. Signed-off-by: Huy Nguyen Reviewed-by: Boris Pismenny Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/qp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 36492a1342cf..d75ef8aa8fac 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -245,6 +245,10 @@ enum { MLX5_ETH_WQE_SWP_OUTER_L4_UDP = 1 << 5, }; +enum { + MLX5_ETH_WQE_FT_META_IPSEC = BIT(0), +}; + struct mlx5_wqe_eth_seg { u8 swp_outer_l4_offset; u8 swp_outer_l3_offset; @@ -253,7 +257,7 @@ struct mlx5_wqe_eth_seg { u8 cs_flags; u8 swp_flags; __be16 mss; - __be32 rsvd2; + __be32 flow_table_metadata; union { struct { __be16 sz; -- cgit v1.2.3 From 3528f8ec95a5b1ee1b98d3e85371843c6428e4be Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:28:58 -0700 Subject: bcm963xx_tag.h: fix duplicated word Change doubled word "is" to "it is". Signed-off-by: Randy Dunlap Cc: Florian Fainelli Cc: bcm-kernel-feedback-list@broadcom.com Cc: linux-mips@vger.kernel.org Acked-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer --- include/linux/bcm963xx_tag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bcm963xx_tag.h b/include/linux/bcm963xx_tag.h index b87945cb6946..7edb809a2586 100644 --- a/include/linux/bcm963xx_tag.h +++ b/include/linux/bcm963xx_tag.h @@ -84,7 +84,7 @@ struct bcm_tag { char flash_layout_ver[FLASHLAYOUTVER_LEN]; /* 196-199: kernel+rootfs CRC32 */ __u32 fskernel_crc; - /* 200-215: Unused except on Alice Gate where is is information */ + /* 200-215: Unused except on Alice Gate where it is information */ char information2[TAGINFO2_LEN]; /* 216-219: CRC32 of image less imagetag (kernel for Alice Gate) */ __u32 image_crc; -- cgit v1.2.3 From f82cd2f0b5eb715b1a296e20b34da7d296b6e9a4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 18 Aug 2020 09:05:56 -0400 Subject: XArray: Add private interface for workingset node deletion Move the tricky bits of dealing with the XArray from the workingset code to the XArray. Make it clear in the documentation that this is a private interface, and only export it for the benefit of the test suite. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 6b336098fca7..29db4e16eb89 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1286,6 +1286,8 @@ static inline bool xa_is_advanced(const void *entry) */ typedef void (*xa_update_node_t)(struct xa_node *node); +void xa_delete_node(struct xa_node *, xa_update_node_t); + /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be -- cgit v1.2.3 From ca7b639e8611b3260a30b18aaa0d6db9c80a75ef Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 2 Aug 2020 14:17:21 -0400 Subject: XArray: Fix xas_reload for multi-index entries xas_reload() was only checking that the head entry was still at the head index. If the entry has been split, that's not enough as there may be a different entry at the specified index now. Solve this by checking the slot for the requested index instead of the head index. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 29db4e16eb89..4be9c57132fe 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1524,10 +1524,21 @@ void xas_create_range(struct xa_state *); static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; - - if (node) - return xa_entry(xas->xa, node, xas->xa_offset); - return xa_head(xas->xa); + void *entry; + char offset; + + if (!node) + return xa_head(xas->xa); + if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { + offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; + entry = xa_entry(xas->xa, node, offset); + if (!xa_is_sibling(entry)) + return entry; + offset = xa_to_sibling(entry); + } else { + offset = xas->xa_offset; + } + return xa_entry(xas->xa, node, offset); } /** -- cgit v1.2.3 From f78b8250a076ac63ddd021c7ea9739bcc2f6f737 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Mon, 28 Sep 2020 01:15:53 +0800 Subject: radix-tree: fix the comment of radix_tree_next_slot() fix the comment of radix_tree_next_slot(): interator --> iterator. Signed-off-by: Hui Su Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/radix-tree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 5c85059a92ba..64ad900ac742 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -377,7 +377,7 @@ radix_tree_chunk_size(struct radix_tree_iter *iter) * radix_tree_next_slot - find next slot in chunk * * @slot: pointer to current slot - * @iter: pointer to interator state + * @iter: pointer to iterator state * @flags: RADIX_TREE_ITER_*, should be constant * Returns: pointer to next slot, or NULL if there no more left * -- cgit v1.2.3 From 3b481d91356e5693d8358d4ef9c383bdb92c8da0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 24 Sep 2020 13:53:28 -0700 Subject: block: add zone specific block statuses A zoned device with limited resources to open or activate zones may return an error when the host exceeds those limits. The same command may be successful if retried later, but the host needs to wait for specific zone states before it should expect a retry to succeed. Have the block layer provide an appropriate status for these conditions so applications can distinuguish this error for special handling. Cc: linux-api@vger.kernel.org Cc: Niklas Cassel Reviewed-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Reviewed-by: Martin K. Petersen Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 7d7c13238fdb..d9b69bbde5cc 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -104,6 +104,24 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) +/* + * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion + * path if the device returns a status indicating that too many zone resources + * are currently open. The same command should be successful if resubmitted + * after the number of open zones decreases below the device's limits, which is + * reported in the request_queue's max_open_zones. + */ +#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) + +/* + * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion + * path if the device returns a status indicating that too many zone resources + * are currently active. The same command should be successful if resubmitted + * after the number of active zones decreases below the device's limits, which + * is reported in the request_queue's max_active_zones. + */ +#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with -- cgit v1.2.3 From 8adea9b9459cf2ea9538cd0765a12200306179df Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Fri, 18 Sep 2020 15:23:02 +0200 Subject: dt-bindings: clock: mediatek: add bindings for MT8167 clocks Add binding documentation for topckgen, apmixedsys, infracfg, audsys, imgsys, mfgcfg, vdecsys on MT8167 SoC. Signed-off-by: Fabien Parent Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20200918132303.2831815-1-fparent@baylibre.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/mt8167-clk.h | 131 +++++++++++++++++++++++++++++++++ 1 file changed, 131 insertions(+) create mode 100644 include/dt-bindings/clock/mt8167-clk.h (limited to 'include') diff --git a/include/dt-bindings/clock/mt8167-clk.h b/include/dt-bindings/clock/mt8167-clk.h new file mode 100644 index 000000000000..a96158edd817 --- /dev/null +++ b/include/dt-bindings/clock/mt8167-clk.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + * Copyright (c) 2020 BayLibre, SAS. + * Author: James Liao + * Fabien Parent + */ + +#ifndef _DT_BINDINGS_CLK_MT8167_H +#define _DT_BINDINGS_CLK_MT8167_H + +/* MT8167 is based on MT8516 */ +#include + +/* APMIXEDSYS */ + +#define CLK_APMIXED_TVDPLL (CLK_APMIXED_NR_CLK + 0) +#define CLK_APMIXED_LVDSPLL (CLK_APMIXED_NR_CLK + 1) +#define CLK_APMIXED_HDMI_REF (CLK_APMIXED_NR_CLK + 2) +#define MT8167_CLK_APMIXED_NR_CLK (CLK_APMIXED_NR_CLK + 3) + +/* TOPCKGEN */ + +#define CLK_TOP_DSI0_LNTC_DSICK (CLK_TOP_NR_CLK + 0) +#define CLK_TOP_VPLL_DPIX (CLK_TOP_NR_CLK + 1) +#define CLK_TOP_LVDSTX_CLKDIG_CTS (CLK_TOP_NR_CLK + 2) +#define CLK_TOP_HDMTX_CLKDIG_CTS (CLK_TOP_NR_CLK + 3) +#define CLK_TOP_LVDSPLL (CLK_TOP_NR_CLK + 4) +#define CLK_TOP_LVDSPLL_D2 (CLK_TOP_NR_CLK + 5) +#define CLK_TOP_LVDSPLL_D4 (CLK_TOP_NR_CLK + 6) +#define CLK_TOP_LVDSPLL_D8 (CLK_TOP_NR_CLK + 7) +#define CLK_TOP_MIPI_26M (CLK_TOP_NR_CLK + 8) +#define CLK_TOP_TVDPLL (CLK_TOP_NR_CLK + 9) +#define CLK_TOP_TVDPLL_D2 (CLK_TOP_NR_CLK + 10) +#define CLK_TOP_TVDPLL_D4 (CLK_TOP_NR_CLK + 11) +#define CLK_TOP_TVDPLL_D8 (CLK_TOP_NR_CLK + 12) +#define CLK_TOP_TVDPLL_D16 (CLK_TOP_NR_CLK + 13) +#define CLK_TOP_PWM_MM (CLK_TOP_NR_CLK + 14) +#define CLK_TOP_CAM_MM (CLK_TOP_NR_CLK + 15) +#define CLK_TOP_MFG_MM (CLK_TOP_NR_CLK + 16) +#define CLK_TOP_SPM_52M (CLK_TOP_NR_CLK + 17) +#define CLK_TOP_MIPI_26M_DBG (CLK_TOP_NR_CLK + 18) +#define CLK_TOP_SCAM_MM (CLK_TOP_NR_CLK + 19) +#define CLK_TOP_SMI_MM (CLK_TOP_NR_CLK + 20) +#define CLK_TOP_26M_HDMI_SIFM (CLK_TOP_NR_CLK + 21) +#define CLK_TOP_26M_CEC (CLK_TOP_NR_CLK + 22) +#define CLK_TOP_32K_CEC (CLK_TOP_NR_CLK + 23) +#define CLK_TOP_GCPU_B (CLK_TOP_NR_CLK + 24) +#define CLK_TOP_RG_VDEC (CLK_TOP_NR_CLK + 25) +#define CLK_TOP_RG_FDPI0 (CLK_TOP_NR_CLK + 26) +#define CLK_TOP_RG_FDPI1 (CLK_TOP_NR_CLK + 27) +#define CLK_TOP_RG_AXI_MFG (CLK_TOP_NR_CLK + 28) +#define CLK_TOP_RG_SLOW_MFG (CLK_TOP_NR_CLK + 29) +#define CLK_TOP_GFMUX_EMI1X_SEL (CLK_TOP_NR_CLK + 30) +#define CLK_TOP_CSW_MUX_MFG_SEL (CLK_TOP_NR_CLK + 31) +#define CLK_TOP_CAMTG_MM_SEL (CLK_TOP_NR_CLK + 32) +#define CLK_TOP_PWM_MM_SEL (CLK_TOP_NR_CLK + 33) +#define CLK_TOP_SPM_52M_SEL (CLK_TOP_NR_CLK + 34) +#define CLK_TOP_MFG_MM_SEL (CLK_TOP_NR_CLK + 35) +#define CLK_TOP_SMI_MM_SEL (CLK_TOP_NR_CLK + 36) +#define CLK_TOP_SCAM_MM_SEL (CLK_TOP_NR_CLK + 37) +#define CLK_TOP_VDEC_MM_SEL (CLK_TOP_NR_CLK + 38) +#define CLK_TOP_DPI0_MM_SEL (CLK_TOP_NR_CLK + 39) +#define CLK_TOP_DPI1_MM_SEL (CLK_TOP_NR_CLK + 40) +#define CLK_TOP_AXI_MFG_IN_SEL (CLK_TOP_NR_CLK + 41) +#define CLK_TOP_SLOW_MFG_SEL (CLK_TOP_NR_CLK + 42) +#define MT8167_CLK_TOP_NR_CLK (CLK_TOP_NR_CLK + 43) + +/* MFGCFG */ + +#define CLK_MFG_BAXI 0 +#define CLK_MFG_BMEM 1 +#define CLK_MFG_BG3D 2 +#define CLK_MFG_B26M 3 +#define CLK_MFG_NR_CLK 4 + +/* MMSYS */ + +#define CLK_MM_SMI_COMMON 0 +#define CLK_MM_SMI_LARB0 1 +#define CLK_MM_CAM_MDP 2 +#define CLK_MM_MDP_RDMA 3 +#define CLK_MM_MDP_RSZ0 4 +#define CLK_MM_MDP_RSZ1 5 +#define CLK_MM_MDP_TDSHP 6 +#define CLK_MM_MDP_WDMA 7 +#define CLK_MM_MDP_WROT 8 +#define CLK_MM_FAKE_ENG 9 +#define CLK_MM_DISP_OVL0 10 +#define CLK_MM_DISP_RDMA0 11 +#define CLK_MM_DISP_RDMA1 12 +#define CLK_MM_DISP_WDMA 13 +#define CLK_MM_DISP_COLOR 14 +#define CLK_MM_DISP_CCORR 15 +#define CLK_MM_DISP_AAL 16 +#define CLK_MM_DISP_GAMMA 17 +#define CLK_MM_DISP_DITHER 18 +#define CLK_MM_DISP_UFOE 19 +#define CLK_MM_DISP_PWM_MM 20 +#define CLK_MM_DISP_PWM_26M 21 +#define CLK_MM_DSI_ENGINE 22 +#define CLK_MM_DSI_DIGITAL 23 +#define CLK_MM_DPI0_ENGINE 24 +#define CLK_MM_DPI0_PXL 25 +#define CLK_MM_LVDS_PXL 26 +#define CLK_MM_LVDS_CTS 27 +#define CLK_MM_DPI1_ENGINE 28 +#define CLK_MM_DPI1_PXL 29 +#define CLK_MM_HDMI_PXL 30 +#define CLK_MM_HDMI_SPDIF 31 +#define CLK_MM_HDMI_ADSP_BCK 32 +#define CLK_MM_HDMI_PLL 33 +#define CLK_MM_NR_CLK 34 + +/* IMGSYS */ + +#define CLK_IMG_LARB1_SMI 0 +#define CLK_IMG_CAM_SMI 1 +#define CLK_IMG_CAM_CAM 2 +#define CLK_IMG_SEN_TG 3 +#define CLK_IMG_SEN_CAM 4 +#define CLK_IMG_VENC 5 +#define CLK_IMG_NR_CLK 6 + +/* VDECSYS */ + +#define CLK_VDEC_CKEN 0 +#define CLK_VDEC_LARB1_CKEN 1 +#define CLK_VDEC_NR_CLK 2 + +#endif /* _DT_BINDINGS_CLK_MT8167_H */ -- cgit v1.2.3 From 0d9826bc18ce356e8909919ad681ad65d0a6061e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 12 Oct 2020 17:06:06 +0200 Subject: netfilter: nf_log: missing vlan offload tag and proto Dump vlan tag and proto for the usual vlan offload case if the NF_LOG_MACDECODE flag is set on. Without this information the logging is misleading as there is no reference to the VLAN header. [12716.993704] test: IN=veth0 OUT= MACSRC=86:6c:92:ea:d6:73 MACDST=0e:3b:eb:86:73:76 VPROTO=8100 VID=10 MACPROTO=0800 SRC=192.168.10.2 DST=172.217.168.163 LEN=52 TOS=0x00 PREC=0x00 TTL=64 ID=2548 DF PROTO=TCP SPT=55848 DPT=80 WINDOW=501 RES=0x00 ACK FIN URGP=0 [12721.157643] test: IN=veth0 OUT= MACSRC=86:6c:92:ea:d6:73 MACDST=0e:3b:eb:86:73:76 VPROTO=8100 VID=10 MACPROTO=0806 ARP HTYPE=1 PTYPE=0x0800 OPCODE=2 MACSRC=86:6c:92:ea:d6:73 IPSRC=192.168.10.2 MACDST=0e:3b:eb:86:73:76 IPDST=192.168.10.1 Fixes: 83e96d443b37 ("netfilter: log: split family specific code to nf_log_{ip,ip6,common}.c files") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_log.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 0d3920896d50..716db4a0fed8 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -108,6 +108,7 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, unsigned int logflags); void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, struct sock *sk); +void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb); void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, -- cgit v1.2.3 From bf41a0910cb2dd06abd4d6a920edcee798460ad7 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Fri, 2 Oct 2020 11:09:02 -0700 Subject: remoteproc: Change default dump configuration to "disabled" Currently "default" configuration option means coredumps are enabled. To avoid confusion rename the "default" configuration option to "enabled" and disable collection of dumps by default as doing so makes sense for production devices. Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1601662144-5964-2-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 2fa68bf5aa4f..3fa3ba6498e8 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -442,16 +442,16 @@ enum rproc_crash_type { /** * enum rproc_dump_mechanism - Coredump options for core - * @RPROC_COREDUMP_DEFAULT: Copy dump to separate buffer and carry on with + * @RPROC_COREDUMP_DISABLED: Don't perform any dump + * @RPROC_COREDUMP_ENABLED: Copy dump to separate buffer and carry on with recovery * @RPROC_COREDUMP_INLINE: Read segments directly from device memory. Stall recovery until all segments are read - * @RPROC_COREDUMP_DISABLED: Don't perform any dump */ enum rproc_dump_mechanism { - RPROC_COREDUMP_DEFAULT, - RPROC_COREDUMP_INLINE, RPROC_COREDUMP_DISABLED, + RPROC_COREDUMP_ENABLED, + RPROC_COREDUMP_INLINE, }; /** -- cgit v1.2.3 From 44fa32f008ab7092842095a7a474c48303a2f186 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 12 Oct 2020 10:01:27 +0200 Subject: net: add function dev_fetch_sw_netstats for fetching pcpu_sw_netstats In several places the same code is used to populate rtnl_link_stats64 fields with data from pcpu_sw_netstats. Therefore factor out this code to a new function dev_fetch_sw_netstats(). v2: - constify argument netstats - don't ignore netstats being NULL or an ERRPTR - switch to EXPORT_SYMBOL_GPL Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/6d16a338-52f5-df69-0020-6bc771a7d498@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 948d7105e91a..964b494b0e8d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4499,6 +4499,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage); void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats); +void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, + const struct pcpu_sw_netstats __percpu *netstats); extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; -- cgit v1.2.3 From 8c18b41b3931ad828111ec1e185fcdfffaf1c693 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 5 Oct 2020 16:58:55 +0200 Subject: clk: qcom: gcc-msm8994: Add missing clocks, resets and GDSCs This change adds GDSCs, resets and most of the missing clocks to the msm8994 GCC driver. The remaining ones are of local_vote_clk and gate_clk type, which are not yet supported upstream. Also reorder them to match the original downstream driver. Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20201005145855.149206-1-konradybcio@gmail.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/qcom,gcc-msm8994.h | 36 ++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-msm8994.h b/include/dt-bindings/clock/qcom,gcc-msm8994.h index 938969309e00..507b8d6effd2 100644 --- a/include/dt-bindings/clock/qcom,gcc-msm8994.h +++ b/include/dt-bindings/clock/qcom,gcc-msm8994.h @@ -126,5 +126,41 @@ #define GCC_USB3_PHY_AUX_CLK 116 #define GCC_USB_HS_SYSTEM_CLK 117 #define GCC_SDCC1_AHB_CLK 118 +#define GCC_LPASS_Q6_AXI_CLK 119 +#define GCC_MSS_Q6_BIMC_AXI_CLK 120 +#define GCC_PCIE_0_CFG_AHB_CLK 121 +#define GCC_PCIE_0_MSTR_AXI_CLK 122 +#define GCC_PCIE_0_SLV_AXI_CLK 123 +#define GCC_PCIE_1_CFG_AHB_CLK 124 +#define GCC_PCIE_1_MSTR_AXI_CLK 125 +#define GCC_PCIE_1_SLV_AXI_CLK 126 +#define GCC_PDM_AHB_CLK 127 +#define GCC_SDCC2_AHB_CLK 128 +#define GCC_SDCC3_AHB_CLK 129 +#define GCC_SDCC4_AHB_CLK 130 +#define GCC_TSIF_AHB_CLK 131 +#define GCC_UFS_AHB_CLK 132 +#define GCC_UFS_RX_SYMBOL_0_CLK 133 +#define GCC_UFS_RX_SYMBOL_1_CLK 134 +#define GCC_UFS_TX_SYMBOL_0_CLK 135 +#define GCC_UFS_TX_SYMBOL_1_CLK 136 +#define GCC_USB2_HS_PHY_SLEEP_CLK 137 +#define GCC_USB30_SLEEP_CLK 138 +#define GCC_USB_HS_AHB_CLK 139 +#define GCC_USB_PHY_CFG_AHB2PHY_CLK 140 + +/* GDSCs */ +#define PCIE_GDSC 0 +#define PCIE_0_GDSC 1 +#define PCIE_1_GDSC 2 +#define USB30_GDSC 3 +#define UFS_GDSC 4 + +/* Resets */ +#define USB3_PHY_RESET 0 +#define USB3PHY_PHY_RESET 1 +#define PCIE_PHY_0_RESET 2 +#define PCIE_PHY_1_RESET 3 +#define QUSB2_PHY_RESET 4 #endif -- cgit v1.2.3 From df3f61d2cdc9eac4c9c8316ca2d1a2efea39c8a0 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Wed, 23 Sep 2020 12:06:28 -0400 Subject: dt-bindings: clock: add SM8150 QCOM video clock bindings Add device tree bindings for video clock controller for SM8150 SoCs. Signed-off-by: Jonathan Marek Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20200923160635.28370-3-jonathan@marek.ca Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/qcom,videocc-sm8150.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,videocc-sm8150.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,videocc-sm8150.h b/include/dt-bindings/clock/qcom,videocc-sm8150.h new file mode 100644 index 000000000000..e24ee840cfdb --- /dev/null +++ b/include/dt-bindings/clock/qcom,videocc-sm8150.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8150_H +#define _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8150_H + +/* VIDEO_CC clocks */ +#define VIDEO_CC_IRIS_AHB_CLK 0 +#define VIDEO_CC_IRIS_CLK_SRC 1 +#define VIDEO_CC_MVS0_CORE_CLK 2 +#define VIDEO_CC_MVS1_CORE_CLK 3 +#define VIDEO_CC_MVSC_CORE_CLK 4 +#define VIDEO_CC_PLL0 5 + +/* VIDEO_CC Resets */ +#define VIDEO_CC_MVSC_CORE_CLK_BCR 0 + +/* VIDEO_CC GDSCRs */ +#define VENUS_GDSC 0 +#define VCODEC0_GDSC 1 +#define VCODEC1_GDSC 2 + +#endif -- cgit v1.2.3 From dafb992a95e1c19ba62596b111d88f56f20ef887 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Wed, 23 Sep 2020 12:06:29 -0400 Subject: dt-bindings: clock: add SM8250 QCOM video clock bindings Add device tree bindings for video clock controller for SM8250 SoCs. Signed-off-by: Jonathan Marek Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20200923160635.28370-4-jonathan@marek.ca Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/qcom,videocc-sm8250.h | 34 +++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,videocc-sm8250.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,videocc-sm8250.h b/include/dt-bindings/clock/qcom,videocc-sm8250.h new file mode 100644 index 000000000000..2b2b3867af25 --- /dev/null +++ b/include/dt-bindings/clock/qcom,videocc-sm8250.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8250_H +#define _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8250_H + +/* VIDEO_CC clocks */ +#define VIDEO_CC_MVS0_CLK_SRC 0 +#define VIDEO_CC_MVS0C_CLK 1 +#define VIDEO_CC_MVS0C_DIV2_DIV_CLK_SRC 2 +#define VIDEO_CC_MVS1_CLK_SRC 3 +#define VIDEO_CC_MVS1_DIV2_CLK 4 +#define VIDEO_CC_MVS1C_CLK 5 +#define VIDEO_CC_MVS1C_DIV2_DIV_CLK_SRC 6 +#define VIDEO_CC_PLL0 7 +#define VIDEO_CC_PLL1 8 + +/* VIDEO_CC resets */ +#define VIDEO_CC_CVP_INTERFACE_BCR 0 +#define VIDEO_CC_CVP_MVS0_BCR 1 +#define VIDEO_CC_MVS0C_CLK_ARES 2 +#define VIDEO_CC_CVP_MVS0C_BCR 3 +#define VIDEO_CC_CVP_MVS1_BCR 4 +#define VIDEO_CC_MVS1C_CLK_ARES 5 +#define VIDEO_CC_CVP_MVS1C_BCR 6 + +#define MVS0C_GDSC 0 +#define MVS1C_GDSC 1 +#define MVS0_GDSC 2 +#define MVS1_GDSC 3 + +#endif -- cgit v1.2.3 From d05a58047c75126a74dc32f3f94cbcd9a6fbad0e Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Sun, 27 Sep 2020 15:06:50 -0400 Subject: dt-bindings: clock: add QCOM SM8150 and SM8250 display clock bindings Add device tree bindings for display clock controller for Qualcomm Technology Inc's SM8150 and SM8250 SoCs. Signed-off-by: Jonathan Marek Tested-by: Dmitry Baryshkov (SM8250) Link: https://lore.kernel.org/r/20200927190653.13876-2-jonathan@marek.ca Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/qcom,dispcc-sm8150.h | 1 + include/dt-bindings/clock/qcom,dispcc-sm8250.h | 66 ++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) create mode 120000 include/dt-bindings/clock/qcom,dispcc-sm8150.h create mode 100644 include/dt-bindings/clock/qcom,dispcc-sm8250.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,dispcc-sm8150.h b/include/dt-bindings/clock/qcom,dispcc-sm8150.h new file mode 120000 index 000000000000..0312b4544acb --- /dev/null +++ b/include/dt-bindings/clock/qcom,dispcc-sm8150.h @@ -0,0 +1 @@ +qcom,dispcc-sm8250.h \ No newline at end of file diff --git a/include/dt-bindings/clock/qcom,dispcc-sm8250.h b/include/dt-bindings/clock/qcom,dispcc-sm8250.h new file mode 100644 index 000000000000..fdaca6ad5c85 --- /dev/null +++ b/include/dt-bindings/clock/qcom,dispcc-sm8250.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_DISP_CC_SM8250_H +#define _DT_BINDINGS_CLK_QCOM_DISP_CC_SM8250_H + +/* DISP_CC clock registers */ +#define DISP_CC_MDSS_AHB_CLK 0 +#define DISP_CC_MDSS_AHB_CLK_SRC 1 +#define DISP_CC_MDSS_BYTE0_CLK 2 +#define DISP_CC_MDSS_BYTE0_CLK_SRC 3 +#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC 4 +#define DISP_CC_MDSS_BYTE0_INTF_CLK 5 +#define DISP_CC_MDSS_BYTE1_CLK 6 +#define DISP_CC_MDSS_BYTE1_CLK_SRC 7 +#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC 8 +#define DISP_CC_MDSS_BYTE1_INTF_CLK 9 +#define DISP_CC_MDSS_DP_AUX1_CLK 10 +#define DISP_CC_MDSS_DP_AUX1_CLK_SRC 11 +#define DISP_CC_MDSS_DP_AUX_CLK 12 +#define DISP_CC_MDSS_DP_AUX_CLK_SRC 13 +#define DISP_CC_MDSS_DP_LINK1_CLK 14 +#define DISP_CC_MDSS_DP_LINK1_CLK_SRC 15 +#define DISP_CC_MDSS_DP_LINK1_DIV_CLK_SRC 16 +#define DISP_CC_MDSS_DP_LINK1_INTF_CLK 17 +#define DISP_CC_MDSS_DP_LINK_CLK 18 +#define DISP_CC_MDSS_DP_LINK_CLK_SRC 19 +#define DISP_CC_MDSS_DP_LINK_DIV_CLK_SRC 20 +#define DISP_CC_MDSS_DP_LINK_INTF_CLK 21 +#define DISP_CC_MDSS_DP_PIXEL1_CLK 22 +#define DISP_CC_MDSS_DP_PIXEL1_CLK_SRC 23 +#define DISP_CC_MDSS_DP_PIXEL2_CLK 24 +#define DISP_CC_MDSS_DP_PIXEL2_CLK_SRC 25 +#define DISP_CC_MDSS_DP_PIXEL_CLK 26 +#define DISP_CC_MDSS_DP_PIXEL_CLK_SRC 27 +#define DISP_CC_MDSS_ESC0_CLK 28 +#define DISP_CC_MDSS_ESC0_CLK_SRC 29 +#define DISP_CC_MDSS_ESC1_CLK 30 +#define DISP_CC_MDSS_ESC1_CLK_SRC 31 +#define DISP_CC_MDSS_MDP_CLK 32 +#define DISP_CC_MDSS_MDP_CLK_SRC 33 +#define DISP_CC_MDSS_MDP_LUT_CLK 34 +#define DISP_CC_MDSS_NON_GDSC_AHB_CLK 35 +#define DISP_CC_MDSS_PCLK0_CLK 36 +#define DISP_CC_MDSS_PCLK0_CLK_SRC 37 +#define DISP_CC_MDSS_PCLK1_CLK 38 +#define DISP_CC_MDSS_PCLK1_CLK_SRC 39 +#define DISP_CC_MDSS_ROT_CLK 40 +#define DISP_CC_MDSS_ROT_CLK_SRC 41 +#define DISP_CC_MDSS_RSCC_AHB_CLK 42 +#define DISP_CC_MDSS_RSCC_VSYNC_CLK 43 +#define DISP_CC_MDSS_VSYNC_CLK 44 +#define DISP_CC_MDSS_VSYNC_CLK_SRC 45 +#define DISP_CC_PLL0 46 +#define DISP_CC_PLL1 47 + +/* DISP_CC Reset */ +#define DISP_CC_MDSS_CORE_BCR 0 +#define DISP_CC_MDSS_RSCC_BCR 1 + +/* DISP_CC GDSCR */ +#define MDSS_GDSC 0 + +#endif -- cgit v1.2.3 From 1f7a44f63e6c782c9c2aa9f18f40c23914e6b46a Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 13 Oct 2020 16:47:33 -0700 Subject: compiler-clang: add build check for clang 10.0.1 Patch series "set clang minimum version to 10.0.1", v3. Adds a compile time #error to compiler-clang.h setting the effective minimum supported version to clang 10.0.1. A separate patch has already been picked up into the Documentation/ tree also confirming the version. Next are a series of reverts. One for 32b arm is a partial revert. Then Marco suggested fixes to KASAN docs. Finally, improve the warning for GCC too as per Kees. This patch (of 7): During Plumbers 2020, we voted to just support the latest release of Clang for now. Add a compile time check for this. We plan to remove workarounds for older versions now, which will break in subtle and not so subtle ways. Suggested-by: Sedat Dilek Suggested-by: Nathan Chancellor Suggested-by: Kees Cook Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Tested-by: Sedat Dilek Reviewed-by: Kees Cook Reviewed-by: Miguel Ojeda Reviewed-by: Sedat Dilek Acked-by: Marco Elver Acked-by: Nathan Chancellor Acked-by: Sedat Dilek Cc: Andrey Konovalov Cc: Fangrui Song Cc: Masahiro Yamada Cc: Daniel Borkmann Cc: Alexei Starovoitov Cc: Will Deacon Cc: Vincenzo Frascino Link: https://lkml.kernel.org/r/20200902225911.209899-1-ndesaulniers@google.com Link: https://lkml.kernel.org/r/20200902225911.209899-2-ndesaulniers@google.com Link: https://github.com/ClangBuiltLinux/linux/issues/9 Link: https://github.com/ClangBuiltLinux/linux/issues/941 Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index cee0c728d39a..230604e7f057 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -3,6 +3,14 @@ #error "Please don't include directly, include instead." #endif +#define CLANG_VERSION (__clang_major__ * 10000 \ + + __clang_minor__ * 100 \ + + __clang_patchlevel__) + +#if CLANG_VERSION < 100001 +# error Sorry, your version of Clang is too old - please use 10.0.1 or newer. +#endif + /* Compiler specific definitions for Clang compiler */ /* same as gcc, this was present in clang-2.6 so we can assume it works -- cgit v1.2.3 From c8db3b0a7ba7614f761f309d6aa7499127b18a0b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 13 Oct 2020 16:47:55 -0700 Subject: compiler-gcc: improve version error As Kees suggests, doing so provides developers with two useful pieces of information: - The kernel build was attempting to use GCC. (Maybe they accidentally poked the wrong configs in a CI.) - They need 4.9 or better. ("Upgrade to what version?" doesn't need to be dug out of documentation, headers, etc.) Suggested-by: Kees Cook Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Tested-by: Sedat Dilek Reviewed-by: Kees Cook Reviewed-by: Miguel Ojeda Reviewed-by: Nathan Chancellor Reviewed-by: Sedat Dilek Cc: Andrey Konovalov Cc: Fangrui Song Cc: Marco Elver Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Masahiro Yamada Cc: Vincenzo Frascino Cc: Will Deacon Link: https://lkml.kernel.org/r/20200902225911.209899-8-ndesaulniers@google.com Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7a3769040d7d..d1e3c6896b71 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -12,7 +12,7 @@ /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ #if GCC_VERSION < 40900 -# error Sorry, your compiler is too old - please upgrade it. +# error Sorry, your version of GCC is too old - please use 4.9 or newer. #endif /* Optimization barrier */ -- cgit v1.2.3 From a25c13b3aa1bdbf100e8770902c30908728f8410 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 13 Oct 2020 16:47:58 -0700 Subject: compiler.h: avoid escaped section names The stringification operator, `#`, in the preprocessor escapes strings. For example, `# "foo"` becomes `"\"foo\""`. GCC and Clang differ in how they treat section names that contain \". The portable solution is to not use a string literal with the preprocessor stringification operator. In this case, since __section unconditionally uses the stringification operator, we actually want the more verbose __attribute__((__section__())). Fixes: commit e04462fb82f8 ("Compiler Attributes: remove uses of __attribute__ from compiler.h") Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Cc: Miguel Ojeda Cc: Luc Van Oostenryck Cc: Nathan Chancellor Cc: Arvind Sankar Link: https://bugs.llvm.org/show_bug.cgi?id=42950 Link: https://lkml.kernel.org/r/20200929194318.548707-1-ndesaulniers@google.com Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 92ef163a7479..ac45f6d40d39 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -155,7 +155,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __section("___kentry" "+" #sym ) \ + __attribute__((__section__("___kentry+" #sym))) \ = (unsigned long)&sym; #endif -- cgit v1.2.3 From 4d6fb34acb5d0bfc579ccd29df9cc6f653e51ab2 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 13 Oct 2020 16:48:01 -0700 Subject: export.h: fix section name for CONFIG_TRIM_UNUSED_KSYMS for Clang When enabling CONFIG_TRIM_UNUSED_KSYMS, the linker will warn about the orphan sections: (".discard.ksym") is being placed in '".discard.ksym"' repeatedly when linking vmlinux. This is because the stringification operator, `#`, in the preprocessor escapes strings. GCC and Clang differ in how they treat section names that contain \". The portable solution is to not use a string literal with the preprocessor stringification operator. Fixes: commit bbda5ec671d3 ("kbuild: simplify dependency generation for CONFIG_TRIM_UNUSED_KSYMS") Reported-by: kbuild test robot Suggested-by: Kees Cook Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Cc: Nathan Chancellor Cc: Masahiro Yamada Cc: Matthias Maennich Cc: Jessica Yu Cc: Greg Kroah-Hartman Cc: Will Deacon Link: https://bugs.llvm.org/show_bug.cgi?id=42950 Link: https://github.com/ClangBuiltLinux/linux/issues/1166 Link: https://lkml.kernel.org/r/20200929190701.398762-1-ndesaulniers@google.com Signed-off-by: Linus Torvalds --- include/linux/export.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/export.h b/include/linux/export.h index fceb5e855717..8933ff6ad23a 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -130,7 +130,7 @@ struct kernel_symbol { * discarded in the final link stage. */ #define __ksym_marker(sym) \ - static int __ksym_marker_##sym[0] __section(".discard.ksym") __used + static int __ksym_marker_##sym[0] __section(.discard.ksym) __used #define __EXPORT_SYMBOL(sym, sec, ns) \ __ksym_marker(sym); \ -- cgit v1.2.3 From d7cff4ded857ff7cc3e49eb39cc14df9345b9662 Mon Sep 17 00:00:00 2001 From: tangjianqiang Date: Tue, 13 Oct 2020 16:48:37 -0700 Subject: include/linux/slab.h: fix a typo error in comment fix a typo error in slab.h "allocagtor" -> "allocator" Signed-off-by: tangjianqiang Signed-off-by: Andrew Morton Acked-by: Souptick Joarder Link: https://lkml.kernel.org/r/1600230053-24303-1-git-send-email-tangjianqiang@xiaomi.com Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 24df2393ec03..9e155cc83b8a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -279,7 +279,7 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) -/* Maximum order allocatable via the slab allocagtor */ +/* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* -- cgit v1.2.3 From 2dd57d3415f8623a5e9494c88978a202886041aa Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:48:57 -0700 Subject: x86/numa: cleanup configuration dependent command-line options MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "device-dax: Support sub-dividing soft-reserved ranges", v5. The device-dax facility allows an address range to be directly mapped through a chardev, or optionally hotplugged to the core kernel page allocator as System-RAM. It is the mechanism for converting persistent memory (pmem) to be used as another volatile memory pool i.e. the current Memory Tiering hot topic on linux-mm. In the case of pmem the nvdimm-namespace-label mechanism can sub-divide it, but that labeling mechanism is not available / applicable to soft-reserved ("EFI specific purpose") memory [3]. This series provides a sysfs-mechanism for the daxctl utility to enable provisioning of volatile-soft-reserved memory ranges. The motivations for this facility are: 1/ Allow performance differentiated memory ranges to be split between kernel-managed and directly-accessed use cases. 2/ Allow physical memory to be provisioned along performance relevant address boundaries. For example, divide a memory-side cache [4] along cache-color boundaries. 3/ Parcel out soft-reserved memory to VMs using device-dax as a security / permissions boundary [5]. Specifically I have seen people (ab)using memmap=nn!ss (mark System-RAM as Persistent Memory) just to get the device-dax interface on custom address ranges. A follow-on for the VM use case is to teach device-dax to dynamically allocate 'struct page' at runtime to reduce the duplication of 'struct page' space in both the guest and the host kernel for the same physical pages. [2]: http://lore.kernel.org/r/20200713160837.13774-11-joao.m.martins@oracle.com [3]: http://lore.kernel.org/r/157309097008.1579826.12818463304589384434.stgit@dwillia2-desk3.amr.corp.intel.com [4]: http://lore.kernel.org/r/154899811738.3165233.12325692939590944259.stgit@dwillia2-desk3.amr.corp.intel.com [5]: http://lore.kernel.org/r/20200110190313.17144-1-joao.m.martins@oracle.com This patch (of 23): In preparation for adding a new numa= option clean up the existing ones to avoid ifdefs in numa_setup(), and provide feedback when the option is numa=fake= option is invalid due to kernel config. The same does not need to be done for numa=noacpi, since the capability is already hard disabled at compile-time. Suggested-by: Rafael J. Wysocki Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Benjamin Herrenschmidt Cc: Ben Skeggs Cc: Borislav Petkov Cc: Brice Goglin Cc: Catalin Marinas Cc: Daniel Vetter Cc: Dave Hansen Cc: Dave Jiang Cc: David Airlie Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jeff Moyer Cc: Jia He Cc: Joao Martins Cc: Jonathan Cameron Cc: Michael Ellerman Cc: Mike Rapoport Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Vishal Verma Cc: Wei Yang Cc: Will Deacon Cc: Ard Biesheuvel Cc: Bjorn Helgaas Cc: Boris Ostrovsky Cc: Hulk Robot Cc: Jason Yan Cc: "Jérôme Glisse" Cc: Juergen Gross Cc: kernel test robot Cc: Randy Dunlap Cc: Stefano Stabellini Cc: Vivek Goyal Link: https://lkml.kernel.org/r/160106109960.30709.7379926726669669398.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/159643094279.4062302.17779410714418721328.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/159643094925.4062302.14979872973043772305.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- include/acpi/acpi_numa.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h index fdebcfc6c8df..8784183b2204 100644 --- a/include/acpi/acpi_numa.h +++ b/include/acpi/acpi_numa.h @@ -17,10 +17,14 @@ extern int pxm_to_node(int); extern int node_to_pxm(int); extern int acpi_map_pxm_to_node(int); extern unsigned char acpi_srat_revision; -extern int acpi_numa __initdata; +extern void disable_srat(void); extern void bad_srat(void); extern int srat_disabled(void); +#else /* CONFIG_ACPI_NUMA */ +static inline void disable_srat(void) +{ +} #endif /* CONFIG_ACPI_NUMA */ #endif /* __ACP_NUMA_H */ -- cgit v1.2.3 From 3b0d31011d39759e3ba7214f75f77bb31983b5a4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:49:02 -0700 Subject: x86/numa: add 'nohmat' option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Disable parsing of the HMAT for debug, to workaround broken platform instances, or cases where it is otherwise not wanted. [rdunlap@infradead.org: fix build when CONFIG_ACPI is not set] Link: https://lkml.kernel.org/r/70e5ee34-9809-a997-7b49-499e4be61307@infradead.org Signed-off-by: Dan Williams Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ard Biesheuvel Cc: Ard Biesheuvel Cc: Benjamin Herrenschmidt Cc: Ben Skeggs Cc: Brice Goglin Cc: Catalin Marinas Cc: Daniel Vetter Cc: Dave Jiang Cc: David Airlie Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jeff Moyer Cc: Jia He Cc: Joao Martins Cc: Jonathan Cameron Cc: Michael Ellerman Cc: Mike Rapoport Cc: Paul Mackerras Cc: Pavel Tatashin Cc: "Rafael J. Wysocki" Cc: Tom Lendacky Cc: Vishal Verma Cc: Wei Yang Cc: Will Deacon Cc: Bjorn Helgaas Cc: Boris Ostrovsky Cc: Hulk Robot Cc: Jason Yan Cc: "Jérôme Glisse" Cc: Juergen Gross Cc: kernel test robot Cc: Randy Dunlap Cc: Stefano Stabellini Cc: Vivek Goyal Link: https://lkml.kernel.org/r/159643095540.4062302.732962081968036212.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- include/acpi/acpi_numa.h | 8 ++++++++ include/linux/acpi.h | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h index 8784183b2204..0e9302285f14 100644 --- a/include/acpi/acpi_numa.h +++ b/include/acpi/acpi_numa.h @@ -27,4 +27,12 @@ static inline void disable_srat(void) { } #endif /* CONFIG_ACPI_NUMA */ + +#ifdef CONFIG_ACPI_HMAT +extern void disable_hmat(void); +#else /* CONFIG_ACPI_HMAT */ +static inline void disable_hmat(void) +{ +} +#endif /* CONFIG_ACPI_HMAT */ #endif /* __ACP_NUMA_H */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 64ae25c59d55..cfa8c0015863 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -709,6 +709,8 @@ static inline u64 acpi_arch_get_root_pointer(void) #define ACPI_HANDLE_FWNODE(fwnode) (NULL) #define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (0), .cls_msk = (0), +#include + struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) -- cgit v1.2.3 From c01044cc819160323f3ca4acd44fca487c4432e6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:49:13 -0700 Subject: ACPI: HMAT: refactor hmat_register_target_device to hmem_register_device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation for exposing "Soft Reserved" memory ranges without an HMAT, move the hmem device registration to its own compilation unit and make the implementation generic. The generic implementation drops usage acpi_map_pxm_to_online_node() that was translating ACPI proximity domain values and instead relies on numa_map_to_online_node() to determine the numa node for the device. [joao.m.martins@oracle.com: CONFIG_DEV_DAX_HMEM_DEVICES should depend on CONFIG_DAX=y] Link: https://lkml.kernel.org/r/8f34727f-ec2d-9395-cb18-969ec8a5d0d4@oracle.com Signed-off-by: Dan Williams Signed-off-by: Joao Martins Signed-off-by: Andrew Morton Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Ben Skeggs Cc: Borislav Petkov Cc: Brice Goglin Cc: Catalin Marinas Cc: Daniel Vetter Cc: Dave Hansen Cc: Dave Jiang Cc: David Airlie Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jeff Moyer Cc: Jia He Cc: Joao Martins Cc: Jonathan Cameron Cc: Michael Ellerman Cc: Mike Rapoport Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Vishal Verma Cc: Wei Yang Cc: Will Deacon Cc: Ard Biesheuvel Cc: Ard Biesheuvel Cc: Bjorn Helgaas Cc: Boris Ostrovsky Cc: Hulk Robot Cc: Jason Yan Cc: "Jérôme Glisse" Cc: Juergen Gross Cc: kernel test robot Cc: Randy Dunlap Cc: Stefano Stabellini Cc: Vivek Goyal Link: https://lkml.kernel.org/r/159643096584.4062302.5035370788475153738.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lore.kernel.org/r/158318761484.2216124.2049322072599482736.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- include/linux/dax.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 43b39ab9de1a..4ec0bbf86205 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -238,4 +238,12 @@ static inline bool dax_mapping(struct address_space *mapping) return mapping->host && IS_DAX(mapping->host); } +#ifdef CONFIG_DEV_DAX_HMEM_DEVICES +void hmem_register_device(int target_nid, struct resource *r); +#else +static inline void hmem_register_device(int target_nid, struct resource *r) +{ +} +#endif + #endif -- cgit v1.2.3 From a035b6bf863e5c42c2746de2a8ed6600140307e7 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:49:23 -0700 Subject: mm/memory_hotplug: introduce default phys_to_target_node() implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to set a fallback value for dev_dax->target_node, introduce generic fallback helpers for phys_to_target_node() A generic implementation based on node-data or memblock was proposed, but as noted by Mike: "Here again, I would prefer to add a weak default for phys_to_target_node() because the "generic" implementation is not really generic. The fallback to reserved ranges is x86 specfic because on x86 most of the reserved areas is not in memblock.memory. AFAIK, no other architecture does this." The info message in the generic memory_add_physaddr_to_nid() implementation is fixed up to properly reflect that memory_add_physaddr_to_nid() communicates "online" node info and phys_to_target_node() indicates "target / to-be-onlined" node info. [akpm@linux-foundation.org: fix CONFIG_MEMORY_HOTPLUG=n build] Link: https://lkml.kernel.org/r/202008252130.7YrHIyMI%25lkp@intel.com Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Cc: David Hildenbrand Cc: Mike Rapoport Cc: Jia He Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Benjamin Herrenschmidt Cc: Ben Skeggs Cc: Borislav Petkov Cc: Brice Goglin Cc: Catalin Marinas Cc: Daniel Vetter Cc: Dave Hansen Cc: Dave Jiang Cc: David Airlie Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jeff Moyer Cc: Joao Martins Cc: Jonathan Cameron Cc: Michael Ellerman Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Vishal Verma Cc: Wei Yang Cc: Will Deacon Cc: Ard Biesheuvel Cc: Bjorn Helgaas Cc: Boris Ostrovsky Cc: Hulk Robot Cc: Jason Yan Cc: "Jérôme Glisse" Cc: Juergen Gross Cc: kernel test robot Cc: Randy Dunlap Cc: Stefano Stabellini Cc: Vivek Goyal Link: https://lkml.kernel.org/r/159643097768.4062302.3135192588966888630.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 23 ++++++++++++++--------- include/linux/numa.h | 11 ----------- 2 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 375515803cd8..c0faa7a30c46 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -149,15 +149,6 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params); #endif /* ARCH_HAS_ADD_PAGES */ -#ifdef CONFIG_NUMA -extern int memory_add_physaddr_to_nid(u64 start); -#else -static inline int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -#endif - #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION /* * For supporting node-hotadd, we have to allocate a new pgdat. @@ -284,6 +275,20 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ +#ifdef CONFIG_NUMA +extern int memory_add_physaddr_to_nid(u64 start); +extern int phys_to_target_node(u64 start); +#else +static inline int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +static inline int phys_to_target_node(u64 start) +{ + return 0; +} +#endif + #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/numa.h b/include/linux/numa.h index a42df804679e..8cb33ccfb671 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -23,22 +23,11 @@ #ifdef CONFIG_NUMA /* Generic implementation available */ int numa_map_to_online_node(int node); - -/* - * Optional architecture specific implementation, users need a "depends - * on $ARCH" - */ -int phys_to_target_node(phys_addr_t addr); #else static inline int numa_map_to_online_node(int node) { return NUMA_NO_NODE; } - -static inline int phys_to_target_node(phys_addr_t addr) -{ - return NUMA_NO_NODE; -} #endif #endif /* _LINUX_NUMA_H */ -- cgit v1.2.3 From a4574f63edc6f76fb46dcd65d3eb4d5a8e23ba38 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:50:29 -0700 Subject: mm/memremap_pages: convert to 'struct range' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams Signed-off-by: Dan Carpenter Signed-off-by: Andrew Morton Reviewed-by: Boris Ostrovsky [xen] Cc: Paul Mackerras Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Vishal Verma Cc: Vivek Goyal Cc: Dave Jiang Cc: Ben Skeggs Cc: David Airlie Cc: Daniel Vetter Cc: Ira Weiny Cc: Bjorn Helgaas Cc: Juergen Gross Cc: Stefano Stabellini Cc: "Jérôme Glisse" Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Ard Biesheuvel Cc: Borislav Petkov Cc: Brice Goglin Cc: Catalin Marinas Cc: Dave Hansen Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Hulk Robot Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Jason Yan Cc: Jeff Moyer Cc: Jia He Cc: Joao Martins Cc: Jonathan Cameron Cc: kernel test robot Cc: Mike Rapoport Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Wei Yang Cc: Will Deacon Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 5 +++-- include/linux/range.h | 6 ++++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index e5862746751b..d0dd261d87c0 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ +#include #include #include @@ -93,7 +94,7 @@ struct dev_pagemap_ops { /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations - * @res: physical address range covered by @ref + * @range: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping * @internal_ref: internal reference if @ref is not provided by the caller * @done: completion for @internal_ref @@ -106,7 +107,7 @@ struct dev_pagemap_ops { */ struct dev_pagemap { struct vmem_altmap altmap; - struct resource res; + struct range range; struct percpu_ref *ref; struct percpu_ref internal_ref; struct completion done; diff --git a/include/linux/range.h b/include/linux/range.h index d1fbeb664012..274681cc3154 100644 --- a/include/linux/range.h +++ b/include/linux/range.h @@ -1,12 +1,18 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RANGE_H #define _LINUX_RANGE_H +#include struct range { u64 start; u64 end; }; +static inline u64 range_len(const struct range *range) +{ + return range->end - range->start + 1; +} + int add_range(struct range *range, int az, int nr_range, u64 start, u64 end); -- cgit v1.2.3 From b7b3c01b191596d27a6980d1a42504f5b607f802 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:50:34 -0700 Subject: mm/memremap_pages: support multiple ranges per invocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In support of device-dax growing the ability to front physically dis-contiguous ranges of memory, update devm_memremap_pages() to track multiple ranges with a single reference counter and devm instance. Convert all [devm_]memremap_pages() users to specify the number of ranges they are mapping in their 'struct dev_pagemap' instance. Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Cc: Paul Mackerras Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Vishal Verma Cc: Vivek Goyal Cc: Dave Jiang Cc: Ben Skeggs Cc: David Airlie Cc: Daniel Vetter Cc: Ira Weiny Cc: Bjorn Helgaas Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Stefano Stabellini Cc: "Jérôme Glisse" Cc: Ard Biesheuvel Cc: Ard Biesheuvel Cc: Borislav Petkov Cc: Brice Goglin Cc: Catalin Marinas Cc: Dave Hansen Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Hulk Robot Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Jason Yan Cc: Jeff Moyer Cc: "Jérôme Glisse" Cc: Jia He Cc: Joao Martins Cc: Jonathan Cameron Cc: kernel test robot Cc: Mike Rapoport Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Wei Yang Cc: Will Deacon Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index d0dd261d87c0..79c49e7f5c30 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -94,7 +94,6 @@ struct dev_pagemap_ops { /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations - * @range: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping * @internal_ref: internal reference if @ref is not provided by the caller * @done: completion for @internal_ref @@ -104,10 +103,12 @@ struct dev_pagemap_ops { * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. + * @nr_range: number of ranges to be mapped + * @range: range to be mapped when nr_range == 1 + * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; - struct range range; struct percpu_ref *ref; struct percpu_ref internal_ref; struct completion done; @@ -115,6 +116,11 @@ struct dev_pagemap { unsigned int flags; const struct dev_pagemap_ops *ops; void *owner; + int nr_range; + union { + struct range range; + struct range ranges[0]; + }; }; static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) -- cgit v1.2.3 From bac3cf4d01d43b587c873360dc8c84e3b570b344 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Tue, 13 Oct 2020 16:51:14 -0700 Subject: mm, dump_page: rename head_mapcount() --> head_compound_mapcount() Rename head_pincount() --> head_compound_pincount(). These names are more accurate (or less misleading) than the original ones. Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Cc: Qian Cai Cc: Matthew Wilcox Cc: Vlastimil Babka Cc: Kirill A. Shutemov Cc: Mike Rapoport Cc: William Kucharski Link: https://lkml.kernel.org/r/20200807183358.105097-1-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 13dc9b9ccf8e..9cc0894e7d61 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -791,7 +791,7 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); -static inline int head_mapcount(struct page *head) +static inline int head_compound_mapcount(struct page *head) { return atomic_read(compound_mapcount_ptr(head)) + 1; } @@ -805,7 +805,7 @@ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); - return head_mapcount(page); + return head_compound_mapcount(page); } /* @@ -918,7 +918,7 @@ static inline bool hpage_pincount_available(struct page *page) return PageCompound(page) && compound_order(page) > 1; } -static inline int head_pincount(struct page *head) +static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); } @@ -927,7 +927,7 @@ static inline int compound_pincount(struct page *page) { VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); page = compound_head(page); - return head_pincount(page); + return head_compound_pincount(page); } static inline void set_compound_order(struct page *page, unsigned int order) -- cgit v1.2.3 From 61ef1865570452801f6e554a668e049c2e25c1fd Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 13 Oct 2020 16:51:17 -0700 Subject: mm: factor find_get_incore_page out of mincore_page Patch series "Return head pages from find_*_entry", v2. This patch series started out as part of the THP patch set, but it has some nice effects along the way and it seems worth splitting it out and submitting separately. Currently find_get_entry() and find_lock_entry() return the page corresponding to the requested index, but the first thing most callers do is find the head page, which we just threw away. As part of auditing all the callers, I found some misuses of the APIs and some plain inefficiencies that I've fixed. The diffstat is unflattering, but I added more kernel-doc and a new wrapper. This patch (of 8); Provide this functionality from the swap cache. It's useful for more than just mincore(). Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Hugh Dickins Cc: William Kucharski Cc: Jani Nikula Cc: Alexey Dobriyan Cc: Johannes Weiner Cc: Chris Wilson Cc: Matthew Auld Cc: Huang Ying Link: https://lkml.kernel.org/r/20200910183318.20139-1-willy@infradead.org Link: https://lkml.kernel.org/r/20200910183318.20139-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 4340a7b6e7a1..23c6e43a956d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -427,6 +427,7 @@ extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); +struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool do_poll); @@ -570,6 +571,12 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp, return NULL; } +static inline +struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) +{ + return find_get_page(mapping, index); +} + static inline int add_to_swap(struct page *page) { return 0; -- cgit v1.2.3 From 9dfc8ff34b951f83632815a87e97a625a11360f0 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 13 Oct 2020 16:51:31 -0700 Subject: i915: use find_lock_page instead of find_lock_entry i915 does not want to see value entries. Switch it to use find_lock_page() instead, and remove the export of find_lock_entry(). Move find_lock_entry() and find_get_entry() to mm/internal.h to discourage any future use. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Cc: Alexey Dobriyan Cc: Chris Wilson Cc: Huang Ying Cc: Hugh Dickins Cc: Jani Nikula Cc: Matthew Auld Cc: William Kucharski Link: https://lkml.kernel.org/r/20200910183318.20139-6-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 434c9c34aeb6..9d282fe6700d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -385,8 +385,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) return head + (index & (thp_nr_pages(head) - 1)); } -struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); -struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); -- cgit v1.2.3 From 63ec1973ddf3eb70feb5728088ca190f1af449cb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 13 Oct 2020 16:51:38 -0700 Subject: mm/shmem: return head page from find_lock_entry Convert shmem_getpage_gfp() (the only remaining caller of find_lock_entry()) to cope with a head page being returned instead of the subpage for the index. [willy@infradead.org: fix BUG()s] Link https://lore.kernel.org/linux-mm/20200912032042.GA6583@casper.infradead.org/ Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Alexey Dobriyan Cc: Chris Wilson Cc: Huang Ying Cc: Hugh Dickins Cc: Jani Nikula Cc: Johannes Weiner Cc: Matthew Auld Cc: William Kucharski Link: https://lkml.kernel.org/r/20200910183318.20139-8-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 9d282fe6700d..5176009e4ffa 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -372,6 +372,15 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } +/* Does this page contain this index? */ +static inline bool thp_contains(struct page *head, pgoff_t index) +{ + /* HugeTLBfs indexes the page cache in units of hpage_size */ + if (PageHuge(head)) + return head->index == index; + return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); +} + /* * Given the page we found in the page cache, return the page corresponding * to this index in the file -- cgit v1.2.3 From a8cf7f272b5a28a62ecfc39d6f7d75b4f486e350 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 13 Oct 2020 16:51:41 -0700 Subject: mm: add find_lock_head Add a new FGP_HEAD flag which avoids calling find_subpage() and add a convenience wrapper for it. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Alexey Dobriyan Cc: Chris Wilson Cc: Huang Ying Cc: Hugh Dickins Cc: Jani Nikula Cc: Johannes Weiner Cc: Matthew Auld Cc: William Kucharski Link: https://lkml.kernel.org/r/20200910183318.20139-9-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 5176009e4ffa..1a3554f5d992 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -279,6 +279,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 +#define FGP_HEAD 0x00000080 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t cache_gfp_mask); @@ -310,18 +311,37 @@ static inline struct page *find_get_page_flags(struct address_space *mapping, * @mapping: the address_space to search * @offset: the page index * - * Looks up the page cache slot at @mapping & @offset. If there is a + * Looks up the page cache entry at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * - * Otherwise, %NULL is returned. - * - * find_lock_page() may sleep. + * Context: May sleep. + * Return: A struct page or %NULL if there is no page in the cache for this + * index. */ static inline struct page *find_lock_page(struct address_space *mapping, - pgoff_t offset) + pgoff_t index) +{ + return pagecache_get_page(mapping, index, FGP_LOCK, 0); +} + +/** + * find_lock_head - Locate, pin and lock a pagecache page. + * @mapping: The address_space to search. + * @offset: The page index. + * + * Looks up the page cache entry at @mapping & @offset. If there is a + * page cache page, its head page is returned locked and with an increased + * refcount. + * + * Context: May sleep. + * Return: A struct page which is !PageTail, or %NULL if there is no page + * in the cache for this index. + */ +static inline struct page *find_lock_head(struct address_space *mapping, + pgoff_t index) { - return pagecache_get_page(mapping, offset, FGP_LOCK, 0); + return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0); } /** -- cgit v1.2.3 From eb1d7a65f08a52dfb828bf45b4ead7f617c64047 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Tue, 13 Oct 2020 16:51:47 -0700 Subject: mm, fadvise: improve the expensive remote LRU cache draining after FADV_DONTNEED Our users reported that there're some random latency spikes when their RT process is running. Finally we found that latency spike is caused by FADV_DONTNEED. Which may call lru_add_drain_all() to drain LRU cache on remote CPUs, and then waits the per-cpu work to complete. The wait time is uncertain, which may be tens millisecond. That behavior is unreasonable, because this process is bound to a specific CPU and the file is only accessed by itself, IOW, there should be no pagecache pages on a per-cpu pagevec of a remote CPU. That unreasonable behavior is partially caused by the wrong comparation of the number of invalidated pages and the number of the target. For example, if (count < (end_index - start_index + 1)) The count above is how many pages were invalidated in the local CPU, and (end_index - start_index + 1) is how many pages should be invalidated. The usage of (end_index - start_index + 1) is incorrect, because they are virtual addresses, which may not mapped to pages. Besides that, there may be holes between start and end. So we'd better check whether there are still pages on per-cpu pagevec after drain the local cpu, and then decide whether or not to call lru_add_drain_all(). After I applied it with a hotfix to our production environment, most of the lru_add_drain_all() can be avoided. Suggested-by: Mel Gorman Signed-off-by: Yafang Shao Signed-off-by: Andrew Morton Acked-by: Mel Gorman Cc: Johannes Weiner Link: https://lkml.kernel.org/r/20200923133318.14373-1-laoar.shao@gmail.com Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2e621d28cd65..5815f7d4dbf4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2581,6 +2581,10 @@ extern bool is_bad_inode(struct inode *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); +void invalidate_mapping_pagevec(struct address_space *mapping, + pgoff_t start, pgoff_t end, + unsigned long *nr_pagevec); + static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || -- cgit v1.2.3 From 3264631548b1f2bf89b71793d06bfd0f748f649d Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 13 Oct 2020 16:52:04 -0700 Subject: swap: rename SWP_FS to SWAP_FS_OPS to avoid ambiguity SWP_FS is used to make swap_{read,write}page() go through the filesystem, and it's only used for swap files over NFS for now. Otherwise it will directly submit IO to blockdev according to swapfile extents reported by filesystems in advance. As Matthew pointed out [1], SWP_FS naming is somewhat confusing, so let's rename to SWP_FS_OPS. [1] https://lore.kernel.org/r/20200820113448.GM17456@casper.infradead.org Suggested-by: Matthew Wilcox Signed-off-by: Gao Xiang Signed-off-by: Andrew Morton Link: https://lkml.kernel.org/r/20200822113019.11319-1-hsiangkao@redhat.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 23c6e43a956d..7bd5b4aac049 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -170,7 +170,7 @@ enum { SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ - SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ -- cgit v1.2.3 From cc2828b21c764f901128ca2e7b9f056d0e72104f Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Tue, 13 Oct 2020 16:52:08 -0700 Subject: mm: remove activate_page() from unuse_pte() We don't initially add anon pages to active lruvec after commit b518154e59aa ("mm/vmscan: protect the workingset on anonymous LRU"). Remove activate_page() from unuse_pte(), which seems to be missed by the commit. And make the function static while we are at it. Before the commit, we called lru_cache_add_active_or_unevictable() to add new ksm pages to active lruvec. Therefore, activate_page() wasn't necessary for them in the first place. Signed-off-by: Yu Zhao Signed-off-by: Andrew Morton Reviewed-by: Yang Shi Cc: Alexander Duyck Cc: Huang Ying Cc: David Hildenbrand Cc: Michal Hocko Cc: Qian Cai Cc: Mel Gorman Cc: Nicholas Piggin Cc: Hugh Dickins Cc: Joonsoo Kim Link: http://lkml.kernel.org/r/20200818184704.3625199-1-yuzhao@google.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 7bd5b4aac049..667935c0dbd4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -340,7 +340,6 @@ extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); -extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); -- cgit v1.2.3 From f3bc52cb04bcfccd12da3f03ca8bc50484898436 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 13 Oct 2020 16:52:18 -0700 Subject: mm/swap_slots.c: remove always zero and unused return value of enable_swap_slots_cache() enable_swap_slots_cache() always return zero and its return value is just ignored by the caller. So make enable_swap_slots_cache() void. Signed-off-by: Miaohe Lin Signed-off-by: Andrew Morton Link: https://lkml.kernel.org/r/20200924113554.50614-1-linmiaohe@huawei.com Signed-off-by: Linus Torvalds --- include/linux/swap_slots.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index e36b200c2a77..347f1a304190 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -23,7 +23,7 @@ struct swap_slots_cache { void disable_swap_slots_cache_lock(void); void reenable_swap_slots_cache_unlock(void); -int enable_swap_slots_cache(void); +void enable_swap_slots_cache(void); int free_swap_slot(swp_entry_t entry); extern bool swap_slot_cache_enabled; -- cgit v1.2.3 From bd0b230fe14554bfffbae54e19038716f96f5a41 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 13 Oct 2020 16:52:56 -0700 Subject: mm/memcg: unify swap and memsw page counters The swap page counter is v2 only while memsw is v1 only. As v1 and v2 controllers cannot be active at the same time, there is no point to keep both swap and memsw page counters in mem_cgroup. The previous patch has made sure that memsw page counter is updated and accessed only when in v1 code paths. So it is now safe to alias the v1 memsw page counter to v2 swap page counter. This saves 14 long's in the size of mem_cgroup. This is a saving of 112 bytes for 64-bit archs. While at it, also document which page counters are used in v1 and/or v2. Signed-off-by: Waiman Long Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Chris Down Cc: Johannes Weiner Cc: Roman Gushchin Cc: Tejun Heo Cc: Vladimir Davydov Cc: Yafang Shao Link: https://lkml.kernel.org/r/20200914024452.19167-4-longman@redhat.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d0b036123c6a..6ef4a552e09d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -215,13 +215,16 @@ struct mem_cgroup { struct mem_cgroup_id id; /* Accounted resources */ - struct page_counter memory; - struct page_counter swap; + struct page_counter memory; /* Both v1 & v2 */ + + union { + struct page_counter swap; /* v2 only */ + struct page_counter memsw; /* v1 only */ + }; /* Legacy consumer-oriented counters */ - struct page_counter memsw; - struct page_counter kmem; - struct page_counter tcpmem; + struct page_counter kmem; /* v1 only */ + struct page_counter tcpmem; /* v1 only */ /* Range enforcement for interrupt charges */ struct work_struct high_work; -- cgit v1.2.3 From b2b29d6d01194404dfef4eafa026959be301705b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 13 Oct 2020 16:53:22 -0700 Subject: mm: account PMD tables like PTE tables We account the PTE level of the page tables to the process in order to make smarter OOM decisions and help diagnose why memory is fragmented. For these same reasons, we should account pages allocated for PMDs. With larger process address spaces and ASLR, the number of PMDs in use is higher than it used to be so the inaccuracy is starting to matter. [rppt@linux.ibm.com: arm: __pmd_free_tlb(): call page table destructor] Link: https://lkml.kernel.org/r/20200825111303.GB69694@linux.ibm.