From e692b4021a2e48745d4bdac2b2775bdc8f03b433 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 4 Nov 2019 18:37:19 +0100 Subject: lockdep: add might_lock_nested() Necessary to annotate functions where we might acquire a mutex_lock_nested() or similar. Needed by i915. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Daniel Vetter Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Vetter Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20191104173720.2696-2-daniel.vetter@ffwll.ch --- include/linux/lockdep.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b8a835fd611b..827722c21797 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -628,6 +628,13 @@ do { \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ } while (0) +# define might_lock_nested(lock, subclass) \ +do { \ + typecheck(struct lockdep_map *, &(lock)->dep_map); \ + lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL, \ + _THIS_IP_); \ + lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ +} while (0) #define lockdep_assert_irqs_enabled() do { \ WARN_ONCE(debug_locks && !current->lockdep_recursion && \ @@ -650,6 +657,7 @@ do { \ #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) +# define might_lock_nested(lock, subclass) do { } while (0) # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) -- cgit v1.2.3 From f597c2089da4dd55133546b1255493579a295bff Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 14 Nov 2019 13:51:06 +0100 Subject: fbdev: Unexport unlink_framebuffer() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no external callers of unlink_framebuffer() left. Make the function an internal interface. Signed-off-by: Thomas Zimmermann Reviewed-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20191114125106.28347-4-tzimmermann@suse.de --- include/linux/fb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 41e0069eca0a..a6ad528990de 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -606,7 +606,6 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, /* drivers/video/fbmem.c */ extern int register_framebuffer(struct fb_info *fb_info); extern void unregister_framebuffer(struct fb_info *fb_info); -extern void unlink_framebuffer(struct fb_info *fb_info); extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, -- cgit v1.2.3 From 6a9afcb198b4de323485c0ee94ff09f653012d4b Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:11 +0200 Subject: iio: imu: adis: rename txrx_lock -> state_lock The lock can be extended a bit to protect other elements that are not particular to just TX/RX. Another idea would have been to just add a new `state_lock`, but that would mean 2 locks which would be redundant, and probably cause more potential for dead-locks. What will be done in the next patches, will be to add some unlocked versions for read/write_reg functions. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 92aae14593bf..100b5d1cebf1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -61,7 +61,7 @@ struct adis { const struct adis_data *data; struct adis_burst *burst; - struct mutex txrx_lock; + struct mutex state_lock; struct spi_message msg; struct spi_transfer *xfer; unsigned int current_page; -- cgit v1.2.3 From 770d465619423a946248018ea39ed9a74c8f2ff4 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:12 +0200 Subject: iio: imu: adis: add unlocked read/write function versions This will allow more flexible control to group reads & writes into a single lock (particularly the state_lock). The end-goal is to remove the indio_dev->mlock usage, and the simplest fix would have been to just add another lock, which would not be a good idea on the long-run. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 116 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 114 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 100b5d1cebf1..38ebe41092e1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -75,11 +75,123 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev, struct spi_device *spi, const struct adis_data *data); int adis_reset(struct adis *adis); -int adis_write_reg(struct adis *adis, unsigned int reg, +int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int val, unsigned int size); -int adis_read_reg(struct adis *adis, unsigned int reg, +int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val, unsigned int size); +/** + * __adis_write_reg_8() - Write single byte to a register (unlocked) + * @adis: The adis device + * @reg: The address of the register to be written + * @value: The value to write + */ +static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, + uint8_t val) +{ + return __adis_write_reg(adis, reg, val, 1); +} + +/** + * __adis_write_reg_16() - Write 2 bytes to a pair of registers (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @value: Value to be written + */ +static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, + uint16_t val) +{ + return __adis_write_reg(adis, reg, val, 2); +} + +/** + * __adis_write_reg_32() - write 4 bytes to four registers (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the four register + * @value: Value to be written + */ +static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, + uint32_t val) +{ + return __adis_write_reg(adis, reg, val, 4); +} + +/** + * __adis_read_reg_16() - read 2 bytes from a 16-bit register (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @val: The value read back from the device + */ +static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, + uint16_t *val) +{ + unsigned int tmp; + int ret; + + ret = __adis_read_reg(adis, reg, &tmp, 2); + if (ret == 0) + *val = tmp; + + return ret; +} + +/** + * __adis_read_reg_32() - read 4 bytes from a 32-bit register (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @val: The value read back from the device + */ +static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, + uint32_t *val) +{ + unsigned int tmp; + int ret; + + ret = __adis_read_reg(adis, reg, &tmp, 4); + if (ret == 0) + *val = tmp; + + return ret; +} + +/** + * adis_write_reg() - write N bytes to register + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @value: The value to write to device (up to 4 bytes) + * @size: The size of the @value (in bytes) + */ +static inline int adis_write_reg(struct adis *adis, unsigned int reg, + unsigned int val, unsigned int size) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_write_reg(adis, reg, val, size); + mutex_unlock(&adis->state_lock); + + return ret; +} + +/** + * adis_read_reg() - read N bytes from register + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @val: The value read back from the device + * @size: The size of the @val buffer + */ +static int adis_read_reg(struct adis *adis, unsigned int reg, + unsigned int *val, unsigned int size) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_read_reg(adis, reg, val, size); + mutex_unlock(&adis->state_lock); + + return ret; +} + /** * adis_write_reg_8() - Write single byte to a register * @adis: The adis device -- cgit v1.2.3 From 6a4d6a7d6588d8c15501542da786ebff6602475c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:14 +0200 Subject: iio: imu: adis: create an unlocked version of adis_check_status() This one also gets re-used in certain operations, so it makes sense to have an unlocked version of this to group it with other reads/writes/operations to have a single lock for the whole state change. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 38ebe41092e1..db759957e1c1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -267,7 +267,18 @@ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, } int adis_enable_irq(struct adis *adis, bool enable); -int adis_check_status(struct adis *adis); +int __adis_check_status(struct adis *adis); + +static inline int adis_check_status(struct adis *adis) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_check_status(adis); + mutex_unlock(&adis->state_lock); + + return ret; +} int adis_initial_startup(struct adis *adis); -- cgit v1.2.3 From 762ab093cbe26451175a5a63ea06c971bf973525 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:15 +0200 Subject: iio: imu: adis: create an unlocked version of adis_reset() The reset routine may also be important to be protected by the state-lock and grouped with other operations, so create an unlocked version, so that this can be done. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index db759957e1c1..4b5bc0e06e69 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -73,7 +73,24 @@ struct adis { int adis_init(struct adis *adis, struct iio_dev *indio_dev, struct spi_device *spi, const struct adis_data *data); -int adis_reset(struct adis *adis); +int __adis_reset(struct adis *adis); + +/** + * adis_reset() - Reset the device + * @adis: The adis device + * + * Returns 0 on success, a negative error code otherwise + */ +static inline int adis_reset(struct adis *adis) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_reset(adis); + mutex_unlock(&adis->state_lock); + + return ret; +} int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int val, unsigned int size); -- cgit v1.2.3 From 8cb3403633146afe1ba81f79224679f5df2940d4 Mon Sep 17 00:00:00 2001 From: Andrea Merello Date: Wed, 20 Nov 2019 15:47:51 +0100 Subject: iio: core: add char type for sysfs attributes This patch introduces IIO_VAL_CHAR type for standard IIO attributes to allow for attributes that needs to be represented by character rather than a number. This is preparatory for introducing a new attribute whose purpose is to describe thermocouple type, that can be i.e. "J", "K", etc.. The char-type value is stored in the first "value" integer that is passed to the .[read/write]_raw() callbacks. Note that in order to make it possible for the IIO core to correctly parse this type (actually, to avoid integer parsing), it became mandatory for any driver that wish to use IIO_VAL_CHAR on a writable attribute to implement .write_raw_get_fmt(). Cc: Hartmut Knaack Cc: Lars-Peter Clausen Cc: Peter Meerwald-Stadler Cc: Colin Ian King Cc: Patrick Havelange Cc: Matt Weber Cc: Matt Ranostay Cc: Chuhong Yuan Cc: Daniel Gomez Cc: linux-iio@vger.kernel.org Signed-off-by: Andrea Merello Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index fa824e160f35..8e0026da38c9 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -25,6 +25,7 @@ enum iio_event_info { #define IIO_VAL_INT_MULTIPLE 5 #define IIO_VAL_FRACTIONAL 10 #define IIO_VAL_FRACTIONAL_LOG2 11 +#define IIO_VAL_CHAR 12 enum iio_available_type { IIO_AVAIL_LIST, -- cgit v1.2.3 From ddfb97d8f06c98fa5d80bbb6a997155a838161e9 Mon Sep 17 00:00:00 2001 From: Andrea Merello Date: Wed, 20 Nov 2019 15:47:52 +0100 Subject: iio: core: add thermocouple_type standard attribute We have a couple of thermocouple IIO drivers, supporting several chips. Some of them support only one specific thermocouple type (e.g. "K", "J"), one of them can be configured to work with several different thermocouple types. In certain applications thermocouples could be externally connected to the chip by the user. This patch introduces a new IIO standard attribute to report the supported thermocouple type and, where applicable, to allow it to be dynamically set using sysfs. Cc: Hartmut Knaack Cc: Lars-Peter Clausen Cc: Peter Meerwald-Stadler Cc: Colin Ian King Cc: Patrick Havelange Cc: Matt Weber Cc: Matt Ranostay Cc: Chuhong Yuan Cc: Daniel Gomez Cc: linux-iio@vger.kernel.org Signed-off-by: Andrea Merello Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 8e0026da38c9..e6fd3645963c 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -58,6 +58,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_DEBOUNCE_TIME, IIO_CHAN_INFO_CALIBEMISSIVITY, IIO_CHAN_INFO_OVERSAMPLING_RATIO, + IIO_CHAN_INFO_THERMOCOUPLE_TYPE, }; #endif /* _IIO_TYPES_H_ */ -- cgit v1.2.3 From 35bd71dd1c161e6e89b21138e01e8c04c6347716 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 18 Nov 2019 11:35:23 +0100 Subject: drm/tegra: Delete host1x_bo_ops->k(un)map It doesn't have any callers anymore. Aside: The ->mmap/munmap hooks have a bit a confusing name, they don't do userspace mmaps, but a kernel vmap. I think most places use vmap for this, except ttm, which uses kmap for vmap for added confusion. mmap seems entirely for userspace mappings set up through mmap(2) syscall. Reviewed-by: Thierry Reding Tested-by: Thierry Reding Acked-by: Sumit Semwal Signed-off-by: Daniel Vetter Cc: Thierry Reding Cc: Jonathan Hunter Cc: linux-tegra@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20191118103536.17675-3-daniel.vetter@ffwll.ch --- include/linux/host1x.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index e6eea45e1154..d11e89db7d7f 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -68,8 +68,6 @@ struct host1x_bo_ops { void (*unpin)(struct host1x_bo *bo, struct sg_table *sgt); void *(*mmap)(struct host1x_bo *bo); void (*munmap)(struct host1x_bo *bo, void *addr); - void *(*kmap)(struct host1x_bo *bo, unsigned int pagenum); - void (*kunmap)(struct host1x_bo *bo, unsigned int pagenum, void *addr); }; struct host1x_bo { @@ -113,17 +111,6 @@ static inline void host1x_bo_munmap(struct host1x_bo *bo, void *addr) bo->ops->munmap(bo, addr); } -static inline void *host1x_bo_kmap(struct host1x_bo *bo, unsigned int pagenum) -{ - return bo->ops->kmap(bo, pagenum); -} - -static inline void host1x_bo_kunmap(struct host1x_bo *bo, - unsigned int pagenum, void *addr) -{ - bo->ops->kunmap(bo, pagenum, addr); -} - /* * host1x syncpoints */ -- cgit v1.2.3 From 7f0de8d80816d9620e995cf98acf4b6cd2d7c230 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 18 Nov 2019 11:35:30 +0100 Subject: dma-buf: Drop dma_buf_k(un)map It's unused. 10 years ago, back when 32bit was still fairly common and trying to not exhaust vmalloc space sounded like a worthwhile goal, adding these to dma_buf made sense. Reality is that they simply never caught on, and nowadays everyone who needs plenty of buffers will run in 64bit mode anyway. Also update the docs in this area to adjust them to reality. The actual hooks in dma_buf_ops will be removed once all the implementations are gone. Acked-by: Sumit Semwal Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20191118103536.17675-10-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index af73f835c51c..7feb9c3805ae 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -464,8 +464,6 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); int dma_buf_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); -void *dma_buf_kmap(struct dma_buf *, unsigned long); -void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); -- cgit v1.2.3 From 4337ebbbbda3fb82e4fd928188a86e0bff0e9042 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 18 Nov 2019 11:35:36 +0100 Subject: dma-buf: Remove kernel map/unmap hooks All implementations are gone now. Acked-by: Sumit Semwal Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20191118103536.17675-16-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 7feb9c3805ae..abf5459a5b9d 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -249,31 +249,6 @@ struct dma_buf_ops { */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); - /** - * @map: - * - * Maps a page from the buffer into kernel address space. The page is - * specified by offset into the buffer in PAGE_SIZE units. - * - * This callback is optional. - * - * Returns: - * - * Virtual address pointer where requested page can be accessed. NULL - * on error or when this function is unimplemented by the exporter. - */ - void *(*map)(struct dma_buf *, unsigned long); - - /** - * @unmap: - * - * Unmaps a page from the buffer. Page offset and address pointer should - * be the same as the one passed to and returned by matching call to map. - * - * This callback is optional. - */ - void (*unmap)(struct dma_buf *, unsigned long, void *); - void *(*vmap)(struct dma_buf *); void (*vunmap)(struct dma_buf *, void *vaddr); }; -- cgit v1.2.3 From 958de668197651bbf2b4b9528f204ab5a0f1af65 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Oct 2019 21:07:31 +0200 Subject: module: Remove set_all_modules_text_*() Now that there are no users of set_all_modules_text_*() left, remove it. While it appears nds32 uses it, it does not have STRICT_MODULE_RWX and therefore ends up with the NOP stubs. Tested-by: Alexei Starovoitov Tested-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Acked-by: Alexei Starovoitov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Greentime Hu Cc: H. Peter Anvin Cc: Jessica Yu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vincent Chen Link: https://lkml.kernel.org/r/20191111132458.284298307@infradead.org Signed-off-by: Ingo Molnar --- include/linux/module.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 6d20895e7739..daae84705040 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -846,13 +846,9 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) #ifdef CONFIG_STRICT_MODULE_RWX -extern void set_all_modules_text_rw(void); -extern void set_all_modules_text_ro(void); extern void module_enable_ro(const struct module *mod, bool after_init); extern void module_disable_ro(const struct module *mod); #else -static inline void set_all_modules_text_rw(void) { } -static inline void set_all_modules_text_ro(void) { } static inline void module_enable_ro(const struct module *mod, bool after_init) { } static inline void module_disable_ro(const struct module *mod) { } #endif -- cgit v1.2.3 From 04ae87a52074e2d448fc66143f1bd2c7d694d2b9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 24 Oct 2019 22:26:59 +0200 Subject: ftrace: Rework event_create_dir() Rework event_create_dir() to use an array of static data instead of function pointers where possible. The problem is that it would call the function pointer on module load before parse_args(), possibly even before jump_labels were initialized. Luckily the generated functions don't use jump_labels but it still seems fragile. It also gets in the way of changing when we make the module map executable. The generated function are basically calling trace_define_field() with a bunch of static arguments. So instead of a function, capture these arguments in a static array, avoiding the function call. Now there are a number of cases where the fields are dynamic (syscall arguments, kprobes and uprobes), in which case a static array does not work, for these we preserve the function call. Luckily all these cases are not related to modules and so we can retain the function call for them. Also fix up all broken tracepoint definitions that now generate a compile error. Tested-by: Alexei Starovoitov Tested-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (VMware) Acked-by: Alexei Starovoitov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191111132458.342979914@infradead.org Signed-off-by: Ingo Molnar --- include/linux/trace_events.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 30a8cdcfd4a4..a379255c14a9 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -187,6 +187,22 @@ enum trace_reg { struct trace_event_call; +#define TRACE_FUNCTION_TYPE ((const char *)~0UL) + +struct trace_event_fields { + const char *type; + union { + struct { + const char *name; + const int size; + const int align; + const int is_signed; + const int filter_type; + }; + int (*define_fields)(struct trace_event_call *); + }; +}; + struct trace_event_class { const char *system; void *probe; @@ -195,7 +211,7 @@ struct trace_event_class { #endif int (*reg)(struct trace_event_call *event, enum trace_reg type, void *data); - int (*define_fields)(struct trace_event_call *); + struct trace_event_fields *fields_array; struct list_head *(*get_fields)(struct trace_event_call *); struct list_head fields; int (*raw_init)(struct trace_event_call *); -- cgit v1.2.3 From e6bff4665c595b5a4aff173848851ed49ac3bfad Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:20 -0800 Subject: software node: replace is_array with is_inline We do not need a special flag to know if we are dealing with an array, as we can get that data from ratio between element length and the data size, but we do need a flag to know whether or not the data is stored directly inside property_entry. Signed-off-by: Dmitry Torokhov [ rjw: Subject & changelog, struct property_entry kerneldoc ] Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 48335288c2a9..6c1ca870a9a9 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -227,15 +227,15 @@ static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode, * struct property_entry - "Built-in" device property representation. * @name: Name of the property. * @length: Length of data making up the value. - * @is_array: True when the property is an array. + * @is_inline: True when the property value is stored inline. * @type: Type of the data in unions. - * @pointer: Pointer to the property (an array of items of the given type). - * @value: Value of the property (when it is a single item of the given type). + * @pointer: Pointer to the property when it is not stored inline. + * @value: Value of the property when it is stored inline. */ struct property_entry { const char *name; size_t length; - bool is_array; + bool is_inline; enum dev_prop_type type; union { const void *pointer; @@ -262,7 +262,6 @@ struct property_entry { (struct property_entry) { \ .name = _name_, \ .length = (_len_) * __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ - .is_array = true, \ .type = DEV_PROP_##_Type_, \ { .pointer = _val_ }, \ } @@ -293,6 +292,7 @@ struct property_entry { (struct property_entry) { \ .name = _name_, \ .length = __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ + .is_inline = true, \ .type = DEV_PROP_##_Type_, \ { .value = { ._elem_ = _val_ } }, \ } @@ -311,6 +311,7 @@ struct property_entry { #define PROPERTY_ENTRY_BOOL(_name_) \ (struct property_entry) { \ .name = _name_, \ + .is_inline = true, \ } struct property_entry * -- cgit v1.2.3 From 996b0830f95d132e50891a5568fef9e2965e4af2 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:21 -0800 Subject: software node: allow embedding of small arrays into property_entry We should not conflate whether a property data is an array or a single value with where it is stored (embedded into property_entry structure or out-of-line). All single-value properties are in effect 1-element arrays, and we can figure the amount of data stored in a property by examining its length and the data type. And arrays can be as easily stored in property entry instances as single values are, provided that we have enough space (we have up to 8 bytes). We can embed: - up to 8 bytes from U8 arrays - up to 4 words - up to 2 double words - one U64 value - one (on 64 bit architectures) or 2 (on 32 bit) strings. This change also has an effect of switching properties with small amount of data to embed it instead of keeping it separate when copying such properties. Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 6c1ca870a9a9..fc819c6ebf33 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -240,11 +240,11 @@ struct property_entry { union { const void *pointer; union { - u8 u8_data; - u16 u16_data; - u32 u32_data; - u64 u64_data; - const char *str; + u8 u8_data[sizeof(u64) / sizeof(u8)]; + u16 u16_data[sizeof(u64) / sizeof(u16)]; + u32 u32_data[sizeof(u64) / sizeof(u32)]; + u64 u64_data[sizeof(u64) / sizeof(u64)]; + const char *str[sizeof(u64) / sizeof(char *)]; } value; }; }; @@ -256,7 +256,7 @@ struct property_entry { */ #define __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_) \ - sizeof(((struct property_entry *)NULL)->value._elem_) + sizeof(((struct property_entry *)NULL)->value._elem_[0]) #define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\ (struct property_entry) { \ @@ -294,7 +294,7 @@ struct property_entry { .length = __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ .is_inline = true, \ .type = DEV_PROP_##_Type_, \ - { .value = { ._elem_ = _val_ } }, \ + { .value = { ._elem_[0] = _val_ } }, \ } #define PROPERTY_ENTRY_U8(_name_, _val_) \ -- cgit v1.2.3 From e64b674bc9d76edb4cf1b8c98446b1d29a16b9df Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:22 -0800 Subject: software node: implement reference properties It is possible to store references to software nodes in the same fashion as other static properties, so that users do not need to define separate structures: static const struct software_node gpio_bank_b_node = { .name = "B", }; static const struct property_entry simone_key_enter_props[] = { PROPERTY_ENTRY_U32("linux,code", KEY_ENTER), PROPERTY_ENTRY_STRING("label", "enter"), PROPERTY_ENTRY_REF("gpios", &gpio_bank_b_node, 123, GPIO_ACTIVE_LOW), { } }; Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 57 ++++++++++++++++++++++++++++++++++-------------- 1 file changed, 41 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index fc819c6ebf33..3df7089f0dbd 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -22,6 +22,7 @@ enum dev_prop_type { DEV_PROP_U32, DEV_PROP_U64, DEV_PROP_STRING, + DEV_PROP_REF, }; enum dev_dma_attr { @@ -223,6 +224,20 @@ static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode, return fwnode_property_read_u64_array(fwnode, propname, NULL, 0); } +struct software_node; + +/** + * struct software_node_ref_args - Reference property with additional arguments + * @node: Reference to a software node + * @nargs: Number of elements in @args array + * @args: Integer arguments + */ +struct software_node_ref_args { + const struct software_node *node; + unsigned int nargs; + u64 args[NR_FWNODE_REFERENCE_ARGS]; +}; + /** * struct property_entry - "Built-in" device property representation. * @name: Name of the property. @@ -258,14 +273,20 @@ struct property_entry { #define __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_) \ sizeof(((struct property_entry *)NULL)->value._elem_[0]) -#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\ +#define __PROPERTY_ENTRY_ARRAY_ELSIZE_LEN(_name_, _elsize_, _Type_, \ + _val_, _len_) \ (struct property_entry) { \ .name = _name_, \ - .length = (_len_) * __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ + .length = (_len_) * (_elsize_), \ .type = DEV_PROP_##_Type_, \ { .pointer = _val_ }, \ } +#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\ + __PROPERTY_ENTRY_ARRAY_ELSIZE_LEN(_name_, \ + __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ + _Type_, _val_, _len_) + #define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, u8_data, U8, _val_, _len_) #define PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, _len_) \ @@ -276,6 +297,10 @@ struct property_entry { __PROPERTY_ENTRY_ARRAY_LEN(_name_, u64_data, U64, _val_, _len_) #define PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, str, STRING, _val_, _len_) +#define PROPERTY_ENTRY_REF_ARRAY_LEN(_name_, _val_, _len_) \ + __PROPERTY_ENTRY_ARRAY_ELSIZE_LEN(_name_, \ + sizeof(struct software_node_ref_args), \ + REF, _val_, _len_) #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) @@ -287,6 +312,8 @@ struct property_entry { PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) +#define PROPERTY_ENTRY_REF_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_REF_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define __PROPERTY_ENTRY_ELEMENT(_name_, _elem_, _Type_, _val_) \ (struct property_entry) { \ @@ -314,6 +341,18 @@ struct property_entry { .is_inline = true, \ } +#define PROPERTY_ENTRY_REF(_name_, _ref_, ...) \ +(struct property_entry) { \ + .name = _name_, \ + .length = sizeof(struct software_node_ref_args), \ + .type = DEV_PROP_REF, \ + { .pointer = &(const struct software_node_ref_args) { \ + .node = _ref_, \ + .nargs = ARRAY_SIZE(((u64[]){ 0, ##__VA_ARGS__ })) - 1, \ + .args = { __VA_ARGS__ }, \ + } }, \ +} + struct property_entry * property_entries_dup(const struct property_entry *properties); @@ -377,20 +416,6 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ -struct software_node; - -/** - * struct software_node_ref_args - Reference with additional arguments - * @node: Reference to a software node - * @nargs: Number of elements in @args array - * @args: Integer arguments - */ -struct software_node_ref_args { - const struct software_node *node; - unsigned int nargs; - u64 args[NR_FWNODE_REFERENCE_ARGS]; -}; - /** * struct software_node_reference - Named software node reference property * @name: Name of the property -- cgit v1.2.3 From e933bedd45099dce1165104138bb703a6e31df82 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:24 -0800 Subject: software node: remove separate handling of references Now that all users of references have moved to reference properties, we can remove separate handling of references. Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 3df7089f0dbd..d86de017c689 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -416,30 +416,16 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ -/** - * struct software_node_reference - Named software node reference property - * @name: Name of the property - * @nrefs: Number of elements in @refs array - * @refs: Array of references with optional arguments - */ -struct software_node_reference { - const char *name; - unsigned int nrefs; - const struct software_node_ref_args *refs; -}; - /** * struct software_node - Software node description * @name: Name of the software node * @parent: Parent of the software node * @properties: Array of device properties - * @references: Array of software node reference properties */ struct software_node { const char *name; const struct software_node *parent; const struct property_entry *properties; - const struct software_node_reference *references; }; bool is_software_node(const struct fwnode_handle *fwnode); -- cgit v1.2.3 From bf9e25ec12877a622857460c2f542a6c31393250 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 3 Dec 2019 18:38:47 +0200 Subject: video: fbdev: make fbops member of struct fb_info a const pointer Now that we no longer modify the fbops, or hold non-const pointers to it, we can make it const. After this, we can start making the fbops const all over the place. Cc: linux-fbdev@vger.kernel.org Reviewed-by: Daniel Vetter Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/700c6b52c39c6e7babaa921f583eac354714d9fc.1575390740.git.jani.nikula@intel.com --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index a6ad528990de..6557fabdea62 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -472,7 +472,7 @@ struct fb_info { struct fb_deferred_io *fbdefio; #endif - struct fb_ops *fbops; + const struct fb_ops *fbops; struct device *device; /* This is the parent */ struct device *dev; /* This is this fb device */ int class_flag; /* private sysfs flags */ -- cgit v1.2.3 From 2496396fcb44404ead24b578c583d5286886e857 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Oct 2019 21:18:10 +0200 Subject: sched/rt, fs: Use CONFIG_PREEMPTION MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Switch the i_size() and part_nr_sects_…() code over to use CONFIG_PREEMPTION. Update the comment for fsstack_copy_inode_size() also to refer to CONFIG_PREEMPTION. [bigeasy: +PREEMPT comments] Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Alexander Viro Cc: Linus Torvalds Cc: Peter Zijlstra Cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20191015191821.11479-24-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/fs.h | 4 ++-- include/linux/genhd.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..dddfcbb140a7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -855,7 +855,7 @@ static inline loff_t i_size_read(const struct inode *inode) i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); @@ -880,7 +880,7 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8bb63027e4d6..a927829bb73a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -718,7 +718,7 @@ static inline void hd_free_part(struct hd_struct *part) * accessor function. * * Code written along the lines of i_size_read() and i_size_write(). - * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption + * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption * on. */ static inline sector_t part_nr_sects_read(struct hd_struct *part) @@ -731,7 +731,7 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part) nr_sects = part->nr_sects; } while (read_seqcount_retry(&part->nr_sects_seq, seq)); return nr_sects; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) sector_t nr_sects; preempt_disable(); @@ -754,7 +754,7 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) write_seqcount_begin(&part->nr_sects_seq); part->nr_sects = size; write_seqcount_end(&part->nr_sects_seq); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); part->nr_sects = size; preempt_enable(); -- cgit v1.2.3 From ce623f89872df4253719be71531116751eeab85f Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:27 +1100 Subject: nsfs: clean-up ns_get_path() signature to return int ns_get_path() and ns_get_path_cb() only ever return either NULL or an ERR_PTR. It is far more idiomatic to simply return an integer, and it makes all of the callers of ns_get_path() more straightforward to read. Fixes: e149ed2b805f ("take the targets of /proc/*/ns/* symlinks to separate fs") Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/proc_ns.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index d31cb6215905..aed366b4795c 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -76,10 +76,10 @@ static inline int ns_alloc_inum(struct ns_common *ns) extern struct file *proc_ns_fget(int fd); #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) -extern void *ns_get_path(struct path *path, struct task_struct *task, +extern int ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops); typedef struct ns_common *ns_get_path_helper_t(void *); -extern void *ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, +extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, void *private_data); extern int ns_get_name(char *buf, size_t size, struct task_struct *task, -- cgit v1.2.3 From 1bc82070fa2763bdca626fa8bde72b35f11e8960 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:28 +1100 Subject: namei: allow nd_jump_link() to produce errors In preparation for LOOKUP_NO_MAGICLINKS, it's necessary to add the ability for nd_jump_link() to return an error which the corresponding get_link() caller must propogate back up to the VFS. Suggested-by: Al Viro Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 7fe7b87a3ded..b2479cc119c6 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -69,7 +69,7 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); -extern void nd_jump_link(struct path *path); +extern int __must_check nd_jump_link(struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { -- cgit v1.2.3 From 278121417a72d87fb29dd8c48801f80821e8f75a Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:30 +1100 Subject: namei: LOOKUP_NO_SYMLINKS: block symlink resolution /* Background. */ Userspace cannot easily resolve a path without resolving symlinks, and would have to manually resolve each path component with O_PATH and O_NOFOLLOW. This is clearly inefficient, and can be fairly easy to screw up (resulting in possible security bugs). Linus has mentioned that Git has a particular need for this kind of flag[1]. It also resolves a fairly long-standing perceived deficiency in O_NOFOLLOw -- that it only blocks the opening of trailing symlinks. This is part of a refresh of Al's AT_NO_JUMPS patchset[2] (which was a variation on David Drysdale's O_BENEATH patchset[3], which in turn was based on the Capsicum project[4]). /* Userspace API. */ LOOKUP_NO_SYMLINKS will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_NO_SYMLINKS applies to all components of the path. With LOOKUP_NO_SYMLINKS, any symlink path component encountered during path resolution will yield -ELOOP. If the trailing component is a symlink (and no other components were symlinks), then O_PATH|O_NOFOLLOW will not error out and will instead provide a handle to the trailing symlink -- without resolving it. /* Testing. */ LOOKUP_NO_SYMLINKS is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/CA+55aFyOKM7DW7+0sdDFKdZFXgptb5r1id9=Wvhd8AgSP7qjwQ@mail.gmail.com/ [2]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [3]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [4]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ Cc: Christian Brauner Suggested-by: Al Viro Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index b2479cc119c6..c42a1924ad67 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -39,6 +39,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_ROOT 0x2000 #define LOOKUP_ROOT_GRABBED 0x0008 +/* Scoping flags for lookup. */ +#define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ + extern int path_pts(struct path *path); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -- cgit v1.2.3 From 4b99d4996979d582859c5a49072e92de124bf691 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:31 +1100 Subject: namei: LOOKUP_NO_MAGICLINKS: block magic-link resolution /* Background. */ There has always been a special class of symlink-like objects in procfs (and a few other pseudo-filesystems) which allow for non-lexical resolution of paths using nd_jump_link(). These "magic-links" do not follow traditional mount namespace boundaries, and have been used consistently in container escape attacks because they can be used to trick unsuspecting privileged processes into resolving unexpected paths. It is also non-trivial for userspace to unambiguously avoid resolving magic-links, because they do not have a reliable indication that they are a magic-link (in order to verify them you'd have to manually open the path given by readlink(2) and then verify that the two file descriptors reference the same underlying file, which is plagued with possible race conditions or supplementary attack scenarios). It would therefore be very helpful for userspace to be able to avoid these symlinks easily, thus hopefully removing a tool from attackers' toolboxes. This is part of a refresh of Al's AT_NO_JUMPS patchset[1] (which was a variation on David Drysdale's O_BENEATH patchset[2], which in turn was based on the Capsicum project[3]). /* Userspace API. */ LOOKUP_NO_MAGICLINKS will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_NO_MAGICLINKS applies to all components of the path. With LOOKUP_NO_MAGICLINKS, any magic-link path component encountered during path resolution will yield -ELOOP. The handling of ~LOOKUP_FOLLOW for a trailing magic-link is identical to LOOKUP_NO_SYMLINKS. LOOKUP_NO_SYMLINKS implies LOOKUP_NO_MAGICLINKS. /* Testing. */ LOOKUP_NO_MAGICLINKS is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [2]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [3]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ Cc: Christian Brauner Suggested-by: David Drysdale Suggested-by: Al Viro Suggested-by: Andy Lutomirski Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index c42a1924ad67..f8acec81cf03 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -41,6 +41,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ +#define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ extern int path_pts(struct path *path); -- cgit v1.2.3 From 72ba29297e1439efaa54d9125b866ae9d15df339 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:32 +1100 Subject: namei: LOOKUP_NO_XDEV: block mountpoint crossing /* Background. */ The need to contain path operations within a mountpoint has been a long-standing usecase that userspace has historically implemented manually with liberal usage of stat(). find, rsync, tar and many other programs implement these semantics -- but it'd be much simpler to have a fool-proof way of refusing to open a path if it crosses a mountpoint. This is part of a refresh of Al's AT_NO_JUMPS patchset[1] (which was a variation on David Drysdale's O_BENEATH patchset[2], which in turn was based on the Capsicum project[3]). /* Userspace API. */ LOOKUP_NO_XDEV will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_NO_XDEV applies to all components of the path. With LOOKUP_NO_XDEV, any path component which crosses a mount-point during path resolution (including "..") will yield an -EXDEV. Absolute paths, absolute symlinks, and magic-links will only yield an -EXDEV if the jump involved changing mount-points. /* Testing. */ LOOKUP_NO_XDEV is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [2]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [3]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ Cc: Christian Brauner Suggested-by: David Drysdale Suggested-by: Al Viro Suggested-by: Andy Lutomirski Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index f8acec81cf03..edb4562b5c4e 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -42,6 +42,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ +#define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ extern int path_pts(struct path *path); -- cgit v1.2.3 From adb21d2b526f7f196b2f3fdca97d80ba05dd14a0 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:33 +1100 Subject: namei: LOOKUP_BENEATH: O_BENEATH-like scoped resolution /* Background. */ There are many circumstances when userspace wants to resolve a path and ensure that it doesn't go outside of a particular root directory during resolution. Obvious examples include archive extraction tools, as well as other security-conscious userspace programs. FreeBSD spun out O_BENEATH from their Capsicum project[1,2], so it also seems reasonable to implement similar functionality for Linux. This is part of a refresh of Al's AT_NO_JUMPS patchset[3] (which was a variation on David Drysdale's O_BENEATH patchset[4], which in turn was based on the Capsicum project[5]). /* Userspace API. */ LOOKUP_BENEATH will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_BENEATH applies to all components of the path. With LOOKUP_BENEATH, any path component which attempts to "escape" the starting point of the filesystem lookup (the dirfd passed to openat) will yield -EXDEV. Thus, all absolute paths and symlinks are disallowed. Due to a security concern brought up by Jann[6], any ".." path components are also blocked. This restriction will be lifted in a future patch, but requires more work to ensure that permitting ".." is done safely. Magic-link jumps are also blocked, because they can beam the path lookup across the starting point. It would be possible to detect and block only the "bad" crossings with path_is_under() checks, but it's unclear whether it makes sense to permit magic-links at all. However, userspace is recommended to pass LOOKUP_NO_MAGICLINKS if they want to ensure that magic-link crossing is entirely disabled. /* Testing. */ LOOKUP_BENEATH is tested as part of the openat2(2) selftests. [1]: https://reviews.freebsd.org/D2808 [2]: https://reviews.freebsd.org/D17547 [3]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [4]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [5]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ [6]: https://lore.kernel.org/lkml/CAG48ez1jzNvxB+bfOBnERFGp=oMM0vHWuLD6EULmne3R6xa53w@mail.gmail.com/ Cc: Christian Brauner Suggested-by: David Drysdale Suggested-by: Al Viro Suggested-by: Andy Lutomirski Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index edb4562b5c4e..d2a98083be77 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -2,6 +2,7 @@ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H +#include #include #include #include @@ -43,6 +44,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ +#define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ +/* LOOKUP_* flags which do scope-related checks based on the dirfd. */ +#define LOOKUP_IS_SCOPED LOOKUP_BENEATH extern int path_pts(struct path *path); -- cgit v1.2.3 From 8db52c7e7ee1bd861b6096fcafc0fe7d0f24a994 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:34 +1100 Subject: namei: LOOKUP_IN_ROOT: chroot-like scoped resolution /* Background. */ Container runtimes or other administrative management processes will often interact with root filesystems while in the host mount namespace, because the cost of doing a chroot(2) on every operation is too prohibitive (especially in Go, which cannot safely use vfork). However, a malicious program can trick the management process into doing operations on files outside of the root filesystem through careful crafting of symlinks. Most programs that need this feature have attempted to make this process safe, by doing all of the path resolution in userspace (with symlinks being scoped to the root of the malicious root filesystem). Unfortunately, this method is prone to foot-guns and usually such implementations have subtle security bugs. Thus, what userspace needs is a way to resolve a path as though it were in a chroot(2) -- with all absolute symlinks being resolved relative to the dirfd root (and ".." components being stuck under the dirfd root). It is much simpler and more straight-forward to provide this functionality in-kernel (because it can be done far more cheaply and correctly). More classical applications that also have this problem (which have their own potentially buggy userspace path sanitisation code) include web servers, archive extraction tools, network file servers, and so on. /* Userspace API. */ LOOKUP_IN_ROOT will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_IN_ROOT applies to all components of the path. With LOOKUP_IN_ROOT, any path component which attempts to cross the starting point of the pathname lookup (the dirfd passed to openat) will remain at the starting point. Thus, all absolute paths and symlinks will be scoped within the starting point. There is a slight change in behaviour regarding pathnames -- if the pathname is absolute then the dirfd is still used as the root of resolution of LOOKUP_IN_ROOT is specified (this is to avoid obvious foot-guns, at the cost of a minor API inconsistency). As with LOOKUP_BENEATH, Jann's security concern about ".."[1] applies to LOOKUP_IN_ROOT -- therefore ".." resolution is blocked. This restriction will be lifted in a future patch, but requires more work to ensure that permitting ".." is done safely. Magic-link jumps are also blocked, because they can beam the path lookup across the starting point. It would be possible to detect and block only the "bad" crossings with path_is_under() checks, but it's unclear whether it makes sense to permit magic-links at all. However, userspace is recommended to pass LOOKUP_NO_MAGICLINKS if they want to ensure that magic-link crossing is entirely disabled. /* Testing. */ LOOKUP_IN_ROOT is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/CAG48ez1jzNvxB+bfOBnERFGp=oMM0vHWuLD6EULmne3R6xa53w@mail.gmail.com/ Cc: Christian Brauner Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index d2a98083be77..4e77068f7a1a 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -45,8 +45,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ +#define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ -#define LOOKUP_IS_SCOPED LOOKUP_BENEATH +#define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); -- cgit v1.2.3 From ba70609d5ec664a8f36ba1c857fcd97a478adf79 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 2 Dec 2019 21:19:44 -0800 Subject: fs: Delete timespec64_trunc() There are no more callers to the function remaining. Signed-off-by: Deepa Dinamani Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..46dd7e6f6d73 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1575,7 +1575,6 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } -extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran); extern struct timespec64 current_time(struct inode *inode); /* -- cgit v1.2.3 From b50b0580d27bc45a0637aefc8bac4d31aa85771a Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Mon, 25 Nov 2019 14:48:57 +0100 Subject: net: add queue argument to __skb_wait_for_more_packets and __skb_{,try_}recv_datagram This will be used by ESP over TCP to handle the queue of IKE messages. Signed-off-by: Sabrina Dubroca Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/linux/skbuff.