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Mike Rapoport Cc: Abdul Haleem Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Christophe Leroy Cc: Joerg Roedel Cc: Max Filippov Cc: Peter Zijlstra Cc: Satheesh Rajendran Cc: Stafford Horne Cc: Naresh Kamboju Cc: Anders Roxell Link: http://lkml.kernel.org/r/20200627184642.GF25039@casper.infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9cc0894e7d61..5320e7ab843f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2254,7 +2254,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(pmd_to_page(pmd)); } -static inline bool pgtable_pmd_page_ctor(struct page *page) +static inline bool pmd_ptlock_init(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE page->pmd_huge_pte = NULL; @@ -2262,7 +2262,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page) return ptlock_init(page); } -static inline void pgtable_pmd_page_dtor(struct page *page) +static inline void pmd_ptlock_free(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON_PAGE(page->pmd_huge_pte, page); @@ -2279,8 +2279,8 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) return &mm->page_table_lock; } -static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; } -static inline void pgtable_pmd_page_dtor(struct page *page) {} +static inline bool pmd_ptlock_init(struct page *page) { return true; } +static inline void pmd_ptlock_free(struct page *page) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) @@ -2293,6 +2293,22 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } +static inline bool pgtable_pmd_page_ctor(struct page *page) +{ + if (!pmd_ptlock_init(page)) + return false; + __SetPageTable(page); + inc_zone_page_state(page, NR_PAGETABLE); + return true; +} + +static inline void pgtable_pmd_page_dtor(struct page *page) +{ + pmd_ptlock_free(page); + __ClearPageTable(page); + dec_zone_page_state(page, NR_PAGETABLE); +} + /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be -- cgit v1.2.3 From 07e5bfe651f8595ca6a777d989016aa8d8217924 Mon Sep 17 00:00:00 2001 From: Chinwen Chang Date: Tue, 13 Oct 2020 16:53:39 -0700 Subject: mmap locking API: add mmap_lock_is_contended() Patch series "Try to release mmap_lock temporarily in smaps_rollup", v4. Recently, we have observed some janky issues caused by unpleasantly long contention on mmap_lock which is held by smaps_rollup when probing large processes. To address the problem, we let smaps_rollup detect if anyone wants to acquire mmap_lock for write attempts. If yes, just release the lock temporarily to ease the contention. smaps_rollup is a procfs interface which allows users to summarize the process's memory usage without the overhead of seq_* calls. Android uses it to sample the memory usage of various processes to balance its memory pool sizes. If no one wants to take the lock for write requests, smaps_rollup with this patch will behave like the original one. Although there are on-going mmap_lock optimizations like range-based locks, the lock applied to smaps_rollup would be the coarse one, which is hard to avoid the occurrence of aforementioned issues. So the detection and temporary release for write attempts on mmap_lock in smaps_rollup is still necessary. This patch (of 3): Add new API to query if someone wants to acquire mmap_lock for write attempts. Using this instead of rwsem_is_contended makes it more tolerant of future changes to the lock type. Signed-off-by: Chinwen Chang Signed-off-by: Andrew Morton Reviewed-by: Steven Price Acked-by: Michel Lespinasse Cc: Alexey Dobriyan Cc: Daniel Jordan Cc: Daniel Kiss Cc: Davidlohr Bueso Cc: Huang Ying Cc: Jason Gunthorpe Cc: Jimmy Assarsson Cc: Laurent Dufour Cc: "Matthew Wilcox (Oracle)" Cc: Matthias Brugger Cc: Song Liu Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/1597715898-3854-1-git-send-email-chinwen.chang@mediatek.com Link: http://lkml.kernel.org/r/1597715898-3854-2-git-send-email-chinwen.chang@mediatek.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 0707671851a8..18e7eae9b5ba 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -87,4 +87,9 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm) VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } +static inline int mmap_lock_is_contended(struct mm_struct *mm) +{ + return rwsem_is_contended(&mm->mmap_lock); +} + #endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From e18c45ffcfa347b13c2f300f290bacff55a4b41e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 13 Oct 2020 16:53:50 -0700 Subject: mm: move PageDoubleMap bit Patch series "Fix PageDoubleMap". This is a purely theoretical problem for now as none of the filesystems which use PG_private_2 (ie PG_fscache) are being converted at this time, but it's confusing to leave it like this. This patch (of 2): PG_private_2 is defined as being PF_ANY (applicable to tail pages as well as regular & head pages). That means that the first tail page of a double-map page will appear to have Private2 set. Use the Workingset bit instead which is defined as PF_HEAD so any attempt to access the Workingset bit on a tail page will redirect to the head page's Workingset bit. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Zi Yan Link: https://lkml.kernel.org/r/20200629151933.15671-1-willy@infradead.org Link: https://lkml.kernel.org/r/20200629151933.15671-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 276140c94f4a..76413b2ffef0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -167,7 +167,7 @@ enum pageflags { PG_slob_free = PG_private, /* Compound pages. Stored in first tail page's flags */ - PG_double_map = PG_private_2, + PG_double_map = PG_workingset, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, -- cgit v1.2.3 From a08d93e5752a35a771054f6c463f789720f9a3e8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 13 Oct 2020 16:53:54 -0700 Subject: mm: simplify PageDoubleMap with PF_SECOND policy Introduce the new page policy of PF_SECOND which lets us use the normal pageflags generation machinery to create the various DoubleMap manipulation functions. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Zi Yan Link: https://lkml.kernel.org/r/20200629151933.15671-3-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 40 ++++++++++------------------------------ 1 file changed, 10 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 76413b2ffef0..38ded408bd4c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -235,6 +235,9 @@ static inline void page_init_poison(struct page *page, size_t size) * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. + * + * PF_SECOND: + * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ @@ -250,6 +253,9 @@ static inline void page_init_poison(struct page *page, size_t size) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) +#define PF_SECOND(page, enforce) ({ \ + VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ + PF_POISONED_CHECK(&page[1]); }) /* * Macros to create function definitions for page flags @@ -688,42 +694,15 @@ static inline int PageTransTail(struct page *page) * * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap(). */ -static inline int PageDoubleMap(struct page *page) -{ - return PageHead(page) && test_bit(PG_double_map, &page[1].flags); -} - -static inline void SetPageDoubleMap(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - set_bit(PG_double_map, &page[1].flags); -} - -static inline void ClearPageDoubleMap(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - clear_bit(PG_double_map, &page[1].flags); -} -static inline int TestSetPageDoubleMap(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - return test_and_set_bit(PG_double_map, &page[1].flags); -} - -static inline int TestClearPageDoubleMap(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - return test_and_clear_bit(PG_double_map, &page[1].flags); -} - +PAGEFLAG(DoubleMap, double_map, PF_SECOND) + TESTSCFLAG(DoubleMap, double_map, PF_SECOND) #else TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) TESTPAGEFLAG_FALSE(TransCompoundMap) TESTPAGEFLAG_FALSE(TransTail) PAGEFLAG_FALSE(DoubleMap) - TESTSETFLAG_FALSE(DoubleMap) - TESTCLEARFLAG_FALSE(DoubleMap) + TESTSCFLAG_FALSE(DoubleMap) #endif /* @@ -888,6 +867,7 @@ static inline int page_has_private(struct page *page) #undef PF_ONLY_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND +#undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ -- cgit v1.2.3 From c78f463649d60f4ed12df97a32def4d77b583853 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 13 Oct 2020 16:54:21 -0700 Subject: mm: remove src/dst mm parameter in copy_page_range() Both of the mm pointers are not needed after commit 7a4830c380f3 ("mm/fork: Pass new vma pointer into copy_page_range()"). Jason Gunthorpe also reported that the ordering of copy_page_range() is odd. Since working at it, reorder the parameters to be logical, by (1) always put the dst_* fields to be before src_* fields, and (2) keep the same type of parameters together. [peterx@redhat.com: further reorder some parameters and line format, per Jason] Link: https://lkml.kernel.org/r/20201002192647.7161-1-peterx@redhat.com [peterx@redhat.com: fix warnings] Link: https://lkml.kernel.org/r/20201006200138.GA6026@xz-x1 Reported-by: Kirill A. Shutemov Signed-off-by: Peter Xu Signed-off-by: Andrew Morton Reviewed-by: Jason Gunthorpe Acked-by: Kirill A. Shutemov Link: https://lkml.kernel.org/r/20200930204950.6668-1-peterx@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5320e7ab843f..620961e4f32b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1653,8 +1653,8 @@ struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma, struct vm_area_struct *new); +int +copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); -- cgit v1.2.3 From f577e143d85aa7ea3d9c62c607ad00fc46a5730c Mon Sep 17 00:00:00 2001 From: yuleixzhang Date: Tue, 13 Oct 2020 16:54:25 -0700 Subject: include/linux/huge_mm.h: remove mincore_huge_pmd declaration As mincore_huge_pmd() was dropped, remove the declaration from the header file. Signed-off-by: Yulei Zhang Signed-off-by: Andrew Morton Reviewed-by: Zi Yan Link: https://lkml.kernel.org/r/20200922083423.15074-1-yuleixzhang@tencent.com Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8a8bc46a2432..0365aa97f8e7 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -38,9 +38,6 @@ extern int zap_huge_pmd(struct mmu_gather *tlb, extern int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); -extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned char *vec); extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); -- cgit v1.2.3 From 393824f650fabf6ea32bb09bea7acbc3a062dac8 Mon Sep 17 00:00:00 2001 From: Patricia Alfonso Date: Tue, 13 Oct 2020 16:54:58 -0700 Subject: kasan/kunit: add KUnit Struct to Current Task Patch series "KASAN-KUnit Integration", v14. This patchset contains everything needed to integrate KASAN and KUnit. KUnit will be able to: (1) Fail tests when an unexpected KASAN error occurs (2) Pass tests when an expected KASAN error occurs Convert KASAN tests to KUnit with the exception of copy_user_test because KUnit is unable to test those. Add documentation on how to run the KASAN tests with KUnit and what to expect when running these tests. This patch (of 5): In order to integrate debugging tools like KASAN into the KUnit framework, add KUnit struct to the current task to keep track of the current KUnit test. Signed-off-by: Patricia Alfonso Signed-off-by: David Gow Signed-off-by: Andrew Morton Tested-by: Andrey Konovalov Reviewed-by: Brendan Higgins Cc: Brendan Higgins Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Juri Lelli Cc: Vincent Guittot Cc: Shuah Khan Link: https://lkml.kernel.org/r/20200915035828.570483-1-davidgow@google.com Link: https://lkml.kernel.org/r/20200915035828.570483-2-davidgow@google.com Link: https://lkml.kernel.org/r/20200910070331.3358048-1-davidgow@google.com Link: https://lkml.kernel.org/r/20200910070331.3358048-2-davidgow@google.com Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 829b0697d19c..9030f3abd969 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1208,6 +1208,10 @@ struct task_struct { #endif #endif +#if IS_ENABLED(CONFIG_KUNIT) + struct kunit *kunit_test; +#endif + #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; -- cgit v1.2.3 From 83c4e7a0363bdb8104f510370907161623e31086 Mon Sep 17 00:00:00 2001 From: Patricia Alfonso Date: Tue, 13 Oct 2020 16:55:02 -0700 Subject: KUnit: KASAN Integration Integrate KASAN into KUnit testing framework. - Fail tests when KASAN reports an error that is not expected - Use KUNIT_EXPECT_KASAN_FAIL to expect a KASAN error in KASAN tests - Expected KASAN reports pass tests and are still printed when run without kunit_tool (kunit_tool still bypasses the report due to the test passing) - KUnit struct in current task used to keep track of the current test from KASAN code Make use of "[PATCH v3 kunit-next 1/2] kunit: generalize kunit_resource API beyond allocated resources" and "[PATCH v3 kunit-next 2/2] kunit: add support for named resources" from Alan Maguire [1] - A named resource is added to a test when a KASAN report is expected - This resource contains a struct for kasan_data containing booleans representing if a KASAN report is expected and if a KASAN report is found [1] (https://lore.kernel.org/linux-kselftest/1583251361-12748-1-git-send-email-alan.maguire@oracle.com/T/#t) Signed-off-by: Patricia Alfonso Signed-off-by: David Gow Signed-off-by: Andrew Morton Tested-by: Andrey Konovalov Reviewed-by: Andrey Konovalov Reviewed-by: Dmitry Vyukov Acked-by: Brendan Higgins Cc: Andrey Ryabinin Cc: Ingo Molnar Cc: Juri Lelli Cc: Peter Zijlstra Cc: Shuah Khan Cc: Vincent Guittot Link: https://lkml.kernel.org/r/20200915035828.570483-3-davidgow@google.com Link: https://lkml.kernel.org/r/20200910070331.3358048-3-davidgow@google.com Signed-off-by: Linus Torvalds --- include/kunit/test.h | 5 +++++ include/linux/kasan.h | 6 ++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 59f3144f009a..3391f38389f8 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -224,6 +224,11 @@ struct kunit { struct list_head resources; /* Protected by lock. */ }; +static inline void kunit_set_failure(struct kunit *test) +{ + WRITE_ONCE(test->success, false); +} + void kunit_init_test(struct kunit *test, const char *name, char *log); int kunit_run_tests(struct kunit_suite *suite); diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 087fba34b209..30d343b4a40a 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -14,6 +14,12 @@ struct task_struct; #include #include +/* kasan_data struct is used in KUnit tests for KASAN expected failures */ +struct kunit_kasan_expectation { + bool report_expected; + bool report_found; +}; + extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD]; -- cgit v1.2.3 From 9181a980625a45425085ccec0fc38074a16470a5 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 13 Oct 2020 16:55:35 -0700 Subject: mm: document semantics of ZONE_MOVABLE Let's document what ZONE_MOVABLE means, how it's used, and which special cases we have regarding unmovable pages (memory offlining vs. migration / allocations). Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Acked-by: Mike Rapoport Cc: Michal Hocko Cc: Michael S. Tsirkin Cc: Mike Kravetz Cc: Pankaj Gupta Cc: Baoquan He Cc: Jason Wang Cc: Qian Cai Link: http://lkml.kernel.org/r/20200816125333.7434-7-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0f7a4ff4b059..927bd7e98a88 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -396,6 +396,41 @@ enum zone_type { */ ZONE_HIGHMEM, #endif + /* + * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains + * movable pages with few exceptional cases described below. Main use + * cases for ZONE_MOVABLE are to make memory offlining/unplug more + * likely to succeed, and to locally limit unmovable allocations - e.g., + * to increase the number of THP/huge pages. Notable special cases are: + * + * 1. Pinned pages: (long-term) pinning of movable pages might + * essentially turn such pages unmovable. Memory offlining might + * retry a long time. + * 2. memblock allocations: kernelcore/movablecore setups might create + * situations where ZONE_MOVABLE contains unmovable allocations + * after boot. Memory offlining and allocations fail early. + * 3. Memory holes: kernelcore/movablecore setups might create very rare + * situations where ZONE_MOVABLE contains memory holes after boot, + * for example, if we have sections that are only partially + * populated. Memory offlining and allocations fail early. + * 4. PG_hwpoison pages: while poisoned pages can be skipped during + * memory offlining, such pages cannot be allocated. + * 5. Unmovable PG_offline pages: in paravirtualized environments, + * hotplugged memory blocks might only partially be managed by the + * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The + * parts not manged by the buddy are unmovable PG_offline pages. In + * some cases (virtio-mem), such pages can be skipped during + * memory offlining, however, cannot be moved/allocated. These + * techniques might use alloc_contig_range() to hide previously + * exposed pages from the buddy again (e.g., to implement some sort + * of memory unplug in virtio-mem). + * + * In general, no unmovable allocations that degrade memory offlining + * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) + * have to expect that migrating pages in ZONE_MOVABLE can fail (even + * if has_unmovable_pages() states that there are no unmovable pages, + * there can be false negatives). + */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, -- cgit v1.2.3 From 30d8ec73e8772b32a7eae626d14004bd37d8f13c Mon Sep 17 00:00:00 2001 From: Mateusz Nosek Date: Tue, 13 Oct 2020 16:55:57 -0700 Subject: mmzone: clean code by removing unused macro parameter Previously 'for_next_zone_zonelist_nodemask' macro parameter 'zlist' was unused so this patch removes it. Signed-off-by: Mateusz Nosek Signed-off-by: Andrew Morton Link: https://lkml.kernel.org/r/20200917211906.30059-1-mateusznosek0@gmail.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 927bd7e98a88..c27fb1faffe5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1116,7 +1116,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) -#define for_next_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ +#define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = z->zone; \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ -- cgit v1.2.3 From ab00db216c9c78cc0a68bc4e27889c1ee374598d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 13 Oct 2020 16:56:07 -0700 Subject: include/linux/gfp.h: clarify usage of GFP_ATOMIC in !preemptible contexts There is a general understanding that GFP_ATOMIC/GFP_NOWAIT are to be used from atomic contexts. E.g. from within a spin lock or from the IRQ context. This is correct but there are some atomic contexts where the above doesn't hold. One of them would be an NMI context. Page allocator has never supported that and the general fear of this context didn't let anybody to actually even try to use the allocator there. Good, but let's be more specific about that. Another such a context, and that is where people seem to be more daring, is raw_spin_lock. Mostly because it simply resembles regular spin lock which is supported by the allocator and there is not any implementation difference with !RT kernels in the first place. Be explicit that such a context is not supported by the allocator. The underlying reason is that zone->lock would have to become raw_spin_lock as well and that has turned out to be a problem for RT (http://lkml.kernel.org/r/87mu305c1w.fsf@nanos.tec.linutronix.de). Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: Thomas Gleixner Reviewed-by: Uladzislau Rezki Cc: "Paul E. McKenney" Link: https://lkml.kernel.org/r/20200929123010.5137-1-mhocko@kernel.org Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 67a0774e080b..2e8370cf60c7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -238,7 +238,9 @@ struct vm_area_struct; * %__GFP_FOO flags as necessary. * * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower - * watermark is applied to allow access to "atomic reserves" + * watermark is applied to allow access to "atomic reserves". + * The current implementation doesn't support NMI and few other strict + * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. * * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. -- cgit v1.2.3 From 74c9da4e1dc0ecf70e7fa78568821e3ed8f77938 Mon Sep 17 00:00:00 2001 From: Mateusz Nosek Date: Tue, 13 Oct 2020 16:57:01 -0700 Subject: include/linux/compaction.h: clean code by removing unused enum value The enum value 'COMPACT_INACTIVE' is never used so can be removed. Signed-off-by: Mateusz Nosek Signed-off-by: Andrew Morton Link: https://lkml.kernel.org/r/20200917110750.12015-1-mateusznosek0@gmail.com Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 25a521d299c1..1de5a1151ee7 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -29,9 +29,6 @@ enum compact_result { /* compaction didn't start as it was deferred due to past failures */ COMPACT_DEFERRED, - /* compaction not active last round */ - COMPACT_INACTIVE = COMPACT_DEFERRED, - /* For more detailed tracepoint output - internal to compaction */ COMPACT_NO_SUITABLE_PAGE, /* compaction should continue to another pageblock */ -- cgit v1.2.3 From f8fd52535c7326d72645c9878d7897aaf44db51c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 13 Oct 2020 16:57:11 -0700 Subject: mm: remove unused alloc_page_vma_node() No one use this macro anymore. Also fix code style of policy_node(). Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: https://lkml.kernel.org/r/20200921021401.84508-1-richard.weiyang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2e8370cf60c7..07e481993ef5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -562,8 +562,6 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) -#define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -- cgit v1.2.3 From cd991db8ddc33d2d2c7af45627fc48352915001c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 13 Oct 2020 16:57:49 -0700 Subject: memblock: make for_each_memblock_type() iterator private for_each_memblock_type() is not used outside mm/memblock.c, move it there from include/linux/memblock.h Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Daniel Axtens Cc: Dave Hansen Cc: Emil Renner Berthing Cc: Hari Bathini Cc: Ingo Molnar Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Marek Szyprowski Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Miguel Ojeda Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Will Deacon Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200818151634.14343-9-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9d925db0d355..550faf69fc1c 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -552,11 +552,6 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo region < (memblock.memblock_type.regions + memblock.memblock_type.cnt); \ region++) -#define for_each_memblock_type(i, memblock_type, rgn) \ - for (i = 0, rgn = &memblock_type->regions[0]; \ - i < memblock_type->cnt; \ - i++, rgn = &memblock_type->regions[i]) - extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, unsigned long numentries, -- cgit v1.2.3 From 87c55870f01266fe22f345a0767162f85f1cf8f1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 13 Oct 2020 16:57:54 -0700 Subject: memblock: make memblock_debug and related functionality private The only user of memblock_dbg() outside memblock was s390 setup code and it is converted to use pr_debug() instead. This allows to stop exposing memblock_debug and memblock_dbg() to the rest of the kernel. [akpm@linux-foundation.org: make memblock_dbg() safer and neater] Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Daniel Axtens Cc: Dave Hansen Cc: Emil Renner Berthing Cc: Hari Bathini Cc: Ingo Molnar Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Marek Szyprowski Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Miguel Ojeda Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Will Deacon Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200818151634.14343-10-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 550faf69fc1c..47a76e237fca 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -86,7 +86,6 @@ struct memblock { }; extern struct memblock memblock; -extern int memblock_debug; #ifndef CONFIG_ARCH_KEEP_MEMBLOCK #define __init_memblock __meminit @@ -98,9 +97,6 @@ void memblock_discard(void); static inline void memblock_discard(void) {} #endif -#define memblock_dbg(fmt, ...) \ - if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) - phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); void memblock_allow_resize(void); @@ -476,13 +472,7 @@ bool memblock_is_region_memory(phys_addr_t base, phys_addr_t size); bool memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); -extern void __memblock_dump_all(void); - -static inline void memblock_dump_all(void) -{ - if (memblock_debug) - __memblock_dump_all(); -} +void memblock_dump_all(void); /** * memblock_set_current_limit - Set the current allocation limit to allow -- cgit v1.2.3 From 6e245ad4a17ab92dba63406d3f517520a86c0a80 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 13 Oct 2020 16:57:59 -0700 Subject: memblock: reduce number of parameters in for_each_mem_range() Currently for_each_mem_range() and for_each_mem_range_rev() iterators are the most generic way to traverse memblock regions. As such, they have 8 parameters and they are hardly convenient to users. Most users choose to utilize one of their wrappers and the only user that actually needs most of the parameters is memblock itself. To avoid yet another naming for memblock iterators, rename the existing for_each_mem_range[_rev]() to __for_each_mem_range[_rev]() and add a new for_each_mem_range[_rev]() wrappers with only index, start and end parameters. The new wrapper nicely fits into init_unavailable_mem() and will be used in upcoming changes to simplify memblock traversals. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Acked-by: Thomas Bogendoerfer [MIPS] Cc: Andy Lutomirski Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Daniel Axtens Cc: Dave Hansen Cc: Emil Renner Berthing Cc: Hari Bathini Cc: Ingo Molnar Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Marek Szyprowski Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Miguel Ojeda Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Stafford Horne Cc: Thomas Gleixner Cc: Will Deacon Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200818151634.14343-11-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 41 +++++++++++++++++++++++++++++++---------- 1 file changed, 31 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 47a76e237fca..27c3b84d1615 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -162,7 +162,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, #endif /* CONFIG_HAVE_MEMBLOCK_PHYS_MAP */ /** - * for_each_mem_range - iterate through memblock areas from type_a and not + * __for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. * @i: u64 used as loop variable * @type_a: ptr to memblock_type to iterate @@ -173,7 +173,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL */ -#define for_each_mem_range(i, type_a, type_b, nid, flags, \ +#define __for_each_mem_range(i, type_a, type_b, nid, flags, \ p_start, p_end, p_nid) \ for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid); \ @@ -182,7 +182,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, p_start, p_end, p_nid)) /** - * for_each_mem_range_rev - reverse iterate through memblock areas from + * __for_each_mem_range_rev - reverse iterate through memblock areas from * type_a and not included in type_b. Or just type_a if type_b is NULL. * @i: u64 used as loop variable * @type_a: ptr to memblock_type to iterate @@ -193,15 +193,36 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL */ -#define for_each_mem_range_rev(i, type_a, type_b, nid, flags, \ - p_start, p_end, p_nid) \ +#define __for_each_mem_range_rev(i, type_a, type_b, nid, flags, \ + p_start, p_end, p_nid) \ for (i = (u64)ULLONG_MAX, \ - __next_mem_range_rev(&i, nid, flags, type_a, type_b,\ + __next_mem_range_rev(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid); \ i != (u64)ULLONG_MAX; \ __next_mem_range_rev(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid)) +/** + * for_each_mem_range - iterate through memory areas. + * @i: u64 used as loop variable + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + */ +#define for_each_mem_range(i, p_start, p_end) \ + __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ + MEMBLOCK_NONE, p_start, p_end, NULL) + +/** + * for_each_mem_range_rev - reverse iterate through memblock areas from + * type_a and not included in type_b. Or just type_a if type_b is NULL. + * @i: u64 used as loop variable + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + */ +#define for_each_mem_range_rev(i, p_start, p_end) \ + __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ + MEMBLOCK_NONE, p_start, p_end, NULL) + /** * for_each_reserved_mem_region - iterate over all reserved memblock areas * @i: u64 used as loop variable @@ -307,8 +328,8 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); * soon as memblock is initialized. */ #define for_each_free_mem_range(i, nid, flags, p_start, p_end, p_nid) \ - for_each_mem_range(i, &memblock.memory, &memblock.reserved, \ - nid, flags, p_start, p_end, p_nid) + __for_each_mem_range(i, &memblock.memory, &memblock.reserved, \ + nid, flags, p_start, p_end, p_nid) /** * for_each_free_mem_range_reverse - rev-iterate through free memblock areas @@ -324,8 +345,8 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); */ #define for_each_free_mem_range_reverse(i, nid, flags, p_start, p_end, \ p_nid) \ - for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ - nid, flags, p_start, p_end, p_nid) + __for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ + nid, flags, p_start, p_end, p_nid) int memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid); -- cgit v1.2.3 From 5bd0960b85d7e3e4a2dc5bbf1c87d0b505115d71 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 13 Oct 2020 16:58:20 -0700 Subject: memblock: remove unused memblock_mem_size() The only user of memblock_mem_size() was x86 setup code, it is gone now and memblock_mem_size() funciton can be removed. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Daniel Axtens Cc: Dave Hansen Cc: Emil Renner Berthing Cc: Hari Bathini Cc: Ingo Molnar Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Marek Szyprowski Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Miguel Ojeda Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Will Deacon Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200818151634.14343-16-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 27c3b84d1615..15ed119701c1 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -481,7 +481,6 @@ static inline bool memblock_bottom_up(void) phys_addr_t memblock_phys_mem_size(void); phys_addr_t memblock_reserved_size(void); -phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); -- cgit v1.2.3 From 9f3d5eaa3c60f95d9fff1ce4eea7553a3dc04906 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 13 Oct 2020 16:58:25 -0700 Subject: memblock: implement for_each_reserved_mem_region() using __next_mem_region() Iteration over memblock.reserved with for_each_reserved_mem_region() used __next_reserved_mem_region() that implemented a subset of __next_mem_region(). Use __for_each_mem_range() and, essentially, __next_mem_region() with appropriate parameters to reduce code duplication. While on it, rename for_each_reserved_mem_region() to for_each_reserved_mem_range() for consistency. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Acked-by: Miguel Ojeda [.clang-format] Cc: Andy Lutomirski Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Daniel Axtens Cc: Dave Hansen Cc: Emil Renner Berthing Cc: Hari Bathini Cc: Ingo Molnar Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Marek Szyprowski Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Will Deacon Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200818151634.14343-17-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 15ed119701c1..354078713cd1 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -132,9 +132,6 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, - phys_addr_t *out_end); - void __memblock_free_late(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP @@ -224,7 +221,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, MEMBLOCK_NONE, p_start, p_end, NULL) /** - * for_each_reserved_mem_region - iterate over all reserved memblock areas + * for_each_reserved_mem_range - iterate over all reserved memblock areas * @i: u64 used as loop variable * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL @@ -232,10 +229,9 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, * Walks over reserved areas of memblock. Available as soon as memblock * is initialized. */ -#define for_each_reserved_mem_region(i, p_start, p_end) \ - for (i = 0UL, __next_reserved_mem_region(&i, p_start, p_end); \ - i != (u64)ULLONG_MAX; \ - __next_reserved_mem_region(&i, p_start, p_end)) +#define for_each_reserved_mem_range(i, p_start, p_end) \ + __for_each_mem_range(i, &memblock.reserved, NULL, NUMA_NO_NODE, \ + MEMBLOCK_NONE, p_start, p_end, NULL) static inline bool memblock_is_hotpluggable(struct memblock_region *m) { -- cgit v1.2.3 From cc6de1680538633e4ef9540b2313fa2481a7c641 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 13 Oct 2020 16:58:30 -0700 Subject: memblock: use separate iterators for memory and reserved regions for_each_memblock() is used to iterate over memblock.memory in a few places that use data from memblock_region rather than the memory ranges. Introduce separate for_each_mem_region() and for_each_reserved_mem_region() to improve encapsulation of memblock internals from its users. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Acked-by: Ingo Molnar [x86] Acked-by: Thomas Bogendoerfer [MIPS] Acked-by: Miguel Ojeda [.clang-format] Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Daniel Axtens Cc: Dave Hansen Cc: Emil Renner Berthing Cc: Hari Bathini Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Marek Szyprowski Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Stafford Horne Cc: Thomas Gleixner Cc: Will Deacon Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200818151634.14343-18-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 354078713cd1..ef131255cedc 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -553,9 +553,22 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo return PFN_UP(reg->base + reg->size); } -#define for_each_memblock(memblock_type, region) \ - for (region = memblock.memblock_type.regions; \ - region < (memblock.memblock_type.regions + memblock.memblock_type.cnt); \ +/** + * for_each_mem_region - itereate over memory regions + * @region: loop variable + */ +#define for_each_mem_region(region) \ + for (region = memblock.memory.regions; \ + region < (memblock.memory.regions + memblock.memory.cnt); \ + region++) + +/** + * for_each_reserved_mem_region - itereate over reserved memory regions + * @region: loop variable + */ +#define for_each_reserved_mem_region(region) \ + for (region = memblock.reserved.regions; \ + region < (memblock.reserved.regions + memblock.reserved.cnt); \ region++) extern void *alloc_large_system_hash(const char *tablename, -- cgit v1.2.3 From 67197a4f28d28d0b073ab0427b03cb2ee5382578 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 13 Oct 2020 16:58:35 -0700 Subject: mm, oom_adj: don't loop through tasks in __set_oom_adj when not necessary Currently __set_oom_adj loops through all processes in the system to keep oom_score_adj and oom_score_adj_min in sync between processes sharing their mm. This is done for any task with more that one mm_users, which includes processes with multiple threads (sharing mm and signals). However for such processes the loop is unnecessary because their signal structure is shared as well. Android updates oom_score_adj whenever a tasks changes its role (background/foreground/...) or binds to/unbinds from a service, making it more/less important. Such operation can happen frequently. We noticed that updates to oom_score_adj became more expensive and after further investigation found out that the patch mentioned in "Fixes" introduced a regression. Using Pixel 4 with a typical Android workload, write time to oom_score_adj increased from ~3.57us to ~362us. Moreover this regression linearly depends on the number of multi-threaded processes running on the system. Mark the mm with a new MMF_MULTIPROCESS flag bit when task is created with (CLONE_VM && !CLONE_THREAD && !CLONE_VFORK). Change __set_oom_adj to use MMF_MULTIPROCESS instead of mm_users to decide whether oom_score_adj update should be synchronized between multiple processes. To prevent races between clone() and __set_oom_adj(), when oom_score_adj of the process being cloned might be modified from userspace, we use oom_adj_mutex. Its scope is changed to global. The combination of (CLONE_VM && !CLONE_THREAD) is rarely used except for the case of vfork(). To prevent performance regressions of vfork(), we skip taking oom_adj_mutex and setting MMF_MULTIPROCESS when CLONE_VFORK is specified. Clearing the MMF_MULTIPROCESS flag (when the last process sharing the mm exits) is left out of this patch to keep it simple and because it is believed that this threading model is rare. Should there ever be a need for optimizing that case as well, it can be done by hooking into the exit path, likely following the mm_update_next_owner pattern. With the combination of (CLONE_VM && !CLONE_THREAD && !CLONE_VFORK) being quite rare, the regression is gone after the change is applied. [surenb@google.com: v3] Link: https://lkml.kernel.org/r/20200902012558.2335613-1-surenb@google.com Fixes: 44a70adec910 ("mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj") Reported-by: Tim Murray Suggested-by: Michal Hocko Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton Acked-by: Christian Brauner Acked-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Eugene Syromiatnikov Cc: Christian Kellner Cc: Adrian Reber Cc: Shakeel Butt Cc: Aleksa Sarai Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Cc: Alexey Gladkov Cc: Michel Lespinasse Cc: Daniel Jordan Cc: Andrei Vagin Cc: Bernd Edlinger Cc: John Johansen Cc: Yafang Shao Link: https://lkml.kernel.org/r/20200824153036.3201505-1-surenb@google.com Debugged-by: Minchan Kim Signed-off-by: Linus Torvalds --- include/linux/oom.h | 1 + include/linux/sched/coredump.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index f022f581ac29..2db9a1432511 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -55,6 +55,7 @@ struct oom_control { }; extern struct mutex oom_lock; +extern struct mutex oom_adj_mutex; static inline void set_current_oom_origin(void) { diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ecdc6542070f..dfd82eab2902 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -72,6 +72,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ #define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 27 /* mm is shared between processes */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ -- cgit v1.2.3 From ed3e453798d4f81c99056aa09fcd79d0874a60fd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 13 Oct 2020 14:14:43 +0200 Subject: locking/seqlocks: Fix kernel-doc warnings Right now, seqlock.h produces kernel-doc warnings: ./include/linux/seqlock.h:181: error: Cannot parse typedef! Convert it to a plain comment to avoid confusing kernel-doc. Fixes: a8772dccb2ec ("seqlock: Fold seqcount_LOCKNAME_t definition") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/a59144cdaadf7fdf1fe5d55d0e1575abbf1c0cb3.1602590106.git.mchehab+huawei@kernel.org --- include/linux/seqlock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index ac5b07f558b0..cbfc78b92b65 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -154,7 +154,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #define __SEQ_LOCK(expr) #endif -/** +/* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock -- cgit v1.2.3 From 626b901f60446355e35e8c76c6b391a7d7491203 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Fri, 14 Aug 2020 12:45:04 -0700 Subject: Drivers: hv: vmbus: Add parsing of VMbus interrupt in ACPI DSDT On ARM64, Hyper-V now specifies the interrupt to be used by VMbus in the ACPI DSDT. This information is not used on x86 because the interrupt vector must be hardcoded. But update the generic VMbus driver to do the parsing and pass the information to the architecture specific code that sets up the Linux IRQ. Update consumers of the interrupt to get it from an architecture specific function. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1597434304-40631-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/asm-generic/mshyperv.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c5edc5e08b94..c57799684170 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -89,7 +89,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) } } -void hv_setup_vmbus_irq(void (*handler)(void)); +int hv_setup_vmbus_irq(int irq, void (*handler)(void)); void hv_remove_vmbus_irq(void); void hv_enable_vmbus_irq(void); void hv_disable_vmbus_irq(void); @@ -99,6 +99,8 @@ void hv_remove_kexec_handler(void); void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)); void hv_remove_crash_handler(void); +extern int vmbus_interrupt; + #if IS_ENABLED(CONFIG_HYPERV) /* * Hypervisor's notion of virtual processor ID is different from -- cgit v1.2.3 From 02e83f46ebfaf9405881e290794c913d457541f0 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 14 Oct 2020 16:47:08 -0700 Subject: vfs: move generic_remap_checks out of mm I would like to move all the generic helpers for the vfs remap range functionality (aka clonerange and dedupe) into a separate file so that they won't be scattered across the vfs and the mm subsystems. The eventual goal is to be able to deselect remap_range.c if none of the filesystems need that code, but the tricky part here is picking a stable(ish) part of the merge window to rearrange code. Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a08..eea754a8dd67 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3012,6 +3012,8 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); +extern int generic_write_check_limits(struct file *file, loff_t pos, + loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, -- cgit v1.2.3 From d25e2e9388eda61b6e298585024ee3355f50c493 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 14 Oct 2020 21:34:32 +0200 Subject: netfilter: restore NF_INET_NUMHOOKS This definition is used by the iptables legacy UAPI, restore it. Fixes: d3519cb89f6d ("netfilter: nf_tables: add inet ingress support") Reported-by: Jason A. Donenfeld Tested-by: Jason A. Donenfeld Signed-off-by: Pablo Neira Ayuso Signed-off-by: Jakub Kicinski --- include/net/netfilter/nf_tables.h | 4 +++- include/uapi/linux/netfilter.h | 4 ++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3965ce18226f..3f7e56b1171e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -14,6 +14,8 @@ #include #include +#define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) + struct module; #define NFT_JUMP_STACK_SIZE 16 @@ -979,7 +981,7 @@ struct nft_chain_type { int family; struct module *owner; unsigned int hook_mask; - nf_hookfn *hooks[NF_MAX_HOOKS]; + nf_hookfn *hooks[NFT_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); }; diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index 6a6179af0d7c..ef9a44286e23 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -45,8 +45,8 @@ enum nf_inet_hooks { NF_INET_FORWARD, NF_INET_LOCAL_OUT, NF_INET_POST_ROUTING, - NF_INET_INGRESS, - NF_INET_NUMHOOKS + NF_INET_NUMHOOKS, + NF_INET_INGRESS = NF_INET_NUMHOOKS, }; enum nf_dev_hooks { -- cgit v1.2.3 From c2a9a645591f11761fdbe3c7f45c0ad32af97eb4 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Sep 2020 15:25:17 +0200 Subject: math64.h: kernel-docs: Convert some markups into normal comments There are several functions at math64.h that are also defined at div64.c. As both are included at kernel-api.rst, Sphinx 3.x complains about symbol duplication: ./lib/math/div64.c:73: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'. Declaration is 'div_s64_rem'. ./lib/math/div64.c:104: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'. Declaration is 'div64_u64_rem'. ./lib/math/div64.c:144: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'. Declaration is 'div64_u64'. ./lib/math/div64.c:172: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'. Declaration is 'div64_s64'. In order to avoid Sphinx warnings about duplication, change the kernel-doc markups to just comments at math64.h. Reviewed-by: Vincenzo Frascino Signed-off-by: Mauro Carvalho Chehab --- include/linux/math64.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/math64.h b/include/linux/math64.h index 3381d9e33c4e..66deb1fdc2ef 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -28,7 +28,7 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) return dividend / divisor; } -/** +/* * div_s64_rem - signed 64bit divide with 32bit divisor with remainder * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor @@ -42,7 +42,7 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) return dividend / divisor; } -/** +/* * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor @@ -56,7 +56,7 @@ static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) return dividend / divisor; } -/** +/* * div64_u64 - unsigned 64bit divide with 64bit divisor * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor @@ -68,7 +68,7 @@ static inline u64 div64_u64(u64 dividend, u64 divisor) return dividend / divisor; } -/** +/* * div64_s64 - signed 64bit divide with 64bit divisor * @dividend: signed 64bit dividend * @divisor: signed 64bit divisor -- cgit v1.2.3 From 38d9b909f90e715c4b5d572e4e9c914a10931094 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Aug 2020 08:31:43 +0200 Subject: kunit: test.h: solve kernel-doc warnings There are some warnings there: ./include/kunit/test.h:90: warning: Function parameter or member 'name' not described in 'kunit_resource' ./include/kunit/test.h:353: warning: Function parameter or member 'res' not described in 'kunit_add_resource' ./include/kunit/test.h:367: warning: Function parameter or member 'res' not described in 'kunit_add_named_resource' ./include/kunit/test.h:367: warning: Function parameter or member 'name' not described in 'kunit_add_named_resource' ./include/kunit/test.h:367: warning: Function parameter or member 'data' not described in 'kunit_add_named_resource' ./include/kunit/test.h:367: warning: Excess function parameter 'name_data' description in 'kunit_add_named_resource' Address them, ensuring that all non-private arguments will be properly described. With that regards, at struct kunit_resource, the free argument is described as user-provided. So, this doesn't seem to belong to the "private" part of the struct. Signed-off-by: Mauro Carvalho Chehab --- include/kunit/test.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 3391f38389f8..dba5867c2621 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -25,6 +25,7 @@ typedef void (*kunit_resource_free_t)(struct kunit_resource *); /** * struct kunit_resource - represents a *test managed resource* * @data: for the user to store arbitrary data. + * @name: optional name * @free: a user supplied function to free the resource. Populated by * kunit_resource_alloc(). * @@ -80,10 +81,10 @@ typedef void (*kunit_resource_free_t)(struct kunit_resource *); */ struct kunit_resource { void *data; - const char *name; /* optional name */ + const char *name; + kunit_resource_free_t free; /* private: internal use only. */ - kunit_resource_free_t free; struct kref refcount; struct list_head node; }; @@ -348,6 +349,7 @@ static inline void kunit_put_resource(struct kunit_resource *res) * none is supplied, the resource data value is simply set to @data. * If an init function is supplied, @data is passed to it instead. * @free: a user-supplied function to free the resource (if needed). + * @res: The resource. * @data: value to pass to init function or set in resource data field. */ int kunit_add_resource(struct kunit *test, @@ -361,7 +363,9 @@ int kunit_add_resource(struct kunit *test, * @test: The test context object. * @init: a user-supplied function to initialize the resource data, if needed. * @free: a user-supplied function to free the resource data, if needed. - * @name_data: name and data to be set for resource. + * @res: The resource. + * @name: name to be set for resource. + * @data: value to pass to init function or set in resource data field. */ int kunit_add_named_resource(struct kunit *test, kunit_resource_init_t init, -- cgit v1.2.3 From 623050ae373162a65973f62c128eabe3ec288c4d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 9 Sep 2020 12:07:49 +0200 Subject: kunit: test.h: fix a bad kernel-doc markup As warned by: ./include/kunit/test.h:504: WARNING: Block quote ends without a blank line; unexpected unindent. The right way to describe a function is: name - description Instead, kunit_remove_resource was using: name: description Causing it to be improperly parsed. Signed-off-by: Mauro Carvalho Chehab --- include/kunit/test.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index dba5867c2621..037de35ae0ff 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -503,8 +503,8 @@ static inline int kunit_destroy_named_resource(struct kunit *test, } /** - * kunit_remove_resource: remove resource from resource list associated with - * test. + * kunit_remove_resource() - remove resource from resource list associated with + * test. * @test: The test context object. * @res: The resource to be removed. * -- cgit v1.2.3 From 1b7743912bcf2b4a9d9c96de668542156450554f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 10 Sep 2020 09:25:14 +0200 Subject: usb: docs: document altmode register/unregister functions The typec_bus.rst asks for documentation of those two functions, but they don't exist: ./drivers/usb/typec/bus.c:1: warning: 'typec_altmode_unregister_driver' not found ./drivers/usb/typec/bus.c:1: warning: 'typec_altmode_register_driver' not found Also, they're not declared on bus.c but, instead, at a header file (typec_altmode.h). So, add documentation for both functions at the header and change the kernel-doc markup under typec_bus.rst to point to the right place. While here, also place the documentation for both structs declared on typec_altmode.h at the rst file. Signed-off-by: Mauro Carvalho Chehab --- include/linux/usb/typec_altmode.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index a4b65eaa0f62..5e0a7b7647c3 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -152,10 +152,26 @@ struct typec_altmode_driver { #define to_altmode_driver(d) container_of(d, struct typec_altmode_driver, \ driver) +/** + * typec_altmode_register_driver - registers a USB Type-C alternate mode + * device driver + * @drv: pointer to struct typec_altmode_driver + * + * These drivers will be bind to the partner alternate mode devices. They will + * handle all SVID specific communication. + */ #define typec_altmode_register_driver(drv) \ __typec_altmode_register_driver(drv, THIS_MODULE) int __typec_altmode_register_driver(struct typec_altmode_driver *drv, struct module *module); +/** + * typec_altmode_unregister_driver - unregisters a USB Type-C alternate mode + * device driver + * @drv: pointer to struct typec_altmode_driver + * + * These drivers will be bind to the partner alternate mode devices. They will + * handle all SVID specific communication. + */ void typec_altmode_unregister_driver(struct typec_altmode_driver *drv); #define module_typec_altmode_driver(__typec_altmode_driver) \ -- cgit v1.2.3 From 8a50c0572ffa816d0067fcf24911a27efd45237c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 10 Sep 2020 10:06:47 +0200 Subject: nl80211: docs: add a description for s1g_cap parameter Changeset df78a0c0b67d ("nl80211: S1G band and channel definitions") added a new parameter, but didn't add the corresponding kernel-doc markup, as repoted when doing "make htmldocs": ./include/net/cfg80211.h:471: warning: Function parameter or member 's1g_cap' not described in 'ieee80211_supported_band' Add a documentation for it. Fixes: df78a0c0b67d ("nl80211: S1G band and channel definitions") Signed-off-by: Thomas Pedersen Signed-off-by: Mauro Carvalho Chehab --- include/net/cfg80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d9e6b9fbd95b..fb6aece00549 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -449,6 +449,7 @@ struct ieee80211_sta_s1g_cap { * @n_bitrates: Number of bitrates in @bitrates * @ht_cap: HT capabilities in this band * @vht_cap: VHT capabilities in this band + * @s1g_cap: S1G capabilities in this band * @edmg_cap: EDMG capabilities in this band * @n_iftype_data: number of iftype data entries * @iftype_data: interface type data entries. Note that the bits in -- cgit v1.2.3 From f2c6855159228861f4552d563c13f5b194b9889f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 10 Sep 2020 10:27:17 +0200 Subject: Input: sparse-keymap: add a description for @sw Add a description for it, in order to avoids this warning: ./include/linux/input/sparse-keymap.h:43: warning: Function parameter or member 'sw' not described in 'key_entry' Signed-off-by: Mauro Carvalho Chehab --- include/linux/input/sparse-keymap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/input/sparse-keymap.h b/include/linux/input/sparse-keymap.h index d25d1452dc6e..d0dddc14ebc8 100644 --- a/include/linux/input/sparse-keymap.h +++ b/include/linux/input/sparse-keymap.h @@ -20,6 +20,7 @@ * private definitions. * @code: Device-specific data identifying the button/switch * @keycode: KEY_* code assigned to a key/button + * @sw: struct with code/value used by KE_SW and KE_VSW * @sw.code: SW_* code assigned to a switch * @sw.value: Value that should be sent in an input even when KE_SW * switch is toggled. KE_VSW switches ignore this field and -- cgit v1.2.3 From 770c03e6dabacd5b9f57bba93c4311d32b618640 Mon Sep 17 00:00:00 2001 From: Fei Shao Date: Thu, 8 Oct 2020 17:34:14 +0800 Subject: rtc: mt6397: Remove unused member dev Removing the struct member "dev" in mt6397 RTC driver because it's not initialized and the only usage is for one debugging message. Also fixed a typo in the error message. Signed-off-by: Fei Shao Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20201008093414.1911699-1-fshao@chromium.org --- include/linux/mfd/mt6397/rtc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index 66989a16221a..c3748b53bf7d 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -72,7 +72,6 @@ struct mtk_rtc_data { }; struct mt6397_rtc { - struct device *dev; struct rtc_device *rtc_dev; /* Protect register access from multiple tasks */ -- cgit v1.2.3 From d086a1c65aabb5a4e1edc580ca583e2964c62b44 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 14 Oct 2020 11:56:42 +0300 Subject: net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info The access of tcf_tunnel_info() produces the following splat, so fix it by dereferencing the tcf_tunnel_key_params pointer with marker that internal tcfa_liock is held. ============================= WARNING: suspicious RCU usage 5.9.0+ #1 Not tainted ----------------------------- include/net/tc_act/tc_tunnel_key.h:59 suspicious rcu_dereference_protected() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by tc/34839: #0: ffff88828572c2a0 (&p->tcfa_lock){+...}-{2:2}, at: tc_setup_flow_action+0xb3/0x48b5 stack backtrace: CPU: 1 PID: 34839 Comm: tc Not tainted 5.9.0+ #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x9a/0xd0 tc_setup_flow_action+0x14cb/0x48b5 fl_hw_replace_filter+0x347/0x690 [cls_flower] fl_change+0x2bad/0x4875 [cls_flower] tc_new_tfilter+0xf6f/0x1ba0 rtnetlink_rcv_msg+0x5f2/0x870 netlink_rcv_skb+0x124/0x350 netlink_unicast+0x433/0x700 netlink_sendmsg+0x6f1/0xbd0 sock_sendmsg+0xb0/0xe0 ____sys_sendmsg+0x4fa/0x6d0 ___sys_sendmsg+0x12e/0x1b0 __sys_sendmsg+0xa4/0x120 do_syscall_64+0x2d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f1f8cd4fe57 Code: 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 RSP: 002b:00007ffdc1e193b8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1f8cd4fe57 RDX: 0000000000000000 RSI: 00007ffdc1e19420 RDI: 0000000000000003 RBP: 000000005f85aafa R08: 0000000000000001 R09: 00007ffdc1e1936c R10: 000000000040522d R11: 0000000000000246 R12: 0000000000000001 R13: 0000000000000000 R14: 00007ffdc1e1d6f0 R15: 0000000000482420 Fixes: 3ebaf6da0716 ("net: sched: Do not assume RTNL is held in tunnel key action helpers") Fixes: 7a47281439ba ("net: sched: lock action when translating it to flow_action infra") Signed-off-by: Leon Romanovsky Acked-by: Cong Wang Signed-off-by: Jakub Kicinski --- include/net/tc_act/tc_tunnel_key.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h index e1057b255f69..879fe8cff581 100644 --- a/include/net/tc_act/tc_tunnel_key.h +++ b/include/net/tc_act/tc_tunnel_key.h @@ -56,7 +56,10 @@ static inline struct ip_tunnel_info *tcf_tunnel_info(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT struct tcf_tunnel_key *t = to_tunnel_key(a); - struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); + struct tcf_tunnel_key_params *params; + + params = rcu_dereference_protected(t->params, + lockdep_is_held(&a->tcfa_lock)); return ¶ms->tcft_enc_metadata->u.tun_info; #else -- cgit v1.2.3 From 1b2c54d63cde7e8cf15aa6319aba168d81c7e364 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 14 Oct 2020 16:38:47 -0700 Subject: vfs: move the remap range helpers to remap_range.c Complete the migration by moving the file remapping helper functions out of read_write.c and into remap_range.c. This reduces the clutter in the first file and (eventually) will make it so that we can compile out the second file if it isn't needed. Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index eea754a8dd67..073da53b59b0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3009,9 +3009,6 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); -extern int generic_remap_checks(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *count, unsigned int remap_flags); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); -- cgit v1.2.3 From 407e9c63ee571f44a2dfb0828fc30daa02abb6dc Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 15 Oct 2020 09:21:17 -0700 Subject: vfs: move the generic write and copy checks out of mm The generic write check helpers also don't have much to do with the page cache, so move them to the vfs. Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 073da53b59b0..8fb063ab7d50 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3012,9 +3012,6 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); -extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t *count, unsigned int flags); extern ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From 346e320cb2103edef709c4466a29140c4a8e527a Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 15 Oct 2020 18:39:27 +0200 Subject: netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements nftables payload statements are used to mangle SCTP headers, but they can only replace the Internet Checksum. As a consequence, nftables rules that mangle sport/dport/vtag in SCTP headers potentially generate packets that are discarded by the receiver, unless the CRC-32C is "offloaded" (e.g the rule mangles a skb having 'ip_summed' equal to 'CHECKSUM_PARTIAL'. Fix this extending uAPI definitions and L4 checksum update function, in a way that userspace programs (e.g. nft) can instruct the kernel to compute CRC-32C in SCTP headers. Also ensure that LIBCRC32C is built if NF_TABLES is 'y' or 'm' in the kernel build configuration. Signed-off-by: Davide Caratti Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Jakub Kicinski --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 352ee51707a1..98272cb5f617 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -749,10 +749,12 @@ enum nft_payload_bases { * * @NFT_PAYLOAD_CSUM_NONE: no checksumming * @NFT_PAYLOAD_CSUM_INET: internet checksum (RFC 791) + * @NFT_PAYLOAD_CSUM_SCTP: CRC-32c, for use in SCTP header (RFC 3309) */ enum nft_payload_csum_types { NFT_PAYLOAD_CSUM_NONE, NFT_PAYLOAD_CSUM_INET, + NFT_PAYLOAD_CSUM_SCTP, }; enum nft_payload_csum_flags { -- cgit v1.2.3 From 3e2ac9798e13ad1f52d735ea2ea1d252cb140ae5 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 5 Oct 2020 10:58:18 +0200 Subject: PM / devfreq: remove a duplicated kernel-doc markup The update_devfreq() is also documented at devfreq.c, which has a more complete note. So, drop the duplicated markup, in order to avoid this warning: .../Documentation/driver-api/device_link.rst: WARNING: Duplicate C declaration, also defined in 'driver-api/infrastructure'. Declaration is 'device_link_state'. (and to cause a problem with cross-references to it) Signed-off-by: Mauro Carvalho Chehab --- include/linux/devfreq.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 2f4a74efa6be..121a2430d7f7 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -228,12 +228,7 @@ int devfreq_resume_device(struct devfreq *devfreq); void devfreq_suspend(void); void devfreq_resume(void); -/** - * update_devfreq() - Reevaluate the device and configure frequency - * @devfreq: the devfreq device - * - * Note: devfreq->lock must be held - */ +/* update_devfreq() - Reevaluate the device and configure frequency */ int update_devfreq(struct devfreq *devfreq); /* Helper functions for devfreq user device driver with OPP. */ -- cgit v1.2.3 From 8c39076c276be0b31982e44654e2c2357473258a Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 16 Oct 2020 09:25:45 -0400 Subject: NFSv4.2: support EXCHGID4_FLAG_SUPP_FENCE_OPS 4.2 EXCHANGE_ID flag RFC 7862 introduced a new flag that either client or server is allowed to set: EXCHGID4_FLAG_SUPP_FENCE_OPS. Client needs to update its bitmask to allow for this flag value. v2: changed minor version argument to unsigned int Signed-off-by: Olga Kornievskaia CC: Signed-off-by: Anna Schumaker --- include/uapi/linux/nfs4.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index bf197e99b98f..ed5415e0f1c1 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -139,6 +139,8 @@ #define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A 0x40000000 #define EXCHGID4_FLAG_CONFIRMED_R 0x80000000 + +#define EXCHGID4_FLAG_SUPP_FENCE_OPS 0x00000004 /* * Since the validity of these bits depends on whether * they're set in the argument or response, have separate @@ -146,6 +148,7 @@ */ #define EXCHGID4_FLAG_MASK_A 0x40070103 #define EXCHGID4_FLAG_MASK_R 0x80070103 +#define EXCHGID4_2_FLAG_MASK_R 0x80070107 #define SEQ4_STATUS_CB_PATH_DOWN 0x00000001 #define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING 0x00000002 -- cgit v1.2.3 From dca54a7bbb8ca9148ae10d60c66c926e222a9c4b Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 13 Oct 2020 20:51:59 +0100 Subject: afs: Add tracing for cell refcount and active user count Add a tracepoint to log the cell refcount and active user count and pass in a reason code through various functions that manipulate these counters. Additionally, a helper function, afs_see_cell(), is provided to log interesting places that deal with a cell without actually doing any accounting directly. Signed-off-by: David Howells --- include/trace/events/afs.h | 107 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 107 insertions(+) (limited to 'include') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 5f0c1cf1ea13..a79c5ca376b3 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -50,6 +50,7 @@ enum afs_server_trace { afs_server_trace_update, }; + enum afs_volume_trace { afs_volume_trace_alloc, afs_volume_trace_free, @@ -67,6 +68,46 @@ enum afs_volume_trace { afs_volume_trace_remove, }; +enum afs_cell_trace { + afs_cell_trace_alloc, + afs_cell_trace_free, + afs_cell_trace_get_queue_dns, + afs_cell_trace_get_queue_manage, + afs_cell_trace_get_queue_new, + afs_cell_trace_get_vol, + afs_cell_trace_insert, + afs_cell_trace_manage, + afs_cell_trace_put_candidate, + afs_cell_trace_put_destroy, + afs_cell_trace_put_queue_fail, + afs_cell_trace_put_queue_work, + afs_cell_trace_put_vol, + afs_cell_trace_see_source, + afs_cell_trace_see_ws, + afs_cell_trace_unuse_alias, + afs_cell_trace_unuse_check_alias, + afs_cell_trace_unuse_delete, + afs_cell_trace_unuse_fc, + afs_cell_trace_unuse_lookup, + afs_cell_trace_unuse_mntpt, + afs_cell_trace_unuse_no_pin, + afs_cell_trace_unuse_parse, + afs_cell_trace_unuse_pin, + afs_cell_trace_unuse_probe, + afs_cell_trace_unuse_sbi, + afs_cell_trace_unuse_ws, + afs_cell_trace_use_alias, + afs_cell_trace_use_check_alias, + afs_cell_trace_use_fc, + afs_cell_trace_use_fc_alias, + afs_cell_trace_use_lookup, + afs_cell_trace_use_mntpt, + afs_cell_trace_use_pin, + afs_cell_trace_use_probe, + afs_cell_trace_use_sbi, + afs_cell_trace_wait, +}; + enum afs_fs_operation { afs_FS_FetchData = 130, /* AFS Fetch file data */ afs_FS_FetchACL = 131, /* AFS Fetch file ACL */ @@ -295,6 +336,44 @@ enum afs_cb_break_reason { EM(afs_volume_trace_put_validate_fc, "PUT fc-validat") \ E_(afs_volume_trace_remove, "REMOVE ") +#define afs_cell_traces \ + EM(afs_cell_trace_alloc, "ALLOC ") \ + EM(afs_cell_trace_free, "FREE ") \ + EM(afs_cell_trace_get_queue_dns, "GET q-dns ") \ + EM(afs_cell_trace_get_queue_manage, "GET q-mng ") \ + EM(afs_cell_trace_get_queue_new, "GET q-new ") \ + EM(afs_cell_trace_get_vol, "GET vol ") \ + EM(afs_cell_trace_insert, "INSERT ") \ + EM(afs_cell_trace_manage, "MANAGE ") \ + EM(afs_cell_trace_put_candidate, "PUT candid") \ + EM(afs_cell_trace_put_destroy, "PUT destry") \ + EM(afs_cell_trace_put_queue_work, "PUT q-work") \ + EM(afs_cell_trace_put_queue_fail, "PUT q-fail") \ + EM(afs_cell_trace_put_vol, "PUT vol ") \ + EM(afs_cell_trace_see_source, "SEE source") \ + EM(afs_cell_trace_see_ws, "SEE ws ") \ + EM(afs_cell_trace_unuse_alias, "UNU alias ") \ + EM(afs_cell_trace_unuse_check_alias, "UNU chk-al") \ + EM(afs_cell_trace_unuse_delete, "UNU delete") \ + EM(afs_cell_trace_unuse_fc, "UNU fc ") \ + EM(afs_cell_trace_unuse_lookup, "UNU lookup") \ + EM(afs_cell_trace_unuse_mntpt, "UNU mntpt ") \ + EM(afs_cell_trace_unuse_parse, "UNU parse ") \ + EM(afs_cell_trace_unuse_pin, "UNU pin ") \ + EM(afs_cell_trace_unuse_probe, "UNU probe ") \ + EM(afs_cell_trace_unuse_sbi, "UNU sbi ") \ + EM(afs_cell_trace_unuse_ws, "UNU ws ") \ + EM(afs_cell_trace_use_alias, "USE alias ") \ + EM(afs_cell_trace_use_check_alias, "USE chk-al") \ + EM(afs_cell_trace_use_fc, "USE fc ") \ + EM(afs_cell_trace_use_fc_alias, "USE fc-al ") \ + EM(afs_cell_trace_use_lookup, "USE lookup") \ + EM(afs_cell_trace_use_mntpt, "USE mntpt ") \ + EM(afs_cell_trace_use_pin, "USE pin ") \ + EM(afs_cell_trace_use_probe, "USE probe ") \ + EM(afs_cell_trace_use_sbi, "USE sbi ") \ + E_(afs_cell_trace_wait, "WAIT ") + #define afs_fs_operations \ EM(afs_FS_FetchData, "FS.FetchData") \ EM(afs_FS_FetchStatus, "FS.FetchStatus") \ @@ -483,6 +562,7 @@ enum afs_cb_break_reason { afs_call_traces; afs_server_traces; +afs_cell_traces; afs_fs_operations; afs_vl_operations; afs_edit_dir_ops; @@ -1358,6 +1438,33 @@ TRACE_EVENT(afs_volume, __entry->ref) ); +TRACE_EVENT(afs_cell, + TP_PROTO(unsigned int cell_debug_id, int usage, int active, + enum afs_cell_trace reason), + + TP_ARGS(cell_debug_id, usage, active, reason), + + TP_STRUCT__entry( + __field(unsigned int, cell ) + __field(int, usage ) + __field(int, active ) + __field(int, reason ) + ), + + TP_fast_assign( + __entry->cell = cell_debug_id; + __entry->usage = usage; + __entry->active = active; + __entry->reason = reason; + ), + + TP_printk("L=%08x %s u=%d a=%d", + __entry->cell, + __print_symbolic(__entry->reason, afs_cell_traces), + __entry->usage, + __entry->active) + ); + #endif /* _TRACE_AFS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7530d3eb3dcf1a30750e8e7f1f88b782b96b72b8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 15 Oct 2020 09:02:25 +0100 Subject: afs: Don't assert on unpurgeable server records Don't give an assertion failure on unpurgeable afs_server records - which kills the thread - but rather emit a trace line when we are purging a record (which only happens during network namespace removal or rmmod) and print a notice of the problem. Signed-off-by: David Howells --- include/trace/events/afs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index a79c5ca376b3..8eb49231c6bb 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -40,6 +40,7 @@ enum afs_server_trace { afs_server_trace_get_new_cbi, afs_server_trace_get_probe, afs_server_trace_give_up_cb, + afs_server_trace_purging, afs_server_trace_put_call, afs_server_trace_put_cbi, afs_server_trace_put_find_rsq, @@ -311,6 +312,7 @@ enum afs_cb_break_reason { EM(afs_server_trace_get_new_cbi, "GET cbi ") \ EM(afs_server_trace_get_probe, "GET probe") \ EM(afs_server_trace_give_up_cb, "giveup-cb") \ + EM(afs_server_trace_purging, "PURGE ") \ EM(afs_server_trace_put_call, "PUT call ") \ EM(afs_server_trace_put_cbi, "PUT cbi ") \ EM(afs_server_trace_put_find_rsq, "PUT f-rsq") \ -- cgit v1.2.3 From bae314dd5d8dfdd90ee584003a0f8c06e1bf3ea2 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 15 Oct 2020 16:44:27 +0200 Subject: cpuidle: Remove pointless stub The cpuidle.h header is declaring a function with an empty stub for the cpuidle disabled case, but that function is only called by cpuidle governors which depend on cpuidle anyway. In other words, the function is only called when cpuidle is enabled, so there is no need for the stub. Remove the pointless stub. Signed-off-by: Daniel Lezcano [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index ed0da0e58e8b..bd605b5585cf 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -271,13 +271,8 @@ struct cpuidle_governor { void (*reflect) (struct cpuidle_device *dev, int index); }; -#ifdef CONFIG_CPU_IDLE extern int cpuidle_register_governor(struct cpuidle_governor *gov); extern s64 cpuidle_governor_latency_req(unsigned int cpu); -#else -static inline int cpuidle_register_governor(struct cpuidle_governor *gov) -{return 0;} -#endif #define __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, \ idx, \ -- cgit v1.2.3 From f1e8d7560d3051b38f73a0cf6acc1b0bf5305ad9 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 13 Oct 2020 15:42:41 +0800 Subject: powercap/intel_rapl: enumerate Psys RAPL domain together with package RAPL domain On multi-package systems, the Psys MSR is only valid for CPUs on specific package (master package). The current code makes the assumption that package 0 is the master package, but this is not true on new platforms like SPR. Fix the problem by emuerating the Psys RAPL domain for every package, so CPUs in slave packages will read 0 for the Psys energy counter and only CPUs in master packages can get a valid reading and register the Psys RAPL domain. The sysfs I/F for the Psys RAPL domain is not changed. Signed-off-by: Zhang Rui [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 3582176a1eca..50b8398ffd21 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -79,8 +79,10 @@ struct rapl_power_limit { struct rapl_package; +#define RAPL_DOMAIN_NAME_LENGTH 16 + struct rapl_domain { - const char *name; + char name[RAPL_DOMAIN_NAME_LENGTH]; enum rapl_domain_type id; u64 regs[RAPL_DOMAIN_REG_MAX]; struct powercap_zone power_zone; @@ -152,7 +154,4 @@ struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv); void rapl_remove_package(struct rapl_package *rp); -int rapl_add_platform_domain(struct rapl_if_priv *priv); -void rapl_remove_platform_domain(struct rapl_if_priv *priv); - #endif /* __INTEL_RAPL_H__ */ -- cgit v1.2.3 From d4f8138354b9ec290de0c7ba527a945c5549e32b Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 13 Oct 2020 14:23:39 +0200 Subject: PM: domains: Add support for PM domain on/off notifiers for genpd A device may have specific HW constraints that must be obeyed to, before its corresponding PM domain (genpd) can be powered off - and vice verse at power on. These constraints can't be managed through the regular runtime PM based deployment for a device, because the access pattern for it, isn't always request based. In other words, using the runtime PM callbacks to deal with the constraints doesn't work for these cases. For these reasons, let's instead add a PM domain power on/off notification mechanism to genpd. To add/remove a notifier for a device, the device must already have been attached to the genpd, which also means that it needs to be a part of the PM domain topology. To add/remove a notifier, let's introduce two genpd specific functions: - dev_pm_genpd_add|remove_notifier() Note that, to further clarify when genpd power on/off notifiers may be used, one can compare with the existing CPU_CLUSTER_PM_ENTER|EXIT notifiers. In the long run, the genpd power on/off notifiers should be able to replace them, but that requires additional genpd based platform support for the current users. Signed-off-by: Ulf Hansson Tested-by: Lina Iyer Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 66f3c5d64d81..db039da0aba2 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -68,6 +68,13 @@ enum gpd_status { GENPD_STATE_OFF, /* PM domain is off */ }; +enum genpd_notication { + GENPD_NOTIFY_PRE_OFF = 0, + GENPD_NOTIFY_OFF, + GENPD_NOTIFY_PRE_ON, + GENPD_NOTIFY_ON, +}; + struct dev_power_governor { bool (*power_down_ok)(struct dev_pm_domain *domain); bool (*suspend_ok)(struct device *dev); @@ -112,6 +119,7 @@ struct generic_pm_domain { cpumask_var_t cpus; /* A cpumask of the attached CPUs */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); + struct raw_notifier_head power_notifiers; /* Power on/off notifiers */ struct opp_table *opp_table; /* OPP table of the genpd */ unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd, struct dev_pm_opp *opp); @@ -178,6 +186,7 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; + struct notifier_block *power_nb; int cpu; unsigned int performance_state; void *data; @@ -204,6 +213,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); int pm_genpd_remove(struct generic_pm_domain *genpd); int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); +int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb); +int dev_pm_genpd_remove_notifier(struct device *dev); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -251,6 +262,17 @@ static inline int dev_pm_genpd_set_performance_state(struct device *dev, return -ENOTSUPP; } +static inline int dev_pm_genpd_add_notifier(struct device *dev, + struct notifier_block *nb) +{ + return -ENOTSUPP; +} + +static inline int dev_pm_genpd_remove_notifier(struct device *dev) +{ + return -ENOTSUPP; +} + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif -- cgit v1.2.3 From c6a113b52302adcfadda63af81dc05f7a669fbc8 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Thu, 15 Oct 2020 14:47:22 -0600 Subject: PM: domains: enable domain idle state accounting To enable better debug of PM domains, keep a track of successful and failing attempts to enter each domain idle state. This statistics are exported in debugfs when reading the idle_states node associated with each PM domain. Signed-off-by: Lina Iyer [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index db039da0aba2..1ad0ec481416 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -89,6 +89,8 @@ struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; s64 residency_ns; + u64 usage; + u64 rejected; struct fwnode_handle *fwnode; ktime_t idle_time; void *data; -- cgit v1.2.3 From c6e5f02b5281a3166a9b7b4d66830cc234421ba5 Mon Sep 17 00:00:00 2001 From: "Saheed O. Bolarinwa" Date: Thu, 15 Oct 2020 14:30:31 -0500 Subject: PCI/ASPM: Remove struct aspm_register_info.support Previously we stored the "ASPM Support" field from the Link Capabilities register in the struct aspm_register_info. Read the Link Capabilities directly when needed and remove it from the struct aspm_register_info. No functional change intended. [bhelgaas: remove pci_dev cached copy since LNKCAP isn't truly read-only, add PCI_EXP_LNKCAP_ASPM_L0S & PCI_EXP_LNKCAP_ASPM_L1, check them directly instead of adding aspm_support()] Link: https://lore.kernel.org/r/20201015193039.12585-5-helgaas@kernel.org Signed-off-by: Saheed O. Bolarinwa Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f9701410d3b5..06846ec2e071 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -532,6 +532,8 @@ #define PCI_EXP_LNKCAP_SLS_32_0GB 0x00000005 /* LNKCAP2 SLS Vector bit 4 */ #define PCI_EXP_LNKCAP_MLW 0x000003f0 /* Maximum Link Width */ #define PCI_EXP_LNKCAP_ASPMS 0x00000c00 /* ASPM Support */ +#define PCI_EXP_LNKCAP_ASPM_L0S 0x00000400 /* ASPM L0s Support */ +#define PCI_EXP_LNKCAP_ASPM_L1 0x00000800 /* ASPM L1 Support */ #define PCI_EXP_LNKCAP_L0SEL 0x00007000 /* L0s Exit Latency */ #define PCI_EXP_LNKCAP_L1EL 0x00038000 /* L1 Exit Latency */ #define PCI_EXP_LNKCAP_CLKPM 0x00040000 /* Clock Power Management */ -- cgit v1.2.3 From ecdf57b4f6748f3cb89eaf2ffdc9cfae4829f493 Mon Sep 17 00:00:00 2001 From: "Saheed O. Bolarinwa" Date: Thu, 15 Oct 2020 14:30:34 -0500 Subject: PCI/ASPM: Remove struct aspm_register_info.l1ss_cap_ptr Save the L1 Substates Capability pointer in struct pci_dev. Then we don't have to keep track of it in the struct aspm_register_info and struct pcie_link_state, which makes the code easier to read. No functional change intended. [bhelgaas: split to a separate patch] Link: https://lore.kernel.org/r/20201015193039.12585-8-helgaas@kernel.org Signed-off-by: Saheed O. Bolarinwa Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 835530605c0d..c5288cd71a2e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -380,6 +380,7 @@ struct pci_dev { struct pcie_link_state *link_state; /* ASPM link state */ unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ + int l1ss; /* L1SS Capability pointer */ #endif unsigned int eetlp_prefix_path:1; /* End-to-End TLP Prefix */ -- cgit v1.2.3 From df8f10587d3d11b055d54138994a1a9a681da0c4 Mon Sep 17 00:00:00 2001 From: "Saheed O. Bolarinwa" Date: Thu, 15 Oct 2020 14:30:39 -0500 Subject: PCI/ASPM: Remove struct pcie_link_state.l1ss Previously we computed L1.2 parameters in the enumeration path, saved them in struct pcie_link_state.l1ss, and programmed them into the devices whenever we enabled or disabled L1.2 on the link. But these parameters are constant and don't need to be updated when enabling/disabling L1.2. Compute and program the L1.2 parameters once during enumeration and remove the struct pcie_link_state.l1ss member. No functional change intended. [bhelgaas: rework to program L1.2 parameters during enumeration] Link: https://lore.kernel.org/r/20201015193039.12585-13-helgaas@kernel.org Signed-off-by: Saheed O. Bolarinwa Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 06846ec2e071..c7e0acba0e20 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1058,6 +1058,7 @@ #define PCI_L1SS_CTL1_PCIPM_L1_1 0x00000002 /* PCI-PM L1.1 Enable */ #define PCI_L1SS_CTL1_ASPM_L1_2 0x00000004 /* ASPM L1.2 Enable */ #define PCI_L1SS_CTL1_ASPM_L1_1 0x00000008 /* ASPM L1.1 Enable */ +#define PCI_L1SS_CTL1_L1_2_MASK 0x00000005 #define PCI_L1SS_CTL1_L1SS_MASK 0x0000000f #define PCI_L1SS_CTL1_CM_RESTORE_TIME 0x0000ff00 /* Common_Mode_Restore_Time */ #define PCI_L1SS_CTL1_LTR_L12_TH_VALUE 0x03ff0000 /* LTR_L1.2_THRESHOLD_Value */ -- cgit v1.2.3 From e0477b34d9d11c1a7b1f80bfdbcdc8952ce2adb7 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 8 Oct 2020 11:27:52 +0300 Subject: RDMA: Explicitly pass in the dma_device to ib_register_device The code in setup_dma_device has become rather convoluted, move all of this to the drivers. Drives now pass in a DMA capable struct device which will be used to setup DMA, or drivers must fully configure the ibdev for DMA and pass in NULL. Other than setting the masks in rvt all drivers were doing this already anyhow. mthca, mlx4 and mlx5 were already setting up maximum DMA segment size for DMA based on their hardweare limits in: __mthca_init_one() dma_set_max_seg_size (1G) __mlx4_init_one() dma_set_max_seg_size (1G) mlx5_pci_init() set_dma_caps() dma_set_max_seg_size (2G) Other non software drivers (except usnic) were extended to UINT_MAX [1, 2] instead of 2G as was before. [1] https://lore.kernel.org/linux-rdma/20200924114940.GE9475@nvidia.com/ [2] https://lore.kernel.org/linux-rdma/20200924114940.GE9475@nvidia.com/ Link: https://lore.kernel.org/r/20201008082752.275846-1-leon@kernel.org Link: https://lore.kernel.org/r/6b2ed339933d066622d5715903870676d8cc523a.1602590106.git.mchehab+huawei@kernel.org Suggested-by: Christoph Hellwig Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Reviewed-by: Christoph Hellwig Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index ce935d70fdc8..9bf6c319a670 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2782,7 +2782,8 @@ void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); -int ib_register_device(struct ib_device *device, const char *name); +int ib_register_device(struct ib_device *device, const char *name, + struct device *dma_device); void ib_unregister_device(struct ib_device *device); void ib_unregister_driver(enum rdma_driver_id driver_id); void ib_unregister_device_and_put(struct ib_device *device); -- cgit v1.2.3 From e0d696d201dd5d31813787d9b61a42fc459eee89 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 15 Oct 2020 20:42:18 -0300 Subject: RDMA/rxe: Move the definitions for rxe_av.network_type to uAPI RXE was wrongly using an internal kernel enum as part of its uAPI, split this out into a dedicated uAPI enum just for RXE. It only uses the IPv4 and IPv6 values. This was exposed by changing the internal kernel enum definition which broke RXE. Fixes: 1c15b4f2a42f ("RDMA/core: Modify enum ib_gid_type and enum rdma_network_type") Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/rdma_user_rxe.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index d8f2e0e46dab..e591d8c1f3cf 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -39,6 +39,11 @@ #include #include +enum { + RXE_NETWORK_TYPE_IPV4 = 1, + RXE_NETWORK_TYPE_IPV6 = 2, +}; + union rxe_gid { __u8 raw[16]; struct { @@ -57,6 +62,7 @@ struct rxe_global_route { struct rxe_av { __u8 port_num; + /* From RXE_NETWORK_TYPE_* */ __u8 network_type; __u8 dmac[6]; struct rxe_global_route grh; -- cgit v1.2.3 From 57417cebc96b57122a2207fc84a6077d20c84b4b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:05:13 -0700 Subject: XArray: add xa_get_order Patch series "Fix read-only THP for non-tmpfs filesystems". As described more verbosely in the [3/3] changelog, we can inadvertently put an order-0 page in the page cache which occupies 512 consecutive entries. Users are running into this if they enable the READ_ONLY_THP_FOR_FS config option; see https://bugzilla.kernel.org/show_bug.cgi?id=206569 and Qian Cai has also reported it here: https://lore.kernel.org/lkml/20200616013309.GB815@lca.pw/ This is a rather intrusive way of fixing the problem, but has the advantage that I've actually been testing it with the THP patches, which means that it sees far more use than it does upstream -- indeed, Song has been entirely unable to reproduce it. It also has the advantage that it removes a few patches from my gargantuan backlog of THP patches. This patch (of 3): This function returns the order of the entry at the index. We need this because there isn't space in the shadow entry to encode its order. [akpm@linux-foundation.org: export xa_get_order to modules] Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: "Kirill A . Shutemov" Cc: Qian Cai Cc: Song Liu Link: https://lkml.kernel.org/r/20200903183029.14930-1-willy@infradead.org Link: https://lkml.kernel.org/r/20200903183029.14930-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/xarray.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index b4d70e7568b2..5b7f4ebcf4ff 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1505,6 +1505,15 @@ void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); +#ifdef CONFIG_XARRAY_MULTI +int xa_get_order(struct xarray *, unsigned long index); +#else +static inline int xa_get_order(struct xarray *xa, unsigned long index) +{ + return 0; +} +#endif + /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. -- cgit v1.2.3 From 8fc75643c5e14574c8be59b69182452ece28315a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:05:16 -0700 Subject: XArray: add xas_split In order to use multi-index entries for huge pages in the page cache, we need to be able to split a multi-index entry (eg if a file is truncated in the middle of a huge page entry). This version does not support splitting more than one level of the tree at a time. This is an acceptable limitation for the page cache as we do not expect to support order-12 pages in the near future. [akpm@linux-foundation.org: export xas_split_alloc() to modules] [willy@infradead.org: fix xarray split] Link: https://lkml.kernel.org/r/20200910175450.GV6583@casper.infradead.org [willy@infradead.org: fix xarray] Link: https://lkml.kernel.org/r/20201001233943.GW20115@casper.infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: "Kirill A . Shutemov" Cc: Qian Cai Cc: Song Liu Link: https://lkml.kernel.org/r/20200903183029.14930-3-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/xarray.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5b7f4ebcf4ff..5cdf441f6377 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1507,11 +1507,24 @@ void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); +void xas_split(struct xa_state *, void *entry, unsigned int order); +void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } + +static inline void xas_split(struct xa_state *xas, void *entry, + unsigned int order) +{ + xas_store(xas, entry); +} + +static inline void xas_split_alloc(struct xa_state *xas, void *entry, + unsigned int order, gfp_t gfp) +{ +} #endif /** -- cgit v1.2.3 From 8fb156c9ee2db94f7127c930c89917634a1a9f56 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:05:29 -0700 Subject: mm/page_owner: change split_page_owner to take a count The implementation of split_page_owner() prefers a count rather than the old order of the page. When we support a variable size THP, we won't have the order at this point, but we will have the number of pages. So change the interface to what the caller and callee would prefer. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: SeongJae Park Acked-by: Kirill A. Shutemov Cc: Huang Ying Link: https://lkml.kernel.org/r/20200908195539.25896-4-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 8679ccd722e8..3468794f83d2 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -11,7 +11,7 @@ extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); -extern void __split_page_owner(struct page *page, unsigned int order); +extern void __split_page_owner(struct page *page, unsigned int nr); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(struct page *page); @@ -31,10 +31,10 @@ static inline void set_page_owner(struct page *page, __set_page_owner(page, order, gfp_mask); } -static inline void split_page_owner(struct page *page, unsigned int order) +static inline void split_page_owner(struct page *page, unsigned int nr) { if (static_branch_unlikely(&page_owner_inited)) - __split_page_owner(page, order); + __split_page_owner(page, nr); } static inline void copy_page_owner(struct page *oldpage, struct page *newpage) { -- cgit v1.2.3 From 01c70267053d6718820ac0902d8823d5dd2a6adb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:06:00 -0700 Subject: fs: add a filesystem flag for THPs The page cache needs to know whether the filesystem supports THPs so that it doesn't send THPs to filesystems which can't handle them. Dave Chinner points out that getting from the page mapping to the filesystem type is too many steps (mapping->host->i_sb->s_type->fs_flags) so cache that information in the address space flags. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Alexander Viro Cc: "Matthew Wilcox (Oracle)" Cc: Hugh Dickins Cc: Song Liu Cc: Rik van Riel Cc: "Kirill A . Shutemov" Cc: Johannes Weiner Cc: Dave Chinner Cc: Christoph Hellwig Link: https://lkml.kernel.org/r/20200916032717.22917-1-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + include/linux/pagemap.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index ae97d87a00d2..72369be23f91 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2209,6 +2209,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ +#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c3afd3242b54..820c970fd24a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -29,6 +29,7 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, + AS_THP_SUPPORT = 6, /* THPs supported */ }; /** @@ -120,6 +121,11 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +static inline bool mapping_thp_support(struct address_space *mapping) +{ + return test_bit(AS_THP_SUPPORT, &mapping->flags); +} + void release_pages(struct page **pages, int nr); /* -- cgit v1.2.3 From 6f4d2f9770cf154f9867f466d7b1b463a39f05a7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:06:03 -0700 Subject: fs: do not update nr_thps for mappings which support THPs The nr_thps counter is to support THPs in the page cache when the filesystem doesn't understand THPs. Eventually it will be removed, but we should still support filesystems which do not understand THPs yet. Move the nr_thp manipulation functions to filemap.h since they're page-cache specific. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Alexander Viro Cc: "Matthew Wilcox (Oracle)" Cc: Hugh Dickins Cc: Song Liu Cc: Rik van Riel Cc: "Kirill A . Shutemov" Cc: Johannes Weiner Cc: Dave Chinner Cc: Christoph Hellwig Link: https://lkml.kernel.org/r/20200916032717.22917-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 27 --------------------------- include/linux/pagemap.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 72369be23f91..d1d166b46131 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2697,33 +2697,6 @@ static inline errseq_t file_sample_sb_err(struct file *file) return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); } -static inline int filemap_nr_thps(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - return atomic_read(&mapping->nr_thps); -#else - return 0; -#endif -} - -static inline void filemap_nr_thps_inc(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - atomic_inc(&mapping->nr_thps); -#else - WARN_ON_ONCE(1); -#endif -} - -static inline void filemap_nr_thps_dec(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - atomic_dec(&mapping->nr_thps); -#else - WARN_ON_ONCE(1); -#endif -} - extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 820c970fd24a..a0024528a9ee 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -126,6 +126,35 @@ static inline bool mapping_thp_support(struct address_space *mapping) return test_bit(AS_THP_SUPPORT, &mapping->flags); } +static inline int filemap_nr_thps(struct address_space *mapping) +{ +#ifdef CONFIG_READ_ONLY_THP_FOR_FS + return atomic_read(&mapping->nr_thps); +#else + return 0; +#endif +} + +static inline void filemap_nr_thps_inc(struct address_space *mapping) +{ +#ifdef CONFIG_READ_ONLY_THP_FOR_FS + if (!mapping_thp_support(mapping)) + atomic_inc(&mapping->nr_thps); +#else + WARN_ON_ONCE(1); +#endif +} + +static inline void filemap_nr_thps_dec(struct address_space *mapping) +{ +#ifdef CONFIG_READ_ONLY_THP_FOR_FS + if (!mapping_thp_support(mapping)) + atomic_dec(&mapping->nr_thps); +#else + WARN_ON_ONCE(1); +#endif +} + void release_pages(struct page **pages, int nr); /* -- cgit v1.2.3 From 1aa83cfa5a20a6bbd39d2355a89c95152e4b37b4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:06:10 -0700 Subject: mm/readahead: add DEFINE_READAHEAD Patch series "Readahead patches for 5.9/5.10". These are infrastructure for both the THP patchset and for the fscache rewrite, For both pieces of infrastructure being build on top of this patchset, we want the ractl to be available higher in the call-stack. For David's work, he wants to add the 'critical page' to the ractl so that he knows which page NEEDS to be brought in from storage, and which ones are nice-to-have. We might want something similar in block storage too. It used to be simple -- the first page was the critical one, but then mmap added fault-around and so for that usecase, the middle page is the critical one. Anyway, I don't have any code to show that yet, we just know that the lowest point in the callchain where we have that information is do_sync_mmap_readahead() and so the ractl needs to start its life there. For THP, we havew the code that needs it. It's actually the apex patch to the series; the one which finally starts to allocate THPs and present them to consenting filesystems: http://git.infradead.org/users/willy/pagecache.git/commitdiff/798bcf30ab2eff278caad03a9edca74d2f8ae760 This patch (of 8): Allow for a more concise definition of a struct readahead_control. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Eric Biggers Cc: David Howells Link: https://lkml.kernel.org/r/20200903140844.14194-1-willy@infradead.org Link: https://lkml.kernel.org/r/20200903140844.14194-3-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a0024528a9ee..63c81b512e80 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -812,6 +812,13 @@ struct readahead_control { unsigned int _batch_count; }; +#define DEFINE_READAHEAD(rac, f, m, i) \ + struct readahead_control rac = { \ + .file = f, \ + .mapping = m, \ + ._index = i, \ + } + /** * readahead_page - Get the next page to read. * @rac: The current readahead request. -- cgit v1.2.3 From 73bb49da50cd460bb3ba31250ed2e7fbf2115edf Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:06:14 -0700 Subject: mm/readahead: make page_cache_ra_unbounded take a readahead_control Define it in the callers instead of in page_cache_ra_unbounded(). Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: David Howells Cc: Eric Biggers Link: https://lkml.kernel.org/r/20200903140844.14194-4-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 63c81b512e80..37f209ccef0f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -768,9 +768,8 @@ void page_cache_sync_readahead(struct address_space *, struct file_ra_state *, void page_cache_async_readahead(struct address_space *, struct file_ra_state *, struct file *, struct page *, pgoff_t index, unsigned long req_count); -void page_cache_readahead_unbounded(struct address_space *, struct file *, - pgoff_t index, unsigned long nr_to_read, - unsigned long lookahead_count); +void page_cache_ra_unbounded(struct readahead_control *, + unsigned long nr_to_read, unsigned long lookahead_count); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: -- cgit v1.2.3 From fefa7c478fdafe71c64b5ddf817ac0271aed1146 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 15 Oct 2020 20:06:28 -0700 Subject: mm/readahead: add page_cache_sync_ra and page_cache_async_ra Reimplement page_cache_sync_readahead() and page_cache_async_readahead() as wrappers around versions of the function which take a readahead_control in preparation for making do_sync_mmap_readahead() pass down an RAC struct. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: David Howells Cc: Eric Biggers Link: https://lkml.kernel.org/r/20200903140844.14194-8-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 64 +++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 54 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 37f209ccef0f..c77b7c31b2e4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -761,16 +761,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); -#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) - -void page_cache_sync_readahead(struct address_space *, struct file_ra_state *, - struct file *, pgoff_t index, unsigned long req_count); -void page_cache_async_readahead(struct address_space *, struct file_ra_state *, - struct file *, struct page *, pgoff_t index, - unsigned long req_count); -void page_cache_ra_unbounded(struct readahead_control *, - unsigned long nr_to_read, unsigned long lookahead_count); - /* * Like add_to_page_cache_locked, but used to add newly allocated pages: * the page is new, so we can just run __SetPageLocked() against it. @@ -818,6 +808,60 @@ struct readahead_control { ._index = i, \ } +#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) + +void page_cache_ra_unbounded(struct readahead_control *, + unsigned long nr_to_read, unsigned long lookahead_count); +void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *, + unsigned long req_count); +void page_cache_async_ra(struct readahead_control *, struct file_ra_state *, + struct page *, unsigned long req_count); + +/** + * page_cache_sync_readahead - generic file readahead + * @mapping: address_space which holds the pagecache and I/O vectors + * @ra: file_ra_state which holds the readahead state + * @file: Used by the filesystem for authentication. + * @index: Index of first page to be read. + * @req_count: Total number of pages being read by the caller. + * + * page_cache_sync_readahead() should be called when a cache miss happened: + * it will submit the read. The readahead logic may decide to piggyback more + * pages onto the read request if access patterns suggest it will improve + * performance. + */ +static inline +void page_cache_sync_readahead(struct address_space *mapping, + struct file_ra_state *ra, struct file *file, pgoff_t index, + unsigned long req_count) +{ + DEFINE_READAHEAD(ractl, file, mapping, index); + page_cache_sync_ra(&ractl, ra, req_count); +} + +/** + * page_cache_async_readahead - file readahead for marked pages + * @mapping: address_space which holds the pagecache and I/O vectors + * @ra: file_ra_state which holds the readahead state + * @file: Used by the filesystem for authentication. + * @page: The page at @index which triggered the readahead call. + * @index: Index of first page to be read. + * @req_count: Total number of pages being read by the caller. + * + * page_cache_async_readahead() should be called when a page is used which + * is marked as PageReadahead; this is a marker to suggest that the application + * has used up enough of the readahead window that we should start pulling in + * more pages. + */ +static inline +void page_cache_async_readahead(struct address_space *mapping, + struct file_ra_state *ra, struct file *file, + struct page *page, pgoff_t index, unsigned long req_count) +{ + DEFINE_READAHEAD(ractl, file, mapping, index); + page_cache_async_ra(&ractl, ra, page, req_count); +} + /** * readahead_page - Get the next page to read. * @rac: The current readahead request. -- cgit v1.2.3 From 7e27f22c9e40b66186e0675376f0495725ff1b0a Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 15 Oct 2020 20:06:50 -0700 Subject: mm,hwpoison: unexport get_hwpoison_page and make it static Since get_hwpoison_page is only used in memory-failure code now, let us un-export it and make it private to that code. Signed-off-by: Oscar Salvador Signed-off-by: Andrew Morton Acked-by: Naoya Horiguchi Cc: "Aneesh Kumar K.V" Cc: Aneesh Kumar K.V Cc: Aristeu Rozanski Cc: Dave Hansen Cc: David Hildenbrand Cc: Dmitry Yakunin Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qian Cai Cc: Tony Luck Link: https://lkml.kernel.org/r/20200922135650.1634-5-osalvador@suse.de Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 620961e4f32b..1977c09afe7a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern int get_hwpoison_page(struct page *page); #define put_hwpoison_page(page) put_page(page) extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; -- cgit v1.2.3 From dd6e2402fad966290f35dc687294fb6049714aac Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 15 Oct 2020 20:06:57 -0700 Subject: mm,hwpoison: kill put_hwpoison_page After commit 4e41a30c6d50 ("mm: hwpoison: adjust for new thp refcounting"), put_hwpoison_page got reduced to a put_page. Let us just use put_page instead. Signed-off-by: Oscar Salvador Signed-off-by: Andrew Morton Acked-by: Naoya Horiguchi Cc: "Aneesh Kumar K.V" Cc: Aneesh Kumar K.V Cc: Aristeu Rozanski Cc: Dave Hansen Cc: David Hildenbrand Cc: Dmitry Yakunin Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qian Cai Cc: Tony Luck Link: https://lkml.kernel.org/r/20200922135650.1634-7-osalvador@suse.de Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1977c09afe7a..ab038a3521b4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -#define put_hwpoison_page(page) put_page(page) extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); -- cgit v1.2.3 From 06be6ff3d2ec8be806b859fc054a1909b16d2473 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 15 Oct 2020 20:07:05 -0700 Subject: mm,hwpoison: rework soft offline for free pages When trying to soft-offline a free page, we need to first take it off the buddy allocator. Once we know is out of reach, we can safely flag it as poisoned. take_page_off_buddy will be used to take a page meant to be poisoned off the buddy allocator. take_page_off_buddy calls break_down_buddy_pages, which splits a higher-order page in case our page belongs to one. Once the page is under our control, we call page_handle_poison to set it as poisoned and grab a refcount on it. Signed-off-by: Oscar Salvador Signed-off-by: Andrew Morton Acked-by: Naoya Horiguchi Cc: "Aneesh Kumar K.V" Cc: Aneesh Kumar K.V Cc: Aristeu Rozanski Cc: Dave Hansen Cc: David Hildenbrand Cc: Dmitry Yakunin Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qian Cai Cc: Tony Luck Link: https://lkml.kernel.org/r/20200922135650.1634-9-osalvador@suse.de Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 38ded408bd4c..a02b6d0221db 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -432,6 +432,7 @@ PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) extern bool set_hwpoison_free_buddy_page(struct page *page); +extern bool take_page_off_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison) static inline bool set_hwpoison_free_buddy_page(struct page *page) -- cgit v1.2.3 From 79f5f8fab482dfff62948214468ac4ebbf0a016f Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 15 Oct 2020 20:07:09 -0700 Subject: mm,hwpoison: rework soft offline for in-use pages This patch changes the way we set and handle in-use poisoned pages. Until now, poisoned pages were released to the buddy allocator, trusting that the checks that take place at allocation time would act as a safe net and would skip that page. This has proved to be wrong, as we got some pfn walkers out there, like compaction, that all they care is the page to be in a buddy freelist. Although this might not be the only user, having poisoned pages in the buddy allocator seems a bad idea as we should only have free pages that are ready and meant to be used as such. Before explaining the taken approach, let us break down the kind of pages we can soft offline. - Anonymous THP (after the split, they end up being 4K pages) - Hugetlb - Order-0 pages (that can be either migrated or invalited) * Normal pages (order-0 and anon-THP) - If they are clean and unmapped page cache pages, we invalidate then by means of invalidate_inode_page(). - If they are mapped/dirty, we do the isolate-and-migrate dance. Either way, do not call put_page directly from those paths. Instead, we keep the page and send it to page_handle_poison to perform the right handling. page_handle_poison sets the HWPoison flag and does the last put_page. Down the chain, we placed a check for HWPoison page in free_pages_prepare, that just skips any poisoned page, so those pages do not end up in any pcplist/freelist. After that, we set the refcount on the page to 1 and we increment the poisoned pages counter. If we see that the check in free_pages_prepare creates trouble, we can always do what we do for free pages: - wait until the page hits buddy's freelists - take it off, and flag it The downside of the above approach is that we could race with an allocation, so by the time we want to take the page off the buddy, the page has been already allocated so we cannot soft offline it. But the user could always retry it. * Hugetlb pages - We isolate-and-migrate them After the migration has been successful, we call dissolve_free_huge_page, and we set HWPoison on the page if we succeed. Hugetlb has a slightly different handling though. While for non-hugetlb pages we cared about closing the race with an allocation, doing so for hugetlb pages requires quite some additional and intrusive code (we would need to hook in free_huge_page and some other places). So I decided to not make the code overly complicated and just fail normally if the page we allocated in the meantime. We can always build on top of this. As a bonus, because of the way we handle now in-use pages, we no longer need the put-as-isolation-migratetype dance, that was guarding for poisoned pages to end up in pcplists. Signed-off-by: Oscar Salvador Signed-off-by: Andrew Morton Acked-by: Naoya Horiguchi Cc: "Aneesh Kumar K.V" Cc: Aneesh Kumar K.V Cc: Aristeu Rozanski Cc: Dave Hansen Cc: David Hildenbrand Cc: Dmitry Yakunin Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qian Cai Cc: Tony Luck Link: https://lkml.kernel.org/r/20200922135650.1634-10-osalvador@suse.de Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a02b6d0221db..4f6ba9379112 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -431,14 +431,9 @@ PAGEFLAG_FALSE(Uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) -extern bool set_hwpoison_free_buddy_page(struct page *page); extern bool take_page_off_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison) -static inline bool set_hwpoison_free_buddy_page(struct page *page) -{ - return 0; -} #define __PG_HWPOISON 0 #endif -- cgit v1.2.3 From 5d1fd5dc877bc1c670e7b1c174aa659b76c07de1 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 15 Oct 2020 20:07:21 -0700 Subject: mm,hwpoison: introduce MF_MSG_UNSPLIT_THP memory_failure() is supposed to call action_result() when it handles a memory error event, but there's one missing case. So let's add it. I find that include/ras/ras_event.h has some other MF_MSG_* undefined, so this patch also adds them. Signed-off-by: Naoya Horiguchi Signed-off-by: Oscar Salvador Signed-off-by: Andrew Morton Cc: "Aneesh Kumar K.V" Cc: Aneesh Kumar K.V Cc: Aristeu Rozanski Cc: Dave Hansen Cc: David Hildenbrand Cc: Dmitry Yakunin Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qian Cai Cc: Tony Luck Link: https://lkml.kernel.org/r/20200922135650.1634-13-osalvador@suse.de Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/ras/ras_event.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ab038a3521b4..a9df46309e07 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3064,6 +3064,7 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_BUDDY_2ND, MF_MSG_DAX, + MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, }; diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 36c5c5e38c1d..0bdbc0d17d2f 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -361,6 +361,7 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" ) \ EM ( MF_MSG_HUGE, "huge page" ) \ EM ( MF_MSG_FREE_HUGE, "free huge page" ) \ + EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" ) \ EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \ EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \ EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \ @@ -373,6 +374,8 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \ EM ( MF_MSG_BUDDY, "free buddy page" ) \ EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" ) \ + EM ( MF_MSG_DAX, "dax page" ) \ + EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) /* -- cgit v1.2.3 From 257bea71582d895894201b604990a900df489103 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:07:59 -0700 Subject: mm/page_alloc: simplify __offline_isolated_pages() offline_pages() is the only user. __offline_isolated_pages() never gets called with ranges that contain memory holes and we no longer care about the return value. Drop the return value handling and all pfn_valid() checks. Update the documentation. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Wei Yang Cc: Baoquan He Cc: Pankaj Gupta Cc: Charan Teja Reddy Cc: Dan Williams Cc: Fenghua Yu Cc: Logan Gunthorpe Cc: "Matthew Wilcox (Oracle)" Cc: Mel Gorman Cc: Mel Gorman Cc: Michel Lespinasse Cc: Mike Rapoport Cc: Tony Luck Link: https://lkml.kernel.org/r/20200819175957.28465-5-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index c0faa7a30c46..76b314031f09 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -103,8 +103,8 @@ extern int online_pages(unsigned long pfn, unsigned long nr_pages, int online_type, int nid); extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn); -extern unsigned long __offline_isolated_pages(unsigned long start_pfn, - unsigned long end_pfn); +extern void __offline_isolated_pages(unsigned long start_pfn, + unsigned long end_pfn); typedef void (*online_page_callback_t)(struct page *page, unsigned int order); -- cgit v1.2.3 From d882c0067d99d0f2add9a41628703cc99511a639 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:08:19 -0700 Subject: mm: pass migratetype into memmap_init_zone() and move_pfn_range_to_zone() On the memory onlining path, we want to start with MIGRATE_ISOLATE, to un-isolate the pages after memory onlining is complete. Let's allow passing in the migratetype. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Wei Yang Cc: Baoquan He Cc: Pankaj Gupta Cc: Tony Luck Cc: Fenghua Yu Cc: Logan Gunthorpe Cc: Dan Williams Cc: Mike Rapoport Cc: "Matthew Wilcox (Oracle)" Cc: Michel Lespinasse Cc: Charan Teja Reddy Cc: Mel Gorman Link: https://lkml.kernel.org/r/20200819175957.28465-10-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 ++- include/linux/mm.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 76b314031f09..51a877fec8da 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -351,7 +351,8 @@ extern int add_memory_resource(int nid, struct resource *resource); extern int add_memory_driver_managed(int nid, u64 start, u64 size, const char *resource_name); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); + unsigned long nr_pages, + struct vmem_altmap *altmap, int migratetype); extern void remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); diff --git a/include/linux/mm.h b/include/linux/mm.h index a9df46309e07..61a2633fcc7f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2440,7 +2440,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, - enum meminit_context, struct vmem_altmap *); + enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); -- cgit v1.2.3 From ec62d04e3fdc4ba3a7912cd7f6da1a4e787a0d75 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:08:28 -0700 Subject: kernel/resource: make release_mem_region_adjustable() never fail Patch series "selective merging of system ram resources", v4. Some add_memory*() users add memory in small, contiguous memory blocks. Examples include virtio-mem, hyper-v balloon, and the XEN balloon. This can quickly result in a lot of memory resources, whereby the actual resource boundaries are not of interest (e.g., it might be relevant for DIMMs, exposed via /proc/iomem to user space). We really want to merge added resources in this scenario where possible. Resources are effectively stored in a list-based tree. Having a lot of resources not only wastes memory, it also makes traversing that tree more expensive, and makes /proc/iomem explode in size (e.g., requiring kexec-tools to manually merge resources when creating a kdump header. The current kexec-tools resource count limit does not allow for more than ~100GB of memory with a memory block size of 128MB on x86-64). Let's allow to selectively merge system ram resources by specifying a new flag for add_memory*(). Patch #5 contains a /proc/iomem example. Only tested with virtio-mem. This patch (of 8): Let's make sure splitting a resource on memory hotunplug will never fail. This will become more relevant once we merge selected System RAM resources - then, we'll trigger that case more often on memory hotunplug. In general, this function is already unlikely to fail. When we remove memory, we free up quite a lot of metadata (memmap, page tables, memory block device, etc.). The only reason it could really fail would be when injecting allocation errors. All other error cases inside release_mem_region_adjustable() seem to be sanity checks if the function would be abused in different context - let's add WARN_ON_ONCE() in these cases so we can catch them. [natechancellor@gmail.com: fix use of ternary condition in release_mem_region_adjustable] Link: https://lkml.kernel.org/r/20200922060748.2452056-1-natechancellor@gmail.com Link: https://github.com/ClangBuiltLinux/linux/issues/1159 Signed-off-by: David Hildenbrand Signed-off-by: Nathan Chancellor Signed-off-by: Andrew Morton Cc: Michal Hocko Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kees Cook Cc: Ard Biesheuvel Cc: Pankaj Gupta Cc: Baoquan He Cc: Wei Yang Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Boris Ostrovsky Cc: Christian Borntraeger Cc: Dave Jiang Cc: Eric Biederman Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jason Wang Cc: Juergen Gross Cc: Julien Grall Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Leonardo Bras Cc: Libor Pechacek Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Nathan Lynch Cc: "Oliver O'Halloran" Cc: Paul Mackerras Cc: Pingfan Liu Cc: "Rafael J. Wysocki" Cc: Roger Pau Monn Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vishal Verma Cc: Wei Liu Link: https://lkml.kernel.org/r/20200911103459.10306-2-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 6c2b06fe8beb..52a91f5fa1a3 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -248,8 +248,8 @@ extern struct resource * __request_region(struct resource *, extern void __release_region(struct resource *, resource_size_t, resource_size_t); #ifdef CONFIG_MEMORY_HOTREMOVE -extern int release_mem_region_adjustable(struct resource *, resource_size_t, - resource_size_t); +extern void release_mem_region_adjustable(struct resource *, resource_size_t, + resource_size_t); #endif /* Wrappers for managed devices */ -- cgit v1.2.3 From 7cf603d17d9bddbda90c424b6f30c7bc2e6f48f2 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:08:33 -0700 Subject: kernel/resource: move and rename IORESOURCE_MEM_DRIVER_MANAGED MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit IORESOURCE_MEM_DRIVER_MANAGED currently uses an unused PnP bit, which is always set to 0 by hardware. This is far from beautiful (and confusing), and the bit only applies to SYSRAM. So let's move it out of the bus-specific (PnP) defined bits. We'll add another SYSRAM specific bit soon. If we ever need more bits for other purposes, we can steal some from "desc", or reshuffle/regroup what we have. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Cc: Michal Hocko Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kees Cook Cc: Ard Biesheuvel Cc: Pankaj Gupta Cc: Baoquan He Cc: Wei Yang Cc: Eric Biederman Cc: Thomas Gleixner Cc: Greg Kroah-Hartman Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Boris Ostrovsky Cc: Christian Borntraeger Cc: Dave Jiang Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jason Wang Cc: Juergen Gross Cc: Julien Grall Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Leonardo Bras Cc: Libor Pechacek Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Nathan Lynch Cc: "Oliver O'Halloran" Cc: Paul Mackerras Cc: Pingfan Liu Cc: "Rafael J. Wysocki" Cc: Roger Pau Monné Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Vasily Gorbik Cc: Vishal Verma Cc: Wei Liu Link: https://lkml.kernel.org/r/20200911103459.10306-3-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 52a91f5fa1a3..d7620d7c941a 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -58,6 +58,9 @@ struct resource { #define IORESOURCE_EXT_TYPE_BITS 0x01000000 /* Resource extended types */ #define IORESOURCE_SYSRAM 0x01000000 /* System RAM (modifier) */ +/* IORESOURCE_SYSRAM specific bits. */ +#define IORESOURCE_SYSRAM_DRIVER_MANAGED 0x02000000 /* Always detected via a driver. */ + #define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */ #define IORESOURCE_DISABLED 0x10000000 @@ -103,7 +106,6 @@ struct resource { #define IORESOURCE_MEM_32BIT (3<<3) #define IORESOURCE_MEM_SHADOWABLE (1<<5) /* dup: IORESOURCE_SHADOWABLE */ #define IORESOURCE_MEM_EXPANSIONROM (1<<6) -#define IORESOURCE_MEM_DRIVER_MANAGED (1<<7) /* PnP I/O specific bits (IORESOURCE_BITS) */ #define IORESOURCE_IO_16BIT_ADDR (1<<0) -- cgit v1.2.3 From 3a0aaefe4134951b4e89feb873c457428154530c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:08:39 -0700 Subject: mm/memory_hotplug: guard more declarations by CONFIG_MEMORY_HOTPLUG MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We soon want to pass flags via a new type to add_memory() and friends. That revealed that we currently don't guard some declarations by CONFIG_MEMORY_HOTPLUG. While some definitions could be moved to different places, let's keep it minimal for now and use CONFIG_MEMORY_HOTPLUG for all functions only compiled with CONFIG_MEMORY_HOTPLUG. Wrap sparse_decode_mem_map() into CONFIG_MEMORY_HOTPLUG, it's only called from CONFIG_MEMORY_HOTPLUG code. While at it, remove allow_online_pfn_range(), which is no longer around, and mhp_notimplemented(), which is unused. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Cc: Michal Hocko Cc: Dan Williams Cc: Pankaj Gupta Cc: Baoquan He Cc: Wei Yang Cc: Anton Blanchard Cc: Ard Biesheuvel Cc: Benjamin Herrenschmidt Cc: Boris Ostrovsky Cc: Christian Borntraeger Cc: Dave Jiang Cc: Eric Biederman Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jason Gunthorpe Cc: Jason Wang Cc: Juergen Gross Cc: Julien Grall Cc: Kees Cook Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Leonardo Bras Cc: Libor Pechacek Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Nathan Lynch Cc: "Oliver O'Halloran" Cc: Paul Mackerras Cc: Pingfan Liu Cc: "Rafael J. Wysocki" Cc: Roger Pau Monné Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vishal Verma Cc: Wei Liu Link: https://lkml.kernel.org/r/20200911103459.10306-4-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 51a877fec8da..1504b4d5ae6c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -247,13 +247,6 @@ static inline void zone_span_writelock(struct zone *zone) {} static inline void zone_span_writeunlock(struct zone *zone) {} static inline void zone_seqlock_init(struct zone *zone) {} -static inline int mhp_notimplemented(const char *func) -{ - printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func); - dump_stack(); - return -ENOSYS; -} - static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } @@ -344,6 +337,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {} extern void set_zone_contiguous(struct zone *zone); extern void clear_zone_contiguous(struct zone *zone); +#ifdef CONFIG_MEMORY_HOTPLUG extern void __ref free_area_init_core_hotplug(int nid); extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); @@ -364,8 +358,8 @@ extern void sparse_remove_section(struct mem_section *ms, unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, - int online_type); extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, unsigned long nr_pages); +#endif /* CONFIG_MEMORY_HOTPLUG */ + #endif /* __LINUX_MEMORY_HOTPLUG_H */ -- cgit v1.2.3 From b6117199787c60539105d2de0d010146e8396fc3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:08:44 -0700 Subject: mm/memory_hotplug: prepare passing flags to add_memory() and friends MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We soon want to pass flags, e.g., to mark added System RAM resources. mergeable. Prepare for that. This patch is based on a similar patch by Oscar Salvador: https://lkml.kernel.org/r/20190625075227.15193-3-osalvador@suse.de Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Juergen Gross # Xen related part Reviewed-by: Pankaj Gupta Acked-by: Wei Liu Cc: Michal Hocko Cc: Dan Williams Cc: Jason Gunthorpe Cc: Baoquan He Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: Vishal Verma Cc: Dave Jiang Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Wei Liu Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: David Hildenbrand Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Boris Ostrovsky Cc: Stefano Stabellini Cc: "Oliver O'Halloran" Cc: Pingfan Liu Cc: Nathan Lynch Cc: Libor Pechacek Cc: Anton Blanchard Cc: Leonardo Bras Cc: Ard Biesheuvel Cc: Eric Biederman Cc: Julien Grall Cc: Kees Cook Cc: Roger Pau Monné Cc: Thomas Gleixner Cc: Wei Yang Link: https://lkml.kernel.org/r/20200911103459.10306-5-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 1504b4d5ae6c..33eb80fdba22 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -57,6 +57,12 @@ enum { MMOP_ONLINE_MOVABLE, }; +/* Flags for add_memory() and friends to specify memory hotplug details. */ +typedef int __bitwise mhp_t; + +/* No special request */ +#define MHP_NONE ((__force mhp_t)0) + /* * Extended parameters for memory hotplug: * altmap: alternative allocator for memmap array (optional) @@ -339,11 +345,13 @@ extern void clear_zone_contiguous(struct zone *zone); #ifdef CONFIG_MEMORY_HOTPLUG extern void __ref free_area_init_core_hotplug(int nid); -extern int __add_memory(int nid, u64 start, u64 size); -extern int add_memory(int nid, u64 start, u64 size); -extern int add_memory_resource(int nid, struct resource *resource); +extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); +extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); +extern int add_memory_resource(int nid, struct resource *resource, + mhp_t mhp_flags); extern int add_memory_driver_managed(int nid, u64 start, u64 size, - const char *resource_name); + const char *resource_name, + mhp_t mhp_flags); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap, int migratetype); -- cgit v1.2.3 From 9ca6551ee24368a4d2b09566ea4d10fe87860379 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:08:49 -0700 Subject: mm/memory_hotplug: MEMHP_MERGE_RESOURCE to specify merging of System RAM resources MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some add_memory*() users add memory in small, contiguous memory blocks. Examples include virtio-mem, hyper-v balloon, and the XEN balloon. This can quickly result in a lot of memory resources, whereby the actual resource boundaries are not of interest (e.g., it might be relevant for DIMMs, exposed via /proc/iomem to user space). We really want to merge added resources in this scenario where possible. Let's provide a flag (MEMHP_MERGE_RESOURCE) to specify that a resource either created within add_memory*() or passed via add_memory_resource() shall be marked mergeable and merged with applicable siblings. To implement that, we need a kernel/resource interface to mark selected System RAM resources mergeable (IORESOURCE_SYSRAM_MERGEABLE) and trigger merging. Note: We really want to merge after the whole operation succeeded, not directly when adding a resource to the resource tree (it would break add_memory_resource() and require splitting resources again when the operation failed - e.g., due to -ENOMEM). Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Pankaj Gupta Cc: Michal Hocko Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kees Cook Cc: Ard Biesheuvel Cc: Thomas Gleixner Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Wei Liu Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Stefano Stabellini Cc: Roger Pau Monné Cc: Julien Grall Cc: Baoquan He Cc: Wei Yang Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Christian Borntraeger Cc: Dave Jiang Cc: Eric Biederman Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: Jason Wang Cc: Len Brown Cc: Leonardo Bras Cc: Libor Pechacek Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Nathan Lynch Cc: "Oliver O'Halloran" Cc: Paul Mackerras Cc: Pingfan Liu Cc: "Rafael J. Wysocki" Cc: Vasily Gorbik Cc: Vishal Verma Link: https://lkml.kernel.org/r/20200911103459.10306-6-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 4 ++++ include/linux/memory_hotplug.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index d7620d7c941a..7e61389dcb01 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -60,6 +60,7 @@ struct resource { /* IORESOURCE_SYSRAM specific bits. */ #define IORESOURCE_SYSRAM_DRIVER_MANAGED 0x02000000 /* Always detected via a driver. */ +#define IORESOURCE_SYSRAM_MERGEABLE 0x04000000 /* Resource can be merged. */ #define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */ @@ -253,6 +254,9 @@ extern void __release_region(struct resource *, resource_size_t, extern void release_mem_region_adjustable(struct resource *, resource_size_t, resource_size_t); #endif +#ifdef CONFIG_MEMORY_HOTPLUG +extern void merge_system_ram_resource(struct resource *res); +#endif /* Wrappers for managed devices */ struct device; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 33eb80fdba22..d65c6fdc5cfc 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -62,6 +62,13 @@ typedef int __bitwise mhp_t; /* No special request */ #define MHP_NONE ((__force mhp_t)0) +/* + * Allow merging of the added System RAM resource with adjacent, + * mergeable resources. After a successful call to add_memory_resource() + * with this flag set, the resource pointer must no longer be used as it + * might be stale, or the resource might have changed. + */ +#define MEMHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) /* * Extended parameters for memory hotplug: -- cgit v1.2.3 From cb8e3c8b4f45e4ed8987a581956dc9c3827a5bcf Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:09:12 -0700 Subject: kernel/resource: make iomem_resource implicit in release_mem_region_adjustable() "mem" in the name already indicates the root, similar to release_mem_region() and devm_request_mem_region(). Make it implicit. The only single caller always passes iomem_resource, other parents are not applicable. Suggested-by: Wei Yang Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Wei Yang Cc: Michal Hocko Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kees Cook Cc: Ard Biesheuvel Cc: Pankaj Gupta Cc: Baoquan He Link: https://lkml.kernel.org/r/20200916073041.10355-1-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 7e61389dcb01..5135d4b86cd6 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -251,8 +251,7 @@ extern struct resource * __request_region(struct resource *, extern void __release_region(struct resource *, resource_size_t, resource_size_t); #ifdef CONFIG_MEMORY_HOTREMOVE -extern void release_mem_region_adjustable(struct resource *, resource_size_t, - resource_size_t); +extern void release_mem_region_adjustable(resource_size_t, resource_size_t); #endif #ifdef CONFIG_MEMORY_HOTPLUG extern void merge_system_ram_resource(struct resource *res); -- cgit v1.2.3 From 90c7eaeb14a325a760d732184ff1fbed47e5fa98 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Thu, 15 Oct 2020 20:09:15 -0700 Subject: mm: don't panic when links can't be created in sysfs At boot time, or when doing memory hot-add operations, if the links in sysfs can't be created, the system is still able to run, so just report the error in the kernel log rather than BUG_ON and potentially make system unusable because the callpath can be called with locks held. Since the number of memory blocks managed could be high, the messages are rate limited. As a consequence, link_mem_sections() has no status to report anymore. Signed-off-by: Laurent Dufour Signed-off-by: Andrew Morton Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Acked-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Fenghua Yu Cc: Nathan Lynch Cc: "Rafael J . Wysocki" Cc: Scott Cheloha Cc: Tony Luck Link: https://lkml.kernel.org/r/20200915094143.79181-4-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds --- include/linux/node.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/node.h b/include/linux/node.h index 014ba3ab2efd..8e5a29897936 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,15 +99,14 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context); +void link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else -static inline int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context) +static inline void link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context) { - return 0; } #endif @@ -130,8 +129,7 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, start_pfn, end_pfn, - MEMINIT_EARLY); + link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY); } return error; -- cgit v1.2.3 From ed0173733dd468883198c3136284394320b8fad6 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 15 Oct 2020 20:09:55 -0700 Subject: mm: use self-explanatory macros rather than "2" Signed-off-by: Yu Zhao Signed-off-by: Andrew Morton Cc: Alex Shi Link: http://lkml.kernel.org/r/20200831175042.3527153-2-yuzhao@google.