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e9133bcf0544..49a10f9cc538 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3459,7 +3459,8 @@ static inline void skb_frag_list_init(struct sk_buff *skb) for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) -int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, +int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, + int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, @@ -3468,12 +3469,16 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff *skb), int *off, int *err, struct sk_buff **last); -struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, +struct sk_buff *__skb_try_recv_datagram(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err, struct sk_buff **last); -struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, +struct sk_buff *__skb_recv_datagram(struct sock *sk, + struct sk_buff_head *sk_queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err); -- cgit v1.2.3 From b6d0531ec7e2ae923395a1d5a80edb7ee51ac204 Mon Sep 17 00:00:00 2001 From: Fabien Dessenne Date: Mon, 2 Dec 2019 10:01:17 +0100 Subject: moduleparam: fix kerneldoc Document missing @arg in xxx_param_cb(). Describe all parameters of module_param_[named_]unsafe() and all *_param_cb() to make ./scripts/kernel-doc happy. Acked-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Fabien Dessenne Signed-off-by: Jessica Yu --- include/linux/moduleparam.h | 82 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 77 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index e5c3e23919b8..3ef917ff0964 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -128,6 +128,9 @@ struct kparam_array /** * module_param_unsafe - same as module_param but taints kernel + * @name: the variable to alter, and exposed parameter name. + * @type: the type of the parameter + * @perm: visibility in sysfs. */ #define module_param_unsafe(name, type, perm) \ module_param_named_unsafe(name, name, type, perm) @@ -150,6 +153,10 @@ struct kparam_array /** * module_param_named_unsafe - same as module_param_named but taints kernel + * @name: a valid C identifier which is the parameter name. + * @value: the actual lvalue to alter. + * @type: the type of the parameter + * @perm: visibility in sysfs. */ #define module_param_named_unsafe(name, value, type, perm) \ param_check_##type(name, &(value)); \ @@ -160,6 +167,7 @@ struct kparam_array * module_param_cb - general callback for a module/cmdline parameter * @name: a valid C identifier which is the parameter name. * @ops: the set & get operations for this parameter. + * @arg: args for @ops * @perm: visibility in sysfs. * * The ops can have NULL set or get functions. @@ -171,36 +179,96 @@ struct kparam_array __module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1, \ KERNEL_PARAM_FL_UNSAFE) +#define __level_param_cb(name, ops, arg, perm, level) \ + __module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, level, 0) /** - * _param_cb - general callback for a module/cmdline parameter - * to be evaluated before certain initcall level + * core_param_cb - general callback for a module/cmdline parameter + * to be evaluated before core initcall level * @name: a valid C identifier which is the parameter name. * @ops: the set & get operations for this parameter. + * @arg: args for @ops * @perm: visibility in sysfs. * * The ops can have NULL set or get functions. */ -#define __level_param_cb(name, ops, arg, perm, level) \ - __module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, level, 0) - #define core_param_cb(name, ops, arg, perm) \ __level_param_cb(name, ops, arg, perm, 1) +/** + * postcore_param_cb - general callback for a module/cmdline parameter + * to be evaluated before postcore initcall level + * @name: a valid C identifier which is the parameter name. + * @ops: the set & get operations for this parameter. + * @arg: args for @ops + * @perm: visibility in sysfs. + * + * The ops can have NULL set or get functions. + */ #define postcore_param_cb(name, ops, arg, perm) \ __level_param_cb(name, ops, arg, perm, 2) +/** + * arch_param_cb - general callback for a module/cmdline parameter + * to be evaluated before arch initcall level + * @name: a valid C identifier which is the parameter name. + * @ops: the set & get operations for this parameter. + * @arg: args for @ops + * @perm: visibility in sysfs. + * + * The ops can have NULL set or get functions. + */ #define arch_param_cb(name, ops, arg, perm) \ __level_param_cb(name, ops, arg, perm, 3) +/** + * subsys_param_cb - general callback for a module/cmdline parameter + * to be evaluated before subsys initcall level + * @name: a valid C identifier which is the parameter name. + * @ops: the set & get operations for this parameter. + * @arg: args for @ops + * @perm: visibility in sysfs. + * + * The ops can have NULL set or get functions. + */ #define subsys_param_cb(name, ops, arg, perm) \ __level_param_cb(name, ops, arg, perm, 4) +/** + * fs_param_cb - general callback for a module/cmdline parameter + * to be evaluated before fs initcall level + * @name: a valid C identifier which is the parameter name. + * @ops: the set & get operations for this parameter. + * @arg: args for @ops + * @perm: visibility in sysfs. + * + * The ops can have NULL set or get functions. + */ #define fs_param_cb(name, ops, arg, perm) \ __level_param_cb(name, ops, arg, perm, 5) +/** + * device_param_cb - general callback for a module/cmdline parameter + * to be evaluated before device initcall level + * @name: a valid C identifier which is the parameter name. + * @ops: the set & get operations for this parameter. + * @arg: args for @ops + * @perm: visibility in sysfs. + * + * The ops can have NULL set or get functions. + */ #define device_param_cb(name, ops, arg, perm) \ __level_param_cb(name, ops, arg, perm, 6) +/** + * late_param_cb - general callback for a module/cmdline parameter + * to be evaluated before late initcall level + * @name: a valid C identifier which is the parameter name. + * @ops: the set & get operations for this parameter. + * @arg: args for @ops + * @perm: visibility in sysfs. + * + * The ops can have NULL set or get functions. + */ #define late_param_cb(name, ops, arg, perm) \ __level_param_cb(name, ops, arg, perm, 7) @@ -263,6 +331,10 @@ static inline void kernel_param_unlock(struct module *mod) /** * core_param_unsafe - same as core_param but taints kernel + * @name: the name of the cmdline and sysfs parameter (often the same as var) + * @var: the variable + * @type: the type of the parameter + * @perm: visibility in sysfs */ #define core_param_unsafe(name, var, type, perm) \ param_check_##type(name, &(var)); \ -- cgit v1.2.3 From df1e849ae4559544ff00ff5052eefe2479750539 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 27 Nov 2019 16:36:45 -0800 Subject: rcu: Enable tick for nohz_full CPUs slow to provide expedited QS An expedited grace period can be stalled by a nohz_full CPU looping in kernel context. This possibility is currently handled by some carefully crafted checks in rcu_read_unlock_special() that enlist help from ksoftirqd when permitted by the scheduler. However, it is exactly these checks that require the scheduler avoid holding any of its rq or pi locks across rcu_read_unlock() without also having held them across the entire RCU read-side critical section. It would therefore be very nice if expedited grace periods could handle nohz_full CPUs looping in kernel context without such checks. This commit therefore adds code to the expedited grace period's wait and cleanup code that forces the scheduler-clock interrupt on for CPUs that fail to quickly supply a quiescent state. "Quickly" is currently a hard-coded single-jiffy delay. Signed-off-by: Paul E. McKenney --- include/linux/tick.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 7896f792d3b0..7340613c7eff 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -109,8 +109,10 @@ enum tick_dep_bits { TICK_DEP_BIT_PERF_EVENTS = 1, TICK_DEP_BIT_SCHED = 2, TICK_DEP_BIT_CLOCK_UNSTABLE = 3, - TICK_DEP_BIT_RCU = 4 + TICK_DEP_BIT_RCU = 4, + TICK_DEP_BIT_RCU_EXP = 5 }; +#define TICK_DEP_BIT_MAX TICK_DEP_BIT_RCU_EXP #define TICK_DEP_MASK_NONE 0 #define TICK_DEP_MASK_POSIX_TIMER (1 << TICK_DEP_BIT_POSIX_TIMER) @@ -118,6 +120,7 @@ enum tick_dep_bits { #define TICK_DEP_MASK_SCHED (1 << TICK_DEP_BIT_SCHED) #define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) #define TICK_DEP_MASK_RCU (1 << TICK_DEP_BIT_RCU) +#define TICK_DEP_MASK_RCU_EXP (1 << TICK_DEP_BIT_RCU_EXP) #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; -- cgit v1.2.3 From f452ee096d95482892b101bde4fd037fa025d3cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Fri, 4 Oct 2019 23:54:02 +0200 Subject: rculist: Describe variadic macro argument in a Sphinx-compatible way MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Without this patch, Sphinx shows "variable arguments" as the description of the cond argument, rather than the intended description, and prints the following warnings: ./include/linux/rculist.h:374: warning: Excess function parameter 'cond' description in 'list_for_each_entry_rcu' ./include/linux/rculist.h:651: warning: Excess function parameter 'cond' description in 'hlist_for_each_entry_rcu' Signed-off-by: Jonathan Neuschäfer Acked-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 4158b7212936..61c6728a71f7 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -361,7 +361,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @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: optional lockdep expression if called from non-RCU protection. + * @cond...: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() @@ -636,7 +636,7 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @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: optional lockdep expression if called from non-RCU protection. + * @cond...: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() -- cgit v1.2.3 From c54a2744497db4b6887b9c905ef7aa0b3620c956 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 11:37:37 -0800 Subject: list: Add hlist_unhashed_lockless() We would like to use hlist_unhashed() from timer_pending(), which runs without protection of a lock. Note that other callers might also want to use this variant. Instead of forcing a READ_ONCE() for all hlist_unhashed() callers, add a new helper with an explicit _lockless suffix in the name to better document what is going on. Also add various WRITE_ONCE() in __hlist_del(), hlist_add_head() and hlist_add_before()/hlist_add_behind() to pair with the READ_ONCE(). Signed-off-by: Eric Dumazet Cc: Thomas Gleixner [ paulmck: Also add WRITE_ONCE() to rculist.h. ] Signed-off-by: Paul E. McKenney --- include/linux/list.h | 32 +++++++++++++++++++++----------- include/linux/rculist.h | 24 ++++++++++++------------ 2 files changed, 33 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 85c92555e31f..61f5aaf96192 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -749,6 +749,16 @@ static inline int hlist_unhashed(const struct hlist_node *h) return !h->pprev; } +/* This variant of hlist_unhashed() must be used in lockless contexts + * to avoid potential load-tearing. + * The READ_ONCE() is paired with the various WRITE_ONCE() in hlist + * helpers that are defined below. + */ +static inline int hlist_unhashed_lockless(const struct hlist_node *h) +{ + return !READ_ONCE(h->pprev); +} + static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); @@ -761,7 +771,7 @@ static inline void __hlist_del(struct hlist_node *n) WRITE_ONCE(*pprev, next); if (next) - next->pprev = pprev; + WRITE_ONCE(next->pprev, pprev); } static inline void hlist_del(struct hlist_node *n) @@ -782,32 +792,32 @@ static inline void hlist_del_init(struct hlist_node *n) static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; - n->next = first; + WRITE_ONCE(n->next, first); if (first) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); } /* next must be != NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { - n->pprev = next->pprev; - n->next = next; - next->pprev = &n->next; + WRITE_ONCE(n->pprev, next->pprev); + WRITE_ONCE(n->next, next); + WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { - n->next = prev->next; - prev->next = n; - n->pprev = &prev->next; + WRITE_ONCE(n->next, prev->next); + WRITE_ONCE(prev->next, n); + WRITE_ONCE(n->pprev, &prev->next); if (n->next) - n->next->pprev = &n->next; + WRITE_ONCE(n->next->pprev, &n->next); } /* after that we'll appear to be on some hlist and hlist_del will work */ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 61c6728a71f7..4b7ae1bf50b3 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -173,7 +173,7 @@ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); - n->pprev = NULL; + WRITE_ONCE(n->pprev, NULL); } } @@ -473,7 +473,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); - n->pprev = LIST_POISON2; + WRITE_ONCE(n->pprev, LIST_POISON2); } /** @@ -489,11 +489,11 @@ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *next = old->next; new->next = next; - new->pprev = old->pprev; + WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) - new->next->pprev = &new->next; - old->pprev = LIST_POISON2; + WRITE_ONCE(new->next->pprev, &new->next); + WRITE_ONCE(old->pprev, LIST_POISON2); } /* @@ -528,10 +528,10 @@ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_node *first = h->first; n->next = first; - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); } /** @@ -564,7 +564,7 @@ static inline void hlist_add_tail_rcu(struct hlist_node *n, if (last) { n->next = last->next; - n->pprev = &last->next; + WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); @@ -592,10 +592,10 @@ static inline void hlist_add_tail_rcu(struct hlist_node *n, static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { - n->pprev = next->pprev; + WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); - next->pprev = &n->next; + WRITE_ONCE(next->pprev, &n->next); } /** @@ -620,10 +620,10 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; - n->pprev = &prev->next; + WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) - n->next->pprev = &n->next; + WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ -- cgit v1.2.3 From b3e627d3d5092a87fc9b9e37e341610cfecfbfdc Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 15 Oct 2019 02:55:57 +0000 Subject: rcu: Make PREEMPT_RCU be a modifier to TREE_RCU Currently PREEMPT_RCU and TREE_RCU are mutually exclusive Kconfig options. But PREEMPT_RCU actually specifies a kind of TREE_RCU, namely a preemptible TREE_RCU. This commit therefore makes PREEMPT_RCU be a modifer to the TREE_RCU Kconfig option. This has the benefit of simplifying several of the #if expressions that formerly needed to check both, but now need only check one or the other. Signed-off-by: Lai Jiangshan Signed-off-by: Lai Jiangshan Reviewed-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0b7506330c87..70a41cd8f58d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -167,7 +167,7 @@ do { \ * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) +#if defined(CONFIG_TREE_RCU) #include #elif defined(CONFIG_TINY_RCU) #include @@ -601,7 +601,7 @@ do { \ * read-side critical section that would block in a !PREEMPT kernel. * But if you want the full story, read on! * - * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), + * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, -- cgit v1.2.3 From 90326f0521a88004194f88f1b597b54347482b5c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 15 Oct 2019 21:18:14 +0200 Subject: rcu: Use CONFIG_PREEMPTION where appropriate The config option `CONFIG_PREEMPT' is used for the preemption model "Low-Latency Desktop". The config option `CONFIG_PREEMPTION' is enabled when kernel preemption is enabled which is true for the preemption model `CONFIG_PREEMPT' and `CONFIG_PREEMPT_RT'. Use `CONFIG_PREEMPTION' if it applies to both preemption models and not just to `CONFIG_PREEMPT'. Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Davidlohr Bueso Cc: rcu@vger.kernel.org Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 70a41cd8f58d..eb32fff81c30 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -154,7 +154,7 @@ static inline void exit_tasks_rcu_finish(void) { } * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() - * machinery were to be shut off, as some advocate for PREEMPT kernels. + * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ @@ -598,7 +598,7 @@ do { \ * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU - * read-side critical section that would block in a !PREEMPT kernel. + * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), -- cgit v1.2.3 From 59438b46471ae6cdfb761afc8c9beaf1e428a331 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Wed, 27 Nov 2019 12:04:36 -0500 Subject: security,lockdown,selinux: implement SELinux lockdown Implement a SELinux hook for lockdown. If the lockdown module is also enabled, then a denial by the lockdown module will take precedence over SELinux, so SELinux can only further restrict lockdown decisions. The SELinux hook only distinguishes at the granularity of integrity versus confidentiality similar to the lockdown module, but includes the full lockdown reason as part of the audit record as a hint in diagnosing what triggered the denial. To support this auditing, move the lockdown_reasons[] string array from being private to the lockdown module to the security framework so that it can be used by the lsm audit code and so that it is always available even when the lockdown module is disabled. Note that the SELinux implementation allows the integrity and confidentiality reasons to be controlled independently from one another. Thus, in an SELinux policy, one could allow operations that specify an integrity reason while blocking operations that specify a confidentiality reason. The SELinux hook implementation is stricter than the lockdown module in validating the provided reason value. Sample AVC audit output from denials: avc: denied { integrity } for pid=3402 comm="fwupd" lockdown_reason="/dev/mem,kmem,port" scontext=system_u:system_r:fwupd_t:s0 tcontext=system_u:system_r:fwupd_t:s0 tclass=lockdown permissive=0 avc: denied { confidentiality } for pid=4628 comm="cp" lockdown_reason="/proc/kcore access" scontext=unconfined_u:unconfined_r:test_lockdown_integrity_t:s0-s0:c0.c1023 tcontext=unconfined_u:unconfined_r:test_lockdown_integrity_t:s0-s0:c0.c1023 tclass=lockdown permissive=0 Signed-off-by: Stephen Smalley Reviewed-by: James Morris [PM: some merge fuzz do the the perf hooks] Signed-off-by: Paul Moore --- include/linux/lsm_audit.h | 2 ++ include/linux/security.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 915330abf6e5..99d629fd9944 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -74,6 +74,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_FILE 12 #define LSM_AUDIT_DATA_IBPKEY 13 #define LSM_AUDIT_DATA_IBENDPORT 14 +#define LSM_AUDIT_DATA_LOCKDOWN 15 union { struct path path; struct dentry *dentry; @@ -93,6 +94,7 @@ struct common_audit_data { struct file *file; struct lsm_ibpkey_audit *ibpkey; struct lsm_ibendport_audit *ibendport; + int reason; } u; /* this union contains LSM specific data */ union { diff --git a/include/linux/security.h b/include/linux/security.h index 3e8d4bacd59d..64b19f050343 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -128,6 +128,8 @@ enum lockdown_reason { LOCKDOWN_CONFIDENTIALITY_MAX, }; +extern const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1]; + /* These functions are in security/commoncap.c */ extern int cap_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts); -- cgit v1.2.3 From dda510890498b9a2f4b2142192f6d516c6c1e2e5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 6 Dec 2019 14:24:35 +0100 Subject: dmaengine: Remove spaces before TABs Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20191206132435.29139-1-geert+renesas@glider.be Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 8fcdee1c0cf9..dfd2d35b64af 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -481,7 +481,7 @@ struct dmaengine_unmap_data { * @cookie: tracking cookie for this transaction, set to -EBUSY if * this tx is sitting on a dependency list * @flags: flags to augment operation preparation, control completion, and - * communicate status + * communicate status * @phys: physical address of the descriptor * @chan: target channel for this operation * @tx_submit: accept the descriptor, assign ordered cookie and mark the -- cgit v1.2.3 From 1f059dfdf5d170dccbac92193be2fee3c1763384 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 28 Nov 2019 08:19:36 +0100 Subject: mm/vmalloc: Add empty headers and use them from In the x86 MM code we'd like to untangle various types of historic header dependency spaghetti, but for this we'd need to pass to the generic vmalloc code various vmalloc related defines that customarily come via the low level arch header. Signed-off-by: Ingo Molnar --- include/linux/vmalloc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a4b241102771..ec3813236699 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -10,6 +10,8 @@ #include #include +#include + struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ -- cgit v1.2.3 From 186525bd6b83efc592672e2d6185e4d7c810d2b4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 29 Nov 2019 08:17:25 +0100 Subject: mm, x86/mm: Untangle address space layout definitions from basic pgtable type definitions - Untangle the somewhat incestous way of how VMALLOC_START is used all across the kernel, but is, on x86, defined deep inside one of the lowest level page table headers. It doesn't help that vmalloc.h only includes a single asm header: #include /* pgprot_t */ So there was no existing cross-arch way to decouple address layout definitions from page.h details. I used this: #ifndef VMALLOC_START # include #endif This way every architecture that wants to simplify page.h can do so. - Also on x86 we had a couple of LDT related inline functions that used the late-stage address space layout positions - but these could be uninlined without real trouble - the end result is cleaner this way as well. Signed-off-by: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Borislav Petkov Cc: Linus Torvalds Cc: Andrew Morton Cc: Rik van Riel Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar --- include/linux/mm.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c97ea3b694e6..fb8f9412e2cf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -625,24 +625,19 @@ unsigned long vmalloc_to_pfn(const void *addr); * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ -static inline bool is_vmalloc_addr(const void *x) -{ -#ifdef CONFIG_MMU - unsigned long addr = (unsigned long)x; - - return addr >= VMALLOC_START && addr < VMALLOC_END; -#else - return false; -#endif -} #ifndef is_ioremap_addr #define is_ioremap_addr(x) is_vmalloc_addr(x) #endif #ifdef CONFIG_MMU +extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else +static inline bool is_vmalloc_addr(const void *x) +{ + return false; +} static inline int is_vmalloc_or_module_addr(const void *x) { return 0; -- cgit v1.2.3 From 03521794966c0123e45b84da5faa7382ad53cc16 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 6 Dec 2019 14:28:49 +0100 Subject: usb: host: ehci-sh: Remove unused platform data support ehci_sh_platdata was never used, remove it. It can be resurrected from git history when needed. This basically reverts commit 3e0c70d050c7ed6d ("usb: ehci-sh: Add PHY init function with platform data"). Signed-off-by: Geert Uytterhoeven Acked-by: Alan Stern Acked-by: Nobuhiro Iwamatsu Link: https://lore.kernel.org/r/20191206132849.29406-1-geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/ehci-sh.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/platform_data/ehci-sh.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ehci-sh.h b/include/linux/platform_data/ehci-sh.h deleted file mode 100644 index 219bd79dabfc..000000000000 --- a/include/linux/platform_data/ehci-sh.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * - * EHCI SuperH driver platform data - * - * Copyright (C) 2012 Nobuhiro Iwamatsu - * Copyright (C) 2012 Renesas Solutions Corp. - */ - -#ifndef __USB_EHCI_SH_H -#define __USB_EHCI_SH_H - -struct ehci_sh_platdata { - void (*phy_init)(void); /* Phy init function */ -}; - -#endif /* __USB_EHCI_SH_H */ -- cgit v1.2.3 From a3d1e7eb5abe3aa1095bc75d1a6760d3809bd672 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 18 Nov 2019 09:43:10 -0500 Subject: simple_recursive_removal(): kernel-side rm -rf for ramfs-style filesystems two requirements: no file creations in IS_DEADDIR and no cross-directory renames whatsoever. Signed-off-by: Al Viro --- include/linux/debugfs.h | 2 +- include/linux/fs.h | 2 ++ include/linux/tracefs.h | 1 - 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index bf9b6cafa4c2..3d013de64f70 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -83,7 +83,7 @@ struct dentry *debugfs_create_automount(const char *name, void *data); void debugfs_remove(struct dentry *dentry); -void debugfs_remove_recursive(struct dentry *dentry); +#define debugfs_remove_recursive debugfs_remove const struct file_operations *debugfs_real_fops(const struct file *filp); diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..9a2be7c0c088 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3303,6 +3303,8 @@ extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); +extern void simple_recursive_removal(struct dentry *, + void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern int noop_set_page_dirty(struct page *page); extern void noop_invalidatepage(struct page *page, unsigned int offset, diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 88d279c1b863..99912445974c 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -28,7 +28,6 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *tracefs_create_dir(const char *name, struct dentry *parent); void tracefs_remove(struct dentry *dentry); -void tracefs_remove_recursive(struct dentry *dentry); struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *parent, int (*mkdir)(const char *name), -- cgit v1.2.3 From c02a81fba74fe3488ad6b08bfb5a1329005418f8 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Tue, 3 Dec 2019 17:26:37 +0000 Subject: dma-buf: Add dma-buf heaps framework This framework allows a unified userspace interface for dma-buf exporters, allowing userland to allocate specific types of memory for use in dma-buf sharing. Each heap is given its own device node, which a user can allocate a dma-buf fd from using the DMA_HEAP_IOC_ALLOC. This code is an evoluiton of the Android ION implementation, and a big thanks is due to its authors/maintainers over time for their effort: Rebecca Schultz Zavin, Colin Cross, Benjamin Gaignard, Laura Abbott, and many other contributors! Cc: Laura Abbott Cc: Benjamin Gaignard Cc: Sumit Semwal Cc: Liam Mark Cc: Pratik Patel Cc: Brian Starkey Cc: Vincent Donnefort Cc: Sudipto Paul Cc: Andrew F. Davis Cc: Christoph Hellwig Cc: Chenbo Feng Cc: Alistair Strachan Cc: Hridya Valsaraju Cc: Sandeep Patil Cc: Hillf Danton Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Reviewed-by: Brian Starkey Acked-by: Sandeep Patil Signed-off-by: Andrew F. Davis Signed-off-by: John Stultz Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20191203172641.66642-2-john.stultz@linaro.org --- include/linux/dma-heap.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 include/linux/dma-heap.h (limited to 'include/linux') diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h new file mode 100644 index 000000000000..454e354d1ffb --- /dev/null +++ b/include/linux/dma-heap.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DMABUF Heaps Allocation Infrastructure + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#ifndef _DMA_HEAPS_H +#define _DMA_HEAPS_H + +#include +#include + +struct dma_heap; + +/** + * struct dma_heap_ops - ops to operate on a given heap + * @allocate: allocate dmabuf and return fd + * + * allocate returns dmabuf fd on success, -errno on error. + */ +struct dma_heap_ops { + int (*allocate)(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags); +}; + +/** + * struct dma_heap_export_info - information needed to export a new dmabuf heap + * @name: used for debugging/device-node name + * @ops: ops struct for this heap + * @priv: heap exporter private data + * + * Information needed to export a new dmabuf heap. + */ +struct dma_heap_export_info { + const char *name; + const struct dma_heap_ops *ops; + void *priv; +}; + +/** + * dma_heap_get_drvdata() - get per-heap driver data + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The per-heap data for the heap. + */ +void *dma_heap_get_drvdata(struct dma_heap *heap); + +/** + * dma_heap_add - adds a heap to dmabuf heaps + * @exp_info: information needed to register this heap + */ +struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info); + +#endif /* _DMA_HEAPS_H */ -- cgit v1.2.3 From f10870b05d5edc0652701c6a92eafcab5044795f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 10 Dec 2019 21:59:15 +0100 Subject: staging: remove isdn capi drivers As described in drivers/staging/isdn/TODO, the drivers are all assumed to be unmaintained and unused now, with gigaset being the last one to stop being maintained after Paul Bolle lost access to an ISDN network. The CAPI subsystem remains for now, as it is still required by bluetooth/cmtp. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20191210210455.3475361-1-arnd@arndb.de Signed-off-by: Greg Kroah-Hartman --- include/linux/b1pcmcia.h | 21 --------------------- 1 file changed, 21 deletions(-) delete mode 100644 include/linux/b1pcmcia.h (limited to 'include/linux') diff --git a/include/linux/b1pcmcia.h b/include/linux/b1pcmcia.h deleted file mode 100644 index 12a867c6061e..000000000000 --- a/include/linux/b1pcmcia.h +++ /dev/null @@ -1,21 +0,0 @@ -/* $Id: b1pcmcia.h,v 1.1.8.2 2001/09/23 22:25:05 kai Exp $ - * - * Exported functions of module b1pcmcia to be called by - * avm_cs card services module. - * - * Copyright 1999 by Carsten Paeth (calle@calle.in-berlin.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _B1PCMCIA_H_ -#define _B1PCMCIA_H_ - -int b1pcmcia_addcard_b1(unsigned int port, unsigned irq); -int b1pcmcia_addcard_m1(unsigned int port, unsigned irq); -int b1pcmcia_addcard_m2(unsigned int port, unsigned irq); -int b1pcmcia_delcard(unsigned int port, unsigned irq); - -#endif /* _B1PCMCIA_H_ */ -- cgit v1.2.3 From f59aba2f75795e5b6a4f1aa31f3e20d7b71ca804 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 10 Dec 2019 21:59:16 +0100 Subject: isdn: capi: dead code removal The staging isdn drivers are gone, and CONFIG_BT_CMTP is now the only user. This means a lot of the code in the subsystem has no remaining callers and can be removed. Change the capi user space front-end to be part of kernelcapi, and the combined module to only be compiled if BT_CMTP is also enabled, then remove the interfaces that have no remaining callers. As the notifier list and the capi_drivers list have no callers outside of kcapi.c, the implementation gets much simpler. Some definitions from the include/linux/*.h headers are only needed internally and are moved to kcapi.h. Acked-by: David Miller Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20191210210455.3475361-2-arnd@arndb.de Signed-off-by: Greg Kroah-Hartman --- include/linux/isdn/capilli.h | 18 -- include/linux/isdn/capiutil.h | 456 ------------------------------------------ include/linux/kernelcapi.h | 75 ------- 3 files changed, 549 deletions(-) (limited to 'include/linux') diff --git a/include/linux/isdn/capilli.h b/include/linux/isdn/capilli.h index d75e1ad72964..12be09b6883b 100644 --- a/include/linux/isdn/capilli.h +++ b/include/linux/isdn/capilli.h @@ -69,7 +69,6 @@ struct capi_ctr { unsigned short state; /* controller state */ int blocked; /* output blocked */ int traceflag; /* capi trace */ - wait_queue_head_t state_wait_queue; struct proc_dir_entry *procent; char procfn[128]; @@ -80,8 +79,6 @@ int detach_capi_ctr(struct capi_ctr *); void capi_ctr_ready(struct capi_ctr * card); void capi_ctr_down(struct capi_ctr * card); -void capi_ctr_suspend_output(struct capi_ctr * card); -void capi_ctr_resume_output(struct capi_ctr * card); void capi_ctr_handle_message(struct capi_ctr * card, u16 appl, struct sk_buff *skb); // --------------------------------------------------------------------------- @@ -91,23 +88,8 @@ struct capi_driver { char name[32]; /* driver name */ char revision[32]; - int (*add_card)(struct capi_driver *driver, capicardparams *data); - /* management information for kcapi */ struct list_head list; }; -void register_capi_driver(struct capi_driver *driver); -void unregister_capi_driver(struct capi_driver *driver); - -// --------------------------------------------------------------------------- -// library functions for use by hardware controller drivers - -void capilib_new_ncci(struct list_head *head, u16 applid, u32 ncci, u32 winsize); -void capilib_free_ncci(struct list_head *head, u16 applid, u32 ncci); -void capilib_release_appl(struct list_head *head, u16 applid); -void capilib_release(struct list_head *head); -void capilib_data_b3_conf(struct list_head *head, u16 applid, u32 ncci, u16 msgid); -u16 capilib_data_b3_req(struct list_head *head, u16 applid, u32 ncci, u16 msgid); - #endif /* __CAPILLI_H__ */ diff --git a/include/linux/isdn/capiutil.h b/include/linux/isdn/capiutil.h index 44bd6046e6e2..953fd500dff7 100644 --- a/include/linux/isdn/capiutil.h +++ b/include/linux/isdn/capiutil.h @@ -57,460 +57,4 @@ static inline void capimsg_setu32(void *m, int off, __u32 val) #define CAPIMSG_SETCONTROL(m, contr) capimsg_setu32(m, 8, contr) #define CAPIMSG_SETDATALEN(m, len) capimsg_setu16(m, 16, len) -/*----- basic-type definitions -----*/ - -typedef __u8 *_cstruct; - -typedef enum { - CAPI_COMPOSE, - CAPI_DEFAULT -} _cmstruct; - -/* - The _cmsg structure contains all possible CAPI 2.0 parameter. - All parameters are stored here first. The function CAPI_CMSG_2_MESSAGE - assembles the parameter and builds CAPI2.0 conform messages. - CAPI_MESSAGE_2_CMSG disassembles CAPI 2.0 messages and stores the - parameter in the _cmsg structure - */ - -typedef struct { - /* Header */ - __u16 ApplId; - __u8 Command; - __u8 Subcommand; - __u16 Messagenumber; - - /* Parameter */ - union { - __u32 adrController; - __u32 adrPLCI; - __u32 adrNCCI; - } adr; - - _cmstruct AdditionalInfo; - _cstruct B1configuration; - __u16 B1protocol; - _cstruct B2configuration; - __u16 B2protocol; - _cstruct B3configuration; - __u16 B3protocol; - _cstruct BC; - _cstruct BChannelinformation; - _cmstruct BProtocol; - _cstruct CalledPartyNumber; - _cstruct CalledPartySubaddress; - _cstruct CallingPartyNumber; - _cstruct CallingPartySubaddress; - __u32 CIPmask; - __u32 CIPmask2; - __u16 CIPValue; - __u32 Class; - _cstruct ConnectedNumber; - _cstruct ConnectedSubaddress; - __u32 Data; - __u16 DataHandle; - __u16 DataLength; - _cstruct FacilityConfirmationParameter; - _cstruct Facilitydataarray; - _cstruct FacilityIndicationParameter; - _cstruct FacilityRequestParameter; - __u16 FacilitySelector; - __u16 Flags; - __u32 Function; - _cstruct HLC; - __u16 Info; - _cstruct InfoElement; - __u32 InfoMask; - __u16 InfoNumber; - _cstruct Keypadfacility; - _cstruct LLC; - _cstruct ManuData; - __u32 ManuID; - _cstruct NCPI; - __u16 Reason; - __u16 Reason_B3; - __u16 Reject; - _cstruct Useruserdata; - - /* intern */ - unsigned l, p; - unsigned char *par; - __u8 *m; - - /* buffer to construct message */ - __u8 buf[180]; - -} _cmsg; - -/* - * capi_cmsg2message() assembles the parameter from _cmsg to a CAPI 2.0 - * conform message - */ -unsigned capi_cmsg2message(_cmsg * cmsg, __u8 * msg); - -/* - * capi_message2cmsg disassembles a CAPI message an writes the parameter - * into _cmsg for easy access - */ -unsigned capi_message2cmsg(_cmsg * cmsg, __u8 * msg); - -/* - * capi_cmsg_header() fills the _cmsg structure with default values, so only - * parameter with non default values must be changed before sending the - * message. - */ -unsigned capi_cmsg_header(_cmsg * cmsg, __u16 _ApplId, - __u8 _Command, __u8 _Subcommand, - __u16 _Messagenumber, __u32 _Controller); - -/*-----------------------------------------------------------------------*/ - -/* - * Debugging / Tracing functions - */ - -char *capi_cmd2str(__u8 cmd, __u8 subcmd); - -typedef struct { - u_char *buf; - u_char *p; - size_t size; - size_t pos; -} _cdebbuf; - -#define CDEBUG_SIZE 1024 -#define CDEBUG_GSIZE 4096 - -void cdebbuf_free(_cdebbuf *cdb); -int cdebug_init(void); -void cdebug_exit(void); - -_cdebbuf *capi_cmsg2str(_cmsg *cmsg); -_cdebbuf *capi_message2str(__u8 *msg); - -/*-----------------------------------------------------------------------*/ - -static inline void capi_cmsg_answer(_cmsg * cmsg) -{ - cmsg->Subcommand |= 0x01; -} - -/*-----------------------------------------------------------------------*/ - -static inline void capi_fill_CONNECT_B3_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - _cstruct NCPI) -{ - capi_cmsg_header(cmsg, ApplId, 0x82, 0x80, Messagenumber, adr); - cmsg->NCPI = NCPI; -} - -static inline void capi_fill_FACILITY_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u16 FacilitySelector, - _cstruct FacilityRequestParameter) -{ - capi_cmsg_header(cmsg, ApplId, 0x80, 0x80, Messagenumber, adr); - cmsg->FacilitySelector = FacilitySelector; - cmsg->FacilityRequestParameter = FacilityRequestParameter; -} - -static inline void capi_fill_INFO_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - _cstruct CalledPartyNumber, - _cstruct BChannelinformation, - _cstruct Keypadfacility, - _cstruct Useruserdata, - _cstruct Facilitydataarray) -{ - capi_cmsg_header(cmsg, ApplId, 0x08, 0x80, Messagenumber, adr); - cmsg->CalledPartyNumber = CalledPartyNumber; - cmsg->BChannelinformation = BChannelinformation; - cmsg->Keypadfacility = Keypadfacility; - cmsg->Useruserdata = Useruserdata; - cmsg->Facilitydataarray = Facilitydataarray; -} - -static inline void capi_fill_LISTEN_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u32 InfoMask, - __u32 CIPmask, - __u32 CIPmask2, - _cstruct CallingPartyNumber, - _cstruct CallingPartySubaddress) -{ - capi_cmsg_header(cmsg, ApplId, 0x05, 0x80, Messagenumber, adr); - cmsg->InfoMask = InfoMask; - cmsg->CIPmask = CIPmask; - cmsg->CIPmask2 = CIPmask2; - cmsg->CallingPartyNumber = CallingPartyNumber; - cmsg->CallingPartySubaddress = CallingPartySubaddress; -} - -static inline void capi_fill_ALERT_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - _cstruct BChannelinformation, - _cstruct Keypadfacility, - _cstruct Useruserdata, - _cstruct Facilitydataarray) -{ - capi_cmsg_header(cmsg, ApplId, 0x01, 0x80, Messagenumber, adr); - cmsg->BChannelinformation = BChannelinformation; - cmsg->Keypadfacility = Keypadfacility; - cmsg->Useruserdata = Useruserdata; - cmsg->Facilitydataarray = Facilitydataarray; -} - -static inline void capi_fill_CONNECT_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u16 CIPValue, - _cstruct CalledPartyNumber, - _cstruct CallingPartyNumber, - _cstruct CalledPartySubaddress, - _cstruct CallingPartySubaddress, - __u16 B1protocol, - __u16 B2protocol, - __u16 B3protocol, - _cstruct B1configuration, - _cstruct B2configuration, - _cstruct B3configuration, - _cstruct BC, - _cstruct LLC, - _cstruct HLC, - _cstruct BChannelinformation, - _cstruct Keypadfacility, - _cstruct Useruserdata, - _cstruct Facilitydataarray) -{ - - capi_cmsg_header(cmsg, ApplId, 0x02, 0x80, Messagenumber, adr); - cmsg->CIPValue = CIPValue; - cmsg->CalledPartyNumber = CalledPartyNumber; - cmsg->CallingPartyNumber = CallingPartyNumber; - cmsg->CalledPartySubaddress = CalledPartySubaddress; - cmsg->CallingPartySubaddress = CallingPartySubaddress; - cmsg->B1protocol = B1protocol; - cmsg->B2protocol = B2protocol; - cmsg->B3protocol = B3protocol; - cmsg->B1configuration = B1configuration; - cmsg->B2configuration = B2configuration; - cmsg->B3configuration = B3configuration; - cmsg->BC = BC; - cmsg->LLC = LLC; - cmsg->HLC = HLC; - cmsg->BChannelinformation = BChannelinformation; - cmsg->Keypadfacility = Keypadfacility; - cmsg->Useruserdata = Useruserdata; - cmsg->Facilitydataarray = Facilitydataarray; -} - -static inline void capi_fill_DATA_B3_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u32 Data, - __u16 DataLength, - __u16 DataHandle, - __u16 Flags) -{ - - capi_cmsg_header(cmsg, ApplId, 0x86, 0x80, Messagenumber, adr); - cmsg->Data = Data; - cmsg->DataLength = DataLength; - cmsg->DataHandle = DataHandle; - cmsg->Flags = Flags; -} - -static inline void capi_fill_DISCONNECT_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - _cstruct BChannelinformation, - _cstruct Keypadfacility, - _cstruct Useruserdata, - _cstruct Facilitydataarray) -{ - - capi_cmsg_header(cmsg, ApplId, 0x04, 0x80, Messagenumber, adr); - cmsg->BChannelinformation = BChannelinformation; - cmsg->Keypadfacility = Keypadfacility; - cmsg->Useruserdata = Useruserdata; - cmsg->Facilitydataarray = Facilitydataarray; -} - -static inline void capi_fill_DISCONNECT_B3_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - _cstruct NCPI) -{ - - capi_cmsg_header(cmsg, ApplId, 0x84, 0x80, Messagenumber, adr); - cmsg->NCPI = NCPI; -} - -static inline void capi_fill_MANUFACTURER_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u32 ManuID, - __u32 Class, - __u32 Function, - _cstruct ManuData) -{ - - capi_cmsg_header(cmsg, ApplId, 0xff, 0x80, Messagenumber, adr); - cmsg->ManuID = ManuID; - cmsg->Class = Class; - cmsg->Function = Function; - cmsg->ManuData = ManuData; -} - -static inline void capi_fill_RESET_B3_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - _cstruct NCPI) -{ - - capi_cmsg_header(cmsg, ApplId, 0x87, 0x80, Messagenumber, adr); - cmsg->NCPI = NCPI; -} - -static inline void capi_fill_SELECT_B_PROTOCOL_REQ(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u16 B1protocol, - __u16 B2protocol, - __u16 B3protocol, - _cstruct B1configuration, - _cstruct B2configuration, - _cstruct B3configuration) -{ - - capi_cmsg_header(cmsg, ApplId, 0x41, 0x80, Messagenumber, adr); - cmsg->B1protocol = B1protocol; - cmsg->B2protocol = B2protocol; - cmsg->B3protocol = B3protocol; - cmsg->B1configuration = B1configuration; - cmsg->B2configuration = B2configuration; - cmsg->B3configuration = B3configuration; -} - -static inline void capi_fill_CONNECT_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u16 Reject, - __u16 B1protocol, - __u16 B2protocol, - __u16 B3protocol, - _cstruct B1configuration, - _cstruct B2configuration, - _cstruct B3configuration, - _cstruct ConnectedNumber, - _cstruct ConnectedSubaddress, - _cstruct LLC, - _cstruct BChannelinformation, - _cstruct Keypadfacility, - _cstruct Useruserdata, - _cstruct Facilitydataarray) -{ - capi_cmsg_header(cmsg, ApplId, 0x02, 0x83, Messagenumber, adr); - cmsg->Reject = Reject; - cmsg->B1protocol = B1protocol; - cmsg->B2protocol = B2protocol; - cmsg->B3protocol = B3protocol; - cmsg->B1configuration = B1configuration; - cmsg->B2configuration = B2configuration; - cmsg->B3configuration = B3configuration; - cmsg->ConnectedNumber = ConnectedNumber; - cmsg->ConnectedSubaddress = ConnectedSubaddress; - cmsg->LLC = LLC; - cmsg->BChannelinformation = BChannelinformation; - cmsg->Keypadfacility = Keypadfacility; - cmsg->Useruserdata = Useruserdata; - cmsg->Facilitydataarray = Facilitydataarray; -} - -static inline void capi_fill_CONNECT_ACTIVE_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr) -{ - - capi_cmsg_header(cmsg, ApplId, 0x03, 0x83, Messagenumber, adr); -} - -static inline void capi_fill_CONNECT_B3_ACTIVE_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr) -{ - - capi_cmsg_header(cmsg, ApplId, 0x83, 0x83, Messagenumber, adr); -} - -static inline void capi_fill_CONNECT_B3_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u16 Reject, - _cstruct NCPI) -{ - capi_cmsg_header(cmsg, ApplId, 0x82, 0x83, Messagenumber, adr); - cmsg->Reject = Reject; - cmsg->NCPI = NCPI; -} - -static inline void capi_fill_CONNECT_B3_T90_ACTIVE_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr) -{ - - capi_cmsg_header(cmsg, ApplId, 0x88, 0x83, Messagenumber, adr); -} - -static inline void capi_fill_DATA_B3_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u16 DataHandle) -{ - - capi_cmsg_header(cmsg, ApplId, 0x86, 0x83, Messagenumber, adr); - cmsg->DataHandle = DataHandle; -} - -static inline void capi_fill_DISCONNECT_B3_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr) -{ - - capi_cmsg_header(cmsg, ApplId, 0x84, 0x83, Messagenumber, adr); -} - -static inline void capi_fill_DISCONNECT_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr) -{ - - capi_cmsg_header(cmsg, ApplId, 0x04, 0x83, Messagenumber, adr); -} - -static inline void capi_fill_FACILITY_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u16 FacilitySelector) -{ - - capi_cmsg_header(cmsg, ApplId, 0x80, 0x83, Messagenumber, adr); - cmsg->FacilitySelector = FacilitySelector; -} - -static inline void capi_fill_INFO_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr) -{ - - capi_cmsg_header(cmsg, ApplId, 0x08, 0x83, Messagenumber, adr); -} - -static inline void capi_fill_MANUFACTURER_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr, - __u32 ManuID, - __u32 Class, - __u32 Function, - _cstruct ManuData) -{ - - capi_cmsg_header(cmsg, ApplId, 0xff, 0x83, Messagenumber, adr); - cmsg->ManuID = ManuID; - cmsg->Class = Class; - cmsg->Function = Function; - cmsg->ManuData = ManuData; -} - -static inline void capi_fill_RESET_B3_RESP(_cmsg * cmsg, __u16 ApplId, __u16 Messagenumber, - __u32 adr) -{ - - capi_cmsg_header(cmsg, ApplId, 0x87, 0x83, Messagenumber, adr); -} - #endif /* __CAPIUTIL_H__ */ diff --git a/include/linux/kernelcapi.h b/include/linux/kernelcapi.h index 075fab5f92e1..94ba42bf9da1 100644 --- a/include/linux/kernelcapi.h +++ b/include/linux/kernelcapi.h @@ -10,46 +10,12 @@ #ifndef __KERNELCAPI_H__ #define __KERNELCAPI_H__ - #include #include #include #include #include -struct capi20_appl { - u16 applid; - capi_register_params rparam; - void (*recv_message)(struct capi20_appl *ap, struct sk_buff *skb); - void *private; - - /* internal to kernelcapi.o */ - unsigned long nrecvctlpkt; - unsigned long nrecvdatapkt; - unsigned long nsentctlpkt; - unsigned long nsentdatapkt; - struct mutex recv_mtx; - struct sk_buff_head recv_queue; - struct work_struct recv_work; - int release_in_progress; -}; - -u16 capi20_isinstalled(void); -u16 capi20_register(struct capi20_appl *ap); -u16 capi20_release(struct capi20_appl *ap); -u16 capi20_put_message(struct capi20_appl *ap, struct sk_buff *skb); -u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN]); -u16 capi20_get_version(u32 contr, struct capi_version *verp); -u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN]); -u16 capi20_get_profile(u32 contr, struct capi_profile *profp); -int capi20_manufacturer(unsigned long cmd, void __user *data); - -#define CAPICTR_UP 0 -#define CAPICTR_DOWN 1 - -int register_capictr_notifier(struct notifier_block *nb); -int unregister_capictr_notifier(struct notifier_block *nb); - #define CAPI_NOERROR 0x0000 #define CAPI_TOOMANYAPPLS 0x1001 @@ -76,45 +42,4 @@ int unregister_capictr_notifier(struct notifier_block *nb); #define CAPI_MSGCTRLERNOTSUPPORTEXTEQUIP 0x110a #define CAPI_MSGCTRLERONLYSUPPORTEXTEQUIP 0x110b -typedef enum { - CapiMessageNotSupportedInCurrentState = 0x2001, - CapiIllContrPlciNcci = 0x2002, - CapiNoPlciAvailable = 0x2003, - CapiNoNcciAvailable = 0x2004, - CapiNoListenResourcesAvailable = 0x2005, - CapiNoFaxResourcesAvailable = 0x2006, - CapiIllMessageParmCoding = 0x2007, -} RESOURCE_CODING_PROBLEM; - -typedef enum { - CapiB1ProtocolNotSupported = 0x3001, - CapiB2ProtocolNotSupported = 0x3002, - CapiB3ProtocolNotSupported = 0x3003, - CapiB1ProtocolParameterNotSupported = 0x3004, - CapiB2ProtocolParameterNotSupported = 0x3005, - CapiB3ProtocolParameterNotSupported = 0x3006, - CapiBProtocolCombinationNotSupported = 0x3007, - CapiNcpiNotSupported = 0x3008, - CapiCipValueUnknown = 0x3009, - CapiFlagsNotSupported = 0x300a, - CapiFacilityNotSupported = 0x300b, - CapiDataLengthNotSupportedByCurrentProtocol = 0x300c, - CapiResetProcedureNotSupportedByCurrentProtocol = 0x300d, - CapiTeiAssignmentFailed = 0x300e, -} REQUESTED_SERVICES_PROBLEM; - -typedef enum { - CapiSuccess = 0x0000, - CapiSupplementaryServiceNotSupported = 0x300e, - CapiRequestNotAllowedInThisState = 0x3010, -} SUPPLEMENTARY_SERVICE_INFO; - -typedef enum { - CapiProtocolErrorLayer1 = 0x3301, - CapiProtocolErrorLayer2 = 0x3302, - CapiProtocolErrorLayer3 = 0x3303, - CapiTimeOut = 0x3303, // SuppServiceReason - CapiCallGivenToOtherApplication = 0x3304, -} CAPI_REASON; - #endif /* __KERNELCAPI_H__ */ -- cgit v1.2.3 From bbefa1dd6a6d53537c11624752219e39959d04fb Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 26 Nov 2019 15:58:45 +0800 Subject: crypto: pcrypt - Avoid deadlock by using per-instance padata queues If the pcrypt template is used multiple times in an algorithm, then a deadlock occurs because all pcrypt instances share the same padata_instance, which completes requests in the order submitted. That is, the inner pcrypt request waits for the outer pcrypt request while the outer request is already waiting for the inner. This patch fixes this by allocating a set of queues for each pcrypt instance instead of using two global queues. In order to maintain the existing user-space interface, the pinst structure remains global so any sysfs modifications will apply to every pcrypt instance. Note that when an update occurs we have to allocate memory for every pcrypt instance. Should one of the allocations fail we will abort the update without rolling back changes already made. The new per-instance data structure is called padata_shell and is essentially a wrapper around parallel_data. Reproducer: #include #include #include int main() { struct sockaddr_alg addr = { .salg_type = "aead", .salg_name = "pcrypt(pcrypt(rfc4106-gcm-aesni))" }; int algfd, reqfd; char buf[32] = { 0 }; algfd = socket(AF_ALG, SOCK_SEQPACKET, 0); bind(algfd, (void *)&addr, sizeof(addr)); setsockopt(algfd, SOL_ALG, ALG_SET_KEY, buf, 20); reqfd = accept(algfd, 0, 0); write(reqfd, buf, 32); read(reqfd, buf, 16); } Reported-by: syzbot+56c7151cad94eec37c521f0e47d2eee53f9361c4@syzkaller.appspotmail.com Fixes: 5068c7a883d1 ("crypto: pcrypt - Add pcrypt crypto parallelization wrapper") Signed-off-by: Herbert Xu Tested-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/padata.h | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 23717eeaad23..cccab7a59787 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -9,6 +9,7 @@ #ifndef PADATA_H #define PADATA_H +#include #include #include #include @@ -98,7 +99,7 @@ struct padata_cpumask { * struct parallel_data - Internal control structure, covers everything * that depends on the cpumask in use. * - * @pinst: padata instance. + * @sh: padata_shell object. * @pqueue: percpu padata queues used for parallelization. * @squeue: percpu padata queues used for serialuzation. * @reorder_objects: Number of objects waiting in the reorder queues. @@ -111,7 +112,7 @@ struct padata_cpumask { * @lock: Reorder lock. */ struct parallel_data { - struct padata_instance *pinst; + struct padata_shell *ps; struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; atomic_t reorder_objects; @@ -124,14 +125,33 @@ struct parallel_data { spinlock_t lock ____cacheline_aligned; }; +/** + * struct padata_shell - Wrapper around struct parallel_data, its + * purpose is to allow the underlying control structure to be replaced + * on the fly using RCU. + * + * @pinst: padat instance. + * @pd: Actual parallel_data structure which may be substituted on the fly. + * @opd: Pointer to old pd to be freed by padata_replace. + * @list: List entry in padata_instance list. + */ +struct padata_shell { + struct padata_instance *pinst; + struct parallel_data __rcu *pd; + struct parallel_data *opd; + struct list_head list; +}; + /** * struct padata_instance - The overall control structure. * * @cpu_notifier: cpu hotplug notifier. * @parallel_wq: The workqueue used for parallel work. * @serial_wq: The workqueue used for serial work. - * @pd: The internal control structure. + * @pslist: List of padata_shell objects attached to this instance. * @cpumask: User supplied cpumasks for parallel and serial works. + * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask. + * @omask: Temporary storage used to compute the notification mask. * @cpumask_change_notifier: Notifiers chain for user-defined notify * callbacks that will be called when either @pcpu or @cbcpu * or both cpumasks change. @@ -143,8 +163,10 @@ struct padata_instance { struct hlist_node node; struct workqueue_struct *parallel_wq; struct workqueue_struct *serial_wq; - struct parallel_data *pd; + struct list_head pslist; struct padata_cpumask cpumask; + struct padata_cpumask rcpumask; + cpumask_var_t omask; struct blocking_notifier_head cpumask_change_notifier; struct kobject kobj; struct mutex lock; @@ -156,7 +178,9 @@ struct padata_instance { extern struct padata_instance *padata_alloc_possible(const char *name); extern void padata_free(struct padata_instance *pinst); -extern int padata_do_parallel(struct padata_instance *pinst, +extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); +extern void padata_free_shell(struct padata_shell *ps); +extern int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu); extern void padata_do_serial(struct padata_priv *padata); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, -- cgit v1.2.3 From c441a909c68618ff64aa70394d0b270b0665a229 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 2 Dec 2019 13:42:29 -0800 Subject: crypto: compress - remove crt_u.compress (struct compress_tfm) crt_u.compress (struct compress_tfm) is pointless because its two fields, ->cot_compress() and ->cot_decompress(), always point to crypto_compress() and crypto_decompress(). Remove this pointless indirection, and just make crypto_comp_compress() and crypto_comp_decompress() be direct calls to what used to be crypto_compress() and crypto_decompress(). Also remove the unused function crypto_comp_cast(). Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 43 ++++++------------------------------------- 1 file changed, 6 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 23365a9d062e..8f708564b98b 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -606,17 +606,7 @@ struct cipher_tfm { void (*cit_decrypt_one)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); }; -struct compress_tfm { - int (*cot_compress)(struct crypto_tfm *tfm, - const u8 *src, unsigned int slen, - u8 *dst, unsigned int *dlen); - int (*cot_decompress)(struct crypto_tfm *tfm, - const u8 *src, unsigned int slen, - u8 *dst, unsigned int *dlen); -}; - #define crt_cipher crt_u.cipher -#define crt_compress crt_u.compress struct crypto_tfm { @@ -624,7 +614,6 @@ struct crypto_tfm { union { struct cipher_tfm cipher; - struct compress_tfm compress; } crt_u; void (*exit)(struct crypto_tfm *tfm); @@ -928,13 +917,6 @@ static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) return (struct crypto_comp *)tfm; } -static inline struct crypto_comp *crypto_comp_cast(struct crypto_tfm *tfm) -{ - BUG_ON((crypto_tfm_alg_type(tfm) ^ CRYPTO_ALG_TYPE_COMPRESS) & - CRYPTO_ALG_TYPE_MASK); - return __crypto_comp_cast(tfm); -} - static inline struct crypto_comp *crypto_alloc_comp(const char *alg_name, u32 type, u32 mask) { @@ -969,26 +951,13 @@ static inline const char *crypto_comp_name(struct crypto_comp *tfm) return crypto_tfm_alg_name(crypto_comp_tfm(tfm)); } -static inline struct compress_tfm *crypto_comp_crt(struct crypto_comp *tfm) -{ - return &crypto_comp_tfm(tfm)->crt_compress; -} - -static inline int crypto_comp_compress(struct crypto_comp *tfm, - const u8 *src, unsigned int slen, - u8 *dst, unsigned int *dlen) -{ - return crypto_comp_crt(tfm)->cot_compress(crypto_comp_tfm(tfm), - src, slen, dst, dlen); -} +int crypto_comp_compress(struct crypto_comp *tfm, + const u8 *src, unsigned int slen, + u8 *dst, unsigned int *dlen); -static inline int crypto_comp_decompress(struct crypto_comp *tfm, - const u8 *src, unsigned int slen, - u8 *dst, unsigned int *dlen) -{ - return crypto_comp_crt(tfm)->cot_decompress(crypto_comp_tfm(tfm), - src, slen, dst, dlen); -} +int crypto_comp_decompress(struct crypto_comp *tfm, + const u8 *src, unsigned int slen, + u8 *dst, unsigned int *dlen); #endif /* _LINUX_CRYPTO_H */ -- cgit v1.2.3 From e8cfed5e4e2b5929371955f476a52a4c3398ead3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 2 Dec 2019 13:42:30 -0800 Subject: crypto: cipher - remove crt_u.cipher (struct cipher_tfm) Of the three fields in crt_u.cipher (struct cipher_tfm), ->cit_setkey() is pointless because it always points to setkey() in crypto/cipher.c. ->cit_decrypt_one() and ->cit_encrypt_one() are slightly less pointless, since if the algorithm doesn't have an alignmask, they are set directly to ->cia_encrypt() and ->cia_decrypt(). However, this "optimization" isn't worthwhile because: - The "cipher" algorithm type is the only algorithm still using crt_u, so it's bloating every struct crypto_tfm for every algorithm type. - If the algorithm has an alignmask, this "optimization" actually makes things slower, as it causes 2 indirect calls per block rather than 1. - It adds extra code complexity. - Some templates already call ->cia_encrypt()/->cia_decrypt() directly instead of going through ->cit_encrypt_one()/->cit_decrypt_one(). - The "cipher" algorithm type never gives optimal performance anyway. For that, a higher-level type such as skcipher needs to be used. Therefore, just remove the extra indirection, and make crypto_cipher_setkey(), crypto_cipher_encrypt_one(), and crypto_cipher_decrypt_one() be direct calls into crypto/cipher.c. Also remove the unused function crypto_cipher_cast(). Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 48 ++++++------------------------------------------ 1 file changed, 6 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 8f708564b98b..c23f1eed7970 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -599,23 +599,10 @@ int crypto_has_alg(const char *name, u32 type, u32 mask); * crypto_free_*(), as well as the various helpers below. */ -struct cipher_tfm { - int (*cit_setkey)(struct crypto_tfm *tfm, - const u8 *key, unsigned int keylen); - void (*cit_encrypt_one)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); - void (*cit_decrypt_one)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); -}; - -#define crt_cipher crt_u.cipher - struct crypto_tfm { u32 crt_flags; - union { - struct cipher_tfm cipher; - } crt_u; - void (*exit)(struct crypto_tfm *tfm); struct crypto_alg *__crt_alg; @@ -752,12 +739,6 @@ static inline struct crypto_cipher *__crypto_cipher_cast(struct crypto_tfm *tfm) return (struct crypto_cipher *)tfm; } -static inline struct crypto_cipher *crypto_cipher_cast(struct crypto_tfm *tfm) -{ - BUG_ON(crypto_tfm_alg_type(tfm) != CRYPTO_ALG_TYPE_CIPHER); - return __crypto_cipher_cast(tfm); -} - /** * crypto_alloc_cipher() - allocate single block cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the @@ -815,11 +796,6 @@ static inline int crypto_has_cipher(const char *alg_name, u32 type, u32 mask) return crypto_has_alg(alg_name, type, mask); } -static inline struct cipher_tfm *crypto_cipher_crt(struct crypto_cipher *tfm) -{ - return &crypto_cipher_tfm(tfm)->crt_cipher; -} - /** * crypto_cipher_blocksize() - obtain block size for cipher * @tfm: cipher handle @@ -873,12 +849,8 @@ static inline void crypto_cipher_clear_flags(struct crypto_cipher *tfm, * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ -static inline int crypto_cipher_setkey(struct crypto_cipher *tfm, - const u8 *key, unsigned int keylen) -{ - return crypto_cipher_crt(tfm)->cit_setkey(crypto_cipher_tfm(tfm), - key, keylen); -} +int crypto_cipher_setkey(struct crypto_cipher *tfm, + const u8 *key, unsigned int keylen); /** * crypto_cipher_encrypt_one() - encrypt one block of plaintext @@ -889,12 +861,8 @@ static inline int crypto_cipher_setkey(struct crypto_cipher *tfm, * Invoke the encryption operation of one block. The caller must ensure that * the plaintext and ciphertext buffers are at least one block in size. */ -static inline void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, - u8 *dst, const u8 *src) -{ - crypto_cipher_crt(tfm)->cit_encrypt_one(crypto_cipher_tfm(tfm), - dst, src); -} +void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, + u8 *dst, const u8 *src); /** * crypto_cipher_decrypt_one() - decrypt one block of ciphertext @@ -905,12 +873,8 @@ static inline void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, * Invoke the decryption operation of one block. The caller must ensure that * the plaintext and ciphertext buffers are at least one block in size. */ -static inline void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, - u8 *dst, const u8 *src) -{ - crypto_cipher_crt(tfm)->cit_decrypt_one(crypto_cipher_tfm(tfm), - dst, src); -} +void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, + u8 *dst, const u8 *src); static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) { -- cgit v1.2.3 From 894c9ef9780c5cf2f143415e867ee39a33ecb75d Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 3 Dec 2019 14:31:10 -0500 Subject: padata: validate cpumask without removed CPU during offline Configuring an instance's parallel mask without any online CPUs... echo 2 > /sys/kernel/pcrypt/pencrypt/parallel_cpumask echo 0 > /sys/devices/system/cpu/cpu1/online ...makes tcrypt mode=215 crash like this: divide error: 0000 [#1] SMP PTI CPU: 4 PID: 283 Comm: modprobe Not tainted 5.4.0-rc8-padata-doc-v2+ #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20191013_105130-anatol 04/01/2014 RIP: 0010:padata_do_parallel+0x114/0x300 Call Trace: pcrypt_aead_encrypt+0xc0/0xd0 [pcrypt] crypto_aead_encrypt+0x1f/0x30 do_mult_aead_op+0x4e/0xdf [tcrypt] test_mb_aead_speed.constprop.0.cold+0x226/0x564 [tcrypt] do_test+0x28c2/0x4d49 [tcrypt] tcrypt_mod_init+0x55/0x1000 [tcrypt] ... cpumask_weight() in padata_cpu_hash() returns 0 because the mask has no CPUs. The problem is __padata_remove_cpu() checks for valid masks too early and so doesn't mark the instance PADATA_INVALID as expected, which would have made padata_do_parallel() return error before doing the division. Fix by introducing a second padata CPU hotplug state before CPUHP_BRINGUP_CPU so that __padata_remove_cpu() sees the online mask without @cpu. No need for the second argument to padata_replace() since @cpu is now already missing from the online mask. Fixes: 33e54450683c ("padata: Handle empty padata cpumasks") Signed-off-by: Daniel Jordan Cc: Eric Biggers Cc: Herbert Xu Cc: Sebastian Andrzej Siewior Cc: Steffen Klassert Cc: Thomas Gleixner Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index e51ee772b9f5..def48a583670 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -59,6 +59,7 @@ enum cpuhp_state { CPUHP_IOMMU_INTEL_DEAD, CPUHP_LUSTRE_CFS_DEAD, CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, + CPUHP_PADATA_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit v1.2.3 From 91a71d612128f84f725022d7b7c5d5a741f6fdc7 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 3 Dec 2019 14:31:12 -0500 Subject: padata: remove cpumask change notifier Since commit 63d3578892dc ("crypto: pcrypt - remove padata cpumask notifier") this feature is unused, so get rid of it. Signed-off-by: Daniel Jordan Cc: Eric Biggers Cc: Herbert Xu Cc: Jonathan Corbet Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index cccab7a59787..178d5cc6b494 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -13,7 +13,6 @@ #include #include #include -#include #include #define PADATA_CPU_SERIAL 0x01 @@ -151,10 +150,6 @@ struct padata_shell { * @pslist: List of padata_shell objects attached to this instance. * @cpumask: User supplied cpumasks for parallel and serial works. * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask. - * @omask: Temporary storage used to compute the notification mask. - * @cpumask_change_notifier: Notifiers chain for user-defined notify - * callbacks that will be called when either @pcpu or @cbcpu - * or both cpumasks change. * @kobj: padata instance kernel object. * @lock: padata instance lock. * @flags: padata flags. @@ -166,8 +161,6 @@ struct padata_instance { struct list_head pslist; struct padata_cpumask cpumask; struct padata_cpumask rcpumask; - cpumask_var_t omask; - struct blocking_notifier_head cpumask_change_notifier; struct kobject kobj; struct mutex lock; u8 flags; @@ -187,8 +180,4 @@ extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); extern int padata_start(struct padata_instance *pinst); extern void padata_stop(struct padata_instance *pinst); -extern int padata_register_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock); -extern int padata_unregister_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock); #endif -- cgit v1.2.3 From 3facced7aeed131c1002b724e488d68ebe59c56f Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 3 Dec 2019 14:31:13 -0500 Subject: padata: remove reorder_objects reorder_objects is unused since the rework of padata's flushing, so remove it. Signed-off-by: Daniel Jordan Cc: Eric Biggers Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 178d5cc6b494..faa2e36832f8 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -101,7 +101,6 @@ struct padata_cpumask { * @sh: padata_shell object. * @pqueue: percpu padata queues used for parallelization. * @squeue: percpu padata queues used for serialuzation. - * @reorder_objects: Number of objects waiting in the reorder queues. * @refcnt: Number of objects holding a reference on this parallel_data. * @max_seq_nr: Maximal used sequence number. * @processed: Number of already processed objects. @@ -114,7 +113,6 @@ struct parallel_data { struct padata_shell *ps; struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; - atomic_t reorder_objects; atomic_t refcnt; atomic_t seq_nr; unsigned int processed; -- cgit v1.2.3 From bfcdcef8c8e3469f4d6c082a1da27a6ef77e5715 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 3 Dec 2019 14:31:14 -0500 Subject: padata: update documentation Remove references to unused functions, standardize language, update to reflect new functionality, migrate to rst format, and fix all kernel-doc warnings. Fixes: 815613da6a67 ("kernel/padata.c: removed unused code") Signed-off-by: Daniel Jordan Cc: Eric Biggers Cc: Herbert Xu Cc: Jonathan Corbet Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Jordan Signed-off-by: Herbert Xu --- include/linux/padata.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index faa2e36832f8..a0d8b41850b2 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -19,7 +19,7 @@ #define PADATA_CPU_PARALLEL 0x02 /** - * struct padata_priv - Embedded to the users data structure. + * struct padata_priv - Represents one job * * @list: List entry, to attach to the padata lists. * @pd: Pointer to the internal control structure. @@ -42,7 +42,7 @@ struct padata_priv { }; /** - * struct padata_list + * struct padata_list - one per work type per CPU * * @list: List head. * @lock: List lock. @@ -70,9 +70,6 @@ struct padata_serial_queue { * * @parallel: List to wait for parallelization. * @reorder: List to wait for reordering after parallel processing. - * @serial: List to wait for serialization after reordering. - * @pwork: work struct for parallelization. - * @swork: work struct for serialization. * @work: work struct for parallelization. * @num_obj: Number of objects that are processed by this cpu. */ @@ -98,11 +95,11 @@ struct padata_cpumask { * struct parallel_data - Internal control structure, covers everything * that depends on the cpumask in use. * - * @sh: padata_shell object. + * @ps: padata_shell object. * @pqueue: percpu padata queues used for parallelization. * @squeue: percpu padata queues used for serialuzation. * @refcnt: Number of objects holding a reference on this parallel_data. - * @max_seq_nr: Maximal used sequence number. + * @seq_nr: Sequence number of the parallelized data object. * @processed: Number of already processed objects. * @cpu: Next CPU to be processed. * @cpumask: The cpumasks in use for parallel and serial workers. @@ -119,7 +116,7 @@ struct parallel_data { int cpu; struct padata_cpumask cpumask; struct work_struct reorder_work; - spinlock_t lock ____cacheline_aligned; + spinlock_t ____cacheline_aligned lock; }; /** @@ -142,7 +139,7 @@ struct padata_shell { /** * struct padata_instance - The overall control structure. * - * @cpu_notifier: cpu hotplug notifier. + * @node: Used by CPU hotplug. * @parallel_wq: The workqueue used for parallel work. * @serial_wq: The workqueue used for serial work. * @pslist: List of padata_shell objects attached to this instance. -- cgit v1.2.3 From 653997eeecef95c3ead4fba1b2d27e6a5854d6cd Mon Sep 17 00:00:00 2001 From: Ran Bi Date: Wed, 11 Dec 2019 17:43:54 +0800 Subject: rtc: mt6397: fix alarm register overwrite Alarm registers high byte was reserved for other functions. This add mask in alarm registers operation functions. This also fix error condition in interrupt handler. Fixes: fc2979118f3f ("rtc: mediatek: Add MT6397 RTC driver") Signed-off-by: Ran Bi Signed-off-by: Hsin-Hsiung Wang Link: https://lore.kernel.org/r/1576057435-3561-6-git-send-email-hsin-hsiung.wang@mediatek.com Signed-off-by: Alexandre Belloni --- include/linux/mfd/mt6397/rtc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index f84b9163c0ee..7dfb63b81373 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -46,6 +46,14 @@ #define RTC_AL_SEC 0x0018 +#define RTC_AL_SEC_MASK 0x003f +#define RTC_AL_MIN_MASK 0x003f +#define RTC_AL_HOU_MASK 0x001f +#define RTC_AL_DOM_MASK 0x001f +#define RTC_AL_DOW_MASK 0x0007 +#define RTC_AL_MTH_MASK 0x000f +#define RTC_AL_YEA_MASK 0x007f + #define RTC_PDN2 0x002e #define RTC_PDN2_PWRON_ALARM BIT(4) -- cgit v1.2.3 From a4516c7053b96fed98a0439a9226983b5275474b Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 11 Dec 2019 10:55:59 +0000 Subject: net: sfp: derive interface mode from ethtool link modes We don't need the EEPROM ID to derive the phy interface mode as we can derive it merely from the ethtool link modes. Remove the EEPROM ID argument to sfp_select_interface(). Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/sfp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 487fd9412d10..8d7b98c214d7 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -504,7 +504,6 @@ int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support); phy_interface_t sfp_select_interface(struct sfp_bus *bus, - const struct sfp_eeprom_id *id, unsigned long *link_modes); int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); @@ -532,7 +531,6 @@ static inline void sfp_parse_support(struct sfp_bus *bus, } static inline phy_interface_t sfp_select_interface(struct sfp_bus *bus, - const struct sfp_eeprom_id *id, unsigned long *link_modes) { return PHY_INTERFACE_MODE_NA; -- cgit v1.2.3 From 0fbd26a9fb6875b98fcfff523831fec47bc5e9a2 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 11 Dec 2019 10:56:04 +0000 Subject: net: sfp: add more extended compliance codes SFF-8024 is used to define various constants re-used in several SFF SFP-related specifications. Split these constants from the enum, and rename them to indicate that they're defined by SFF-8024. Add and use updated SFF-8024 extended compliance code definitions for 10GBASE-T, 5GBASE-T and 2.5GBASE-T modules. Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/sfp.h | 82 +++++++++++++++++++++++++++++++++++------------------ 1 file changed, 55 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 8d7b98c214d7..373d8b67ea86 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -275,6 +275,61 @@ struct sfp_diag { __be16 cal_v_offset; } __packed; +/* SFF8024 defined constants */ +enum { + SFF8024_ID_UNK = 0x00, + SFF8024_ID_SFF_8472 = 0x02, + SFF8024_ID_SFP = 0x03, + SFF8024_ID_DWDM_SFP = 0x0b, + SFF8024_ID_QSFP_8438 = 0x0c, + SFF8024_ID_QSFP_8436_8636 = 0x0d, + SFF8024_ID_QSFP28_8636 = 0x11, + + SFF8024_ENCODING_UNSPEC = 0x00, + SFF8024_ENCODING_8B10B = 0x01, + SFF8024_ENCODING_4B5B = 0x02, + SFF8024_ENCODING_NRZ = 0x03, + SFF8024_ENCODING_8472_MANCHESTER= 0x04, + SFF8024_ENCODING_8472_SONET = 0x05, + SFF8024_ENCODING_8472_64B66B = 0x06, + SFF8024_ENCODING_8436_MANCHESTER= 0x06, + SFF8024_ENCODING_8436_SONET = 0x04, + SFF8024_ENCODING_8436_64B66B = 0x05, + SFF8024_ENCODING_256B257B = 0x07, + SFF8024_ENCODING_PAM4 = 0x08, + + SFF8024_CONNECTOR_UNSPEC = 0x00, + /* codes 01-05 not supportable on SFP, but some modules have single SC */ + SFF8024_CONNECTOR_SC = 0x01, + SFF8024_CONNECTOR_FIBERJACK = 0x06, + SFF8024_CONNECTOR_LC = 0x07, + SFF8024_CONNECTOR_MT_RJ = 0x08, + SFF8024_CONNECTOR_MU = 0x09, + SFF8024_CONNECTOR_SG = 0x0a, + SFF8024_CONNECTOR_OPTICAL_PIGTAIL= 0x0b, + SFF8024_CONNECTOR_MPO_1X12 = 0x0c, + SFF8024_CONNECTOR_MPO_2X16 = 0x0d, + SFF8024_CONNECTOR_HSSDC_II = 0x20, + SFF8024_CONNECTOR_COPPER_PIGTAIL= 0x21, + SFF8024_CONNECTOR_RJ45 = 0x22, + SFF8024_CONNECTOR_NOSEPARATE = 0x23, + SFF8024_CONNECTOR_MXC_2X16 = 0x24, + + SFF8024_ECC_UNSPEC = 0x00, + SFF8024_ECC_100G_25GAUI_C2M_AOC = 0x01, + SFF8024_ECC_100GBASE_SR4_25GBASE_SR = 0x02, + SFF8024_ECC_100GBASE_LR4_25GBASE_LR = 0x03, + SFF8024_ECC_100GBASE_ER4_25GBASE_ER = 0x04, + SFF8024_ECC_100GBASE_SR10 = 0x05, + SFF8024_ECC_100GBASE_CR4 = 0x0b, + SFF8024_ECC_25GBASE_CR_S = 0x0c, + SFF8024_ECC_25GBASE_CR_N = 0x0d, + SFF8024_ECC_10GBASE_T_SFI = 0x16, + SFF8024_ECC_10GBASE_T_SR = 0x1c, + SFF8024_ECC_5GBASE_T = 0x1d, + SFF8024_ECC_2_5GBASE_T = 0x1e, +}; + /* SFP EEPROM registers */ enum { SFP_PHYS_ID = 0x00, @@ -309,34 +364,7 @@ enum { SFP_SFF8472_COMPLIANCE = 0x5e, SFP_CC_EXT = 0x5f, - SFP_PHYS_ID_SFF = 0x02, - SFP_PHYS_ID_SFP = 0x03, SFP_PHYS_EXT_ID_SFP = 0x04, - SFP_CONNECTOR_UNSPEC = 0x00, - /* codes 01-05 not supportable on SFP, but some modules have single SC */ - SFP_CONNECTOR_SC = 0x01, - SFP_CONNECTOR_FIBERJACK = 0x06, - SFP_CONNECTOR_LC = 0x07, - SFP_CONNECTOR_MT_RJ = 0x08, - SFP_CONNECTOR_MU = 0x09, - SFP_CONNECTOR_SG = 0x0a, - SFP_CONNECTOR_OPTICAL_PIGTAIL = 0x0b, - SFP_CONNECTOR_MPO_1X12 = 0x0c, - SFP_CONNECTOR_MPO_2X16 = 0x0d, - SFP_CONNECTOR_HSSDC_II = 0x20, - SFP_CONNECTOR_COPPER_PIGTAIL = 0x21, - SFP_CONNECTOR_RJ45 = 0x22, - SFP_CONNECTOR_NOSEPARATE = 0x23, - SFP_CONNECTOR_MXC_2X16 = 0x24, - SFP_ENCODING_UNSPEC = 0x00, - SFP_ENCODING_8B10B = 0x01, - SFP_ENCODING_4B5B = 0x02, - SFP_ENCODING_NRZ = 0x03, - SFP_ENCODING_8472_MANCHESTER = 0x04, - SFP_ENCODING_8472_SONET = 0x05, - SFP_ENCODING_8472_64B66B = 0x06, - SFP_ENCODING_256B257B = 0x07, - SFP_ENCODING_PAM4 = 0x08, SFP_OPTIONS_HIGH_POWER_LEVEL = BIT(13), SFP_OPTIONS_PAGING_A2 = BIT(12), SFP_OPTIONS_RETIMER = BIT(11), -- cgit v1.2.3 From 74c551ca5a0edcc9cf66a3b73fd95b9a8615bfd0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 11 Dec 2019 10:56:09 +0000 Subject: net: sfp: add module start/stop upstream notifications When dealing with some copper modules, we can't positively know the module capabilities are until we have probed the PHY. Without the full capabilities, we may end up failing a module that we could otherwise drive with a restricted set of capabilities. An example of this would be a module with a NBASE-T PHY plugged into a host that supports phy interface modes 2500BASE-X and SGMII. The PHY supports 10GBASE-R, 5000BASE-X, 2500BASE-X, SGMII interface modes, which means a subset of the capabilities are compatible with the host. However, reading the module EEPROM leads us to believe that the module only supports ethtool link mode 10GBASE-T, which is incompatible with the host - and thus results in the module being rejected. This patch adds an extra notification which are triggered after the SFP module's PHY probe, and a corresponding notification just before the PHY is removed. Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/sfp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 373d8b67ea86..66a56396e8e3 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -507,6 +507,8 @@ struct sfp_bus; * @module_insert: called after a module has been detected to determine * whether the module is supported for the upstream device. * @module_remove: called after the module has been removed. + * @module_start: called after the PHY probe step + * @module_stop: called before the PHY is removed * @link_down: called when the link is non-operational for whatever * reason. * @link_up: called when the link is operational. @@ -520,6 +522,8 @@ struct sfp_upstream_ops { void (*detach)(void *priv, struct sfp_bus *bus); int (*module_insert)(void *priv, const struct sfp_eeprom_id *id); void (*module_remove)(void *priv); + int (*module_start)(void *priv); + void (*module_stop)(void *priv); void (*link_down)(void *priv); void (*link_up)(void *priv); int (*connect_phy)(void *priv, struct phy_device *); -- cgit v1.2.3 From 52c956003a9d5bcae1f445f9dfd42b624adb6e87 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 11 Dec 2019 10:56:45 +0000 Subject: net: phylink: delay MAC configuration for copper SFP modules Knowing whether we need to delay the MAC configuration because a module may have a PHY is useful to phylink to allow NBASE-T modules to work on systems supporting no more than 2.5G speeds. This commit allows us to delay such configuration until after the PHY has been probed by recording the parsed capabilities, and if the module may have a PHY, doing no more until the module_start() notification is called. At that point, we either have a PHY, or we don't. We move the PHY-based setup a little later, and use the PHYs support capabilities rather than the EEPROM parsed capabilities to determine whether we can support the PHY. Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/sfp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 66a56396e8e3..38893e4dd0f0 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -533,6 +533,7 @@ struct sfp_upstream_ops { #if IS_ENABLED(CONFIG_SFP) int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support); +bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support); phy_interface_t sfp_select_interface(struct sfp_bus *bus, @@ -556,6 +557,12 @@ static inline int sfp_parse_port(struct sfp_bus *bus, return PORT_OTHER; } +static inline bool sfp_may_have_phy(struct sfp_bus *bus, + const struct sfp_eeprom_id *id) +{ + return false; +} + static inline void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support) -- cgit v1.2.3 From 528be501b7d4a64e04672a38ebfc9e19c555e770 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 11 Dec 2019 19:44:57 -0600 Subject: soundwire: sdw_slave: add probe_complete structure and new fields When a Slave device becomes synchronized with the bus, it may report its presence in PING frames, as well as optionally asserting an in-band PREQ signal. The bus driver will detect a new Device0, start the enumeration process and assign it a non-zero device number. The SoundWire enumeration provides an arbitration to deal with multiple Slaves reporting ATTACHED at the same time. The bus driver will also invoke the driver .probe() callback associated with this device. The probe() depends on the Linux device core, which handles the match operations and may result in modules being loaded. Once the non-zero device number is programmed, the Slave will report its new status in PING frames and the Master hardware will typically report this status change with an interrupt. At this point, the .update_status() callback of the codec driver will be invoked (usually from an interrupt thread or workqueue scheduled from the interrupt thread). The first race condition which can happen is between the .probe(), which allocates the resources, and .update_status() where initializations are typically handled. The .probe() is only called once during the initial boot, while .update_status() will be called for every bus hardware reset and if the Slave device loses synchronization (an unlikely event but with non-zero probability). The time difference between the end of the enumeration process and a change of status reported by the hardware may be as small as one SoundWire PING frame. The scheduling of the interrupt thread, which invokes .update_status() is not deterministic, but can be small enough to create a race condition. With a 48 kHz frame rate and ideal scheduling cases, the .probe() may be pre-empted within double-digit microseconds. Since there is no guarantee that the .probe() completes by the time .update_status() is invoked as a result of an interrupt, it's not unusual for the .update_status() to rely on data structures that have not been allocated yet, leading to kernel oopses. This patch adds a probe_complete utility, which is used in the sdw_update_slave_status() routine. The codec driver does not need to do anything and can safely assume all resources are allocated in its update_status() callback. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 28745b9ba279..cb1db4a7475d 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -547,6 +547,10 @@ struct sdw_slave_ops { * @node: node for bus list * @port_ready: Port ready completion flag for each Slave port * @dev_num: Device Number assigned by Bus + * @probed: boolean tracking driver state + * @probe_complete: completion utility to control potential races + * on startup between driver probe/initialization and SoundWire + * Slave state changes/implementation-defined interrupts */ struct sdw_slave { struct sdw_slave_id id; @@ -561,6 +565,8 @@ struct sdw_slave { struct list_head node; struct completion *port_ready; u16 dev_num; + bool probed; + struct completion probe_complete; }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) -- cgit v1.2.3 From fbbff36325079fd9d2fcd30063c84f4b38a0ad9b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 11 Dec 2019 19:44:58 -0600 Subject: soundwire: sdw_slave: add enumeration_complete structure When the Master starts the bus (be it during the initial boot or system resume), it usually performs a HardReset to make sure electrical levels are correct, then enables the control channel. While the PM framework guarantees that the Slave devices will only become 'active' once the Master completes the bus initialization, there is still a risk of a race condition: the Slave enumeration is handled in a separate interrupt thread triggered by hardware status changes, so the Slave device may not be ready to accept commands when the Slave driver tries to access the registers and restore settings in its resume or pm_runtime_resume callbacks. In those cases, any read/write commands from/to the Slave device will result in a timeout. This patch adds an enumeration_complete structure. When the bus is goes through a HardReset sequence and restarted, the Slave will be marked as UNATTACHED, which will result in a call to init_completion(). When the Slave reports its presence during PING frames as a non-zero Device, the Master hardware will issue an interrupt and the bus driver will invoke complete(). The order between init_completion()/complete() is predictable since this is a Master-initiated transition. The Slave driver may use wait_for_completion() in its resume callback. When regmap is used, the Slave driver will typically set its regmap in cache-only mode on suspend, then on resume block on wait_for_completion(&enumeration_complete) to guarantee it is safe to start read/write transactions. It may then exit the cache-only mode and use a regmap_sync to restore settings. All these steps are optional, their use completely depends on the Slave device capabilities and how the Slave driver is implemented. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-3-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index cb1db4a7475d..3fa8d875b16b 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -551,6 +551,9 @@ struct sdw_slave_ops { * @probe_complete: completion utility to control potential races * on startup between driver probe/initialization and SoundWire * Slave state changes/implementation-defined interrupts + * @enumeration_complete: completion utility to control potential races + * on startup between device enumeration and read/write access to the + * Slave device */ struct sdw_slave { struct sdw_slave_id id; @@ -567,6 +570,7 @@ struct sdw_slave { u16 dev_num; bool probed; struct completion probe_complete; + struct completion enumeration_complete; }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) -- cgit v1.2.3 From 7afc50e441af0afc8055920a64cff70b648e4b44 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 11 Dec 2019 19:44:59 -0600 Subject: soundwire: sdw_slave: add initialization_complete definition Slave drivers may have different ways of handling their settings, with or without regmap. During the integration of codec drivers, done in partnership between Intel and Realtek, it became desirable to implement a predictable order between low-level initializations performed in .update_status() (invoked by an interrupt thread) and the settings restored in the resume steps (invoked by the PM core). This patch builds on the previous solution to wait for the Slave device to be fully enumerated. The complete() in this case is signaled not before the .update_status() is called, but after .update_status() returns. Without this patch, the settings were not properly restored, leading to timing-dependent 'no sound after resume' or 'no headset detected after resume' bug reports. Depending on how initialization is handled, a Slave device driver may wait for enumeration_complete, or for initialization_complete, both are valid synchronization points. They are initialized at the same time, they only differ on when complete() is invoked. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-4-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 3fa8d875b16b..ed42cd79eab7 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -554,6 +554,8 @@ struct sdw_slave_ops { * @enumeration_complete: completion utility to control potential races * on startup between device enumeration and read/write access to the * Slave device + * @initialization_complete: completion utility to control potential races + * on startup between device enumeration and settings being restored */ struct sdw_slave { struct sdw_slave_id id; @@ -571,6 +573,7 @@ struct sdw_slave { bool probed; struct completion probe_complete; struct completion enumeration_complete; + struct completion initialization_complete; }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) -- cgit v1.2.3 From b2bd75f806c49929d7ab5a860c0a69b0a17c59d2 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 11 Dec 2019 19:45:00 -0600 Subject: soundwire: sdw_slave: track unattach_request to handle all init sequences The Slave device initialization can be split in 4 different cases: 1. Master-initiated hardware reset, system suspend-resume and pm_runtime based on clock-stop mode1. To avoid timeouts and a bad audio experience, the Slave device resume operations need to wait for the Slave device to be re-enumerated and its settings restored. 2. Exit from clock-stop mode0. In this case, the Slave device is required to remain enumerated and its context preserved while the clock is stopped, so no re-initialization or wait_for_completion() is necessary. 3. Slave-initiated pm_runtime D3 transition. With the parent child relationship, it is possible that a Slave device becomes 'suspended' while its parent is still 'active' with the bus clock still toggling. In this case, during the pm_runtime resume operation, there is no need to wait for any settings to be restored. 4. Slave reset (sync loss or implementation-defined). In that case the bus remains operational and the Slave device will be re-initialized when it becomes ATTACHED again. In previous patches, we suggested the use of wait_for_completion() to deal with the case #1, but case #2 and #3 do not need any wait. To account for those differences, this patch adds an unattach_request field. The field is explicitly set by the Master for the case #1, and if non-zero the Slave device shall wait on resume. In all other cases, the Slave resume operations can proceed without wait. The only request tracked so far is Master HardReset, but the request is declared as a bit mask for future extensions (if needed). The definition for this value is added in bus.h and does not need to be exposed in sdw.h Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-5-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index ed42cd79eab7..b7c9eca4332a 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -556,6 +556,11 @@ struct sdw_slave_ops { * Slave device * @initialization_complete: completion utility to control potential races * on startup between device enumeration and settings being restored + * @unattach_request: mask field to keep track why the Slave re-attached and + * was re-initialized. This is useful to deal with potential race conditions + * 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 */ struct sdw_slave { struct sdw_slave_id id; @@ -574,6 +579,7 @@ struct sdw_slave { struct completion probe_complete; struct completion enumeration_complete; struct completion initialization_complete; + u32 unattach_request; }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) -- cgit v1.2.3 From f98f690fb03c2a8d21dfa31aa1042480cf6f7f9b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 11 Dec 2019 19:45:01 -0600 Subject: soundwire: intel: update interfaces between ASoC and SoundWire The current interfaces between ASoC and SoundWire are limited by the platform_device infrastructure to an init() and exit() (mapped to the platform driver.probe and .remove) To help with the platform detection, machine driver selection and management of power dependencies between DSP and SoundWire IP, the ASoC side requires: a) an ACPI scan helper, to report if any devices are exposed in the DSDT tables, and if any links are disabled by the BIOS. b) a probe helper that allocates the resources without actually starting the bus. c) a startup helper which does start the bus when all power dependencies are settled. d) an exit helper to free all resources e) an interrupt_enable/disable helper, typically invoked after the startup helper but also used in suspend routines. This patch moves all required interfaces to sdw_intel.h, mainly to allow SoundWire and ASoC parts to be merged separately once the header files are shared between trees. To avoid compilation issues, the conflicts in intel_init.c are blindly removed. This would in theory prevent the code from working, but since there are no users of the Intel Soundwire driver this has no impact. Functionality will be restored when the removal of platform devices is complete. Support for SoundWire + SOF builds will only be provided once all the required pieces are upstream. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-6-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 77 ++++++++++++++++++++++++++++++++++--- 1 file changed, 72 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index c9427cb6020b..034eca8df748 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -16,24 +16,91 @@ struct sdw_intel_ops { }; /** - * struct sdw_intel_res - Soundwire Intel resource structure + * struct sdw_intel_acpi_info - Soundwire Intel information found in ACPI tables + * @handle: ACPI controller handle + * @count: link count found with "sdw-master-count" property + * @link_mask: bit-wise mask listing links enabled by BIOS menu + * + * this structure could be expanded to e.g. provide all the _ADR + * information in case the link_mask is not sufficient to identify + * platform capabilities. + */ +struct sdw_intel_acpi_info { + acpi_handle handle; + int count; + u32 link_mask; +}; + +struct sdw_intel_link_res; + +/** + * struct sdw_intel_ctx - context allocated by the controller + * driver probe + * @count: link count + * @mmio_base: mmio base of SoundWire registers, only used to check + * hardware capabilities after all power dependencies are settled. + * @link_mask: bit-wise mask listing SoundWire links reported by the + * Controller + * @handle: ACPI parent handle + * @links: information for each link (controller-specific and kept + * opaque here) + */ +struct sdw_intel_ctx { + int count; + void __iomem *mmio_base; + u32 link_mask; + acpi_handle handle; + struct sdw_intel_link_res *links; +}; + +/** + * struct sdw_intel_res - Soundwire Intel global resource structure, + * typically populated by the DSP driver + * + * @count: link count * @mmio_base: mmio base of SoundWire registers * @irq: interrupt number * @handle: ACPI parent handle * @parent: parent device * @ops: callback ops - * @arg: callback arg + * @dev: device implementing hwparams and free callbacks + * @link_mask: bit-wise mask listing links selected by the DSP driver + * This mask may be a subset of the one reported by the controller since + * machine-specific quirks are handled in the DSP driver. */ struct sdw_intel_res { + int count; void __iomem *mmio_base; int irq; acpi_handle handle; struct device *parent; const struct sdw_intel_ops *ops; - void *arg; + struct device *dev; + u32 link_mask; }; -void *sdw_intel_init(acpi_handle *parent_handle, struct sdw_intel_res *res); -void sdw_intel_exit(void *arg); +/* + * On Intel platforms, the SoundWire IP has dependencies on power + * rails shared with the DSP, and the initialization steps are split + * in three. First an ACPI scan to check what the firmware describes + * in DSDT tables, then an allocation step (with no hardware + * configuration but with all the relevant devices created) and last + * the actual hardware configuration. The final stage is a global + * interrupt enable which is controlled by the DSP driver. Splitting + * these phases helps simplify the boot flow and make early decisions + * on e.g. which machine driver to select (I2S mode, HDaudio or + * SoundWire). + */ +int sdw_intel_acpi_scan(acpi_handle *parent_handle, + struct sdw_intel_acpi_info *info); + +struct sdw_intel_ctx * +sdw_intel_probe(struct sdw_intel_res *res); + +int sdw_intel_startup(struct sdw_intel_ctx *ctx); + +void sdw_intel_exit(struct sdw_intel_ctx *ctx); + +void sdw_intel_enable_irq(void __iomem *mmio_base, bool enable); #endif -- cgit v1.2.3 From 4b206d34b92224496c42226c4b6d92719056c8b6 Mon Sep 17 00:00:00 2001 From: Rander Wang Date: Wed, 11 Dec 2019 19:45:02 -0600 Subject: soundwire: intel: update stream callbacks for hwparams/free stream operations The SoundWire DAIs for Intel platform are created in drivers/soundwire/intel.c, while the communication with the Intel DSP is all controlled in soc/sof/intel When the DAI status changes, a callback is used to bridge the gap between the two subsystems. The naming of the existing 'config_stream' callback does not map well with any of ALSA/ASoC concepts. This patch renames it as 'params_stream' to be more self-explanatory. A new 'free_stream' callback is added in case any resources allocated in the 'params_stream' stage need to be released. In the SOF implementation, this is used in the hw_free case to release the DMA channels over IPC. These two callbacks now rely on structures which expose the link_id and alh_stream_id (required by the firmware IPC), instead of a list of parameters. The 'void *' definitions are changed to use explicit types, as suggested on alsa-devel during earlier reviews. Signed-off-by: Rander Wang Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-7-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 034eca8df748..3ccb38d48eef 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -4,15 +4,39 @@ #ifndef __SDW_INTEL_H #define __SDW_INTEL_H +/** + * struct sdw_intel_stream_params_data: configuration passed during + * the @params_stream callback, e.g. for interaction with DSP + * firmware. + */ +struct sdw_intel_stream_params_data { + struct snd_pcm_substream *substream; + struct snd_soc_dai *dai; + struct snd_pcm_hw_params *hw_params; + int link_id; + int alh_stream_id; +}; + +/** + * struct sdw_intel_stream_free_data: configuration passed during + * the @free_stream callback, e.g. for interaction with DSP + * firmware. + */ +struct sdw_intel_stream_free_data { + struct snd_pcm_substream *substream; + struct snd_soc_dai *dai; + int link_id; +}; + /** * struct sdw_intel_ops: Intel audio driver callback ops * - * @config_stream: configure the stream with the hw_params - * the first argument containing the context is mandatory */ struct sdw_intel_ops { - int (*config_stream)(void *arg, void *substream, - void *dai, void *hw_params, int stream_num); + int (*params_stream)(struct device *dev, + struct sdw_intel_stream_params_data *params_data); + int (*free_stream)(struct device *dev, + struct sdw_intel_stream_free_data *free_data); }; /** -- cgit v1.2.3 From 6cd1d670bee641d5d10b11d58c7c99ac1ddf8068 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Wed, 11 Dec 2019 19:45:03 -0600 Subject: soundwire: intel: update headers for interrupts The existing use of 6 handlers is problematic in MSI mode. Update headers so that all shared interrupts can be handled with a single handler. Signed-off-by: Bard Liao Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-8-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 3ccb38d48eef..2ce3e9ecc4b6 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -4,6 +4,8 @@ #ifndef __SDW_INTEL_H #define __SDW_INTEL_H +#include + /** * struct sdw_intel_stream_params_data: configuration passed during * the @params_stream callback, e.g. for interaction with DSP @@ -127,4 +129,6 @@ void sdw_intel_exit(struct sdw_intel_ctx *ctx); void sdw_intel_enable_irq(void __iomem *mmio_base, bool enable); +irqreturn_t sdw_intel_thread(int irq, void *dev_id); + #endif -- cgit v1.2.3 From eae0b60d64834c75a460d96b1d1e0e187381e341 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Wed, 11 Dec 2019 19:45:04 -0600 Subject: soundwire: intel: add link_list to handle interrupts with a single thread In MSI mode, the use of separate handlers and threads for the Intel IPC, stream and SoundWire shared interrupt leads to timeouts and lost interrupts. The solution is to merge all interrupt handling across all links with a single thread function. The use of a linked list enables this thread function to walk through all contexts and figure out which link needs attention. Signed-off-by: Bard Liao Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-9-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 2ce3e9ecc4b6..2a56180bc9dc 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -70,6 +70,7 @@ struct sdw_intel_link_res; * @handle: ACPI parent handle * @links: information for each link (controller-specific and kept * opaque here) + * @link_list: list to handle interrupts across all links */ struct sdw_intel_ctx { int count; @@ -77,6 +78,7 @@ struct sdw_intel_ctx { u32 link_mask; acpi_handle handle; struct sdw_intel_link_res *links; + struct list_head link_list; }; /** -- cgit v1.2.3 From 905b5a81afe15e8252e5892b8ca1ff1c1adfb79d Mon Sep 17 00:00:00 2001 From: Rander Wang Date: Wed, 11 Dec 2019 19:45:05 -0600 Subject: soundwire: intel: add prototype for WAKEEN interrupt processing In ClockStop mode, the PCI device will be notified of a wake, which will be handled from an interrupt thread. Signed-off-by: Rander Wang Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-10-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 2a56180bc9dc..073121c49695 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -122,6 +122,8 @@ struct sdw_intel_res { int sdw_intel_acpi_scan(acpi_handle *parent_handle, struct sdw_intel_acpi_info *info); +void sdw_intel_process_wakeen_event(struct sdw_intel_ctx *ctx); + struct sdw_intel_ctx * sdw_intel_probe(struct sdw_intel_res *res); -- cgit v1.2.3 From 4da0680f24c9af2de8406ded68c4ef967f448de3 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 11 Dec 2019 19:45:06 -0600 Subject: soundwire: intel: add mutex for shared SHIM register access Some of the Intel SoundWire SHIM registers contain fields for different links. Without protection, the master drivers for the different links will access these shared registers, leading to invalid configurations and timeouts (specifically when changing CPA/SPA power-related registers and polling for the changes to be applied). A mutex is added to make sure all rmw access to those registers are serialized. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-11-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 073121c49695..45fa6d93197f 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -71,6 +71,7 @@ struct sdw_intel_link_res; * @links: information for each link (controller-specific and kept * opaque here) * @link_list: list to handle interrupts across all links + * @shim_lock: mutex to handle concurrent rmw access to shared SHIM registers. */ struct sdw_intel_ctx { int count; @@ -79,6 +80,7 @@ struct sdw_intel_ctx { acpi_handle handle; struct sdw_intel_link_res *links; struct list_head link_list; + struct mutex shim_lock; /* lock for access to shared SHIM registers */ }; /** -- cgit v1.2.3 From 09f6a72d014386939d21899921dd379006471a4b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 11 Dec 2019 19:45:07 -0600 Subject: soundwire: intel: add clock stop quirks Due to power rail dependencies, the SoundWire Master driver cannot make decisions on its own when entering pm runtime suspend. Add quirk mask for each link, so that the SOF parent driver can inform the SoundWire master driver of the desired behavior: a) leave clock on b) power-off instead of clock stop c) power-off if all devices cannot generate wakes d) force bus reset on clock restart Note that for now the interface with the SOF driver relies on a single mask for all links. If needed, the interface might be modified at a later point to provide more freedom. The code at the lower level does not assume any commonality between links. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191212014507.28050-12-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 45fa6d93197f..93b83bdf8035 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -59,6 +59,40 @@ struct sdw_intel_acpi_info { struct sdw_intel_link_res; +/* Intel clock-stop/pm_runtime quirk definitions */ + +/* + * Force the clock to remain on during pm_runtime suspend. This might + * be needed if Slave devices do not have an alternate clock source or + * if the latency requirements are very strict. + */ +#define SDW_INTEL_CLK_STOP_NOT_ALLOWED BIT(0) + +/* + * Stop the bus during pm_runtime suspend. If set, a complete bus + * reset and re-enumeration will be performed when the bus + * restarts. This mode shall not be used if Slave devices can generate + * in-band wakes. + */ +#define SDW_INTEL_CLK_STOP_TEARDOWN BIT(1) + +/* + * Stop the bus during pm_suspend if Slaves are not wake capable + * (e.g. speaker amplifiers). The clock-stop mode is typically + * slightly higher power than when the IP is completely powered-off. + */ +#define SDW_INTEL_CLK_STOP_WAKE_CAPABLE_ONLY BIT(2) + +/* + * Require a bus reset (and complete re-enumeration) when exiting + * clock stop modes. This may be needed if the controller power was + * turned off and all context lost. This quirk shall not be used if a + * Slave device needs to remain enumerated and keep its context, + * e.g. to provide the reasons for the wake, report acoustic events or + * pass a history buffer. + */ +#define SDW_INTEL_CLK_STOP_BUS_RESET BIT(3) + /** * struct sdw_intel_ctx - context allocated by the controller * driver probe @@ -97,6 +131,8 @@ struct sdw_intel_ctx { * @link_mask: bit-wise mask listing links selected by the DSP driver * This mask may be a subset of the one reported by the controller since * machine-specific quirks are handled in the DSP driver. + * @clock_stop_quirks: mask array of possible behaviors requested by the + * DSP driver. The quirks are common for all links for now. */ struct sdw_intel_res { int count; @@ -107,6 +143,7 @@ struct sdw_intel_res { const struct sdw_intel_ops *ops; struct device *dev; u32 link_mask; + u32 clock_stop_quirks; }; /* -- cgit v1.2.3 From cb1aa3823c9280f2bb8218cdb5cb05721e0376b1 Mon Sep 17 00:00:00 2001 From: Lakshmi Ramasubramanian Date: Wed, 11 Dec 2019 08:47:05 -0800 Subject: KEYS: Call the IMA hook to measure keys Call the IMA hook from key_create_or_update() function to measure the payload when a new key is created or an existing key is updated. This patch adds the call to the IMA hook from key_create_or_update() function to measure the key on key create or update. Signed-off-by: Lakshmi Ramasubramanian Cc: David Howells Cc: Jarkko Sakkinen Signed-off-by: Mimi Zohar --- include/linux/ima.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 6d904754d858..3b89136bc218 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -101,6 +101,20 @@ static inline void ima_add_kexec_buffer(struct kimage *image) {} #endif +#if defined(CONFIG_IMA) && defined(CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE) +extern void ima_post_key_create_or_update(struct key *keyring, + struct key *key, + const void *payload, size_t plen, + unsigned long flags, bool create); +#else +static inline void ima_post_key_create_or_update(struct key *keyring, + struct key *key, + const void *payload, + size_t plen, + unsigned long flags, + bool create) {} +#endif /* CONFIG_IMA && CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE */ + #ifdef CONFIG_IMA_APPRAISE extern bool is_ima_appraise_enabled(void); extern void ima_inode_post_setattr(struct dentry *dentry); -- cgit v1.2.3 From 461011b1e1ab62aa8a8af78d5b7ee0f81bd1fa37 Mon Sep 17 00:00:00 2001 From: Ravi Patel Date: Tue, 12 Nov 2019 00:35:55 -0800 Subject: drivers: firmware: xilinx: Add support for feature check Query for corresponding feature before calling EEMI API from the driver. Signed-off-by: Ravi Patel Signed-off-by: Michal Simek Signed-off-by: Rajan Vaja --- include/linux/firmware/xlnx-zynqmp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index e41ad9e37136..e72eccf69721 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -48,6 +48,10 @@ #define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U #define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U +/* Feature check status */ +#define PM_FEATURE_INVALID -1 +#define PM_FEATURE_UNCHECKED 0 + /* * Firmware FPGA Manager flags * XILINX_ZYNQMP_PM_FPGA_FULL: FPGA full reconfiguration @@ -78,11 +82,14 @@ enum pm_api_id { PM_CLOCK_GETRATE, PM_CLOCK_SETPARENT, PM_CLOCK_GETPARENT, + PM_FEATURE_CHECK = 63, + PM_API_MAX, }; /* PMU-FW return status codes */ enum pm_ret_status { XST_PM_SUCCESS = 0, + XST_PM_NO_FEATURE = 19, XST_PM_INTERNAL = 2000, XST_PM_CONFLICT, XST_PM_NO_ACCESS, -- cgit v1.2.3 From 94f6345712b37e4bb23cb265ce4c65b9d177e75a Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 12 Dec 2019 08:57:58 -0800 Subject: bus: ti-sysc: Implement quirk handling for CLKDM_NOAUTO For dra7 dcan and dwc3 instances we need to block clockdomain autoidle. Let's do this with CLKDM_NOAUTO quirk flag and enable it for dcan and dwc3. Cc: Keerthy Cc: Roger Quadros Cc: Tero Kristo Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 8cfe570fdece..2cbde6542849 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -49,6 +49,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_QUIRK_CLKDM_NOAUTO BIT(21) #define SYSC_QUIRK_FORCE_MSTANDBY BIT(20) #define SYSC_MODULE_QUIRK_AESS BIT(19) #define SYSC_MODULE_QUIRK_SGX BIT(18) -- cgit v1.2.3 From 4414abf89158d734a83c99f6504f648417bd9550 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 23 Sep 2019 16:31:42 -0700 Subject: rcu: Remove rcu_swap_protected() Now that the calls to rcu_swap_protected() have been replaced by rcu_replace_pointer(), this commit removes rcu_swap_protected(). Link: https://lore.kernel.org/lkml/CAHk-=wiAsJLw1egFEE=Z7-GGtM6wcvtyytXZA1+BHqta4gg6Hw@mail.gmail.com/ Reported-by: Linus Torvalds Signed-off-by: Paul E. McKenney Cc: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Shane M Seymour Cc: Martin K. Petersen --- include/linux/rcupdate.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0b7506330c87..fe470243acdd 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -400,22 +400,6 @@ do { \ __tmp; \ }) -/** - * rcu_swap_protected() - swap an RCU and a regular pointer - * @rcu_ptr: RCU pointer - * @ptr: regular pointer - * @c: the conditions under which the dereference will take place - * - * Perform swap(@rcu_ptr, @ptr) where @rcu_ptr is an RCU-annotated pointer and - * @c is the argument that is passed to the rcu_dereference_protected() call - * used to read that pointer. - */ -#define rcu_swap_protected(rcu_ptr, ptr, c) do { \ - typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ - rcu_assign_pointer((rcu_ptr), (ptr)); \ - (ptr) = __tmp; \ -} while (0) - /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read -- cgit v1.2.3 From b4653342b1514cb11f25b727c689451aff02996d Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Mon, 9 Dec 2019 13:03:40 +0300 Subject: net: Allow to show socket-specific information in /proc/[pid]/fdinfo/[fd] This adds .show_fdinfo to socket_file_ops, so protocols will be able to print their specific data in fdinfo. Signed-off-by: Kirill Tkhai Signed-off-by: David S. Miller --- include/linux/net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 9cafb5f353a9..6451425e828f 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -171,6 +171,7 @@ struct proto_ops { int (*compat_getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); #endif + void (*show_fdinfo)(struct seq_file *m, struct socket *sock); int (*sendmsg) (struct socket *sock, struct msghdr *m, size_t total_len); /* Notes for implementing recvmsg: -- cgit v1.2.3 From 0290bd291cc0e0488e35e66bf39efcd7d9d9122b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 10 Dec 2019 09:23:51 -0500 Subject: netdev: pass the stuck queue to the timeout handler This allows incrementing the correct timeout statistic without any mess. Down the road, devices can learn to reset just the specific queue. The patch was generated with the following script: use strict; use warnings; our $^I = '.bak'; my @work = ( ["arch/m68k/emu/nfeth.c", "nfeth_tx_timeout"], ["arch/um/drivers/net_kern.c", "uml_net_tx_timeout"], ["arch/um/drivers/vector_kern.c", "vector_net_tx_timeout"], ["arch/xtensa/platforms/iss/network.c", "iss_net_tx_timeout"], ["drivers/char/pcmcia/synclink_cs.c", "hdlcdev_tx_timeout"], ["drivers/infiniband/ulp/ipoib/ipoib_main.c", "ipoib_timeout"], ["drivers/infiniband/ulp/ipoib/ipoib_main.c", "ipoib_timeout"], ["drivers/message/fusion/mptlan.c", "mpt_lan_tx_timeout"], ["drivers/misc/sgi-xp/xpnet.c", "xpnet_dev_tx_timeout"], ["drivers/net/appletalk/cops.c", "cops_timeout"], ["drivers/net/arcnet/arcdevice.h", "arcnet_timeout"], ["drivers/net/arcnet/arcnet.c", "arcnet_timeout"], ["drivers/net/arcnet/com20020.c", "arcnet_timeout"], ["drivers/net/ethernet/3com/3c509.c", "el3_tx_timeout"], ["drivers/net/ethernet/3com/3c515.c", "corkscrew_timeout"], ["drivers/net/ethernet/3com/3c574_cs.c", "el3_tx_timeout"], ["drivers/net/ethernet/3com/3c589_cs.c", "el3_tx_timeout"], ["drivers/net/ethernet/3com/3c59x.c", "vortex_tx_timeout"], ["drivers/net/ethernet/3com/3c59x.c", "vortex_tx_timeout"], ["drivers/net/ethernet/3com/typhoon.c", "typhoon_tx_timeout"], ["drivers/net/ethernet/8390/8390.h", "ei_tx_timeout"], ["drivers/net/ethernet/8390/8390.h", "eip_tx_timeout"], ["drivers/net/ethernet/8390/8390.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/8390p.c", "eip_tx_timeout"], ["drivers/net/ethernet/8390/ax88796.c", "ax_ei_tx_timeout"], ["drivers/net/ethernet/8390/axnet_cs.c", "axnet_tx_timeout"], ["drivers/net/ethernet/8390/etherh.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/hydra.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/mac8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/mcf8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/lib8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/ne2k-pci.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/pcnet_cs.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/smc-ultra.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/wd.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/zorro8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/adaptec/starfire.c", "tx_timeout"], ["drivers/net/ethernet/agere/et131x.c", "et131x_tx_timeout"], ["drivers/net/ethernet/allwinner/sun4i-emac.c", "emac_timeout"], ["drivers/net/ethernet/alteon/acenic.c", "ace_watchdog"], ["drivers/net/ethernet/amazon/ena/ena_netdev.c", "ena_tx_timeout"], ["drivers/net/ethernet/amd/7990.h", "lance_tx_timeout"], ["drivers/net/ethernet/amd/7990.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/a2065.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/am79c961a.c", "am79c961_timeout"], ["drivers/net/ethernet/amd/amd8111e.c", "amd8111e_tx_timeout"], ["drivers/net/ethernet/amd/ariadne.c", "ariadne_tx_timeout"], ["drivers/net/ethernet/amd/atarilance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/au1000_eth.c", "au1000_tx_timeout"], ["drivers/net/ethernet/amd/declance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/lance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/mvme147.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/ni65.c", "ni65_timeout"], ["drivers/net/ethernet/amd/nmclan_cs.c", "mace_tx_timeout"], ["drivers/net/ethernet/amd/pcnet32.c", "pcnet32_tx_timeout"], ["drivers/net/ethernet/amd/sunlance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/xgbe/xgbe-drv.c", "xgbe_tx_timeout"], ["drivers/net/ethernet/apm/xgene-v2/main.c", "xge_timeout"], ["drivers/net/ethernet/apm/xgene/xgene_enet_main.c", "xgene_enet_timeout"], ["drivers/net/ethernet/apple/macmace.c", "mace_tx_timeout"], ["drivers/net/ethernet/atheros/ag71xx.c", "ag71xx_tx_timeout"], ["drivers/net/ethernet/atheros/alx/main.c", "alx_tx_timeout"], ["drivers/net/ethernet/atheros/atl1c/atl1c_main.c", "atl1c_tx_timeout"], ["drivers/net/ethernet/atheros/atl1e/atl1e_main.c", "atl1e_tx_timeout"], ["drivers/net/ethernet/atheros/atlx/atl.c", "atlx_tx_timeout"], ["drivers/net/ethernet/atheros/atlx/atl1.c", "atlx_tx_timeout"], ["drivers/net/ethernet/atheros/atlx/atl2.c", "atl2_tx_timeout"], ["drivers/net/ethernet/broadcom/b44.c", "b44_tx_timeout"], ["drivers/net/ethernet/broadcom/bcmsysport.c", "bcm_sysport_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2.c", "bnx2_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h", "bnx2x_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c", "bnx2x_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c", "bnx2x_tx_timeout"], ["drivers/net/ethernet/broadcom/bnxt/bnxt.c", "bnxt_tx_timeout"], ["drivers/net/ethernet/broadcom/genet/bcmgenet.c", "bcmgenet_timeout"], ["drivers/net/ethernet/broadcom/sb1250-mac.c", "sbmac_tx_timeout"], ["drivers/net/ethernet/broadcom/tg3.c", "tg3_tx_timeout"], ["drivers/net/ethernet/calxeda/xgmac.c", "xgmac_tx_timeout"], ["drivers/net/ethernet/cavium/liquidio/lio_main.c", "liquidio_tx_timeout"], ["drivers/net/ethernet/cavium/liquidio/lio_vf_main.c", "liquidio_tx_timeout"], ["drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c", "lio_vf_rep_tx_timeout"], ["drivers/net/ethernet/cavium/thunder/nicvf_main.c", "nicvf_tx_timeout"], ["drivers/net/ethernet/cirrus/cs89x0.c", "net_timeout"], ["drivers/net/ethernet/cisco/enic/enic_main.c", "enic_tx_timeout"], ["drivers/net/ethernet/cisco/enic/enic_main.c", "enic_tx_timeout"], ["drivers/net/ethernet/cortina/gemini.c", "gmac_tx_timeout"], ["drivers/net/ethernet/davicom/dm9000.c", "dm9000_timeout"], ["drivers/net/ethernet/dec/tulip/de2104x.c", "de_tx_timeout"], ["drivers/net/ethernet/dec/tulip/tulip_core.c", "tulip_tx_timeout"], ["drivers/net/ethernet/dec/tulip/winbond-840.c", "tx_timeout"], ["drivers/net/ethernet/dlink/dl2k.c", "rio_tx_timeout"], ["drivers/net/ethernet/dlink/sundance.c", "tx_timeout"], ["drivers/net/ethernet/emulex/benet/be_main.c", "be_tx_timeout"], ["drivers/net/ethernet/ethoc.c", "ethoc_tx_timeout"], ["drivers/net/ethernet/faraday/ftgmac100.c", "ftgmac100_tx_timeout"], ["drivers/net/ethernet/fealnx.c", "fealnx_tx_timeout"], ["drivers/net/ethernet/freescale/dpaa/dpaa_eth.c", "dpaa_tx_timeout"], ["drivers/net/ethernet/freescale/fec_main.c", "fec_timeout"], ["drivers/net/ethernet/freescale/fec_mpc52xx.c", "mpc52xx_fec_tx_timeout"], ["drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c", "fs_timeout"], ["drivers/net/ethernet/freescale/gianfar.c", "gfar_timeout"], ["drivers/net/ethernet/freescale/ucc_geth.c", "ucc_geth_timeout"], ["drivers/net/ethernet/fujitsu/fmvj18x_cs.c", "fjn_tx_timeout"], ["drivers/net/ethernet/google/gve/gve_main.c", "gve_tx_timeout"], ["drivers/net/ethernet/hisilicon/hip04_eth.c", "hip04_timeout"], ["drivers/net/ethernet/hisilicon/hix5hd2_gmac.c", "hix5hd2_net_timeout"], ["drivers/net/ethernet/hisilicon/hns/hns_enet.c", "hns_nic_net_timeout"], ["drivers/net/ethernet/hisilicon/hns3/hns3_enet.c", "hns3_nic_net_timeout"], ["drivers/net/ethernet/huawei/hinic/hinic_main.c", "hinic_tx_timeout"], ["drivers/net/ethernet/i825xx/82596.c", "i596_tx_timeout"], ["drivers/net/ethernet/i825xx/ether1.c", "ether1_timeout"], ["drivers/net/ethernet/i825xx/lib82596.c", "i596_tx_timeout"], ["drivers/net/ethernet/i825xx/sun3_82586.c", "sun3_82586_timeout"], ["drivers/net/ethernet/ibm/ehea/ehea_main.c", "ehea_tx_watchdog"], ["drivers/net/ethernet/ibm/emac/core.c", "emac_tx_timeout"], ["drivers/net/ethernet/ibm/emac/core.c", "emac_tx_timeout"], ["drivers/net/ethernet/ibm/ibmvnic.c", "ibmvnic_tx_timeout"], ["drivers/net/ethernet/intel/e100.c", "e100_tx_timeout"], ["drivers/net/ethernet/intel/e1000/e1000_main.c", "e1000_tx_timeout"], ["drivers/net/ethernet/intel/e1000e/netdev.c", "e1000_tx_timeout"], ["drivers/net/ethernet/intel/fm10k/fm10k_netdev.c", "fm10k_tx_timeout"], ["drivers/net/ethernet/intel/i40e/i40e_main.c", "i40e_tx_timeout"], ["drivers/net/ethernet/intel/iavf/iavf_main.c", "iavf_tx_timeout"], ["drivers/net/ethernet/intel/ice/ice_main.c", "ice_tx_timeout"], ["drivers/net/ethernet/intel/ice/ice_main.c", "ice_tx_timeout"], ["drivers/net/ethernet/intel/igb/igb_main.c", "igb_tx_timeout"], ["drivers/net/ethernet/intel/igbvf/netdev.c", "igbvf_tx_timeout"], ["drivers/net/ethernet/intel/ixgb/ixgb_main.c", "ixgb_tx_timeout"], ["drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c", "adapter->netdev->netdev_ops->ndo_tx_timeout(adapter->netdev);"], ["drivers/net/ethernet/intel/ixgbe/ixgbe_main.c", "ixgbe_tx_timeout"], ["drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c", "ixgbevf_tx_timeout"], ["drivers/net/ethernet/jme.c", "jme_tx_timeout"], ["drivers/net/ethernet/korina.c", "korina_tx_timeout"], ["drivers/net/ethernet/lantiq_etop.c", "ltq_etop_tx_timeout"], ["drivers/net/ethernet/marvell/mv643xx_eth.c", "mv643xx_eth_tx_timeout"], ["drivers/net/ethernet/marvell/pxa168_eth.c", "pxa168_eth_tx_timeout"], ["drivers/net/ethernet/marvell/skge.c", "skge_tx_timeout"], ["drivers/net/ethernet/marvell/sky2.c", "sky2_tx_timeout"], ["drivers/net/ethernet/marvell/sky2.c", "sky2_tx_timeout"], ["drivers/net/ethernet/mediatek/mtk_eth_soc.c", "mtk_tx_timeout"], ["drivers/net/ethernet/mellanox/mlx4/en_netdev.c", "mlx4_en_tx_timeout"], ["drivers/net/ethernet/mellanox/mlx4/en_netdev.c", "mlx4_en_tx_timeout"], ["drivers/net/ethernet/mellanox/mlx5/core/en_main.c", "mlx5e_tx_timeout"], ["drivers/net/ethernet/micrel/ks8842.c", "ks8842_tx_timeout"], ["drivers/net/ethernet/micrel/ksz884x.c", "netdev_tx_timeout"], ["drivers/net/ethernet/microchip/enc28j60.c", "enc28j60_tx_timeout"], ["drivers/net/ethernet/microchip/encx24j600.c", "encx24j600_tx_timeout"], ["drivers/net/ethernet/natsemi/sonic.h", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/sonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/jazzsonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/macsonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/natsemi.c", "ns_tx_timeout"], ["drivers/net/ethernet/natsemi/ns83820.c", "ns83820_tx_timeout"], ["drivers/net/ethernet/natsemi/xtsonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/neterion/s2io.h", "s2io_tx_watchdog"], ["drivers/net/ethernet/neterion/s2io.c", "s2io_tx_watchdog"], ["drivers/net/ethernet/neterion/vxge/vxge-main.c", "vxge_tx_watchdog"], ["drivers/net/ethernet/netronome/nfp/nfp_net_common.c", "nfp_net_tx_timeout"], ["drivers/net/ethernet/nvidia/forcedeth.c", "nv_tx_timeout"], ["drivers/net/ethernet/nvidia/forcedeth.c", "nv_tx_timeout"], ["drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c", "pch_gbe_tx_timeout"], ["drivers/net/ethernet/packetengines/hamachi.c", "hamachi_tx_timeout"], ["drivers/net/ethernet/packetengines/yellowfin.c", "yellowfin_tx_timeout"], ["drivers/net/ethernet/pensando/ionic/ionic_lif.c", "ionic_tx_timeout"], ["drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c", "netxen_tx_timeout"], ["drivers/net/ethernet/qlogic/qla3xxx.c", "ql3xxx_tx_timeout"], ["drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c", "qlcnic_tx_timeout"], ["drivers/net/ethernet/qualcomm/emac/emac.c", "emac_tx_timeout"], ["drivers/net/ethernet/qualcomm/qca_spi.c", "qcaspi_netdev_tx_timeout"], ["drivers/net/ethernet/qualcomm/qca_uart.c", "qcauart_netdev_tx_timeout"], ["drivers/net/ethernet/rdc/r6040.c", "r6040_tx_timeout"], ["drivers/net/ethernet/realtek/8139cp.c", "cp_tx_timeout"], ["drivers/net/ethernet/realtek/8139too.c", "rtl8139_tx_timeout"], ["drivers/net/ethernet/realtek/atp.c", "tx_timeout"], ["drivers/net/ethernet/realtek/r8169_main.c", "rtl8169_tx_timeout"], ["drivers/net/ethernet/renesas/ravb_main.c", "ravb_tx_timeout"], ["drivers/net/ethernet/renesas/sh_eth.c", "sh_eth_tx_timeout"], ["drivers/net/ethernet/renesas/sh_eth.c", "sh_eth_tx_timeout"], ["drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c", "sxgbe_tx_timeout"], ["drivers/net/ethernet/seeq/ether3.c", "ether3_timeout"], ["drivers/net/ethernet/seeq/sgiseeq.c", "timeout"], ["drivers/net/ethernet/sfc/efx.c", "efx_watchdog"], ["drivers/net/ethernet/sfc/falcon/efx.c", "ef4_watchdog"], ["drivers/net/ethernet/sgi/ioc3-eth.c", "ioc3_timeout"], ["drivers/net/ethernet/sgi/meth.c", "meth_tx_timeout"], ["drivers/net/ethernet/silan/sc92031.c", "sc92031_tx_timeout"], ["drivers/net/ethernet/sis/sis190.c", "sis190_tx_timeout"], ["drivers/net/ethernet/sis/sis900.c", "sis900_tx_timeout"], ["drivers/net/ethernet/smsc/epic100.c", "epic_tx_timeout"], ["drivers/net/ethernet/smsc/smc911x.c", "smc911x_timeout"], ["drivers/net/ethernet/smsc/smc9194.c", "smc_timeout"], ["drivers/net/ethernet/smsc/smc91c92_cs.c", "smc_tx_timeout"], ["drivers/net/ethernet/smsc/smc91x.c", "smc_timeout"], ["drivers/net/ethernet/stmicro/stmmac/stmmac_main.c", "stmmac_tx_timeout"], ["drivers/net/ethernet/sun/cassini.c", "cas_tx_timeout"], ["drivers/net/ethernet/sun/ldmvsw.c", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/sun/niu.c", "niu_tx_timeout"], ["drivers/net/ethernet/sun/sunbmac.c", "bigmac_tx_timeout"], ["drivers/net/ethernet/sun/sungem.c", "gem_tx_timeout"], ["drivers/net/ethernet/sun/sunhme.c", "happy_meal_tx_timeout"], ["drivers/net/ethernet/sun/sunqe.c", "qe_tx_timeout"], ["drivers/net/ethernet/sun/sunvnet.c", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/sun/sunvnet_common.c", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/sun/sunvnet_common.h", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/synopsys/dwc-xlgmac-net.c", "xlgmac_tx_timeout"], ["drivers/net/ethernet/ti/cpmac.c", "cpmac_tx_timeout"], ["drivers/net/ethernet/ti/cpsw.c", "cpsw_ndo_tx_timeout"], ["drivers/net/ethernet/ti/cpsw_priv.c", "cpsw_ndo_tx_timeout"], ["drivers/net/ethernet/ti/cpsw_priv.h", "cpsw_ndo_tx_timeout"], ["drivers/net/ethernet/ti/davinci_emac.c", "emac_dev_tx_timeout"], ["drivers/net/ethernet/ti/netcp_core.c", "netcp_ndo_tx_timeout"], ["drivers/net/ethernet/ti/tlan.c", "tlan_tx_timeout"], ["drivers/net/ethernet/toshiba/ps3_gelic_net.h", "gelic_net_tx_timeout"], ["drivers/net/ethernet/toshiba/ps3_gelic_net.c", "gelic_net_tx_timeout"], ["drivers/net/ethernet/toshiba/ps3_gelic_wireless.c", "gelic_net_tx_timeout"], ["drivers/net/ethernet/toshiba/spider_net.c", "spider_net_tx_timeout"], ["drivers/net/ethernet/toshiba/tc35815.c", "tc35815_tx_timeout"], ["drivers/net/ethernet/via/via-rhine.c", "rhine_tx_timeout"], ["drivers/net/ethernet/wiznet/w5100.c", "w5100_tx_timeout"], ["drivers/net/ethernet/wiznet/w5300.c", "w5300_tx_timeout"], ["drivers/net/ethernet/xilinx/xilinx_emaclite.c", "xemaclite_tx_timeout"], ["drivers/net/ethernet/xircom/xirc2ps_cs.c", "xirc_tx_timeout"], ["drivers/net/fjes/fjes_main.c", "fjes_tx_retry"], ["drivers/net/slip/slip.c", "sl_tx_timeout"], ["include/linux/usb/usbnet.h", "usbnet_tx_timeout"], ["drivers/net/usb/aqc111.c", "usbnet_tx_timeout"], ["drivers/net/usb/asix_devices.c", "usbnet_tx_timeout"], ["drivers/net/usb/asix_devices.c", "usbnet_tx_timeout"], ["drivers/net/usb/asix_devices.c", "usbnet_tx_timeout"], ["drivers/net/usb/ax88172a.c", "usbnet_tx_timeout"], ["drivers/net/usb/ax88179_178a.c", "usbnet_tx_timeout"], ["drivers/net/usb/catc.c", "catc_tx_timeout"], ["drivers/net/usb/cdc_mbim.c", "usbnet_tx_timeout"], ["drivers/net/usb/cdc_ncm.c", "usbnet_tx_timeout"], ["drivers/net/usb/dm9601.c", "usbnet_tx_timeout"], ["drivers/net/usb/hso.c", "hso_net_tx_timeout"], ["drivers/net/usb/int51x1.c", "usbnet_tx_timeout"], ["drivers/net/usb/ipheth.c", "ipheth_tx_timeout"], ["drivers/net/usb/kaweth.c", "kaweth_tx_timeout"], ["drivers/net/usb/lan78xx.c", "lan78xx_tx_timeout"], ["drivers/net/usb/mcs7830.c", "usbnet_tx_timeout"], ["drivers/net/usb/pegasus.c", "pegasus_tx_timeout"], ["drivers/net/usb/qmi_wwan.c", "usbnet_tx_timeout"], ["drivers/net/usb/r8152.c", "rtl8152_tx_timeout"], ["drivers/net/usb/rndis_host.c", "usbnet_tx_timeout"], ["drivers/net/usb/rtl8150.c", "rtl8150_tx_timeout"], ["drivers/net/usb/sierra_net.c", "usbnet_tx_timeout"], ["drivers/net/usb/smsc75xx.c", "usbnet_tx_timeout"], ["drivers/net/usb/smsc95xx.c", "usbnet_tx_timeout"], ["drivers/net/usb/sr9700.c", "usbnet_tx_timeout"], ["drivers/net/usb/sr9800.c", "usbnet_tx_timeout"], ["drivers/net/usb/usbnet.c", "usbnet_tx_timeout"], ["drivers/net/vmxnet3/vmxnet3_drv.c", "vmxnet3_tx_timeout"], ["drivers/net/wan/cosa.c", "cosa_net_timeout"], ["drivers/net/wan/farsync.c", "fst_tx_timeout"], ["drivers/net/wan/fsl_ucc_hdlc.c", "uhdlc_tx_timeout"], ["drivers/net/wan/lmc/lmc_main.c", "lmc_driver_timeout"], ["drivers/net/wan/x25_asy.c", "x25_asy_timeout"], ["drivers/net/wimax/i2400m/netdev.c", "i2400m_tx_timeout"], ["drivers/net/wireless/intel/ipw2x00/ipw2100.c", "ipw2100_tx_timeout"], ["drivers/net/wireless/intersil/hostap/hostap_main.c", "prism2_tx_timeout"], ["drivers/net/wireless/intersil/hostap/hostap_main.c", "prism2_tx_timeout"], ["drivers/net/wireless/intersil/hostap/hostap_main.c", "prism2_tx_timeout"], ["drivers/net/wireless/intersil/orinoco/main.c", "orinoco_tx_timeout"], ["drivers/net/wireless/intersil/orinoco/orinoco_usb.c", "orinoco_tx_timeout"], ["drivers/net/wireless/intersil/orinoco/orinoco.h", "orinoco_tx_timeout"], ["drivers/net/wireless/intersil/prism54/islpci_dev.c", "islpci_eth_tx_timeout"], ["drivers/net/wireless/intersil/prism54/islpci_eth.c", "islpci_eth_tx_timeout"], ["drivers/net/wireless/intersil/prism54/islpci_eth.h", "islpci_eth_tx_timeout"], ["drivers/net/wireless/marvell/mwifiex/main.c", "mwifiex_tx_timeout"], ["drivers/net/wireless/quantenna/qtnfmac/core.c", "qtnf_netdev_tx_timeout"], ["drivers/net/wireless/quantenna/qtnfmac/core.h", "qtnf_netdev_tx_timeout"], ["drivers/net/wireless/rndis_wlan.c", "usbnet_tx_timeout"], ["drivers/net/wireless/wl3501_cs.c", "wl3501_tx_timeout"], ["drivers/net/wireless/zydas/zd1201.c", "zd1201_tx_timeout"], ["drivers/s390/net/qeth_core.h", "qeth_tx_timeout"], ["drivers/s390/net/qeth_core_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l2_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l2_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l3_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l3_main.c", "qeth_tx_timeout"], ["drivers/staging/ks7010/ks_wlan_net.c", "ks_wlan_tx_timeout"], ["drivers/staging/qlge/qlge_main.c", "qlge_tx_timeout"], ["drivers/staging/rtl8192e/rtl8192e/rtl_core.c", "_rtl92e_tx_timeout"], ["drivers/staging/rtl8192u/r8192U_core.c", "tx_timeout"], ["drivers/staging/unisys/visornic/visornic_main.c", "visornic_xmit_timeout"], ["drivers/staging/wlan-ng/p80211netdev.c", "p80211knetdev_tx_timeout"], ["drivers/tty/n_gsm.c", "gsm_mux_net_tx_timeout"], ["drivers/tty/synclink.c", "hdlcdev_tx_timeout"], ["drivers/tty/synclink_gt.c", "hdlcdev_tx_timeout"], ["drivers/tty/synclinkmp.c", "hdlcdev_tx_timeout"], ["net/atm/lec.c", "lec_tx_timeout"], ["net/bluetooth/bnep/netdev.c", "bnep_net_timeout"] ); for my $p (@work) { my @pair = @$p; my $file = $pair[0]; my $func = $pair[1]; print STDERR $file , ": ", $func,"\n"; our @ARGV = ($file); while () { if (m/($func\s*\(struct\s+net_device\s+\*[A-Za-z_]?[A-Za-z-0-9_]*)(\))/) { print STDERR "found $1+$2 in $file\n"; } if (s/($func\s*\(struct\s+net_device\s+\*[A-Za-z_]?[A-Za-z-0-9_]*)(\))/$1, unsigned int txqueue$2/) { print STDERR "$func found in $file\n"; } print; } } where the list of files and functions is simply from: git grep ndo_tx_timeout, with manual addition of headers in the rare cases where the function is from a header, then manually changing the few places which actually call ndo_tx_timeout. Signed-off-by: Michael S. Tsirkin Acked-by: Heiner Kallweit Acked-by: Jakub Kicinski Acked-by: Shannon Nelson Reviewed-by: Martin Habets changes from v9: fixup a forward declaration changes from v9: more leftovers from v3 change changes from v8: fix up a missing direct call to timeout rebased on net-next changes from v7: fixup leftovers from v3 change changes from v6: fix typo in rtl driver changes from v5: add missing files (allow any net device argument name) changes from v4: add a missing driver header changes from v3: change queue # to unsigned Changes from v2: added headers Changes from v1: Fix errors found by kbuild: generalize the pattern a bit, to pick up a couple of instances missed by the previous version. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++-- include/linux/usb/usbnet.h | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ef20389622d..30745068fb39 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1014,7 +1014,7 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); * Called when a user wants to change the Maximum Transfer Unit * of a device. * - * void (*ndo_tx_timeout)(struct net_device *dev); + * void (*ndo_tx_timeout)(struct net_device *dev, unsigned int txqueue); * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * @@ -1281,7 +1281,8 @@ struct net_device_ops { int new_mtu); int (*ndo_neigh_setup)(struct net_device *dev, struct neigh_parms *); - void (*ndo_tx_timeout) (struct net_device *dev); + void (*ndo_tx_timeout) (struct net_device *dev, + unsigned int txqueue); void (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index d8860f2d0976..b0bff3083278 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -253,7 +253,7 @@ extern int usbnet_open(struct net_device *net); extern int usbnet_stop(struct net_device *net); extern netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, struct net_device *net); -extern void usbnet_tx_timeout(struct net_device *net); +extern void usbnet_tx_timeout(struct net_device *net, unsigned int txqueue); extern int usbnet_change_mtu(struct net_device *net, int new_mtu); extern int usbnet_get_endpoints(struct usbnet *, struct usb_interface *); -- cgit v1.2.3 From 55d54d1ee84e5980446b390154526d62bee24ca2 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 6 Dec 2019 18:08:13 +0100 Subject: pinctrl: core: Add pinctrl_select_default_state() and export it It has turned out that some mmc host drivers, but perhaps also others drivers, needs to reset the pinctrl into the default state (PINCTRL_STATE_DEFAULT). However, they can't use the existing pinctrl_pm_select_default_state(), as that requires CONFIG_PM to be set. This leads to open coding, as they need to look up the default state themselves and then select it. To avoid the open coding, let's introduce pinctrl_select_default_state() and make it available independently of CONFIG_PM. As a matter of fact, this makes it more consistent with the behaviour of the driver core, as it already tries to looks up the default state during probe. Going forward, users of pinctrl_pm_select_default_state() are encouraged to move to pinctrl_select_default_state(), so the old API can be removed. Signed-off-by: Ulf Hansson Link: https://lore.kernel.org/r/20191206170821.29711-2-ulf.hansson@linaro.org Signed-off-by: Linus Walleij --- include/linux/pinctrl/consumer.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h index 7f8c7d9583d3..019fecd75d0c 100644 --- a/include/linux/pinctrl/consumer.h +++ b/include/linux/pinctrl/consumer.h @@ -40,6 +40,7 @@ extern int pinctrl_select_state(struct pinctrl *p, struct pinctrl_state *s); extern struct pinctrl * __must_check devm_pinctrl_get(struct device *dev); extern void devm_pinctrl_put(struct pinctrl *p); +extern int pinctrl_select_default_state(struct device *dev); #ifdef CONFIG_PM extern int pinctrl_pm_select_default_state(struct device *dev); @@ -122,6 +123,11 @@ static inline void devm_pinctrl_put(struct pinctrl *p) { } +static inline int pinctrl_select_default_state(struct device *dev) +{ + return 0; +} + static inline int pinctrl_pm_select_default_state(struct device *dev) { return 0; -- cgit v1.2.3 From 98e8627efcada18ac043a77b9101b4b4c768090b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Fri, 13 Dec 2019 18:51:07 +0100 Subject: bpf: Move trampoline JIT image allocation to a function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Refactor the image allocation in the BPF trampoline code into a separate function, so it can be shared with the BPF dispatcher in upcoming commits. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191213175112.30208-2-bjorn.topel@gmail.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 35903f148be5..5d744828b399 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -475,6 +475,7 @@ 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); void bpf_trampoline_put(struct bpf_trampoline *tr); +void *bpf_jit_alloc_exec_page(void); #else static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { -- cgit v1.2.3 From 75ccbef6369e94ecac696a152a998a978d41376b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Fri, 13 Dec 2019 18:51:08 +0100 Subject: bpf: Introduce BPF dispatcher MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The BPF dispatcher is a multi-way branch code generator, mainly targeted for XDP programs. When an XDP program is executed via the bpf_prog_run_xdp(), it is invoked via an indirect call. The indirect call has a substantial performance impact, when retpolines are enabled. The dispatcher transform indirect calls to direct calls, and therefore avoids the retpoline. The dispatcher is generated using the BPF JIT, and relies on text poking provided by bpf_arch_text_poke(). The dispatcher hijacks a trampoline function it via the __fentry__ nop of the trampoline. One dispatcher instance currently supports up to 64 dispatch points. A user creates a dispatcher with its corresponding trampoline with the DEFINE_BPF_DISPATCHER macro. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191213175112.30208-3-bjorn.topel@gmail.com --- include/linux/bpf.h | 56 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5d744828b399..53ae4a50abe4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -470,12 +470,61 @@ struct bpf_trampoline { void *image; u64 selector; }; + +#define BPF_DISPATCHER_MAX 64 /* Fits in 2048B */ + +struct bpf_dispatcher_prog { + struct bpf_prog *prog; + refcount_t users; +}; + +struct bpf_dispatcher { + /* dispatcher mutex */ + struct mutex mutex; + void *func; + struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; + int num_progs; + void *image; + u32 image_off; +}; + #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); void bpf_trampoline_put(struct bpf_trampoline *tr); void *bpf_jit_alloc_exec_page(void); +#define BPF_DISPATCHER_INIT(name) { \ + .mutex = __MUTEX_INITIALIZER(name.mutex), \ + .func = &name##func, \ + .progs = {}, \ + .num_progs = 0, \ + .image = NULL, \ + .image_off = 0 \ +} + +#define DEFINE_BPF_DISPATCHER(name) \ + noinline unsigned int name##func( \ + const void *ctx, \ + const struct bpf_insn *insnsi, \ + unsigned int (*bpf_func)(const void *, \ + const struct bpf_insn *)) \ + { \ + return bpf_func(ctx, insnsi); \ + } \ + EXPORT_SYMBOL(name##func); \ + struct bpf_dispatcher name = BPF_DISPATCHER_INIT(name); +#define DECLARE_BPF_DISPATCHER(name) \ + unsigned int name##func( \ + const void *ctx, \ + const struct bpf_insn *insnsi, \ + unsigned int (*bpf_func)(const void *, \ + const struct bpf_insn *)); \ + extern struct bpf_dispatcher name; +#define BPF_DISPATCHER_FUNC(name) name##func +#define BPF_DISPATCHER_PTR(name) (&name) +void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, + struct bpf_prog *to); #else static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { @@ -490,6 +539,13 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) return -ENOTSUPP; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} +#define DEFINE_BPF_DISPATCHER(name) +#define DECLARE_BPF_DISPATCHER(name) +#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nopfunc +#define BPF_DISPATCHER_PTR(name) NULL +static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, + struct bpf_prog *from, + struct bpf_prog *to) {} #endif struct bpf_func_info_aux { -- cgit v1.2.3 From 7e6897f95935973c3253fd756135b5ea58043dc8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Fri, 13 Dec 2019 18:51:09 +0100 Subject: bpf, xdp: Start using the BPF dispatcher for XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit adds a BPF dispatcher for XDP. The dispatcher is updated from the XDP control-path, dev_xdp_install(), and used when an XDP program is run via bpf_prog_run_xdp(). Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191213175112.30208-4-bjorn.topel@gmail.com --- include/linux/bpf.h | 15 +++++++++++++++ include/linux/filter.h | 40 ++++++++++++++++++++++++---------------- 2 files changed, 39 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 53ae4a50abe4..5970989b99d1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,6 +488,14 @@ struct bpf_dispatcher { u32 image_off; }; +static __always_inline unsigned int bpf_dispatcher_nopfunc( + const void *ctx, + const struct bpf_insn *insnsi, + unsigned int (*bpf_func)(const void *, + const struct bpf_insn *)) +{ + 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); @@ -997,6 +1005,8 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog); +struct bpf_prog *bpf_prog_by_id(u32 id); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1128,6 +1138,11 @@ static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, static inline void bpf_map_put(struct bpf_map *map) { } + +static inline struct bpf_prog *bpf_prog_by_id(u32 id) +{ + return ERR_PTR(-ENOTSUPP); +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, diff --git a/include/linux/filter.h b/include/linux/filter.h index a141cb07e76a..37ac7025031d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -559,23 +559,26 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); -#define BPF_PROG_RUN(prog, ctx) ({ \ - u32 ret; \ - cant_sleep(); \ - if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ - struct bpf_prog_stats *stats; \ - u64 start = sched_clock(); \ - ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \ - stats = this_cpu_ptr(prog->aux->stats); \ - u64_stats_update_begin(&stats->syncp); \ - stats->cnt++; \ - stats->nsecs += sched_clock() - start; \ - u64_stats_update_end(&stats->syncp); \ - } else { \ - ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \ - } \ +#define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ + u32 ret; \ + cant_sleep(); \ + if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ + struct bpf_prog_stats *stats; \ + u64 start = sched_clock(); \ + ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + stats = this_cpu_ptr(prog->aux->stats); \ + u64_stats_update_begin(&stats->syncp); \ + stats->cnt++; \ + stats->nsecs += sched_clock() - start; \ + u64_stats_update_end(&stats->syncp); \ + } else { \ + ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + } \ ret; }) +#define BPF_PROG_RUN(prog, ctx) __BPF_PROG_RUN(prog, ctx, \ + bpf_dispatcher_nopfunc) + #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { @@ -699,6 +702,8 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, return res; } +DECLARE_BPF_DISPATCHER(bpf_dispatcher_xdp) + static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { @@ -708,9 +713,12 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, * already takes rcu_read_lock() when fetching the program, so * it's not necessary here anymore. */ - return BPF_PROG_RUN(prog, xdp); + return __BPF_PROG_RUN(prog, xdp, + BPF_DISPATCHER_FUNC(bpf_dispatcher_xdp)); } +void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); + static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); -- cgit v1.2.3 From 116eb788f57c9c35c40b29cfaa2607020de99a84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Fri, 13 Dec 2019 18:51:12 +0100 Subject: bpf, x86: Align dispatcher branch targets to 16B MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit >From Intel 64 and IA-32 Architectures Optimization Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler Coding Rule 11: All branch targets should be 16-byte aligned. This commits aligns branch targets according to the Intel manual. The nops used to align branch targets make the dispatcher larger, and therefore the number of supported dispatch points/programs are descreased from 64 to 48. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191213175112.30208-7-bjorn.topel@gmail.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5970989b99d1..d467983e61bb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -471,7 +471,7 @@ struct bpf_trampoline { u64 selector; }; -#define BPF_DISPATCHER_MAX 64 /* Fits in 2048B */ +#define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ struct bpf_dispatcher_prog { struct bpf_prog *prog; -- cgit v1.2.3 From cd6a1ca38698b0c8ff8afe5074fe53aff3647973 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 6 Dec 2019 10:43:01 +0100 Subject: drm/gma500: Pass GPIO for Intel MID using descriptors The GMA500 driver is using the legacy GPIO API to fetch three optional display control GPIO lines from the SFI description used by the Medfield platform. Switch this over to use GPIO descriptors and delete the custom platform data. We create three new static locals in the tc35876x bridge code but it is hardly any worse than the I2C client static local already there: I tried first to move it to the DRM driver state container but there are workarounds for probe order in the code so I just stayed off it, as the result is unpredictable. People wanting to do a more throrugh and proper cleanup of the GMA500 driver can work on top of this, I can't solve much more since I don't have access to the hardware, I can only attempt to tidy up my GPIO corner. Cc: Daniel Stone Cc: Daniel Vetter Reviewed-by: Andy Shevchenko Acked-by: Patrik Jakobsson Link: https://patchwork.freedesktop.org/patch/msgid/20191206094301.76368-1-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- include/linux/platform_data/tc35876x.h | 11 ----------- 1 file changed, 11 deletions(-) delete mode 100644 include/linux/platform_data/tc35876x.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tc35876x.h b/include/linux/platform_data/tc35876x.h deleted file mode 100644 index cd6a51c71e7e..000000000000 --- a/include/linux/platform_data/tc35876x.h +++ /dev/null @@ -1,11 +0,0 @@ - -#ifndef _TC35876X_H -#define _TC35876X_H - -struct tc35876x_platform_data { - int gpio_bridge_reset; - int gpio_panel_bl_en; - int gpio_panel_vadd; -}; - -#endif /* _TC35876X_H */ -- cgit v1.2.3 From 2c289e63944467a41c6703f46bcf2f3340713510 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 2 Dec 2019 09:17:30 +0100 Subject: iio: ak8975: Convert to use GPIO descriptor The end-of-conversion (EOC) GPIO line is better to grab using a GPIO descriptor. We drop the pdata for this: clients using board files can use machine descriptor tables to pass this GPIO from static data. Cc: Stephan Gerhold Signed-off-by: Linus Walleij Reviewed-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/magnetometer/ak8975.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/magnetometer/ak8975.h b/include/linux/iio/magnetometer/ak8975.h index ac9366f807cb..df3697183800 100644 --- a/include/linux/iio/magnetometer/ak8975.h +++ b/include/linux/iio/magnetometer/ak8975.h @@ -6,11 +6,9 @@ /** * struct ak8975_platform_data - AK8975 magnetometer driver platform data - * @eoc_gpio: data ready event gpio * @orientation: mounting matrix relative to main hardware */ struct ak8975_platform_data { - int eoc_gpio; struct iio_mount_matrix orientation; }; -- cgit v1.2.3 From 4a89d2f47ccdce69597ba2f92e0b55c9a1f1d1ea Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 2 Dec 2019 09:38:30 +0100 Subject: iio: adf4350: Convert to use GPIO descriptor The lock detect GPIO line is better to grab using a GPIO descriptor. We drop the pdata for this: clients using board files can use machine descriptor tables to pass this GPIO from static data. Cc: Michael Hennerich Signed-off-by: Linus Walleij Reviewed-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/frequency/adf4350.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/frequency/adf4350.h b/include/linux/iio/frequency/adf4350.h index ce9490bfeb89..de45cf2ee1e4 100644 --- a/include/linux/iio/frequency/adf4350.h +++ b/include/linux/iio/frequency/adf4350.h @@ -103,9 +103,6 @@ * @r2_user_settings: User defined settings for ADF4350/1 REGISTER_2. * @r3_user_settings: User defined settings for ADF4350/1 REGISTER_3. * @r4_user_settings: User defined settings for ADF4350/1 REGISTER_4. - * @gpio_lock_detect: Optional, if set with a valid GPIO number, - * pll lock state is tested upon read. - * If not used - set to -1. */ struct adf4350_platform_data { @@ -121,7 +118,6 @@ struct adf4350_platform_data { unsigned r2_user_settings; unsigned r3_user_settings; unsigned r4_user_settings; - int gpio_lock_detect; }; #endif /* IIO_PLL_ADF4350_H_ */ -- cgit v1.2.3 From 5750ebab14907f05aa9904ef2f3c1bb8dcb1fd2b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 2 Dec 2019 10:38:06 +0100 Subject: iio: ad7266: Convert to use GPIO descriptors The AD7266 have no in-tree users making use of the platform data mechanism to pass address GPIO lines when not using a fixed address, so we can easily convert this to use GPIO descriptors instead of the platform data integers currently passed. Lowercase the labels "ad0".."ad2" as this will make a better fit for platform descriptions like device tree that prefer lowercase names such as "ad0-gpios" rather than "AD0-gpios". Board files and other static users of this device can pass the same GPIO descriptors using machine descriptor tables if need be. Cc: Alison Schofield Cc: Lars-Peter Clausen Signed-off-by: Linus Walleij Reviewed-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/platform_data/ad7266.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ad7266.h b/include/linux/platform_data/ad7266.h index 7de6c16122df..f0652567afba 100644 --- a/include/linux/platform_data/ad7266.h +++ b/include/linux/platform_data/ad7266.h @@ -40,14 +40,11 @@ enum ad7266_mode { * @range: Reference voltage range the device is configured for * @mode: Sample mode the device is configured for * @fixed_addr: Whether the address pins are hard-wired - * @addr_gpios: GPIOs used for controlling the address pins, only used if - * fixed_addr is set to false. */ struct ad7266_platform_data { enum ad7266_range range; enum ad7266_mode mode; bool fixed_addr; - unsigned int addr_gpios[3]; }; #endif -- cgit v1.2.3 From 0cd9ff1535f4339710dfd577a7d91b96fd4b423b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 5 Dec 2019 19:46:36 +0200 Subject: iio: adc: ti-ads1015: Get rid of legacy platform data Platform data is a legacy interface to supply device properties to the driver. In this case we even don't have in-kernel users for it. Just remove it for good. Signed-off-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- include/linux/platform_data/ads1015.h | 23 ----------------------- 1 file changed, 23 deletions(-) delete mode 100644 include/linux/platform_data/ads1015.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ads1015.h b/include/linux/platform_data/ads1015.h deleted file mode 100644 index 4cc9ffcafcbf..000000000000 --- a/include/linux/platform_data/ads1015.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Platform Data for ADS1015 12-bit 4-input ADC - * (C) Copyright 2010 - * Dirk Eibach, Guntermann & Drunck GmbH - */ - -#ifndef LINUX_ADS1015_H -#define LINUX_ADS1015_H - -#define ADS1015_CHANNELS 8 - -struct ads1015_channel_data { - bool enabled; - unsigned int pga; - unsigned int data_rate; -}; - -struct ads1015_platform_data { - struct ads1015_channel_data channel_data[ADS1015_CHANNELS]; -}; - -#endif /* LINUX_ADS1015_H */ -- cgit v1.2.3 From 3cce2c6fa70c768e516bff011d77db72e2f38a15 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Mon, 2 Dec 2019 18:21:32 +0200 Subject: interconnect: Add a common helper for removing all nodes The removal of all nodes from a provider seem to be a common functionality for all existing users and it would make sense to factor out this into a a common helper function. Suggested-by: Dmitry Osipenko Reviewed-by: Bjorn Andersson Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index b16f9effa555..31440c921216 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -98,6 +98,7 @@ int icc_link_create(struct icc_node *node, const int dst_id); int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); 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); @@ -130,6 +131,11 @@ void icc_node_del(struct icc_node *node) { } +static inline int icc_nodes_remove(struct icc_provider *provider) +{ + return -ENOTSUPP; +} + static inline int icc_provider_add(struct icc_provider *provider) { return -ENOTSUPP; -- cgit v1.2.3 From 3172e4d276315afa82c12b14c8dd0db526c7aff1 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Thu, 28 Nov 2019 15:48:38 +0200 Subject: interconnect: Add a common standard aggregate function Currently there is one very standard aggregation method that is used by several drivers. Let's add this as a common function, so that drivers could just point to it, instead of copy/pasting code. Suggested-by: Evan Green Reviewed-by: Brian Masney Reviewed-by: Bjorn Andersson Reviewed-by: Evan Green Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 31440c921216..0c494534b4d3 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -92,6 +92,8 @@ struct icc_node { #if IS_ENABLED(CONFIG_INTERCONNECT) +int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, + u32 peak_bw, u32 *agg_avg, u32 *agg_peak); struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); int icc_link_create(struct icc_node *node, const int dst_id); @@ -104,6 +106,12 @@ int icc_provider_del(struct icc_provider *provider); #else +static inline int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, + u32 peak_bw, u32 *agg_avg, u32 *agg_peak) +{ + return -ENOTSUPP; +} + static inline struct icc_node *icc_node_create(int id) { return ERR_PTR(-ENOTSUPP); -- cgit v1.2.3 From cf901a1c5dd8df18d2308188d094a01e1e7c2143 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Dec 2019 20:32:59 +0100 Subject: device.h: move devtmpfs prototypes out of the file The devtmpfs functions do not need to be in device.h as only the driver core uses them, so move them to the private .h file for the driver core. Cc: "Rafael J. Wysocki" Cc: Suzuki K Poulose Cc: Saravana Kannan Cc: Heikki Krogerus Link: https://lore.kernel.org/r/20191209193303.1694546-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 96ff76731e93..ba4c24f9cd8b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1664,12 +1664,8 @@ extern void put_device(struct device *dev); extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS -extern int devtmpfs_create_node(struct device *dev); -extern int devtmpfs_delete_node(struct device *dev); extern int devtmpfs_mount(void); #else -static inline int devtmpfs_create_node(struct device *dev) { return 0; } -static inline int devtmpfs_delete_node(struct device *dev) { return 0; } static inline int devtmpfs_mount(void) { return 0; } #endif -- cgit v1.2.3 From af628aae8640c268938a0c9344b4ec0d102c0a0a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Dec 2019 20:33:00 +0100 Subject: device.h: move dev_printk()-like functions to dev_printk.h device.h has everything and the kitchen sink when it comes to struct device things, so split out the printk-specific things to a separate .h file to make things easier to maintain and manage over time. Cc: Suzuki K Poulose Cc: "Rafael J. Wysocki" Cc: Saravana Kannan Cc: Heikki Krogerus Link: https://lore.kernel.org/r/20191209193303.1694546-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/dev_printk.h | 235 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/device.h | 217 +---------------------------------------- 2 files changed, 236 insertions(+), 216 deletions(-) create mode 100644 include/linux/dev_printk.h (limited to 'include/linux') diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h new file mode 100644 index 000000000000..5aad06b4ca7b --- /dev/null +++ b/include/linux/dev_printk.h @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * dev_printk.h - printk messages helpers for devices + * + * Copyright (c) 2001-2003 Patrick Mochel + * Copyright (c) 2004-2009 Greg Kroah-Hartman + * Copyright (c) 2008-2009 Novell Inc. + * + */ + +#ifndef _DEVICE_PRINTK_H_ +#define _DEVICE_PRINTK_H_ + +#include +#include +#include + +#ifndef dev_fmt +#define dev_fmt(fmt) fmt +#endif + +struct device; + +#ifdef CONFIG_PRINTK + +__printf(3, 0) __cold +int dev_vprintk_emit(int level, const struct device *dev, + const char *fmt, va_list args); +__printf(3, 4) __cold +int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); + +__printf(3, 4) __cold +void dev_printk(const char *level, const struct device *dev, + const char *fmt, ...); +__printf(2, 3) __cold +void _dev_emerg(const struct device *dev, const char *fmt, ...); +__printf(2, 3) __cold +void _dev_alert(const struct device *dev, const char *fmt, ...); +__printf(2, 3) __cold +void _dev_crit(const struct device *dev, const char *fmt, ...); +__printf(2, 3) __cold +void _dev_err(const struct device *dev, const char *fmt, ...); +__printf(2, 3) __cold +void _dev_warn(const struct device *dev, const char *fmt, ...); +__printf(2, 3) __cold +void _dev_notice(const struct device *dev, const char *fmt, ...); +__printf(2, 3) __cold +void _dev_info(const struct device *dev, const char *fmt, ...); + +#else + +static inline __printf(3, 0) +int dev_vprintk_emit(int level, const struct device *dev, + const char *fmt, va_list args) +{ return 0; } +static inline __printf(3, 4) +int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...) +{ return 0; } + +static inline void __dev_printk(const char *level, const struct device *dev, + struct va_format *vaf) +{} +static inline __printf(3, 4) +void dev_printk(const char *level, const struct device *dev, + const char *fmt, ...) +{} + +static inline __printf(2, 3) +void _dev_emerg(const struct device *dev, const char *fmt, ...) +{} +static inline __printf(2, 3) +void _dev_crit(const struct device *dev, const char *fmt, ...) +{} +static inline __printf(2, 3) +void _dev_alert(const struct device *dev, const char *fmt, ...) +{} +static inline __printf(2, 3) +void _dev_err(const struct device *dev, const char *fmt, ...) +{} +static inline __printf(2, 3) +void _dev_warn(const struct device *dev, const char *fmt, ...) +{} +static inline __printf(2, 3) +void _dev_notice(const struct device *dev, const char *fmt, ...) +{} +static inline __printf(2, 3) +void _dev_info(const struct device *dev, const char *fmt, ...) +{} + +#endif + +/* + * #defines for all the dev_ macros to prefix with whatever + * possible use of #define dev_fmt(fmt) ... + */ + +#define dev_emerg(dev, fmt, ...) \ + _dev_emerg(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_crit(dev, fmt, ...) \ + _dev_crit(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_alert(dev, fmt, ...) \ + _dev_alert(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_err(dev, fmt, ...) \ + _dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_warn(dev, fmt, ...) \ + _dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_notice(dev, fmt, ...) \ + _dev_notice(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_info(dev, fmt, ...) \ + _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__) + +#if defined(CONFIG_DYNAMIC_DEBUG) +#define dev_dbg(dev, fmt, ...) \ + dynamic_dev_dbg(dev, dev_fmt(fmt), ##__VA_ARGS__) +#elif defined(DEBUG) +#define dev_dbg(dev, fmt, ...) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) +#else +#define dev_dbg(dev, fmt, ...) \ +({ \ + if (0) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ +}) +#endif + +#ifdef CONFIG_PRINTK +#define dev_level_once(dev_level, dev, fmt, ...) \ +do { \ + static bool __print_once __read_mostly; \ + \ + if (!__print_once) { \ + __print_once = true; \ + dev_level(dev, fmt, ##__VA_ARGS__); \ + } \ +} while (0) +#else +#define dev_level_once(dev_level, dev, fmt, ...) \ +do { \ + if (0) \ + dev_level(dev, fmt, ##__VA_ARGS__); \ +} while (0) +#endif + +#define dev_emerg_once(dev, fmt, ...) \ + dev_level_once(dev_emerg, dev, fmt, ##__VA_ARGS__) +#define dev_alert_once(dev, fmt, ...) \ + dev_level_once(dev_alert, dev, fmt, ##__VA_ARGS__) +#define dev_crit_once(dev, fmt, ...) \ + dev_level_once(dev_crit, dev, fmt, ##__VA_ARGS__) +#define dev_err_once(dev, fmt, ...) \ + dev_level_once(dev_err, dev, fmt, ##__VA_ARGS__) +#define dev_warn_once(dev, fmt, ...) \ + dev_level_once(dev_warn, dev, fmt, ##__VA_ARGS__) +#define dev_notice_once(dev, fmt, ...) \ + dev_level_once(dev_notice, dev, fmt, ##__VA_ARGS__) +#define dev_info_once(dev, fmt, ...) \ + dev_level_once(dev_info, dev, fmt, ##__VA_ARGS__) +#define dev_dbg_once(dev, fmt, ...) \ + dev_level_once(dev_dbg, dev, fmt, ##__VA_ARGS__) + +#define dev_level_ratelimited(dev_level, dev, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + dev_level(dev, fmt, ##__VA_ARGS__); \ +} while (0) + +#define dev_emerg_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_emerg, dev, fmt, ##__VA_ARGS__) +#define dev_alert_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_alert, dev, fmt, ##__VA_ARGS__) +#define dev_crit_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_crit, dev, fmt, ##__VA_ARGS__) +#define dev_err_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_err, dev, fmt, ##__VA_ARGS__) +#define dev_warn_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_warn, dev, fmt, ##__VA_ARGS__) +#define dev_notice_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__) +#define dev_info_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__) +#if defined(CONFIG_DYNAMIC_DEBUG) +/* descriptor check is first to prevent flooding with "callbacks suppressed" */ +#define dev_dbg_ratelimited(dev, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ + __ratelimit(&_rs)) \ + __dynamic_dev_dbg(&descriptor, dev, dev_fmt(fmt), \ + ##__VA_ARGS__); \ +} while (0) +#elif defined(DEBUG) +#define dev_dbg_ratelimited(dev, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ +} while (0) +#else +#define dev_dbg_ratelimited(dev, fmt, ...) \ +do { \ + if (0) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ +} while (0) +#endif + +#ifdef VERBOSE_DEBUG +#define dev_vdbg dev_dbg +#else +#define dev_vdbg(dev, fmt, ...) \ +({ \ + if (0) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ +}) +#endif + +/* + * dev_WARN*() acts like dev_printk(), but with the key difference of + * using WARN/WARN_ONCE to include file/line information and a backtrace. + */ +#define dev_WARN(dev, format, arg...) \ + WARN(1, "%s %s: " format, dev_driver_string(dev), dev_name(dev), ## arg); + +#define dev_WARN_ONCE(dev, condition, format, arg...) \ + WARN_ONCE(condition, "%s %s: " format, \ + dev_driver_string(dev), dev_name(dev), ## arg) + +#endif /* _DEVICE_PRINTK_H_ */ diff --git a/include/linux/device.h b/include/linux/device.h index ba4c24f9cd8b..758e7dccfcbb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -12,6 +12,7 @@ #ifndef _DEVICE_H_ #define _DEVICE_H_ +#include #include #include #include @@ -22,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -1683,221 +1683,6 @@ void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); -#ifndef dev_fmt -#define dev_fmt(fmt) fmt -#endif - -#ifdef CONFIG_PRINTK - -__printf(3, 0) __cold -int dev_vprintk_emit(int level, const struct device *dev, - const char *fmt, va_list args); -__printf(3, 4) __cold -int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); - -__printf(3, 4) __cold -void dev_printk(const char *level, const struct device *dev, - const char *fmt, ...); -__printf(2, 3) __cold -void _dev_emerg(const struct device *dev, const char *fmt, ...); -__printf(2, 3) __cold -void _dev_alert(const struct device *dev, const char *fmt, ...); -__printf(2, 3) __cold -void _dev_crit(const struct device *dev, const char *fmt, ...); -__printf(2, 3) __cold -void _dev_err(const struct device *dev, const char *fmt, ...); -__printf(2, 3) __cold -void _dev_warn(const struct device *dev, const char *fmt, ...); -__printf(2, 3) __cold -void _dev_notice(const struct device *dev, const char *fmt, ...); -__printf(2, 3) __cold -void _dev_info(const struct device *dev, const char *fmt, ...); - -#else - -static inline __printf(3, 0) -int dev_vprintk_emit(int level, const struct device *dev, - const char *fmt, va_list args) -{ return 0; } -static inline __printf(3, 4) -int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...) -{ return 0; } - -static inline void __dev_printk(const char *level, const struct device *dev, - struct va_format *vaf) -{} -static inline __printf(3, 4) -void dev_printk(const char *level, const struct device *dev, - const char *fmt, ...) -{} - -static inline __printf(2, 3) -void _dev_emerg(const struct device *dev, const char *fmt, ...) -{} -static inline __printf(2, 3) -void _dev_crit(const struct device *dev, const char *fmt, ...) -{} -static inline __printf(2, 3) -void _dev_alert(const struct device *dev, const char *fmt, ...) -{} -static inline __printf(2, 3) -void _dev_err(const struct device *dev, const char *fmt, ...) -{} -static inline __printf(2, 3) -void _dev_warn(const struct device *dev, const char *fmt, ...) -{} -static inline __printf(2, 3) -void _dev_notice(const struct device *dev, const char *fmt, ...) -{} -static inline __printf(2, 3) -void _dev_info(const struct device *dev, const char *fmt, ...) -{} - -#endif - -/* - * #defines for all the dev_ macros to prefix with whatever - * possible use of #define dev_fmt(fmt) ... - */ - -#define dev_emerg(dev, fmt, ...) \ - _dev_emerg(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_crit(dev, fmt, ...) \ - _dev_crit(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_alert(dev, fmt, ...) \ - _dev_alert(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_err(dev, fmt, ...) \ - _dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_warn(dev, fmt, ...) \ - _dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_notice(dev, fmt, ...) \ - _dev_notice(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_info(dev, fmt, ...) \ - _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__) - -#if defined(CONFIG_DYNAMIC_DEBUG) -#define dev_dbg(dev, fmt, ...) \ - dynamic_dev_dbg(dev, dev_fmt(fmt), ##__VA_ARGS__) -#elif defined(DEBUG) -#define dev_dbg(dev, fmt, ...) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) -#else -#define dev_dbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) -#endif - -#ifdef CONFIG_PRINTK -#define dev_level_once(dev_level, dev, fmt, ...) \ -do { \ - static bool __print_once __read_mostly; \ - \ - if (!__print_once) { \ - __print_once = true; \ - dev_level(dev, fmt, ##__VA_ARGS__); \ - } \ -} while (0) -#else -#define dev_level_once(dev_level, dev, fmt, ...) \ -do { \ - if (0) \ - dev_level(dev, fmt, ##__VA_ARGS__); \ -} while (0) -#endif - -#define dev_emerg_once(dev, fmt, ...) \ - dev_level_once(dev_emerg, dev, fmt, ##__VA_ARGS__) -#define dev_alert_once(dev, fmt, ...) \ - dev_level_once(dev_alert, dev, fmt, ##__VA_ARGS__) -#define dev_crit_once(dev, fmt, ...) \ - dev_level_once(dev_crit, dev, fmt, ##__VA_ARGS__) -#define dev_err_once(dev, fmt, ...) \ - dev_level_once(dev_err, dev, fmt, ##__VA_ARGS__) -#define dev_warn_once(dev, fmt, ...) \ - dev_level_once(dev_warn, dev, fmt, ##__VA_ARGS__) -#define dev_notice_once(dev, fmt, ...) \ - dev_level_once(dev_notice, dev, fmt, ##__VA_ARGS__) -#define dev_info_once(dev, fmt, ...) \ - dev_level_once(dev_info, dev, fmt, ##__VA_ARGS__) -#define dev_dbg_once(dev, fmt, ...) \ - dev_level_once(dev_dbg, dev, fmt, ##__VA_ARGS__) - -#define dev_level_ratelimited(dev_level, dev, fmt, ...) \ -do { \ - static DEFINE_RATELIMIT_STATE(_rs, \ - DEFAULT_RATELIMIT_INTERVAL, \ - DEFAULT_RATELIMIT_BURST); \ - if (__ratelimit(&_rs)) \ - dev_level(dev, fmt, ##__VA_ARGS__); \ -} while (0) - -#define dev_emerg_ratelimited(dev, fmt, ...) \ - dev_level_ratelimited(dev_emerg, dev, fmt, ##__VA_ARGS__) -#define dev_alert_ratelimited(dev, fmt, ...) \ - dev_level_ratelimited(dev_alert, dev, fmt, ##__VA_ARGS__) -#define dev_crit_ratelimited(dev, fmt, ...) \ - dev_level_ratelimited(dev_crit, dev, fmt, ##__VA_ARGS__) -#define dev_err_ratelimited(dev, fmt, ...) \ - dev_level_ratelimited(dev_err, dev, fmt, ##__VA_ARGS__) -#define dev_warn_ratelimited(dev, fmt, ...) \ - dev_level_ratelimited(dev_warn, dev, fmt, ##__VA_ARGS__) -#define dev_notice_ratelimited(dev, fmt, ...) \ - dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__) -#define dev_info_ratelimited(dev, fmt, ...) \ - dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) -/* descriptor check is first to prevent flooding with "callbacks suppressed" */ -#define dev_dbg_ratelimited(dev, fmt, ...) \ -do { \ - static DEFINE_RATELIMIT_STATE(_rs, \ - DEFAULT_RATELIMIT_INTERVAL, \ - DEFAULT_RATELIMIT_BURST); \ - DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ - __ratelimit(&_rs)) \ - __dynamic_dev_dbg(&descriptor, dev, dev_fmt(fmt), \ - ##__VA_ARGS__); \ -} while (0) -#elif defined(DEBUG) -#define dev_dbg_ratelimited(dev, fmt, ...) \ -do { \ - static DEFINE_RATELIMIT_STATE(_rs, \ - DEFAULT_RATELIMIT_INTERVAL, \ - DEFAULT_RATELIMIT_BURST); \ - if (__ratelimit(&_rs)) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -} while (0) -#else -#define dev_dbg_ratelimited(dev, fmt, ...) \ -do { \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -} while (0) -#endif - -#ifdef VERBOSE_DEBUG -#define dev_vdbg dev_dbg -#else -#define dev_vdbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) -#endif - -/* - * dev_WARN*() acts like dev_printk(), but with the key difference of - * using WARN/WARN_ONCE to include file/line information and a backtrace. - */ -#define dev_WARN(dev, format, arg...) \ - WARN(1, "%s %s: " format, dev_driver_string(dev), dev_name(dev), ## arg); - -#define dev_WARN_ONCE(dev, condition, format, arg...) \ - WARN_ONCE(condition, "%s %s: " format, \ - dev_driver_string(dev), dev_name(dev), ## arg) - /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From 5aee2bf2629d7db2619110f62b15cf742c116e0b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Dec 2019 20:33:01 +0100 Subject: device.h: move 'struct bus' stuff out to device/bus.h device.h has everything and the kitchen sink when it comes to struct device things, so split out the struct bus things things to a separate .h file to make things easier to maintain and manage over time. Cc: "Rafael J. Wysocki" Cc: Suzuki K Poulose Cc: Saravana Kannan Cc: Heikki Krogerus Link: https://lore.kernel.org/r/20191209193303.1694546-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 265 +---------------------------------------- include/linux/device/bus.h | 288 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 289 insertions(+), 264 deletions(-) create mode 100644 include/linux/device/bus.h (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 758e7dccfcbb..22fd0b91d0fa 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -26,6 +26,7 @@ #include #include #include +#include #include struct device; @@ -35,7 +36,6 @@ struct driver_private; struct module; struct class; struct subsys_private; -struct bus_type; struct device_node; struct fwnode_handle; struct iommu_ops; @@ -44,269 +44,6 @@ struct iommu_fwspec; struct dev_pin_info; struct iommu_param; -struct bus_attribute { - struct attribute attr; - ssize_t (*show)(struct bus_type *bus, char *buf); - ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); -}; - -#define BUS_ATTR_RW(_name) \ - struct bus_attribute bus_attr_##_name = __ATTR_RW(_name) -#define BUS_ATTR_RO(_name) \ - struct bus_attribute bus_attr_##_name = __ATTR_RO(_name) -#define BUS_ATTR_WO(_name) \ - struct bus_attribute bus_attr_##_name = __ATTR_WO(_name) - -extern int __must_check bus_create_file(struct bus_type *, - struct bus_attribute *); -extern void bus_remove_file(struct bus_type *, struct bus_attribute *); - -/** - * struct bus_type - The bus type of the device - * - * @name: The name of the bus. - * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). - * @dev_root: Default device to use as the parent. - * @bus_groups: Default attributes of the bus. - * @dev_groups: Default attributes of the devices on the bus. - * @drv_groups: Default attributes of the device drivers on the bus. - * @match: Called, perhaps multiple times, whenever a new device or driver - * is added for this bus. It should return a positive value if the - * given device can be handled by the given driver and zero - * otherwise. It may also return error code if determining that - * the driver supports the device is not possible. In case of - * -EPROBE_DEFER it will queue the device for deferred probing. - * @uevent: Called when a device is added, removed, or a few other things - * that generate uevents to add the environment variables. - * @probe: Called when a new device or driver add to this bus, and callback - * the specific driver's probe to initial the matched device. - * @sync_state: Called to sync device state to software state after all the - * state tracking consumers linked to this device (present at - * the time of late_initcall) have successfully bound to a - * driver. If the device has no consumers, this function will - * be called at late_initcall_sync level. If the device has - * consumers that are never bound to a driver, this function - * will never get called until they do. - * @remove: Called when a device removed from this bus. - * @shutdown: Called at shut-down time to quiesce the device. - * - * @online: Called to put the device back online (after offlining it). - * @offline: Called to put the device offline for hot-removal. May fail. - * - * @suspend: Called when a device on this bus wants to go to sleep mode. - * @resume: Called to bring a device on this bus out of sleep mode. - * @num_vf: Called to find out how many virtual functions a device on this - * bus supports. - * @dma_configure: Called to setup DMA configuration on a device on - * this bus. - * @pm: Power management operations of this bus, callback the specific - * device driver's pm-ops. - * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU - * driver implementations to a bus and allow the driver to do - * bus-specific setup - * @p: The private data of the driver core, only the driver core can - * touch this. - * @lock_key: Lock class key for use by the lock validator - * @need_parent_lock: When probing or removing a device on this bus, the - * device core should lock the device's parent. - * - * A bus is a channel between the processor and one or more devices. For the - * purposes of the device model, all devices are connected via a bus, even if - * it is an internal, virtual, "platform" bus. Buses can plug into each other. - * A USB controller is usually a PCI device, for example. The device model - * represents the actual connections between buses and the devices they control. - * A bus is represented by the bus_type structure. It contains the name, the - * default attributes, the bus' methods, PM operations, and the driver core's - * private data. - */ -struct bus_type { - const char *name; - const char *dev_name; - struct device *dev_root; - const struct attribute_group **bus_groups; - const struct attribute_group **dev_groups; - const struct attribute_group **drv_groups; - - int (*match)(struct device *dev, struct device_driver *drv); - int (*uevent)(struct device *dev, struct kobj_uevent_env *env); - int (*probe)(struct device *dev); - void (*sync_state)(struct device *dev); - int (*remove)(struct device *dev); - void (*shutdown)(struct device *dev); - - int (*online)(struct device *dev); - int (*offline)(struct device *dev); - - int (*suspend)(struct device *dev, pm_message_t state); - int (*resume)(struct device *dev); - - int (*num_vf)(struct device *dev); - - int (*dma_configure)(struct device *dev); - - const struct dev_pm_ops *pm; - - const struct iommu_ops *iommu_ops; - - struct subsys_private *p; - struct lock_class_key lock_key; - - bool need_parent_lock; -}; - -extern int __must_check bus_register(struct bus_type *bus); - -extern void bus_unregister(struct bus_type *bus); - -extern int __must_check bus_rescan_devices(struct bus_type *bus); - -/* iterator helpers for buses */ -struct subsys_dev_iter { - struct klist_iter ki; - const struct device_type *type; -}; -void subsys_dev_iter_init(struct subsys_dev_iter *iter, - struct bus_type *subsys, - struct device *start, - const struct device_type *type); -struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter); -void subsys_dev_iter_exit(struct subsys_dev_iter *iter); - -int device_match_name(struct device *dev, const void *name); -int device_match_of_node(struct device *dev, const void *np); -int device_match_fwnode(struct device *dev, const void *fwnode); -int device_match_devt(struct device *dev, const void *pdevt); -int device_match_acpi_dev(struct device *dev, const void *adev); -int device_match_any(struct device *dev, const void *unused); - -int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, - int (*fn)(struct device *dev, void *data)); -struct device *bus_find_device(struct bus_type *bus, struct device *start, - const void *data, - int (*match)(struct device *dev, const void *data)); -/** - * bus_find_device_by_name - device iterator for locating a particular device - * of a specific name. - * @bus: bus type - * @start: Device to begin with - * @name: name of the device to match - */ -static inline struct device *bus_find_device_by_name(struct bus_type *bus, - struct device *start, - const char *name) -{ - return bus_find_device(bus, start, name, device_match_name); -} - -/** - * bus_find_device_by_of_node : device iterator for locating a particular device - * matching the of_node. - * @bus: bus type - * @np: of_node of the device to match. - */ -static inline struct device * -bus_find_device_by_of_node(struct bus_type *bus, const struct device_node *np) -{ - return bus_find_device(bus, NULL, np, device_match_of_node); -} - -/** - * bus_find_device_by_fwnode : device iterator for locating a particular device - * matching the fwnode. - * @bus: bus type - * @fwnode: fwnode of the device to match. - */ -static inline struct device * -bus_find_device_by_fwnode(struct bus_type *bus, const struct fwnode_handle *fwnode) -{ - return bus_find_device(bus, NULL, fwnode, device_match_fwnode); -} - -/** - * bus_find_device_by_devt : device iterator for locating a particular device - * matching the device type. - * @bus: bus type - * @devt: device type of the device to match. - */ -static inline struct device *bus_find_device_by_devt(struct bus_type *bus, - dev_t devt) -{ - return bus_find_device(bus, NULL, &devt, device_match_devt); -} - -/** - * bus_find_next_device - Find the next device after a given device in a - * given bus. - * @bus: bus type - * @cur: device to begin the search with. - */ -static inline struct device * -bus_find_next_device(struct bus_type *bus,struct device *cur) -{ - return bus_find_device(bus, cur, NULL, device_match_any); -} - -#ifdef CONFIG_ACPI -struct acpi_device; - -/** - * bus_find_device_by_acpi_dev : device iterator for locating a particular device - * matching the ACPI COMPANION device. - * @bus: bus type - * @adev: ACPI COMPANION device to match. - */ -static inline struct device * -bus_find_device_by_acpi_dev(struct bus_type *bus, const struct acpi_device *adev) -{ - return bus_find_device(bus, NULL, adev, device_match_acpi_dev); -} -#else -static inline struct device * -bus_find_device_by_acpi_dev(struct bus_type *bus, const void *adev) -{ - return NULL; -} -#endif - -struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, - struct device *hint); -int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, - void *data, int (*fn)(struct device_driver *, void *)); -void bus_sort_breadthfirst(struct bus_type *bus, - int (*compare)(const struct device *a, - const struct device *b)); -/* - * Bus notifiers: Get notified of addition/removal of devices - * and binding/unbinding of drivers to devices. - * In the long run, it should be a replacement for the platform - * notify hooks. - */ -struct notifier_block; - -extern int bus_register_notifier(struct bus_type *bus, - struct notifier_block *nb); -extern int bus_unregister_notifier(struct bus_type *bus, - struct notifier_block *nb); - -/* All 4 notifers below get called with the target struct device * - * as an argument. Note that those functions are likely to be called - * with the device lock held in the core, so be careful. - */ -#define BUS_NOTIFY_ADD_DEVICE 0x00000001 /* device added */ -#define BUS_NOTIFY_DEL_DEVICE 0x00000002 /* device to be removed */ -#define BUS_NOTIFY_REMOVED_DEVICE 0x00000003 /* device removed */ -#define BUS_NOTIFY_BIND_DRIVER 0x00000004 /* driver about to be - bound */ -#define BUS_NOTIFY_BOUND_DRIVER 0x00000005 /* driver bound to device */ -#define BUS_NOTIFY_UNBIND_DRIVER 0x00000006 /* driver about to be - unbound */ -#define BUS_NOTIFY_UNBOUND_DRIVER 0x00000007 /* driver is unbound - from the device */ -#define BUS_NOTIFY_DRIVER_NOT_BOUND 0x00000008 /* driver fails to be bound */ - -extern struct kset *bus_get_kset(struct bus_type *bus); -extern struct klist *bus_get_device_klist(struct bus_type *bus); - /** * enum probe_type - device driver probe type to try * Device drivers may opt in for special handling of their diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h new file mode 100644 index 000000000000..1ea5e1d1545b --- /dev/null +++ b/include/linux/device/bus.h @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * bus.h - the bus-specific portions of the driver model + * + * Copyright (c) 2001-2003 Patrick Mochel + * Copyright (c) 2004-2009 Greg Kroah-Hartman + * Copyright (c) 2008-2009 Novell Inc. + * Copyright (c) 2012-2019 Greg Kroah-Hartman + * Copyright (c) 2012-2019 Linux Foundation + * + * See Documentation/driver-api/driver-model/ for more information. + */ + +#ifndef _DEVICE_BUS_H_ +#define _DEVICE_BUS_H_ + +#include +#include +#include + +struct device_driver; +struct fwnode_handle; + +/** + * struct bus_type - The bus type of the device + * + * @name: The name of the bus. + * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). + * @dev_root: Default device to use as the parent. + * @bus_groups: Default attributes of the bus. + * @dev_groups: Default attributes of the devices on the bus. + * @drv_groups: Default attributes of the device drivers on the bus. + * @match: Called, perhaps multiple times, whenever a new device or driver + * is added for this bus. It should return a positive value if the + * given device can be handled by the given driver and zero + * otherwise. It may also return error code if determining that + * the driver supports the device is not possible. In case of + * -EPROBE_DEFER it will queue the device for deferred probing. + * @uevent: Called when a device is added, removed, or a few other things + * that generate uevents to add the environment variables. + * @probe: Called when a new device or driver add to this bus, and callback + * the specific driver's probe to initial the matched device. + * @sync_state: Called to sync device state to software state after all the + * state tracking consumers linked to this device (present at + * the time of late_initcall) have successfully bound to a + * driver. If the device has no consumers, this function will + * be called at late_initcall_sync level. If the device has + * consumers that are never bound to a driver, this function + * will never get called until they do. + * @remove: Called when a device removed from this bus. + * @shutdown: Called at shut-down time to quiesce the device. + * + * @online: Called to put the device back online (after offlining it). + * @offline: Called to put the device offline for hot-removal. May fail. + * + * @suspend: Called when a device on this bus wants to go to sleep mode. + * @resume: Called to bring a device on this bus out of sleep mode. + * @num_vf: Called to find out how many virtual functions a device on this + * bus supports. + * @dma_configure: Called to setup DMA configuration on a device on + * this bus. + * @pm: Power management operations of this bus, callback the specific + * device driver's pm-ops. + * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU + * driver implementations to a bus and allow the driver to do + * bus-specific setup + * @p: The private data of the driver core, only the driver core can + * touch this. + * @lock_key: Lock class key for use by the lock validator + * @need_parent_lock: When probing or removing a device on this bus, the + * device core should lock the device's parent. + * + * A bus is a channel between the processor and one or more devices. For the + * purposes of the device model, all devices are connected via a bus, even if + * it is an internal, virtual, "platform" bus. Buses can plug into each other. + * A USB controller is usually a PCI device, for example. The device model + * represents the actual connections between buses and the devices they control. + * A bus is represented by the bus_type structure. It contains the name, the + * default attributes, the bus' methods, PM operations, and the driver core's + * private data. + */ +struct bus_type { + const char *name; + const char *dev_name; + struct device *dev_root; + const struct attribute_group **bus_groups; + const struct attribute_group **dev_groups; + const struct attribute_group **drv_groups; + + int (*match)(struct device *dev, struct device_driver *drv); + int (*uevent)(struct device *dev, struct kobj_uevent_env *env); + int (*probe)(struct device *dev); + void (*sync_state)(struct device *dev); + int (*remove)(struct device *dev); + void (*shutdown)(struct device *dev); + + int (*online)(struct device *dev); + int (*offline)(struct device *dev); + + int (*suspend)(struct device *dev, pm_message_t state); + int (*resume)(struct device *dev); + + int (*num_vf)(struct device *dev); + + int (*dma_configure)(struct device *dev); + + const struct dev_pm_ops *pm; + + const struct iommu_ops *iommu_ops; + + struct subsys_private *p; + struct lock_class_key lock_key; + + bool need_parent_lock; +}; + +extern int __must_check bus_register(struct bus_type *bus); + +extern void bus_unregister(struct bus_type *bus); + +extern int __must_check bus_rescan_devices(struct bus_type *bus); + +struct bus_attribute { + struct attribute attr; + ssize_t (*show)(struct bus_type *bus, char *buf); + ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); +}; + +#define BUS_ATTR_RW(_name) \ + struct bus_attribute bus_attr_##_name = __ATTR_RW(_name) +#define BUS_ATTR_RO(_name) \ + struct bus_attribute bus_attr_##_name = __ATTR_RO(_name) +#define BUS_ATTR_WO(_name) \ + struct bus_attribute bus_attr_##_name = __ATTR_WO(_name) + +extern int __must_check bus_create_file(struct bus_type *, + struct bus_attribute *); +extern void bus_remove_file(struct bus_type *, struct bus_attribute *); + +/* Generic device matching functions that all busses can use to match with */ +int device_match_name(struct device *dev, const void *name); +int device_match_of_node(struct device *dev, const void *np); +int device_match_fwnode(struct device *dev, const void *fwnode); +int device_match_devt(struct device *dev, const void *pdevt); +int device_match_acpi_dev(struct device *dev, const void *adev); +int device_match_any(struct device *dev, const void *unused); + +/* iterator helpers for buses */ +struct subsys_dev_iter { + struct klist_iter ki; + const struct device_type *type; +}; +void subsys_dev_iter_init(struct subsys_dev_iter *iter, + struct bus_type *subsys, + struct device *start, + const struct device_type *type); +struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter); +void subsys_dev_iter_exit(struct subsys_dev_iter *iter); + +int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, + int (*fn)(struct device *dev, void *data)); +struct device *bus_find_device(struct bus_type *bus, struct device *start, + const void *data, + int (*match)(struct device *dev, const void *data)); +/** + * bus_find_device_by_name - device iterator for locating a particular device + * of a specific name. + * @bus: bus type + * @start: Device to begin with + * @name: name of the device to match + */ +static inline struct device *bus_find_device_by_name(struct bus_type *bus, + struct device *start, + const char *name) +{ + return bus_find_device(bus, start, name, device_match_name); +} + +/** + * bus_find_device_by_of_node : device iterator for locating a particular device + * matching the of_node. + * @bus: bus type + * @np: of_node of the device to match. + */ +static inline struct device * +bus_find_device_by_of_node(struct bus_type *bus, const struct device_node *np) +{ + return bus_find_device(bus, NULL, np, device_match_of_node); +} + +/** + * bus_find_device_by_fwnode : device iterator for locating a particular device + * matching the fwnode. + * @bus: bus type + * @fwnode: fwnode of the device to match. + */ +static inline struct device * +bus_find_device_by_fwnode(struct bus_type *bus, const struct fwnode_handle *fwnode) +{ + return bus_find_device(bus, NULL, fwnode, device_match_fwnode); +} + +/** + * bus_find_device_by_devt : device iterator for locating a particular device + * matching the device type. + * @bus: bus type + * @devt: device type of the device to match. + */ +static inline struct device *bus_find_device_by_devt(struct bus_type *bus, + dev_t devt) +{ + return bus_find_device(bus, NULL, &devt, device_match_devt); +} + +/** + * bus_find_next_device - Find the next device after a given device in a + * given bus. + * @bus: bus type + * @cur: device to begin the search with. + */ +static inline struct device * +bus_find_next_device(struct bus_type *bus,struct device *cur) +{ + return bus_find_device(bus, cur, NULL, device_match_any); +} + +#ifdef CONFIG_ACPI +struct acpi_device; + +/** + * bus_find_device_by_acpi_dev : device iterator for locating a particular device + * matching the ACPI COMPANION device. + * @bus: bus type + * @adev: ACPI COMPANION device to match. + */ +static inline struct device * +bus_find_device_by_acpi_dev(struct bus_type *bus, const struct acpi_device *adev) +{ + return bus_find_device(bus, NULL, adev, device_match_acpi_dev); +} +#else +static inline struct device * +bus_find_device_by_acpi_dev(struct bus_type *bus, const void *adev) +{ + return NULL; +} +#endif + +struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, + struct device *hint); +int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, + void *data, int (*fn)(struct device_driver *, void *)); +void bus_sort_breadthfirst(struct bus_type *bus, + int (*compare)(const struct device *a, + const struct device *b)); +/* + * Bus notifiers: Get notified of addition/removal of devices + * and binding/unbinding of drivers to devices. + * In the long run, it should be a replacement for the platform + * notify hooks. + */ +struct notifier_block; + +extern int bus_register_notifier(struct bus_type *bus, + struct notifier_block *nb); +extern int bus_unregister_notifier(struct bus_type *bus, + struct notifier_block *nb); + +/* All 4 notifers below get called with the target struct device * + * as an argument. Note that those functions are likely to be called + * with the device lock held in the core, so be careful. + */ +#define BUS_NOTIFY_ADD_DEVICE 0x00000001 /* device added */ +#define BUS_NOTIFY_DEL_DEVICE 0x00000002 /* device to be removed */ +#define BUS_NOTIFY_REMOVED_DEVICE 0x00000003 /* device removed */ +#define BUS_NOTIFY_BIND_DRIVER 0x00000004 /* driver about to be + bound */ +#define BUS_NOTIFY_BOUND_DRIVER 0x00000005 /* driver bound to device */ +#define BUS_NOTIFY_UNBIND_DRIVER 0x00000006 /* driver about to be + unbound */ +#define BUS_NOTIFY_UNBOUND_DRIVER 0x00000007 /* driver is unbound + from the device */ +#define BUS_NOTIFY_DRIVER_NOT_BOUND 0x00000008 /* driver fails to be bound */ + +extern struct kset *bus_get_kset(struct bus_type *bus); +extern struct klist *bus_get_device_klist(struct bus_type *bus); + +#endif -- cgit v1.2.3 From a8ae608529ab1b71a3830895f98a107be90fed48 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Dec 2019 20:33:02 +0100 Subject: device.h: move 'struct class' stuff out to device/class.h device.h has everything and the kitchen sink when it comes to struct device things, so split out the struct class things things to a separate .h file to make things easier to maintain and manage over time. Cc: "Rafael J. Wysocki" Cc: Suzuki K Poulose Cc: Saravana Kannan Cc: Heikki Krogerus Link: https://lore.kernel.org/r/20191209193303.1694546-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 241 +-------------------------------------- include/linux/device/class.h | 266 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 267 insertions(+), 240 deletions(-) create mode 100644 include/linux/device/class.h (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22fd0b91d0fa..4c261fbd7053 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -27,6 +27,7 @@ #include #include #include +#include #include struct device; @@ -294,246 +295,6 @@ int subsys_system_register(struct bus_type *subsys, int subsys_virtual_register(struct bus_type *subsys, const struct attribute_group **groups); -/** - * struct class - device classes - * @name: Name of the class. - * @owner: The module owner. - * @class_groups: Default attributes of this class. - * @dev_groups: Default attributes of the devices that belong to the class. - * @dev_kobj: The kobject that represents this class and links it into the hierarchy. - * @dev_uevent: Called when a device is added, removed from this class, or a - * few other things that generate uevents to add the environment - * variables. - * @devnode: Callback to provide the devtmpfs. - * @class_release: Called to release this class. - * @dev_release: Called to release the device. - * @shutdown_pre: Called at shut-down time before driver shutdown. - * @ns_type: Callbacks so sysfs can detemine namespaces. - * @namespace: Namespace of the device belongs to this class. - * @get_ownership: Allows class to specify uid/gid of the sysfs directories - * for the devices belonging to the class. Usually tied to - * device's namespace. - * @pm: The default device power management operations of this class. - * @p: The private data of the driver core, no one other than the - * driver core can touch this. - * - * A class is a higher-level view of a device that abstracts out low-level - * implementation details. Drivers may see a SCSI disk or an ATA disk, but, - * at the class level, they are all simply disks. Classes allow user space - * to work with devices based on what they do, rather than how they are - * connected or how they work. - */ -struct class { - const char *name; - struct module *owner; - - const struct attribute_group **class_groups; - const struct attribute_group **dev_groups; - struct kobject *dev_kobj; - - int (*dev_uevent)(struct device *dev, struct kobj_uevent_env *env); - char *(*devnode)(struct device *dev, umode_t *mode); - - void (*class_release)(struct class *class); - void (*dev_release)(struct device *dev); - - int (*shutdown_pre)(struct device *dev); - - const struct kobj_ns_type_operations *ns_type; - const void *(*namespace)(struct device *dev); - - void (*get_ownership)(struct device *dev, kuid_t *uid, kgid_t *gid); - - const struct dev_pm_ops *pm; - - struct subsys_private *p; -}; - -struct class_dev_iter { - struct klist_iter ki; - const struct device_type *type; -}; - -extern struct kobject *sysfs_dev_block_kobj; -extern struct kobject *sysfs_dev_char_kobj; -extern int __must_check __class_register(struct class *class, - struct lock_class_key *key); -extern void class_unregister(struct class *class); - -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, &__key); \ -}) - -struct class_compat; -struct class_compat *class_compat_register(const char *name); -void class_compat_unregister(struct class_compat *cls); -int class_compat_create_link(struct class_compat *cls, struct device *dev, - struct device *device_link); -void class_compat_remove_link(struct class_compat *cls, struct device *dev, - struct device *device_link); - -extern void class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, - const struct device_type *type); -extern struct device *class_dev_iter_next(struct class_dev_iter *iter); -extern void class_dev_iter_exit(struct class_dev_iter *iter); - -extern int class_for_each_device(struct class *class, struct device *start, - void *data, - int (*fn)(struct device *dev, void *data)); -extern struct device *class_find_device(struct class *class, - struct device *start, const void *data, - int (*match)(struct device *, const void *)); - -/** - * class_find_device_by_name - device iterator for locating a particular device - * of a specific name. - * @class: class type - * @name: name of the device to match - */ -static inline struct device *class_find_device_by_name(struct class *class, - const char *name) -{ - return class_find_device(class, NULL, name, device_match_name); -} - -/** - * class_find_device_by_of_node : device iterator for locating a particular device - * matching the of_node. - * @class: class type - * @np: of_node of the device to match. - */ -static inline struct device * -class_find_device_by_of_node(struct class *class, const struct device_node *np) -{ - return class_find_device(class, NULL, np, device_match_of_node); -} - -/** - * class_find_device_by_fwnode : device iterator for locating a particular device - * matching the fwnode. - * @class: class type - * @fwnode: fwnode of the device to match. - */ -static inline struct device * -class_find_device_by_fwnode(struct class *class, - const struct fwnode_handle *fwnode) -{ - return class_find_device(class, NULL, fwnode, device_match_fwnode); -} - -/** - * class_find_device_by_devt : device iterator for locating a particular device - * matching the device type. - * @class: class type - * @devt: device type of the device to match. - */ -static inline struct device *class_find_device_by_devt(struct class *class, - dev_t devt) -{ - return class_find_device(class, NULL, &devt, device_match_devt); -} - -#ifdef CONFIG_ACPI -struct acpi_device; -/** - * class_find_device_by_acpi_dev : device iterator for locating a particular - * device matching the ACPI_COMPANION device. - * @class: class type - * @adev: ACPI_COMPANION device to match. - */ -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) -{ - return class_find_device(class, NULL, adev, device_match_acpi_dev); -} -#else -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const void *adev) -{ - return NULL; -} -#endif - -struct class_attribute { - struct attribute attr; - ssize_t (*show)(struct class *class, struct class_attribute *attr, - char *buf); - ssize_t (*store)(struct class *class, struct class_attribute *attr, - const char *buf, size_t count); -}; - -#define CLASS_ATTR_RW(_name) \ - struct class_attribute class_attr_##_name = __ATTR_RW(_name) -#define CLASS_ATTR_RO(_name) \ - struct class_attribute class_attr_##_name = __ATTR_RO(_name) -#define CLASS_ATTR_WO(_name) \ - struct class_attribute class_attr_##_name = __ATTR_WO(_name) - -extern int __must_check class_create_file_ns(struct class *class, - const struct class_attribute *attr, - const void *ns); -extern void class_remove_file_ns(struct class *class, - const struct class_attribute *attr, - const void *ns); - -static inline int __must_check class_create_file(struct class *class, - const struct class_attribute *attr) -{ - return class_create_file_ns(class, attr, NULL); -} - -static inline void class_remove_file(struct class *class, - const struct class_attribute *attr) -{ - return class_remove_file_ns(class, attr, NULL); -} - -/* Simple class attribute that is just a static string */ -struct class_attribute_string { - struct class_attribute attr; - char *str; -}; - -/* Currently read-only only */ -#define _CLASS_ATTR_STRING(_name, _mode, _str) \ - { __ATTR(_name, _mode, show_class_attr_string, NULL), _str } -#define CLASS_ATTR_STRING(_name, _mode, _str) \ - struct class_attribute_string class_attr_##_name = \ - _CLASS_ATTR_STRING(_name, _mode, _str) - -extern ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, - char *buf); - -struct class_interface { - struct list_head node; - struct class *class; - - int (*add_dev) (struct device *, struct class_interface *); - void (*remove_dev) (struct device *, struct class_interface *); -}; - -extern int __must_check class_interface_register(struct class_interface *); -extern void class_interface_unregister(struct class_interface *); - -extern struct class * __must_check __class_create(struct module *owner, - const char *name, - struct lock_class_key *key); -extern void class_destroy(struct class *cls); - -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ -#define class_create(owner, name) \ -({ \ - static struct lock_class_key __key; \ - __class_create(owner, name, &__key); \ -}) - /* * The type of device, "struct device" is embedded in. A class * or bus can contain devices of different types diff --git a/include/linux/device/class.h b/include/linux/device/class.h new file mode 100644 index 000000000000..e8d470c457d1 --- /dev/null +++ b/include/linux/device/class.h @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The class-specific portions of the driver model + * + * Copyright (c) 2001-2003 Patrick Mochel + * Copyright (c) 2004-2009 Greg Kroah-Hartman + * Copyright (c) 2008-2009 Novell Inc. + * Copyright (c) 2012-2019 Greg Kroah-Hartman + * Copyright (c) 2012-2019 Linux Foundation + * + * See Documentation/driver-api/driver-model/ for more information. + */ + +#ifndef _DEVICE_CLASS_H_ +#define _DEVICE_CLASS_H_ + +#include +#include +#include +#include + +struct device; +struct fwnode_handle; + +/** + * struct class - device classes + * @name: Name of the class. + * @owner: The module owner. + * @class_groups: Default attributes of this class. + * @dev_groups: Default attributes of the devices that belong to the class. + * @dev_kobj: The kobject that represents this class and links it into the hierarchy. + * @dev_uevent: Called when a device is added, removed from this class, or a + * few other things that generate uevents to add the environment + * variables. + * @devnode: Callback to provide the devtmpfs. + * @class_release: Called to release this class. + * @dev_release: Called to release the device. + * @shutdown_pre: Called at shut-down time before driver shutdown. + * @ns_type: Callbacks so sysfs can detemine namespaces. + * @namespace: Namespace of the device belongs to this class. + * @get_ownership: Allows class to specify uid/gid of the sysfs directories + * for the devices belonging to the class. Usually tied to + * device's namespace. + * @pm: The default device power management operations of this class. + * @p: The private data of the driver core, no one other than the + * driver core can touch this. + * + * A class is a higher-level view of a device that abstracts out low-level + * implementation details. Drivers may see a SCSI disk or an ATA disk, but, + * at the class level, they are all simply disks. Classes allow user space + * to work with devices based on what they do, rather than how they are + * connected or how they work. + */ +struct class { + const char *name; + struct module *owner; + + const struct attribute_group **class_groups; + const struct attribute_group **dev_groups; + struct kobject *dev_kobj; + + int (*dev_uevent)(struct device *dev, struct kobj_uevent_env *env); + char *(*devnode)(struct device *dev, umode_t *mode); + + void (*class_release)(struct class *class); + void (*dev_release)(struct device *dev); + + int (*shutdown_pre)(struct device *dev); + + const struct kobj_ns_type_operations *ns_type; + const void *(*namespace)(struct device *dev); + + void (*get_ownership)(struct device *dev, kuid_t *uid, kgid_t *gid); + + const struct dev_pm_ops *pm; + + struct subsys_private *p; +}; + +struct class_dev_iter { + struct klist_iter ki; + const struct device_type *type; +}; + +extern struct kobject *sysfs_dev_block_kobj; +extern struct kobject *sysfs_dev_char_kobj; +extern int __must_check __class_register(struct class *class, + struct lock_class_key *key); +extern void class_unregister(struct class *class); + +/* This is a #define to keep the compiler from merging different + * instances of the __key variable */ +#define class_register(class) \ +({ \ + static struct lock_class_key __key; \ + __class_register(class, &__key); \ +}) + +struct class_compat; +struct class_compat *class_compat_register(const char *name); +void class_compat_unregister(struct class_compat *cls); +int class_compat_create_link(struct class_compat *cls, struct device *dev, + struct device *device_link); +void class_compat_remove_link(struct class_compat *cls, struct device *dev, + struct device *device_link); + +extern void class_dev_iter_init(struct class_dev_iter *iter, + struct class *class, + struct device *start, + const struct device_type *type); +extern struct device *class_dev_iter_next(struct class_dev_iter *iter); +extern void class_dev_iter_exit(struct class_dev_iter *iter); + +extern int class_for_each_device(struct class *class, struct device *start, + void *data, + int (*fn)(struct device *dev, void *data)); +extern struct device *class_find_device(struct class *class, + struct device *start, const void *data, + int (*match)(struct device *, const void *)); + +/** + * class_find_device_by_name - device iterator for locating a particular device + * of a specific name. + * @class: class type + * @name: name of the device to match + */ +static inline struct device *class_find_device_by_name(struct class *class, + const char *name) +{ + return class_find_device(class, NULL, name, device_match_name); +} + +/** + * class_find_device_by_of_node : device iterator for locating a particular device + * matching the of_node. + * @class: class type + * @np: of_node of the device to match. + */ +static inline struct device * +class_find_device_by_of_node(struct class *class, const struct device_node *np) +{ + return class_find_device(class, NULL, np, device_match_of_node); +} + +/** + * class_find_device_by_fwnode : device iterator for locating a particular device + * matching the fwnode. + * @class: class type + * @fwnode: fwnode of the device to match. + */ +static inline struct device * +class_find_device_by_fwnode(struct class *class, + const struct fwnode_handle *fwnode) +{ + return class_find_device(class, NULL, fwnode, device_match_fwnode); +} + +/** + * class_find_device_by_devt : device iterator for locating a particular device + * matching the device type. + * @class: class type + * @devt: device type of the device to match. + */ +static inline struct device *class_find_device_by_devt(struct class *class, + dev_t devt) +{ + return class_find_device(class, NULL, &devt, device_match_devt); +} + +#ifdef CONFIG_ACPI +struct acpi_device; +/** + * class_find_device_by_acpi_dev : device iterator for locating a particular + * device matching the ACPI_COMPANION device. + * @class: class type + * @adev: ACPI_COMPANION device to match. + */ +static inline struct device * +class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) +{ + return class_find_device(class, NULL, adev, device_match_acpi_dev); +} +#else +static inline struct device * +class_find_device_by_acpi_dev(struct class *class, const void *adev) +{ + return NULL; +} +#endif + +struct class_attribute { + struct attribute attr; + ssize_t (*show)(struct class *class, struct class_attribute *attr, + char *buf); + ssize_t (*store)(struct class *class, struct class_attribute *attr, + const char *buf, size_t count); +}; + +#define CLASS_ATTR_RW(_name) \ + struct class_attribute class_attr_##_name = __ATTR_RW(_name) +#define CLASS_ATTR_RO(_name) \ + struct class_attribute class_attr_##_name = __ATTR_RO(_name) +#define CLASS_ATTR_WO(_name) \ + struct class_attribute class_attr_##_name = __ATTR_WO(_name) + +extern int __must_check class_create_file_ns(struct class *class, + const struct class_attribute *attr, + const void *ns); +extern void class_remove_file_ns(struct class *class, + const struct class_attribute *attr, + const void *ns); + +static inline int __must_check class_create_file(struct class *class, + const struct class_attribute *attr) +{ + return class_create_file_ns(class, attr, NULL); +} + +static inline void class_remove_file(struct class *class, + const struct class_attribute *attr) +{ + return class_remove_file_ns(class, attr, NULL); +} + +/* Simple class attribute that is just a static string */ +struct class_attribute_string { + struct class_attribute attr; + char *str; +}; + +/* Currently read-only only */ +#define _CLASS_ATTR_STRING(_name, _mode, _str) \ + { __ATTR(_name, _mode, show_class_attr_string, NULL), _str } +#define CLASS_ATTR_STRING(_name, _mode, _str) \ + struct class_attribute_string class_attr_##_name = \ + _CLASS_ATTR_STRING(_name, _mode, _str) + +extern ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, + char *buf); + +struct class_interface { + struct list_head node; + struct class *class; + + int (*add_dev) (struct device *, struct class_interface *); + void (*remove_dev) (struct device *, struct class_interface *); +}; + +extern int __must_check class_interface_register(struct class_interface *); +extern void class_interface_unregister(struct class_interface *); + +extern struct class * __must_check __class_create(struct module *owner, + const char *name, + struct lock_class_key *key); +extern void class_destroy(struct class *cls); + +/* This is a #define to keep the compiler from merging different + * instances of the __key variable */ +#define class_create(owner, name) \ +({ \ + static struct lock_class_key __key; \ + __class_create(owner, name, &__key); \ +}) + + +#endif /* _DEVICE_CLASS_H_ */ -- cgit v1.2.3 From 4c002c978b7f2f2306d53de051c054504af920a9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Dec 2019 20:33:03 +0100 Subject: device.h: move 'struct driver' stuff out to device/driver.h device.h has everything and the kitchen sink when it comes to struct device things, so split out the struct driver things things to a separate .h file to make things easier to maintain and manage over time. Cc: "Rafael J. Wysocki" Cc: Suzuki K Poulose Cc: Saravana Kannan Cc: Heikki Krogerus Link: https://lore.kernel.org/r/20191209193303.1694546-7-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 272 +-------------------------------------- include/linux/device/driver.h | 292 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 293 insertions(+), 271 deletions(-) create mode 100644 include/linux/device/driver.h (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 4c261fbd7053..0cd7c647c16c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -28,6 +28,7 @@ #include #include #include +#include #include struct device; @@ -45,227 +46,6 @@ struct iommu_fwspec; struct dev_pin_info; struct iommu_param; -/** - * enum probe_type - device driver probe type to try - * Device drivers may opt in for special handling of their - * respective probe routines. This tells the core what to - * expect and prefer. - * - * @PROBE_DEFAULT_STRATEGY: Used by drivers that work equally well - * whether probed synchronously or asynchronously. - * @PROBE_PREFER_ASYNCHRONOUS: Drivers for "slow" devices which - * probing order is not essential for booting the system may - * opt into executing their probes asynchronously. - * @PROBE_FORCE_SYNCHRONOUS: Use this to annotate drivers that need - * their probe routines to run synchronously with driver and - * device registration (with the exception of -EPROBE_DEFER - * handling - re-probing always ends up being done asynchronously). - * - * Note that the end goal is to switch the kernel to use asynchronous - * probing by default, so annotating drivers with - * %PROBE_PREFER_ASYNCHRONOUS is a temporary measure that allows us - * to speed up boot process while we are validating the rest of the - * drivers. - */ -enum probe_type { - PROBE_DEFAULT_STRATEGY, - PROBE_PREFER_ASYNCHRONOUS, - PROBE_FORCE_SYNCHRONOUS, -}; - -/** - * struct device_driver - The basic device driver structure - * @name: Name of the device driver. - * @bus: The bus which the device of this driver belongs to. - * @owner: The module owner. - * @mod_name: Used for built-in modules. - * @suppress_bind_attrs: Disables bind/unbind via sysfs. - * @probe_type: Type of the probe (synchronous or asynchronous) to use. - * @of_match_table: The open firmware table. - * @acpi_match_table: The ACPI match table. - * @probe: Called to query the existence of a specific device, - * whether this driver can work with it, and bind the driver - * to a specific device. - * @sync_state: Called to sync device state to software state after all the - * state tracking consumers linked to this device (present at - * the time of late_initcall) have successfully bound to a - * driver. If the device has no consumers, this function will - * be called at late_initcall_sync level. If the device has - * consumers that are never bound to a driver, this function - * will never get called until they do. - * @remove: Called when the device is removed from the system to - * unbind a device from this driver. - * @shutdown: Called at shut-down time to quiesce the device. - * @suspend: Called to put the device to sleep mode. Usually to a - * low power state. - * @resume: Called to bring a device from sleep mode. - * @groups: Default attributes that get created by the driver core - * automatically. - * @dev_groups: Additional attributes attached to device instance once the - * it is bound to the driver. - * @pm: Power management operations of the device which matched - * this driver. - * @coredump: Called when sysfs entry is written to. The device driver - * is expected to call the dev_coredump API resulting in a - * uevent. - * @p: Driver core's private data, no one other than the driver - * core can touch this. - * - * The device driver-model tracks all of the drivers known to the system. - * The main reason for this tracking is to enable the driver core to match - * up drivers with new devices. Once drivers are known objects within the - * system, however, a number of other things become possible. Device drivers - * can export information and configuration variables that are independent - * of any specific device. - */ -struct device_driver { - const char *name; - struct bus_type *bus; - - struct module *owner; - const char *mod_name; /* used for built-in modules */ - - bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ - enum probe_type probe_type; - - const struct of_device_id *of_match_table; - const struct acpi_device_id *acpi_match_table; - - int (*probe) (struct device *dev); - void (*sync_state)(struct device *dev); - int (*remove) (struct device *dev); - void (*shutdown) (struct device *dev); - int (*suspend) (struct device *dev, pm_message_t state); - int (*resume) (struct device *dev); - const struct attribute_group **groups; - const struct attribute_group **dev_groups; - - const struct dev_pm_ops *pm; - void (*coredump) (struct device *dev); - - struct driver_private *p; -}; - - -extern int __must_check driver_register(struct device_driver *drv); -extern void driver_unregister(struct device_driver *drv); - -extern struct device_driver *driver_find(const char *name, - struct bus_type *bus); -extern int driver_probe_done(void); -extern void wait_for_device_probe(void); - -/* sysfs interface for exporting driver attributes */ - -struct driver_attribute { - struct attribute attr; - ssize_t (*show)(struct device_driver *driver, char *buf); - ssize_t (*store)(struct device_driver *driver, const char *buf, - size_t count); -}; - -#define DRIVER_ATTR_RW(_name) \ - struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) -#define DRIVER_ATTR_RO(_name) \ - struct driver_attribute driver_attr_##_name = __ATTR_RO(_name) -#define DRIVER_ATTR_WO(_name) \ - struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) - -extern int __must_check driver_create_file(struct device_driver *driver, - const struct driver_attribute *attr); -extern void driver_remove_file(struct device_driver *driver, - const struct driver_attribute *attr); - -extern int __must_check driver_for_each_device(struct device_driver *drv, - struct device *start, - void *data, - int (*fn)(struct device *dev, - void *)); -struct device *driver_find_device(struct device_driver *drv, - struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)); - -/** - * driver_find_device_by_name - device iterator for locating a particular device - * of a specific name. - * @drv: the driver we're iterating - * @name: name of the device to match - */ -static inline struct device *driver_find_device_by_name(struct device_driver *drv, - const char *name) -{ - return driver_find_device(drv, NULL, name, device_match_name); -} - -/** - * driver_find_device_by_of_node- device iterator for locating a particular device - * by of_node pointer. - * @drv: the driver we're iterating - * @np: of_node pointer to match. - */ -static inline struct device * -driver_find_device_by_of_node(struct device_driver *drv, - const struct device_node *np) -{ - return driver_find_device(drv, NULL, np, device_match_of_node); -} - -/** - * driver_find_device_by_fwnode- device iterator for locating a particular device - * by fwnode pointer. - * @drv: the driver we're iterating - * @fwnode: fwnode pointer to match. - */ -static inline struct device * -driver_find_device_by_fwnode(struct device_driver *drv, - const struct fwnode_handle *fwnode) -{ - return driver_find_device(drv, NULL, fwnode, device_match_fwnode); -} - -/** - * driver_find_device_by_devt- device iterator for locating a particular device - * by devt. - * @drv: the driver we're iterating - * @devt: devt pointer to match. - */ -static inline struct device *driver_find_device_by_devt(struct device_driver *drv, - dev_t devt) -{ - return driver_find_device(drv, NULL, &devt, device_match_devt); -} - -static inline struct device *driver_find_next_device(struct device_driver *drv, - struct device *start) -{ - return driver_find_device(drv, start, NULL, device_match_any); -} - -#ifdef CONFIG_ACPI -/** - * driver_find_device_by_acpi_dev : device iterator for locating a particular - * device matching the ACPI_COMPANION device. - * @drv: the driver we're iterating - * @adev: ACPI_COMPANION device to match. - */ -static inline struct device * -driver_find_device_by_acpi_dev(struct device_driver *drv, - const struct acpi_device *adev) -{ - return driver_find_device(drv, NULL, adev, device_match_acpi_dev); -} -#else -static inline struct device * -driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev) -{ - return NULL; -} -#endif - -void driver_deferred_probe_add(struct device *dev); -int driver_deferred_probe_check_state(struct device *dev); -int driver_deferred_probe_check_state_continue(struct device *dev); - /** * struct subsys_interface - interfaces to device functions * @name: name of the device function @@ -1018,8 +798,6 @@ static inline struct device_node *dev_of_node(struct device *dev) return dev->of_node; } -void driver_init(void); - /* * High level routines for use by the bus drivers */ @@ -1193,52 +971,4 @@ extern long sysfs_deprecated; #define sysfs_deprecated 0 #endif -/** - * module_driver() - Helper macro for drivers that don't do anything - * special in module init/exit. This eliminates a lot of boilerplate. - * Each module may only use this macro once, and calling it replaces - * module_init() and module_exit(). - * - * @__driver: driver name - * @__register: register function for this driver type - * @__unregister: unregister function for this driver type - * @...: Additional arguments to be passed to __register and __unregister. - * - * Use this macro to construct bus specific macros for registering - * drivers, and do not use it on its own. - */ -#define module_driver(__driver, __register, __unregister, ...) \ -static int __init __driver##_init(void) \ -{ \ - return __register(&(__driver) , ##__VA_ARGS__); \ -} \ -module_init(__driver##_init); \ -static void __exit __driver##_exit(void) \ -{ \ - __unregister(&(__driver) , ##__VA_ARGS__); \ -} \ -module_exit(__driver##_exit); - -/** - * builtin_driver() - Helper macro for drivers that don't do anything - * special in init and have no exit. This eliminates some boilerplate. - * Each driver may only use this macro once, and calling it replaces - * device_initcall (or in some cases, the legacy __initcall). This is - * meant to be a direct parallel of module_driver() above but without - * the __exit stuff that is not used for builtin cases. - * - * @__driver: driver name - * @__register: register function for this driver type - * @...: Additional arguments to be passed to __register - * - * Use this macro to construct bus specific macros for registering - * drivers, and do not use it on its own. - */ -#define builtin_driver(__driver, __register, ...) \ -static int __init __driver##_init(void) \ -{ \ - return __register(&(__driver) , ##__VA_ARGS__); \ -} \ -device_initcall(__driver##_init); - #endif /* _DEVICE_H_ */ diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h new file mode 100644 index 000000000000..1188260f9a02 --- /dev/null +++ b/include/linux/device/driver.h @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The driver-specific portions of the driver model + * + * Copyright (c) 2001-2003 Patrick Mochel + * Copyright (c) 2004-2009 Greg Kroah-Hartman + * Copyright (c) 2008-2009 Novell Inc. + * Copyright (c) 2012-2019 Greg Kroah-Hartman + * Copyright (c) 2012-2019 Linux Foundation + * + * See Documentation/driver-api/driver-model/ for more information. + */ + +#ifndef _DEVICE_DRIVER_H_ +#define _DEVICE_DRIVER_H_ + +#include +#include +#include +#include + +/** + * enum probe_type - device driver probe type to try + * Device drivers may opt in for special handling of their + * respective probe routines. This tells the core what to + * expect and prefer. + * + * @PROBE_DEFAULT_STRATEGY: Used by drivers that work equally well + * whether probed synchronously or asynchronously. + * @PROBE_PREFER_ASYNCHRONOUS: Drivers for "slow" devices which + * probing order is not essential for booting the system may + * opt into executing their probes asynchronously. + * @PROBE_FORCE_SYNCHRONOUS: Use this to annotate drivers that need + * their probe routines to run synchronously with driver and + * device registration (with the exception of -EPROBE_DEFER + * handling - re-probing always ends up being done asynchronously). + * + * Note that the end goal is to switch the kernel to use asynchronous + * probing by default, so annotating drivers with + * %PROBE_PREFER_ASYNCHRONOUS is a temporary measure that allows us + * to speed up boot process while we are validating the rest of the + * drivers. + */ +enum probe_type { + PROBE_DEFAULT_STRATEGY, + PROBE_PREFER_ASYNCHRONOUS, + PROBE_FORCE_SYNCHRONOUS, +}; + +/** + * struct device_driver - The basic device driver structure + * @name: Name of the device driver. + * @bus: The bus which the device of this driver belongs to. + * @owner: The module owner. + * @mod_name: Used for built-in modules. + * @suppress_bind_attrs: Disables bind/unbind via sysfs. + * @probe_type: Type of the probe (synchronous or asynchronous) to use. + * @of_match_table: The open firmware table. + * @acpi_match_table: The ACPI match table. + * @probe: Called to query the existence of a specific device, + * whether this driver can work with it, and bind the driver + * to a specific device. + * @sync_state: Called to sync device state to software state after all the + * state tracking consumers linked to this device (present at + * the time of late_initcall) have successfully bound to a + * driver. If the device has no consumers, this function will + * be called at late_initcall_sync level. If the device has + * consumers that are never bound to a driver, this function + * will never get called until they do. + * @remove: Called when the device is removed from the system to + * unbind a device from this driver. + * @shutdown: Called at shut-down time to quiesce the device. + * @suspend: Called to put the device to sleep mode. Usually to a + * low power state. + * @resume: Called to bring a device from sleep mode. + * @groups: Default attributes that get created by the driver core + * automatically. + * @dev_groups: Additional attributes attached to device instance once the + * it is bound to the driver. + * @pm: Power management operations of the device which matched + * this driver. + * @coredump: Called when sysfs entry is written to. The device driver + * is expected to call the dev_coredump API resulting in a + * uevent. + * @p: Driver core's private data, no one other than the driver + * core can touch this. + * + * The device driver-model tracks all of the drivers known to the system. + * The main reason for this tracking is to enable the driver core to match + * up drivers with new devices. Once drivers are known objects within the + * system, however, a number of other things become possible. Device drivers + * can export information and configuration variables that are independent + * of any specific device. + */ +struct device_driver { + const char *name; + struct bus_type *bus; + + struct module *owner; + const char *mod_name; /* used for built-in modules */ + + bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ + enum probe_type probe_type; + + const struct of_device_id *of_match_table; + const struct acpi_device_id *acpi_match_table; + + int (*probe) (struct device *dev); + void (*sync_state)(struct device *dev); + int (*remove) (struct device *dev); + void (*shutdown) (struct device *dev); + int (*suspend) (struct device *dev, pm_message_t state); + int (*resume) (struct device *dev); + const struct attribute_group **groups; + const struct attribute_group **dev_groups; + + const struct dev_pm_ops *pm; + void (*coredump) (struct device *dev); + + struct driver_private *p; +}; + + +extern int __must_check driver_register(struct device_driver *drv); +extern void driver_unregister(struct device_driver *drv); + +extern struct device_driver *driver_find(const char *name, + struct bus_type *bus); +extern int driver_probe_done(void); +extern void wait_for_device_probe(void); + +/* sysfs interface for exporting driver attributes */ + +struct driver_attribute { + struct attribute attr; + ssize_t (*show)(struct device_driver *driver, char *buf); + ssize_t (*store)(struct device_driver *driver, const char *buf, + size_t count); +}; + +#define DRIVER_ATTR_RW(_name) \ + struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) +#define DRIVER_ATTR_RO(_name) \ + struct driver_attribute driver_attr_##_name = __ATTR_RO(_name) +#define DRIVER_ATTR_WO(_name) \ + struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) + +extern int __must_check driver_create_file(struct device_driver *driver, + const struct driver_attribute *attr); +extern void driver_remove_file(struct device_driver *driver, + const struct driver_attribute *attr); + +extern int __must_check driver_for_each_device(struct device_driver *drv, + struct device *start, + void *data, + int (*fn)(struct device *dev, + void *)); +struct device *driver_find_device(struct device_driver *drv, + struct device *start, const void *data, + int (*match)(struct device *dev, const void *data)); + +/** + * driver_find_device_by_name - device iterator for locating a particular device + * of a specific name. + * @drv: the driver we're iterating + * @name: name of the device to match + */ +static inline struct device *driver_find_device_by_name(struct device_driver *drv, + const char *name) +{ + return driver_find_device(drv, NULL, name, device_match_name); +} + +/** + * driver_find_device_by_of_node- device iterator for locating a particular device + * by of_node pointer. + * @drv: the driver we're iterating + * @np: of_node pointer to match. + */ +static inline struct device * +driver_find_device_by_of_node(struct device_driver *drv, + const struct device_node *np) +{ + return driver_find_device(drv, NULL, np, device_match_of_node); +} + +/** + * driver_find_device_by_fwnode- device iterator for locating a particular device + * by fwnode pointer. + * @drv: the driver we're iterating + * @fwnode: fwnode pointer to match. + */ +static inline struct device * +driver_find_device_by_fwnode(struct device_driver *drv, + const struct fwnode_handle *fwnode) +{ + return driver_find_device(drv, NULL, fwnode, device_match_fwnode); +} + +/** + * driver_find_device_by_devt- device iterator for locating a particular device + * by devt. + * @drv: the driver we're iterating + * @devt: devt pointer to match. + */ +static inline struct device *driver_find_device_by_devt(struct device_driver *drv, + dev_t devt) +{ + return driver_find_device(drv, NULL, &devt, device_match_devt); +} + +static inline struct device *driver_find_next_device(struct device_driver *drv, + struct device *start) +{ + return driver_find_device(drv, start, NULL, device_match_any); +} + +#ifdef CONFIG_ACPI +/** + * driver_find_device_by_acpi_dev : device iterator for locating a particular + * device matching the ACPI_COMPANION device. + * @drv: the driver we're iterating + * @adev: ACPI_COMPANION device to match. + */ +static inline struct device * +driver_find_device_by_acpi_dev(struct device_driver *drv, + const struct acpi_device *adev) +{ + return driver_find_device(drv, NULL, adev, device_match_acpi_dev); +} +#else +static inline struct device * +driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev) +{ + return NULL; +} +#endif + +void driver_deferred_probe_add(struct device *dev); +int driver_deferred_probe_check_state(struct device *dev); +int driver_deferred_probe_check_state_continue(struct device *dev); +void driver_init(void); + +/** + * module_driver() - Helper macro for drivers that don't do anything + * special in module init/exit. This eliminates a lot of boilerplate. + * Each module may only use this macro once, and calling it replaces + * module_init() and module_exit(). + * + * @__driver: driver name + * @__register: register function for this driver type + * @__unregister: unregister function for this driver type + * @...: Additional arguments to be passed to __register and __unregister. + * + * Use this macro to construct bus specific macros for registering + * drivers, and do not use it on its own. + */ +#define module_driver(__driver, __register, __unregister, ...) \ +static int __init __driver##_init(void) \ +{ \ + return __register(&(__driver) , ##__VA_ARGS__); \ +} \ +module_init(__driver##_init); \ +static void __exit __driver##_exit(void) \ +{ \ + __unregister(&(__driver) , ##__VA_ARGS__); \ +} \ +module_exit(__driver##_exit); + +/** + * builtin_driver() - Helper macro for drivers that don't do anything + * special in init and have no exit. This eliminates some boilerplate. + * Each driver may only use this macro once, and calling it replaces + * device_initcall (or in some cases, the legacy __initcall). This is + * meant to be a direct parallel of module_driver() above but without + * the __exit stuff that is not used for builtin cases. + * + * @__driver: driver name + * @__register: register function for this driver type + * @...: Additional arguments to be passed to __register + * + * Use this macro to construct bus specific macros for registering + * drivers, and do not use it on its own. + */ +#define builtin_driver(__driver, __register, ...) \ +static int __init __driver##_init(void) \ +{ \ + return __register(&(__driver) , ##__VA_ARGS__); \ +} \ +device_initcall(__driver##_init); + +#endif /* _DEVICE_DRIVER_H_ */ -- cgit v1.2.3 From ce2b617ce8cbb7ba7a956299061bbc784131333c Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Tue, 12 Nov 2019 12:35:59 +0100 Subject: export.h: reduce __ksymtab_strings string duplication by using "MS" section flags Commit c3a6cf19e695 ("export: avoid code duplication in include/linux/export.h") refactors export.h quite nicely, but introduces a slight increase in memory usage due to using the empty string "" instead of NULL to indicate that an exported symbol has no namespace. As mentioned in that commit, this meant an increase of 1 byte per exported symbol without a namespace. For example, if a kernel configuration has about 10k exported symbols, this would mean that the size of __ksymtab_strings would increase by roughly 10kB. We can alleviate this situation by utilizing the SHF_MERGE and SHF_STRING section flags. SHF_MERGE|SHF_STRING indicate to the linker that the data in the section are null-terminated strings that can be merged to eliminate duplication. More specifically, from the binutils documentation - "for sections with both M and S, a string which is a suffix of a larger string is considered a duplicate. Thus "def" will be merged with "abcdef"; A reference to the first "def" will be changed to a reference to "abcdef"+3". Thus, all the empty strings would be merged as well as any strings that can be merged according to the cited method above. For example, "memset" and "__memset" would be merged to just "__memset" in __ksymtab_strings. As of v5.4-rc5, the following statistics were gathered with x86 defconfig with approximately 10.7k exported symbols. Size of __ksymtab_strings in vmlinux: ------------------------------------- v5.4-rc5: 213834 bytes v5.4-rc5 with commit c3a6cf19e695: 224455 bytes v5.4-rc5 with this patch: 205759 bytes So, we already see memory savings of ~8kB compared to vanilla -rc5 and savings of nearly 18.7kB compared to -rc5 with commit c3a6cf19e695 on top. Unfortunately, as of this writing, strings will not get deduplicated for kernel modules, as ld does not do the deduplication for SHF_MERGE|SHF_STRINGS sections for relocatable files (ld -r), which kernel modules are. A patch for ld is currently being worked on to hopefully allow for string deduplication in relocatable files in the future. Suggested-by: Rasmus Villemoes Reviewed-by: Masahiro Yamada Reviewed-by: Matthias Maennich Signed-off-by: Jessica Yu --- include/linux/export.h | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 627841448293..fceb5e855717 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -82,16 +82,29 @@ struct kernel_symbol { #else -/* For every exported symbol, place a struct in the __ksymtab section */ -#define ___EXPORT_SYMBOL(sym, sec, ns) \ - extern typeof(sym) sym; \ - __CRC_SYMBOL(sym, sec); \ - static const char __kstrtab_##sym[] \ - __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ - = #sym; \ - static const char __kstrtabns_##sym[] \ - __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ - = ns; \ +/* + * For every exported symbol, do the following: + * + * - If applicable, place a CRC entry in the __kcrctab section. + * - Put the name of the symbol and namespace (empty string "" for none) in + * __ksymtab_strings. + * - Place a struct kernel_symbol entry in the __ksymtab section. + * + * note on .section use: we specify progbits since usage of the "M" (SHF_MERGE) + * section flag requires it. Use '%progbits' instead of '@progbits' since the + * former apparently works on all arches according to the binutils source. + */ +#define ___EXPORT_SYMBOL(sym, sec, ns) \ + extern typeof(sym) sym; \ + extern const char __kstrtab_##sym[]; \ + extern const char __kstrtabns_##sym[]; \ + __CRC_SYMBOL(sym, sec); \ + asm(" .section \"__ksymtab_strings\",\"aMS\",%progbits,1 \n" \ + "__kstrtab_" #sym ": \n" \ + " .asciz \"" #sym "\" \n" \ + "__kstrtabns_" #sym ": \n" \ + " .asciz \"" ns "\" \n" \ + " .previous \n"); \ __KSYMTAB_ENTRY(sym, sec) #endif -- cgit v1.2.3 From c8fdcc86725cc93a021139e8de68914857ea7489 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 2 Dec 2019 11:30:28 +0100 Subject: backlight: bd6107: Convert to use GPIO descriptor The Rohm BD6107 driver can pass a fixed GPIO line using the old GPIO API using platform data. As there are no in-tree users of this platform data since 2013, we can convert this to use a GPIO descriptor and require any out-of-tree consumers to pass the GPIO using a machine descriptor table instead. Signed-off-by: Linus Walleij Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/platform_data/bd6107.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/bd6107.h b/include/linux/platform_data/bd6107.h index 3bd019037eb3..54a06a4d2618 100644 --- a/include/linux/platform_data/bd6107.h +++ b/include/linux/platform_data/bd6107.h @@ -9,7 +9,6 @@ struct device; struct bd6107_platform_data { struct device *fbdev; - int reset; /* Reset GPIO */ unsigned int def_value; }; -- cgit v1.2.3 From bc94638886ab21f8247d3f7f39573d3feb7d8284 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 13 Dec 2019 09:55:14 +0100 Subject: ACPI: processor: Export function to claim _CST control The intel_idle driver will be modified to use ACPI _CST subsequently and it will need to notify the platform firmware of that if acpi_gbl_FADT.cst_control is set, so add a routine for this purpose, acpi_processor_claim_cst_control(), to acpi_processor.c (so that it is always present which is required by intel_idle) and export it to allow the ACPI processor driver (which is modular) to call it. No intentional functional impact. Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 0f37a7d5fa77..ee39b05e7f76 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -279,6 +279,12 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); +/* Processor _CTS control */ +#ifdef CONFIG_ACPI_PROCESSOR_CSTATE +bool acpi_processor_claim_cst_control(void); +#else +static inline bool acpi_processor_claim_cst_control(void) { return false; } +#endif #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ -- cgit v1.2.3 From 12e3c55d236b18fae00daa4ff54195b15cd741c3 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 3 Dec 2019 21:05:12 +0100 Subject: mmc: renesas_sdhi: remove 4taps as a TMIO flag Now that the quirks structure is accessible, we can remove the TMIO flag for HS400 using only 4 taps. This is Renesas specific anyhow. Signed-off-by: Wolfram Sang Reviewed-by: Geert Uytterhoeven Reviewed-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20191203200513.1758-5-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 739b7bf37eaa..8ba042430d8e 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -79,9 +79,6 @@ /* Some controllers have a CBSY bit */ #define TMIO_MMC_HAVE_CBSY BIT(11) -/* Some controllers that support HS400 use 4 taps while others use 8. */ -#define TMIO_MMC_HAVE_4TAP_HS400 BIT(13) - int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state); -- cgit v1.2.3 From faced7e0806cf44095a2833ad53ff59c39e6748d Mon Sep 17 00:00:00 2001 From: Giuseppe Scrivano Date: Mon, 16 Dec 2019 20:38:31 +0100 Subject: mm: hugetlb controller for cgroups v2 In the effort of supporting cgroups v2 into Kubernetes, I stumped on the lack of the hugetlb controller. When the controller is enabled, it exposes four new files for each hugetlb size on non-root cgroups: - hugetlb..current - hugetlb..max - hugetlb..events - hugetlb..events.local The differences with the legacy hierarchy are in the file names and using the value "max" instead of "-1" to disable a limit. The file .limit_in_bytes is renamed to .max. The file .usage_in_bytes is renamed to .current. .failcnt is not provided as a single file anymore, but its value can be read through the new flat-keyed files .events and .events.local, through the "max" key. Signed-off-by: Giuseppe Scrivano Signed-off-by: Tejun Heo --- include/linux/hugetlb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 31d4920994b9..1e897e4168ac 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -432,7 +432,8 @@ struct hstate { unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files[5]; + struct cftype cgroup_files_dfl[5]; + struct cftype cgroup_files_legacy[5]; #endif char name[HSTATE_NAME_LEN]; }; -- cgit v1.2.3 From 9429439f59cd3b82a3e2732ead5363578de97a84 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Thu, 12 Dec 2019 18:08:05 +0800 Subject: ptp_qoriq: export extts_clean_up() function Export extts_clean_up() function so that dpaa2-ptp driver is able to reuse it. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 992bf9fa1729..b0b743563f43 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -192,6 +192,7 @@ int ptp_qoriq_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts); int ptp_qoriq_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on); +int extts_clean_up(struct ptp_qoriq *ptp_qoriq, int index, bool update_event); #ifdef CONFIG_DEBUG_FS void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq); void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq); -- cgit v1.2.3 From a5e37de90e67ac1072a9a44bd0cec9f5e98ded08 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sat, 14 Dec 2019 19:51:07 +0000 Subject: stop_machine: remove try_stop_cpus helper try_stop_cpus is not used after this: commit c190c3b16c0f ("rcu: Switch synchronize_sched_expedited() to stop_one_cpu()") So remove it. Signed-off-by: Yangtao Li Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191214195107.26480-1-tiny.windzz@gmail.com --- include/linux/stop_machine.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index f9a0c6189852..648298f877da 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -33,7 +33,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); -int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); void stop_machine_park(int cpu); void stop_machine_unpark(int cpu); void stop_machine_yield(const struct cpumask *cpumask); @@ -90,12 +89,6 @@ static inline int stop_cpus(const struct cpumask *cpumask, return -ENOENT; } -static inline int try_stop_cpus(const struct cpumask *cpumask, - cpu_stop_fn_t fn, void *arg) -{ - return stop_cpus(cpumask, fn, arg); -} - #endif /* CONFIG_SMP */ /* -- cgit v1.2.3 From 7e5ed9f5e012f21a1514edcf8c35b9b4cfbd96c3 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Fri, 13 Dec 2019 00:06:01 +0000 Subject: serial: Move sysrq members above At the current place members those follow are: : upf_t flags; : upstat_t status; : int hw_stopped; : unsigned int mctrl; : unsigned int timeout; : unsigned int type; : const struct uart_ops *ops; Together, they give (*ops) 8-byte align on 64-bit platforms. And `sysrq_ch` introduces 4-byte padding. On the other side, above: : struct device *dev; : unsigned char hub6; : unsigned char suspended; : unsigned char unused[2]; : const char *name; Adds another 4-byte padding. Moving sysrq members just before `hub6` allows to save 8 bytes per-uart_port on 64-bit platforms: On my gcc, x86_64 sizeof(struct uart_port) goes from 528 to 520. Signed-off-by: Dmitry Safonov Link: https://lore.kernel.org/r/20191213000657.931618-3-dima@arista.