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 12 ++++++++---- include/linux/vmstat.h | 2 +- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c27fb1faffe5..7e0ea3fe95ca 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -266,6 +266,8 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } +#define ANON_AND_FILE 2 + enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI @@ -283,8 +285,8 @@ struct lruvec { unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; - /* Refaults at the time of last reclaim cycle, anon=0, file=1 */ - unsigned long refaults[2]; + /* Refaults at the time of last reclaim cycle */ + unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_MEMCG @@ -441,6 +443,8 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H +#define ASYNC_AND_SYNC 2 + struct zone { /* Read-mostly fields */ @@ -560,8 +564,8 @@ struct zone { #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; - /* pfn where async and sync compaction migration scanner should start */ - unsigned long compact_cached_migrate_pfn[2]; + /* pfn where compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 7557c1070fd7..322dcbfcc933 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -28,7 +28,7 @@ struct reclaim_stat { unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; - unsigned nr_activate[2]; + unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; -- cgit v1.2.3 From 1f0f8c0de09066d23760c1f5fac2cd53b32f1127 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 15 Oct 2020 20:10:11 -0700 Subject: include/linux/mmzone.h: remove unused early_pfn_valid() The early_pfn_valid() macro is defined but it is never used. Remove it. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Acked-by: David Hildenbrand Link: https://lkml.kernel.org/r/20200923162915.26935-1-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7e0ea3fe95ca..fb3bf696c05e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1420,7 +1420,6 @@ static inline unsigned long next_present_section_nr(unsigned long section_nr) #define pfn_to_nid(pfn) (0) #endif -#define early_pfn_valid(pfn) pfn_valid(pfn) void sparse_init(void); #else #define sparse_init() do {} while (0) @@ -1440,10 +1439,6 @@ struct mminit_pfnnid_cache { int last_nid; }; -#ifndef early_pfn_valid -#define early_pfn_valid(pfn) (1) -#endif - /* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we * need to check pfn validity within that MAX_ORDER_NR_PAGES block. -- cgit v1.2.3 From b296a6d53339a79082c1d2c1761e948e8b3def69 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 15 Oct 2020 20:10:21 -0700 Subject: kernel.h: split out min()/max() et al. helpers kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt to start cleaning it up by splitting out min()/max() et al. helpers. At the same time convert users in header and lib folder to use new header. Though for time being include new header back to kernel.h to avoid twisted indirected includes for other existing users. Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Rasmus Villemoes Cc: Joe Perches Cc: Linus Torvalds Link: https://lkml.kernel.org/r/20200910164152.GA1891694@smile.fi.intel.com Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 1 + include/linux/bvec.h | 6 +- include/linux/jiffies.h | 3 +- include/linux/kernel.h | 150 +--------------------------------------------- include/linux/minmax.h | 153 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nodemask.h | 2 +- include/linux/uaccess.h | 1 + 7 files changed, 164 insertions(+), 152 deletions(-) create mode 100644 include/linux/minmax.h (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c09375e0a0eb..639cae2c158b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/bvec.h b/include/linux/bvec.h index dd74503f7e5e..2efec10bf792 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -7,10 +7,14 @@ #ifndef __LINUX_BVEC_ITER_H #define __LINUX_BVEC_ITER_H -#include #include #include +#include +#include #include +#include + +struct page; /** * struct bio_vec - a contiguous range of physical memory addresses diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index fed6ba96c527..5e13f801c902 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -3,8 +3,9 @@ #define _LINUX_JIFFIES_H #include +#include #include -#include +#include #include #include #include diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e4aa29b1ad62..c629215fdad9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -833,155 +834,6 @@ ftrace_vprintk(const char *fmt, va_list ap) static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* CONFIG_TRACING */ -/* - * min()/max()/clamp() macros must accomplish three things: - * - * - avoid multiple evaluations of the arguments (so side-effects like - * "x++" happen only once) when non-constant. - * - perform strict type-checking (to generate warnings instead of - * nasty runtime surprises). See the "unnecessary" pointer comparison - * in __typecheck(). - * - retain result as a constant expressions when called with only - * constant expressions (to avoid tripping VLA warnings in stack - * allocation usage). - */ -#define __typecheck(x, y) \ - (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) - -/* - * This returns a constant expression while determining if an argument is - * a constant expression, most importantly without evaluating the argument. - * Glory to Martin Uecker - */ -#define __is_constexpr(x) \ - (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) - -#define __no_side_effects(x, y) \ - (__is_constexpr(x) && __is_constexpr(y)) - -#define __safe_cmp(x, y) \ - (__typecheck(x, y) && __no_side_effects(x, y)) - -#define __cmp(x, y, op) ((x) op (y) ? (x) : (y)) - -#define __cmp_once(x, y, unique_x, unique_y, op) ({ \ - typeof(x) unique_x = (x); \ - typeof(y) unique_y = (y); \ - __cmp(unique_x, unique_y, op); }) - -#define __careful_cmp(x, y, op) \ - __builtin_choose_expr(__safe_cmp(x, y), \ - __cmp(x, y, op), \ - __cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op)) - -/** - * min - return minimum of two values of the same or compatible types - * @x: first value - * @y: second value - */ -#define min(x, y) __careful_cmp(x, y, <) - -/** - * max - return maximum of two values of the same or compatible types - * @x: first value - * @y: second value - */ -#define max(x, y) __careful_cmp(x, y, >) - -/** - * min3 - return minimum of three values - * @x: first value - * @y: second value - * @z: third value - */ -#define min3(x, y, z) min((typeof(x))min(x, y), z) - -/** - * max3 - return maximum of three values - * @x: first value - * @y: second value - * @z: third value - */ -#define max3(x, y, z) max((typeof(x))max(x, y), z) - -/** - * min_not_zero - return the minimum that is _not_ zero, unless both are zero - * @x: value1 - * @y: value2 - */ -#define min_not_zero(x, y) ({ \ - typeof(x) __x = (x); \ - typeof(y) __y = (y); \ - __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) - -/** - * clamp - return a value clamped to a given range with strict typechecking - * @val: current value - * @lo: lowest allowable value - * @hi: highest allowable value - * - * This macro does strict typechecking of @lo/@hi to make sure they are of the - * same type as @val. See the unnecessary pointer comparisons. - */ -#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) - -/* - * ..and if you can't take the strict - * types, you can specify one yourself. - * - * Or not use min/max/clamp at all, of course. - */ - -/** - * min_t - return minimum of two values, using the specified type - * @type: data type to use - * @x: first value - * @y: second value - */ -#define min_t(type, x, y) __careful_cmp((type)(x), (type)(y), <) - -/** - * max_t - return maximum of two values, using the specified type - * @type: data type to use - * @x: first value - * @y: second value - */ -#define max_t(type, x, y) __careful_cmp((type)(x), (type)(y), >) - -/** - * clamp_t - return a value clamped to a given range using a given type - * @type: the type of variable to use - * @val: current value - * @lo: minimum allowable value - * @hi: maximum allowable value - * - * This macro does no typechecking and uses temporary variables of type - * @type to make all the comparisons. - */ -#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi) - -/** - * clamp_val - return a value clamped to a given range using val's type - * @val: current value - * @lo: minimum allowable value - * @hi: maximum allowable value - * - * This macro does no typechecking and uses temporary variables of whatever - * type the input argument @val is. This is useful when @val is an unsigned - * type and @lo and @hi are literals that will otherwise be assigned a signed - * integer type. - */ -#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) - - -/** - * swap - swap values of @a and @b - * @a: first value - * @b: second value - */ -#define swap(a, b) \ - do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) - /* This counts to 12. Any more, it will return 13th argument. */ #define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n #define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) diff --git a/include/linux/minmax.h b/include/linux/minmax.h new file mode 100644 index 000000000000..c0f57b0c64d9 --- /dev/null +++ b/include/linux/minmax.h @@ -0,0 +1,153 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MINMAX_H +#define _LINUX_MINMAX_H + +/* + * min()/max()/clamp() macros must accomplish three things: + * + * - avoid multiple evaluations of the arguments (so side-effects like + * "x++" happen only once) when non-constant. + * - perform strict type-checking (to generate warnings instead of + * nasty runtime surprises). See the "unnecessary" pointer comparison + * in __typecheck(). + * - retain result as a constant expressions when called with only + * constant expressions (to avoid tripping VLA warnings in stack + * allocation usage). + */ +#define __typecheck(x, y) \ + (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) + +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + +#define __no_side_effects(x, y) \ + (__is_constexpr(x) && __is_constexpr(y)) + +#define __safe_cmp(x, y) \ + (__typecheck(x, y) && __no_side_effects(x, y)) + +#define __cmp(x, y, op) ((x) op (y) ? (x) : (y)) + +#define __cmp_once(x, y, unique_x, unique_y, op) ({ \ + typeof(x) unique_x = (x); \ + typeof(y) unique_y = (y); \ + __cmp(unique_x, unique_y, op); }) + +#define __careful_cmp(x, y, op) \ + __builtin_choose_expr(__safe_cmp(x, y), \ + __cmp(x, y, op), \ + __cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op)) + +/** + * min - return minimum of two values of the same or compatible types + * @x: first value + * @y: second value + */ +#define min(x, y) __careful_cmp(x, y, <) + +/** + * max - return maximum of two values of the same or compatible types + * @x: first value + * @y: second value + */ +#define max(x, y) __careful_cmp(x, y, >) + +/** + * min3 - return minimum of three values + * @x: first value + * @y: second value + * @z: third value + */ +#define min3(x, y, z) min((typeof(x))min(x, y), z) + +/** + * max3 - return maximum of three values + * @x: first value + * @y: second value + * @z: third value + */ +#define max3(x, y, z) max((typeof(x))max(x, y), z) + +/** + * min_not_zero - return the minimum that is _not_ zero, unless both are zero + * @x: value1 + * @y: value2 + */ +#define min_not_zero(x, y) ({ \ + typeof(x) __x = (x); \ + typeof(y) __y = (y); \ + __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) + +/** + * clamp - return a value clamped to a given range with strict typechecking + * @val: current value + * @lo: lowest allowable value + * @hi: highest allowable value + * + * This macro does strict typechecking of @lo/@hi to make sure they are of the + * same type as @val. See the unnecessary pointer comparisons. + */ +#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) + +/* + * ..and if you can't take the strict + * types, you can specify one yourself. + * + * Or not use min/max/clamp at all, of course. + */ + +/** + * min_t - return minimum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ +#define min_t(type, x, y) __careful_cmp((type)(x), (type)(y), <) + +/** + * max_t - return maximum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ +#define max_t(type, x, y) __careful_cmp((type)(x), (type)(y), >) + +/** + * clamp_t - return a value clamped to a given range using a given type + * @type: the type of variable to use + * @val: current value + * @lo: minimum allowable value + * @hi: maximum allowable value + * + * This macro does no typechecking and uses temporary variables of type + * @type to make all the comparisons. + */ +#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi) + +/** + * clamp_val - return a value clamped to a given range using val's type + * @val: current value + * @lo: minimum allowable value + * @hi: maximum allowable value + * + * This macro does no typechecking and uses temporary variables of whatever + * type the input argument @val is. This is useful when @val is an unsigned + * type and @lo and @hi are literals that will otherwise be assigned a signed + * integer type. + */ +#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) + +/** + * swap - swap values of @a and @b + * @a: first value + * @b: second value + */ +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + +#endif /* _LINUX_MINMAX_H */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 3334ce056335..ac398e143c9a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -90,9 +90,9 @@ * for such situations. See below and CPUMASK_ALLOC also. */ -#include #include #include +#include #include typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1ae36bc8db35..ef084eacaa7c 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -3,6 +3,7 @@ #define __LINUX_UACCESS_H__ #include +#include #include #include -- cgit v1.2.3 From 3b6742618ed9216dd6caad968fe8c83b32dff485 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 15 Oct 2020 20:11:17 -0700 Subject: lib/idr.c: document calling context for IDA APIs mustn't use locks The documentation for these functions indicates that callers don't need to hold a lock while calling them, but that documentation is only in one place under "IDA Usage". Let's state the same information on each IDA function so that it's clear what the calling context requires. Furthermore, let's document ida_simple_get() with the same information so that callers know how this API works. Signed-off-by: Stephen Boyd Signed-off-by: Andrew Morton Reviewed-by: Greg Kroah-Hartman Cc: Tri Vo Cc: Jonathan Corbet Cc: Matthew Wilcox Link: https://lkml.kernel.org/r/20200910055246.2297797-1-swboyd@chromium.org Signed-off-by: Linus Torvalds --- include/linux/idr.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/idr.h b/include/linux/idr.h index 3ade03e5c7af..b235ed987021 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -263,7 +263,8 @@ void ida_destroy(struct ida *ida); * * Allocate an ID between 0 and %INT_MAX, inclusive. * - * Context: Any context. + * Context: Any context. It is safe to call this function without + * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ @@ -280,7 +281,8 @@ static inline int ida_alloc(struct ida *ida, gfp_t gfp) * * Allocate an ID between @min and %INT_MAX, inclusive. * - * Context: Any context. + * Context: Any context. It is safe to call this function without + * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ @@ -297,7 +299,8 @@ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp) * * Allocate an ID between 0 and @max, inclusive. * - * Context: Any context. + * Context: Any context. It is safe to call this function without + * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ -- cgit v1.2.3 From 3264ceec8f17a99a3895de7de06b4d7e9c8f3f30 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 15 Oct 2020 20:11:21 -0700 Subject: lib/idr.c: document that ida_simple_{get,remove}() are deprecated These two functions are deprecated. Users should call ida_alloc() or ida_free() respectively instead. Add documentation to this effect until the macro can be removed. Signed-off-by: Stephen Boyd Signed-off-by: Andrew Morton Reviewed-by: Tri Vo Cc: Greg KH Cc: Jonathan Corbet Cc: Matthew Wilcox Link: https://lkml.kernel.org/r/20200910055246.2297797-2-swboyd@chromium.org Signed-off-by: Linus Torvalds --- include/linux/idr.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/idr.h b/include/linux/idr.h index b235ed987021..a0dce14090a9 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -314,6 +314,10 @@ static inline void ida_init(struct ida *ida) xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } +/* + * ida_simple_get() and ida_simple_remove() are deprecated. Use + * ida_alloc() and ida_free() instead respectively. + */ #define ida_simple_get(ida, start, end, gfp) \ ida_alloc_range(ida, start, (end) - 1, gfp) #define ida_simple_remove(ida, id) ida_free(ida, id) -- cgit v1.2.3 From e130816164e244b692921de49771eeb28205152d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 15 Oct 2020 20:11:31 -0700 Subject: include/linux/list.h: add a macro to test if entry is pointing to the head Add a macro to test if entry is pointing to the head of the list which is useful in cases like: list_for_each_entry(pos, &head, member) { if (cond) break; } if (list_entry_is_head(pos, &head, member)) return -ERRNO; that allows to avoid additional variable to be added to track if loop has not been stopped in the middle. While here, convert list_for_each_entry*() family of macros to use a new one. Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Reviewed-by: Cezary Rojewski Link: https://lkml.kernel.org/r/20200929134342.51489-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Torvalds --- include/linux/list.h | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index 0d0d17a10d25..a18c87b63376 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -609,6 +609,15 @@ static inline void list_splice_tail_init(struct list_head *list, pos != (head); \ pos = n, n = pos->prev) +/** + * list_entry_is_head - test if the entry points to the head of the list + * @pos: the type * to cursor + * @head: the head for your list. + * @member: the name of the list_head within the struct. + */ +#define list_entry_is_head(pos, head, member) \ + (&pos->member == (head)) + /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. @@ -617,7 +626,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** @@ -628,7 +637,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** @@ -653,7 +662,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** @@ -667,7 +676,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** @@ -679,7 +688,7 @@ static inline void list_splice_tail_init(struct list_head *list, * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ - for (; &pos->member != (head); \ + for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** @@ -692,7 +701,7 @@ static inline void list_splice_tail_init(struct list_head *list, * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ - for (; &pos->member != (head); \ + for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** @@ -705,7 +714,7 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** @@ -721,7 +730,7 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** @@ -736,7 +745,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** @@ -752,7 +761,7 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ - &pos->member != (head); \ + !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** -- cgit v1.2.3 From a9eb63705e379f10a3c9d13fc6aee8b50805e862 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 15 Oct 2020 20:11:41 -0700 Subject: bitops: simplify get_count_order_long() These two cases could be unified into one. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Cc: Christian Brauner Cc: Andy Shevchenko Link: https://lkml.kernel.org/r/20200807085837.11697-2-richard.weiyang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 99f2ac30b1d9..030a98f0c452 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -206,10 +206,7 @@ static inline int get_count_order_long(unsigned long l) { if (l == 0UL) return -1; - else if (l & (l - 1UL)) - return (int)fls_long(l); - else - return (int)fls_long(l) - 1; + return (int)fls_long(--l); } /** -- cgit v1.2.3 From 004fba1ae6ddd66ba0faa4f60c603b3ca77b3554 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 15 Oct 2020 20:11:46 -0700 Subject: bitops: use the same mechanism for get_count_order[_long] These two functions share the same logic. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Cc: Christian Brauner Cc: Andy Shevchenko Link: https://lkml.kernel.org/r/20200807085837.11697-3-richard.weiyang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 030a98f0c452..5b74bdf159d6 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -188,12 +188,10 @@ static inline unsigned fls_long(unsigned long l) static inline int get_count_order(unsigned int count) { - int order; + if (count == 0) + return -1; - order = fls(count) - 1; - if (count & (count - 1)) - order++; - return order; + return fls(--count); } /** -- cgit v1.2.3 From afc63a97b764bc5a715762d0d9cc9785c2ef4e75 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 15 Oct 2020 20:12:46 -0700 Subject: coredump: refactor page range dumping into common helper Both fs/binfmt_elf.c and fs/binfmt_elf_fdpic.c need to dump ranges of pages into the coredump file. Extract that logic into a common helper. Signed-off-by: Jann Horn Signed-off-by: Andrew Morton Acked-by: Linus Torvalds Cc: Christoph Hellwig Cc: Alexander Viro Cc: "Eric W . Biederman" Cc: Oleg Nesterov Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200827114932.3572699-4-jannh@google.com Signed-off-by: Linus Torvalds --- include/linux/coredump.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 7a899e83835d..f0b71a74d0bc 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -16,6 +16,8 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); extern void dump_truncate(struct coredump_params *cprm); +int dump_user_range(struct coredump_params *cprm, unsigned long start, + unsigned long len); #ifdef CONFIG_COREDUMP extern void do_coredump(const kernel_siginfo_t *siginfo); #else -- cgit v1.2.3 From 429a22e776a2b9f85a2b9c53d8e647598b553dd1 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 15 Oct 2020 20:12:50 -0700 Subject: coredump: rework elf/elf_fdpic vma_dump_size() into common helper At the moment, the binfmt_elf and binfmt_elf_fdpic code have slightly different code to figure out which VMAs should be dumped, and if so, whether the dump should contain the entire VMA or just its first page. Eliminate duplicate code by reworking the binfmt_elf version into a generic core dumping helper in coredump.c. As part of that, change the heuristic for detecting executable/library header pages to check whether the inode is executable instead of looking at the file mode. This is less problematic in terms of locking because it lets us avoid get_user() under the mmap_sem. (And arguably it looks nicer and makes more sense in generic code.) Adjust a little bit based on the binfmt_elf_fdpic version: ->anon_vma is only meaningful under CONFIG_MMU, otherwise we have to assume that the VMA has been written to. Suggested-by: Linus Torvalds Signed-off-by: Jann Horn Signed-off-by: Andrew Morton Acked-by: Linus Torvalds Cc: Christoph Hellwig Cc: Alexander Viro Cc: "Eric W . Biederman" Cc: Oleg Nesterov Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200827114932.3572699-5-jannh@google.com Signed-off-by: Linus Torvalds --- include/linux/coredump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index f0b71a74d0bc..bfecb8d79a7f 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -16,6 +16,7 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); extern void dump_truncate(struct coredump_params *cprm); +unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); #ifdef CONFIG_COREDUMP -- cgit v1.2.3 From a07279c9a8cd7dbd321640ff7210591599ee00a4 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 15 Oct 2020 20:12:54 -0700 Subject: binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot In both binfmt_elf and binfmt_elf_fdpic, use a new helper dump_vma_snapshot() to take a snapshot of the VMA list (including the gate VMA, if we have one) while protected by the mmap_lock, and then use that snapshot instead of walking the VMA list without locking. An alternative approach would be to keep the mmap_lock held across the entire core dumping operation; however, keeping the mmap_lock locked while we may be blocked for an unbounded amount of time (e.g. because we're dumping to a FUSE filesystem or so) isn't really optimal; the mmap_lock blocks things like the ->release handler of userfaultfd, and we don't really want critical system daemons to grind to a halt just because someone "gifted" them SCM_RIGHTS to an eternally-locked userfaultfd, or something like that. Since both the normal ELF code and the FDPIC ELF code need this functionality (and if any other binfmt wants to add coredump support in the future, they'd probably need it, too), implement this with a common helper in fs/coredump.c. A downside of this approach is that we now need a bigger amount of kernel memory per userspace VMA in the normal ELF case, and that we need O(n) kernel memory in the FDPIC ELF case at all; but 40 bytes per VMA shouldn't be terribly bad. There currently is a data race between stack expansion and anything that reads ->vm_start or ->vm_end under the mmap_lock held in read mode; to mitigate that for core dumping, take the mmap_lock in write mode when taking a snapshot of the VMA hierarchy. (If we only took the mmap_lock in read mode, we could end up with a corrupted core dump if someone does get_user_pages_remote() concurrently. Not really a major problem, but taking the mmap_lock either way works here, so we might as well avoid the issue.) (This doesn't do anything about the existing data races with stack expansion in other mm code.) Signed-off-by: Jann Horn Signed-off-by: Andrew Morton Acked-by: Linus Torvalds Cc: Christoph Hellwig Cc: Alexander Viro Cc: "Eric W . Biederman" Cc: Oleg Nesterov Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200827114932.3572699-6-jannh@google.com Signed-off-by: Linus Torvalds --- include/linux/coredump.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index bfecb8d79a7f..e58e8c207782 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -7,6 +7,12 @@ #include #include +struct core_vma_metadata { + unsigned long start, end; + unsigned long flags; + unsigned long dump_size; +}; + /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. @@ -16,9 +22,11 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); extern void dump_truncate(struct coredump_params *cprm); -unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); +int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count, + struct core_vma_metadata **vma_meta, + size_t *vma_data_size_ptr); #ifdef CONFIG_COREDUMP extern void do_coredump(const kernel_siginfo_t *siginfo); #else -- cgit v1.2.3 From 4d45e75a9955ade5c2f49bd96fc4173b2cec9a72 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 15 Oct 2020 20:13:00 -0700 Subject: mm: remove the now-unnecessary mmget_still_valid() hack The preceding patches have ensured that core dumping properly takes the mmap_lock. Thanks to that, we can now remove mmget_still_valid() and all its users. Signed-off-by: Jann Horn Signed-off-by: Andrew Morton Acked-by: Linus Torvalds Cc: Christoph Hellwig Cc: Alexander Viro Cc: "Eric W . Biederman" Cc: Oleg Nesterov Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200827114932.3572699-8-jannh@google.com Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 15bfb06f2884..981e34cb1409 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,31 +49,6 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } -/* - * This has to be called after a get_task_mm()/mmget_not_zero() - * followed by taking the mmap_lock for writing before modifying the - * vmas or anything the coredump pretends not to change from under it. - * - * It also has to be called when mmgrab() is used in the context of - * the process, but then the mm_count refcount is transferred outside - * the context of the process to run down_write() on that pinned mm. - * - * NOTE: find_extend_vma() called from GUP context is the only place - * that can modify the "mm" (notably the vm_start/end) under mmap_lock - * for reading and outside the context of the process, so it is also - * the only case that holds the mmap_lock for reading that must call - * this function. Generally if the mmap_lock is hold for reading - * there's no need of this check after get_task_mm()/mmget_not_zero(). - * - * This function can be obsoleted and the check can be removed, after - * the coredump code will hold the mmap_lock for writing before - * invoking the ->core_dump methods. - */ -static inline bool mmget_still_valid(struct mm_struct *mm) -{ - return likely(!mm->core_state); -} - /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. -- cgit v1.2.3 From 5cf53f3ce3b9ff5321b56f9ed9d90d59307be7d0 Mon Sep 17 00:00:00 2001 From: Elena Petrova Date: Thu, 15 Oct 2020 20:13:35 -0700 Subject: sched.h: drop in_ubsan field when UBSAN is in trap mode in_ubsan field of task_struct is only used in lib/ubsan.c, which in its turn is used only `ifneq ($(CONFIG_UBSAN_TRAP),y)`. Removing unnecessary field from a task_struct will help preserve the ABI between vanilla and CONFIG_UBSAN_TRAP'ed kernels. In particular, this will help enabling bounds sanitizer transparently for Android's GKI. Signed-off-by: Elena Petrova Signed-off-by: Andrew Morton Acked-by: Kees Cook Cc: Jann Horn Link: https://lkml.kernel.org/r/20200910134802.3160311-1-lenaptr@google.com Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9030f3abd969..063cd120b459 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1013,7 +1013,7 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif -#ifdef CONFIG_UBSAN +#if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif -- cgit v1.2.3 From 2c739ced5886cd8c8361faa79a9522ec05174ed0 Mon Sep 17 00:00:00 2001 From: Albert van der Linde Date: Thu, 15 Oct 2020 20:13:46 -0700 Subject: lib, include/linux: add usercopy failure capability Patch series "add fault injection to user memory access", v3. The goal of this series is to improve testing of fault-tolerance in usages of user memory access functions, by adding support for fault injection. syzkaller/syzbot are using the existing fault injection modes and will use this particular feature also. The first patch adds failure injection capability for usercopy functions. The second changes usercopy functions to use this new failure capability (copy_from_user, ...). The third patch adds get/put/clear_user failures to x86. This patch (of 3): Add a failure injection capability to improve testing of fault-tolerance in usages of user memory access functions. Add CONFIG_FAULT_INJECTION_USERCOPY to enable faults in usercopy functions. The should_fail_usercopy function is to be called by these functions (copy_from_user, get_user, ...) in order to fail or not. Signed-off-by: Albert van der Linde Signed-off-by: Andrew Morton Reviewed-by: Akinobu Mita Reviewed-by: Alexander Potapenko Cc: Borislav Petkov Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Thomas Gleixner Cc: Arnd Bergmann Cc: Peter Zijlstra (Intel) Cc: "H. Peter Anvin" Cc: Al Viro Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Marco Elver Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20200831171733.955393-1-alinde@google.com Link: http://lkml.kernel.org/r/20200831171733.955393-2-alinde@google.com Signed-off-by: Linus Torvalds --- include/linux/fault-inject-usercopy.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/fault-inject-usercopy.h (limited to 'include') diff --git a/include/linux/fault-inject-usercopy.h b/include/linux/fault-inject-usercopy.h new file mode 100644 index 000000000000..56c3a693fdd9 --- /dev/null +++ b/include/linux/fault-inject-usercopy.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_FAULT_INJECT_USERCOPY_H__ +#define __LINUX_FAULT_INJECT_USERCOPY_H__ + +/* + * This header provides a wrapper for injecting failures to user space memory + * access functions. + */ + +#include + +#ifdef CONFIG_FAULT_INJECTION_USERCOPY + +bool should_fail_usercopy(void); + +#else + +static inline bool should_fail_usercopy(void) { return false; } + +#endif /* CONFIG_FAULT_INJECTION_USERCOPY */ + +#endif /* __LINUX_FAULT_INJECT_USERCOPY_H__ */ -- cgit v1.2.3 From 4d0e9df5e43dba52d38b251e3b909df8fa1110be Mon Sep 17 00:00:00 2001 From: Albert van der Linde Date: Thu, 15 Oct 2020 20:13:50 -0700 Subject: lib, uaccess: add failure injection to usercopy functions To test fault-tolerance of user memory access functions, introduce fault injection to usercopy functions. If a failure is expected return either -EFAULT or the total amount of bytes that were not copied. Signed-off-by: Albert van der Linde Signed-off-by: Andrew Morton Reviewed-by: Akinobu Mita Reviewed-by: Alexander Potapenko Cc: Al Viro Cc: Andrey Konovalov Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Dmitry Vyukov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Marco Elver Cc: Peter Zijlstra (Intel) Cc: Thomas Gleixner Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20200831171733.955393-3-alinde@google.com Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ef084eacaa7c..1b8c9d6162bc 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -2,6 +2,7 @@ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ +#include #include #include #include @@ -84,6 +85,8 @@ static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); + if (should_fail_usercopy()) + return n; instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); @@ -105,6 +108,8 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { + if (should_fail_usercopy()) + return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); @@ -114,6 +119,8 @@ static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); + if (should_fail_usercopy()) + return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); @@ -125,7 +132,7 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); - if (likely(access_ok(from, n))) { + if (!should_fail_usercopy() && likely(access_ok(from, n))) { instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } @@ -143,6 +150,8 @@ static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); + if (should_fail_usercopy()) + return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); -- cgit v1.2.3 From 98447d65b4a7a59f8ea37dc6e5d743247d9a7b01 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 14 Oct 2020 10:48:51 -0600 Subject: io_uring: move io identity items into separate struct io-wq contains a pointer to the identity, which we just hold in io_kiocb for now. This is in preparation for putting this outside io_kiocb. The only exception is struct files_struct, which we'll need different rules for to avoid a circular dependency. No functional changes in this patch. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 96315cfaf6d1..352aa6bbd36b 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -4,7 +4,18 @@ #include #include -#include + +struct io_identity { + struct files_struct *files; + struct mm_struct *mm; +#ifdef CONFIG_BLK_CGROUP + struct cgroup_subsys_state *blkcg_css; +#endif + const struct cred *creds; + struct nsproxy *nsproxy; + struct fs_struct *fs; + unsigned long fsize; +}; struct io_uring_task { /* submission side */ -- cgit v1.2.3 From 1e6fa5216a0e59ef02e8b6b40d553238a3b81d49 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Oct 2020 08:46:24 -0600 Subject: io_uring: COW io_identity on mismatch If the io_identity doesn't completely match the task, then create a copy of it and use that. The existing copy remains valid until the last user of it has gone away. This also changes the personality lookup to be indexed by io_identity, instead of creds directly. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 352aa6bbd36b..342cc574d5c0 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -15,6 +15,7 @@ struct io_identity { struct nsproxy *nsproxy; struct fs_struct *fs; unsigned long fsize; + refcount_t count; }; struct io_uring_task { -- cgit v1.2.3 From 5c3462cfd123b341c9d3c947c1a2bab373f1697f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Oct 2020 09:02:33 -0600 Subject: io_uring: store io_identity in io_uring_task This is, by definition, a per-task structure. So store it in the task context, instead of doing carrying it in each io_kiocb. We're being a bit inefficient if members have changed, as that requires an alloc and copy of a new io_identity struct. The next patch will fix that up. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 342cc574d5c0..bd3346194bca 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -24,6 +24,7 @@ struct io_uring_task { struct wait_queue_head wait; struct file *last; atomic_long_t req_issue; + struct io_identity identity; /* completion side */ bool in_idle ____cacheline_aligned_in_smp; -- cgit v1.2.3 From 500a373d731ac506612db12631ec21295c1ff360 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Oct 2020 17:38:03 -0600 Subject: io_uring: assign new io_identity for task if members have changed This avoids doing a copy for each new async IO, if some parts of the io_identity has changed. We avoid reference counting for the normal fast path of nothing ever changing. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index bd3346194bca..607d14f61132 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -24,7 +24,8 @@ struct io_uring_task { struct wait_queue_head wait; struct file *last; atomic_long_t req_issue; - struct io_identity identity; + struct io_identity __identity; + struct io_identity *identity; /* completion side */ bool in_idle ____cacheline_aligned_in_smp; -- cgit v1.2.3 From d8a6df10aac9f2e4d5f30aff3129d552d2984ce7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Oct 2020 16:24:45 -0600 Subject: io_uring: use percpu counters to track inflight requests Even though we place the req_issued and req_complete in separate cachelines, there's considerable overhead in doing the atomics particularly on the completion side. Get rid of having the two counters, and just use a percpu_counter for this. That's what it was made for, after all. This considerably reduces the overhead in __io_free_req(). Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 607d14f61132..28939820b6b0 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -23,13 +23,10 @@ struct io_uring_task { struct xarray xa; struct wait_queue_head wait; struct file *last; - atomic_long_t req_issue; + struct percpu_counter inflight; struct io_identity __identity; struct io_identity *identity; - - /* completion side */ - bool in_idle ____cacheline_aligned_in_smp; - atomic_long_t req_complete; + bool in_idle; }; #if defined(CONFIG_IO_URING) -- cgit v1.2.3 From 4ea33a976bfe79293965d0815e1914e4b6e58967 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Oct 2020 13:46:44 -0600 Subject: io-wq: inherit audit loginuid and sessionid Make sure the async io-wq workers inherit the loginuid and sessionid from the original task, and restore them to unset once we're done with the async work item. While at it, disable the ability for kernel threads to write to their own loginuid. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 28939820b6b0..868364cea3b7 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -15,6 +15,10 @@ struct io_identity { struct nsproxy *nsproxy; struct fs_struct *fs; unsigned long fsize; +#ifdef CONFIG_AUDIT + kuid_t loginuid; + unsigned int sessionid; +#endif refcount_t count; }; -- cgit v1.2.3 From 3c532798ec96b6c2d77706f04ed1d8b566a805df Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 3 Oct 2020 10:49:22 -0600 Subject: tracehook: clear TIF_NOTIFY_RESUME in tracehook_notify_resume() All the callers currently do this, clean it up and move the clearing into tracehook_notify_resume() instead. Reviewed-by: Oleg Nesterov Reviewed-by: Thomas Gleixner Signed-off-by: Jens Axboe --- include/linux/tracehook.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 36fb3bbed6b2..b480e1a07ed8 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -178,9 +178,9 @@ static inline void set_notify_resume(struct task_struct *task) */ static inline void tracehook_notify_resume(struct pt_regs *regs) { + clear_thread_flag(TIF_NOTIFY_RESUME); /* - * The caller just cleared TIF_NOTIFY_RESUME. This barrier - * pairs with task_work_add()->set_notify_resume() after + * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); -- cgit v1.2.3 From 91989c707884ecc7cd537281ab1a4b8fb7219da3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 16 Oct 2020 09:02:26 -0600 Subject: task_work: cleanup notification modes A previous commit changed the notification mode from true/false to an int, allowing notify-no, notify-yes, or signal-notify. This was backwards compatible in the sense that any existing true/false user would translate to either 0 (on notification sent) or 1, the latter which mapped to TWA_RESUME. TWA_SIGNAL was assigned a value of 2. Clean this up properly, and define a proper enum for the notification mode. Now we have: - TWA_NONE. This is 0, same as before the original change, meaning no notification requested. - TWA_RESUME. This is 1, same as before the original change, meaning that we use TIF_NOTIFY_RESUME. - TWA_SIGNAL. This uses TIF_SIGPENDING/JOBCTL_TASK_WORK for the notification. Clean up all the callers, switching their 0/1/false/true to using the appropriate TWA_* mode for notifications. Fixes: e91b48162332 ("task_work: teach task_work_add() to do signal_wake_up()") Reviewed-by: Thomas Gleixner Signed-off-by: Jens Axboe --- include/linux/task_work.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 0fb93aafa478..0d848a1e9e62 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -13,9 +13,14 @@ init_task_work(struct callback_head *twork, task_work_func_t func) twork->func = func; } -#define TWA_RESUME 1 -#define TWA_SIGNAL 2 -int task_work_add(struct task_struct *task, struct callback_head *twork, int); +enum task_work_notify_mode { + TWA_NONE, + TWA_RESUME, + TWA_SIGNAL, +}; + +int task_work_add(struct task_struct *task, struct callback_head *twork, + enum task_work_notify_mode mode); struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); -- cgit v1.2.3 From 15a119e09344a346384ec05c781c126a29b18235 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Wed, 23 Sep 2020 01:12:31 +0800 Subject: jbd2: fix the comment of struct jbd2_journal_handle the struct name was modified long ago, but the comment still use struct handle_s. Signed-off-by: Hui Su Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20200922171231.GA53120@rlk Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 08f904943ab2..a1ef05412acf 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -452,8 +452,8 @@ struct jbd2_inode { struct jbd2_revoke_table_s; /** - * struct handle_s - The handle_s type is the concrete type associated with - * handle_t. + * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete + * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. -- cgit v1.2.3 From aa3c0c61f62d682259e3e66cdc01846290f9cd6c Mon Sep 17 00:00:00 2001 From: Mauricio Faria de Oliveira Date: Mon, 5 Oct 2020 21:48:38 -0300 Subject: jbd2: introduce/export functions jbd2_journal_submit|finish_inode_data_buffers() Export functions that implement the current behavior done for an inode in journal_submit|finish_inode_data_buffers(). No functional change. Signed-off-by: Mauricio Faria de Oliveira Suggested-by: Jan Kara Reviewed-by: Jan Kara Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/20201006004841.600488-2-mfo@canonical.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index a1ef05412acf..8b7b06066bc2 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1421,6 +1421,10 @@ extern int jbd2_journal_inode_ranged_write(handle_t *handle, extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); +extern int jbd2_journal_submit_inode_data_buffers( + struct jbd2_inode *jinode); +extern int jbd2_journal_finish_inode_data_buffers( + struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); -- cgit v1.2.3 From 342af94ec6c02aa478fe2adcd41b950e154b03ba Mon Sep 17 00:00:00 2001 From: Mauricio Faria de Oliveira Date: Mon, 5 Oct 2020 21:48:39 -0300 Subject: jbd2, ext4, ocfs2: introduce/use journal callbacks j_submit|finish_inode_data_buffers() Introduce journal callbacks to allow different behaviors for an inode in journal_submit|finish_inode_data_buffers(). The existing users of the current behavior (ext4, ocfs2) are adapted to use the previously exported functions that implement the current behavior. Users are callers of jbd2_journal_inode_ranged_write|wait(), which adds the inode to the transaction's inode list with the JI_WRITE|WAIT_DATA flags. Only ext4 and ocfs2 in-tree. Both CONFIG_EXT4_FS and CONFIG_OCSFS2_FS select CONFIG_JBD2, which builds fs/jbd2/commit.c and journal.c that define and export the functions, so we can call directly in ext4/ocfs2. Signed-off-by: Mauricio Faria de Oliveira Suggested-by: Jan Kara Reviewed-by: Jan Kara Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/20201006004841.600488-3-mfo@canonical.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 8b7b06066bc2..04afa6dcd60d 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -629,7 +629,9 @@ struct transaction_s struct journal_head *t_shadow_list; /* - * List of inodes whose data we've modified in data=ordered mode. + * List of inodes associated with the transaction; e.g., ext4 uses + * this to track inodes in data=ordered and data=journal mode that + * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; @@ -1111,6 +1113,27 @@ struct journal_s void (*j_commit_callback)(journal_t *, transaction_t *); + /** + * @j_submit_inode_data_buffers: + * + * This function is called for all inodes associated with the + * committing transaction marked with JI_WRITE_DATA flag + * before we start to write out the transaction to the journal. + */ + int (*j_submit_inode_data_buffers) + (struct jbd2_inode *); + + /** + * @j_finish_inode_data_buffers: + * + * This function is called for all inodes associated with the + * committing transaction marked with JI_WAIT_DATA flag + * after we have written the transaction to the journal + * but before we write out the commit block. + */ + int (*j_finish_inode_data_buffers) + (struct jbd2_inode *); + /* * Journal statistics */ -- cgit v1.2.3 From b87d8cefe43c7f22e8aa13919c1dfa2b4b4b4e01 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 17 Oct 2020 16:13:40 -0700 Subject: mm, memcg: rework remote charging API to support nesting Currently the remote memcg charging API consists of two functions: memalloc_use_memcg() and memalloc_unuse_memcg(), which set and clear the memcg value, which overwrites the memcg of the current task. memalloc_use_memcg(target_memcg); <...> memalloc_unuse_memcg(); It works perfectly for allocations performed from a normal context, however an attempt to call it from an interrupt context or just nest two remote charging blocks will lead to an incorrect accounting. On exit from the inner block the active memcg will be cleared instead of being restored. memalloc_use_memcg(target_memcg); memalloc_use_memcg(target_memcg_2); <...> memalloc_unuse_memcg(); Error: allocation here are charged to the memcg of the current process instead of target_memcg. memalloc_unuse_memcg(); This patch extends the remote charging API by switching to a single function: struct mem_cgroup *set_active_memcg(struct mem_cgroup *memcg), which sets the new value and returns the old one. So a remote charging block will look like: old_memcg = set_active_memcg(target_memcg); <...> set_active_memcg(old_memcg); This patch is heavily based on the patch by Johannes Weiner, which can be found here: https://lkml.org/lkml/2020/5/28/806 . Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Dan Schatzberg Link: https://lkml.kernel.org/r/20200821212056.3769116-1-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 30 ++++++++++-------------------- 1 file changed, 10 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 981e34cb1409..1a80fb128e74 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -280,38 +280,28 @@ static inline void memalloc_nocma_restore(unsigned int flags) #ifdef CONFIG_MEMCG /** - * memalloc_use_memcg - Starts the remote memcg charging scope. + * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * - * NOTE: This function is not nesting safe. + * NOTE: This function can nest. Users must save the return value and + * reset the previous value after their own charging scope is over. */ -static inline void memalloc_use_memcg(struct mem_cgroup *memcg) +static inline struct mem_cgroup * +set_active_memcg(struct mem_cgroup *memcg) { - WARN_ON_ONCE(current->active_memcg); + struct mem_cgroup *old = current->active_memcg; current->active_memcg = memcg; -} - -/** - * memalloc_unuse_memcg - Ends the remote memcg charging scope. - * - * This function marks the end of the remote memcg charging scope started by - * memalloc_use_memcg(). - */ -static inline void memalloc_unuse_memcg(void) -{ - current->active_memcg = NULL; + return old; } #else -static inline void memalloc_use_memcg(struct mem_cgroup *memcg) -{ -} - -static inline void memalloc_unuse_memcg(void) +static inline struct mem_cgroup * +set_active_memcg(struct mem_cgroup *memcg) { + return NULL; } #endif -- cgit v1.2.3 From 37d5985c003daab138a72dd4af9853b396d91c26 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 17 Oct 2020 16:13:50 -0700 Subject: mm: kmem: prepare remote memcg charging infra for interrupt contexts Remote memcg charging API uses current->active_memcg to store the currently active memory cgroup, which overwrites the memory cgroup of the current process. It works well for normal contexts, but doesn't work for interrupt contexts: indeed, if an interrupt occurs during the execution of a section with an active memcg set, all allocations inside the interrupt will be charged to the active memcg set (given that we'll enable accounting for allocations from an interrupt context). But because the interrupt might have no relation to the active memcg set outside, it's obviously wrong from the accounting prospective. To resolve this problem, let's add a global percpu int_active_memcg variable, which will be used to store an active memory cgroup which will be used from interrupt contexts. set_active_memcg() will transparently use current->active_memcg or int_active_memcg depending on the context. To make the read part simple and transparent for the caller, let's introduce two new functions: - struct mem_cgroup *active_memcg(void), - struct mem_cgroup *get_active_memcg(void). They are returning the active memcg if it's set, hiding all implementation details: where to get it depending on the current context. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Link: http://lkml.kernel.org/r/20200827225843.1270629-4-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1a80fb128e74..d5ece7a9a403 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -279,6 +279,7 @@ static inline void memalloc_nocma_restore(unsigned int flags) #endif #ifdef CONFIG_MEMCG +DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); /** * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. @@ -293,8 +294,16 @@ static inline void memalloc_nocma_restore(unsigned int flags) static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { - struct mem_cgroup *old = current->active_memcg; - current->active_memcg = memcg; + struct mem_cgroup *old; + + if (in_interrupt()) { + old = this_cpu_read(int_active_memcg); + this_cpu_write(int_active_memcg, memcg); + } else { + old = current->active_memcg; + current->active_memcg = memcg; + } + return old; } #else -- cgit v1.2.3 From 4127c6504f25c4fcff52dc996efda2ef859dd661 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 17 Oct 2020 16:13:53 -0700 Subject: mm: kmem: enable kernel memcg accounting from interrupt contexts If a memcg to charge can be determined (using remote charging API), there are no reasons to exclude allocations made from an interrupt context from the accounting. Such allocations will pass even if the resulting memcg size will exceed the hard limit, but it will affect the application of the memory pressure and an inability to put the workload under the limit will eventually trigger the OOM. To use active_memcg() helper, memcg_kmem_bypass() is moved back to memcontrol.c. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Link: http://lkml.kernel.org/r/20200827225843.1270629-5-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6ef4a552e09d..e391e3c56de5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1531,18 +1531,6 @@ static inline bool memcg_kmem_enabled(void) return static_branch_likely(&memcg_kmem_enabled_key); } -static inline bool memcg_kmem_bypass(void) -{ - if (in_interrupt()) - return true; - - /* Allow remote memcg charging in kthread contexts. */ - if ((!current->mm || (current->flags & PF_KTHREAD)) && - !current->active_memcg) - return true; - return false; -} - static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { -- cgit v1.2.3 From 0726b01e70455f9900ab524117c7b520d197dc8c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 17 Oct 2020 16:14:50 -0700 Subject: mm/madvise: pass mm to do_madvise Patch series "introduce memory hinting API for external process", v9. Now, we have MADV_PAGEOUT and MADV_COLD as madvise hinting API. With that, application could give hints to kernel what memory range are preferred to be reclaimed. However, in some platform(e.g., Android), the information required to make the hinting decision is not known to the app. Instead, it is known to a centralized userspace daemon(e.g., ActivityManagerService), and that daemon must be able to initiate reclaim on its own without any app involvement. To solve the concern, this patch introduces new syscall - process_madvise(2). Bascially, it's same with madvise(2) syscall but it has some differences. 1. It needs pidfd of target process to provide the hint 2. It supports only MADV_{COLD|PAGEOUT|MERGEABLE|UNMEREABLE} at this moment. Other hints in madvise will be opened when there are explicit requests from community to prevent unexpected bugs we couldn't support. 3. Only privileged processes can do something for other process's address space. For more detail of the new API, please see "mm: introduce external memory hinting API" description in this patchset. This patch (of 3): In upcoming patches, do_madvise will be called from external process context so we shouldn't asssume "current" is always hinted process's task_struct. Furthermore, we must not access mm_struct via task->mm, but obtain it via access_mm() once (in the following patch) and only use that pointer [1], so pass it to do_madvise() as well. Note the vma->vm_mm pointers are safe, so we can use them further down the call stack. And let's pass current->mm as arguments of do_madvise so it shouldn't change existing behavior but prepare next patch to make review easy. [vbabka@suse.cz: changelog tweak] [minchan@kernel.org: use current->mm for io_uring] Link: http://lkml.kernel.org/r/20200423145215.72666-1-minchan@kernel.org [akpm@linux-foundation.org: fix it for upstream changes] [akpm@linux-foundation.org: whoops] [rdunlap@infradead.org: add missing includes] Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Reviewed-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Acked-by: David Rientjes Cc: Jens Axboe Cc: Jann Horn Cc: Tim Murray Cc: Daniel Colascione Cc: Sandeep Patil Cc: Sonny Rao Cc: Brian Geffon Cc: Michal Hocko Cc: Johannes Weiner Cc: Shakeel Butt Cc: John Dias Cc: Joel Fernandes Cc: Alexander Duyck Cc: SeongJae Park Cc: Christian Brauner Cc: Kirill Tkhai Cc: Oleksandr Natalenko Cc: SeongJae Park Cc: Christian Brauner Cc: Florian Weimer Cc: Link: https://lkml.kernel.org/r/20200901000633.1920247-1-minchan@kernel.org Link: http://lkml.kernel.org/r/20200622192900.22757-1-minchan@kernel.org Link: http://lkml.kernel.org/r/20200302193630.68771-2-minchan@kernel.org Link: http://lkml.kernel.org/r/20200622192900.22757-2-minchan@kernel.org Link: https://lkml.kernel.org/r/20200901000633.1920247-2-minchan@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 61a2633fcc7f..ef360fe70aaf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2579,7 +2579,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); -extern int do_madvise(unsigned long start, size_t len_in, int behavior); +extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, -- cgit v1.2.3 From 1aa92cd31c1c032ddfed27e79d646bbb429e9b52 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 17 Oct 2020 16:14:54 -0700 Subject: pid: move pidfd_get_pid() to pid.c process_madvise syscall needs pidfd_get_pid function to translate pidfd to pid so this patch move the function to kernel/pid.c. Suggested-by: Alexander Duyck Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Reviewed-by: Suren Baghdasaryan Reviewed-by: Alexander Duyck Reviewed-by: Vlastimil Babka Acked-by: Christian Brauner Acked-by: David Rientjes Cc: Jens Axboe Cc: Jann Horn Cc: Brian Geffon Cc: Daniel Colascione Cc: Joel Fernandes Cc: Johannes Weiner Cc: John Dias Cc: Kirill Tkhai Cc: Michal Hocko Cc: Oleksandr Natalenko Cc: Sandeep Patil Cc: SeongJae Park Cc: SeongJae Park Cc: Shakeel Butt Cc: Sonny Rao Cc: Tim Murray Cc: Christian Brauner Cc: Florian Weimer Cc: Link: http://lkml.kernel.org/r/20200302193630.68771-5-minchan@kernel.org Link: http://lkml.kernel.org/r/20200622192900.22757-3-minchan@kernel.org Link: https://lkml.kernel.org/r/20200901000633.1920247-3-minchan@kernel.org Signed-off-by: Linus Torvalds --- include/linux/pid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pid.h b/include/linux/pid.h index 176d6cf80e7c..fa10acb8d6a4 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -77,6 +77,7 @@ extern const struct file_operations pidfd_fops; struct file; extern struct pid *pidfd_pid(const struct file *file); +struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); static inline struct pid *get_pid(struct pid *pid) { -- cgit v1.2.3 From ecb8ac8b1f146915aa6b96449b66dd48984caacc Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 17 Oct 2020 16:14:59 -0700 Subject: mm/madvise: introduce process_madvise() syscall: an external memory hinting API There is usecase that System Management Software(SMS) want to give a memory hint like MADV_[COLD|PAGEEOUT] to other processes and in the case of Android, it is the ActivityManagerService. The information required to make the reclaim decision is not known to the app. Instead, it is known to the centralized userspace daemon(ActivityManagerService), and that daemon must be able to initiate reclaim on its own without any app involvement. To solve the issue, this patch introduces a new syscall process_madvise(2). It uses pidfd of an external process to give the hint. It also supports vector address range because Android app has thousands of vmas due to zygote so it's totally waste of CPU and power if we should call the syscall one by one for each vma.(With testing 2000-vma syscall vs 1-vector syscall, it showed 15% performance improvement. I think it would be bigger in real practice because the testing ran very cache friendly environment). Another potential use case for the vector range is to amortize the cost ofTLB shootdowns for multiple ranges when using MADV_DONTNEED; this could benefit users like TCP receive zerocopy and malloc implementations. In future, we could find more usecases for other advises so let's make it happens as API since we introduce a new syscall at this moment. With that, existing madvise(2) user could replace it with process_madvise(2) with their own pid if they want to have batch address ranges support feature. ince it could affect other process's address range, only privileged process(PTRACE_MODE_ATTACH_FSCREDS) or something else(e.g., being the same UID) gives it the right to ptrace the process could use it successfully. The flag argument is reserved for future use if we need to extend the API. I think supporting all hints madvise has/will supported/support to process_madvise is rather risky. Because we are not sure all hints make sense from external process and implementation for the hint may rely on the caller being in the current context so it could be error-prone. Thus, I just limited hints as MADV_[COLD|PAGEOUT] in this patch. If someone want to add other hints, we could hear the usecase and review it for each hint. It's safer for maintenance rather than introducing a buggy syscall but hard to fix it later. So finally, the API is as follows, ssize_t process_madvise(int pidfd, const struct iovec *iovec, unsigned long vlen, int advice, unsigned int flags); DESCRIPTION The process_madvise() system call is used to give advice or directions to the kernel about the address ranges from external process as well as local process. It provides the advice to address ranges of process described by iovec and vlen. The goal of such advice is to improve system or application performance. The pidfd selects the process referred to by the PID file descriptor specified in pidfd. (See pidofd_open(2) for further information) The pointer iovec points to an array of iovec structures, defined in as: struct iovec { void *iov_base; /* starting address */ size_t iov_len; /* number of bytes to be advised */ }; The iovec describes address ranges beginning at address(iov_base) and with size length of bytes(iov_len). The vlen represents the number of elements in iovec. The advice is indicated in the advice argument, which is one of the following at this moment if the target process specified by pidfd is external. MADV_COLD MADV_PAGEOUT Permission to provide a hint to external process is governed by a ptrace access mode PTRACE_MODE_ATTACH_FSCREDS check; see ptrace(2). The process_madvise supports every advice madvise(2) has if target process is in same thread group with calling process so user could use process_madvise(2) to extend existing madvise(2) to support vector address ranges. RETURN VALUE On success, process_madvise() returns the number of bytes advised. This return value may be less than the total number of requested bytes, if an error occurred. The caller should check return value to determine whether a partial advice occurred. FAQ: Q.1 - Why does any external entity have better knowledge? Quote from Sandeep "For Android, every application (including the special SystemServer) are forked from Zygote. The reason of course is to share as many libraries and classes between the two as possible to benefit from the preloading during boot. After applications start, (almost) all of the APIs end up calling into this SystemServer process over IPC (binder) and back to the application. In a fully running system, the SystemServer monitors every single process periodically to calculate their PSS / RSS and also decides which process is "important" to the user for interactivity. So, because of how these processes start _and_ the fact that the SystemServer is looping to monitor each process, it does tend to *know* which address range of the application is not used / useful. Besides, we can never rely on applications to clean things up themselves. We've had the "hey app1, the system is low on memory, please trim your memory usage down" notifications for a long time[1]. They rely on applications honoring the broadcasts and very few do. So, if we want to avoid the inevitable killing of the application and restarting it, some way to be able to tell the OS about unimportant memory in these applications will be useful. - ssp Q.2 - How to guarantee the race(i.e., object validation) between when giving a hint from an external process and get the hint from the target process? process_madvise operates on the target process's address space as it exists at the instant that process_madvise is called. If the space target process can run between the time the process_madvise process inspects the target process address space and the time that process_madvise is actually called, process_madvise may operate on memory regions that the calling process does not expect. It's the responsibility of the process calling process_madvise to close this race condition. For example, the calling process can suspend the target process with ptrace, SIGSTOP, or the freezer cgroup so that it doesn't have an opportunity to change its own address space before process_madvise is called. Another option is to operate on memory regions that the caller knows a priori will be unchanged in the target process. Yet another option is to accept the race for certain process_madvise calls after reasoning that mistargeting will do no harm. The suggested API itself does not provide synchronization. It also apply other APIs like move_pages, process_vm_write. The race isn't really a problem though. Why is it so wrong to require that callers do their own synchronization in some manner? Nobody objects to write(2) merely because it's possible for two processes to open the same file and clobber each other's writes --- instead, we tell people to use flock or something. Think about mmap. It never guarantees newly allocated address space is still valid when the user tries to access it because other threads could unmap the memory right before. That's where we need synchronization by using other API or design from userside. It shouldn't be part of API itself. If someone needs more fine-grained synchronization rather than process level, there were two ideas suggested - cookie[2] and anon-fd[3]. Both are applicable via using last reserved argument of the API but I don't think it's necessary right now since we have already ways to prevent the race so don't want to add additional complexity with more fine-grained optimization model. To make the API extend, it reserved an unsigned long as last argument so we could support it in future if someone really needs it. Q.3 - Why doesn't ptrace work? Injecting an madvise in the target process using ptrace would not work for us because such injected madvise would have to be executed by the target process, which means that process would have to be runnable and that creates the risk of the abovementioned race and hinting a wrong VMA. Furthermore, we want to act the hint in caller's context, not the callee's, because the callee is usually limited in cpuset/cgroups or even freezed state so they can't act by themselves quick enough, which causes more thrashing/kill. It doesn't work if the target process are ptraced(e.g., strace, debugger, minidump) because a process can have at most one ptracer. [1] https://developer.android.com/topic/performance/memory" [2] process_getinfo for getting the cookie which is updated whenever vma of process address layout are changed - Daniel Colascione - https://lore.kernel.org/lkml/20190520035254.57579-1-minchan@kernel.org/T/#m7694416fd179b2066a2c62b5b139b14e3894e224 [3] anonymous fd which is used for the object(i.e., address range) validation - Michal Hocko - https://lore.kernel.org/lkml/20200120112722.GY18451@dhcp22.suse.cz/ [minchan@kernel.org: fix process_madvise build break for arm64] Link: http://lkml.kernel.org/r/20200303145756.GA219683@google.com [minchan@kernel.org: fix build error for mips of process_madvise] Link: http://lkml.kernel.org/r/20200508052517.GA197378@google.com [akpm@linux-foundation.org: fix patch ordering issue] [akpm@linux-foundation.org: fix arm64 whoops] [minchan@kernel.org: make process_madvise() vlen arg have type size_t, per Florian] [akpm@linux-foundation.org: fix i386 build] [sfr@canb.auug.org.au: fix syscall numbering] Link: https://lkml.kernel.org/r/20200905142639.49fc3f1a@canb.auug.org.au [sfr@canb.auug.org.au: madvise.c needs compat.h] Link: https://lkml.kernel.org/r/20200908204547.285646b4@canb.auug.org.au [minchan@kernel.org: fix mips build] Link: https://lkml.kernel.org/r/20200909173655.GC2435453@google.com [yuehaibing@huawei.com: remove duplicate header which is included twice] Link: https://lkml.kernel.org/r/20200915121550.30584-1-yuehaibing@huawei.com [minchan@kernel.org: do not use helper functions for process_madvise] Link: https://lkml.kernel.org/r/20200921175539.GB387368@google.com [akpm@linux-foundation.org: pidfd_get_pid() gained an argument] [sfr@canb.auug.org.au: fix up for "iov_iter: transparently handle compat iovecs in import_iovec"] Link: https://lkml.kernel.org/r/20200928212542.468e1fef@canb.auug.org.au Signed-off-by: Minchan Kim Signed-off-by: YueHaibing Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Reviewed-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Acked-by: David Rientjes Cc: Alexander Duyck Cc: Brian Geffon Cc: Christian Brauner Cc: Daniel Colascione Cc: Jann Horn Cc: Jens Axboe Cc: Joel Fernandes Cc: Johannes Weiner Cc: John Dias Cc: Kirill Tkhai Cc: Michal Hocko Cc: Oleksandr Natalenko Cc: Sandeep Patil Cc: SeongJae Park Cc: SeongJae Park Cc: Shakeel Butt Cc: Sonny Rao Cc: Tim Murray Cc: Christian Brauner Cc: Florian Weimer Cc: Link: http://lkml.kernel.org/r/20200302193630.68771-3-minchan@kernel.org Link: http://lkml.kernel.org/r/20200508183320.GA125527@google.com Link: http://lkml.kernel.org/r/20200622192900.22757-4-minchan@kernel.org Link: https://lkml.kernel.org/r/20200901000633.1920247-4-minchan@kernel.org Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 ++ include/uapi/asm-generic/unistd.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 06db09875aa4..2eda7678fe1d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -879,6 +879,8 @@ asmlinkage long sys_munlockall(void); asmlinkage long sys_mincore(unsigned long start, size_t len, unsigned char __user * vec); asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); +asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec, + size_t vlen, int behavior, unsigned int flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index f2b5d72a46c2..2056318988f7 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2) __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) #define __NR_faccessat2 439 __SYSCALL(__NR_faccessat2, sys_faccessat2) +#define __NR_process_madvise 440 +__SYSCALL(__NR_process_madvise, sys_process_madvise) #undef __NR_syscalls -#define __NR_syscalls 440 +#define __NR_syscalls 441 /* * 32 bit systems traditionally used different -- cgit v1.2.3 From b944afc9d64ddf1b6a152c23ff86bf26e1fd430c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 17 Oct 2020 16:15:06 -0700 Subject: mm: add a VM_MAP_PUT_PAGES flag for vmap Add a flag so that vmap takes ownership of the passed in page array. When vfree is called on such an allocation it will put one reference on each page, and free the page array itself. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Boris Ostrovsky Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Matthew Auld Cc: "Matthew Wilcox (Oracle)" Cc: Minchan Kim Cc: Nitin Gupta Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Stefano Stabellini Cc: Tvrtko Ursulin Cc: Uladzislau Rezki (Sony) Link: https://lkml.kernel.org/r/20201002122204.1534411-3-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0221f852a7e1..b899681e3ff9 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -24,6 +24,7 @@ struct notifier_block; /* in notifier.h */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ +#define VM_MAP_PUT_PAGES 0x00000100 /* put pages and free array in vfree */ /* * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC. -- cgit v1.2.3 From 3e9a9e256b1e1e6e8f19faf76fa9c37578ae35ee Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 17 Oct 2020 16:15:10 -0700 Subject: mm: add a vmap_pfn function Add a proper helper to remap PFNs into kernel virtual space so that drivers don't have to abuse alloc_vm_area and open coded PTE manipulation for it. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Boris Ostrovsky Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Matthew Auld Cc: "Matthew Wilcox (Oracle)" Cc: Minchan Kim Cc: Nitin Gupta Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Stefano Stabellini Cc: Tvrtko Ursulin Cc: Uladzislau Rezki (Sony) Link: https://lkml.kernel.org/r/20201002122204.1534411-4-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index b899681e3ff9..c77efeac2425 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -122,6 +122,7 @@ extern void vfree_atomic(const void *addr); extern void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot); +void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot); extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, -- cgit v1.2.3 From 301fa9f2ddf7fb248c188af292c9cc04f8283dff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 17 Oct 2020 16:15:39 -0700 Subject: mm: remove alloc_vm_area All users are gone now. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Boris Ostrovsky Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Matthew Auld Cc: "Matthew Wilcox (Oracle)" Cc: Minchan Kim Cc: Nitin Gupta Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Stefano Stabellini Cc: Tvrtko Ursulin Cc: Uladzislau Rezki (Sony) Link: https://lkml.kernel.org/r/20201002122204.1534411-12-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index c77efeac2425..938eaf9517e2 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -169,6 +169,7 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller); +void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); @@ -204,10 +205,6 @@ static inline void set_vm_flush_reset_perms(void *addr) } #endif -/* Allocate/destroy a 'vmalloc' VM area. */ -extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes); -extern void free_vm_area(struct vm_struct *area); - /* for /dev/kmem */ extern long vread(char *buf, char *addr, unsigned long count); extern long vwrite(char *buf, char *addr, unsigned long count); -- cgit v1.2.3 From f3d301c1f2f5676465cdf3259737ea19cc82731f Mon Sep 17 00:00:00 2001 From: Al Grant Date: Mon, 21 Sep 2020 21:46:37 +0100 Subject: perf: correct SNOOPX field offset perf_event.h has macros that define the field offsets in the data_src bitmask in perf records. The SNOOPX and REMOTE offsets were both 37. These are distinct fields, and the bitfield layout in perf_mem_data_src confirms that SNOOPX should be at offset 38. Fixes: 52839e653b5629bd ("perf tools: Add support for printing new mem_info encodings") Signed-off-by: Al Grant Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andi Kleen Link: https://lkml.kernel.org/r/4ac9f5cc-4388-b34a-9999-418a4099415d@foss.arm.com --- include/uapi/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 077e7ee69e3d..b95d3c485d27 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1196,7 +1196,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ /* 1 free */ -#define PERF_MEM_SNOOPX_SHIFT 37 +#define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ #define PERF_MEM_LOCK_NA 0x01 /* not available */ -- cgit v1.2.3 From 54c9de89895e0a36047fcc4ae754ea5b8655fb9d Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 7 Sep 2020 15:47:27 +0200 Subject: xen/events: add a new "late EOI" evtchn framework In order to avoid tight event channel related IRQ loops add a new framework of "late EOI" handling: the IRQ the event channel is bound to will be masked until the event has been handled and the related driver is capable to handle another event. The driver is responsible for unmasking the event channel via the new function xen_irq_lateeoi(). This is similar to binding an event channel to a threaded IRQ, but without having to structure the driver accordingly. In order to support a future special handling in case a rogue guest is sending lots of unsolicited events, add a flag to xen_irq_lateeoi() which can be set by the caller to indicate the event was a spurious one. This is part of XSA-332. Cc: stable@vger.kernel.org Reported-by: Julien Grall Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Reviewed-by: Stefano Stabellini Reviewed-by: Wei Liu --- include/xen/events.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/xen/events.h b/include/xen/events.h index df1e6391f63f..3b8155c2ea03 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -15,10 +15,15 @@ unsigned xen_evtchn_nr_channels(void); int bind_evtchn_to_irq(evtchn_port_t evtchn); +int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn); int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); +int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, const char *devname, + void *dev_id); int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu); int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, @@ -32,12 +37,20 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, void *dev_id); int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, evtchn_port_t remote_port); +int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port); int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, evtchn_port_t remote_port, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); +int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id); /* * Common unbind function for all event sources. Takes IRQ to unbind from. @@ -46,6 +59,14 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, */ void unbind_from_irqhandler(unsigned int irq, void *dev_id); +/* + * Send late EOI for an IRQ bound to an event channel via one of the *_lateeoi + * functions above. + */ +void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags); +/* Signal an event was spurious, i.e. there was no action resulting from it. */ +#define XEN_EOI_FLAG_SPURIOUS 0x00000001 + #define XEN_IRQ_PRIORITY_MAX EVTCHN_FIFO_PRIORITY_MAX #define XEN_IRQ_PRIORITY_DEFAULT EVTCHN_FIFO_PRIORITY_DEFAULT #define XEN_IRQ_PRIORITY_MIN EVTCHN_FIFO_PRIORITY_MIN -- cgit v1.2.3 From 695cebe58dcf3d9802cdfa9c327b5c7641a5914b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 20 Oct 2020 10:41:07 +0200 Subject: dma-mapping: move more functions to dma-map-ops.h Due to a mismerge a bunch of prototypes that should have moved to dma-map-ops.h are still in dma-mapping.h, fix that up. Signed-off-by: Christoph Hellwig --- include/linux/dma-map-ops.h | 23 +++++++++++++++++++++++ include/linux/dma-mapping.h | 24 ------------------------ 2 files changed, 23 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 8029f7e04145..a5f89fc4d6df 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -203,6 +203,29 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_DECLARE_COHERENT */ +int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +struct page *dma_common_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); +void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr, + dma_addr_t dma_handle, enum dma_data_direction dir); + +struct page **dma_common_find_pages(void *cpu_addr); +void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot, + const void *caller); +void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, + const void *caller); +void dma_common_free_remap(void *cpu_addr, size_t size); + +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t flags, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)); +bool dma_free_from_pool(struct device *dev, void *start, size_t size); + #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H #include #elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 3f029afdc9dc..956151052d45 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -389,30 +389,6 @@ static inline void dma_sync_sgtable_for_device(struct device *dev, #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) -extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); -struct page *dma_common_alloc_pages(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); -void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); -struct page **dma_common_find_pages(void *cpu_addr); -void *dma_common_contiguous_remap(struct page *page, size_t size, - pgprot_t prot, const void *caller); - -void *dma_common_pages_remap(struct page **pages, size_t size, - pgprot_t prot, const void *caller); -void dma_common_free_remap(void *cpu_addr, size_t size); - -struct page *dma_alloc_from_pool(struct device *dev, size_t size, - void **cpu_addr, gfp_t flags, - bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)); -bool dma_free_from_pool(struct device *dev, void *start, size_t size); - -int -dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, - dma_addr_t dma_addr, size_t size, unsigned long attrs); - static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { -- cgit v1.2.3 From 31cc578ae2de19c748af06d859019dced68e325d Mon Sep 17 00:00:00 2001 From: Saeed Mirzamohammadi Date: Tue, 20 Oct 2020 13:41:36 +0200 Subject: netfilter: nftables_offload: KASAN slab-out-of-bounds Read in nft_flow_rule_create This patch fixes the issue due to: BUG: KASAN: slab-out-of-bounds in nft_flow_rule_create+0x622/0x6a2 net/netfilter/nf_tables_offload.c:40 Read of size 8 at addr ffff888103910b58 by task syz-executor227/16244 The error happens when expr->ops is accessed early on before performing the boundary check and after nft_expr_next() moves the expr to go out-of-bounds. This patch checks the boundary condition before expr->ops that fixes the slab-out-of-bounds Read issue. Add nft_expr_more() and use it to fix this problem. Signed-off-by: Saeed Mirzamohammadi Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3f7e56b1171e..55b4cadf290a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -891,6 +891,12 @@ static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule) return (struct nft_expr *)&rule->data[rule->dlen]; } +static inline bool nft_expr_more(const struct nft_rule *rule, + const struct nft_expr *expr) +{ + return expr != nft_expr_last(rule) && expr->ops; +} + static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) { return (void *)&rule->data[rule->dlen]; -- cgit v1.2.3 From cb3a92da231bcf55c243d00fa619ee36281b0001 Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Tue, 20 Oct 2020 05:22:56 -0400 Subject: block: remove unused members for io_context After removing blk-sq code, there is no user of nr_batch_requests and last_waited in kernel. Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- include/linux/iocontext.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 1dcd9198beb7..0a9dc40b7be8 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -106,12 +106,6 @@ struct io_context { unsigned short ioprio; - /* - * For request batching - */ - int nr_batch_requests; /* Number of requests left in the batch */ - unsigned long last_waited; /* Time last woken after wait for request */ - struct radix_tree_root icq_tree; struct io_cq __rcu *icq_hint; struct hlist_head icq_list; -- cgit v1.2.3 From aa9c9b3f3f08cb0fda8a8139e6fb302c9a2e21ed Mon Sep 17 00:00:00 2001 From: Bean Huo Date: Tue, 20 Oct 2020 17:00:27 +0200 Subject: PM: runtime: Fix typo in pm_runtime_set_active() helper comment This patch is to fix typo in the comment of helper pm_runtime_set_active(). Signed-off-by: Bean Huo [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 6245caa18034..18b02dcc168e 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -479,7 +479,7 @@ static inline int pm_runtime_set_active(struct device *dev) } /** - * pm_runtime_set_suspended - Set runtime PM status to "active". + * pm_runtime_set_suspended - Set runtime PM status to "suspended". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that -- cgit v1.2.3 From 0cfcd405e758ba1d277e58436fb32f06888c3e41 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Sun, 18 Oct 2020 23:42:49 -0400 Subject: NFSv4.2: Fix NFS4ERR_STALE error when doing inter server copy NFS_FS=y as dependency of CONFIG_NFSD_V4_2_INTER_SSC still have build errors and some configs with NFSD=m to get NFS4ERR_STALE error when doing inter server copy. Added ops table in nfs_common for knfsd to access NFS client modules. Fixes: 3ac3711adb88 ("NFSD: Fix NFS server build errors") Signed-off-by: Dai Ngo Signed-off-by: J. Bruce Fields --- include/linux/nfs_ssc.h | 67 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 include/linux/nfs_ssc.h (limited to 'include') diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h new file mode 100644 index 000000000000..f5ba0fbff72f --- /dev/null +++ b/include/linux/nfs_ssc.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/nfs_ssc.h + * + * Author: Dai Ngo + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include + +extern struct nfs_ssc_client_ops_tbl nfs_ssc_client_tbl; + +/* + * NFS_V4 + */ +struct nfs4_ssc_client_ops { + struct file *(*sco_open)(struct vfsmount *ss_mnt, + struct nfs_fh *src_fh, nfs4_stateid *stateid); + void (*sco_close)(struct file *filep); +}; + +/* + * NFS_FS + */ +struct nfs_ssc_client_ops { + void (*sco_sb_deactive)(struct super_block *sb); +}; + +struct nfs_ssc_client_ops_tbl { + const struct nfs4_ssc_client_ops *ssc_nfs4_ops; + const struct nfs_ssc_client_ops *ssc_nfs_ops; +}; + +extern void nfs42_ssc_register_ops(void); +extern void nfs42_ssc_unregister_ops(void); + +extern void nfs42_ssc_register(const struct nfs4_ssc_client_ops *ops); +extern void nfs42_ssc_unregister(const struct nfs4_ssc_client_ops *ops); + +#ifdef CONFIG_NFSD_V4_2_INTER_SSC +static inline struct file *nfs42_ssc_open(struct vfsmount *ss_mnt, + struct nfs_fh *src_fh, nfs4_stateid *stateid) +{ + if (nfs_ssc_client_tbl.ssc_nfs4_ops) + return (*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_open)(ss_mnt, src_fh, stateid); + return ERR_PTR(-EIO); +} + +static inline void nfs42_ssc_close(struct file *filep) +{ + if (nfs_ssc_client_tbl.ssc_nfs4_ops) + (*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_close)(filep); +} +#endif + +/* + * NFS_FS + */ +extern void nfs_ssc_register(const struct nfs_ssc_client_ops *ops); +extern void nfs_ssc_unregister(const struct nfs_ssc_client_ops *ops); + +static inline void nfs_do_sb_deactive(struct super_block *sb) +{ + if (nfs_ssc_client_tbl.ssc_nfs_ops) + (*nfs_ssc_client_tbl.ssc_nfs_ops->sco_sb_deactive)(sb); +} -- cgit v1.2.3 From 0afa15e1a5294754066343cad24af5ec8edae96d Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Thu, 10 Sep 2020 10:53:49 +0200 Subject: virtio: let arch advertise guest's memory access restrictions An architecture may restrict host access to guest memory, e.g. IBM s390 Secure Execution or AMD SEV. Provide a new Kconfig entry the architecture can select, CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS, when it provides the arch_has_restricted_virtio_memory_access callback to advertise to VIRTIO common code when the architecture restricts memory access from the host. The common code can then fail the probe for any device where VIRTIO_F_ACCESS_PLATFORM is required, but not set. Signed-off-by: Pierre Morel Reviewed-by: Cornelia Huck Reviewed-by: Halil Pasic Link: https://lore.kernel.org/r/1599728030-17085-2-git-send-email-pmorel@linux.ibm.com Signed-off-by: Michael S. Tsirkin Acked-by: Christian Borntraeger --- include/linux/virtio_config.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 8fe857e27ef3..3f697c8c8205 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -540,4 +540,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev, virtio_cread_le((vdev), structname, member, ptr); \ _r; \ }) + +#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS +int arch_has_restricted_virtio_memory_access(void); +#else +static inline int arch_has_restricted_virtio_memory_access(void) +{ + return 0; +} +#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */ + #endif /* _LINUX_VIRTIO_CONFIG_H */ -- cgit v1.2.3 From 66570e966dd9cb4fd57811d0056c6472a14a2c41 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 18 Aug 2020 15:24:28 +0000 Subject: kvm: x86: only provide PV features if enabled in guest's CPUID KVM unconditionally provides PV features to the guest, regardless of the configured CPUID. An unwitting guest that doesn't check KVM_CPUID_FEATURES before use could access paravirt features that userspace did not intend to provide. Fix this by checking the guest's CPUID before performing any paravirtual operations. Introduce a capability, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, to gate the aforementioned enforcement. Migrating a VM from a host w/o this patch to a host with this patch could silently change the ABI exposed to the guest, warranting that we default to the old behavior and opt-in for the new one. Reviewed-by: Jim Mattson Reviewed-by: Peter Shier Signed-off-by: Oliver Upton Change-Id: I202a0926f65035b872bfe8ad15307c026de59a98 Message-Id: <20200818152429.1923996-4-oupton@google.com> Reviewed-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 58f43aa1fc21..ca41220b40b8 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1052,6 +1052,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_STEAL_TIME 187 #define KVM_CAP_X86_USER_SPACE_MSR 188 #define KVM_CAP_X86_MSR_FILTER 189 +#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 9e9eb226b91225fc199bbafc06f3cd70bfce0100 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 14 Oct 2020 11:26:46 -0700 Subject: KVM: Cache as_id in kvm_memory_slot Cache the address space ID just like the slot ID. It will be used in order to fill in the dirty ring entries. Suggested-by: Paolo Bonzini Suggested-by: Sean Christopherson Reviewed-by: Sean Christopherson Signed-off-by: Peter Xu Message-Id: <20201014182700.2888246-7-bgardon@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 05e3c2fb3ef7..c6f45687ba89 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -346,6 +346,7 @@ struct kvm_memory_slot { unsigned long userspace_addr; u32 flags; short id; + u16 as_id; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) -- cgit v1.2.3 From ba452c9e996d8a4c347b32805f91abb70de5de7e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 20 Oct 2020 23:25:56 +0200 Subject: bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Based on the discussion in [0], update the bpf_redirect_neigh() helper to accept an optional parameter specifying the nexthop information. This makes it possible to combine bpf_fib_lookup() and bpf_redirect_neigh() without incurring a duplicate FIB lookup - since the FIB lookup helper will return the nexthop information even if no neighbour is present, this can simply be passed on to bpf_redirect_neigh() if bpf_fib_lookup() returns BPF_FIB_LKUP_RET_NO_NEIGH. Thus fix & extend it before helper API is frozen. [0] https://lore.kernel.org/bpf/393e17fc-d187-3a8d-2f0d-a627c7c63fca@iogearbox.net/ Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Reviewed-by: David Ahern Link: https://lore.kernel.org/bpf/160322915615.32199.1187570224032024535.stgit@toke.dk --- include/linux/filter.h | 9 +++++++++ include/uapi/linux/bpf.h | 22 ++++++++++++++++++---- 2 files changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 20fc24c9779a..72d62cbc1578 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -607,12 +607,21 @@ struct bpf_skb_data_end { void *data_end; }; +struct bpf_nh_params { + u32 nh_family; + union { + u32 ipv4_nh; + struct in6_addr ipv6_nh; + }; +}; + struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; struct bpf_map *map; u32 kern_flags; + struct bpf_nh_params nh; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bf5a99d803e4..e6ceac3f7d62 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3677,15 +3677,19 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * long bpf_redirect_neigh(u32 ifindex, u64 flags) + * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags) * Description * Redirect the packet to another net device of index *ifindex* * and fill in L2 addresses from neighboring subsystem. This helper * is somewhat similar to **bpf_redirect**\ (), except that it * populates L2 addresses as well, meaning, internally, the helper - * performs a FIB lookup based on the skb's networking header to - * get the address of the next hop and then relies on the neighbor - * lookup for the L2 address of the nexthop. + * relies on the neighbor lookup for the L2 address of the nexthop. + * + * The helper will perform a FIB lookup based on the skb's + * networking header to get the address of the next hop, unless + * this is supplied by the caller in the *params* argument. The + * *plen* argument indicates the len of *params* and should be set + * to 0 if *params* is NULL. * * The *flags* argument is reserved and must be 0. The helper is * currently only supported for tc BPF program types, and enabled @@ -4906,6 +4910,16 @@ struct bpf_fib_lookup { __u8 dmac[6]; /* ETH_ALEN */ }; +struct bpf_redir_neigh { + /* network family for lookup (AF_INET, AF_INET6) */ + __u32 nh_family; + /* network address of nexthop; skips fib lookup to find gateway */ + union { + __be32 ipv4_nh; + __u32 ipv6_nh[4]; /* in6_addr; network order */ + }; +}; + enum bpf_task_fd_type { BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ BPF_FD_TYPE_TRACEPOINT, /* tp name */ -- cgit v1.2.3 From ebfe3c5183733f784264450a41646a482f964e5e Mon Sep 17 00:00:00 2001 From: Di Zhu Date: Wed, 21 Oct 2020 10:00:53 +0800 Subject: rtnetlink: fix data overflow in rtnl_calcit() "ip addr show" command execute error when we have a physical network card with a large number of VFs The return value of if_nlmsg_size() in rtnl_calcit() will exceed range of u16 data type when any network cards has a larger number of VFs. rtnl_vfinfo_size() will significant increase needed dump size when the value of num_vfs is larger. Eventually we get a wrong value of min_ifinfo_dump_size because of overflow which decides the memory size needed by netlink dump and netlink_dump() will return -EMSGSIZE because of not enough memory was allocated. So fix it by promoting min_dump_alloc data type to u32 to avoid whole netlink message size overflow and it's also align with the data type of struct netlink_callback{}.min_dump_alloc which is assigned by return value of rtnl_calcit() Signed-off-by: Di Zhu Link: https://lore.kernel.org/r/20201021020053.1401-1-zhudi21@huawei.com Signed-off-by: Jakub Kicinski --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 666cd0390699..9f118771e248 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -240,7 +240,7 @@ struct netlink_dump_control { int (*done)(struct netlink_callback *); void *data; struct module *module; - u16 min_dump_alloc; + u32 min_dump_alloc; }; int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, -- cgit v1.2.3 From 995a3ed67fc8c0e3301a770016fb66f1bbf15ec8 Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 15 Oct 2020 13:37:54 -0700 Subject: ext4: add fast_commit feature and handling for extended mount options We are running out of mount option bits. Add handling for using s_mount_opt2. Add ext4 and jbd2 fast commit feature flag and also add ability to turn off the fast commit feature in Ext4. Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20201015203802.3597742-3-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 04afa6dcd60d..0685cc95e501 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -289,6 +289,7 @@ typedef struct journal_superblock_s #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 +#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ @@ -299,7 +300,8 @@ typedef struct journal_superblock_s JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ - JBD2_FEATURE_INCOMPAT_CSUM_V3) + JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ + JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ @@ -1263,6 +1265,7 @@ JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) +JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* * Journal flag definitions -- cgit v1.2.3 From 6866d7b3f2bb4f011041ba54c98b1584497fe2fd Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 15 Oct 2020 13:37:55 -0700 Subject: ext4 / jbd2: add fast commit initialization This patch adds fast commit area trackers in the journal_t structure. These are initialized via the jbd2_fc_init() routine that this patch adds. This patch also adds ext4/fast_commit.c and ext4/fast_commit.h files for fast commit code that will be added in subsequent patches in this series. Reported-by: kernel test robot Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20201015203802.3597742-4-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0685cc95e501..008629b4d615 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -918,6 +918,30 @@ struct journal_s */ unsigned long j_last; + /** + * @j_fc_first: + * + * The block number of the first fast commit block in the journal + * [j_state_lock]. + */ + unsigned long j_fc_first; + + /** + * @j_fc_off: + * + * Number of fast commit blocks currently allocated. + * [j_state_lock]. + */ + unsigned long j_fc_off; + + /** + * @j_fc_last: + * + * The block number one beyond the last fast commit block in the journal + * [j_state_lock]. + */ + unsigned long j_fc_last; + /** * @j_dev: Device where we store the journal. */ @@ -1068,6 +1092,12 @@ struct journal_s */ struct buffer_head **j_wbuf; + /** + * @j_fc_wbuf: Array of fast commit bhs for + * jbd2_journal_commit_transaction. + */ + struct buffer_head **j_fc_wbuf; + /** * @j_wbufsize: * @@ -1075,6 +1105,13 @@ struct journal_s */ int j_wbufsize; + /** + * @j_fc_wbufsize: + * + * Size of @j_fc_wbuf array. + */ + int j_fc_wbufsize; + /** * @j_last_sync_writer: * @@ -1535,6 +1572,8 @@ void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); +/* Fast commit related APIs */ +int jbd2_fc_init(journal_t *journal, int num_fc_blks); /* * is_journal_abort * -- cgit v1.2.3 From ff780b91efe901b8eecd8114785abae5341820ad Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 15 Oct 2020 13:37:56 -0700 Subject: jbd2: add fast commit machinery This functions adds necessary APIs needed in JBD2 layer for fast commits. Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20201015203802.3597742-5-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 008629b4d615..a009d9b9c620 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -861,6 +861,13 @@ struct journal_s */ wait_queue_head_t j_wait_reserved; + /** + * @j_fc_wait: + * + * Wait queue to wait for completion of async fast commits. + */ + wait_queue_head_t j_fc_wait; + /** * @j_checkpoint_mutex: * @@ -1232,6 +1239,15 @@ struct journal_s */ struct lockdep_map j_trans_commit_map; #endif + + /** + * @j_fc_cleanup_callback: + * + * Clean-up after fast commit or full commit. JBD2 calls this function + * after every commit operation. + */ + void (*j_fc_cleanup_callback)(struct journal_s *journal, int); + }; #define jbd2_might_wait_for_commit(j) \ @@ -1316,6 +1332,8 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ +#define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ +#define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ /* * Function declarations for the journaling transaction and buffer @@ -1574,6 +1592,15 @@ extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_init(journal_t *journal, int num_fc_blks); +int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); +int jbd2_fc_end_commit(journal_t *journal); +int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid); +int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); +int jbd2_submit_inode_data(struct jbd2_inode *jinode); +int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); +int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); +int jbd2_fc_release_bufs(journal_t *journal); + /* * is_journal_abort * -- cgit v1.2.3 From aa75f4d3daaeb1389b9cce9d6b84401eaf228d4e Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 15 Oct 2020 13:37:57 -0700 Subject: ext4: main fast-commit commit path This patch adds main fast commit commit path handlers. The overall patch can be divided into two inter-related parts: (A) Metadata updates tracking This part consists of helper functions to track changes that need to be committed during a commit operation. These updates are maintained by Ext4 in different in-memory queues. Following are the APIs and their short description that are implemented in this patch: - ext4_fc_track_link/unlink/creat() - Track unlink. link and creat operations - ext4_fc_track_range() - Track changed logical block offsets inodes - ext4_fc_track_inode() - Track inodes - ext4_fc_mark_ineligible() - Mark file system fast commit ineligible() - ext4_fc_start_update() / ext4_fc_stop_update() / ext4_fc_start_ineligible() / ext4_fc_stop_ineligible() These functions are useful for co-ordinating inode updates with commits. (B) Main commit Path This part consists of functions to convert updates tracked in in-memory data structures into on-disk commits. Function ext4_fc_commit() is the main entry point to commit path. Reported-by: kernel test robot Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20201015203802.3597742-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 172 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 172 insertions(+) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 4c8b99ec8606..521de3a82118 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -95,6 +95,16 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B); { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}) +#define show_fc_reason(reason) \ + __print_symbolic(reason, \ + { EXT4_FC_REASON_XATTR, "XATTR"}, \ + { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ + { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ + { EXT4_FC_REASON_MEM, "NO_MEM"}, \ + { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ + { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ + { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ + { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), @@ -2791,6 +2801,168 @@ TRACE_EVENT(ext4_lazy_itable_init, MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); +TRACE_EVENT(ext4_fc_commit_start, + TP_PROTO(struct super_block *sb), + + TP_ARGS(sb), + + TP_STRUCT__entry( + __field(dev_t, dev) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + ), + + TP_printk("fast_commit started on dev %d,%d", + MAJOR(__entry->dev), MINOR(__entry->dev)) +); + +TRACE_EVENT(ext4_fc_commit_stop, + TP_PROTO(struct super_block *sb, int nblks, int reason), + + TP_ARGS(sb, nblks, reason), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, nblks) + __field(int, reason) + __field(int, num_fc) + __field(int, num_fc_ineligible) + __field(int, nblks_agg) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->nblks = nblks; + __entry->reason = reason; + __entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits; + __entry->num_fc_ineligible = + EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; + __entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks; + ), + + TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->nblks, __entry->reason, __entry->num_fc, + __entry->num_fc_ineligible, __entry->nblks_agg) +); + +#define FC_REASON_NAME_STAT(reason) \ + show_fc_reason(reason), \ + __entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason] + +TRACE_EVENT(ext4_fc_stats, + TP_PROTO(struct super_block *sb), + + TP_ARGS(sb), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(struct ext4_sb_info *, sbi) + __field(int, count) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->sbi = EXT4_SB(sb); + ), + + TP_printk("dev %d:%d fc ineligible reasons:\n" + "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; " + "num_commits:%ld, ineligible: %ld, numblks: %ld", + MAJOR(__entry->dev), MINOR(__entry->dev), + FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), + FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), + FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM), + FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), + FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), + FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), + __entry->sbi->s_fc_stats.fc_num_commits, + __entry->sbi->s_fc_stats.fc_ineligible_commits, + __entry->sbi->s_fc_stats.fc_numblks) + +); + +#define DEFINE_TRACE_DENTRY_EVENT(__type) \ + TRACE_EVENT(ext4_fc_track_##__type, \ + TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \ + \ + TP_ARGS(inode, dentry, ret), \ + \ + TP_STRUCT__entry( \ + __field(dev_t, dev) \ + __field(int, ino) \ + __field(int, error) \ + ), \ + \ + TP_fast_assign( \ + __entry->dev = inode->i_sb->s_dev; \ + __entry->ino = inode->i_ino; \ + __entry->error = ret; \ + ), \ + \ + TP_printk("dev %d:%d, inode %d, error %d, fc_%s", \ + MAJOR(__entry->dev), MINOR(__entry->dev), \ + __entry->ino, __entry->error, \ + #__type) \ + ) + +DEFINE_TRACE_DENTRY_EVENT(create); +DEFINE_TRACE_DENTRY_EVENT(link); +DEFINE_TRACE_DENTRY_EVENT(unlink); + +TRACE_EVENT(ext4_fc_track_inode, + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, ino) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->error = ret; + ), + + TP_printk("dev %d:%d, inode %d, error %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, __entry->error) + ); + +TRACE_EVENT(ext4_fc_track_range, + TP_PROTO(struct inode *inode, long start, long end, int ret), + + TP_ARGS(inode, start, end, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, ino) + __field(long, start) + __field(long, end) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->start = start; + __entry->end = end; + __entry->error = ret; + ), + + TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, __entry->error, __entry->start, + __entry->end) + ); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 5b849b5f96b47d82b5a432d8b91a8ad260e1de46 Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 15 Oct 2020 13:37:58 -0700 Subject: jbd2: fast commit recovery path This patch adds fast commit recovery support in JBD2. Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20201015203802.3597742-7-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index a009d9b9c620..fb3d71ad6eea 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -751,6 +751,11 @@ jbd2_time_diff(unsigned long start, unsigned long end) #define JBD2_NR_BATCH 64 +enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; + +#define JBD2_FC_REPLAY_STOP 0 +#define JBD2_FC_REPLAY_CONTINUE 1 + /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. @@ -1248,6 +1253,21 @@ struct journal_s */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int); + /* + * @j_fc_replay_callback: + * + * File-system specific function that performs replay of a fast + * commit. JBD2 calls this function for each fast commit block found in + * the journal. This function should return JBD2_FC_REPLAY_CONTINUE + * to indicate that the block was processed correctly and more fast + * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP + * indicates the end of replay (no more blocks remaining). A negative + * return value indicates error. + */ + int (*j_fc_replay_callback)(struct journal_s *journal, + struct buffer_head *bh, + enum passtype pass, int off, + tid_t expected_commit_id); }; #define jbd2_might_wait_for_commit(j) \ -- cgit v1.2.3 From 8016e29f4362e285f0f7e38fadc61a5b7bdfdfa2 Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 15 Oct 2020 13:37:59 -0700 Subject: ext4: fast commit recovery path This patch adds fast commit recovery path support for Ext4 file system. We add several helper functions that are similar in spirit to e2fsprogs journal recovery path handlers. Example of such functions include - a simple block allocator, idempotent block bitmap update function etc. Using these routines and the fast commit log in the fast commit area, the recovery path (ext4_fc_replay()) performs fast commit log recovery. Reported-by: kernel test robot Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20201015203802.3597742-8-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 56 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 52 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 521de3a82118..b14314fcf732 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -1776,9 +1776,9 @@ TRACE_EVENT(ext4_ext_load_extent, ); TRACE_EVENT(ext4_load_inode, - TP_PROTO(struct inode *inode), + TP_PROTO(struct super_block *sb, unsigned long ino), - TP_ARGS(inode), + TP_ARGS(sb, ino), TP_STRUCT__entry( __field( dev_t, dev ) @@ -1786,8 +1786,8 @@ TRACE_EVENT(ext4_load_inode, ), TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; + __entry->dev = sb->s_dev; + __entry->ino = ino; ), TP_printk("dev %d,%d ino %ld", @@ -2801,6 +2801,54 @@ TRACE_EVENT(ext4_lazy_itable_init, MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); +TRACE_EVENT(ext4_fc_replay_scan, + TP_PROTO(struct super_block *sb, int error, int off), + + TP_ARGS(sb, error, off), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(int, off) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->error = error; + __entry->off = off; + ), + + TP_printk("FC scan pass on dev %d,%d: error %d, off %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->error, __entry->off) +); + +TRACE_EVENT(ext4_fc_replay, + TP_PROTO(struct super_block *sb, int tag, int ino, int priv1, int priv2), + + TP_ARGS(sb, tag, ino, priv1, priv2), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, tag) + __field(int, ino) + __field(int, priv1) + __field(int, priv2) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->tag = tag; + __entry->ino = ino; + __entry->priv1 = priv1; + __entry->priv2 = priv2; + ), + + TP_printk("FC Replay %d,%d: tag %d, ino %d, data1 %d, data2 %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->tag, __entry->ino, __entry->priv1, __entry->priv2) +); + TRACE_EVENT(ext4_fc_commit_start, TP_PROTO(struct super_block *sb), -- cgit v1.2.3 From ee6e00c868221f5f7d0b6eb4e8379a148e26bc20 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Oct 2020 14:15:51 -0600 Subject: splice: change exported internal do_splice() helper to take kernel offset With the set_fs change, we can no longer rely on copy_{to,from}_user() accepting a kernel pointer, and it was bad form to do so anyway. Clean this up and change the internal helper that io_uring uses to deal with kernel pointers instead. This puts the offset copy in/out in __do_splice() instead, which just calls the same helper. Signed-off-by: Jens Axboe --- include/linux/splice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/splice.h b/include/linux/splice.h index 5c47013f708e..a55179fd60fc 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -78,8 +78,8 @@ extern ssize_t add_to_pipe(struct pipe_inode_info *, struct pipe_buffer *); extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, splice_direct_actor *); -extern long do_splice(struct file *in, loff_t __user *off_in, - struct file *out, loff_t __user *off_out, +extern long do_splice(struct file *in, loff_t *off_in, + struct file *out, loff_t *off_out, size_t len, unsigned int flags); extern long do_tee(struct file *in, struct file *out, size_t len, -- cgit v1.2.3 From 879bc2d27904354b98ca295b6168718e045c4aa2 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 19 Oct 2020 16:57:50 +0200 Subject: hil/parisc: Disable HIL driver when it gets stuck When starting a HP machine with HIL driver but without an HIL keyboard or HIL mouse attached, it may happen that data written to the HIL loop gets stuck (e.g. because the transaction queue is full). Usually one will then have to reboot the machine because all you see is and endless output of: Transaction add failed: transaction already queued? In the higher layers hp_sdc_enqueue_transaction() is called to queued up a HIL packet. This function returns an error code, and this patch adds the necessary checks for this return code and disables the HIL driver if further packets can't be sent. Tested on a HP 730 and a HP 715/64 machine. Signed-off-by: Helge Deller Cc: --- include/linux/hil_mlc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hil_mlc.h b/include/linux/hil_mlc.h index 774f7d3b8f6a..369221fd5518 100644 --- a/include/linux/hil_mlc.h +++ b/include/linux/hil_mlc.h @@ -103,7 +103,7 @@ struct hilse_node { /* Methods for back-end drivers, e.g. hp_sdc_mlc */ typedef int (hil_mlc_cts) (hil_mlc *mlc); -typedef void (hil_mlc_out) (hil_mlc *mlc); +typedef int (hil_mlc_out) (hil_mlc *mlc); typedef int (hil_mlc_in) (hil_mlc *mlc, suseconds_t timeout); struct hil_mlc_devinfo { -- cgit v1.2.3 From a6a0b05da9f37ff56faa6b8351ed6e0b55032460 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Wed, 14 Oct 2020 11:26:55 -0700 Subject: kvm: x86/mmu: Support dirty logging for the TDP MMU Dirty logging is a key feature of the KVM MMU and must be supported by the TDP MMU. Add support for both the write protection and PML dirty logging modes. Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell machine. This series introduced no new failures. This series can be viewed in Gerrit at: https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538 Signed-off-by: Ben Gardon Message-Id: <20201014182700.2888246-16-bgardon@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c6f45687ba89..7f2e2a09ebbd 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -798,6 +798,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 5894048775df4a65ee2b58a7c2fa3ca8c6984a78 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 22 Oct 2020 11:49:03 +0200 Subject: xen: remove no longer used functions With the switch to the lateeoi model for interdomain event channels some functions are no longer in use. Remove them. Suggested-by: Jan Beulich Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Link: https://lore.kernel.org/r/20201022094907.28560-2-jgross@suse.com Signed-off-by: Boris Ostrovsky --- include/xen/events.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/xen/events.h b/include/xen/events.h index 3b8155c2ea03..8ec418e30c7f 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -35,16 +35,8 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, unsigned long irqflags, const char *devname, void *dev_id); -int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, - evtchn_port_t remote_port); int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, evtchn_port_t remote_port); -int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - evtchn_port_t remote_port, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, - void *dev_id); int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, evtchn_port_t remote_port, irq_handler_t handler, -- cgit v1.2.3 From 3f1b623a1be92103386bcab818e25885d6be9419 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 23 Oct 2020 17:00:41 +0800 Subject: vdpa: introduce config op to get valid iova range This patch introduce a config op to get valid iova range from the vDPA device. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20201023090043.14430-2-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index eae0bfd87d91..30bc7a7223bb 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -52,6 +52,16 @@ struct vdpa_device { int nvqs; }; +/** + * vDPA IOVA range - the IOVA range support by the device + * @first: start of the IOVA range + * @last: end of the IOVA range + */ +struct vdpa_iova_range { + u64 first; + u64 last; +}; + /** * vDPA_config_ops - operations for configuring a vDPA device. * Note: vDPA device drivers are required to implement all of the @@ -151,6 +161,10 @@ struct vdpa_device { * @get_generation: Get device config generation (optional) * @vdev: vdpa device * Returns u32: device generation + * @get_iova_range: Get supported iova range (optional) + * @vdev: vdpa device + * Returns the iova range supported by + * the device. * @set_map: Set device memory mapping (optional) * Needed for device that using device * specific DMA translation (on-chip IOMMU) @@ -216,6 +230,7 @@ struct vdpa_config_ops { void (*set_config)(struct vdpa_device *vdev, unsigned int offset, const void *buf, unsigned int len); u32 (*get_generation)(struct vdpa_device *vdev); + struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); /* DMA ops */ int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb); -- cgit v1.2.3 From 1b48dc03e575a872404f33b04cd237953c5d7498 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 23 Oct 2020 17:00:42 +0800 Subject: vhost: vdpa: report iova range This patch introduces a new ioctl for vhost-vdpa device that can report the iova range by the device. For device that implements get_iova_range() method, we fetch it from the vDPA device. If device doesn't implement get_iova_range() but depends on platform IOMMU, we will query via DOMAIN_ATTR_GEOMETRY, otherwise [0, ULLONG_MAX] is assumed. For safety, this patch also rules out the map request which is not in the valid range. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20201023090043.14430-3-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 4 ++++ include/uapi/linux/vhost_types.h | 9 +++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 75232185324a..c998860d7bbc 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -146,4 +146,8 @@ /* Set event fd for config interrupt*/ #define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int) + +/* Get the valid iova range */ +#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ + struct vhost_vdpa_iova_range) #endif diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 9a269a88a6ff..f7f6a3a28977 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -138,6 +138,15 @@ struct vhost_vdpa_config { __u8 buf[0]; }; +/* vhost vdpa IOVA range + * @first: First address that can be mapped by vhost-vDPA + * @last: Last address that can be mapped by vhost-vDPA + */ +struct vhost_vdpa_iova_range { + __u64 first; + __u64 last; +}; + /* Feature bits */ /* Log all write descriptors. Can be changed while device is active. */ #define VHOST_F_LOG_ALL 26 -- cgit v1.2.3 From c51f8f88d705e06bd696d7510aff22b33eb8e638 Mon Sep 17 00:00:00 2001 From: George Spelvin Date: Sun, 9 Aug 2020 06:57:44 +0000 Subject: random32: make prandom_u32() output unpredictable Non-cryptographic PRNGs may have great statistical properties, but are usually trivially predictable to someone who knows the algorithm, given a small sample of their output. An LFSR like prandom_u32() is particularly simple, even if the sample is widely scattered bits. It turns out the network stack uses prandom_u32() for some things like random port numbers which it would prefer are *not* trivially predictable. Predictability led to a practical DNS spoofing attack. Oops. This patch replaces the LFSR with a homebrew cryptographic PRNG based on the SipHash round function, which is in turn seeded with 128 bits of strong random key. (The authors of SipHash have *not* been consulted about this abuse of their algorithm.) Speed is prioritized over security; attacks are rare, while performance is always wanted. Replacing all callers of prandom_u32() is the quick fix. Whether to reinstate a weaker PRNG for uses which can tolerate it is an open question. Commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity") was an earlier attempt at a solution. This patch replaces it. Reported-by: Amit Klein Cc: Willy Tarreau Cc: Eric Dumazet Cc: "Jason A. Donenfeld" Cc: Andy Lutomirski Cc: Kees Cook Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Linus Torvalds Cc: tytso@mit.edu Cc: Florian Westphal Cc: Marc Plumb Fixes: f227e3ec3b5c ("random32: update the net random state on interrupt and activity") Signed-off-by: George Spelvin Link: https://lore.kernel.org/netdev/20200808152628.GA27941@SDF.ORG/ [ willy: partial reversal of f227e3ec3b5c; moved SIPROUND definitions to prandom.h for later use; merged George's prandom_seed() proposal; inlined siprand_u32(); replaced the net_rand_state[] array with 4 members to fix a build issue; cosmetic cleanups to make checkpatch happy; fixed RANDOM32_SELFTEST build ] Signed-off-by: Willy Tarreau --- include/linux/prandom.h | 36 ++++++++++++++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index aa16e6468f91..cc1e71334e53 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -16,12 +16,44 @@ void prandom_bytes(void *buf, size_t nbytes); void prandom_seed(u32 seed); void prandom_reseed_late(void); +#if BITS_PER_LONG == 64 +/* + * The core SipHash round function. Each line can be executed in + * parallel given enough CPU resources. + */ +#define PRND_SIPROUND(v0, v1, v2, v3) ( \ + v0 += v1, v1 = rol64(v1, 13), v2 += v3, v3 = rol64(v3, 16), \ + v1 ^= v0, v0 = rol64(v0, 32), v3 ^= v2, \ + v0 += v3, v3 = rol64(v3, 21), v2 += v1, v1 = rol64(v1, 17), \ + v3 ^= v0, v1 ^= v2, v2 = rol64(v2, 32) \ +) + +#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261) +#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573) + +#elif BITS_PER_LONG == 32 +/* + * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash. + * This is weaker, but 32-bit machines are not used for high-traffic + * applications, so there is less output for an attacker to analyze. + */ +#define PRND_SIPROUND(v0, v1, v2, v3) ( \ + v0 += v1, v1 = rol32(v1, 5), v2 += v3, v3 = rol32(v3, 8), \ + v1 ^= v0, v0 = rol32(v0, 16), v3 ^= v2, \ + v0 += v3, v3 = rol32(v3, 7), v2 += v1, v1 = rol32(v1, 13), \ + v3 ^= v0, v1 ^= v2, v2 = rol32(v2, 16) \ +) +#define PRND_K0 0x6c796765 +#define PRND_K1 0x74656462 + +#else +#error Unsupported BITS_PER_LONG +#endif + struct rnd_state { __u32 s1, s2, s3, s4; }; -DECLARE_PER_CPU(struct rnd_state, net_rand_state); - u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); -- cgit v1.2.3 From 3744741adab6d9195551ce30e65e726c7a408421 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 10 Aug 2020 10:27:42 +0200 Subject: random32: add noise from network and scheduling activity With the removal of the interrupt perturbations in previous random32 change (random32: make prandom_u32() output unpredictable), the PRNG has become 100% deterministic again. While SipHash is expected to be way more robust against brute force than the previous Tausworthe LFSR, there's still the risk that whoever has even one temporary access to the PRNG's internal state is able to predict all subsequent draws till the next reseed (roughly every minute). This may happen through a side channel attack or any data leak. This patch restores the spirit of commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity") in that it will perturb the internal PRNG's statee using externally collected noise, except that it will not pick that noise from the random pool's bits nor upon interrupt, but will rather combine a few elements along the Tx path that are collectively hard to predict, such as dev, skb and txq pointers, packet length and jiffies values. These ones are combined using a single round of SipHash into a single long variable that is mixed with the net_rand_state upon each invocation. The operation was inlined because it produces very small and efficient code, typically 3 xor, 2 add and 2 rol. The performance was measured to be the same (even very slightly better) than before the switch to SipHash; on a 6-core 12-thread Core i7-8700k equipped with a 40G NIC (i40e), the connection rate dropped from 556k/s to 555k/s while the SYN cookie rate grew from 5.38 Mpps to 5.45 Mpps. Link: https://lore.kernel.org/netdev/20200808152628.GA27941@SDF.ORG/ Cc: George Spelvin Cc: Amit Klein Cc: Eric Dumazet Cc: "Jason A. Donenfeld" Cc: Andy Lutomirski Cc: Kees Cook Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Linus Torvalds Cc: tytso@mit.edu Cc: Florian Westphal Cc: Marc Plumb Tested-by: Sedat Dilek Signed-off-by: Willy Tarreau --- include/linux/prandom.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index cc1e71334e53..bbf4b4ad61df 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -16,6 +16,12 @@ void prandom_bytes(void *buf, size_t nbytes); void prandom_seed(u32 seed); void prandom_reseed_late(void); +DECLARE_PER_CPU(unsigned long, net_rand_noise); + +#define PRANDOM_ADD_NOISE(a, b, c, d) \ + prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \ + (unsigned long)(c), (unsigned long)(d)) + #if BITS_PER_LONG == 64 /* * The core SipHash round function. Each line can be executed in @@ -50,6 +56,18 @@ void prandom_reseed_late(void); #error Unsupported BITS_PER_LONG #endif +static inline void prandom_u32_add_noise(unsigned long a, unsigned long b, + unsigned long c, unsigned long d) +{ + /* + * This is not used cryptographically; it's just + * a convenient 4-word hash function. (3 xor, 2 add, 2 rol) + */ + a ^= raw_cpu_read(net_rand_noise); + PRND_SIPROUND(a, b, c, d); + raw_cpu_write(net_rand_noise, d); +} + struct rnd_state { __u32 s1, s2, s3, s4; }; @@ -99,6 +117,7 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); + PRANDOM_ADD_NOISE(state, i, 0, 0); } /* Pseudo random number generator from numerical recipes. */ -- cgit v1.2.3 From 23224e45004ed84c8466fd1e8e5860f541187029 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 23 Oct 2020 16:27:16 -0700 Subject: mm: remove kzfree() compatibility definition Commit 453431a54934 ("mm, treewide: rename kzfree() to kfree_sensitive()") renamed kzfree() to kfree_sensitive(), but it left a compatibility definition of kzfree() to avoid being too disruptive. Since then a few more instances of kzfree() have slipped in. Just get rid of them and remove the compatibility definition once and for all. Signed-off-by: Eric Biggers Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 9e155cc83b8a..dd6897f62010 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -187,8 +187,6 @@ void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); -#define kzfree(x) kfree_sensitive(x) /* For backward compatibility */ - #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user); -- cgit v1.2.3 From 33def8498fdde180023444b08e12b72a9efed41d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 21 Oct 2020 19:36:07 -0700 Subject: treewide: Convert macro and uses of __section(foo) to __section("foo") Use a more generic form for __section that requires quotes to avoid complications with clang and gcc differences. Remove the quote operator # from compiler_attributes.h __section macro. Convert all unquoted __section(foo) uses to quoted __section("foo"). Also convert __attribute__((section("foo"))) uses to __section("foo") even if the __attribute__ has multiple list entry forms. Conversion done using the script at: https://lore.kernel.org/lkml/75393e5ddc272dc7403de74d645e6c6e0f4e70eb.camel@perches.com/2-convert_section.pl Signed-off-by: Joe Perches Reviewed-by: Nick Desaulniers Reviewed-by: Miguel Ojeda Signed-off-by: Linus Torvalds --- include/asm-generic/bug.h | 6 +++--- include/asm-generic/error-injection.h | 2 +- include/asm-generic/kprobes.h | 4 ++-- include/kunit/test.h | 2 +- include/linux/acpi.h | 4 ++-- include/linux/cache.h | 2 +- include/linux/compiler.h | 8 ++++---- include/linux/compiler_attributes.h | 2 +- include/linux/cpu.h | 2 +- include/linux/dynamic_debug.h | 2 +- include/linux/export.h | 2 +- include/linux/firmware.h | 2 +- include/linux/init.h | 34 +++++++++++++++++----------------- include/linux/init_task.h | 4 ++-- include/linux/interrupt.h | 4 ++-- include/linux/kernel.h | 6 +++--- include/linux/linkage.h | 4 ++-- include/linux/lsm_hooks.h | 4 ++-- include/linux/module.h | 2 +- include/linux/moduleparam.h | 4 ++-- include/linux/mtd/xip.h | 2 +- include/linux/objtool.h | 2 +- include/linux/of.h | 2 +- include/linux/percpu-defs.h | 2 +- include/linux/printk.h | 4 ++-- include/linux/rcupdate.h | 2 +- include/linux/sched/debug.h | 2 +- include/linux/serial_core.h | 2 +- include/linux/spinlock.h | 2 +- include/linux/syscalls.h | 6 +++--- include/linux/trace_events.h | 2 +- include/linux/tracepoint.h | 8 ++++---- include/trace/bpf_probe.h | 2 +- include/trace/trace_events.h | 10 +++++----- 34 files changed, 74 insertions(+), 74 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 18b0f4eee8cb..76a10e0dca9f 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -141,7 +141,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, #ifndef WARN_ON_ONCE #define WARN_ON_ONCE(condition) ({ \ - static bool __section(.data.once) __warned; \ + static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(condition); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ @@ -153,7 +153,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, #endif #define WARN_ONCE(condition, format...) ({ \ - static bool __section(.data.once) __warned; \ + static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(condition); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ @@ -164,7 +164,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, }) #define WARN_TAINT_ONCE(condition, taint, format...) ({ \ - static bool __section(.data.once) __warned; \ + static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(condition); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h index 80ca61058dd2..7ddd9dc10ce9 100644 --- a/include/asm-generic/error-injection.h +++ b/include/asm-generic/error-injection.h @@ -25,7 +25,7 @@ struct pt_regs; */ #define ALLOW_ERROR_INJECTION(fname, _etype) \ static struct error_injection_entry __used \ - __attribute__((__section__("_error_injection_whitelist"))) \ + __section("_error_injection_whitelist") \ _eil_addr_##fname = { \ .addr = (unsigned long)fname, \ .etype = EI_ETYPE_##_etype, \ diff --git a/include/asm-generic/kprobes.h b/include/asm-generic/kprobes.h index 4a982089c95c..060eab094e5a 100644 --- a/include/asm-generic/kprobes.h +++ b/include/asm-generic/kprobes.h @@ -10,11 +10,11 @@ */ # define __NOKPROBE_SYMBOL(fname) \ static unsigned long __used \ - __attribute__((__section__("_kprobe_blacklist"))) \ + __section("_kprobe_blacklist") \ _kbl_addr_##fname = (unsigned long)fname; # define NOKPROBE_SYMBOL(fname) __NOKPROBE_SYMBOL(fname) /* Use this to forbid a kprobes attach on very low level functions */ -# define __kprobes __attribute__((__section__(".kprobes.text"))) +# define __kprobes __section(".kprobes.text") # define nokprobe_inline __always_inline #else # define NOKPROBE_SYMBOL(fname) diff --git a/include/kunit/test.h b/include/kunit/test.h index a423fffefea0..9197da792336 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -288,7 +288,7 @@ static inline int kunit_run_all_tests(void) static struct kunit_suite *unique_array[] = { __VA_ARGS__, NULL }; \ kunit_test_suites_for_module(unique_array); \ static struct kunit_suite **unique_suites \ - __used __section(.kunit_test_suites) = unique_array + __used __section(".kunit_test_suites") = unique_array /** * kunit_test_suites() - used to register one or more &struct kunit_suite diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 143c6ffce2db..39263c6b52e1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1153,7 +1153,7 @@ struct acpi_probe_entry { #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ - __used __section(__##table##_acpi_probe_table) = { \ + __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ @@ -1164,7 +1164,7 @@ struct acpi_probe_entry { #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ subtable, valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ - __used __section(__##table##_acpi_probe_table) = { \ + __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ diff --git a/include/linux/cache.h b/include/linux/cache.h index 1aa8009f6d06..d742c57eaee5 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -34,7 +34,7 @@ * but may get written to during init, so can't live in .rodata (via "const"). */ #ifndef __ro_after_init -#define __ro_after_init __attribute__((__section__(".data..ro_after_init"))) +#define __ro_after_init __section(".data..ro_after_init") #endif #ifndef ____cacheline_aligned diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ac45f6d40d39..e512f5505dad 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -24,7 +24,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, long ______r; \ static struct ftrace_likely_data \ __aligned(4) \ - __section(_ftrace_annotated_branch) \ + __section("_ftrace_annotated_branch") \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -60,7 +60,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __trace_if_value(cond) ({ \ static struct ftrace_branch_data \ __aligned(4) \ - __section(_ftrace_branch) \ + __section("_ftrace_branch") \ __if_trace = { \ .func = __func__, \ .file = __FILE__, \ @@ -118,7 +118,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, ".popsection\n\t" /* Annotate a C jump table to allow objtool to follow the code flow */ -#define __annotate_jump_table __section(.rodata..c_jump_table) +#define __annotate_jump_table __section(".rodata..c_jump_table") #else #define annotate_reachable() @@ -206,7 +206,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __section(.discard.addressable) __used \ + static void * __section(".discard.addressable") __used \ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym; /** diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index ea7b756b1c8f..b2a3f4f641a7 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -254,7 +254,7 @@ * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate */ -#define __section(S) __attribute__((__section__(#S))) +#define __section(section) __attribute__((__section__(section))) /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 8aa84c052fdf..d6428aaf67e7 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -173,7 +173,7 @@ void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); /* Attach to any functions which should be considered cpuidle. */ -#define __cpuidle __attribute__((__section__(".cpuidle.text"))) +#define __cpuidle __section(".cpuidle.text") bool cpu_in_idle(unsigned long pc); diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 8aa0c7c2608c..a57ee75342cf 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -84,7 +84,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, #define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ static struct _ddebug __aligned(8) \ - __section(__dyndbg) name = { \ + __section("__dyndbg") name = { \ .modname = KBUILD_MODNAME, \ .function = __func__, \ .filename = __FILE__, \ diff --git a/include/linux/export.h b/include/linux/export.h index 8933ff6ad23a..fceb5e855717 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -130,7 +130,7 @@ struct kernel_symbol { * discarded in the final link stage. */ #define __ksym_marker(sym) \ - static int __ksym_marker_##sym[0] __section(.discard.ksym) __used + static int __ksym_marker_##sym[0] __section(".discard.ksym") __used #define __EXPORT_SYMBOL(sym, sec, ns) \ __ksym_marker(sym); \ diff --git a/include/linux/firmware.h b/include/linux/firmware.h index c15acadc6cf4..84e346ae766e 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -36,7 +36,7 @@ struct builtin_fw { #define DECLARE_BUILTIN_FIRMWARE_SIZE(name, blob, size) \ static const struct builtin_fw __fw_concat(__builtin_fw,__COUNTER__) \ - __used __section(.builtin_fw) = { name, blob, size } + __used __section(".builtin_fw") = { name, blob, size } #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE)) int request_firmware(const struct firmware **fw, const char *name, diff --git a/include/linux/init.h b/include/linux/init.h index 212fc9e2f691..7b53cb3092ee 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -47,11 +47,11 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __latent_entropy __noinitretpoline -#define __initdata __section(.init.data) -#define __initconst __section(.init.rodata) -#define __exitdata __section(.exit.data) -#define __exit_call __used __section(.exitcall.exit) +#define __init __section(".init.text") __cold __latent_entropy __noinitretpoline +#define __initdata __section(".init.data") +#define __initconst __section(".init.rodata") +#define __exitdata __section(".exit.data") +#define __exit_call __used __section(".exitcall.exit") /* * modpost check for section mismatches during the kernel build. @@ -70,9 +70,9 @@ * * The markers follow same syntax rules as __init / __initdata. */ -#define __ref __section(.ref.text) noinline -#define __refdata __section(.ref.data) -#define __refconst __section(.ref.rodata) +#define __ref __section(".ref.text") noinline +#define __refdata __section(".ref.data") +#define __refconst __section(".ref.rodata") #ifdef MODULE #define __exitused @@ -80,16 +80,16 @@ #define __exitused __used #endif -#define __exit __section(.exit.text) __exitused __cold notrace +#define __exit __section(".exit.text") __exitused __cold notrace /* Used for MEMORY_HOTPLUG */ -#define __meminit __section(.meminit.text) __cold notrace \ +#define __meminit __section(".meminit.text") __cold notrace \ __latent_entropy -#define __meminitdata __section(.meminit.data) -#define __meminitconst __section(.meminit.rodata) -#define __memexit __section(.memexit.text) __exitused __cold notrace -#define __memexitdata __section(.memexit.data) -#define __memexitconst __section(.memexit.rodata) +#define __meminitdata __section(".meminit.data") +#define __meminitconst __section(".meminit.rodata") +#define __memexit __section(".memexit.text") __exitused __cold notrace +#define __memexitdata __section(".memexit.data") +#define __memexitconst __section(".memexit.rodata") /* For assembly routines */ #define __HEAD .section ".head.text","ax" @@ -254,7 +254,7 @@ struct obs_kernel_param { static const char __setup_str_##unique_id[] __initconst \ __aligned(1) = str; \ static struct obs_kernel_param __setup_##unique_id \ - __used __section(.init.setup) \ + __used __section(".init.setup") \ __attribute__((aligned((sizeof(long))))) \ = { __setup_str_##unique_id, fn, early } @@ -298,7 +298,7 @@ void __init parse_early_options(char *cmdline); #endif /* Data marked not to be saved by software suspend */ -#define __nosavedata __section(.data..nosave) +#define __nosavedata __section(".data..nosave") #ifdef MODULE #define __exit_p(x) x diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 2c620d7ac432..b2412b4d4c20 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -40,12 +40,12 @@ extern struct cred init_cred; /* Attach to the init_task data structure for proper alignment */ #ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK -#define __init_task_data __attribute__((__section__(".data..init_task"))) +#define __init_task_data __section(".data..init_task") #else #define __init_task_data /**/ #endif /* Attach to the thread_info data structure for proper alignment */ -#define __init_thread_info __attribute__((__section__(".data..init_thread_info"))) +#define __init_thread_info __section(".data..init_thread_info") #endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f9aee3538461..ee8299eb1f52 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -792,9 +792,9 @@ extern int arch_early_irq_init(void); * We want to know which function is an entrypoint of a hardirq or a softirq. */ #ifndef __irq_entry -# define __irq_entry __attribute__((__section__(".irqentry.text"))) +# define __irq_entry __section(".irqentry.text") #endif -#define __softirq_entry __attribute__((__section__(".softirqentry.text"))) +#define __softirq_entry __section(".softirqentry.text") #endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index c629215fdad9..2f05e9128201 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -729,7 +729,7 @@ do { \ #define do_trace_printk(fmt, args...) \ do { \ static const char *trace_printk_fmt __used \ - __attribute__((section("__trace_printk_fmt"))) = \ + __section("__trace_printk_fmt") = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ __trace_printk_check_format(fmt, ##args); \ @@ -773,7 +773,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); #define trace_puts(str) ({ \ static const char *trace_printk_fmt __used \ - __attribute__((section("__trace_printk_fmt"))) = \ + __section("__trace_printk_fmt") = \ __builtin_constant_p(str) ? str : NULL; \ \ if (__builtin_constant_p(str)) \ @@ -795,7 +795,7 @@ extern void trace_dump_stack(int skip); do { \ if (__builtin_constant_p(fmt)) { \ static const char *trace_printk_fmt __used \ - __attribute__((section("__trace_printk_fmt"))) = \ + __section("__trace_printk_fmt") = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ __ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \ diff --git a/include/linux/linkage.h b/include/linux/linkage.h index d796ec20d114..5bcfbd972e97 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -36,8 +36,8 @@ __stringify(name)) #endif -#define __page_aligned_data __section(.data..page_aligned) __aligned(PAGE_SIZE) -#define __page_aligned_bss __section(.bss..page_aligned) __aligned(PAGE_SIZE) +#define __page_aligned_data __section(".data..page_aligned") __aligned(PAGE_SIZE) +#define __page_aligned_bss __section(".bss..page_aligned") __aligned(PAGE_SIZE) /* * For assembly routines. diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 8814e3d5952d..c503f7ab8afb 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1611,12 +1611,12 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; #define DEFINE_LSM(lsm) \ static struct lsm_info __lsm_##lsm \ - __used __section(.lsm_info.init) \ + __used __section(".lsm_info.init") \ __aligned(sizeof(unsigned long)) #define DEFINE_EARLY_LSM(lsm) \ static struct lsm_info __early_lsm_##lsm \ - __used __section(.early_lsm_info.init) \ + __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) #ifdef CONFIG_SECURITY_SELINUX_DISABLE diff --git a/include/linux/module.h b/include/linux/module.h index a29187f7c360..7ccdf87f376f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -278,7 +278,7 @@ extern typeof(name) __mod_##type##__##name##_device_table \ .version = _version, \ }; \ static const struct module_version_attribute \ - __used __attribute__ ((__section__ ("__modver"))) \ + __used __section("__modver") \ * __moduleparam_const __modver_attr = &___modver_attr #endif diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 47879fc7f75e..6388eb9734a5 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -22,7 +22,7 @@ #define __MODULE_INFO(tag, name, info) \ static const char __UNIQUE_ID(name)[] \ - __used __attribute__((section(".modinfo"), unused, aligned(1))) \ + __used __section(".modinfo") __attribute__((unused, aligned(1))) \ = __MODULE_INFO_PREFIX __stringify(tag) "=" info #define __MODULE_PARM_TYPE(name, _type) \ @@ -289,7 +289,7 @@ struct kparam_array static const char __param_str_##name[] = prefix #name; \ static struct kernel_param __moduleparam_const __param_##name \ __used \ - __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \ + __section("__param") __attribute__ ((unused, aligned(sizeof(void *)))) \ = { __param_str_##name, THIS_MODULE, ops, \ VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } } diff --git a/include/linux/mtd/xip.h b/include/linux/mtd/xip.h index a4e352b1dfe6..3cac9360588f 100644 --- a/include/linux/mtd/xip.h +++ b/include/linux/mtd/xip.h @@ -28,7 +28,7 @@ * those functions so they get relocated to ram. */ #ifdef CONFIG_XIP_KERNEL -#define __xipram noinline __attribute__ ((__section__ (".xiptext"))) +#define __xipram noinline __section(".xiptext") #endif /* diff --git a/include/linux/objtool.h b/include/linux/objtool.h index ab82c793c897..577f51436cf9 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -60,7 +60,7 @@ struct unwind_hint { * For more information, see tools/objtool/Documentation/stack-validation.txt. */ #define STACK_FRAME_NON_STANDARD(func) \ - static void __used __section(.discard.func_stack_frame_non_standard) \ + static void __used __section(".discard.func_stack_frame_non_standard") \ *__func_stack_frame_non_standard_##func = func #else /* __ASSEMBLY__ */ diff --git a/include/linux/of.h b/include/linux/of.h index 481ec0467285..5d51891cbf1a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1299,7 +1299,7 @@ static inline int of_get_available_child_count(const struct device_node *np) #if defined(CONFIG_OF) && !defined(MODULE) #define _OF_DECLARE(table, name, compat, fn, fn_type) \ static const struct of_device_id __of_table_##name \ - __used __section(__##table##_of_table) \ + __used __section("__" #table "_of_table") \ = { .compatible = compat, \ .data = (fn == (fn_type)NULL) ? fn : fn } #else diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 176bfbd52d97..dff7040f629a 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -51,7 +51,7 @@ PER_CPU_ATTRIBUTES #define __PCPU_DUMMY_ATTRS \ - __attribute__((section(".discard"), unused)) + __section(".discard") __attribute__((unused)) /* * s390 and alpha modules require percpu variables to be defined as diff --git a/include/linux/printk.h b/include/linux/printk.h index 78479633ccfc..fe7eb2351610 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -437,7 +437,7 @@ extern int kptr_restrict; #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ ({ \ - static bool __section(.data.once) __print_once; \ + static bool __section(".data.once") __print_once; \ bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ @@ -448,7 +448,7 @@ extern int kptr_restrict; }) #define printk_deferred_once(fmt, ...) \ ({ \ - static bool __section(.data.once) __print_once; \ + static bool __section(".data.once") __print_once; \ bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 7c1ceff02852..6cdd0152c253 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -299,7 +299,7 @@ static inline int rcu_read_lock_any_held(void) */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ - static bool __section(.data.unlikely) __warned; \ + static bool __section(".data.unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && !__warned && (c)) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index 00c45a0e6abe..ae51f4529fc9 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -43,7 +43,7 @@ extern void proc_sched_set_task(struct task_struct *p); #endif /* Attach to any functions which should be ignored in wchan output. */ -#define __sched __attribute__((__section__(".sched.text"))) +#define __sched __section(".sched.text") /* Linker adds these: start and end of __sched functions */ extern char __sched_text_start[], __sched_text_end[]; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 8a99279a579b..ff63c2963359 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -373,7 +373,7 @@ extern const struct earlycon_id *__earlycon_table_end[]; .compatible = compat, \ .setup = fn }; \ static const struct earlycon_id EARLYCON_USED_OR_UNUSED \ - __section(__earlycon_table) \ + __section("__earlycon_table") \ * const __PASTE(__p, unique_id) = &unique_id #define OF_EARLYCON_DECLARE(_name, compat, fn) \ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index f2f12d746dbd..79897841a2cc 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -76,7 +76,7 @@ #define LOCK_SECTION_END \ ".previous\n\t" -#define __lockfunc __attribute__((section(".spinlock.text"))) +#define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2eda7678fe1d..37bea07c12f2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -144,7 +144,7 @@ extern struct trace_event_functions exit_syscall_print_funcs; .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ static struct trace_event_call __used \ - __attribute__((section("_ftrace_events"))) \ + __section("_ftrace_events") \ *__event_enter_##sname = &event_enter_##sname; #define SYSCALL_TRACE_EXIT_EVENT(sname) \ @@ -160,7 +160,7 @@ extern struct trace_event_functions exit_syscall_print_funcs; .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ static struct trace_event_call __used \ - __attribute__((section("_ftrace_events"))) \ + __section("_ftrace_events") \ *__event_exit_##sname = &event_exit_##sname; #define SYSCALL_METADATA(sname, nb, ...) \ @@ -184,7 +184,7 @@ extern struct trace_event_functions exit_syscall_print_funcs; .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ }; \ static struct syscall_metadata __used \ - __attribute__((section("__syscalls_metadata"))) \ + __section("__syscalls_metadata") \ *__p_syscall_meta_##sname = &__syscall_meta_##sname; static inline int is_syscall_trace_event(struct trace_event_call *tp_event) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 5c6943354049..d321fe5ad1a1 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -709,7 +709,7 @@ do { \ tracing_record_cmdline(current); \ if (__builtin_constant_p(fmt)) { \ static const char *trace_printk_fmt \ - __attribute__((section("__trace_printk_fmt"))) = \ + __section("__trace_printk_fmt") = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ __trace_bprintk(ip, trace_printk_fmt, ##args); \ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 81fa0b2f271e..0f21617f1a66 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -119,7 +119,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define __TRACEPOINT_ENTRY(name) \ static tracepoint_ptr_t __tracepoint_ptr_##name __used \ - __section(__tracepoints_ptrs) = &__tracepoint_##name + __section("__tracepoints_ptrs") = &__tracepoint_##name #endif #endif /* _LINUX_TRACEPOINT_H */ @@ -286,11 +286,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) */ #define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args) \ static const char __tpstrtab_##_name[] \ - __section(__tracepoints_strings) = #_name; \ + __section("__tracepoints_strings") = #_name; \ extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name); \ int __traceiter_##_name(void *__data, proto); \ struct tracepoint __tracepoint_##_name __used \ - __section(__tracepoints) = { \ + __section("__tracepoints") = { \ .name = __tpstrtab_##_name, \ .key = STATIC_KEY_INIT_FALSE, \ .static_call_key = &STATIC_CALL_KEY(tp_func_##_name), \ @@ -396,7 +396,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static const char *___tp_str __tracepoint_string = str; \ ___tp_str; \ }) -#define __tracepoint_string __used __section(__tracepoint_str) +#define __tracepoint_string __used __section("__tracepoint_str") #else /* * tracepoint_string() is used to save the string address for userspace diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index 1ce3be63add1..cd74bffed5c6 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -79,7 +79,7 @@ static union { \ struct bpf_raw_event_map event; \ btf_trace_##call handler; \ } __bpf_trace_tp_map_##call __used \ -__attribute__((section("__bpf_raw_tp_map"))) = { \ +__section("__bpf_raw_tp_map") = { \ .event = { \ .tp = &__tracepoint_##call, \ .bpf_func = __bpf_trace_##template, \ diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 1bc3e7bba9a4..7785961d82ba 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -45,7 +45,7 @@ TRACE_MAKE_SYSTEM_STR(); .eval_value = a \ }; \ static struct trace_eval_map __used \ - __attribute__((section("_ftrace_eval_map"))) \ + __section("_ftrace_eval_map") \ *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a #undef TRACE_DEFINE_SIZEOF @@ -58,7 +58,7 @@ TRACE_MAKE_SYSTEM_STR(); .eval_value = sizeof(a) \ }; \ static struct trace_eval_map __used \ - __attribute__((section("_ftrace_eval_map"))) \ + __section("_ftrace_eval_map") \ *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a /* @@ -607,7 +607,7 @@ static inline notrace int trace_event_get_offsets_##call( \ * // its only safe to use pointers when doing linker tricks to * // create an array. * static struct trace_event_call __used - * __attribute__((section("_ftrace_events"))) *__event_ = &event_; + * __section("_ftrace_events") *__event_ = &event_; * */ @@ -755,7 +755,7 @@ static struct trace_event_call __used event_##call = { \ .flags = TRACE_EVENT_FL_TRACEPOINT, \ }; \ static struct trace_event_call __used \ -__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call +__section("_ftrace_events") *__event_##call = &event_##call #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, call, proto, args, print) \ @@ -772,6 +772,6 @@ static struct trace_event_call __used event_##call = { \ .flags = TRACE_EVENT_FL_TRACEPOINT, \ }; \ static struct trace_event_call __used \ -__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call +__section("_ftrace_events") *__event_##call = &event_##call #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -- cgit v1.2.3 From 58b24a38f0deac253ba9c5be128e3da6a86041ad Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 29 Jul 2019 14:26:15 +0200 Subject: gpu: ipu-v3: remove unused functions ipu_mbus_code_to_colorspace, ipu_stride_to_bytes, and ipu_pixelformat_is_planar are unused. Remove them. Signed-off-by: Philipp Zabel Reviewed-by: Sam Ravnborg --- include/video/imx-ipu-v3.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index 06b0b57e996c..d1b3889f74d8 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -484,9 +484,6 @@ int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level); enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc); enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat); -enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code); -int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat); -bool ipu_pixelformat_is_planar(u32 pixelformat); int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees, bool hflip, bool vflip); int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode, -- cgit v1.2.3 From cb47755725da7b90fecbb2aa82ac3b24a7adb89b Mon Sep 17 00:00:00 2001 From: Zeng Tao Date: Tue, 1 Sep 2020 17:30:13 +0800 Subject: time: Prevent undefined behaviour in timespec64_to_ns() UBSAN reports: Undefined behaviour in ./include/linux/time64.h:127:27 signed integer overflow: 17179869187 * 1000000000 cannot be represented in type 'long long int' Call Trace: timespec64_to_ns include/linux/time64.h:127 [inline] set_cpu_itimer+0x65c/0x880 kernel/time/itimer.c:180 do_setitimer+0x8e/0x740 kernel/time/itimer.c:245 __x64_sys_setitimer+0x14c/0x2c0 kernel/time/itimer.c:336 do_syscall_64+0xa1/0x540 arch/x86/entry/common.c:295 Commit bd40a175769d ("y2038: itimer: change implementation to timespec64") replaced the original conversion which handled time clamping correctly with timespec64_to_ns() which has no overflow protection. Fix it in timespec64_to_ns() as this is not necessarily limited to the usage in itimers. [ tglx: Added comment and adjusted the fixes tag ] Fixes: 361a3bf00582 ("time64: Add time64.h header and define struct timespec64") Signed-off-by: Zeng Tao Signed-off-by: Thomas Gleixner Reviewed-by: Arnd Bergmann Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1598952616-6416-1-git-send-email-prime.zeng@hisilicon.com --- include/linux/time64.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/time64.h b/include/linux/time64.h index c9dcb3e5781f..5117cb5b5656 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -124,6 +124,10 @@ static inline bool timespec64_valid_settod(const struct timespec64 *ts) */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { + /* Prevent multiplication overflow */ + if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + return KTIME_MAX; + return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } -- cgit v1.2.3 From f7b6603c666798a1f8379e692d11d500885f32d8 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 23 Oct 2020 18:33:35 +0200 Subject: ALSA: fix kernel-doc markups Kernel-doc markups should use this format: identifier - description There is a common comment marked, instead, with kernel-doc notation. Some identifiers have different names between their prototypes and the kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Acked-by: Mark Brown Link: https://lore.kernel.org/r/535182d6f55d7a7de293dda9676df68f5f60afc6.1603469755.git.mchehab+huawei@kernel.org Signed-off-by: Takashi Iwai --- include/sound/core.h | 3 ++- include/sound/pcm.h | 4 ++-- include/uapi/sound/compress_offload.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/sound/core.h b/include/sound/core.h index 381a010a1bd4..0462c577d7a3 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -332,7 +332,8 @@ void __snd_printk(unsigned int level, const char *file, int line, #define snd_BUG() WARN(1, "BUG?\n") /** - * Suppress high rates of output when CONFIG_SND_DEBUG is enabled. + * snd_printd_ratelimit - Suppress high rates of output when + * CONFIG_SND_DEBUG is enabled. */ #define snd_printd_ratelimit() printk_ratelimit() diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 2ba5df2c9e23..2336bf9243e1 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1284,8 +1284,8 @@ snd_pcm_sgbuf_get_ptr(struct snd_pcm_substream *substream, unsigned int ofs) } /** - * snd_pcm_sgbuf_chunk_size - Compute the max size that fits within the contig. - * page from the given size + * snd_pcm_sgbuf_get_chunk_size - Compute the max size that fits within the + * contig. page from the given size * @substream: PCM substream * @ofs: byte offset * @size: byte size to examine diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h index 7184265c0b0d..9555f31c8425 100644 --- a/include/uapi/sound/compress_offload.h +++ b/include/uapi/sound/compress_offload.h @@ -144,7 +144,7 @@ struct snd_compr_metadata { __u32 value[8]; } __attribute__((packed, aligned(4))); -/** +/* * compress path ioctl definitions * SNDRV_COMPRESS_GET_CAPS: Query capability of DSP * SNDRV_COMPRESS_GET_CODEC_CAPS: Query capability of a codec -- cgit v1.2.3 From 7f32b10c6b461a369b9741623cd3f722134066f0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 21 Oct 2020 14:17:26 +0200 Subject: kunit: test: fix remaining kernel-doc warnings test.h still produce three warnings: include/kunit/test.h:282: warning: Function parameter or member '__suites' not described in 'kunit_test_suites_for_module' include/kunit/test.h:282: warning: Excess function parameter 'suites_list' description in 'kunit_test_suites_for_module' include/kunit/test.h:314: warning: Excess function parameter 'suites' description in 'kunit_test_suites' They're all due to errors at kernel-doc markups. Update them. It should be noticed that this patch moved a kernel-doc markup that were located at the wrong place, and using a wrong name. Kernel-doc only supports kaving the markup just before the function/macro declaration. Placing it elsewhere will make it do wrong assumptions. Fixes: aac35468ca20 ("kunit: test: create a single centralized executor for all tests") Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Brendan Higgins Tested-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 9197da792336..db1b0ae666c4 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -252,13 +252,14 @@ static inline int kunit_run_all_tests(void) } #endif /* IS_BUILTIN(CONFIG_KUNIT) */ +#ifdef MODULE /** - * kunit_test_suites() - used to register one or more &struct kunit_suite - * with KUnit. + * kunit_test_suites_for_module() - used to register one or more + * &struct kunit_suite with KUnit. * - * @suites_list...: a statically allocated list of &struct kunit_suite. + * @__suites: a statically allocated list of &struct kunit_suite. * - * Registers @suites_list with the test framework. See &struct kunit_suite for + * Registers @__suites with the test framework. See &struct kunit_suite for * more information. * * If a test suite is built-in, module_init() gets translated into @@ -267,7 +268,6 @@ static inline int kunit_run_all_tests(void) * module_{init|exit} functions for the builtin case when registering * suites via kunit_test_suites() below. */ -#ifdef MODULE #define kunit_test_suites_for_module(__suites) \ static int __init kunit_test_suites_init(void) \ { \ @@ -294,7 +294,7 @@ static inline int kunit_run_all_tests(void) * kunit_test_suites() - used to register one or more &struct kunit_suite * with KUnit. * - * @suites: a statically allocated list of &struct kunit_suite. + * @__suites: a statically allocated list of &struct kunit_suite. * * Registers @suites with the test framework. See &struct kunit_suite for * more information. @@ -308,10 +308,10 @@ static inline int kunit_run_all_tests(void) * module. * */ -#define kunit_test_suites(...) \ +#define kunit_test_suites(__suites...) \ __kunit_test_suites(__UNIQUE_ID(array), \ __UNIQUE_ID(suites), \ - __VA_ARGS__) + ##__suites) #define kunit_test_suite(suite) kunit_test_suites(&suite) -- cgit v1.2.3 From 2a6eca16f376f6b83aaf73c57f0b6547907a5ed3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 26 Oct 2020 17:52:18 +0100 Subject: ALSA: make snd_kcontrol_new name a normal string When building with W=2, there are lots of warnings about the snd_kcontrol_new name field being an array of 'unsigned char' but initialized to a string: include/sound/soc.h:93:48: warning: pointer targets in initialization of 'const unsigned char *' from 'char *' differ in signedness [-Wpointer-sign] Make it a regular 'char *' to avoid flooding the build log with this. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20201026165715.3723704-1-arnd@kernel.org Signed-off-by: Takashi Iwai --- include/sound/control.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/control.h b/include/sound/control.h index e128cff10dfa..77d9fa10812d 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -42,7 +42,7 @@ struct snd_kcontrol_new { snd_ctl_elem_iface_t iface; /* interface identifier */ unsigned int device; /* device/client number */ unsigned int subdevice; /* subdevice (substream) number */ - const unsigned char *name; /* ASCII name of item */ + const char *name; /* ASCII name of item */ unsigned int index; /* index of item */ unsigned int access; /* access rights */ unsigned int count; /* count of same elements */ -- cgit v1.2.3 From fbdd0049d98d44914fc57d4b91f867f4996c787b Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 26 Oct 2020 15:43:59 +0200 Subject: RDMA/mlx5: Fix devlink deadlock on net namespace deletion When a mlx5 core devlink instance is reloaded in different net namespace, its associated IB device is deleted and recreated. Example sequence is: $ ip netns add foo $ devlink dev reload pci/0000:00:08.0 netns foo $ ip netns del foo mlx5 IB device needs to attach and detach the netdevice to it through the netdev notifier chain during load and unload sequence. A below call graph of the unload flow. cleanup_net() down_read(&pernet_ops_rwsem); <- first sem acquired ops_pre_exit_list() pre_exit() devlink_pernet_pre_exit() devlink_reload() mlx5_devlink_reload_down() mlx5_unload_one() [...] mlx5_ib_remove() mlx5_ib_unbind_slave_port() mlx5_remove_netdev_notifier() unregister_netdevice_notifier() down_write(&pernet_ops_rwsem);<- recurrsive lock Hence, when net namespace is deleted, mlx5 reload results in deadlock. When deadlock occurs, devlink mutex is also held. This not only deadlocks the mlx5 device under reload, but all the processes which attempt to access unrelated devlink devices are deadlocked. Hence, fix this by mlx5 ib driver to register for per net netdev notifier instead of global one, which operats on the net namespace without holding the pernet_ops_rwsem. Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload") Link: https://lore.kernel.org/r/20201026134359.23150-1-parav@nvidia.com Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/driver.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index add85094f9a5..0f23e1ed5e71 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1213,4 +1213,22 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) return val.vbool; } +/** + * mlx5_core_net - Provide net namespace of the mlx5_core_dev + * @dev: mlx5 core device + * + * mlx5_core_net() returns the net namespace of mlx5 core device. + * This can be called only in below described limited context. + * (a) When a devlink instance for mlx5_core is registered and + * when devlink reload operation is disabled. + * or + * (b) during devlink reload reload_down() and reload_up callbacks + * where it is ensured that devlink instance's net namespace is + * stable. + */ +static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) +{ + return devlink_net(priv_to_devlink(dev)); +} + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From 08989335e2b6b549ab20dd41ba2f9ca9782f3cd8 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:28 +0100 Subject: drm: drm_edid: remove a duplicated kernel-doc declaration It is not possible to create cross-references for duplicated symbols. While Sphinx always detected it, on Sphinx 3 it generates warnings like this: .../Documentation/gpu/drm-kms-helpers:326: ../drivers/gpu/drm/drm_edid.c:1626: WARNING: Duplicate C declaration, also defined in 'gpu/drm-kms-helpers'. Declaration is 'bool drm_edid_are_equal (const struct edid *edid1, const struct edid *edid2)'. So, get rid of the duplicated kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/9310f4074fa9d29cd3ad60684d86d0ace8dab7ae.1603791716.git.mchehab+huawei@kernel.org --- include/drm/drm_edid.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index b27a0e2169c8..e97daf6ffbb1 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -359,13 +359,6 @@ drm_load_edid_firmware(struct drm_connector *connector) } #endif -/** - * drm_edid_are_equal - compare two edid blobs. - * @edid1: pointer to first blob - * @edid2: pointer to second blob - * This helper can be used during probing to determine if - * edid had changed. - */ bool drm_edid_are_equal(const struct edid *edid1, const struct edid *edid2); int -- cgit v1.2.3 From 38a8b32f467a9389ff413574968baa8777c77355 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:31 +0100 Subject: drm: kernel-doc: drm_dp_helper.h: fix a typo Right now, kernel-doc generates a warning: ./include/drm/drm_dp_helper.h:1786: warning: Function parameter or member 'hbr2_reset' not described in 'drm_dp_phy_test_params' This is due to a typo: @hb2_reset -> @hbr2_reset Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/2a615cb38e951215bb1bddc2481ad323c9cf3fc9.1603791716.git.mchehab+huawei@kernel.org --- include/drm/drm_dp_helper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index da53aebb7230..a53243abd945 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1836,7 +1836,7 @@ static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux) * @link_rate: Requested Link rate from DPCD 0x219 * @num_lanes: Number of lanes requested by sing through DPCD 0x220 * @phy_pattern: DP Phy test pattern from DPCD 0x248 - * @hb2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B + * @hbr2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B * @custom80: DP Test_80BIT_CUSTOM_PATTERN from DPCDs 0x250 through 0x259 * @enhanced_frame_cap: flag for enhanced frame capability. */ -- cgit v1.2.3 From b52817e9de06a3af4ebefd6d244c9c750903d79c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:35 +0100 Subject: drm: drm_print.h: fix kernel-doc markups A kernel-doc markup should start with the identifier on its first line. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/5b76c5625709aaaa3abee98faa620b9f3d27ff85.1603791716.git.mchehab+huawei@kernel.org --- include/drm/drm_print.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 1c9417430d08..f32d179e139d 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -338,7 +338,7 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, const char *format, ...); /** - * Error output. + * DRM_DEV_ERROR() - Error output. * * @dev: device pointer * @fmt: printf() like format string. @@ -347,10 +347,12 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, drm_dev_printk(dev, KERN_ERR, "*ERROR* " fmt, ##__VA_ARGS__) /** - * Rate limited error output. Like DRM_ERROR() but won't flood the log. + * DRM_DEV_ERROR_RATELIMITED() - Rate limited error output. * * @dev: device pointer * @fmt: printf() like format string. + * + * Like DRM_ERROR() but won't flood the log. */ #define DRM_DEV_ERROR_RATELIMITED(dev, fmt, ...) \ ({ \ @@ -375,15 +377,27 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, }) /** - * Debug output. + * DRM_DEV_DEBUG() - Debug output for generic drm code * * @dev: device pointer * @fmt: printf() like format string. */ #define DRM_DEV_DEBUG(dev, fmt, ...) \ drm_dev_dbg(dev, DRM_UT_CORE, fmt, ##__VA_ARGS__) +/** + * DRM_DEV_DEBUG_DRIVER() - Debug output for vendor specific part of the driver + * + * @dev: device pointer + * @fmt: printf() like format string. + */ #define DRM_DEV_DEBUG_DRIVER(dev, fmt, ...) \ drm_dev_dbg(dev, DRM_UT_DRIVER, fmt, ##__VA_ARGS__) +/** + * DRM_DEV_DEBUG_KMS() - Debug output for modesetting code + * + * @dev: device pointer + * @fmt: printf() like format string. + */ #define DRM_DEV_DEBUG_KMS(dev, fmt, ...) \ drm_dev_dbg(dev, DRM_UT_KMS, fmt, ##__VA_ARGS__) -- cgit v1.2.3 From 0bcd0a2be8c9ef39d84d167ff85359a49f7be175 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Oct 2020 09:50:17 +0100 Subject: asm-generic: mark __{get,put}_user_fn as __always_inline Without the explicit __always_inline, some RISC-V configs place the functions out of line, triggering the BUILD_BUG_ON checks in the function. Fixes: 11129e8ed4d9 ("riscv: use memcpy based uaccess for nommu again") Reported-by: kernel test robot Signed-off-by: Christoph Hellwig Signed-off-by: Arnd Bergmann --- include/asm-generic/uaccess.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 45f9872fd747..4973328f3c6e 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -12,7 +12,8 @@ #ifdef CONFIG_UACCESS_MEMCPY #include -static inline int __get_user_fn(size_t size, const void __user *from, void *to) +static __always_inline int +__get_user_fn(size_t size, const void __user *from, void *to) { BUILD_BUG_ON(!__builtin_constant_p(size)); @@ -37,7 +38,8 @@ static inline int __get_user_fn(size_t size, const void __user *from, void *to) } #define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k) -static inline int __put_user_fn(size_t size, void __user *to, void *from) +static __always_inline int +__put_user_fn(size_t size, void __user *to, void *from) { BUILD_BUG_ON(!__builtin_constant_p(size)); -- cgit v1.2.3 From 1c534352f47fd83eb08075ac2474f707e74bf7f7 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 23 Oct 2020 17:35:19 +0200 Subject: cpufreq: Introduce CPUFREQ_NEED_UPDATE_LIMITS driver flag Generally, a cpufreq driver may need to update some internal upper and lower frequency boundaries on policy max and min changes, respectively, but currently this does not work if the target frequency does not change along with the policy limit. Namely, if the target frequency does not change along with the policy min or max, the "target_freq == policy->cur" check in __cpufreq_driver_target() prevents driver callbacks from being invoked and they do not even have a chance to update the corresponding internal boundary. This particularly affects the "powersave" and "performance" governors that always set the target frequency to one of the policy limits and it never changes when the other limit is updated. To allow cpufreq the drivers needing to update internal frequency boundaries on policy limits changes to avoid this issue, introduce a new driver flag, CPUFREQ_NEED_UPDATE_LIMITS, that (when set) will neutralize the check mentioned above. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index fa37b1c66443..038ed83aab41 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -298,7 +298,7 @@ __ATTR(_name, 0644, show_##_name, store_##_name) struct cpufreq_driver { char name[CPUFREQ_NAME_LEN]; - u8 flags; + u16 flags; void *driver_data; /* needed by all drivers */ @@ -422,6 +422,14 @@ struct cpufreq_driver { */ #define CPUFREQ_IS_COOLING_DEV BIT(7) +/* + * Set by drivers that need to update internale upper and lower boundaries along + * with the target frequency and so the core and governors should also invoke + * the diver if the target frequency does not change, but the policy min or max + * may have changed. + */ +#define CPUFREQ_NEED_UPDATE_LIMITS BIT(8) + int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3 From 3e6631485fae70f474d5bd85cfaf0f113f61ccce Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sun, 4 Oct 2020 19:57:20 -0700 Subject: vmlinux.lds.h: Keep .ctors.* with .ctors Under some circumstances, the compiler generates .ctors.* sections. This is seen doing a cross compile of x86_64 from a powerpc64el host: x86_64-linux-gnu-ld: warning: orphan section `.ctors.65435' from `kernel/trace/trace_clock.o' being placed in section `.ctors.65435' x86_64-linux-gnu-ld: warning: orphan section `.ctors.65435' from `kernel/trace/ftrace.o' being placed in section `.ctors.65435' x86_64-linux-gnu-ld: warning: orphan section `.ctors.65435' from `kernel/trace/ring_buffer.o' being placed in section `.ctors.65435' Include these orphans along with the regular .ctors section. Reported-by: Stephen Rothwell Tested-by: Stephen Rothwell Fixes: 83109d5d5fba ("x86/build: Warn on orphan section placement") Signed-off-by: Kees Cook Acked-by: Nick Desaulniers Link: https://lore.kernel.org/r/20201005025720.2599682-1-keescook@chromium.org --- include/asm-generic/vmlinux.lds.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index cd14444bf600..b2b3d81b1535 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -701,6 +701,7 @@ #ifdef CONFIG_CONSTRUCTORS #define KERNEL_CTORS() . = ALIGN(8); \ __ctors_start = .; \ + KEEP(*(SORT(.ctors.*))) \ KEEP(*(.ctors)) \ KEEP(*(SORT(.init_array.*))) \ KEEP(*(.init_array)) \ -- cgit v1.2.3 From 1de111b51b829bcf01d2e57971f8fd07a665fa3f Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 23 Oct 2020 08:47:50 -0700 Subject: KVM: arm64: ARM_SMCCC_ARCH_WORKAROUND_1 doesn't return SMCCC_RET_NOT_REQUIRED According to the SMCCC spec[1](7.5.2 Discovery) the ARM_SMCCC_ARCH_WORKAROUND_1 function id only returns 0, 1, and SMCCC_RET_NOT_SUPPORTED. 0 is "workaround required and safe to call this function" 1 is "workaround not required but safe to call this function" SMCCC_RET_NOT_SUPPORTED is "might be vulnerable or might not be, who knows, I give up!" SMCCC_RET_NOT_SUPPORTED might as well mean "workaround required, except calling this function may not work because it isn't implemented in some cases". Wonderful. We map this SMC call to 0 is SPECTRE_MITIGATED 1 is SPECTRE_UNAFFECTED SMCCC_RET_NOT_SUPPORTED is SPECTRE_VULNERABLE For KVM hypercalls (hvc), we've implemented this function id to return SMCCC_RET_NOT_SUPPORTED, 0, and SMCCC_RET_NOT_REQUIRED. One of those isn't supposed to be there. Per the code we call arm64_get_spectre_v2_state() to figure out what to return for this feature discovery call. 0 is SPECTRE_MITIGATED SMCCC_RET_NOT_REQUIRED is SPECTRE_UNAFFECTED SMCCC_RET_NOT_SUPPORTED is SPECTRE_VULNERABLE Let's clean this up so that KVM tells the guest this mapping: 0 is SPECTRE_MITIGATED 1 is SPECTRE_UNAFFECTED SMCCC_RET_NOT_SUPPORTED is SPECTRE_VULNERABLE Note: SMCCC_RET_NOT_AFFECTED is 1 but isn't part of the SMCCC spec Fixes: c118bbb52743 ("arm64: KVM: Propagate full Spectre v2 workaround state to KVM guests") Signed-off-by: Stephen Boyd Acked-by: Marc Zyngier Acked-by: Will Deacon Cc: Andre Przywara Cc: Steven Price Cc: Marc Zyngier Cc: stable@vger.kernel.org Link: https://developer.arm.com/documentation/den0028/latest [1] Link: https://lore.kernel.org/r/20201023154751.1973872-1-swboyd@chromium.org Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 885c9ffc835c..f860645f6512 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -87,6 +87,8 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1 + /* Paravirtualised time calls (defined by ARM DEN0057A) */ #define ARM_SMCCC_HV_PV_TIME_FEATURES \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ -- cgit v1.2.3 From 071ba4cc559de47160761b9500b72e8fa09d923d Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 26 Oct 2020 11:25:49 -0300 Subject: RDMA: Add rdma_connect_locked() There are two flows for handling RDMA_CM_EVENT_ROUTE_RESOLVED, either the handler triggers a completion and another thread does rdma_connect() or the handler directly calls rdma_connect(). In all cases rdma_connect() needs to hold the handler_mutex, but when handler's are invoked this is already held by the core code. This causes ULPs using the 2nd method to deadlock. Provide a rdma_connect_locked() and have all ULPs call it from their handlers. Link: https://lore.kernel.org/r/0-v2-53c22d5c1405+33-rdma_connect_locking_jgg@nvidia.com Reported-and-tested-by: Guoqing Jiang Fixes: 2a7cec538169 ("RDMA/cma: Fix locking for the RDMA_CM_CONNECT state") Acked-by: Santosh Shilimkar Acked-by: Jack Wang Reviewed-by: Christoph Hellwig Reviewed-by: Max Gurtovoy Reviewed-by: Sagi Grimberg Signed-off-by: Jason Gunthorpe --- include/rdma/rdma_cm.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index c672ae1da26b..32a67af18415 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -227,19 +227,9 @@ void rdma_destroy_qp(struct rdma_cm_id *id); int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int *qp_attr_mask); -/** - * rdma_connect - Initiate an active connection request. - * @id: Connection identifier to connect. - * @conn_param: Connection information used for connected QPs. - * - * Users must have resolved a route for the rdma_cm_id to connect with - * by having called rdma_resolve_route before calling this routine. - * - * This call will either connect to a remote QP or obtain remote QP - * information for unconnected rdma_cm_id's. The actual operation is - * based on the rdma_cm_id's port space. - */ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param); +int rdma_connect_locked(struct rdma_cm_id *id, + struct rdma_conn_param *conn_param); int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece); -- cgit v1.2.3 From cbdc0f54560f94c2205ddbebb5464d65868af0d8 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 23 Oct 2020 18:33:18 +0200 Subject: usb: fix kernel-doc markups There is a common comment marked, instead, with kernel-doc notation. Also, some identifiers have different names between their prototypes and the kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Acked-by: Felipe Balbi Link: https://lore.kernel.org/r/0b964be3884def04fcd20ea5c12cb90d0014871c.1603469755.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 2040696d75b6..a2d229ab63ba 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -437,7 +437,7 @@ static inline struct usb_composite_driver *to_cdriver( #define OS_STRING_IDX 0xEE /** - * struct usb_composite_device - represents one composite usb gadget + * struct usb_composite_dev - represents one composite usb gadget * @gadget: read-only, abstracts the gadget's usb peripheral controller * @req: used for control responses; buffer is pre-allocated * @os_desc_req: used for OS descriptors responses; buffer is pre-allocated -- cgit v1.2.3 From 13150bc5416f45234c955e5bed91623d178c6117 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 27 Oct 2020 16:11:32 +0100 Subject: module: use hidden visibility for weak symbol references Geert reports that commit be2881824ae9eb92 ("arm64/build: Assert for unwanted sections") results in build errors on arm64 for configurations that have CONFIG_MODULES disabled. The commit in question added ASSERT()s to the arm64 linker script to ensure that linker generated sections such as .got.plt etc are empty, but as it turns out, there are corner cases where the linker does emit content into those sections. More specifically, weak references to function symbols (which can remain unsatisfied, and can therefore not be emitted as relative references) will be emitted as GOT and PLT entries when linking the kernel in PIE mode (which is the case when CONFIG_RELOCATABLE is enabled, which is on by default). What happens is that code such as struct device *(*fn)(struct device *dev); struct device *iommu_device; fn = symbol_get(mdev_get_iommu_device); if (fn) { iommu_device = fn(dev); essentially gets converted into the following when CONFIG_MODULES is off: struct device *iommu_device; if (&mdev_get_iommu_device) { iommu_device = mdev_get_iommu_device(dev); where mdev_get_iommu_device is emitted as a weak symbol reference into the object file. The first reference is decorated with an ordinary ABS64 data relocation (which yields 0x0 if the reference remains unsatisfied). However, the indirect call is turned into a direct call covered by a R_AARCH64_CALL26 relocation, which is converted into a call via a PLT entry taking the target address from the associated GOT entry. Given that such GOT and PLT entries are unnecessary for fully linked binaries such as the kernel, let's give these weak symbol references hidden visibility, so that the linker knows that the weak reference via R_AARCH64_CALL26 can simply remain unsatisfied. Signed-off-by: Ard Biesheuvel Tested-by: Geert Uytterhoeven Reviewed-by: Fangrui Song Acked-by: Jessica Yu Cc: Jessica Yu Cc: Kees Cook Cc: Geert Uytterhoeven Cc: Nick Desaulniers Link: https://lore.kernel.org/r/20201027151132.14066-1-ardb@kernel.org Signed-off-by: Will Deacon --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 7ccdf87f376f..6264617bab4d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -740,7 +740,7 @@ static inline bool within_module(unsigned long addr, const struct module *mod) } /* Get/put a kernel symbol (calls should be symmetric) */ -#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); }) +#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); }) #define symbol_put(x) do { } while (0) #define symbol_put_addr(x) do { } while (0) -- cgit v1.2.3 From 6a6223ec7779dfdabb9c2567bb42079bc300cf27 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:13 +0100 Subject: blk-mq: docs: add kernel-doc description for a new struct member As reported by kernel-doc: ./include/linux/blk-mq.h:267: warning: Function parameter or member 'active_queues_shared_sbitmap' not described in 'blk_mq_tag_set' There is now a new member for struct blk_mq_tag_set. Add a description for it, based on the commit that introduced it. Fixes: f1b49fdc1c64 ("blk-mq: Record active_queues_shared_sbitmap per tag_set for when using shared sbitmap") Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Jens Axboe Reviewed-by: John Garry Link: https://lore.kernel.org/r/8e513153b83eefc05e358f51f2632b592c3f6772.1603791716.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b23eeca4d677..794b2a33a2c3 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -235,6 +235,8 @@ enum hctx_type { * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. + * @active_queues_shared_sbitmap: + * number of active request queues per tag set. * @__bitmap_tags: A shared tags sbitmap, used over all hctx's * @__breserved_tags: * A shared reserved tags sbitmap, used over all hctx's -- cgit v1.2.3 From 89b422354409c275e898d26607201797cc05a932 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:17 +0100 Subject: mm: pagemap.h: fix two kernel-doc markups Changeset a8cf7f272b5a ("mm: add find_lock_head") renamed the index parameter, but forgot to update the kernel-doc markups accordingly. Fixes: a8cf7f272b5a ("mm: add find_lock_head") Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/dce89b296a4f5f9f8f798d5e76b6736c14a916ac.1603791716.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/pagemap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c77b7c31b2e4..e1e19c1f9ec9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -344,9 +344,9 @@ static inline struct page *find_get_page_flags(struct address_space *mapping, /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search - * @offset: the page index + * @index: the page index * - * Looks up the page cache entry at @mapping & @offset. If there is a + * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * @@ -363,9 +363,9 @@ static inline struct page *find_lock_page(struct address_space *mapping, /** * find_lock_head - Locate, pin and lock a pagecache page. * @mapping: The address_space to search. - * @offset: The page index. + * @index: The page index. * - * Looks up the page cache entry at @mapping & @offset. If there is a + * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, its head page is returned locked and with an increased * refcount. * -- cgit v1.2.3 From e86c6569c588a01f20e7554cc245f8fae831957b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:18 +0100 Subject: net: phy: remove kernel-doc duplication Sphinx 3 now checks for duplicated function declarations: .../Documentation/networking/kapi:143: ../include/linux/phy.h:163: WARNING: Duplicate C declaration, also defined in 'networking/kapi'. Declaration is 'unsigned int phy_supported_speeds (struct phy_device *phy, unsigned int *speeds, unsigned int size)'. .../Documentation/networking/kapi:143: ../include/linux/phy.h:1034: WARNING: Duplicate C declaration, also defined in 'networking/kapi'. Declaration is 'int phy_read_mmd (struct phy_device *phydev, int devad, u32 regnum)'. .../Documentation/networking/kapi:143: ../include/linux/phy.h:1076: WARNING: Duplicate C declaration, also defined in 'networking/kapi'. Declaration is 'int __phy_read_mmd (struct phy_device *phydev, int devad, u32 regnum)'. .../Documentation/networking/kapi:143: ../include/linux/phy.h:1088: WARNING: Duplicate C declaration, also defined in 'networking/kapi'. Declaration is 'int phy_write_mmd (struct phy_device *phydev, int devad, u32 regnum, u16 val)'. .../Documentation/networking/kapi:143: ../include/linux/phy.h:1100: WARNING: Duplicate C declaration, also defined in 'networking/kapi'. Declaration is 'int __phy_write_mmd (struct phy_device *phydev, int devad, u32 regnum, u16 val)'. It turns that both the C and the H files have the same kernel-doc markup for the same functions. Let's drop the at the header file, keeping the one closer to the code. Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/75e9a357f9a716833d2094b04898754876365e68.1603791716.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/phy.h | 40 +++++----------------------------------- 1 file changed, 5 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index eb3cb1a98b45..56563e5e0dc7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -147,16 +147,8 @@ typedef enum { PHY_INTERFACE_MODE_MAX, } phy_interface_t; -/** +/* * phy_supported_speeds - return all speeds currently supported by a PHY device - * @phy: The PHY device to return supported speeds of. - * @speeds: buffer to store supported speeds in. - * @size: size of speeds buffer. - * - * Description: Returns the number of supported speeds, and fills - * the speeds buffer with the supported speeds. If speeds buffer is - * too small to contain all currently supported speeds, will return as - * many speeds as can fit. */ unsigned int phy_supported_speeds(struct phy_device *phy, unsigned int *speeds, @@ -1022,14 +1014,9 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, regnum, mask, set); } -/** +/* * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * - * Same rules as for phy_read(); */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); @@ -1064,38 +1051,21 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); __ret; \ }) -/** +/* * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * - * Same rules as for __phy_read(); */ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); -/** +/* * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to write to - * @regnum: The register on the MMD to read - * @val: value to write to @regnum - * - * Same rules as for phy_write(); */ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); -/** +/* * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to write to - * @regnum: The register on the MMD to read - * @val: value to write to @regnum - * - * Same rules as for __phy_write(); */ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); -- cgit v1.2.3 From cf38cc9f1e71151f22584c40357afaab6609384b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:23 +0100 Subject: locking/refcount: move kernel-doc markups to the proper place Changeset a435b9a14356 ("locking/refcount: Provide __refcount API to obtain the old value") added a set of functions starting with __ that have a new parameter, adding a series of new warnings: $ ./scripts/kernel-doc -none include/linux/refcount.h include/linux/refcount.h:169: warning: Function parameter or member 'oldp' not described in '__refcount_add_not_zero' include/linux/refcount.h:208: warning: Function parameter or member 'oldp' not described in '__refcount_add' include/linux/refcount.h:239: warning: Function parameter or member 'oldp' not described in '__refcount_inc_not_zero' include/linux/refcount.h:261: warning: Function parameter or member 'oldp' not described in '__refcount_inc' include/linux/refcount.h:291: warning: Function parameter or member 'oldp' not described in '__refcount_sub_and_test' include/linux/refcount.h:327: warning: Function parameter or member 'oldp' not described in '__refcount_dec_and_test' include/linux/refcount.h:347: warning: Function parameter or member 'oldp' not described in '__refcount_dec' The issue is that the kernel-doc markups are now misplaced, as they should be added just before the functions. So, move the kernel-doc markups to the proper places, in order to drop the warnings. It should be noticed that git show produces a crappy output, for this patch without "--patience" flag. Fixes: a435b9a14356 ("locking/refcount: Provide __refcount API to obtain the old value") Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/7985c31d1ace591bc5e1faa05c367f1295b78afd.1603791716.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/refcount.h | 130 +++++++++++++++++++++++------------------------ 1 file changed, 65 insertions(+), 65 deletions(-) (limited to 'include') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 7fabb1af18e0..497990c69b0b 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -147,24 +147,6 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } -/** - * refcount_add_not_zero - add a value to a refcount unless it is 0 - * @i: the value to add to the refcount - * @r: the refcount - * - * Will saturate at REFCOUNT_SATURATED and WARN. - * - * Provides no memory ordering, it is assumed the caller has guaranteed the - * object memory to be stable (RCU, etc.). It does provide a control dependency - * and thereby orders future stores. See the comment on top. - * - * Use of this function is not recommended for the normal reference counting - * use case in which references are taken and released one at a time. In these - * cases, refcount_inc(), or one of its variants, should instead be used to - * increment a reference count. - * - * Return: false if the passed refcount is 0, true otherwise - */ static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); @@ -183,17 +165,12 @@ static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, in return old; } -static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) -{ - return __refcount_add_not_zero(i, r, NULL); -} - /** - * refcount_add - add a value to a refcount + * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * - * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. + * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency @@ -203,7 +180,14 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. + * + * Return: false if the passed refcount is 0, true otherwise */ +static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) +{ + return __refcount_add_not_zero(i, r, NULL); +} + static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); @@ -217,11 +201,32 @@ static inline void __refcount_add(int i, refcount_t *r, int *oldp) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } +/** + * refcount_add - add a value to a refcount + * @i: the value to add to the refcount + * @r: the refcount + * + * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc(), or one of its variants, should instead be used to + * increment a reference count. + */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } +static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) +{ + return __refcount_add_not_zero(1, r, oldp); +} + /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment @@ -235,14 +240,14 @@ static inline void refcount_add(int i, refcount_t *r) * * Return: true if the increment was successful, false otherwise */ -static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) +static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { - return __refcount_add_not_zero(1, r, oldp); + return __refcount_inc_not_zero(r, NULL); } -static inline __must_check bool refcount_inc_not_zero(refcount_t *r) +static inline void __refcount_inc(refcount_t *r, int *oldp) { - return __refcount_inc_not_zero(r, NULL); + __refcount_add(1, r, oldp); } /** @@ -257,14 +262,27 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ -static inline void __refcount_inc(refcount_t *r, int *oldp) +static inline void refcount_inc(refcount_t *r) { - __refcount_add(1, r, oldp); + __refcount_inc(r, NULL); } -static inline void refcount_inc(refcount_t *r) +static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { - __refcount_inc(r, NULL); + int old = atomic_fetch_sub_release(i, &r->refs); + + if (oldp) + *oldp = old; + + if (old == i) { + smp_acquire__after_ctrl_dep(); + return true; + } + + if (unlikely(old < 0 || old - i < 0)) + refcount_warn_saturate(r, REFCOUNT_SUB_UAF); + + return false; } /** @@ -287,27 +305,14 @@ static inline void refcount_inc(refcount_t *r) * * Return: true if the resulting refcount is 0, false otherwise */ -static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) +static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { - int old = atomic_fetch_sub_release(i, &r->refs); - - if (oldp) - *oldp = old; - - if (old == i) { - smp_acquire__after_ctrl_dep(); - return true; - } - - if (unlikely(old < 0 || old - i < 0)) - refcount_warn_saturate(r, REFCOUNT_SUB_UAF); - - return false; + return __refcount_sub_and_test(i, r, NULL); } -static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) +static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { - return __refcount_sub_and_test(i, r, NULL); + return __refcount_sub_and_test(1, r, oldp); } /** @@ -323,26 +328,11 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) * * Return: true if the resulting refcount is 0, false otherwise */ -static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) -{ - return __refcount_sub_and_test(1, r, oldp); -} - static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } -/** - * refcount_dec - decrement a refcount - * @r: the refcount - * - * Similar to atomic_dec(), it will WARN on underflow and fail to decrement - * when saturated at REFCOUNT_SATURATED. - * - * Provides release memory ordering, such that prior loads and stores are done - * before. - */ static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); @@ -354,6 +344,16 @@ static inline void __refcount_dec(refcount_t *r, int *oldp) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } +/** + * refcount_dec - decrement a refcount + * @r: the refcount + * + * Similar to atomic_dec(), it will WARN on underflow and fail to decrement + * when saturated at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before. + */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); -- cgit v1.2.3 From e029c5f2798720b463e8df0e184a4d1036311b43 Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Mon, 26 Oct 2020 21:49:14 -0700 Subject: ext4: make num of fast commit blocks configurable This patch reserves a field in the jbd2 superblock for number of fast commit blocks. When this value is non-zero, Ext4 uses this field to set the number of fast commit blocks. Fixes: 6866d7b3f2bb ("ext4/jbd2: add fast commit initialization") Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20201027044915.2553163-2-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fb3d71ad6eea..7e88bbc16ffb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -263,7 +263,10 @@ typedef struct journal_superblock_s /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; - __u32 s_padding[42]; +/* 0x0054 */ + __be32 s_num_fc_blks; /* Number of fast commit blocks */ +/* 0x0058 */ + __u32 s_padding[41]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ -- cgit v1.2.3 From ea4b01d9b81f5f381fc6832bc31046878a2d1a5d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 27 Oct 2020 10:51:27 +0100 Subject: jbd2: fix a kernel-doc markup The kernel-doc markup that documents _fc_replay_callback is missing an asterisk, causing this warning: ../include/linux/jbd2.h:1271: warning: Function parameter or member 'j_fc_replay_callback' not described in 'journal_s' When building the docs. Fixes: 609f928af48f ("jbd2: fast commit recovery path") Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/6055927ada2015b55b413cdd2670533bdc9a8da2.1603791716.git.mchehab+huawei@kernel.org Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 7e88bbc16ffb..1d5566af48ac 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1256,7 +1256,7 @@ struct journal_s */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int); - /* + /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast -- cgit v1.2.3 From 80ade22c06ca115b81dd168e99479c8e09843513 Mon Sep 17 00:00:00 2001 From: Sudeep Dutt Date: Tue, 27 Oct 2020 20:14:15 -0700 Subject: misc: mic: remove the MIC drivers This patch removes the MIC drivers from the kernel tree since the corresponding devices have been discontinued. Removing the dma and char-misc changes in one patch and merging via the char-misc tree is best to avoid any potential build breakage. Cc: Nikhil Rao Reviewed-by: Ashutosh Dixit Signed-off-by: Sudeep Dutt Acked-By: Vinod Koul Reviewed-by: Sherry Sun Link: https://lore.kernel.org/r/8c1443136563de34699d2c084df478181c205db4.1603854416.git.sudeep.dutt@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/mic_bus.h | 100 --- include/linux/scif.h | 1339 --------------------------------------- include/uapi/linux/mic_common.h | 235 ------- include/uapi/linux/mic_ioctl.h | 77 --- 4 files changed, 1751 deletions(-) delete mode 100644 include/linux/mic_bus.h delete mode 100644 include/linux/scif.h delete mode 100644 include/uapi/linux/mic_common.h delete mode 100644 include/uapi/linux/mic_ioctl.h (limited to 'include') diff --git a/include/linux/mic_bus.h b/include/linux/mic_bus.h deleted file mode 100644 index e99c789424e0..000000000000 --- a/include/linux/mic_bus.h +++ /dev/null @@ -1,100 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Intel MIC Platform Software Stack (MPSS) - * - * Copyright(c) 2014 Intel Corporation. - * - * Intel MIC Bus driver. - * - * This implementation is very similar to the virtio bus driver - * implementation @ include/linux/virtio.h. - */ -#ifndef _MIC_BUS_H_ -#define _MIC_BUS_H_ -/* - * Everything a mbus driver needs to work with any particular mbus - * implementation. - */ -#include -#include - -struct mbus_device_id { - __u32 device; - __u32 vendor; -}; - -#define MBUS_DEV_DMA_HOST 2 -#define MBUS_DEV_DMA_MIC 3 -#define MBUS_DEV_ANY_ID 0xffffffff - -/** - * mbus_device - representation of a device using mbus - * @mmio_va: virtual address of mmio space - * @hw_ops: the hardware ops supported by this device. - * @id: the device type identification (used to match it with a driver). - * @dev: underlying device. - * be used to communicate with. - * @index: unique position on the mbus bus - */ -struct mbus_device { - void __iomem *mmio_va; - struct mbus_hw_ops *hw_ops; - struct mbus_device_id id; - struct device dev; - int index; -}; - -/** - * mbus_driver - operations for a mbus I/O driver - * @driver: underlying device driver (populate name and owner). - * @id_table: the ids serviced by this driver. - * @probe: the function to call when a device is found. Returns 0 or -errno. - * @remove: the function to call when a device is removed. - */ -struct mbus_driver { - struct device_driver driver; - const struct mbus_device_id *id_table; - int (*probe)(struct mbus_device *dev); - void (*scan)(struct mbus_device *dev); - void (*remove)(struct mbus_device *dev); -}; - -/** - * struct mic_irq - opaque pointer used as cookie - */ -struct mic_irq; - -/** - * mbus_hw_ops - Hardware operations for accessing a MIC device on the MIC bus. - */ -struct mbus_hw_ops { - struct mic_irq* (*request_threaded_irq)(struct mbus_device *mbdev, - irq_handler_t handler, - irq_handler_t thread_fn, - const char *name, void *data, - int intr_src); - void (*free_irq)(struct mbus_device *mbdev, - struct mic_irq *cookie, void *data); - void (*ack_interrupt)(struct mbus_device *mbdev, int num); -}; - -struct mbus_device * -mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops, - struct mbus_hw_ops *hw_ops, int index, - void __iomem *mmio_va); -void mbus_unregister_device(struct mbus_device *mbdev); - -int mbus_register_driver(struct mbus_driver *drv); -void mbus_unregister_driver(struct mbus_driver *drv); - -static inline struct mbus_device *dev_to_mbus(struct device *_dev) -{ - return container_of(_dev, struct mbus_device, dev); -} - -static inline struct mbus_driver *drv_to_mbus(struct device_driver *drv) -{ - return container_of(drv, struct mbus_driver, driver); -} - -#endif /* _MIC_BUS_H */ diff --git a/include/linux/scif.h b/include/linux/scif.h deleted file mode 100644 index 329e695b8fe5..000000000000 --- a/include/linux/scif.h +++ /dev/null @@ -1,1339 +0,0 @@ -/* - * Intel MIC Platform Software Stack (MPSS) - * - * This file is provided under a dual BSD/GPLv2 license. When using or - * redistributing this file, you may do so under either license. - * - * GPL LICENSE SUMMARY - * - * Copyright(c) 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * BSD LICENSE - * - * Copyright(c) 2014 Intel Corporation. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * Intel SCIF driver. - * - */ -#ifndef __SCIF_H__ -#define __SCIF_H__ - -#include -#include -#include -#include - -#define SCIF_ACCEPT_SYNC 1 -#define SCIF_SEND_BLOCK 1 -#define SCIF_RECV_BLOCK 1 - -enum { - SCIF_PROT_READ = (1 << 0), - SCIF_PROT_WRITE = (1 << 1) -}; - -enum { - SCIF_MAP_FIXED = 0x10, - SCIF_MAP_KERNEL = 0x20, -}; - -enum { - SCIF_FENCE_INIT_SELF = (1 << 0), - SCIF_FENCE_INIT_PEER = (1 << 1), - SCIF_SIGNAL_LOCAL = (1 << 4), - SCIF_SIGNAL_REMOTE = (1 << 5) -}; - -enum { - SCIF_RMA_USECPU = (1 << 0), - SCIF_RMA_USECACHE = (1 << 1), - SCIF_RMA_SYNC = (1 << 2), - SCIF_RMA_ORDERED = (1 << 3) -}; - -/* End of SCIF Admin Reserved Ports */ -#define SCIF_ADMIN_PORT_END 1024 - -/* End of SCIF Reserved Ports */ -#define SCIF_PORT_RSVD 1088 - -typedef struct scif_endpt *scif_epd_t; -typedef struct scif_pinned_pages *scif_pinned_pages_t; - -/** - * struct scif_range - SCIF registered range used in kernel mode - * @cookie: cookie used internally by SCIF - * @nr_pages: number of pages of PAGE_SIZE - * @prot_flags: R/W protection - * @phys_addr: Array of bus addresses - * @va: Array of kernel virtual addresses backed by the pages in the phys_addr - * array. The va is populated only when called on the host for a remote - * SCIF connection on MIC. This is required to support the use case of DMA - * between MIC and another device which is not a SCIF node e.g., an IB or - * ethernet NIC. - */ -struct scif_range { - void *cookie; - int nr_pages; - int prot_flags; - dma_addr_t *phys_addr; - void __iomem **va; -}; - -/** - * struct scif_pollepd - SCIF endpoint to be monitored via scif_poll - * @epd: SCIF endpoint - * @events: requested events - * @revents: returned events - */ -struct scif_pollepd { - scif_epd_t epd; - __poll_t events; - __poll_t revents; -}; - -/** - * scif_peer_dev - representation of a peer SCIF device - * - * Peer devices show up as PCIe devices for the mgmt node but not the cards. - * The mgmt node discovers all the cards on the PCIe bus and informs the other - * cards about their peers. Upon notification of a peer a node adds a peer - * device to the peer bus to maintain symmetry in the way devices are - * discovered across all nodes in the SCIF network. - * - * @dev: underlying device - * @dnode - The destination node which this device will communicate with. - */ -struct scif_peer_dev { - struct device dev; - u8 dnode; -}; - -/** - * scif_client - representation of a SCIF client - * @name: client name - * @probe - client method called when a peer device is registered - * @remove - client method called when a peer device is unregistered - * @si - subsys_interface used internally for implementing SCIF clients - */ -struct scif_client { - const char *name; - void (*probe)(struct scif_peer_dev *spdev); - void (*remove)(struct scif_peer_dev *spdev); - struct subsys_interface si; -}; - -#define SCIF_OPEN_FAILED ((scif_epd_t)-1) -#define SCIF_REGISTER_FAILED ((off_t)-1) -#define SCIF_MMAP_FAILED ((void *)-1) - -/** - * scif_open() - Create an endpoint - * - * Return: - * Upon successful completion, scif_open() returns an endpoint descriptor to - * be used in subsequent SCIF functions calls to refer to that endpoint; - * otherwise in user mode SCIF_OPEN_FAILED (that is ((scif_epd_t)-1)) is - * returned and errno is set to indicate the error; in kernel mode a NULL - * scif_epd_t is returned. - * - * Errors: - * ENOMEM - Insufficient kernel memory was available - */ -scif_epd_t scif_open(void); - -/** - * scif_bind() - Bind an endpoint to a port - * @epd: endpoint descriptor - * @pn: port number - * - * scif_bind() binds endpoint epd to port pn, where pn is a port number on the - * local node. If pn is zero, a port number greater than or equal to - * SCIF_PORT_RSVD is assigned and returned. Each endpoint may be bound to - * exactly one local port. Ports less than 1024 when requested can only be bound - * by system (or root) processes or by processes executed by privileged users. - * - * Return: - * Upon successful completion, scif_bind() returns the port number to which epd - * is bound; otherwise in user mode -1 is returned and errno is set to - * indicate the error; in kernel mode the negative of one of the following - * errors is returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * EINVAL - the endpoint or the port is already bound - * EISCONN - The endpoint is already connected - * ENOSPC - No port number available for assignment - * EACCES - The port requested is protected and the user is not the superuser - */ -int scif_bind(scif_epd_t epd, u16 pn); - -/** - * scif_listen() - Listen for connections on an endpoint - * @epd: endpoint descriptor - * @backlog: maximum pending connection requests - * - * scif_listen() marks the endpoint epd as a listening endpoint - that is, as - * an endpoint that will be used to accept incoming connection requests. Once - * so marked, the endpoint is said to be in the listening state and may not be - * used as the endpoint of a connection. - * - * The endpoint, epd, must have been bound to a port. - * - * The backlog argument defines the maximum length to which the queue of - * pending connections for epd may grow. If a connection request arrives when - * the queue is full, the client may receive an error with an indication that - * the connection was refused. - * - * Return: - * Upon successful completion, scif_listen() returns 0; otherwise in user mode - * -1 is returned and errno is set to indicate the error; in kernel mode the - * negative of one of the following errors is returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * EINVAL - the endpoint is not bound to a port - * EISCONN - The endpoint is already connected or listening - */ -int scif_listen(scif_epd_t epd, int backlog); - -/** - * scif_connect() - Initiate a connection on a port - * @epd: endpoint descriptor - * @dst: global id of port to which to connect - * - * The scif_connect() function requests the connection of endpoint epd to remote - * port dst. If the connection is successful, a peer endpoint, bound to dst, is - * created on node dst.node. On successful return, the connection is complete. - * - * If the endpoint epd has not already been bound to a port, scif_connect() - * will bind it to an unused local port. - * - * A connection is terminated when an endpoint of the connection is closed, - * either explicitly by scif_close(), or when a process that owns one of the - * endpoints of the connection is terminated. - * - * In user space, scif_connect() supports an asynchronous connection mode - * if the application has set the O_NONBLOCK flag on the endpoint via the - * fcntl() system call. Setting this flag will result in the calling process - * not to wait during scif_connect(). - * - * Return: - * Upon successful completion, scif_connect() returns the port ID to which the - * endpoint, epd, is bound; otherwise in user mode -1 is returned and errno is - * set to indicate the error; in kernel mode the negative of one of the - * following errors is returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNREFUSED - The destination was not listening for connections or refused - * the connection request - * EINVAL - dst.port is not a valid port ID - * EISCONN - The endpoint is already connected - * ENOMEM - No buffer space is available - * ENODEV - The destination node does not exist, or the node is lost or existed, - * but is not currently in the network since it may have crashed - * ENOSPC - No port number available for assignment - * EOPNOTSUPP - The endpoint is listening and cannot be connected - */ -int scif_connect(scif_epd_t epd, struct scif_port_id *dst); - -/** - * scif_accept() - Accept a connection on an endpoint - * @epd: endpoint descriptor - * @peer: global id of port to which connected - * @newepd: new connected endpoint descriptor - * @flags: flags - * - * The scif_accept() call extracts the first connection request from the queue - * of pending connections for the port on which epd is listening. scif_accept() - * creates a new endpoint, bound to the same port as epd, and allocates a new - * SCIF endpoint descriptor, returned in newepd, for the endpoint. The new - * endpoint is connected to the endpoint through which the connection was - * requested. epd is unaffected by this call, and remains in the listening - * state. - * - * On successful return, peer holds the global port identifier (node id and - * local port number) of the port which requested the connection. - * - * A connection is terminated when an endpoint of the connection is closed, - * either explicitly by scif_close(), or when a process that owns one of the - * endpoints of the connection is terminated. - * - * The number of connections that can (subsequently) be accepted on epd is only - * limited by system resources (memory). - * - * The flags argument is formed by OR'ing together zero or more of the - * following values. - * SCIF_ACCEPT_SYNC - block until a connection request is presented. If - * SCIF_ACCEPT_SYNC is not in flags, and no pending - * connections are present on the queue, scif_accept() - * fails with an EAGAIN error - * - * In user mode, the select() and poll() functions can be used to determine - * when there is a connection request. In kernel mode, the scif_poll() - * function may be used for this purpose. A readable event will be delivered - * when a connection is requested. - * - * Return: - * Upon successful completion, scif_accept() returns 0; otherwise in user mode - * -1 is returned and errno is set to indicate the error; in kernel mode the - * negative of one of the following errors is returned. - * - * Errors: - * EAGAIN - SCIF_ACCEPT_SYNC is not set and no connections are present to be - * accepted or SCIF_ACCEPT_SYNC is not set and remote node failed to complete - * its connection request - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * EINTR - Interrupted function - * EINVAL - epd is not a listening endpoint, or flags is invalid, or peer is - * NULL, or newepd is NULL - * ENODEV - The requesting node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOMEM - Not enough space - * ENOENT - Secondary part of epd registration failed - */ -int scif_accept(scif_epd_t epd, struct scif_port_id *peer, scif_epd_t - *newepd, int flags); - -/** - * scif_close() - Close an endpoint - * @epd: endpoint descriptor - * - * scif_close() closes an endpoint and performs necessary teardown of - * facilities associated with that endpoint. - * - * If epd is a listening endpoint then it will no longer accept connection - * requests on the port to which it is bound. Any pending connection requests - * are rejected. - * - * If epd is a connected endpoint, then its peer endpoint is also closed. RMAs - * which are in-process through epd or its peer endpoint will complete before - * scif_close() returns. Registered windows of the local and peer endpoints are - * released as if scif_unregister() was called against each window. - * - * Closing a SCIF endpoint does not affect local registered memory mapped by - * a SCIF endpoint on a remote node. The local memory remains mapped by the peer - * SCIF endpoint explicitly removed by calling munmap(..) by the peer. - * - * If the peer endpoint's receive queue is not empty at the time that epd is - * closed, then the peer endpoint can be passed as the endpoint parameter to - * scif_recv() until the receive queue is empty. - * - * epd is freed and may no longer be accessed. - * - * Return: - * Upon successful completion, scif_close() returns 0; otherwise in user mode - * -1 is returned and errno is set to indicate the error; in kernel mode the - * negative of one of the following errors is returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - */ -int scif_close(scif_epd_t epd); - -/** - * scif_send() - Send a message - * @epd: endpoint descriptor - * @msg: message buffer address - * @len: message length - * @flags: blocking mode flags - * - * scif_send() sends data to the peer of endpoint epd. Up to len bytes of data - * are copied from memory starting at address msg. On successful execution the - * return value of scif_send() is the number of bytes that were sent, and is - * zero if no bytes were sent because len was zero. scif_send() may be called - * only when the endpoint is in a connected state. - * - * If a scif_send() call is non-blocking, then it sends only those bytes which - * can be sent without waiting, up to a maximum of len bytes. - * - * If a scif_send() call is blocking, then it normally returns after sending - * all len bytes. If a blocking call is interrupted or the connection is - * reset, the call is considered successful if some bytes were sent or len is - * zero, otherwise the call is considered unsuccessful. - * - * In user mode, the select() and poll() functions can be used to determine - * when the send queue is not full. In kernel mode, the scif_poll() function - * may be used for this purpose. - * - * It is recommended that scif_send()/scif_recv() only be used for short - * control-type message communication between SCIF endpoints. The SCIF RMA - * APIs are expected to provide better performance for transfer sizes of - * 1024 bytes or longer for the current MIC hardware and software - * implementation. - * - * scif_send() will block until the entire message is sent if SCIF_SEND_BLOCK - * is passed as the flags argument. - * - * Return: - * Upon successful completion, scif_send() returns the number of bytes sent; - * otherwise in user mode -1 is returned and errno is set to indicate the - * error; in kernel mode the negative of one of the following errors is - * returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - flags is invalid, or len is negative - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOMEM - Not enough space - * ENOTCONN - The endpoint is not connected - */ -int scif_send(scif_epd_t epd, void *msg, int len, int flags); - -/** - * scif_recv() - Receive a message - * @epd: endpoint descriptor - * @msg: message buffer address - * @len: message buffer length - * @flags: blocking mode flags - * - * scif_recv() receives data from the peer of endpoint epd. Up to len bytes of - * data are copied to memory starting at address msg. On successful execution - * the return value of scif_recv() is the number of bytes that were received, - * and is zero if no bytes were received because len was zero. scif_recv() may - * be called only when the endpoint is in a connected state. - * - * If a scif_recv() call is non-blocking, then it receives only those bytes - * which can be received without waiting, up to a maximum of len bytes. - * - * If a scif_recv() call is blocking, then it normally returns after receiving - * all len bytes. If the blocking call was interrupted due to a disconnection, - * subsequent calls to scif_recv() will copy all bytes received upto the point - * of disconnection. - * - * In user mode, the select() and poll() functions can be used to determine - * when data is available to be received. In kernel mode, the scif_poll() - * function may be used for this purpose. - * - * It is recommended that scif_send()/scif_recv() only be used for short - * control-type message communication between SCIF endpoints. The SCIF RMA - * APIs are expected to provide better performance for transfer sizes of - * 1024 bytes or longer for the current MIC hardware and software - * implementation. - * - * scif_recv() will block until the entire message is received if - * SCIF_RECV_BLOCK is passed as the flags argument. - * - * Return: - * Upon successful completion, scif_recv() returns the number of bytes - * received; otherwise in user mode -1 is returned and errno is set to - * indicate the error; in kernel mode the negative of one of the following - * errors is returned. - * - * Errors: - * EAGAIN - The destination node is returning from a low power state - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - flags is invalid, or len is negative - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOMEM - Not enough space - * ENOTCONN - The endpoint is not connected - */ -int scif_recv(scif_epd_t epd, void *msg, int len, int flags); - -/** - * scif_register() - Mark a memory region for remote access. - * @epd: endpoint descriptor - * @addr: starting virtual address - * @len: length of range - * @offset: offset of window - * @prot_flags: read/write protection flags - * @map_flags: mapping flags - * - * The scif_register() function opens a window, a range of whole pages of the - * registered address space of the endpoint epd, starting at offset po and - * continuing for len bytes. The value of po, further described below, is a - * function of the parameters offset and len, and the value of map_flags. Each - * page of the window represents the physical memory page which backs the - * corresponding page of the range of virtual address pages starting at addr - * and continuing for len bytes. addr and len are constrained to be multiples - * of the page size. A successful scif_register() call returns po. - * - * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset - * exactly, and offset is constrained to be a multiple of the page size. The - * mapping established by scif_register() will not replace any existing - * registration; an error is returned if any page within the range [offset, - * offset + len - 1] intersects an existing window. - * - * When SCIF_MAP_FIXED is not set, the implementation uses offset in an - * implementation-defined manner to arrive at po. The po value so chosen will - * be an area of the registered address space that the implementation deems - * suitable for a mapping of len bytes. An offset value of 0 is interpreted as - * granting the implementation complete freedom in selecting po, subject to - * constraints described below. A non-zero value of offset is taken to be a - * suggestion of an offset near which the mapping should be placed. When the - * implementation selects a value for po, it does not replace any extant - * window. In all cases, po will be a multiple of the page size. - * - * The physical pages which are so represented by a window are available for - * access in calls to mmap(), scif_readfrom(), scif_writeto(), - * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the - * physical pages represented by the window will not be reused by the memory - * subsystem for any other purpose. Note that the same physical page may be - * represented by multiple windows. - * - * Subsequent operations which change the memory pages to which virtual - * addresses are mapped (such as mmap(), munmap()) have no effect on - * existing window. - * - * If the process will fork(), it is recommended that the registered - * virtual address range be marked with MADV_DONTFORK. Doing so will prevent - * problems due to copy-on-write semantics. - * - * The prot_flags argument is formed by OR'ing together one or more of the - * following values. - * SCIF_PROT_READ - allow read operations from the window - * SCIF_PROT_WRITE - allow write operations to the window - * - * Return: - * Upon successful completion, scif_register() returns the offset at which the - * mapping was placed (po); otherwise in user mode SCIF_REGISTER_FAILED (that - * is (off_t *)-1) is returned and errno is set to indicate the error; in - * kernel mode the negative of one of the following errors is returned. - * - * Errors: - * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags, and pages in the range - * [offset, offset + len -1] are already registered - * EAGAIN - The mapping could not be performed due to lack of resources - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - map_flags is invalid, or prot_flags is invalid, or SCIF_MAP_FIXED is - * set in flags, and offset is not a multiple of the page size, or addr is not a - * multiple of the page size, or len is not a multiple of the page size, or is - * 0, or offset is negative - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOMEM - Not enough space - * ENOTCONN -The endpoint is not connected - */ -off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset, - int prot_flags, int map_flags); - -/** - * scif_unregister() - Mark a memory region for remote access. - * @epd: endpoint descriptor - * @offset: start of range to unregister - * @len: length of range to unregister - * - * The scif_unregister() function closes those previously registered windows - * which are entirely within the range [offset, offset + len - 1]. It is an - * error to specify a range which intersects only a subrange of a window. - * - * On a successful return, pages within the window may no longer be specified - * in calls to mmap(), scif_readfrom(), scif_writeto(), scif_vreadfrom(), - * scif_vwriteto(), scif_get_pages, and scif_fence_signal(). The window, - * however, continues to exist until all previous references against it are - * removed. A window is referenced if there is a mapping to it created by - * mmap(), or if scif_get_pages() was called against the window - * (and the pages have not been returned via scif_put_pages()). A window is - * also referenced while an RMA, in which some range of the window is a source - * or destination, is in progress. Finally a window is referenced while some - * offset in that window was specified to scif_fence_signal(), and the RMAs - * marked by that call to scif_fence_signal() have not completed. While a - * window is in this state, its registered address space pages are not - * available for use in a new registered window. - * - * When all such references to the window have been removed, its references to - * all the physical pages which it represents are removed. Similarly, the - * registered address space pages of the window become available for - * registration in a new window. - * - * Return: - * Upon successful completion, scif_unregister() returns 0; otherwise in user - * mode -1 is returned and errno is set to indicate the error; in kernel mode - * the negative of one of the following errors is returned. In the event of an - * error, no windows are unregistered. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - the range [offset, offset + len - 1] intersects a subrange of a - * window, or offset is negative - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid for the - * registered address space of epd - */ -int scif_unregister(scif_epd_t epd, off_t offset, size_t len); - -/** - * scif_readfrom() - Copy from a remote address space - * @epd: endpoint descriptor - * @loffset: offset in local registered address space to - * which to copy - * @len: length of range to copy - * @roffset: offset in remote registered address space - * from which to copy - * @rma_flags: transfer mode flags - * - * scif_readfrom() copies len bytes from the remote registered address space of - * the peer of endpoint epd, starting at the offset roffset to the local - * registered address space of epd, starting at the offset loffset. - * - * Each of the specified ranges [loffset, loffset + len - 1] and [roffset, - * roffset + len - 1] must be within some registered window or windows of the - * local and remote nodes. A range may intersect multiple registered windows, - * but only if those windows are contiguous in the registered address space. - * - * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using - * programmed read/writes. Otherwise the data is copied using DMA. If rma_- - * flags includes SCIF_RMA_SYNC, then scif_readfrom() will return after the - * transfer is complete. Otherwise, the transfer may be performed asynchron- - * ously. The order in which any two asynchronous RMA operations complete - * is non-deterministic. The synchronization functions, scif_fence_mark()/ - * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to - * the completion of asynchronous RMA operations on the same endpoint. - * - * The DMA transfer of individual bytes is not guaranteed to complete in - * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last - * cacheline or partial cacheline of the source range will become visible on - * the destination node after all other transferred data in the source - * range has become visible on the destination node. - * - * The optimal DMA performance will likely be realized if both - * loffset and roffset are cacheline aligned (are a multiple of 64). Lower - * performance will likely be realized if loffset and roffset are not - * cacheline aligned but are separated by some multiple of 64. The lowest level - * of performance is likely if loffset and roffset are not separated by a - * multiple of 64. - * - * The rma_flags argument is formed by ORing together zero or more of the - * following values. - * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA - * engine. - * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the - * transfer has completed. Passing this flag results in the - * current implementation busy waiting and consuming CPU cycles - * while the DMA transfer is in progress for best performance by - * avoiding the interrupt latency. - * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of - * the source range becomes visible on the destination node - * after all other transferred data in the source range has - * become visible on the destination - * - * Return: - * Upon successful completion, scif_readfrom() returns 0; otherwise in user - * mode -1 is returned and errno is set to indicate the error; in kernel mode - * the negative of one of the following errors is returned. - * - * Errors: - * EACCES - Attempt to write to a read-only range - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - rma_flags is invalid - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered - * address space of epd, or, The range [roffset, roffset + len - 1] is invalid - * for the registered address space of the peer of epd, or loffset or roffset - * is negative - */ -int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t - roffset, int rma_flags); - -/** - * scif_writeto() - Copy to a remote address space - * @epd: endpoint descriptor - * @loffset: offset in local registered address space - * from which to copy - * @len: length of range to copy - * @roffset: offset in remote registered address space to - * which to copy - * @rma_flags: transfer mode flags - * - * scif_writeto() copies len bytes from the local registered address space of - * epd, starting at the offset loffset to the remote registered address space - * of the peer of endpoint epd, starting at the offset roffset. - * - * Each of the specified ranges [loffset, loffset + len - 1] and [roffset, - * roffset + len - 1] must be within some registered window or windows of the - * local and remote nodes. A range may intersect multiple registered windows, - * but only if those windows are contiguous in the registered address space. - * - * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using - * programmed read/writes. Otherwise the data is copied using DMA. If rma_- - * flags includes SCIF_RMA_SYNC, then scif_writeto() will return after the - * transfer is complete. Otherwise, the transfer may be performed asynchron- - * ously. The order in which any two asynchronous RMA operations complete - * is non-deterministic. The synchronization functions, scif_fence_mark()/ - * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to - * the completion of asynchronous RMA operations on the same endpoint. - * - * The DMA transfer of individual bytes is not guaranteed to complete in - * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last - * cacheline or partial cacheline of the source range will become visible on - * the destination node after all other transferred data in the source - * range has become visible on the destination node. - * - * The optimal DMA performance will likely be realized if both - * loffset and roffset are cacheline aligned (are a multiple of 64). Lower - * performance will likely be realized if loffset and roffset are not cacheline - * aligned but are separated by some multiple of 64. The lowest level of - * performance is likely if loffset and roffset are not separated by a multiple - * of 64. - * - * The rma_flags argument is formed by ORing together zero or more of the - * following values. - * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA - * engine. - * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the - * transfer has completed. Passing this flag results in the - * current implementation busy waiting and consuming CPU cycles - * while the DMA transfer is in progress for best performance by - * avoiding the interrupt latency. - * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of - * the source range becomes visible on the destination node - * after all other transferred data in the source range has - * become visible on the destination - * - * Return: - * Upon successful completion, scif_readfrom() returns 0; otherwise in user - * mode -1 is returned and errno is set to indicate the error; in kernel mode - * the negative of one of the following errors is returned. - * - * Errors: - * EACCES - Attempt to write to a read-only range - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - rma_flags is invalid - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered - * address space of epd, or, The range [roffset , roffset + len -1] is invalid - * for the registered address space of the peer of epd, or loffset or roffset - * is negative - */ -int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t - roffset, int rma_flags); - -/** - * scif_vreadfrom() - Copy from a remote address space - * @epd: endpoint descriptor - * @addr: address to which to copy - * @len: length of range to copy - * @roffset: offset in remote registered address space - * from which to copy - * @rma_flags: transfer mode flags - * - * scif_vreadfrom() copies len bytes from the remote registered address - * space of the peer of endpoint epd, starting at the offset roffset, to local - * memory, starting at addr. - * - * The specified range [roffset, roffset + len - 1] must be within some - * registered window or windows of the remote nodes. The range may - * intersect multiple registered windows, but only if those windows are - * contiguous in the registered address space. - * - * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using - * programmed read/writes. Otherwise the data is copied using DMA. If rma_- - * flags includes SCIF_RMA_SYNC, then scif_vreadfrom() will return after the - * transfer is complete. Otherwise, the transfer may be performed asynchron- - * ously. The order in which any two asynchronous RMA operations complete - * is non-deterministic. The synchronization functions, scif_fence_mark()/ - * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to - * the completion of asynchronous RMA operations on the same endpoint. - * - * The DMA transfer of individual bytes is not guaranteed to complete in - * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last - * cacheline or partial cacheline of the source range will become visible on - * the destination node after all other transferred data in the source - * range has become visible on the destination node. - * - * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back - * the specified local memory range may be remain in a pinned state even after - * the specified transfer completes. This may reduce overhead if some or all of - * the same virtual address range is referenced in a subsequent call of - * scif_vreadfrom() or scif_vwriteto(). - * - * The optimal DMA performance will likely be realized if both - * addr and roffset are cacheline aligned (are a multiple of 64). Lower - * performance will likely be realized if addr and roffset are not - * cacheline aligned but are separated by some multiple of 64. The lowest level - * of performance is likely if addr and roffset are not separated by a - * multiple of 64. - * - * The rma_flags argument is formed by ORing together zero or more of the - * following values. - * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA - * engine. - * SCIF_RMA_USECACHE - enable registration caching - * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the - * transfer has completed. Passing this flag results in the - * current implementation busy waiting and consuming CPU cycles - * while the DMA transfer is in progress for best performance by - * avoiding the interrupt latency. - * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of - * the source range becomes visible on the destination node - * after all other transferred data in the source range has - * become visible on the destination - * - * Return: - * Upon successful completion, scif_vreadfrom() returns 0; otherwise in user - * mode -1 is returned and errno is set to indicate the error; in kernel mode - * the negative of one of the following errors is returned. - * - * Errors: - * EACCES - Attempt to write to a read-only range - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - rma_flags is invalid - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the - * registered address space of epd - */ -int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset, - int rma_flags); - -/** - * scif_vwriteto() - Copy to a remote address space - * @epd: endpoint descriptor - * @addr: address from which to copy - * @len: length of range to copy - * @roffset: offset in remote registered address space to - * which to copy - * @rma_flags: transfer mode flags - * - * scif_vwriteto() copies len bytes from the local memory, starting at addr, to - * the remote registered address space of the peer of endpoint epd, starting at - * the offset roffset. - * - * The specified range [roffset, roffset + len - 1] must be within some - * registered window or windows of the remote nodes. The range may intersect - * multiple registered windows, but only if those windows are contiguous in the - * registered address space. - * - * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using - * programmed read/writes. Otherwise the data is copied using DMA. If rma_- - * flags includes SCIF_RMA_SYNC, then scif_vwriteto() will return after the - * transfer is complete. Otherwise, the transfer may be performed asynchron- - * ously. The order in which any two asynchronous RMA operations complete - * is non-deterministic. The synchronization functions, scif_fence_mark()/ - * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to - * the completion of asynchronous RMA operations on the same endpoint. - * - * The DMA transfer of individual bytes is not guaranteed to complete in - * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last - * cacheline or partial cacheline of the source range will become visible on - * the destination node after all other transferred data in the source - * range has become visible on the destination node. - * - * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back - * the specified local memory range may be remain in a pinned state even after - * the specified transfer completes. This may reduce overhead if some or all of - * the same virtual address range is referenced in a subsequent call of - * scif_vreadfrom() or scif_vwriteto(). - * - * The optimal DMA performance will likely be realized if both - * addr and offset are cacheline aligned (are a multiple of 64). Lower - * performance will likely be realized if addr and offset are not cacheline - * aligned but are separated by some multiple of 64. The lowest level of - * performance is likely if addr and offset are not separated by a multiple of - * 64. - * - * The rma_flags argument is formed by ORing together zero or more of the - * following values. - * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA - * engine. - * SCIF_RMA_USECACHE - allow registration caching - * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the - * transfer has completed. Passing this flag results in the - * current implementation busy waiting and consuming CPU cycles - * while the DMA transfer is in progress for best performance by - * avoiding the interrupt latency. - * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of - * the source range becomes visible on the destination node - * after all other transferred data in the source range has - * become visible on the destination - * - * Return: - * Upon successful completion, scif_vwriteto() returns 0; otherwise in user - * mode -1 is returned and errno is set to indicate the error; in kernel mode - * the negative of one of the following errors is returned. - * - * Errors: - * EACCES - Attempt to write to a read-only range - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - rma_flags is invalid - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the - * registered address space of epd - */ -int scif_vwriteto(scif_epd_t epd, void *addr, size_t len, off_t roffset, - int rma_flags); - -/** - * scif_fence_mark() - Mark previously issued RMAs - * @epd: endpoint descriptor - * @flags: control flags - * @mark: marked value returned as output. - * - * scif_fence_mark() returns after marking the current set of all uncompleted - * RMAs initiated through the endpoint epd or the current set of all - * uncompleted RMAs initiated through the peer of endpoint epd. The RMAs are - * marked with a value returned at mark. The application may subsequently call - * scif_fence_wait(), passing the value returned at mark, to await completion - * of all RMAs so marked. - * - * The flags argument has exactly one of the following values. - * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint - * epd are marked - * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer - * of endpoint epd are marked - * - * Return: - * Upon successful completion, scif_fence_mark() returns 0; otherwise in user - * mode -1 is returned and errno is set to indicate the error; in kernel mode - * the negative of one of the following errors is returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - flags is invalid - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENOMEM - Insufficient kernel memory was available - */ -int scif_fence_mark(scif_epd_t epd, int flags, int *mark); - -/** - * scif_fence_wait() - Wait for completion of marked RMAs - * @epd: endpoint descriptor - * @mark: mark request - * - * scif_fence_wait() returns after all RMAs marked with mark have completed. - * The value passed in mark must have been obtained in a previous call to - * scif_fence_mark(). - * - * Return: - * Upon successful completion, scif_fence_wait() returns 0; otherwise in user - * mode -1 is returned and errno is set to indicate the error; in kernel mode - * the negative of one of the following errors is returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENOMEM - Insufficient kernel memory was available - */ -int scif_fence_wait(scif_epd_t epd, int mark); - -/** - * scif_fence_signal() - Request a memory update on completion of RMAs - * @epd: endpoint descriptor - * @loff: local offset - * @lval: local value to write to loffset - * @roff: remote offset - * @rval: remote value to write to roffset - * @flags: flags - * - * scif_fence_signal() returns after marking the current set of all uncompleted - * RMAs initiated through the endpoint epd or marking the current set of all - * uncompleted RMAs initiated through the peer of endpoint epd. - * - * If flags includes SCIF_SIGNAL_LOCAL, then on completion of the RMAs in the - * marked set, lval is written to memory at the address corresponding to offset - * loff in the local registered address space of epd. loff must be within a - * registered window. If flags includes SCIF_SIGNAL_REMOTE, then on completion - * of the RMAs in the marked set, rval is written to memory at the address - * corresponding to offset roff in the remote registered address space of epd. - * roff must be within a remote registered window of the peer of epd. Note - * that any specified offset must be DWORD (4 byte / 32 bit) aligned. - * - * The flags argument is formed by OR'ing together the following. - * Exactly one of the following values. - * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint - * epd are marked - * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer - * of endpoint epd are marked - * One or more of the following values. - * SCIF_SIGNAL_LOCAL - On completion of the marked set of RMAs, write lval to - * memory at the address corresponding to offset loff in the local - * registered address space of epd. - * SCIF_SIGNAL_REMOTE - On completion of the marked set of RMAs, write rval to - * memory at the address corresponding to offset roff in the remote - * registered address space of epd. - * - * Return: - * Upon successful completion, scif_fence_signal() returns 0; otherwise in - * user mode -1 is returned and errno is set to indicate the error; in kernel - * mode the negative of one of the following errors is returned. - * - * Errors: - * EBADF, ENOTTY - epd is not a valid endpoint descriptor - * ECONNRESET - Connection reset by peer - * EINVAL - flags is invalid, or loff or roff are not DWORD aligned - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENXIO - loff is invalid for the registered address of epd, or roff is invalid - * for the registered address space, of the peer of epd - */ -int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval, off_t roff, - u64 rval, int flags); - -/** - * scif_get_node_ids() - Return information about online nodes - * @nodes: array in which to return online node IDs - * @len: number of entries in the nodes array - * @self: address to place the node ID of the local node - * - * scif_get_node_ids() fills in the nodes array with up to len node IDs of the - * nodes in the SCIF network. If there is not enough space in nodes, as - * indicated by the len parameter, only len node IDs are returned in nodes. The - * return value of scif_get_node_ids() is the total number of nodes currently in - * the SCIF network. By checking the return value against the len parameter, - * the user may determine if enough space for nodes was allocated. - * - * The node ID of the local node is returned at self. - * - * Return: - * Upon successful completion, scif_get_node_ids() returns the actual number of - * online nodes in the SCIF network including 'self'; otherwise in user mode - * -1 is returned and errno is set to indicate the error; in kernel mode no - * errors are returned. - */ -int scif_get_node_ids(u16 *nodes, int len, u16 *self); - -/** - * scif_pin_pages() - Pin a set of pages - * @addr: Virtual address of range to pin - * @len: Length of range to pin - * @prot_flags: Page protection flags - * @map_flags: Page classification flags - * @pinned_pages: Handle to pinned pages - * - * scif_pin_pages() pins (locks in physical memory) the physical pages which - * back the range of virtual address pages starting at addr and continuing for - * len bytes. addr and len are constrained to be multiples of the page size. A - * successful scif_pin_pages() call returns a handle to pinned_pages which may - * be used in subsequent calls to scif_register_pinned_pages(). - * - * The pages will remain pinned as long as there is a reference against the - * scif_pinned_pages_t value returned by scif_pin_pages() and until - * scif_unpin_pages() is called, passing the scif_pinned_pages_t value. A - * reference is added to a scif_pinned_pages_t value each time a window is - * created by calling scif_register_pinned_pages() and passing the - * scif_pinned_pages_t value. A reference is removed from a - * scif_pinned_pages_t value each time such a window is deleted. - * - * Subsequent operations which change the memory pages to which virtual - * addresses are mapped (such as mmap(), munmap()) have no effect on the - * scif_pinned_pages_t value or windows created against it. - * - * If the process will fork(), it is recommended that the registered - * virtual address range be marked with MADV_DONTFORK. Doing so will prevent - * problems due to copy-on-write semantics. - * - * The prot_flags argument is formed by OR'ing together one or more of the - * following values. - * SCIF_PROT_READ - allow read operations against the pages - * SCIF_PROT_WRITE - allow write operations against the pages - * The map_flags argument can be set as SCIF_MAP_KERNEL to interpret addr as a - * kernel space address. By default, addr is interpreted as a user space - * address. - * - * Return: - * Upon successful completion, scif_pin_pages() returns 0; otherwise the - * negative of one of the following errors is returned. - * - * Errors: - * EINVAL - prot_flags is invalid, map_flags is invalid, or offset is negative - * ENOMEM - Not enough space - */ -int scif_pin_pages(void *addr, size_t len, int prot_flags, int map_flags, - scif_pinned_pages_t *pinned_pages); - -/** - * scif_unpin_pages() - Unpin a set of pages - * @pinned_pages: Handle to pinned pages to be unpinned - * - * scif_unpin_pages() prevents scif_register_pinned_pages() from registering new - * windows against pinned_pages. The physical pages represented by pinned_pages - * will remain pinned until all windows previously registered against - * pinned_pages are deleted (the window is scif_unregister()'d and all - * references to the window are removed (see scif_unregister()). - * - * pinned_pages must have been obtain from a previous call to scif_pin_pages(). - * After calling scif_unpin_pages(), it is an error to pass pinned_pages to - * scif_register_pinned_pages(). - * - * Return: - * Upon successful completion, scif_unpin_pages() returns 0; otherwise the - * negative of one of the following errors is returned. - * - * Errors: - * EINVAL - pinned_pages is not valid - */ -int scif_unpin_pages(scif_pinned_pages_t pinned_pages); - -/** - * scif_register_pinned_pages() - Mark a memory region for remote access. - * @epd: endpoint descriptor - * @pinned_pages: Handle to pinned pages - * @offset: Registered address space offset - * @map_flags: Flags which control where pages are mapped - * - * The scif_register_pinned_pages() function opens a window, a range of whole - * pages of the registered address space of the endpoint epd, starting at - * offset po. The value of po, further described below, is a function of the - * parameters offset and pinned_pages, and the value of map_flags. Each page of - * the window represents a corresponding physical memory page of the range - * represented by pinned_pages; the length of the window is the same as the - * length of range represented by pinned_pages. A successful - * scif_register_pinned_pages() call returns po as the return value. - * - * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset - * exactly, and offset is constrained to be a multiple of the page size. The - * mapping established by scif_register_pinned_pages() will not replace any - * existing registration; an error is returned if any page of the new window - * would intersect an existing window. - * - * When SCIF_MAP_FIXED is not set, the implementation uses offset in an - * implementation-defined manner to arrive at po. The po so chosen will be an - * area of the registered address space that the implementation deems suitable - * for a mapping of the required size. An offset value of 0 is interpreted as - * granting the implementation complete freedom in selecting po, subject to - * constraints described below. A non-zero value of offset is taken to be a - * suggestion of an offset near which the mapping should be placed. When the - * implementation selects a value for po, it does not replace any extant - * window. In all cases, po will be a multiple of the page size. - * - * The physical pages which are so represented by a window are available for - * access in calls to scif_get_pages(), scif_readfrom(), scif_writeto(), - * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the - * physical pages represented by the window will not be reused by the memory - * subsystem for any other purpose. Note that the same physical page may be - * represented by multiple windows. - * - * Windows created by scif_register_pinned_pages() are unregistered by - * scif_unregister(). - * - * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a - * fixed offset. - * - * Return: - * Upon successful completion, scif_register_pinned_pages() returns the offset - * at which the mapping was placed (po); otherwise the negative of one of the - * following errors is returned. - * - * Errors: - * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags and pages in the new window - * would intersect an existing window - * EAGAIN - The mapping could not be performed due to lack of resources - * ECONNRESET - Connection reset by peer - * EINVAL - map_flags is invalid, or SCIF_MAP_FIXED is set in map_flags, and - * offset is not a multiple of the page size, or offset is negative - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOMEM - Not enough space - * ENOTCONN - The endpoint is not connected - */ -off_t scif_register_pinned_pages(scif_epd_t epd, - scif_pinned_pages_t pinned_pages, - off_t offset, int map_flags); - -/** - * scif_get_pages() - Add references to remote registered pages - * @epd: endpoint descriptor - * @offset: remote registered offset - * @len: length of range of pages - * @pages: returned scif_range structure - * - * scif_get_pages() returns the addresses of the physical pages represented by - * those pages of the registered address space of the peer of epd, starting at - * offset and continuing for len bytes. offset and len are constrained to be - * multiples of the page size. - * - * All of the pages in the specified range [offset, offset + len - 1] must be - * within a single window of the registered address space of the peer of epd. - * - * The addresses are returned as a virtually contiguous array pointed to by the - * phys_addr component of the scif_range structure whose address is returned in - * pages. The nr_pages component of scif_range is the length of the array. The - * prot_flags component of scif_range holds the protection flag value passed - * when the pages were registered. - * - * Each physical page whose address is returned by scif_get_pages() remains - * available and will not be released for reuse until the scif_range structure - * is returned in a call to scif_put_pages(). The scif_range structure returned - * by scif_get_pages() must be unmodified. - * - * It is an error to call scif_close() on an endpoint on which a scif_range - * structure of that endpoint has not been returned to scif_put_pages(). - * - * Return: - * Upon successful completion, scif_get_pages() returns 0; otherwise the - * negative of one of the following errors is returned. - * Errors: - * ECONNRESET - Connection reset by peer. - * EINVAL - offset is not a multiple of the page size, or offset is negative, or - * len is not a multiple of the page size - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid - * for the registered address space of the peer epd - */ -int scif_get_pages(scif_epd_t epd, off_t offset, size_t len, - struct scif_range **pages); - -/** - * scif_put_pages() - Remove references from remote registered pages - * @pages: pages to be returned - * - * scif_put_pages() releases a scif_range structure previously obtained by - * calling scif_get_pages(). The physical pages represented by pages may - * be reused when the window which represented those pages is unregistered. - * Therefore, those pages must not be accessed after calling scif_put_pages(). - * - * Return: - * Upon successful completion, scif_put_pages() returns 0; otherwise the - * negative of one of the following errors is returned. - * Errors: - * EINVAL - pages does not point to a valid scif_range structure, or - * the scif_range structure pointed to by pages was already returned - * ENODEV - The remote node is lost or existed, but is not currently in the - * network since it may have crashed - * ENOTCONN - The endpoint is not connected - */ -int scif_put_pages(struct scif_range *pages); - -/** - * scif_poll() - Wait for some event on an endpoint - * @epds: Array of endpoint descriptors - * @nepds: Length of epds - * @timeout: Upper limit on time for which scif_poll() will block - * - * scif_poll() waits for one of a set of endpoints to become ready to perform - * an I/O operation. - * - * The epds argument specifies the endpoint descriptors to be examined and the - * events of interest for each endpoint descriptor. epds is a pointer to an - * array with one member for each open endpoint descriptor of interest. - * - * The number of items in the epds array is specified in nepds. The epd field - * of scif_pollepd is an endpoint descriptor of an open endpoint. The field - * events is a bitmask specifying the events which the application is - * interested in. The field revents is an output parameter, filled by the - * kernel with the events that actually occurred. The bits returned in revents - * can include any of those specified in events, or one of the values EPOLLERR, - * EPOLLHUP, or EPOLLNVAL. (These three bits are meaningless in the events - * field, and will be set in the revents field whenever the corresponding - * condition is true.) - * - * If none of the events requested (and no error) has occurred for any of the - * endpoint descriptors, then scif_poll() blocks until one of the events occurs. - * - * The timeout argument specifies an upper limit on the time for which - * scif_poll() will block, in milliseconds. Specifying a negative value in - * timeout means an infinite timeout. - * - * The following bits may be set in events and returned in revents. - * EPOLLIN - Data may be received without blocking. For a connected - * endpoint, this means that scif_recv() may be called without blocking. For a - * listening endpoint, this means that scif_accept() may be called without - * blocking. - * EPOLLOUT - Data may be sent without blocking. For a connected endpoint, this - * means that scif_send() may be called without blocking. EPOLLOUT may also be - * used to block waiting for a non-blocking connect to complete. This bit value - * has no meaning for a listening endpoint and is ignored if specified. - * - * The following bits are only returned in revents, and are ignored if set in - * events. - * EPOLLERR - An error occurred on the endpoint - * EPOLLHUP - The connection to the peer endpoint was disconnected - * EPOLLNVAL - The specified endpoint descriptor is invalid. - * - * Return: - * Upon successful completion, scif_poll() returns a non-negative value. A - * positive value indicates the total number of endpoint descriptors that have - * been selected (that is, endpoint descriptors for which the revents member is - * non-zero). A value of 0 indicates that the call timed out and no endpoint - * descriptors have been selected. Otherwise in user mode -1 is returned and - * errno is set to indicate the error; in kernel mode the negative of one of - * the following errors is returned. - * - * Errors: - * EINTR - A signal occurred before any requested event - * EINVAL - The nepds argument is greater than {OPEN_MAX} - * ENOMEM - There was no space to allocate file descriptor tables - */ -int scif_poll(struct scif_pollepd *epds, unsigned int nepds, long timeout); - -/** - * scif_client_register() - Register a SCIF client - * @client: client to be registered - * - * scif_client_register() registers a SCIF client. The probe() method - * of the client is called when SCIF peer devices come online and the - * remove() method is called when the peer devices disappear. - * - * Return: - * Upon successful completion, scif_client_register() returns a non-negative - * value. Otherwise the return value is the same as subsys_interface_register() - * in the kernel. - */ -int scif_client_register(struct scif_client *client); - -/** - * scif_client_unregister() - Unregister a SCIF client - * @client: client to be unregistered - * - * scif_client_unregister() unregisters a SCIF client. - * - * Return: - * None - */ -void scif_client_unregister(struct scif_client *client); - -#endif /* __SCIF_H__ */ diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h deleted file mode 100644 index 504e523f702c..000000000000 --- a/include/uapi/linux/mic_common.h +++ /dev/null @@ -1,235 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Intel MIC Platform Software Stack (MPSS) - * - * Copyright(c) 2013 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License, version 2, as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Intel MIC driver. - * - */ -#ifndef __MIC_COMMON_H_ -#define __MIC_COMMON_H_ - -#include - -#define __mic_align(a, x) (((a) + (x) - 1) & ~((x) - 1)) - -/** - * struct mic_device_desc: Virtio device information shared between the - * virtio driver and userspace backend - * - * @type: Device type: console/network/disk etc. Type 0/-1 terminates. - * @num_vq: Number of virtqueues. - * @feature_len: Number of bytes of feature bits. Multiply by 2: one for - host features and one for guest acknowledgements. - * @config_len: Number of bytes of the config array after virtqueues. - * @status: A status byte, written by the Guest. - * @config: Start of the following variable length config. - */ -struct mic_device_desc { - __s8 type; - __u8 num_vq; - __u8 feature_len; - __u8 config_len; - __u8 status; - __le64 config[0]; -} __attribute__ ((aligned(8))); - -/** - * struct mic_device_ctrl: Per virtio device information in the device page - * used internally by the host and card side drivers. - * - * @vdev: Used for storing MIC vdev information by the guest. - * @config_change: Set to 1 by host when a config change is requested. - * @vdev_reset: Set to 1 by guest to indicate virtio device has been reset. - * @guest_ack: Set to 1 by guest to ack a command. - * @host_ack: Set to 1 by host to ack a command. - * @used_address_updated: Set to 1 by guest when the used address should be - * updated. - * @c2h_vdev_db: The doorbell number to be used by guest. Set by host. - * @h2c_vdev_db: The doorbell number to be used by host. Set by guest. - */ -struct mic_device_ctrl { - __le64 vdev; - __u8 config_change; - __u8 vdev_reset; - __u8 guest_ack; - __u8 host_ack; - __u8 used_address_updated; - __s8 c2h_vdev_db; - __s8 h2c_vdev_db; -} __attribute__ ((aligned(8))); - -/** - * struct mic_bootparam: Virtio device independent information in device page - * - * @magic: A magic value used by the card to ensure it can see the host - * @h2c_config_db: Host to Card Virtio config doorbell set by card - * @node_id: Unique id of the node - * @h2c_scif_db - Host to card SCIF doorbell set by card - * @c2h_scif_db - Card to host SCIF doorbell set by host - * @scif_host_dma_addr - SCIF host queue pair DMA address - * @scif_card_dma_addr - SCIF card queue pair DMA address - */ -struct mic_bootparam { - __le32 magic; - __s8 h2c_config_db; - __u8 node_id; - __u8 h2c_scif_db; - __u8 c2h_scif_db; - __u64 scif_host_dma_addr; - __u64 scif_card_dma_addr; -} __attribute__ ((aligned(8))); - -/** - * struct mic_device_page: High level representation of the device page - * - * @bootparam: The bootparam structure is used for sharing information and - * status updates between MIC host and card drivers. - * @desc: Array of MIC virtio device descriptors. - */ -struct mic_device_page { - struct mic_bootparam bootparam; - struct mic_device_desc desc[0]; -}; -/** - * struct mic_vqconfig: This is how we expect the device configuration field - * for a virtqueue to be laid out in config space. - * - * @address: Guest/MIC physical address of the virtio ring - * (avail and desc rings) - * @used_address: Guest/MIC physical address of the used ring - * @num: The number of entries in the virtio_ring - */ -struct mic_vqconfig { - __le64 address; - __le64 used_address; - __le16 num; -} __attribute__ ((aligned(8))); - -/* - * The alignment to use between consumer and producer parts of vring. - * This is pagesize for historical reasons. - */ -#define MIC_VIRTIO_RING_ALIGN 4096 - -#define MIC_MAX_VRINGS 4 -#define MIC_VRING_ENTRIES 128 - -/* - * Max vring entries (power of 2) to ensure desc and avail rings - * fit in a single page - */ -#define MIC_MAX_VRING_ENTRIES 128 - -/** - * Max size of the desc block in bytes: includes: - * - struct mic_device_desc - * - struct mic_vqconfig (num_vq of these) - * - host and guest features - * - virtio device config space - */ -#define MIC_MAX_DESC_BLK_SIZE 256 - -/** - * struct _mic_vring_info - Host vring info exposed to userspace backend - * for the avail index and magic for the card. - * - * @avail_idx: host avail idx - * @magic: A magic debug cookie. - */ -struct _mic_vring_info { - __u16 avail_idx; - __le32 magic; -}; - -/** - * struct mic_vring - Vring information. - * - * @vr: The virtio ring. - * @info: Host vring information exposed to the userspace backend for the - * avail index and magic for the card. - * @va: The va for the buffer allocated for vr and info. - * @len: The length of the buffer required for allocating vr and info. - */ -struct mic_vring { - struct vring vr; - struct _mic_vring_info *info; - void *va; - int len; -}; - -#define mic_aligned_desc_size(d) __mic_align(mic_desc_size(d), 8) - -#ifndef INTEL_MIC_CARD -static inline unsigned mic_desc_size(const struct mic_device_desc *desc) -{ - return sizeof(*desc) + desc->num_vq * sizeof(struct mic_vqconfig) - + desc->feature_len * 2 + desc->config_len; -} - -static inline struct mic_vqconfig * -mic_vq_config(const struct mic_device_desc *desc) -{ - return (struct mic_vqconfig *)(desc + 1); -} - -static inline __u8 *mic_vq_features(const struct mic_device_desc *desc) -{ - return (__u8 *)(mic_vq_config(desc) + desc->num_vq); -} - -static inline __u8 *mic_vq_configspace(const struct mic_device_desc *desc) -{ - return mic_vq_features(desc) + desc->feature_len * 2; -} -static inline unsigned mic_total_desc_size(struct mic_device_desc *desc) -{ - return mic_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl); -} -#endif - -/* Device page size */ -#define MIC_DP_SIZE 4096 - -#define MIC_MAGIC 0xc0ffee00 - -/** - * enum mic_states - MIC states. - */ -enum mic_states { - MIC_READY = 0, - MIC_BOOTING, - MIC_ONLINE, - MIC_SHUTTING_DOWN, - MIC_RESETTING, - MIC_RESET_FAILED, - MIC_LAST -}; - -/** - * enum mic_status - MIC status reported by card after - * a host or card initiated shutdown or a card crash. - */ -enum mic_status { - MIC_NOP = 0, - MIC_CRASHED, - MIC_HALTED, - MIC_POWER_OFF, - MIC_RESTART, - MIC_STATUS_LAST -}; - -#endif diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h deleted file mode 100644 index 687b9cd9d3e2..000000000000 --- a/include/uapi/linux/mic_ioctl.h +++ /dev/null @@ -1,77 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Intel MIC Platform Software Stack (MPSS) - * - * Copyright(c) 2013 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License, version 2, as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Intel MIC Host driver. - * - */ -#ifndef _MIC_IOCTL_H_ -#define _MIC_IOCTL_H_ - -#include - -/* - * mic_copy - MIC virtio descriptor copy. - * - * @iov: An array of IOVEC structures containing user space buffers. - * @iovcnt: Number of IOVEC structures in iov. - * @vr_idx: The vring index. - * @update_used: A non zero value results in used index being updated. - * @out_len: The aggregate of the total length written to or read from - * the virtio device. - */ -struct mic_copy_desc { -#ifdef __KERNEL__ - struct iovec __user *iov; -#else - struct iovec *iov; -#endif - __u32 iovcnt; - __u8 vr_idx; - __u8 update_used; - __u32 out_len; -}; - -/* - * Add a new virtio device - * The (struct mic_device_desc *) pointer points to a device page entry - * for the virtio device consisting of: - * - struct mic_device_desc - * - struct mic_vqconfig (num_vq of these) - * - host and guest features - * - virtio device config space - * The total size referenced by the pointer should equal the size returned - * by desc_size() in mic_common.h - */ -#define MIC_VIRTIO_ADD_DEVICE _IOWR('s', 1, struct mic_device_desc *) - -/* - * Copy the number of entries in the iovec and update the used index - * if requested by the user. - */ -#define MIC_VIRTIO_COPY_DESC _IOWR('s', 2, struct mic_copy_desc *) - -/* - * Notify virtio device of a config change - * The (__u8 *) pointer points to config space values for the device - * as they should be written into the device page. The total size - * referenced by the pointer should equal the config_len field of struct - * mic_device_desc. - */ -#define MIC_VIRTIO_CONFIG_CHANGE _IOWR('s', 5, __u8 *) - -#endif -- cgit v1.2.3 From a62f68f5ca53ab61cba2f0a410d0add7a6d54a52 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 23 Oct 2020 17:35:46 +0200 Subject: cpufreq: Introduce cpufreq_driver_test_flags() Add a helper function to test the flags of the cpufreq driver in use againt a given flags mask. In particular, this will be needed to test the CPUFREQ_NEED_UPDATE_LIMITS cpufreq driver flag in the schedutil governor. Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 038ed83aab41..1eaa04f1bae6 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -433,6 +433,7 @@ struct cpufreq_driver { int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); +bool cpufreq_driver_test_flags(u16 flags); const char *cpufreq_get_current_driver(void); void *cpufreq_get_driver_data(void); -- cgit v1.2.3 From 185f0c7073bd5c78f86265f703f5daf1306ab5a7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 26 Oct 2020 13:22:47 +0000 Subject: afs: Wrap page->private manipulations in inline functions The afs filesystem uses page->private to store the dirty range within a page such that in the event of a conflicting 3rd-party write to the server, we write back just the bits that got changed locally. However, there are a couple of problems with this: (1) I need a bit to note if the page might be mapped so that partial invalidation doesn't shrink the range. (2) There aren't necessarily sufficient bits to store the entire range of data altered (say it's a 32-bit system with 64KiB pages or transparent huge pages are in use). So wrap the accesses in inline functions so that future commits can change how this works. Also move them out of the tracing header into the in-directory header. There's not really any need for them to be in the tracing header. Signed-off-by: David Howells --- include/trace/events/afs.h | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 8eb49231c6bb..866fc67d5aa5 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -966,19 +966,6 @@ TRACE_EVENT(afs_dir_check_failed, __entry->vnode, __entry->off, __entry->i_size) ); -/* - * We use page->private to hold the amount of the page that we've written to, - * splitting the field into two parts. However, we need to represent a range - * 0...PAGE_SIZE inclusive, so we can't support 64K pages on a 32-bit system. - */ -#if PAGE_SIZE > 32768 -#define AFS_PRIV_MAX 0xffffffff -#define AFS_PRIV_SHIFT 32 -#else -#define AFS_PRIV_MAX 0xffff -#define AFS_PRIV_SHIFT 16 -#endif - TRACE_EVENT(afs_page_dirty, TP_PROTO(struct afs_vnode *vnode, const char *where, pgoff_t page, unsigned long priv), @@ -999,10 +986,10 @@ TRACE_EVENT(afs_page_dirty, __entry->priv = priv; ), - TP_printk("vn=%p %lx %s %lu-%lu", + TP_printk("vn=%p %lx %s %zx-%zx", __entry->vnode, __entry->page, __entry->where, - __entry->priv & AFS_PRIV_MAX, - __entry->priv >> AFS_PRIV_SHIFT) + afs_page_dirty_from(__entry->priv), + afs_page_dirty_to(__entry->priv)) ); TRACE_EVENT(afs_call_state, -- cgit v1.2.3 From f86726a69dec5df6ba051baf9265584419478b64 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 22 Oct 2020 14:08:23 +0100 Subject: afs: Fix afs_invalidatepage to adjust the dirty region Fix afs_invalidatepage() to adjust the dirty region recorded in page->private when truncating a page. If the dirty region is entirely removed, then the private data is cleared and the page dirty state is cleared. Without this, if the page is truncated and then expanded again by truncate, zeros from the expanded, but no-longer dirty region may get written back to the server if the page gets laundered due to a conflicting 3rd-party write. It mustn't, however, shorten the dirty region of the page if that page is still mmapped and has been marked dirty by afs_page_mkwrite(), so a flag is stored in page->private to record this. Fixes: 4343d00872e1 ("afs: Get rid of the afs_writeback record") Signed-off-by: David Howells --- include/trace/events/afs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 866fc67d5aa5..4eef374d4413 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -986,10 +986,11 @@ TRACE_EVENT(afs_page_dirty, __entry->priv = priv; ), - TP_printk("vn=%p %lx %s %zx-%zx", + TP_printk("vn=%p %lx %s %zx-%zx%s", __entry->vnode, __entry->page, __entry->where, afs_page_dirty_from(__entry->priv), - afs_page_dirty_to(__entry->priv)) + afs_page_dirty_to(__entry->priv), + afs_is_page_dirty_mmapped(__entry->priv) ? " M" : "") ); TRACE_EVENT(afs_call_state, -- cgit v1.2.3 From 4169e889e5889405d54cec27d6e9f7f0ce3c7096 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 2 Sep 2020 23:25:55 -0500 Subject: include: jhash/signal: Fix fall-through warnings for Clang In preparation to enable -Wimplicit-fallthrough for Clang, explicitly add break statements instead of letting the code fall through to the next case. This patch adds four break statements that, together, fix almost 40,000 warnings when building Linux 5.10-rc1 with Clang 12.0.0 and this[1] change reverted. Notice that in order to enable -Wimplicit-fallthrough for Clang, such change[1] is meant to be reverted at some point. So, this patch helps to move in that direction. Something important to mention is that there is currently a discrepancy between GCC and Clang when dealing with switch fall-through to empty case statements or to cases that only contain a break/continue/return statement[2][3][4]. Now that the -Wimplicit-fallthrough option has been globally enabled[5], any compiler should really warn on missing either a fallthrough annotation or any of the other case-terminating statements (break/continue/return/ goto) when falling through to the next case statement. Making exceptions to this introduces variation in case handling which may continue to lead to bugs, misunderstandings, and a general lack of robustness. The point of enabling options like -Wimplicit-fallthrough is to prevent human error and aid developers in spotting bugs before their code is even built/ submitted/committed, therefore eliminating classes of bugs. So, in order to really accomplish this, we should, and can, move in the direction of addressing any error-prone scenarios and get rid of the unintentional fallthrough bug-class in the kernel, entirely, even if there is some minor redundancy. Better to have explicit case-ending statements than continue to have exceptions where one must guess as to the right result. The compiler will eliminate any actual redundancy. [1] commit e2079e93f562c ("kbuild: Do not enable -Wimplicit-fallthrough for clang for now") [2] https://github.com/ClangBuiltLinux/linux/issues/636 [3] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91432 [4] https://godbolt.org/z/xgkvIh [5] commit a035d552a93b ("Makefile: Globally enable fall-through warning") Co-developed-by: Kees Cook Signed-off-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- include/linux/jhash.h | 2 ++ include/linux/signal.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/jhash.h b/include/linux/jhash.h index cfb62e9f37be..ab7f8c152b89 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -99,6 +99,7 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); + break; case 0: /* Nothing left to add */ break; } @@ -136,6 +137,7 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); + break; case 0: /* Nothing left to add */ break; } diff --git a/include/linux/signal.h b/include/linux/signal.h index 7bbc0e9cf084..b256f9c65661 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -238,6 +238,7 @@ static inline void siginitset(sigset_t *set, unsigned long mask) memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = 0; + break; case 1: ; } } @@ -250,6 +251,7 @@ static inline void siginitsetinv(sigset_t *set, unsigned long mask) memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = -1; + break; case 1: ; } } -- cgit v1.2.3 From a4147d855f50a676ebe61833a681f7c71945f343 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 31 Aug 2020 10:18:04 -0500 Subject: dmaengine: ti-cppi5: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Gustavo A. R. Silva --- include/linux/dma/ti-cppi5.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h index 5896441ee604..efa2f0309f00 100644 --- a/include/linux/dma/ti-cppi5.h +++ b/include/linux/dma/ti-cppi5.h @@ -47,7 +47,7 @@ struct cppi5_host_desc_t { u32 buf_info1; u32 org_buf_len; u64 org_buf_ptr; - u32 epib[0]; + u32 epib[]; } __packed; #define CPPI5_DESC_MIN_ALIGN (16U) @@ -139,7 +139,7 @@ struct cppi5_desc_epib_t { */ struct cppi5_monolithic_desc_t { struct cppi5_desc_hdr_t hdr; - u32 epib[0]; + u32 epib[]; }; #define CPPI5_INFO2_MDESC_DATA_OFFSET_SHIFT (18U) -- cgit v1.2.3 From 277ffd6c1ec0aa60856a03e18455fcca7d2a1186 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 31 Aug 2020 10:19:18 -0500 Subject: mailbox: zynqmp-ipi-message: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Gustavo A. R. Silva --- include/linux/mailbox/zynqmp-ipi-message.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mailbox/zynqmp-ipi-message.h b/include/linux/mailbox/zynqmp-ipi-message.h index 9542b41eacfd..35ce84c8ca02 100644 --- a/include/linux/mailbox/zynqmp-ipi-message.h +++ b/include/linux/mailbox/zynqmp-ipi-message.h @@ -14,7 +14,7 @@ */ struct zynqmp_ipi_message { size_t len; - u8 data[0]; + u8 data[]; }; #endif /* _LINUX_ZYNQMP_IPI_MESSAGE_H_ */ -- cgit v1.2.3 From 883541051567a62add043a9f4ca5a31f2970bffd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 31 Aug 2020 10:21:14 -0500 Subject: platform/chrome: cros_ec_commands: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Gustavo A. R. Silva --- include/linux/platform_data/cros_ec_commands.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 1fcfe9e63cb9..a3a9a878415f 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -1419,7 +1419,7 @@ struct ec_response_flash_info_2 { uint16_t num_banks_total; /* Number of banks described in banks array. */ uint16_t num_banks_desc; - struct ec_flash_bank banks[0]; + struct ec_flash_bank banks[]; } __ec_align4; /* @@ -2420,12 +2420,12 @@ struct ec_response_motion_sense_fifo_info { /* Total amount of vector lost */ uint16_t total_lost; /* Lost events since the last fifo_info, per sensors */ - uint16_t lost[0]; + uint16_t lost[]; } __ec_todo_packed; struct ec_response_motion_sense_fifo_data { uint32_t number_data; - struct ec_response_motion_sensor_data data[0]; + struct ec_response_motion_sensor_data data[]; } __ec_todo_packed; /* List supported activity recognition */ @@ -3093,7 +3093,7 @@ struct ec_response_tmp006_get_calibration_v1 { uint8_t algorithm; uint8_t num_params; uint8_t reserved[2]; - float val[0]; + float val[]; } __ec_align4; struct ec_params_tmp006_set_calibration_v1 { @@ -3101,7 +3101,7 @@ struct ec_params_tmp006_set_calibration_v1 { uint8_t algorithm; uint8_t num_params; uint8_t reserved; - float val[0]; + float val[]; } __ec_align4; @@ -5076,7 +5076,7 @@ struct ec_response_pd_log { uint8_t type; /* event type : see PD_EVENT_xx below */ uint8_t size_port; /* [7:5] port number [4:0] payload size in bytes */ uint16_t data; /* type-defined data payload */ - uint8_t payload[0]; /* optional additional data payload: 0..16 bytes */ + uint8_t payload[]; /* optional additional data payload: 0..16 bytes */ } __ec_align4; /* The timestamp is the microsecond counter shifted to get about a ms. */ @@ -5789,7 +5789,7 @@ struct ec_response_fp_encryption_status { struct ec_response_tp_frame_info { uint32_t n_frames; - uint32_t frame_sizes[0]; + uint32_t frame_sizes[]; } __ec_align4; /* Create a snapshot of current frame readings */ -- cgit v1.2.3 From 120088832042e6dc9866160ff267f8c347bf53e6 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 31 Aug 2020 10:21:55 -0500 Subject: platform/chrome: cros_ec_proto: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Gustavo A. R. Silva --- include/linux/platform_data/cros_ec_proto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 4a415ae851ef..02599687770c 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -69,7 +69,7 @@ struct cros_ec_command { uint32_t outsize; uint32_t insize; uint32_t result; - uint8_t data[0]; + uint8_t data[]; }; /** -- cgit v1.2.3 From 5e01fdff04b7f7c3b8d456c11c8a9f978b4ddf65 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 31 Aug 2020 08:25:42 -0500 Subject: fs: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Gustavo A. R. Silva --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0bd126418bb6..21cc971fd960 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3285,7 +3285,7 @@ static inline ino_t parent_ino(struct dentry *dentry) */ struct simple_transaction_argresp { ssize_t size; - char data[0]; + char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) -- cgit v1.2.3 From 0d519cbf38eed4f895aed197d4b135fa7f60f7c2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 23 Oct 2020 15:10:37 +0200 Subject: debugfs: remove return value of debugfs_create_devm_seqfile() No one checks the return value of debugfs_create_devm_seqfile(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20201023131037.2500765-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 851dd1f9a8a5..d6c4cc9ecc77 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -144,10 +144,9 @@ void debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, struct debugfs_u32_array *array); -struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, - struct dentry *parent, - int (*read_fn)(struct seq_file *s, - void *data)); +void debugfs_create_devm_seqfile(struct device *dev, const char *name, + struct dentry *parent, + int (*read_fn)(struct seq_file *s, void *data)); bool debugfs_initialized(void); @@ -327,13 +326,12 @@ static inline void debugfs_create_u32_array(const char *name, umode_t mode, { } -static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev, - const char *name, - struct dentry *parent, - int (*read_fn)(struct seq_file *s, - void *data)) +static inline void debugfs_create_devm_seqfile(struct device *dev, + const char *name, + struct dentry *parent, + int (*read_fn)(struct seq_file *s, + void *data)) { - return ERR_PTR(-ENODEV); } static inline ssize_t debugfs_read_file_bool(struct file *file, -- cgit v1.2.3 From b1e8eb11fb9cf666d8ae36bbcf533233a504c921 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 23 Oct 2020 18:33:08 +0200 Subject: mac80211: fix kernel-doc markups Some identifiers have different names between their prototypes and the kernel-doc markup. Others need to be fixed, as kernel-doc markups should use this format: identifier - description In the specific case of __sta_info_flush(), add a documentation for sta_info_flush(), as this one is the one used outside sta_info.c. Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Johannes Berg Link: https://lore.kernel.org/r/978d35eef2dc76e21c81931804e4eaefbd6d635e.1603469755.git.mchehab+huawei@kernel.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 9 +++++---- include/net/mac80211.h | 7 ++++--- 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 661edfc8722e..d5ab8d99739f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1444,7 +1444,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, enum cfg80211_station_type statype); /** - * enum station_info_rate_flags - bitrate info flags + * enum rate_info_flags - bitrate info flags * * Used by the driver to indicate the specific rate transmission * type for 802.11n transmissions. @@ -1517,7 +1517,7 @@ struct rate_info { }; /** - * enum station_info_rate_flags - bitrate info flags + * enum bss_param_flags - bitrate info flags * * Used by the driver to indicate the specific rate transmission * type for 802.11n transmissions. @@ -6467,7 +6467,8 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, struct ieee80211_channel *channel, gfp_t gfp); /** - * cfg80211_notify_new_candidate - notify cfg80211 of a new mesh peer candidate + * cfg80211_notify_new_peer_candidate - notify cfg80211 of a new mesh peer + * candidate * * @dev: network device * @macaddr: the MAC address of the new candidate @@ -7606,7 +7607,7 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate); void cfg80211_unregister_wdev(struct wireless_dev *wdev); /** - * struct cfg80211_ft_event - FT Information Elements + * struct cfg80211_ft_event_params - FT Information Elements * @ies: FT IEs * @ies_len: length of the FT IE in bytes * @target_ap: target AP's MAC address diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e8e295dae744..dcdba96814a2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3311,7 +3311,7 @@ enum ieee80211_roc_type { }; /** - * enum ieee80211_reconfig_complete_type - reconfig type + * enum ieee80211_reconfig_type - reconfig type * * This enum is used by the reconfig_complete() callback to indicate what * reconfiguration type was completed. @@ -6334,7 +6334,8 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, int band, struct ieee80211_sta **sta); /** - * Sanity-check and parse the radiotap header of injected frames + * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header + * of injected frames * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device */ @@ -6389,7 +6390,7 @@ int ieee80211_parse_p2p_noa(const struct ieee80211_p2p_noa_attr *attr, void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf); /** - * ieee80211_tdls_oper - request userspace to perform a TDLS operation + * ieee80211_tdls_oper_request - request userspace to perform a TDLS operation * @vif: virtual interface * @peer: the peer's destination address * @oper: the requested TDLS operation -- cgit v1.2.3 From 46d6c5ae953cc0be38efd0e469284df7c4328cf8 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 29 Oct 2020 03:56:06 +0100 Subject: netfilter: use actual socket sk rather than skb sk when routing harder If netfilter changes the packet mark when mangling, the packet is rerouted using the route_me_harder set of functions. Prior to this commit, there's one big difference between route_me_harder and the ordinary initial routing functions, described in the comment above __ip_queue_xmit(): /* Note: skb->sk can be different from sk, in case of tunnels */ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, That function goes on to correctly make use of sk->sk_bound_dev_if, rather than skb->sk->sk_bound_dev_if. And indeed the comment is true: a tunnel will receive a packet in ndo_start_xmit with an initial skb->sk. It will make some transformations to that packet, and then it will send the encapsulated packet out of a *new* socket. That new socket will basically always have a different sk_bound_dev_if (otherwise there'd be a routing loop). So for the purposes of routing the encapsulated packet, the routing information as it pertains to the socket should come from that socket's sk, rather than the packet's original skb->sk. For that reason __ip_queue_xmit() and related functions all do the right thing. One might argue that all tunnels should just call skb_orphan(skb) before transmitting the encapsulated packet into the new socket. But tunnels do *not* do this -- and this is wisely avoided in skb_scrub_packet() too -- because features like TSQ rely on skb->destructor() being called when that buffer space is truely available again. Calling skb_orphan(skb) too early would result in buffers filling up unnecessarily and accounting info being all wrong. Instead, additional routing must take into account the new sk, just as __ip_queue_xmit() notes. So, this commit addresses the problem by fishing the correct sk out of state->sk -- it's already set properly in the call to nf_hook() in __ip_local_out(), which receives the sk as part of its normal functionality. So we make sure to plumb state->sk through the various route_me_harder functions, and then make correct use of it following the example of __ip_queue_xmit(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jason A. Donenfeld Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4.h | 2 +- include/linux/netfilter_ipv6.h | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 082e2c41b7ff..5b70ca868bb1 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -16,7 +16,7 @@ struct ip_rt_info { u_int32_t mark; }; -int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type); +int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type); struct nf_queue_entry; diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 9b67394471e1..48314ade1506 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -42,7 +42,7 @@ struct nf_ipv6_ops { #if IS_MODULE(CONFIG_IPV6) int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); - int (*route_me_harder)(struct net *net, struct sk_buff *skb); + int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*dev_get_saddr)(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); @@ -143,9 +143,9 @@ static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk, #endif } -int ip6_route_me_harder(struct net *net, struct sk_buff *skb); +int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb); -static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) +static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb) { #if IS_MODULE(CONFIG_IPV6) const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); @@ -153,9 +153,9 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!v6_ops) return -EHOSTUNREACH; - return v6_ops->route_me_harder(net, skb); + return v6_ops->route_me_harder(net, sk, skb); #elif IS_BUILTIN(CONFIG_IPV6) - return ip6_route_me_harder(net, skb); + return ip6_route_me_harder(net, sk, skb); #else return -EHOSTUNREACH; #endif -- cgit v1.2.3 From c0391b6ab810381df632677a1dcbbbbd63d05b6d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 29 Oct 2020 13:50:03 +0100 Subject: netfilter: nf_tables: missing validation from the abort path If userspace does not include the trailing end of batch message, then nfnetlink aborts the transaction. This allows to check that ruleset updates trigger no errors. After this patch, invoking this command from the prerouting chain: # nft -c add rule x y fib saddr . oif type local fails since oif is not supported there. This patch fixes the lack of rule validation from the abort/check path to catch configuration errors such as the one above. Fixes: a654de8fdc18 ("netfilter: nf_tables: fix chain dependency validation") Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 89016d08f6a2..f6267e2883f2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -24,6 +24,12 @@ struct nfnl_callback { const u_int16_t attr_count; /* number of nlattr's */ }; +enum nfnl_abort_action { + NFNL_ABORT_NONE = 0, + NFNL_ABORT_AUTOLOAD, + NFNL_ABORT_VALIDATE, +}; + struct nfnetlink_subsystem { const char *name; __u8 subsys_id; /* nfnetlink subsystem ID */ @@ -31,7 +37,8 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); - int (*abort)(struct net *net, struct sk_buff *skb, bool autoload); + int (*abort)(struct net *net, struct sk_buff *skb, + enum nfnl_abort_action action); void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; -- cgit v1.2.3 From 290562075d4d9e85b7ff4104f9a634ffc3cccb69 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 27 Oct 2020 15:28:40 -0500 Subject: net/mlx5: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Gustavo A. R. Silva --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 651591a2965d..a092346c7b2d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5823,7 +5823,7 @@ struct mlx5_ifc_alloc_modify_header_context_in_bits { u8 reserved_at_68[0x10]; u8 num_of_actions[0x8]; - union mlx5_ifc_set_add_copy_action_in_auto_bits actions[0]; + union mlx5_ifc_set_add_copy_action_in_auto_bits actions[]; }; struct mlx5_ifc_dealloc_modify_header_context_out_bits { @@ -9761,7 +9761,7 @@ struct mlx5_ifc_mcda_reg_bits { u8 reserved_at_60[0x20]; - u8 data[0][0x20]; + u8 data[][0x20]; }; enum { -- cgit v1.2.3 From b59e286be280fa3c2e94a0716ddcee6ba02bc8ba Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 27 Oct 2020 20:33:12 +0800 Subject: ICMPv6: Add ICMPv6 Parameter Problem, code 3 definition Based on RFC7112, Section 6: IANA has added the following "Type 4 - Parameter Problem" message to the "Internet Control Message Protocol version 6 (ICMPv6) Parameters" registry: CODE NAME/DESCRIPTION 3 IPv6 First Fragment has incomplete IPv6 Header Chain Signed-off-by: Hangbin Liu Signed-off-by: Jakub Kicinski --- include/uapi/linux/icmpv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index c1661febc2dc..0564fd7ccde4 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -138,6 +138,7 @@ struct icmp6hdr { #define ICMPV6_HDR_FIELD 0 #define ICMPV6_UNK_NEXTHDR 1 #define ICMPV6_UNK_OPTION 2 +#define ICMPV6_HDR_INCOMP 3 /* * constants for (set|get)sockopt -- cgit v1.2.3 From e0e398e204634db8fb71bd89cf2f6e3e5bd09b51 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 21 Oct 2020 21:12:15 +0200 Subject: PM: runtime: Drop runtime PM references to supplier on link removal While removing a device link, drop the supplier device's runtime PM usage counter as many times as needed to drop all of the runtime PM references to it from the consumer in addition to dropping the consumer's link count. Fixes: baa8809f6097 ("PM / runtime: Optimize the use of device links") Signed-off-by: Rafael J. Wysocki Cc: 5.1+ # 5.1+ Tested-by: Xiang Chen Reviewed-by: Greg Kroah-Hartman --- include/linux/pm_runtime.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 18b02dcc168e..eadc1fdebce6 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -58,7 +58,7 @@ extern void pm_runtime_clean_up_links(struct device *dev); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); -extern void pm_runtime_drop_link(struct device *dev); +extern void pm_runtime_drop_link(struct device_link *link); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. @@ -280,7 +280,7 @@ static inline void pm_runtime_clean_up_links(struct device *dev) {} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} -static inline void pm_runtime_drop_link(struct device *dev) {} +static inline void pm_runtime_drop_link(struct device_link *link) {} #endif /* !CONFIG_PM */ -- cgit v1.2.3 From d6e36668598154820177bfd78c1621d8e6c580a2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 21 Oct 2020 21:13:10 +0200 Subject: PM: runtime: Drop pm_runtime_clean_up_links() After commit d12544fb2aa9 ("PM: runtime: Remove link state checks in rpm_get/put_supplier()") nothing prevents the consumer device's runtime PM from acquiring additional references to the supplier device after pm_runtime_clean_up_links() has run (or even while it is running), so calling this function from __device_release_driver() may be pointless (or even harmful). Moreover, it ignores stateless device links, so the runtime PM handling of managed and stateless device links is inconsistent because of it, so better get rid of it entirely. Fixes: d12544fb2aa9 ("PM: runtime: Remove link state checks in rpm_get/put_supplier()") Signed-off-by: Rafael J. Wysocki Cc: 5.1+ # 5.1+ Tested-by: Xiang Chen Reviewed-by: Greg Kroah-Hartman --- include/linux/pm_runtime.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index eadc1fdebce6..4b708f4e8eed 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -54,7 +54,6 @@ extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); -extern void pm_runtime_clean_up_links(struct device *dev); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); @@ -276,7 +275,6 @@ static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} -static inline void pm_runtime_clean_up_links(struct device *dev) {} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} -- cgit v1.2.3 From f8f6ae5d077a9bdaf5cbf2ac960a5d1a04b47482 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Sun, 1 Nov 2020 17:08:00 -0800 Subject: mm: always have io_remap_pfn_range() set pgprot_decrypted() The purpose of io_remap_pfn_range() is to map IO memory, such as a memory mapped IO exposed through a PCI BAR. IO devices do not understand encryption, so this memory must always be decrypted. Automatically call pgprot_decrypted() as part of the generic implementation. This fixes a bug where enabling AMD SME causes subsystems, such as RDMA, using io_remap_pfn_range() to expose BAR pages to user space to fail. The CPU will encrypt access to those BAR pages instead of passing unencrypted IO directly to the device. Places not mapping IO should use remap_pfn_range(). Fixes: aca20d546214 ("x86/mm: Add support to make use of Secure Memory Encryption") Signed-off-by: Jason Gunthorpe Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Tom Lendacky Cc: Thomas Gleixner Cc: Andrey Ryabinin Cc: Borislav Petkov Cc: Brijesh Singh Cc: Jonathan Corbet Cc: Dmitry Vyukov Cc: "Dave Young" Cc: Alexander Potapenko Cc: Konrad Rzeszutek Wilk Cc: Andy Lutomirski Cc: Larry Woodman Cc: Matt Fleming Cc: Ingo Molnar Cc: "Michael S. Tsirkin" Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Rik van Riel Cc: Toshimitsu Kani Cc: Link: https://lkml.kernel.org/r/0-v1-025d64bdf6c4+e-amd_sme_fix_jgg@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++++++++ include/linux/pgtable.h | 4 ---- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ef360fe70aaf..db6ae4d3fb4e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2759,6 +2759,15 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } +#ifndef io_remap_pfn_range +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); +} +#endif + static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 38c33eabea89..71125a4676c4 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,10 +1427,6 @@ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ -#ifndef io_remap_pfn_range -#define io_remap_pfn_range remap_pfn_range -#endif - #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 -- cgit v1.2.3 From 286228d382ba6320f04fa2e7c6fc8d4d92e428f4 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 18 Dec 2019 09:39:02 +0100 Subject: can: can_create_echo_skb(): fix echo skb generation: always use skb_clone() All user space generated SKBs are owned by a socket (unless injected into the key via AF_PACKET). If a socket is closed, all associated skbs will be cleaned up. This leads to a problem when a CAN driver calls can_put_echo_skb() on a unshared SKB. If the socket is closed prior to the TX complete handler, can_get_echo_skb() and the subsequent delivering of the echo SKB to all registered callbacks, a SKB with a refcount of 0 is delivered. To avoid the problem, in can_get_echo_skb() the original SKB is now always cloned, regardless of shared SKB or not. If the process exists it can now safely discard its SKBs, without disturbing the delivery of the echo SKB. The problem shows up in the j1939 stack, when it clones the incoming skb, which detects the already 0 refcount. We can easily reproduce this with following example: testj1939 -B -r can0: & cansend can0 1823ff40#0123 WARNING: CPU: 0 PID: 293 at lib/refcount.c:25 refcount_warn_saturate+0x108/0x174 refcount_t: addition on 0; use-after-free. Modules linked in: coda_vpu imx_vdoa videobuf2_vmalloc dw_hdmi_ahb_audio vcan CPU: 0 PID: 293 Comm: cansend Not tainted 5.5.0-rc6-00376-g9e20dcb7040d #1 Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree) Backtrace: [] (dump_backtrace) from [] (show_stack+0x20/0x24) [] (show_stack) from [] (dump_stack+0x8c/0xa0) [] (dump_stack) from [] (__warn+0xe0/0x108) [] (__warn) from [] (warn_slowpath_fmt+0xa8/0xcc) [] (warn_slowpath_fmt) from [] (refcount_warn_saturate+0x108/0x174) [] (refcount_warn_saturate) from [] (j1939_can_recv+0x20c/0x210) [] (j1939_can_recv) from [] (can_rcv_filter+0xb4/0x268) [] (can_rcv_filter) from [] (can_receive+0xb0/0xe4) [] (can_receive) from [] (can_rcv+0x48/0x98) [] (can_rcv) from [] (__netif_receive_skb_one_core+0x64/0x88) [] (__netif_receive_skb_one_core) from [] (__netif_receive_skb+0x38/0x94) [] (__netif_receive_skb) from [] (netif_receive_skb_internal+0x64/0xf8) [] (netif_receive_skb_internal) from [] (netif_receive_skb+0x34/0x19c) [] (netif_receive_skb) from [] (can_rx_offload_napi_poll+0x58/0xb4) Fixes: 0ae89beb283a ("can: add destructor for self generated skbs") Signed-off-by: Oleksij Rempel Link: http://lore.kernel.org/r/20200124132656.22156-1-o.rempel@pengutronix.de Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 900b9f4e0605..fc61cf4eff1c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -61,21 +61,17 @@ static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk) */ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) { - if (skb_shared(skb)) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + struct sk_buff *nskb; - if (likely(nskb)) { - can_skb_set_owner(nskb, skb->sk); - consume_skb(skb); - return nskb; - } else { - kfree_skb(skb); - return NULL; - } + nskb = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!nskb)) { + kfree_skb(skb); + return NULL; } - /* we can assume to have an unshared skb with proper owner */ - return skb; + can_skb_set_owner(nskb, skb->sk); + consume_skb(skb); + return nskb; } #endif /* !_CAN_SKB_H */ -- cgit v1.2.3 From 763e4cdc0f6d5cea45c896fef67f7be4bdefcca7 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Thu, 29 Oct 2020 14:30:48 -0700 Subject: iomap: support partial page discard on writeback block mapping failure iomap writeback mapping failure only calls into ->discard_page() if the current page has not been added to the ioend. Accordingly, the XFS callback assumes a full page discard and invalidation. This is problematic for sub-page block size filesystems where some portion of a page might have been mapped successfully before a failure to map a delalloc block occurs. ->discard_page() is not called in that error scenario and the bio is explicitly failed by iomap via the error return from ->prepare_ioend(). As a result, the filesystem leaks delalloc blocks and corrupts the filesystem block counters. Since XFS is the only user of ->discard_page(), tweak the semantics to invoke the callback unconditionally on mapping errors and provide the file offset that failed to map. Update xfs_discard_page() to discard the corresponding portion of the file and pass the range along to iomap_invalidatepage(). The latter already properly handles both full and sub-page scenarios by not changing any iomap or page state on sub-page invalidations. Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 172b3397a1a3..5bd3cac4df9c 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -221,7 +221,7 @@ struct iomap_writeback_ops { * Optional, allows the file system to discard state on a page where * we failed to submit any I/O. */ - void (*discard_page)(struct page *page); + void (*discard_page)(struct page *page, loff_t fileoff); }; struct iomap_writepage_ctx { -- cgit v1.2.3 From fdaf083cdfb556a45c422c8998268baf1ab26829 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 30 Oct 2020 09:37:30 -0600 Subject: io_uring: properly handle SQPOLL request cancelations Track if a given task io_uring context contains SQPOLL instances, so we can iterate those for cancelation (and request counts). This ensures that we properly wait on SQPOLL contexts, and find everything that needs canceling. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 868364cea3b7..35b2d845704d 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -30,7 +30,8 @@ struct io_uring_task { struct percpu_counter inflight; struct io_identity __identity; struct io_identity *identity; - bool in_idle; + atomic_t in_idle; + bool sqpoll; }; #if defined(CONFIG_IO_URING) -- cgit v1.2.3 From d4d50710a8b46082224376ef119a4dbb75b25c56 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Nov 2020 09:27:33 +0100 Subject: seq_file: add seq_read_iter iov_iter based variant for reading a seq_file. seq_read is reimplemented on top of the iter variant. Signed-off-by: Christoph Hellwig Tested-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 813614d4b71f..b83b3ae3c877 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -107,6 +107,7 @@ void seq_pad(struct seq_file *m, char c); char *mangle_path(char *s, const char *p, const char *esc); int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); +ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter); loff_t seq_lseek(struct file *, loff_t, int); int seq_release(struct inode *, struct file *); int seq_write(struct seq_file *seq, const void *data, size_t len); -- cgit v1.2.3 From 964db79d6c186cc2ecc6ae46f98eed7e0ea8cf71 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Thu, 19 Nov 2020 18:53:55 +0100 Subject: of/address: Introduce of_dma_get_max_cpu_address() Introduce of_dma_get_max_cpu_address(), which provides the highest CPU physical address addressable by all DMA masters in the system. It's specially useful for setting memory zones sizes at early boot time. Signed-off-by: Nicolas Saenz Julienne Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20201119175400.9995-4-nsaenzjulienne@suse.de Signed-off-by: Catalin Marinas --- include/linux/of.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 5d51891cbf1a..9ed5b8532c30 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -558,6 +558,8 @@ int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out); +phys_addr_t of_dma_get_max_cpu_address(struct device_node *np); + #else /* CONFIG_OF */ static inline void of_core_init(void) @@ -995,6 +997,11 @@ static inline int of_map_id(struct device_node *np, u32 id, return -EINVAL; } +static inline phys_addr_t of_dma_get_max_cpu_address(struct device_node *np) +{ + return PHYS_ADDR_MAX; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ -- cgit v1.2.3 From 2b8652936f0ca9ca2e6c984ae76c7bfcda1b3f22 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 19 Nov 2020 18:53:58 +0100 Subject: arm64: mm: Set ZONE_DMA size based on early IORT scan We recently introduced a 1 GB sized ZONE_DMA to cater for platforms incorporating masters that can address less than 32 bits of DMA, in particular the Raspberry Pi 4, which has 4 or 8 GB of DRAM, but has peripherals that can only address up to 1 GB (and its PCIe host bridge can only access the bottom 3 GB) Instructing the DMA layer about these limitations is straight-forward, even though we had to fix some issues regarding memory limits set in the IORT for named components, and regarding the handling of ACPI _DMA methods. However, the DMA layer also needs to be able to allocate memory that is guaranteed to meet those DMA constraints, for bounce buffering as well as allocating the backing for consistent mappings. This is why the 1 GB ZONE_DMA was introduced recently. Unfortunately, it turns out the having a 1 GB ZONE_DMA as well as a ZONE_DMA32 causes problems with kdump, and potentially in other places where allocations cannot cross zone boundaries. Therefore, we should avoid having two separate DMA zones when possible. So let's do an early scan of the IORT, and only create the ZONE_DMA if we encounter any devices that need it. This puts the burden on the firmware to describe such limitations in the IORT, which may be redundant (and less precise) if _DMA methods are also being provided. However, it should be noted that this situation is highly unusual for arm64 ACPI machines. Also, the DMA subsystem still gives precedence to the _DMA method if implemented, and so we will not lose the ability to perform streaming DMA outside the ZONE_DMA if the _DMA method permits it. [nsaenz: unified implementation with DT's counterpart] Signed-off-by: Ard Biesheuvel Signed-off-by: Nicolas Saenz Julienne Tested-by: Jeremy Linton Acked-by: Lorenzo Pieralisi Acked-by: Hanjun Guo Cc: Jeremy Linton Cc: Lorenzo Pieralisi Cc: Nicolas Saenz Julienne Cc: Rob Herring Cc: Christoph Hellwig Cc: Robin Murphy Cc: Hanjun Guo Cc: Sudeep Holla Cc: Anshuman Khandual Link: https://lore.kernel.org/r/20201119175400.9995-7-nsaenzjulienne@suse.de Signed-off-by: Catalin Marinas --- include/linux/acpi_iort.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 20a32120bb88..1a12baa58e40 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -38,6 +38,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); const struct iommu_ops *iort_iommu_configure_id(struct device *dev, const u32 *id_in); int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); +phys_addr_t acpi_iort_dma_get_max_cpu_address(void); #else static inline void acpi_iort_init(void) { } static inline u32 iort_msi_map_id(struct device *dev, u32 id) @@ -55,6 +56,9 @@ static inline const struct iommu_ops *iort_iommu_configure_id( static inline int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) { return 0; } + +static inline phys_addr_t acpi_iort_dma_get_max_cpu_address(void) +{ return PHYS_ADDR_MAX; } #endif #endif /* __ACPI_IORT_H__ */ -- cgit v1.2.3 From 04435217f96869ac3a8f055ff68c5237a60bcd7e Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Thu, 19 Nov 2020 18:53:59 +0100 Subject: mm: Remove examples from enum zone_type comment We can't really list every setup in common code. On top of that they are unlikely to stay true for long as things change in the arch trees independently of this comment. Suggested-by: Christoph Hellwig Signed-off-by: Nicolas Saenz Julienne Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20201119175400.9995-8-nsaenzjulienne@suse.de Signed-off-by: Catalin Marinas --- include/linux/mmzone.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fb3bf696c05e..9d0c454d23cd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -354,26 +354,6 @@ enum zone_type { * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. - * - * Some examples: - * - * - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the - * rest of the lower 4G. - * - * - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on - * the specific device. - * - * - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the - * lower 4G. - * - * - powerpc only uses ZONE_DMA, the size, up to 2G, may vary - * depending on the specific device. - * - * - s390 uses ZONE_DMA fixed to the lower 2G. - * - * - ia64 and riscv only use ZONE_DMA32. - * - * - parisc uses neither. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, -- cgit v1.2.3 From 1d82b7898f2ad9cc414805aef23b99b742218f10 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 12 Nov 2020 18:53:33 -0800 Subject: arch: move SA_* definitions to generic headers Most architectures with the exception of alpha, mips, parisc and sparc use the same values for these flags. Move their definitions into asm-generic/signal-defs.h and allow the architectures with non-standard values to override them. Also, document the non-standard flag values in order to make it easier to add new generic flags in the future. A consequence of this change is that on powerpc and x86, the constants' values aside from SA_RESETHAND change signedness from unsigned to signed. This is not expected to impact realistic use of these constants. In particular the typical use of the constants where they are or'ed together and assigned to sa_flags (or another int variable) would not be affected. Signed-off-by: Peter Collingbourne Acked-by: Geert Uytterhoeven Acked-by: "Eric W. Biederman" Reviewed-by: Dave Martin Link: https://linux-review.googlesource.com/id/Ia3849f18b8009bf41faca374e701cdca36974528 Link: https://lkml.kernel.org/r/b6d0d1ec34f9ee93e1105f14f288fba5f89d1f24.1605235762.git.pcc@google.com Signed-off-by: Eric W. Biederman --- include/uapi/asm-generic/signal-defs.h | 47 ++++++++++++++++++++++++++++++++++ include/uapi/asm-generic/signal.h | 29 --------------------- 2 files changed, 47 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index e9304c95ceea..493953fe319b 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -4,6 +4,53 @@ #include +/* + * SA_FLAGS values: + * + * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. + * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. + * SA_SIGINFO delivers the signal with SIGINFO structs. + * SA_ONSTACK indicates that a registered stack_t will be used. + * SA_RESTART flag to get restarting signals (which were the default long ago) + * SA_NODEFER prevents the current signal from being masked in the handler. + * SA_RESETHAND clears the handler when the signal is delivered. + * + * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single + * Unix names RESETHAND and NODEFER respectively. + * + * The following bits are used in architecture-specific SA_* definitions and + * should be avoided for new generic flags: 3, 4, 5, 6, 7, 8, 9, 16, 24, 25, 26. + */ +#ifndef SA_NOCLDSTOP +#define SA_NOCLDSTOP 0x00000001 +#endif +#ifndef SA_NOCLDWAIT +#define SA_NOCLDWAIT 0x00000002 +#endif +#ifndef SA_SIGINFO +#define SA_SIGINFO 0x00000004 +#endif +#ifndef SA_ONSTACK +#define SA_ONSTACK 0x08000000 +#endif +#ifndef SA_RESTART +#define SA_RESTART 0x10000000 +#endif +#ifndef SA_NODEFER +#define SA_NODEFER 0x40000000 +#endif +#ifndef SA_RESETHAND +#define SA_RESETHAND 0x80000000 +#endif + +#define SA_NOMASK SA_NODEFER +#define SA_ONESHOT SA_RESETHAND + +/* + * New architectures should not define the obsolete + * SA_RESTORER 0x04000000 + */ + #ifndef SIG_BLOCK #define SIG_BLOCK 0 /* for blocking signals */ #endif diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h index 5c716a952cbe..f634822906e4 100644 --- a/include/uapi/asm-generic/signal.h +++ b/include/uapi/asm-generic/signal.h @@ -52,35 +52,6 @@ #define SIGRTMAX _NSIG #endif -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001 -#define SA_NOCLDWAIT 0x00000002 -#define SA_SIGINFO 0x00000004 -#define SA_ONSTACK 0x08000000 -#define SA_RESTART 0x10000000 -#define SA_NODEFER 0x40000000 -#define SA_RESETHAND 0x80000000 - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - -/* - * New architectures should not define the obsolete - * SA_RESTORER 0x04000000 - */ - #if !defined MINSIGSTKSZ || !defined SIGSTKSZ #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 -- cgit v1.2.3 From 23acdc76f1798b090bb9dcc90671cd29d929834e Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 12 Nov 2020 18:53:34 -0800 Subject: signal: clear non-uapi flag bits when passing/returning sa_flags Previously we were not clearing non-uapi flag bits in sigaction.sa_flags when storing the userspace-provided sa_flags or when returning them via oldact. Start doing so. This allows userspace to detect missing support for flag bits and allows the kernel to use non-uapi bits internally, as we are already doing in arch/x86 for two flag bits. Now that this change is in place, we no longer need the code in arch/x86 that was hiding these bits from userspace, so remove it. This is technically a userspace-visible behavior change for sigaction, as the unknown bits returned via oldact.sa_flags are no longer set. However, we are free to define the behavior for unknown bits exactly because their behavior is currently undefined, so for now we can define the meaning of each of them to be "clear the bit in oldact.sa_flags unless the bit becomes known in the future". Furthermore, this behavior is consistent with OpenBSD [1], illumos [2] and XNU [3] (FreeBSD [4] and NetBSD [5] fail the syscall if unknown bits are set). So there is some precedent for this behavior in other kernels, and in particular in XNU, which is probably the most popular kernel among those that I looked at, which means that this change is less likely to be a compatibility issue. Link: [1] https://github.com/openbsd/src/blob/f634a6a4b5bf832e9c1de77f7894ae2625e74484/sys/kern/kern_sig.c#L278 Link: [2] https://github.com/illumos/illumos-gate/blob/76f19f5fdc974fe5be5c82a556e43a4df93f1de1/usr/src/uts/common/syscall/sigaction.c#L86 Link: [3] https://github.com/apple/darwin-xnu/blob/a449c6a3b8014d9406c2ddbdc81795da24aa7443/bsd/kern/kern_sig.c#L480 Link: [4] https://github.com/freebsd/freebsd/blob/eded70c37057857c6e23fae51f86b8f8f43cd2d0/sys/kern/kern_sig.c#L699 Link: [5] https://github.com/NetBSD/src/blob/3365779becdcedfca206091a645a0e8e22b2946e/sys/kern/sys_sig.c#L473 Signed-off-by: Peter Collingbourne Reviewed-by: Dave Martin Acked-by: "Eric W. Biederman" Link: https://linux-review.googlesource.com/id/I35aab6f5be932505d90f3b3450c083b4db1eca86 Link: https://lkml.kernel.org/r/878dbcb5f47bc9b11881c81f745c0bef5c23f97f.1605235762.git.pcc@google.com Signed-off-by: Eric W. Biederman --- include/linux/signal_types.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index f8a90ae9c6ec..a7887ad84d36 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -68,4 +68,16 @@ struct ksignal { int sig; }; +#ifndef __ARCH_UAPI_SA_FLAGS +#ifdef SA_RESTORER +#define __ARCH_UAPI_SA_FLAGS SA_RESTORER +#else +#define __ARCH_UAPI_SA_FLAGS 0 +#endif +#endif + +#define UAPI_SA_FLAGS \ + (SA_NOCLDSTOP | SA_NOCLDWAIT | SA_SIGINFO | SA_ONSTACK | SA_RESTART | \ + SA_NODEFER | SA_RESETHAND | __ARCH_UAPI_SA_FLAGS) + #endif /* _LINUX_SIGNAL_TYPES_H */ -- cgit v1.2.3 From 7da5082a2f9a1d16eded00c204fdb52a855c2bb2 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 16 Nov 2020 19:17:24 -0800 Subject: arch: provide better documentation for the arch-specific SA_* flags Instead of documenting the arch-specific flag values in a comment at the top where they may be easily overlooked, document them in comments inline with the definitions in numerical order so that it is clear why specific values must be chosen for new generic flags and to reduce the likelihood of conflicts between generic and arch-specific flags. Signed-off-by: Peter Collingbourne Link: https://linux-review.googlesource.com/id/I40a129cf7c3a71ba1bfd6d936c544072ee3b7ce6 Link: https://lkml.kernel.org/r/198c8b68c76bf3ed73117d817c7cdf9bc0eb174f.1605582887.git.pcc@google.com Signed-off-by: Eric W. Biederman --- include/uapi/asm-generic/signal-defs.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index 493953fe319b..44f070982752 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -17,9 +17,6 @@ * * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single * Unix names RESETHAND and NODEFER respectively. - * - * The following bits are used in architecture-specific SA_* definitions and - * should be avoided for new generic flags: 3, 4, 5, 6, 7, 8, 9, 16, 24, 25, 26. */ #ifndef SA_NOCLDSTOP #define SA_NOCLDSTOP 0x00000001 @@ -30,6 +27,20 @@ #ifndef SA_SIGINFO #define SA_SIGINFO 0x00000004 #endif +/* 0x00000008 used on alpha, mips, parisc */ +/* 0x00000010 used on alpha, parisc */ +/* 0x00000020 used on alpha, parisc, sparc */ +/* 0x00000040 used on alpha, parisc */ +/* 0x00000080 used on parisc */ +/* 0x00000100 used on sparc */ +/* 0x00000200 used on sparc */ +/* 0x00010000 used on mips */ +/* 0x01000000 used on x86 */ +/* 0x02000000 used on x86 */ +/* + * New architectures should not define the obsolete + * SA_RESTORER 0x04000000 + */ #ifndef SA_ONSTACK #define SA_ONSTACK 0x08000000 #endif @@ -46,11 +57,6 @@ #define SA_NOMASK SA_NODEFER #define SA_ONESHOT SA_RESETHAND -/* - * New architectures should not define the obsolete - * SA_RESTORER 0x04000000 - */ - #ifndef SIG_BLOCK #define SIG_BLOCK 0 /* for blocking signals */ #endif -- cgit v1.2.3 From a54f0dfda754c5cecc89a14dab68a3edc1e497b5 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 16 Nov 2020 19:17:25 -0800 Subject: signal: define the SA_UNSUPPORTED bit in sa_flags Define a sa_flags bit, SA_UNSUPPORTED, which will never be supported in the uapi. The purpose of this flag bit is to allow userspace to distinguish an old kernel that does not clear unknown sa_flags bits from a kernel that supports every flag bit. In other words, if userspace does something like: act.sa_flags |= SA_UNSUPPORTED; sigaction(SIGSEGV, &act, 0); sigaction(SIGSEGV, 0, &oldact); and finds that SA_UNSUPPORTED remains set in oldact.sa_flags, it means that the kernel cannot be trusted to have cleared unknown flag bits from sa_flags, so no assumptions about flag bit support can be made. Signed-off-by: Peter Collingbourne Reviewed-by: Dave Martin Link: https://linux-review.googlesource.com/id/Ic2501ad150a3a79c1cf27fb8c99be342e9dffbcb Link: https://lkml.kernel.org/r/bda7ddff8895a9bc4ffc5f3cf3d4d37a32118077.1605582887.git.pcc@google.com Signed-off-by: Eric W. Biederman --- include/uapi/asm-generic/signal-defs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index 44f070982752..c790f67304ba 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -14,6 +14,12 @@ * SA_RESTART flag to get restarting signals (which were the default long ago) * SA_NODEFER prevents the current signal from being masked in the handler. * SA_RESETHAND clears the handler when the signal is delivered. + * SA_UNSUPPORTED is a flag bit that will never be supported. Kernels from + * before the introduction of SA_UNSUPPORTED did not clear unknown bits from + * sa_flags when read using the oldact argument to sigaction and rt_sigaction, + * so this bit allows flag bit support to be detected from userspace while + * allowing an old kernel to be distinguished from a kernel that supports every + * flag bit. * * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single * Unix names RESETHAND and NODEFER respectively. @@ -34,6 +40,7 @@ /* 0x00000080 used on parisc */ /* 0x00000100 used on sparc */ /* 0x00000200 used on sparc */ +#define SA_UNSUPPORTED 0x00000400 /* 0x00010000 used on mips */ /* 0x01000000 used on x86 */ /* 0x02000000 used on x86 */ -- cgit v1.2.3 From 6ac05e832a9e96f9b1c42a8917cdd317d7b6c8fa Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 20 Nov 2020 12:33:45 -0800 Subject: signal: define the SA_EXPOSE_TAGBITS bit in sa_flags Architectures that support address tagging, such as arm64, may want to expose fault address tag bits to the signal handler to help diagnose memory errors. However, these bits have not been previously set, and their presence may confuse unaware user applications. Therefore, introduce a SA_EXPOSE_TAGBITS flag bit in sa_flags that a signal handler may use to explicitly request that the bits are set. The generic signal handler APIs expect to receive tagged addresses. Architectures may specify how to untag addresses in the case where SA_EXPOSE_TAGBITS is clear by defining the arch_untagged_si_addr function. Signed-off-by: Peter Collingbourne Acked-by: "Eric W. Biederman" Link: https://linux-review.googlesource.com/id/I16dd0ed2081f091fce97be0190cb8caa874c26cb Link: https://lkml.kernel.org/r/13cf24d00ebdd8e1f55caf1821c7c29d54100191.1605904350.git.pcc@google.com Signed-off-by: Eric W. Biederman --- include/linux/signal.h | 14 ++++++++++++++ include/linux/signal_types.h | 2 +- include/uapi/asm-generic/signal-defs.h | 3 +++ 3 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/signal.h b/include/linux/signal.h index b256f9c65661..205526c4003a 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -469,4 +469,18 @@ struct seq_file; extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); #endif +#ifndef arch_untagged_si_addr +/* + * Given a fault address and a signal and si_code which correspond to the + * _sigfault union member, returns the address that must appear in si_addr if + * the signal handler does not have SA_EXPOSE_TAGBITS enabled in sa_flags. + */ +static inline void __user *arch_untagged_si_addr(void __user *addr, + unsigned long sig, + unsigned long si_code) +{ + return addr; +} +#endif + #endif /* _LINUX_SIGNAL_H */ diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index a7887ad84d36..68e06c75c5b2 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -78,6 +78,6 @@ struct ksignal { #define UAPI_SA_FLAGS \ (SA_NOCLDSTOP | SA_NOCLDWAIT | SA_SIGINFO | SA_ONSTACK | SA_RESTART | \ - SA_NODEFER | SA_RESETHAND | __ARCH_UAPI_SA_FLAGS) + SA_NODEFER | SA_RESETHAND | SA_EXPOSE_TAGBITS | __ARCH_UAPI_SA_FLAGS) #endif /* _LINUX_SIGNAL_TYPES_H */ diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index c790f67304ba..fe929e7b77ca 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -20,6 +20,8 @@ * so this bit allows flag bit support to be detected from userspace while * allowing an old kernel to be distinguished from a kernel that supports every * flag bit. + * SA_EXPOSE_TAGBITS exposes an architecture-defined set of tag bits in + * siginfo.si_addr. * * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single * Unix names RESETHAND and NODEFER respectively. @@ -41,6 +43,7 @@ /* 0x00000100 used on sparc */ /* 0x00000200 used on sparc */ #define SA_UNSUPPORTED 0x00000400 +#define SA_EXPOSE_TAGBITS 0x00000800 /* 0x00010000 used on mips */ /* 0x01000000 used on x86 */ /* 0x02000000 used on x86 */ -- cgit v1.2.3