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 2b78cc734719..bbbe57bf5163 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -161,11 +161,6 @@ struct uart_port { struct uart_icount icount; /* statistics */ struct console *cons; /* struct console, if any */ -#if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(SUPPORT_SYSRQ) - unsigned long sysrq; /* sysrq timeout */ - unsigned int sysrq_ch; /* char for sysrq */ -#endif - /* flags must be updated while holding port mutex */ upf_t flags; @@ -244,6 +239,12 @@ struct uart_port { resource_size_t mapbase; /* for ioremap */ resource_size_t mapsize; struct device *dev; /* parent device */ + +#if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(SUPPORT_SYSRQ) + unsigned long sysrq; /* sysrq timeout */ + unsigned int sysrq_ch; /* char for sysrq */ +#endif + unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; unsigned char unused[2]; -- cgit v1.2.3 From 1997e9dfdc84c8f73d6fc318355cf9e313aba183 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Fri, 13 Dec 2019 00:06:02 +0000 Subject: serial_core: Un-ifdef sysrq SUPPORT_SYSRQ The SUPPORT_SYSRQ is messy: every .c source should define it before including "serial_core.h" if sysrq is supported or struct uart_port will differ in sizes. Also this prevents moving to serial_core.c functions: uart_handle_sysrq_char(), uart_prepare_sysrq_char(), uart_unlock_and_check_sysrq(). It doesn't save many bytes in the structure, and a better way to reduce it's size would be making rs485 and iso7816 pointers. Introduce `has_sysrq` member to be used by serial line drivers further. Signed-off-by: Dmitry Safonov Link: https://lore.kernel.org/r/20191213000657.931618-4-dima@arista.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 77 +++++++++++++++++++++++++-------------------- 1 file changed, 43 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index bbbe57bf5163..5f761c399282 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -240,14 +240,13 @@ struct uart_port { resource_size_t mapsize; struct device *dev; /* parent device */ -#if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(SUPPORT_SYSRQ) unsigned long sysrq; /* sysrq timeout */ unsigned int sysrq_ch; /* char for sysrq */ -#endif + unsigned char has_sysrq; unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char unused[2]; + unsigned char unused; 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) */ @@ -461,31 +460,46 @@ extern void uart_handle_cts_change(struct uart_port *uport, extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); -#if defined(SUPPORT_SYSRQ) && defined(CONFIG_MAGIC_SYSRQ_SERIAL) static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { - if (port->sysrq) { - if (ch && time_before(jiffies, port->sysrq)) { - handle_sysrq(ch); - port->sysrq = 0; - return 1; - } + if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL)) + return 0; + + if (!port->has_sysrq && !IS_ENABLED(SUPPORT_SYSRQ)) + return 0; + + if (!port->sysrq) + return 0; + + if (ch && time_before(jiffies, port->sysrq)) { + handle_sysrq(ch); port->sysrq = 0; + return 1; } + port->sysrq = 0; + return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) { - if (port->sysrq) { - if (ch && time_before(jiffies, port->sysrq)) { - port->sysrq_ch = ch; - port->sysrq = 0; - return 1; - } + if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL)) + return 0; + + if (!port->has_sysrq && !IS_ENABLED(SUPPORT_SYSRQ)) + return 0; + + if (!port->sysrq) + return 0; + + if (ch && time_before(jiffies, port->sysrq)) { + port->sysrq_ch = ch; port->sysrq = 0; + return 1; } + port->sysrq = 0; + return 0; } static inline void @@ -493,6 +507,11 @@ uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) { int sysrq_ch; + if (!port->has_sysrq && !IS_ENABLED(SUPPORT_SYSRQ)) { + spin_unlock_irqrestore(&port->lock, irqflags); + return; + } + sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; @@ -501,17 +520,6 @@ uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) if (sysrq_ch) handle_sysrq(sysrq_ch); } -#else -static inline int -uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { return 0; } -static inline int -uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) { return 0; } -static inline void -uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) -{ - spin_unlock_irqrestore(&port->lock, irqflags); -} -#endif /* * We do the SysRQ and SAK checking like this... @@ -523,15 +531,16 @@ static inline int uart_handle_break(struct uart_port *port) if (port->handle_break) port->handle_break(port); -#ifdef SUPPORT_SYSRQ - if (port->cons && port->cons->index == port->line) { - if (!port->sysrq) { - port->sysrq = jiffies + HZ*5; - return 1; + if (port->has_sysrq || IS_ENABLED(SUPPORT_SYSRQ)) { + if (port->cons && port->cons->index == port->line) { + if (!port->sysrq) { + port->sysrq = jiffies + HZ*5; + return 1; + } + port->sysrq = 0; } - port->sysrq = 0; } -#endif + if (port->flags & UPF_SAK) do_SAK(state->port.tty); return 0; -- cgit v1.2.3 From c807da539e8276cc1bd2fb08df5ed160e329b40a Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Wed, 4 Dec 2019 13:29:36 +0100 Subject: i2c: remove unneeded 'extern' from function declatations According to coding-style.rst, extern should not be specified for exported functions. Signed-off-by: Luca Ceresoli Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 115 +++++++++++++++++++++++++--------------------------- 1 file changed, 55 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 582ef05ec07e..f834687989f7 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -50,8 +50,8 @@ struct property_entry; * transmit an arbitrary number of messages without interruption. * @count must be be less than 64k since msg.len is u16. */ -extern int i2c_transfer_buffer_flags(const struct i2c_client *client, - char *buf, int count, u16 flags); +int i2c_transfer_buffer_flags(const struct i2c_client *client, + char *buf, int count, u16 flags); /** * i2c_master_recv - issue a single I2C message in master receive mode @@ -115,11 +115,9 @@ static inline int i2c_master_send_dmasafe(const struct i2c_client *client, /* Transfer num messages. */ -extern int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, - int num); +int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); /* Unlocked flavor */ -extern int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, - int num); +int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); /* This is the very generalized SMBus access routine. You probably do not want to use this, though; one of the functions below may be much easier, @@ -138,16 +136,14 @@ s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, /* Now follow the 'nice' access routines. These also document the calling conventions of i2c_smbus_xfer. */ -extern s32 i2c_smbus_read_byte(const struct i2c_client *client); -extern s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value); -extern s32 i2c_smbus_read_byte_data(const struct i2c_client *client, - u8 command); -extern s32 i2c_smbus_write_byte_data(const struct i2c_client *client, - u8 command, u8 value); -extern s32 i2c_smbus_read_word_data(const struct i2c_client *client, - u8 command); -extern s32 i2c_smbus_write_word_data(const struct i2c_client *client, - u8 command, u16 value); +s32 i2c_smbus_read_byte(const struct i2c_client *client); +s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value); +s32 i2c_smbus_read_byte_data(const struct i2c_client *client, u8 command); +s32 i2c_smbus_write_byte_data(const struct i2c_client *client, + u8 command, u8 value); +s32 i2c_smbus_read_word_data(const struct i2c_client *client, u8 command); +s32 i2c_smbus_write_word_data(const struct i2c_client *client, + u8 command, u16 value); static inline s32 i2c_smbus_read_word_swapped(const struct i2c_client *client, u8 command) @@ -165,19 +161,18 @@ i2c_smbus_write_word_swapped(const struct i2c_client *client, } /* Returns the number of read bytes */ -extern s32 i2c_smbus_read_block_data(const struct i2c_client *client, - u8 command, u8 *values); -extern s32 i2c_smbus_write_block_data(const struct i2c_client *client, - u8 command, u8 length, const u8 *values); +s32 i2c_smbus_read_block_data(const struct i2c_client *client, + u8 command, u8 *values); +s32 i2c_smbus_write_block_data(const struct i2c_client *client, + u8 command, u8 length, const u8 *values); /* Returns the number of read bytes */ -extern s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, - u8 command, u8 length, u8 *values); -extern s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, - u8 command, u8 length, - const u8 *values); -extern s32 -i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, - u8 command, u8 length, u8 *values); +s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, + u8 command, u8 length, u8 *values); +s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, + u8 command, u8 length, const u8 *values); +s32 i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, + u8 command, u8 length, + u8 *values); int i2c_get_device_id(const struct i2c_client *client, struct i2c_device_identity *id); #endif /* I2C */ @@ -337,10 +332,10 @@ struct i2c_client { }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) -extern struct i2c_client *i2c_verify_client(struct device *dev); -extern struct i2c_adapter *i2c_verify_adapter(struct device *dev); -extern const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, - const struct i2c_client *client); +struct i2c_client *i2c_verify_client(struct device *dev); +struct i2c_adapter *i2c_verify_adapter(struct device *dev); +const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, + const struct i2c_client *client); static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj) { @@ -369,9 +364,9 @@ enum i2c_slave_event { I2C_SLAVE_STOP, }; -extern int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); -extern int i2c_slave_unregister(struct i2c_client *client); -extern bool i2c_detect_slave_mode(struct device *dev); +int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); +int i2c_slave_unregister(struct i2c_client *client); +bool i2c_detect_slave_mode(struct device *dev); static inline int i2c_slave_event(struct i2c_client *client, enum i2c_slave_event event, u8 *val) @@ -440,10 +435,10 @@ struct i2c_board_info { * with integrated I2C, a config eeprom, sensors, and a codec that's * used in conjunction with the primary hardware. */ -extern struct i2c_client * +struct i2c_client * i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info); -extern struct i2c_client * +struct i2c_client * i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info); /* If you don't know the exact address of an I2C device, use this variant @@ -452,33 +447,33 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf * it must return 1 on successful probe, 0 otherwise. If it is not provided, * a default probing method is used. */ -extern struct i2c_client * +struct i2c_client * i2c_new_scanned_device(struct i2c_adapter *adap, struct i2c_board_info *info, unsigned short const *addr_list, int (*probe)(struct i2c_adapter *adap, unsigned short addr)); -extern struct i2c_client * +struct i2c_client * i2c_new_probed_device(struct i2c_adapter *adap, struct i2c_board_info *info, unsigned short const *addr_list, int (*probe)(struct i2c_adapter *adap, unsigned short addr)); /* Common custom probe functions */ -extern int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); +int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); -extern struct i2c_client * +struct i2c_client * i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address); -extern struct i2c_client * +struct i2c_client * devm_i2c_new_dummy_device(struct device *dev, struct i2c_adapter *adap, u16 address); -extern struct i2c_client * +struct i2c_client * i2c_new_ancillary_device(struct i2c_client *client, - const char *name, - u16 default_addr); + const char *name, + u16 default_addr); -extern void i2c_unregister_device(struct i2c_client *client); +void i2c_unregister_device(struct i2c_client *client); #endif /* I2C */ /* Mainboard arch_initcall() code should register all its I2C devices. @@ -486,7 +481,7 @@ extern void i2c_unregister_device(struct i2c_client *client); * Modules for add-on boards must use other calls. */ #ifdef CONFIG_I2C_BOARDINFO -extern int +int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned n); #else @@ -840,12 +835,12 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) /* administration... */ #if IS_ENABLED(CONFIG_I2C) -extern int i2c_add_adapter(struct i2c_adapter *adap); -extern void i2c_del_adapter(struct i2c_adapter *adap); -extern int i2c_add_numbered_adapter(struct i2c_adapter *adap); +int i2c_add_adapter(struct i2c_adapter *adap); +void i2c_del_adapter(struct i2c_adapter *adap); +int i2c_add_numbered_adapter(struct i2c_adapter *adap); -extern int i2c_register_driver(struct module *owner, struct i2c_driver *driver); -extern void i2c_del_driver(struct i2c_driver *driver); +int i2c_register_driver(struct module *owner, struct i2c_driver *driver); +void i2c_del_driver(struct i2c_driver *driver); /* use a define to avoid include chaining to get THIS_MODULE */ #define i2c_add_driver(driver) \ @@ -858,12 +853,12 @@ static inline bool i2c_client_has_driver(struct i2c_client *client) /* call the i2c_client->command() of all attached clients with * the given arguments */ -extern void i2c_clients_command(struct i2c_adapter *adap, - unsigned int cmd, void *arg); +void i2c_clients_command(struct i2c_adapter *adap, + unsigned int cmd, void *arg); -extern struct i2c_adapter *i2c_get_adapter(int nr); -extern void i2c_put_adapter(struct i2c_adapter *adap); -extern unsigned int i2c_adapter_depth(struct i2c_adapter *adapter); +struct i2c_adapter *i2c_get_adapter(int nr); +void i2c_put_adapter(struct i2c_adapter *adap); +unsigned int i2c_adapter_depth(struct i2c_adapter *adapter); void i2c_parse_fw_timings(struct device *dev, struct i2c_timings *t, bool use_defaults); @@ -935,15 +930,15 @@ int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); #if IS_ENABLED(CONFIG_OF) /* must call put_device() when done with returned i2c_client device */ -extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); +struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); /* must call put_device() when done with returned i2c_adapter device */ -extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node); +struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node); /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node); -extern const struct of_device_id +const struct of_device_id *i2c_of_match_device(const struct of_device_id *matches, struct i2c_client *client); -- cgit v1.2.3 From 28b5afcd06d2b24e31ca4a643ddee9eb92b5bcb1 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 16 Dec 2019 14:41:53 -0800 Subject: ARM: OMAP2+: Drop unused sdma functions We still have lots of legacy code for sdma, but some of it is now unused. To simplify phasing out the old legacy sdma code, let's first remove all currently unused functions: omap_enable_dma_irq omap_set_dma_write_mode omap_set_dma_params omap_dma_link_lch omap_set_dma_callback omap_dma_set_global_params And with this, omap_dma_set_global_params now becomes static. Cc: Aaro Koskinen Cc: Arnd Bergmann Cc: Peter Ujfalusi Cc: Russell King Cc: Vinod Koul Acked-by: Peter Ujfalusi Tested-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- include/linux/omap-dma.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index ba3cfbb52312..61e474ce3ccb 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -303,7 +303,6 @@ extern void omap_set_dma_priority(int lch, int dst_port, int priority); extern int omap_request_dma(int dev_id, const char *dev_name, void (*callback)(int lch, u16 ch_status, void *data), void *data, int *dma_ch); -extern void omap_enable_dma_irq(int ch, u16 irq_bits); extern void omap_disable_dma_irq(int ch, u16 irq_bits); extern void omap_free_dma(int ch); extern void omap_start_dma(int lch); @@ -312,7 +311,6 @@ extern void omap_set_dma_transfer_params(int lch, int data_type, int elem_count, int frame_count, int sync_mode, int dma_trigger, int src_or_dst_synch); -extern void omap_set_dma_write_mode(int lch, enum omap_dma_write_mode mode); extern void omap_set_dma_channel_mode(int lch, enum omap_dma_channel_mode mode); extern void omap_set_dma_src_params(int lch, int src_port, int src_amode, @@ -329,20 +327,10 @@ extern void omap_set_dma_dest_data_pack(int lch, int enable); extern void omap_set_dma_dest_burst_mode(int lch, enum omap_dma_burst_mode burst_mode); -extern void omap_set_dma_params(int lch, - struct omap_dma_channel_params *params); - -extern void omap_dma_link_lch(int lch_head, int lch_queue); - -extern int omap_set_dma_callback(int lch, - void (*callback)(int lch, u16 ch_status, void *data), - void *data); extern dma_addr_t omap_get_dma_src_pos(int lch); extern dma_addr_t omap_get_dma_dst_pos(int lch); extern int omap_get_dma_active_status(int lch); extern int omap_dma_running(void); -extern void omap_dma_set_global_params(int arb_rate, int max_fifo_depth, - int tparams); void omap_dma_global_context_save(void); void omap_dma_global_context_restore(void); -- cgit v1.2.3 From 755cbfd8cf89c09e53be796d7d5c22f2d197ef1a Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 16 Dec 2019 14:41:53 -0800 Subject: ARM: OMAP2+: Drop sdma interrupt handling for mach-omap2 All device tree probing omap SoCs only have device drivers that are using Linux dmaengine API with the IRQENABLE_L1 interrupts. Only omap1 is still using old legacy dma. This means we can remove the legacy sdma interrupt handling for IRQENABLE_L0, and only rely on the dmaengine driver using IRQENABLE_L1. The legacy code still allocates the channels, but that will be deal with in the following patches. Cc: Aaro Koskinen Cc: Arnd Bergmann Cc: Peter Ujfalusi Cc: Russell King Cc: Vinod Koul Acked-by: Peter Ujfalusi Tested-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- include/linux/omap-dma.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 61e474ce3ccb..ee0de8443274 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -129,7 +129,6 @@ #define IS_WORD_16 BIT(0xd) #define ENABLE_16XX_MODE BIT(0xe) #define HS_CHANNELS_RESERVED BIT(0xf) -#define DMA_ENGINE_HANDLE_IRQ BIT(0x10) /* Defines for DMA Capabilities */ #define DMA_HAS_TRANSPARENT_CAPS (0x1 << 18) @@ -239,9 +238,6 @@ struct omap_dma_lch { void (*callback)(int lch, u16 ch_status, void *data); void *data; long flags; - /* required for Dynamic chaining */ - int prev_linked_ch; - int next_linked_ch; int state; int chain_id; int status; -- cgit v1.2.3 From 4c74ecf79227228f31d05d6d4766ccb5f8607b83 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 16 Dec 2019 14:41:53 -0800 Subject: dmaengine: ti: omap-dma: Add device tree match data and use it for cpu_pm With old DMA code disabled for handling DMA requests for device tree based SoCs, we can move omap3 specific context save and restore to the dmaengine driver. Let's do this by adding cpu_pm notifier handling to save and restore context, and enable it based on device tree match data. This way we can use the match data later to configure more SoC specific features later on too. Note that we only clear the channels in use while the platform code also clears reserved channels 0 and 1 on high-security SoCs. Based on testing on n900, this is not needed though and the system idles just fine. With the dmaengine driver handling context save and restore, we must now remove the old custom calls for context save and restore. Cc: Aaro Koskinen Cc: Arnd Bergmann Cc: Peter Ujfalusi Cc: Russell King Cc: Vinod Koul Acked-by: Peter Ujfalusi Tested-by: Peter Ujfalusi Acked-by: Vinod Koul Signed-off-by: Tony Lindgren --- include/linux/omap-dma.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index ee0de8443274..5c5c93ad6b50 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -327,8 +327,6 @@ extern dma_addr_t omap_get_dma_src_pos(int lch); extern dma_addr_t omap_get_dma_dst_pos(int lch); extern int omap_get_dma_active_status(int lch); extern int omap_dma_running(void); -void omap_dma_global_context_save(void); -void omap_dma_global_context_restore(void); #if defined(CONFIG_ARCH_OMAP1) && IS_ENABLED(CONFIG_FB_OMAP) #include -- cgit v1.2.3 From 2f5e70c8ce47396bfa8f5c437574b569c02597bb Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 20 Nov 2019 12:33:59 +0100 Subject: netfilter: Document ingress hook Amend kerneldoc of struct net_device to fix a "make htmldocs" warning: include/linux/netdevice.h:2045: warning: Function parameter or member 'nf_hooks_ingress' not described in 'net_device' Reported-by: kbuild test robot Signed-off-by: Lukas Wunner Cc: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 30745068fb39..0b097bbd3663 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1708,6 +1708,7 @@ enum netdev_priv_flags { * @miniq_ingress: ingress/clsact qdisc specific data for * ingress processing * @ingress_queue: XXX: need comments on this one + * @nf_hooks_ingress: netfilter hooks executed for ingress packets * @broadcast: hw bcast address * * @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts, -- cgit v1.2.3 From cbc943eb37ca1ce2c1c05de54d9768bb7824a7aa Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sat, 14 Dec 2019 23:10:19 +0100 Subject: rtc: rv3029: let the core handle rtc range Despite the comment, the RV3029 uses a 7bit BCD register for the year, making 2079 the last supported year. Link: https://lore.kernel.org/r/20191214221022.622482-14-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 4e9d3c71addb..23990bd29040 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -167,6 +167,7 @@ struct rtc_device { #define RTC_TIMESTAMP_BEGIN_1900 -2208988800LL /* 1900-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2063 2966371199LL /* 2063-12-31 23:59:59 */ +#define RTC_TIMESTAMP_END_2079 3471292799LL /* 2079-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2199 7258118399LL /* 2199-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_9999 253402300799LL /* 9999-12-31 23:59:59 */ -- cgit v1.2.3 From d3a5bcb4a17f1ad072484bb92c42519ff3aba6e1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 11 Dec 2019 03:40:55 +0100 Subject: gpio: add gpiod_toggle_active_low() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add possibility to toggle active-low flag of a gpio descriptor. This is useful for compatibility code, where defaults are inverted vs DT gpio flags or the active-low flag is taken from elsewhere. Acked-by: Linus Walleij Signed-off-by: Michał Mirosław Link: https://lore.kernel.org/r/7ce0338e01ad17fa5a227176813941b41a7c35c1.1576031637.git.mirq-linux@rere.qmqm.pl Signed-off-by: Ulf Hansson --- include/linux/gpio/consumer.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 5215fdba6b9a..bf2d017dd7b7 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -158,6 +158,7 @@ int gpiod_set_raw_array_value_cansleep(unsigned int array_size, int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); int gpiod_set_transitory(struct gpio_desc *desc, bool transitory); +void gpiod_toggle_active_low(struct gpio_desc *desc); int gpiod_is_active_low(const struct gpio_desc *desc); int gpiod_cansleep(const struct gpio_desc *desc); @@ -483,6 +484,12 @@ static inline int gpiod_set_transitory(struct gpio_desc *desc, bool transitory) return -ENOSYS; } +static inline void gpiod_toggle_active_low(struct gpio_desc *desc) +{ + /* GPIO can never have been requested */ + WARN_ON(desc); +} + static inline int gpiod_is_active_low(const struct gpio_desc *desc) { /* GPIO can never have been requested */ -- cgit v1.2.3 From d0052ad90e712aaa76190e05fc1b0a8acb3b449e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 11 Dec 2019 03:40:56 +0100 Subject: mmc: core: Remove mmc_gpiod_request_*(invert_gpio) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that invert_gpio arguments are unused, let's remove them. Signed-off-by: Michał Mirosław Link: https://lore.kernel.org/r/64d766d1f8af2e22bce32f4ffa453f7234207ad6.1576031637.git.mirq-linux@rere.qmqm.pl Signed-off-by: Ulf Hansson --- include/linux/mmc/slot-gpio.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 0de3d7c016cd..4ae2f2908f99 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -17,10 +17,9 @@ int mmc_gpio_get_ro(struct mmc_host *host); int mmc_gpio_get_cd(struct mmc_host *host); int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, - unsigned int debounce, bool *gpio_invert); + unsigned int debounce); int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, - unsigned int idx, - unsigned int debounce, bool *gpio_invert); + unsigned int idx, unsigned int debounce); void mmc_gpio_set_cd_isr(struct mmc_host *host, irqreturn_t (*isr)(int irq, void *dev_id)); int mmc_gpio_set_cd_wake(struct mmc_host *host, bool on); -- cgit v1.2.3 From d68fefdd5b5f107403568c8a4650e858132bd83a Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Fri, 13 Dec 2019 00:06:04 +0000 Subject: tty/serial: Migrate 8250_fsl to use has_sysrq The SUPPORT_SYSRQ ifdeffery is not nice as: - May create misunderstanding about sizeof(struct uart_port) between different objects - Prevents moving functions from serial_core.h - Reduces readability (well, it's ifdeffery - it's hard to follow) In order to remove SUPPORT_SYSRQ, has_sysrq variable has been added. Initialise it in driver's probe and remove ifdeffery. In contrast to 8250/8250_of, legacy_serial on powerpc does fill (struct plat_serial8250_port). The reason is likely that it's done on device_initcall(), not on probe. So, 8250_core is not yet probed. Propagate value from platform_device on 8250 probe - in case powepc legacy driver it's initialized on initcall, in case 8250_of it will be initialized later on of_platform_serial_setup(). Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Dmitry Safonov Link: https://lore.kernel.org/r/20191213000657.931618-6-dima@arista.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index bb2bc99388ca..6a8e8c48c882 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -25,6 +25,7 @@ struct plat_serial8250_port { unsigned char regshift; /* register shift */ unsigned char iotype; /* UPIO_* */ unsigned char hub6; + unsigned char has_sysrq; /* supports magic SysRq */ upf_t flags; /* UPF_* flags */ unsigned int type; /* If UPF_FIXED_TYPE */ unsigned int (*serial_in)(struct uart_port *, int); -- cgit v1.2.3 From 82cfd2e62b354840af6a045e084f6e9e7c49584d Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Fri, 13 Dec 2019 00:06:53 +0000 Subject: serial_core: Remove SUPPORT_SYSRQ ifdeffery No one defines it anymore. Signed-off-by: Dmitry Safonov Link: https://lore.kernel.org/r/20191213000657.931618-55-dima@arista.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 5f761c399282..9cf1682dc580 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -466,10 +466,7 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL)) return 0; - if (!port->has_sysrq && !IS_ENABLED(SUPPORT_SYSRQ)) - return 0; - - if (!port->sysrq) + if (!port->has_sysrq || !port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { @@ -487,10 +484,7 @@ uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL)) return 0; - if (!port->has_sysrq && !IS_ENABLED(SUPPORT_SYSRQ)) - return 0; - - if (!port->sysrq) + if (!port->has_sysrq || !port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { @@ -507,7 +501,7 @@ uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) { int sysrq_ch; - if (!port->has_sysrq && !IS_ENABLED(SUPPORT_SYSRQ)) { + if (!port->has_sysrq) { spin_unlock_irqrestore(&port->lock, irqflags); return; } @@ -531,7 +525,7 @@ static inline int uart_handle_break(struct uart_port *port) if (port->handle_break) port->handle_break(port); - if (port->has_sysrq || IS_ENABLED(SUPPORT_SYSRQ)) { + if (port->has_sysrq) { if (port->cons && port->cons->index == port->line) { if (!port->sysrq) { port->sysrq = jiffies + HZ*5; -- cgit v1.2.3 From 294ec5b87a8aaef664efb00ba62e4ef6ca05707c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 7 Jun 2018 17:02:50 +0200 Subject: sunrpc: convert to time64_t for expiry Using signed 32-bit types for UTC time leads to the y2038 overflow, which is what happens in the sunrpc code at the moment. This changes the sunrpc code over to use time64_t where possible. The one exception is the gss_import_v{1,2}_context() function for kerberos5, which uses 32-bit timestamps in the protocol. Here, we can at least treat the numbers as 'unsigned', which extends the range from 2038 to 2106. Signed-off-by: Arnd Bergmann --- include/linux/sunrpc/gss_api.h | 4 ++-- include/linux/sunrpc/gss_krb5.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index bd691e08be3b..1cc6cefb1220 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -48,7 +48,7 @@ int gss_import_sec_context( size_t bufsize, struct gss_api_mech *mech, struct gss_ctx **ctx_id, - time_t *endtime, + time64_t *endtime, gfp_t gfp_mask); u32 gss_get_mic( struct gss_ctx *ctx_id, @@ -108,7 +108,7 @@ struct gss_api_ops { const void *input_token, size_t bufsize, struct gss_ctx *ctx_id, - time_t *endtime, + time64_t *endtime, gfp_t gfp_mask); u32 (*gss_get_mic)( struct gss_ctx *ctx_id, diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 02c0412e368c..c1d77dd8ed41 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -106,9 +106,9 @@ struct krb5_ctx { struct crypto_sync_skcipher *initiator_enc_aux; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; - s32 endtime; atomic_t seq_send; atomic64_t seq_send64; + time64_t endtime; struct xdr_netobj mech_used; u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; -- cgit v1.2.3 From f559935e7ce4e5d448bb6588f7fa82b0cc2cc2c0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 20 Oct 2017 16:34:42 +0200 Subject: nfs: use time64_t internally The timestamps for the cache are all in boottime seconds, so they don't overflow 32-bit values, but the use of time_t is deprecated because it generally does overflow when used with wall-clock time. There are multiple possible ways of avoiding it: - leave time_t, which is safe here, but forces others to look into this code to determine that it is over and over. - use a more generic type, like 'int' or 'long', which is known to be sufficient here but loses the documentation of referring to timestamps - use ktime_t everywhere, and convert into seconds in the few places where we want realtime-seconds. The conversion is sometimes expensive, but not more so than the conversion we do today. - use time64_t to clarify that this code is safe. Nothing would change for 64-bit architectures, but it is slightly less efficient on 32-bit architectures. Without a clear winner of the three approaches above, this picks the last one, favouring readability over a small performance loss on 32-bit architectures. Signed-off-by: Arnd Bergmann --- include/linux/sunrpc/cache.h | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index f8603724fbee..0f64de7caa39 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -45,8 +45,8 @@ */ struct cache_head { struct hlist_node cache_list; - time_t expiry_time; /* After time time, don't use the data */ - time_t last_refresh; /* If CACHE_PENDING, this is when upcall was + time64_t expiry_time; /* After time 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 * be *after* ->flush_time. @@ -95,22 +95,22 @@ struct cache_detail { /* fields below this comment are for internal use * and should not be touched by cache owners */ - time_t flush_time; /* flush all cache items with + time64_t flush_time; /* flush all cache items with * last_refresh at or earlier * than this. last_refresh * is never set at or earlier * than this. */ struct list_head others; - time_t nextcheck; + time64_t nextcheck; int entries; /* fields for communication over channel */ struct list_head queue; atomic_t writers; /* how many time is /channel open */ - time_t last_close; /* if no writers, when did last close */ - time_t last_warn; /* when we last warned about no writers */ + time64_t last_close; /* if no writers, when did last close */ + time64_t last_warn; /* when we last warned about no writers */ union { struct proc_dir_entry *procfs; @@ -147,18 +147,22 @@ struct cache_deferred_req { * timestamps kept in the cache are expressed in seconds * since boot. This is the best for measuring differences in * real time. + * This reimplemnts ktime_get_boottime_seconds() in a slightly + * faster but less accurate way. When we end up converting + * back to wallclock (CLOCK_REALTIME), that error often + * cancels out during the reverse operation. */ -static inline time_t seconds_since_boot(void) +static inline time64_t seconds_since_boot(void) { - struct timespec boot; - getboottime(&boot); - return get_seconds() - boot.tv_sec; + struct timespec64 boot; + getboottime64(&boot); + return ktime_get_real_seconds() - boot.tv_sec; } -static inline time_t convert_to_wallclock(time_t sinceboot) +static inline time64_t convert_to_wallclock(time64_t sinceboot) { - struct timespec boot; - getboottime(&boot); + struct timespec64 boot; + getboottime64(&boot); return boot.tv_sec + sinceboot; } @@ -273,7 +277,7 @@ static inline int get_uint(char **bpp, unsigned int *anint) return 0; } -static inline int get_time(char **bpp, time_t *time) +static inline int get_time(char **bpp, time64_t *time) { char buf[50]; long long ll; @@ -287,20 +291,20 @@ static inline int get_time(char **bpp, time_t *time) if (kstrtoll(buf, 0, &ll)) return -EINVAL; - *time = (time_t)ll; + *time = ll; return 0; } -static inline time_t get_expiry(char **bpp) +static inline time64_t get_expiry(char **bpp) { - time_t rv; - struct timespec boot; + time64_t rv; + struct timespec64 boot; if (get_time(bpp, &rv)) return 0; if (rv < 0) return 0; - getboottime(&boot); + getboottime64(&boot); return rv - boot.tv_sec; } -- cgit v1.2.3 From 751addac78b6f205ffd47c8736ca6d429dc77703 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 24 Oct 2019 22:53:19 +0200 Subject: y2038: remove obsolete jiffies conversion functions Now that the last user of timespec_to_jiffies() is gone, these can just be removed, everything else is using ktime_t or timespec64 already. Signed-off-by: Arnd Bergmann --- include/linux/jiffies.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1b6d31da7cbc..e3279ef24d28 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -422,26 +422,6 @@ static __always_inline unsigned long usecs_to_jiffies(const unsigned int u) extern unsigned long timespec64_to_jiffies(const struct timespec64 *value); extern void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value); -static inline unsigned long timespec_to_jiffies(const struct timespec *value) -{ - struct timespec64 ts = timespec_to_timespec64(*value); - - return timespec64_to_jiffies(&ts); -} - -static inline void jiffies_to_timespec(const unsigned long jiffies, - struct timespec *value) -{ - struct timespec64 ts; - - jiffies_to_timespec64(jiffies, &ts); - *value = timespec64_to_timespec(ts); -} - -extern unsigned long timeval_to_jiffies(const struct timeval *value); -extern void jiffies_to_timeval(const unsigned long jiffies, - struct timeval *value); - extern clock_t jiffies_to_clock_t(unsigned long x); static inline clock_t jiffies_delta_to_clock_t(long delta) { -- cgit v1.2.3 From 4f9fbd893fe83a1193adceca41c8f7aa6c7382a1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 15 Nov 2019 15:53:29 +0100 Subject: y2038: rename itimerval to __kernel_old_itimerval Take the renaming of timeval and timespec one level further, also renaming itimerval to __kernel_old_itimerval, to avoid namespace conflicts with the user-space structure that may use 64-bit time_t members. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d0391cc2dae9..27245fec2a8a 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -16,8 +16,7 @@ struct inode; struct iocb; struct io_event; struct iovec; -struct itimerspec; -struct itimerval; +struct __kernel_old_itimerval; struct kexec_segment; struct linux_dirent; struct linux_dirent64; @@ -591,10 +590,10 @@ asmlinkage long sys_nanosleep_time32(struct old_timespec32 __user *rqtp, struct old_timespec32 __user *rmtp); /* kernel/itimer.c */ -asmlinkage long sys_getitimer(int which, struct itimerval __user *value); +asmlinkage long sys_getitimer(int which, struct __kernel_old_itimerval __user *value); asmlinkage long sys_setitimer(int which, - struct itimerval __user *value, - struct itimerval __user *ovalue); + struct __kernel_old_itimerval __user *value, + struct __kernel_old_itimerval __user *ovalue); /* kernel/kexec.c */ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, -- cgit v1.2.3 From 09298542cd891b43778db1f65aa3613aa5a562eb Mon Sep 17 00:00:00 2001 From: James Sewart Date: Tue, 10 Dec 2019 16:07:30 -0600 Subject: PCI: Add nr_devfns parameter to pci_add_dma_alias() Add a "nr_devfns" parameter to pci_add_dma_alias() so it can be used to create DMA aliases for a range of devfns. [bhelgaas: incorporate nr_devfns fix from James, update quirk_pex_vca_alias() and setup_aliases()] Signed-off-by: James Sewart Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c393dff2d66f..930fab293073 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2310,7 +2310,7 @@ static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev) } #endif -void pci_add_dma_alias(struct pci_dev *dev, u8 devfn); +void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns); bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2); int pci_for_each_dma_alias(struct pci_dev *pdev, int (*fn)(struct pci_dev *pdev, -- cgit v1.2.3 From d4aef159394d5940bd7158ab789969dab82f7c76 Mon Sep 17 00:00:00 2001 From: Soeren Moch Date: Thu, 12 Dec 2019 00:52:49 +0100 Subject: brcmfmac: add support for BCM4359 SDIO chipset BCM4359 is a 2x2 802.11 abgn+ac Dual-Band HT80 combo chip and it supports Real Simultaneous Dual Band feature. Based on a similar patch by: Wright Feng Signed-off-by: Soeren Moch Acked-by: Chi-Hsien Lin Acked-by: Ulf Hansson Signed-off-by: Kalle Valo --- include/linux/mmc/sdio_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 08b25c02b5a1..2e9a6e4634eb 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -41,8 +41,10 @@ #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 +#define SDIO_DEVICE_ID_BROADCOM_4359 0x4359 #define SDIO_DEVICE_ID_CYPRESS_4373 0x4373 #define SDIO_DEVICE_ID_CYPRESS_43012 43012 +#define SDIO_DEVICE_ID_CYPRESS_89359 0x4355 #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 -- cgit v1.2.3 From 504723af0d85434be5fb6f2dde0b62644a7f1ead Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 18 Dec 2019 11:33:05 +0100 Subject: net: stmmac: Add basic EST support for GMAC5+ Adds the support for EST in GMAC5+ cores. This feature allows to offload scheduling of queues opening time to the IP. Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- include/linux/stmmac.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d4bcd9387136..0531afa9b21e 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -109,6 +109,18 @@ struct stmmac_axi { bool axi_rb; }; +#define EST_GCL 1024 +struct stmmac_est { + int enable; + u32 btr_offset[2]; + u32 btr[2]; + u32 ctr[2]; + u32 ter; + u32 gcl_unaligned[EST_GCL]; + u32 gcl[EST_GCL]; + u32 gcl_size; +}; + struct stmmac_rxq_cfg { u8 mode_to_use; u32 chan; @@ -139,6 +151,7 @@ struct plat_stmmacenet_data { struct device_node *phylink_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; + struct stmmac_est *est; int clk_csr; int has_gmac; int enh_desc; -- cgit v1.2.3 From d35eb52bd2ac7557b62bda52668f2e64dde2cf90 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 18 Dec 2019 14:55:15 +0000 Subject: net: sch_ets: Make the ETS qdisc offloadable Add hooks at appropriate points to make it possible to offload the ETS Qdisc. Signed-off-by: Petr Machata Acked-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 30745068fb39..7a8ed11f5d45 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -849,6 +849,7 @@ enum tc_setup_type { TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, TC_SETUP_FT, + TC_SETUP_QDISC_ETS, }; /* These structures hold the attributes of bpf state that are being passed -- cgit v1.2.3 From bc90705bbb570b2507353ba10d6b6788cfb119b1 Mon Sep 17 00:00:00 2001 From: "Angus Ainslie (Purism)" Date: Sat, 14 Dec 2019 07:27:54 -0800 Subject: power: supply: max17042: add MAX17055 support The MAX17055 is very similar to the MAX17042 so extend the driver. Signed-off-by: Angus Ainslie (Purism) Reviewed-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- include/linux/power/max17042_battery.h | 48 +++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index 4badd5322949..d55c746ac56e 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -105,11 +105,56 @@ enum max17042_register { MAX17042_OCV = 0xEE, - MAX17042_OCVInternal = 0xFB, + MAX17042_OCVInternal = 0xFB, /* MAX17055 VFOCV */ MAX17042_VFSOC = 0xFF, }; +enum max17055_register { + MAX17055_QRes = 0x0C, + MAX17055_TTF = 0x20, + MAX17055_V_empty = 0x3A, + MAX17055_TIMER = 0x3E, + MAX17055_USER_MEM = 0x40, + MAX17055_RGAIN = 0x42, + + MAX17055_ConvgCfg = 0x49, + MAX17055_VFRemCap = 0x4A, + + MAX17055_STATUS2 = 0xB0, + MAX17055_POWER = 0xB1, + MAX17055_ID = 0xB2, + MAX17055_AvgPower = 0xB3, + MAX17055_IAlrtTh = 0xB4, + MAX17055_TTFCfg = 0xB5, + MAX17055_CVMixCap = 0xB6, + MAX17055_CVHalfTime = 0xB7, + MAX17055_CGTempCo = 0xB8, + MAX17055_Curve = 0xB9, + MAX17055_HibCfg = 0xBA, + MAX17055_Config2 = 0xBB, + MAX17055_VRipple = 0xBC, + MAX17055_RippleCfg = 0xBD, + MAX17055_TimerH = 0xBE, + + MAX17055_RSense = 0xD0, + MAX17055_ScOcvLim = 0xD1, + + MAX17055_SOCHold = 0xD3, + MAX17055_MaxPeakPwr = 0xD4, + MAX17055_SusPeakPwr = 0xD5, + MAX17055_PackResistance = 0xD6, + MAX17055_SysResistance = 0xD7, + MAX17055_MinSysV = 0xD8, + MAX17055_MPPCurrent = 0xD9, + MAX17055_SPPCurrent = 0xDA, + MAX17055_ModelCfg = 0xDB, + MAX17055_AtQResidual = 0xDC, + MAX17055_AtTTE = 0xDD, + MAX17055_AtAvSOC = 0xDE, + MAX17055_AtAvCap = 0xDF, +}; + /* Registers specific to max17047/50 */ enum max17047_register { MAX17047_QRTbl00 = 0x12, @@ -125,6 +170,7 @@ enum max170xx_chip_type { MAXIM_DEVICE_TYPE_MAX17042, MAXIM_DEVICE_TYPE_MAX17047, MAXIM_DEVICE_TYPE_MAX17050, + MAXIM_DEVICE_TYPE_MAX17055, MAXIM_DEVICE_TYPE_NUM }; -- cgit v1.2.3 From 65dbad713d5d6a8581921804ae3f5eb4a9bf032e Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 9 Dec 2019 11:56:22 +0800 Subject: power: supply: core: Add battery internal resistance temperature table support Since the battery internal resistance can be changed with the temperature changes, thus add a resistance temperature table support to look up the accurate battery internal resistance in a certain temperature. Signed-off-by: Baolin Wang Signed-off-by: Baolin Wang Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 28413f737e7d..dcd5a71e6c67 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -325,6 +325,11 @@ struct power_supply_battery_ocv_table { int capacity; /* percent */ }; +struct power_supply_resistance_temp_table { + int temp; /* celsius */ + int resistance; /* internal resistance percent */ +}; + #define POWER_SUPPLY_OCV_TEMP_MAX 20 /* @@ -349,6 +354,8 @@ struct power_supply_battery_info { int ocv_temp[POWER_SUPPLY_OCV_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; + int resist_table_size; }; extern struct atomic_notifier_head power_supply_notifier; @@ -381,6 +388,9 @@ power_supply_find_ocv2cap_table(struct power_supply_battery_info *info, int temp, int *table_len); extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info, int ocv, int temp); +extern int +power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table, + int table_len, int temp); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); extern int power_supply_set_input_current_limit_from_supplier( -- cgit v1.2.3 From 28ca0d6d39ab1d01c86762c82a585b7cedd2920c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 29 Nov 2019 00:11:54 +0300 Subject: list: introduce list_for_each_continue() As other *continue() helpers, this continues iteration from a given position. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/list.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 85c92555e31f..3c391bbd03c3 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -538,6 +538,16 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_for_each(pos, head) \ for (pos = (head)->next; pos != (head); pos = pos->next) +/** + * list_for_each_continue - continue iteration over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + * + * Continue to iterate over a list, continuing after the current position. + */ +#define list_for_each_continue(pos, head) \ + for (pos = pos->next; pos != (head); pos = pos->next) + /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. -- cgit v1.2.3 From 2a10ab043ac5a658225ee77852db7942de9ac4c5 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 17 Dec 2019 13:39:11 +0000 Subject: net: phy: add genphy_check_and_restart_aneg() Add a helper for restarting autonegotiation(), similar to the clause 45 variant. Use it in __genphy_config_aneg() Signed-off-by: Russell King Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 5032d453ac66..1c4f97d2631d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1094,6 +1094,7 @@ void phy_attached_info(struct phy_device *phydev); int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); +int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); -- cgit v1.2.3 From 0efc286a923874f0c243e5766cce54e9429ed949 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 17 Dec 2019 13:39:16 +0000 Subject: net: phy: provide and use genphy_read_status_fixed() There are two drivers and generic code which contain exactly the same code to read the status of a PHY operating without autonegotiation enabled. Rather than duplicate this code, provide a helper to read this information. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1c4f97d2631d..b2105e0d72d3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1100,6 +1100,7 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); +int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); -- cgit v1.2.3 From 96360004b8628541f5d05a845ea213267db0b1a2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Thu, 19 Dec 2019 07:10:03 +0100 Subject: xdp: Make devmap flush_list common for all map instances MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The devmap flush list is used to track entries that need to flushed from via the xdp_do_flush_map() function. This list used to be per-map, but there is really no reason for that. Instead make the flush list global for all devmaps, which simplifies __dev_map_flush() and dev_map_init_map(). Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20191219061006.21980-6-bjorn.topel@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d467983e61bb..31191804ca09 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -959,7 +959,7 @@ struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_flush(struct bpf_map *map); +void __dev_map_flush(void); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, @@ -1068,7 +1068,7 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map return NULL; } -static inline void __dev_map_flush(struct bpf_map *map) +static inline void __dev_map_flush(void) { } -- cgit v1.2.3 From cdfafe98cabefeedbbc65af5c191c59745c03298 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Thu, 19 Dec 2019 07:10:04 +0100 Subject: xdp: Make cpumap flush_list common for all map instances MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The cpumap flush list is used to track entries that need to flushed from via the xdp_do_flush_map() function. This list used to be per-map, but there is really no reason for that. Instead make the flush list global for all devmaps, which simplifies __cpu_map_flush() and cpu_map_alloc(). Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20191219061006.21980-7-bjorn.topel@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 31191804ca09..8f3e00c84f39 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -966,7 +966,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); -void __cpu_map_flush(struct bpf_map *map); +void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -1097,7 +1097,7 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) return NULL; } -static inline void __cpu_map_flush(struct bpf_map *map) +static inline void __cpu_map_flush(void) { } -- cgit v1.2.3 From 332f22a60e4c3492d4953cd6f7aaa4e8bd0bba97 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Thu, 19 Dec 2019 07:10:05 +0100 Subject: xdp: Remove map_to_flush and map swap detection MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that all XDP maps that can be used with bpf_redirect_map() tracks entries to be flushed in a global fashion, there is not need to track that the map has changed and flush from xdp_do_generic_map() anymore. All entries will be flushed in xdp_do_flush_map(). This means that the map_to_flush can be removed, and the corresponding checks. Moving the flush logic to one place, xdp_do_flush_map(), give a bulking behavior and performance boost. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20191219061006.21980-8-bjorn.topel@gmail.com --- include/linux/filter.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 37ac7025031d..69d6706fc889 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -592,7 +592,6 @@ struct bpf_redirect_info { u32 tgt_index; void *tgt_value; struct bpf_map *map; - struct bpf_map *map_to_flush; u32 kern_flags; }; -- cgit v1.2.3 From 7dd68b3279f1792103d12e69933db3128c6d416e Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 18 Dec 2019 23:44:35 -0800 Subject: bpf: Support replacing cgroup-bpf program in MULTI mode The common use-case in production is to have multiple cgroup-bpf programs per attach type that cover multiple use-cases. Such programs are attached with BPF_F_ALLOW_MULTI and can be maintained by different people. Order of programs usually matters, for example imagine two egress programs: the first one drops packets and the second one counts packets. If they're swapped the result of counting program will be different. It brings operational challenges with updating cgroup-bpf program(s) attached with BPF_F_ALLOW_MULTI since there is no way to replace a program: * One way to update is to detach all programs first and then attach the new version(s) again in the right order. This introduces an interruption in the work a program is doing and may not be acceptable (e.g. if it's egress firewall); * Another way is attach the new version of a program first and only then detach the old version. This introduces the time interval when two versions of same program are working, what may not be acceptable if a program is not idempotent. It also imposes additional burden on program developers to make sure that two versions of their program can co-exist. Solve the problem by introducing a "replace" mode in BPF_PROG_ATTACH command for cgroup-bpf programs being attached with BPF_F_ALLOW_MULTI flag. This mode is enabled by newly introduced BPF_F_REPLACE attach flag and bpf_attr.replace_bpf_fd attribute to pass fd of the old program to replace That way user can replace any program among those attached with BPF_F_ALLOW_MULTI flag without the problems described above. Details of the new API: * If BPF_F_REPLACE is set but replace_bpf_fd doesn't have valid descriptor of BPF program, BPF_PROG_ATTACH will return corresponding error (EINVAL or EBADF). * If replace_bpf_fd has valid descriptor of BPF program but such a program is not attached to specified cgroup, BPF_PROG_ATTACH will return ENOENT. BPF_F_REPLACE is introduced to make the user intent clear, since replace_bpf_fd alone can't be used for this (its default value, 0, is a valid fd). BPF_F_REPLACE also makes it possible to extend the API in the future (e.g. add BPF_F_BEFORE and BPF_F_AFTER if needed). Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Acked-by: Andrii Narkyiko Link: https://lore.kernel.org/bpf/30cd850044a0057bdfcaaf154b7d2f39850ba813.1576741281.git.rdna@fb.com --- include/linux/bpf-cgroup.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 169fd25f6bc2..18f6a6da7c3c 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -85,6 +85,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + struct bpf_prog *replace_prog, enum bpf_attach_type type, u32 flags); int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type); @@ -93,7 +94,8 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 flags); + struct bpf_prog *replace_prog, enum bpf_attach_type type, + u32 flags); int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, -- cgit v1.2.3 From 632b0b5301f67ce54b840d55950707003a489151 Mon Sep 17 00:00:00 2001 From: Rijo Thomas Date: Wed, 4 Dec 2019 11:49:03 +0530 Subject: crypto: ccp - provide in-kernel API to submit TEE commands Extend the functionality of AMD Secure Processor (SP) driver by providing an in-kernel API to submit commands to TEE ring buffer for processing by Trusted OS running on AMD Secure Processor. Following TEE commands are supported by Trusted OS: * TEE_CMD_ID_LOAD_TA : Load Trusted Application (TA) binary into TEE environment * TEE_CMD_ID_UNLOAD_TA : Unload TA binary from TEE environment * TEE_CMD_ID_OPEN_SESSION : Open session with loaded TA * TEE_CMD_ID_CLOSE_SESSION : Close session with loaded TA * TEE_CMD_ID_INVOKE_CMD : Invoke a command with loaded TA * TEE_CMD_ID_MAP_SHARED_MEM : Map shared memory * TEE_CMD_ID_UNMAP_SHARED_MEM : Unmap shared memory Linux AMD-TEE driver will use this API to submit command buffers for processing in Trusted Execution Environment. The AMD-TEE driver shall be introduced in a separate patch. Cc: Jens Wiklander Cc: Tom Lendacky Cc: Ard Biesheuvel Co-developed-by: Devaraj Rangasamy Signed-off-by: Devaraj Rangasamy Signed-off-by: Rijo Thomas Acked-by: Gary R Hook Signed-off-by: Herbert Xu --- include/linux/psp-tee.h | 73 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 include/linux/psp-tee.h (limited to 'include/linux') diff --git a/include/linux/psp-tee.h b/include/linux/psp-tee.h new file mode 100644 index 000000000000..63bb2212fce0 --- /dev/null +++ b/include/linux/psp-tee.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: MIT */ +/* + * AMD Trusted Execution Environment (TEE) interface + * + * Author: Rijo Thomas + * + * Copyright 2019 Advanced Micro Devices, Inc. + * + */ + +#ifndef __PSP_TEE_H_ +#define __PSP_TEE_H_ + +#include +#include + +/* This file defines the Trusted Execution Environment (TEE) interface commands + * and the API exported by AMD Secure Processor driver to communicate with + * AMD-TEE Trusted OS. + */ + +/** + * enum tee_cmd_id - TEE Interface Command IDs + * @TEE_CMD_ID_LOAD_TA: Load Trusted Application (TA) binary into + * TEE environment + * @TEE_CMD_ID_UNLOAD_TA: Unload TA binary from TEE environment + * @TEE_CMD_ID_OPEN_SESSION: Open session with loaded TA + * @TEE_CMD_ID_CLOSE_SESSION: Close session with loaded TA + * @TEE_CMD_ID_INVOKE_CMD: Invoke a command with loaded TA + * @TEE_CMD_ID_MAP_SHARED_MEM: Map shared memory + * @TEE_CMD_ID_UNMAP_SHARED_MEM: Unmap shared memory + */ +enum tee_cmd_id { + TEE_CMD_ID_LOAD_TA = 1, + TEE_CMD_ID_UNLOAD_TA, + TEE_CMD_ID_OPEN_SESSION, + TEE_CMD_ID_CLOSE_SESSION, + TEE_CMD_ID_INVOKE_CMD, + TEE_CMD_ID_MAP_SHARED_MEM, + TEE_CMD_ID_UNMAP_SHARED_MEM, +}; + +#ifdef CONFIG_CRYPTO_DEV_SP_PSP +/** + * psp_tee_process_cmd() - Process command in Trusted Execution Environment + * @cmd_id: TEE command ID (&enum tee_cmd_id) + * @buf: Command buffer for TEE processing. On success, is updated + * with the response + * @len: Length of command buffer in bytes + * @status: On success, holds the TEE command execution status + * + * This function submits a command to the Trusted OS for processing in the + * TEE environment and waits for a response or until the command times out. + * + * Returns: + * 0 if TEE successfully processed the command + * -%ENODEV if PSP device not available + * -%EINVAL if invalid input + * -%ETIMEDOUT if TEE command timed out + * -%EBUSY if PSP device is not responsive + */ +int psp_tee_process_cmd(enum tee_cmd_id cmd_id, void *buf, size_t len, + u32 *status); + +#else /* !CONFIG_CRYPTO_DEV_SP_PSP */ + +static inline int psp_tee_process_cmd(enum tee_cmd_id cmd_id, void *buf, + size_t len, u32 *status) +{ + return -ENODEV; +} +#endif /* CONFIG_CRYPTO_DEV_SP_PSP */ +#endif /* __PSP_TEE_H_ */ -- cgit v1.2.3 From c6d633a927499f35a06455a960ad6b5a59c87c2c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 15 Dec 2019 15:51:19 -0800 Subject: crypto: algapi - make unregistration functions return void Some of the algorithm unregistration functions return -ENOENT when asked to unregister a non-registered algorithm, while others always return 0 or always return void. But no users check the return value, except for two of the bulk unregistration functions which print a message on error but still always return 0 to their caller, and crypto_del_alg() which calls crypto_unregister_instance() which always returns 0. Since unregistering a non-registered algorithm is always a kernel bug but there isn't anything callers should do to handle this situation at runtime, let's simplify things by making all the unregistration functions return void, and moving the error message into crypto_unregister_alg() and upgrading it to a WARN(). Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index c23f1eed7970..a905e524e332 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -584,9 +584,9 @@ static inline void crypto_init_wait(struct crypto_wait *wait) * Algorithm registration interface. */ int crypto_register_alg(struct crypto_alg *alg); -int crypto_unregister_alg(struct crypto_alg *alg); +void crypto_unregister_alg(struct crypto_alg *alg); int crypto_register_algs(struct crypto_alg *algs, int count); -int crypto_unregister_algs(struct crypto_alg *algs, int count); +void crypto_unregister_algs(struct crypto_alg *algs, int count); /* * Algorithm query interface. -- cgit v1.2.3 From 4c3718f9d6a6f6557b6e5564af8bd90130123fb8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 9 Dec 2019 01:42:42 +0100 Subject: leds: bd2802: Convert to use GPIO descriptors The Rohm BD2802 have no in-kernel users so we can drop the GPIO number from the platform data and require users to provide the GPIO line using machine descriptors. As the descriptors come with inherent polarity inversion semantics, we invert the calls to set the GPIO line such that 0 means "unasserted" and 1 means "asserted". Put a note in the driver that machine descriptor tables will need to specify that the line is active low. Cc: Kim Kyuwon Signed-off-by: Linus Walleij Signed-off-by: Pavel Machek --- include/linux/leds-bd2802.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/leds-bd2802.h b/include/linux/leds-bd2802.h index dd93c8d787b4..ec577f5f8707 100644 --- a/include/linux/leds-bd2802.h +++ b/include/linux/leds-bd2802.h @@ -11,7 +11,6 @@ #define _LEDS_BD2802_H_ struct bd2802_led_platform_data{ - int reset_gpio; u8 rgb_time; }; -- cgit v1.2.3 From 25f003de987aed630db265ceae9cd978537a3f80 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 19 Dec 2019 12:03:41 +0000 Subject: drivers/iommu: Take a ref to the IOMMU driver prior to ->add_device() To avoid accidental removal of an active IOMMU driver module, take a reference to the driver module in 'iommu_probe_device()' immediately prior to invoking the '->add_device()' callback and hold it until the after the device has been removed by '->remove_device()'. Suggested-by: Joerg Roedel Signed-off-by: Will Deacon Tested-by: John Garry # smmu v3 Reviewed-by: Greg Kroah-Hartman Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f2223cbb5fd5..e9f94d3f7a04 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -246,9 +246,10 @@ struct iommu_iotlb_gather { * @sva_get_pasid: Get PASID associated to a SVA handle * @page_response: handle page request response * @cache_invalidate: invalidate translation caches - * @pgsize_bitmap: bitmap of all possible supported page sizes * @sva_bind_gpasid: bind guest pasid and mm * @sva_unbind_gpasid: unbind guest pasid and mm + * @pgsize_bitmap: bitmap of all possible supported page sizes + * @owner: Driver module providing these ops */ struct iommu_ops { bool (*capable)(enum iommu_cap); @@ -318,6 +319,7 @@ struct iommu_ops { int (*sva_unbind_gpasid)(struct device *dev, int pasid); unsigned long pgsize_bitmap; + struct module *owner; }; /** -- cgit v1.2.3 From f9f6971ebb75f5bc302d77e3380dd6363cc1a0f6 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 18 Dec 2019 14:42:01 +0100 Subject: iommu: Implement generic_iommu_put_resv_regions() Implement a generic function for removing reserved regions. This can be used by drivers that don't do anything fancy with these regions other than allocating memory for them. Signed-off-by: Thierry Reding Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f2223cbb5fd5..e80b83b8cab8 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -456,6 +456,8 @@ extern void iommu_set_fault_handler(struct iommu_domain *domain, extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); +extern void generic_iommu_put_resv_regions(struct device *dev, + struct list_head *list); extern int iommu_request_dm_for_dev(struct device *dev); extern int iommu_request_dma_domain_for_dev(struct device *dev); extern void iommu_set_default_passthrough(bool cmd_line); -- cgit v1.2.3 From 52487e21689b40c8ce967ba97518b3dfaaa2d7b2 Mon Sep 17 00:00:00 2001 From: Jungseung Lee Date: Mon, 2 Dec 2019 15:35:05 +0900 Subject: mtd: spi-nor: Rename SR_TB to indicate the bit used Each vendor uses different bits for SR_TB of flash. To avoid ambiguity, rename SR_TB to indicate the bit used. Signed-off-by: Jungseung Lee Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 5a4623fc586b..5124c306f60b 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -128,7 +128,8 @@ #define SR_BP0 BIT(2) /* Block protect 0 */ #define SR_BP1 BIT(3) /* Block protect 1 */ #define SR_BP2 BIT(4) /* Block protect 2 */ -#define SR_TB BIT(5) /* Top/Bottom protect */ +#define SR_TB_BIT5 BIT(5) /* Top/Bottom protect */ +#define SR_TB_BIT6 BIT(6) /* Top/Bottom protect */ #define SR_SRWD BIT(7) /* SR write protect */ /* Spansion/Cypress specific status bits */ #define SR_E_ERR BIT(5) -- cgit v1.2.3 From adf1092fa838e870813f2ac152973af311d8ae02 Mon Sep 17 00:00:00 2001 From: Jungseung Lee Date: Mon, 2 Dec 2019 15:35:06 +0900 Subject: mtd: spi-nor: Support TB selection using SR bit 6 There are some flashes to use bit 6 of status register for Top/Bottom (TB). Use top/bottom bit variable instead of fixed value and support this case. Set the Top/Bottom (TB) mask based on SPI_NOR_TB_SR_BIT6 flash_info flag. We can't use a bigger granularity, for example to set TB_BIT6 per manufacturer using a SNOR_F flag. The manufacturers don't have a common rule in regards to the TB bit: Winbond : Use the 6th bit from 32MB capacity W25Q20EW, W25Q50BW, W25Q128V - TB(5) W25Q256JV, W25M512JV - TB(6) GigaDevice : Use the 6th bit from 32MB capacity GD25Q16C, GD25Q32C, GD25LQ32D, GD25Q64C, GD25Q128 - TB(5) GD25Q256 - TB(6) Micron/STM : Keep to use 5th bit M25PX64, N25Q128A, N25Q512A, MT25QL512ABB, MT25QL02GCBB - TB(5) Spansion : Use the 6th bit from 16MB capacity S25FL116K, S25FL132K, S25FL165K - TB(5) S25FL128L, S25FL256L - TB(6) We can't make a correlation between TB and BP3 either, i.e. assume that if BP3 is defined then TB will be at BIT(6). Micron breaks this rule. Signed-off-by: Jungseung Lee [tudor.ambarus@microchip.com: describe the reason for setting a new flash_info flag.] Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 5124c306f60b..7e32adce72f7 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -245,6 +245,7 @@ enum spi_nor_option_flags { SNOR_F_HAS_LOCK = BIT(8), SNOR_F_HAS_16BIT_SR = BIT(9), SNOR_F_NO_READ_CR = BIT(10), + SNOR_F_HAS_SR_TB_BIT6 = BIT(11), }; -- cgit v1.2.3 From 89d079dc17e8a32397de827cc85c1f4911b90424 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 24 Sep 2019 14:39:53 +0200 Subject: clk: let init callback return an error code If the init callback is allowed to request resources, it needs a return value to report the outcome of such a request. Signed-off-by: Jerome Brunet Link: https://lkml.kernel.org/r/20190924123954.31561-3-jbrunet@baylibre.com Reviewed-by: Andrew Lunn Acked-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index caf4b9df16eb..eed243c2c73e 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -190,8 +190,12 @@ struct clk_duty { * * @init: Perform platform-specific initialization magic. * This is not not used by any of the basic clock types. - * Please consider other ways of solving initialization problems - * before using this callback, as its use is discouraged. + * This callback exist for HW which needs to perform some + * initialisation magic for CCF to get an accurate view of the + * clock. It may also be used dynamic resource allocation is + * required. It shall not used to deal with clock parameters, + * such as rate or parents. + * Returns 0 on success, -EERROR otherwise. * * @debug_init: Set up type-specific debugfs entries for this clock. This * is called once, after the debugfs directory entry for this @@ -243,7 +247,7 @@ struct clk_ops { struct clk_duty *duty); int (*set_duty_cycle)(struct clk_hw *hw, struct clk_duty *duty); - void (*init)(struct clk_hw *hw); + int (*init)(struct clk_hw *hw); void (*debug_init)(struct clk_hw *hw, struct dentry *dentry); }; -- cgit v1.2.3 From f873744c29036cc734ec8ecbedd1a451ce61cef2 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 24 Sep 2019 14:39:54 +0200 Subject: clk: add terminate callback to clk_ops Add a terminate callback to the clk_ops to release the resources claimed in .init() Signed-off-by: Jerome Brunet Link: https://lkml.kernel.org/r/20190924123954.31561-4-jbrunet@baylibre.com Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index eed243c2c73e..013dc667a500 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -197,6 +197,8 @@ struct clk_duty { * such as rate or parents. * Returns 0 on success, -EERROR otherwise. * + * @terminate: Free any resource allocated by init. + * * @debug_init: Set up type-specific debugfs entries for this clock. This * is called once, after the debugfs directory entry for this * clock has been created. The dentry pointer representing that @@ -248,6 +250,7 @@ struct clk_ops { int (*set_duty_cycle)(struct clk_hw *hw, struct clk_duty *duty); int (*init)(struct clk_hw *hw); + void (*terminate)(struct clk_hw *hw); void (*debug_init)(struct clk_hw *hw, struct dentry *dentry); }; -- cgit v1.2.3 From dae7a589c18a4d979d5f14b09374e871b995ceb1 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Mon, 16 Dec 2019 12:01:16 -0700 Subject: dmaengine: Store module owner in dma_device struct dma_chan_to_owner() dereferences the driver from the struct device to obtain the owner and call module_[get|put](). However, if the backing device is unbound before the dma_device is unregistered, the driver will be cleared and this will cause a NULL pointer dereference. Instead, store a pointer to the owner module in the dma_device struct so the module reference can be properly put when the channel is put, even if the backing device was destroyed first. This change helps to support a safer unbind of DMA engines. If the dma_device is unregistered in the driver's remove function, there's no guarantee that there are no existing clients and a users action may trigger the WARN_ONCE in dma_async_device_unregister() which is unlikely to leave the system in a consistent state. Instead, a better approach is to allow the backing driver to go away and fail any subsequent requests to it. Signed-off-by: Logan Gunthorpe Link: https://lore.kernel.org/r/20191216190120.21374-2-logang@deltatee.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index dfd2d35b64af..11b15a2e97a0 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -674,6 +674,7 @@ struct dma_filter { * @fill_align: alignment shift for memset operations * @dev_id: unique device ID * @dev: struct device reference for dma mapping api + * @owner: owner module (automatically set based on the provided dev) * @src_addr_widths: bit mask of src addr widths the device supports * Width is specified in bytes, e.g. for a device supporting * a width of 4 the mask should have BIT(4) set. @@ -737,6 +738,7 @@ struct dma_device { int dev_id; struct device *dev; + struct module *owner; u32 src_addr_widths; u32 dst_addr_widths; -- cgit v1.2.3 From 8ad342a863590b24ce77681b7e081363fb3333f7 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Mon, 16 Dec 2019 12:01:19 -0700 Subject: dmaengine: Add reference counting to dma_device struct Adding a reference count helps drivers to properly implement the unbind while in use case. References are taken and put every time a channel is allocated or freed. Once the final reference is put, the device is removed from the dma_device_list and a release callback function is called to signal the driver to free the memory. Signed-off-by: Logan Gunthorpe Link: https://lore.kernel.org/r/20191216190120.21374-5-logang@deltatee.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 11b15a2e97a0..7927731e3716 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -719,9 +719,14 @@ struct dma_filter { * will just return a simple status code * @device_issue_pending: push pending transactions to hardware * @descriptor_reuse: a submitted transfer can be resubmitted after completion + * @device_release: called sometime atfer dma_async_device_unregister() is + * called and there are no further references to this structure. This + * must be implemented to free resources however many existing drivers + * do not and are therefore not safe to unbind while in use. + * */ struct dma_device { - + struct kref ref; unsigned int chancnt; unsigned int privatecnt; struct list_head channels; @@ -802,6 +807,7 @@ struct dma_device { dma_cookie_t cookie, struct dma_tx_state *txstate); void (*device_issue_pending)(struct dma_chan *chan); + void (*device_release)(struct dma_device *dev); }; static inline int dmaengine_slave_config(struct dma_chan *chan, -- cgit v1.2.3 From ee7a9c9f67c59008b330deff2762bd8cf1407eec Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 21 Dec 2018 18:08:08 +0000 Subject: firmware: arm_scmi: Add support for multiple device per protocol Currently only one scmi device is created for each protocol enumerated. However, there is requirement to make use of some procotols by multiple kernel subsystems/frameworks. One such example is SCMI PERFORMANCE protocol which can be used by both cpufreq and devfreq drivers. Similarly, SENSOR protocol may be used by hwmon and iio subsystems, and POWER protocol may be used by genpd and regulator drivers. In order to achieve that, let us extend the scmi bus to match based not only protocol id but also the scmi device name if one is available. Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 881fea47c83d..5c873a59b387 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -257,6 +257,7 @@ enum scmi_std_protocol { struct scmi_device { u32 id; u8 protocol_id; + const char *name; struct device dev; struct scmi_handle *handle; }; @@ -264,11 +265,13 @@ struct scmi_device { #define to_scmi_dev(d) container_of(d, struct scmi_device, dev) struct scmi_device * -scmi_device_create(struct device_node *np, struct device *parent, int protocol); +scmi_device_create(struct device_node *np, struct device *parent, int protocol, + const char *name); void scmi_device_destroy(struct scmi_device *scmi_dev); struct scmi_device_id { u8 protocol_id; + const char *name; }; struct scmi_driver { -- cgit v1.2.3 From 463f550fb47bede3a5d7d5177f363a6c3b45d50b Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 11 Dec 2019 11:17:12 -0500 Subject: rseq: Unregister rseq for clone CLONE_VM It has been reported by Google that rseq is not behaving properly with respect to clone when CLONE_VM is used without CLONE_THREAD. It keeps the prior thread's rseq TLS registered when the TLS of the thread has moved, so the kernel can corrupt the TLS of the parent. The approach of clearing the per task-struct rseq registration on clone with CLONE_THREAD flag is incomplete. It does not cover the use-case of clone with CLONE_VM set, but without CLONE_THREAD. Here is the rationale for unregistering rseq on clone with CLONE_VM flag set: 1) CLONE_THREAD requires CLONE_SIGHAND, which requires CLONE_VM to be set. Therefore, just checking for CLONE_VM covers all CLONE_THREAD uses. There is no point in checking for both CLONE_THREAD and CLONE_VM, 2) There is the possibility of an unlikely scenario where CLONE_SETTLS is used without CLONE_VM. In order to be an issue, it would require that the rseq TLS is in a shared memory area. I do not plan on adding CLONE_SETTLS to the set of clone flags which unregister RSEQ, because it would require that we also unregister RSEQ on set_thread_area(2) and arch_prctl(2) ARCH_SET_FS for completeness. So rather than doing a partial solution, it appears better to let user-space explicitly perform rseq unregistration across clone if needed in scenarios where CLONE_VM is not set. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191211161713.4490-3-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 467d26046416..716ad1d8d95e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1929,11 +1929,11 @@ static inline void rseq_migrate(struct task_struct *t) /* * If parent process has a registered restartable sequences area, the - * child inherits. Only applies when forking a process, not a thread. + * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { - if (clone_flags & CLONE_THREAD) { + if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_sig = 0; t->rseq_event_mask = 0; -- cgit v1.2.3 From 8d62af1778125bd674cc66e8432305cc6aac5d89 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Tue, 24 Dec 2019 16:10:01 +0100 Subject: efi/gop: Remove bogus packed attribute from GOP structures EFI structures are not packed, they follow natural alignment. The packed attribute doesn't have any effect on the structure layout due to the types and order of the members, and we only ever get these structures as output from the EFI firmware so alignment issues have not come up. Signed-off-by: Arvind Sankar Signed-off-by: Ard Biesheuvel Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-2-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index aa54586db7a5..83a62f5c3fd7 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1429,7 +1429,7 @@ struct efi_graphics_output_mode_info { int pixel_format; struct efi_pixel_bitmask pixel_information; u32 pixels_per_scan_line; -} __packed; +}; struct efi_graphics_output_protocol_mode_32 { u32 max_mode; @@ -1438,7 +1438,7 @@ struct efi_graphics_output_protocol_mode_32 { u32 size_of_info; u64 frame_buffer_base; u32 frame_buffer_size; -} __packed; +}; struct efi_graphics_output_protocol_mode_64 { u32 max_mode; @@ -1447,7 +1447,7 @@ struct efi_graphics_output_protocol_mode_64 { u64 size_of_info; u64 frame_buffer_base; u64 frame_buffer_size; -} __packed; +}; struct efi_graphics_output_protocol_mode { u32 max_mode; @@ -1456,7 +1456,7 @@ struct efi_graphics_output_protocol_mode { unsigned long size_of_info; u64 frame_buffer_base; unsigned long frame_buffer_size; -} __packed; +}; struct efi_graphics_output_protocol_32 { u32 query_mode; -- cgit v1.2.3 From 6c895c2fca8a8d4e740b5498b48f81111569502a Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Tue, 24 Dec 2019 16:10:02 +0100 Subject: efi/gop: Remove unused typedef We have stopped using gop->query_mode(), so remove the unused typedef for the function prototype. Signed-off-by: Arvind Sankar Signed-off-by: Ard Biesheuvel Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-3-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 83a62f5c3fd7..9ea81cfe1576 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1479,10 +1479,6 @@ struct efi_graphics_output_protocol { struct efi_graphics_output_protocol_mode *mode; }; -typedef efi_status_t (*efi_graphics_output_protocol_query_mode)( - struct efi_graphics_output_protocol *, u32, unsigned long *, - struct efi_graphics_output_mode_info **); - extern struct list_head efivar_sysfs_list; static inline void -- cgit v1.2.3 From 44c84b4ada73b8ff156181fcf6e320459b8daefd Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Tue, 24 Dec 2019 16:10:03 +0100 Subject: efi/gop: Convert GOP structures to typedef and clean up some types Use typedef for the GOP structures, in anticipation of unifying 32/64-bit code. Also use more appropriate types in the non-bitness specific structures for the framebuffer address and pointers. Signed-off-by: Arvind Sankar Signed-off-by: Ard Biesheuvel Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-4-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 9ea81cfe1576..561db9deedae 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1415,69 +1415,69 @@ struct efi_simple_text_output_protocol { #define PIXEL_BLT_ONLY 3 #define PIXEL_FORMAT_MAX 4 -struct efi_pixel_bitmask { +typedef struct { u32 red_mask; u32 green_mask; u32 blue_mask; u32 reserved_mask; -}; +} efi_pixel_bitmask_t; -struct efi_graphics_output_mode_info { +typedef struct { u32 version; u32 horizontal_resolution; u32 vertical_resolution; int pixel_format; - struct efi_pixel_bitmask pixel_information; + efi_pixel_bitmask_t pixel_information; u32 pixels_per_scan_line; -}; +} efi_graphics_output_mode_info_t; -struct efi_graphics_output_protocol_mode_32 { +typedef struct { u32 max_mode; u32 mode; u32 info; u32 size_of_info; u64 frame_buffer_base; u32 frame_buffer_size; -}; +} efi_graphics_output_protocol_mode_32_t; -struct efi_graphics_output_protocol_mode_64 { +typedef struct { u32 max_mode; u32 mode; u64 info; u64 size_of_info; u64 frame_buffer_base; u64 frame_buffer_size; -}; +} efi_graphics_output_protocol_mode_64_t; -struct efi_graphics_output_protocol_mode { +typedef struct { u32 max_mode; u32 mode; - unsigned long info; + efi_graphics_output_mode_info_t *info; unsigned long size_of_info; - u64 frame_buffer_base; + efi_physical_addr_t frame_buffer_base; unsigned long frame_buffer_size; -}; +} efi_graphics_output_protocol_mode_t; -struct efi_graphics_output_protocol_32 { +typedef struct { u32 query_mode; u32 set_mode; u32 blt; u32 mode; -}; +} efi_graphics_output_protocol_32_t; -struct efi_graphics_output_protocol_64 { +typedef struct { u64 query_mode; u64 set_mode; u64 blt; u64 mode; -}; +} efi_graphics_output_protocol_64_t; -struct efi_graphics_output_protocol { - unsigned long query_mode; - unsigned long set_mode; - unsigned long blt; - struct efi_graphics_output_protocol_mode *mode; -}; +typedef struct { + void *query_mode; + void *set_mode; + void *blt; + efi_graphics_output_protocol_mode_t *mode; +} efi_graphics_output_protocol_t; extern struct list_head efivar_sysfs_list; -- cgit v1.2.3 From 2732ea0d5c0a67ec86bfbde2bd68b6152e23ec4e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:07 +0100 Subject: efi/libstub: Use a helper to iterate over a EFI handle array Iterating over a EFI handle array is a bit finicky, since we have to take mixed mode into account, where handles are only 32-bit while the native efi_handle_t type is 64-bit. So introduce a helper, and replace the various occurrences of this pattern. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-8-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 561db9deedae..8d267715ce22 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -48,6 +48,19 @@ typedef u16 efi_char16_t; /* UNICODE character */ typedef u64 efi_physical_addr_t; typedef void *efi_handle_t; +#define efi_get_handle_at(array, idx) \ + (efi_is_64bit() ? (efi_handle_t)(unsigned long)((u64 *)(array))[idx] \ + : (efi_handle_t)(unsigned long)((u32 *)(array))[idx]) + +#define efi_get_handle_num(size) \ + ((size) / (efi_is_64bit() ? sizeof(u64) : sizeof(u32))) + +#define for_each_efi_handle(handle, array, size, i) \ + for (i = 0; \ + i < efi_get_handle_num(size) && \ + ((handle = efi_get_handle_at((array), i)) || true); \ + i++) + /* * The UEFI spec and EDK2 reference implementation both define EFI_GUID as * struct { u32 a; u16; b; u16 c; u8 d[8]; }; and so the implied alignment -- cgit v1.2.3 From 1786e83011644e18732ed006413339d5323766e9 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:08 +0100 Subject: efi/libstub: Extend native protocol definitions with mixed_mode aliases In preparation of moving to a native vs. mixed mode split rather than a 32 vs. 64 bit split when it comes to invoking EFI firmware services, update all the native protocol definitions and redefine them as unions containing an anonymous struct for the native view and a struct called 'mixed_mode' describing the 32-bit view of the protocol when called from 64-bit code. While at it, flesh out some PCI I/O member definitions that we will be needing shortly. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-9-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 496 ++++++++++++++++++++++++++++++++++------------------ 1 file changed, 330 insertions(+), 166 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8d267715ce22..5a220af263b1 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -315,55 +315,58 @@ typedef struct { /* * EFI Boot Services table */ -typedef struct { - efi_table_hdr_t hdr; - void *raise_tpl; - void *restore_tpl; - efi_status_t (*allocate_pages)(int, int, unsigned long, - efi_physical_addr_t *); - efi_status_t (*free_pages)(efi_physical_addr_t, unsigned long); - efi_status_t (*get_memory_map)(unsigned long *, void *, unsigned long *, - unsigned long *, u32 *); - efi_status_t (*allocate_pool)(int, unsigned long, void **); - efi_status_t (*free_pool)(void *); - void *create_event; - void *set_timer; - void *wait_for_event; - void *signal_event; - void *close_event; - void *check_event; - void *install_protocol_interface; - void *reinstall_protocol_interface; - void *uninstall_protocol_interface; - efi_status_t (*handle_protocol)(efi_handle_t, efi_guid_t *, void **); - void *__reserved; - void *register_protocol_notify; - efi_status_t (*locate_handle)(int, efi_guid_t *, void *, - unsigned long *, efi_handle_t *); - void *locate_device_path; - efi_status_t (*install_configuration_table)(efi_guid_t *, void *); - void *load_image; - void *start_image; - void *exit; - void *unload_image; - efi_status_t (*exit_boot_services)(efi_handle_t, unsigned long); - void *get_next_monotonic_count; - void *stall; - void *set_watchdog_timer; - void *connect_controller; - void *disconnect_controller; - void *open_protocol; - void *close_protocol; - void *open_protocol_information; - void *protocols_per_handle; - void *locate_handle_buffer; - efi_status_t (*locate_protocol)(efi_guid_t *, void *, void **); - void *install_multiple_protocol_interfaces; - void *uninstall_multiple_protocol_interfaces; - void *calculate_crc32; - void *copy_mem; - void *set_mem; - void *create_event_ex; +typedef union { + struct { + efi_table_hdr_t hdr; + void *raise_tpl; + void *restore_tpl; + efi_status_t (*allocate_pages)(int, int, unsigned long, + efi_physical_addr_t *); + efi_status_t (*free_pages)(efi_physical_addr_t, unsigned long); + efi_status_t (*get_memory_map)(unsigned long *, void *, unsigned long *, + unsigned long *, u32 *); + efi_status_t (*allocate_pool)(int, unsigned long, void **); + efi_status_t (*free_pool)(void *); + void *create_event; + void *set_timer; + void *wait_for_event; + void *signal_event; + void *close_event; + void *check_event; + void *install_protocol_interface; + void *reinstall_protocol_interface; + void *uninstall_protocol_interface; + efi_status_t (*handle_protocol)(efi_handle_t, efi_guid_t *, void **); + void *__reserved; + void *register_protocol_notify; + efi_status_t (*locate_handle)(int, efi_guid_t *, void *, + unsigned long *, efi_handle_t *); + void *locate_device_path; + efi_status_t (*install_configuration_table)(efi_guid_t *, void *); + void *load_image; + void *start_image; + void *exit; + void *unload_image; + efi_status_t (*exit_boot_services)(efi_handle_t, unsigned long); + void *get_next_monotonic_count; + void *stall; + void *set_watchdog_timer; + void *connect_controller; + void *disconnect_controller; + void *open_protocol; + void *close_protocol; + void *open_protocol_information; + void *protocols_per_handle; + void *locate_handle_buffer; + efi_status_t (*locate_protocol)(efi_guid_t *, void *, void **); + void *install_multiple_protocol_interfaces; + void *uninstall_multiple_protocol_interfaces; + void *calculate_crc32; + void *copy_mem; + void *set_mem; + void *create_event_ex; + }; + efi_boot_services_32_t mixed_mode; } efi_boot_services_t; typedef enum { @@ -401,11 +404,24 @@ typedef struct { u64 write; } efi_pci_io_protocol_access_64_t; +typedef union efi_pci_io_protocol efi_pci_io_protocol_t; + +typedef +efi_status_t (*efi_pci_io_protocol_cfg_t)(efi_pci_io_protocol_t *, + EFI_PCI_IO_PROTOCOL_WIDTH, + u32 offset, unsigned long count, + void *buffer); + typedef struct { void *read; void *write; } efi_pci_io_protocol_access_t; +typedef struct { + efi_pci_io_protocol_cfg_t read; + efi_pci_io_protocol_cfg_t write; +} efi_pci_io_protocol_config_access_t; + typedef struct { u32 poll_mem; u32 poll_io; @@ -446,25 +462,46 @@ typedef struct { u64 romimage; } efi_pci_io_protocol_64_t; -typedef struct { - void *poll_mem; - void *poll_io; - efi_pci_io_protocol_access_t mem; - efi_pci_io_protocol_access_t io; - efi_pci_io_protocol_access_t pci; - void *copy_mem; - void *map; - void *unmap; - void *allocate_buffer; - void *free_buffer; - void *flush; - void *get_location; - void *attributes; - void *get_bar_attributes; - void *set_bar_attributes; - uint64_t romsize; - void *romimage; -} efi_pci_io_protocol_t; +union efi_pci_io_protocol { + struct { + void *poll_mem; + void *poll_io; + efi_pci_io_protocol_access_t mem; + efi_pci_io_protocol_access_t io; + efi_pci_io_protocol_config_access_t pci; + void *copy_mem; + void *map; + void *unmap; + void *allocate_buffer; + void *free_buffer; + void *flush; + void *get_location; + void *attributes; + void *get_bar_attributes; + void *set_bar_attributes; + uint64_t romsize; + void *romimage; + }; + struct { + u32 poll_mem; + u32 poll_io; + efi_pci_io_protocol_access_32_t mem; + efi_pci_io_protocol_access_32_t io; + efi_pci_io_protocol_access_32_t pci; + u32 copy_mem; + u32 map; + u32 unmap; + u32 allocate_buffer; + u32 free_buffer; + u32 flush; + u32 get_location; + u32 attributes; + u32 get_bar_attributes; + u32 set_bar_attributes; + u64 romsize; + u32 romimage; + } mixed_mode; +}; #define EFI_PCI_IO_ATTRIBUTE_ISA_MOTHERBOARD_IO 0x0001 #define EFI_PCI_IO_ATTRIBUTE_ISA_IO 0x0002 @@ -502,6 +539,33 @@ typedef struct { u64 get_all; } apple_properties_protocol_64_t; +struct efi_dev_path; + +typedef union apple_properties_protocol apple_properties_protocol_t; + +union apple_properties_protocol { + struct { + unsigned long version; + efi_status_t (*get)(apple_properties_protocol_t *, + struct efi_dev_path *, efi_char16_t *, + void *, u32 *); + efi_status_t (*set)(apple_properties_protocol_t *, + struct efi_dev_path *, efi_char16_t *, + void *, u32); + efi_status_t (*del)(apple_properties_protocol_t *, + struct efi_dev_path *, efi_char16_t *); + efi_status_t (*get_all)(apple_properties_protocol_t *, + void *buffer, u32 *); + }; + struct { + u32 version; + u32 get; + u32 set; + u32 del; + u32 get_all; + } mixed_mode; +}; + typedef struct { u32 get_capability; u32 get_event_log; @@ -524,16 +588,32 @@ typedef struct { typedef u32 efi_tcg2_event_log_format; -typedef struct { - void *get_capability; - efi_status_t (*get_event_log)(efi_handle_t, efi_tcg2_event_log_format, - efi_physical_addr_t *, efi_physical_addr_t *, efi_bool_t *); - void *hash_log_extend_event; - void *submit_command; - void *get_active_pcr_banks; - void *set_active_pcr_banks; - void *get_result_of_set_active_pcr_banks; -} efi_tcg2_protocol_t; +typedef union efi_tcg2_protocol efi_tcg2_protocol_t; + +union efi_tcg2_protocol { + struct { + void *get_capability; + efi_status_t (*get_event_log)(efi_handle_t, + efi_tcg2_event_log_format, + efi_physical_addr_t *, + efi_physical_addr_t *, + efi_bool_t *); + void *hash_log_extend_event; + void *submit_command; + void *get_active_pcr_banks; + void *set_active_pcr_banks; + void *get_result_of_set_active_pcr_banks; + }; + struct { + u32 get_capability; + u32 get_event_log; + u32 hash_log_extend_event; + u32 submit_command; + u32 get_active_pcr_banks; + u32 set_active_pcr_banks; + u32 get_result_of_set_active_pcr_banks; + } mixed_mode; +}; /* * Types and defines for EFI ResetSystem @@ -618,22 +698,25 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size, bool nonblocking); -typedef struct { - efi_table_hdr_t hdr; - efi_get_time_t *get_time; - efi_set_time_t *set_time; - efi_get_wakeup_time_t *get_wakeup_time; - efi_set_wakeup_time_t *set_wakeup_time; - efi_set_virtual_address_map_t *set_virtual_address_map; - void *convert_pointer; - efi_get_variable_t *get_variable; - efi_get_next_variable_t *get_next_variable; - efi_set_variable_t *set_variable; - efi_get_next_high_mono_count_t *get_next_high_mono_count; - efi_reset_system_t *reset_system; - efi_update_capsule_t *update_capsule; - efi_query_capsule_caps_t *query_capsule_caps; - efi_query_variable_info_t *query_variable_info; +typedef union { + struct { + efi_table_hdr_t hdr; + efi_get_time_t *get_time; + efi_set_time_t *set_time; + efi_get_wakeup_time_t *get_wakeup_time; + efi_set_wakeup_time_t *set_wakeup_time; + efi_set_virtual_address_map_t *set_virtual_address_map; + void *convert_pointer; + efi_get_variable_t *get_variable; + efi_get_next_variable_t *get_next_variable; + efi_set_variable_t *set_variable; + efi_get_next_high_mono_count_t *get_next_high_mono_count; + efi_reset_system_t *reset_system; + efi_update_capsule_t *update_capsule; + efi_query_capsule_caps_t *query_capsule_caps; + efi_query_variable_info_t *query_variable_info; + }; + efi_runtime_services_32_t mixed_mode; } efi_runtime_services_t; void efi_native_runtime_setup(void); @@ -719,9 +802,12 @@ typedef struct { u32 table; } efi_config_table_32_t; -typedef struct { - efi_guid_t guid; - unsigned long table; +typedef union { + struct { + efi_guid_t guid; + unsigned long table; + }; + efi_config_table_32_t mixed_mode; } efi_config_table_t; typedef struct { @@ -773,20 +859,23 @@ typedef struct { u32 tables; } efi_system_table_32_t; -typedef struct { - efi_table_hdr_t hdr; - unsigned long fw_vendor; /* physical addr of CHAR16 vendor string */ - u32 fw_revision; - unsigned long con_in_handle; - unsigned long con_in; - unsigned long con_out_handle; - unsigned long con_out; - unsigned long stderr_handle; - unsigned long stderr; - efi_runtime_services_t *runtime; - efi_boot_services_t *boottime; - unsigned long nr_tables; - unsigned long tables; +typedef union { + struct { + efi_table_hdr_t hdr; + unsigned long fw_vendor; /* physical addr of CHAR16 vendor string */ + u32 fw_revision; + unsigned long con_in_handle; + unsigned long con_in; + unsigned long con_out_handle; + unsigned long con_out; + unsigned long stderr_handle; + unsigned long stderr; + efi_runtime_services_t *runtime; + efi_boot_services_t *boottime; + unsigned long nr_tables; + unsigned long tables; + }; + efi_system_table_32_t mixed_mode; } efi_system_table_t; /* @@ -856,22 +945,40 @@ typedef struct { u64 unload; } efi_loaded_image_64_t; -typedef struct { - u32 revision; - efi_handle_t parent_handle; - efi_system_table_t *system_table; - efi_handle_t device_handle; - void *file_path; - void *reserved; - u32 load_options_size; - void *load_options; - void *image_base; - __aligned_u64 image_size; - unsigned int image_code_type; - unsigned int image_data_type; - efi_status_t (*unload)(efi_handle_t image_handle); -} efi_loaded_image_t; +typedef union efi_loaded_image efi_loaded_image_t; +union efi_loaded_image { + struct { + u32 revision; + efi_handle_t parent_handle; + efi_system_table_t *system_table; + efi_handle_t device_handle; + void *file_path; + void *reserved; + u32 load_options_size; + void *load_options; + void *image_base; + __aligned_u64 image_size; + unsigned int image_code_type; + unsigned int image_data_type; + efi_status_t (*unload)(efi_handle_t image_handle); + }; + struct { + u32 revision; + u32 parent_handle; + u32 system_table; + u32 device_handle; + u32 file_path; + u32 reserved; + u32 load_options_size; + u32 load_options; + u32 image_base; + __aligned_u64 image_size; + unsigned int image_code_type; + unsigned int image_data_type; + u32 unload; + } mixed_mode; +}; typedef struct { u64 size; @@ -912,23 +1019,40 @@ typedef struct { u64 flush; } efi_file_handle_64_t; -typedef struct _efi_file_handle { - u64 revision; - efi_status_t (*open)(struct _efi_file_handle *, - struct _efi_file_handle **, - efi_char16_t *, u64, u64); - efi_status_t (*close)(struct _efi_file_handle *); - void *delete; - efi_status_t (*read)(struct _efi_file_handle *, unsigned long *, - void *); - void *write; - void *get_position; - void *set_position; - efi_status_t (*get_info)(struct _efi_file_handle *, efi_guid_t *, - unsigned long *, void *); - void *set_info; - void *flush; -} efi_file_handle_t; +typedef union efi_file_handle efi_file_handle_t; + +union efi_file_handle { + struct { + u64 revision; + efi_status_t (*open)(efi_file_handle_t *, + efi_file_handle_t **, + efi_char16_t *, u64, u64); + efi_status_t (*close)(efi_file_handle_t *); + void *delete; + efi_status_t (*read)(efi_file_handle_t *, unsigned long *, + void *); + void *write; + void *get_position; + void *set_position; + efi_status_t (*get_info)(efi_file_handle_t *, efi_guid_t *, + unsigned long *, void *); + void *set_info; + void *flush; + }; + struct { + u64 revision; + u32 open; + u32 close; + u32 delete; + u32 read; + u32 write; + u32 get_position; + u32 set_position; + u32 get_info; + u32 set_info; + u32 flush; + } mixed_mode; +}; typedef struct { u64 revision; @@ -940,11 +1064,19 @@ typedef struct { u64 open_volume; } efi_file_io_interface_64_t; -typedef struct _efi_file_io_interface { - u64 revision; - int (*open_volume)(struct _efi_file_io_interface *, - efi_file_handle_t **); -} efi_file_io_interface_t; +typedef union efi_file_io_interface efi_file_io_interface_t; + +union efi_file_io_interface { + struct { + u64 revision; + int (*open_volume)(efi_file_io_interface_t *, + efi_file_handle_t **); + }; + struct { + u64 revision; + u32 open_volume; + } mixed_mode; +} ; #define EFI_FILE_MODE_READ 0x0000000000000001 #define EFI_FILE_MODE_WRITE 0x0000000000000002 @@ -1416,10 +1548,20 @@ typedef struct { u64 test_string; } efi_simple_text_output_protocol_64_t; -struct efi_simple_text_output_protocol { - void *reset; - efi_status_t (*output_string)(void *, void *); - void *test_string; +typedef union efi_simple_text_output_protocol efi_simple_text_output_protocol_t; + +union efi_simple_text_output_protocol { + struct { + void *reset; + efi_status_t (*output_string)(efi_simple_text_output_protocol_t *, + efi_char16_t *); + void *test_string; + }; + struct { + u32 reset; + u32 output_string; + u32 test_string; + } mixed_mode; }; #define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0 @@ -1462,14 +1604,26 @@ typedef struct { u64 frame_buffer_size; } efi_graphics_output_protocol_mode_64_t; -typedef struct { - u32 max_mode; - u32 mode; - efi_graphics_output_mode_info_t *info; - unsigned long size_of_info; - efi_physical_addr_t frame_buffer_base; - unsigned long frame_buffer_size; -} efi_graphics_output_protocol_mode_t; +typedef union efi_graphics_output_protocol_mode efi_graphics_output_protocol_mode_t; + +union efi_graphics_output_protocol_mode { + struct { + u32 max_mode; + u32 mode; + efi_graphics_output_mode_info_t *info; + unsigned long size_of_info; + efi_physical_addr_t frame_buffer_base; + unsigned long frame_buffer_size; + }; + struct { + u32 max_mode; + u32 mode; + u32 info; + u32 size_of_info; + u64 frame_buffer_base; + u32 frame_buffer_size; + } mixed_mode; +}; typedef struct { u32 query_mode; @@ -1485,12 +1639,22 @@ typedef struct { u64 mode; } efi_graphics_output_protocol_64_t; -typedef struct { - void *query_mode; - void *set_mode; - void *blt; - efi_graphics_output_protocol_mode_t *mode; -} efi_graphics_output_protocol_t; +typedef union efi_graphics_output_protocol efi_graphics_output_protocol_t; + +union efi_graphics_output_protocol { + struct { + void *query_mode; + void *set_mode; + void *blt; + efi_graphics_output_protocol_mode_t *mode; + }; + struct { + u32 query_mode; + u32 set_mode; + u32 blt; + u32 mode; + } mixed_mode; +}; extern struct list_head efivar_sysfs_list; -- cgit v1.2.3 From f958efe97596837f9504fc38d75ef8e284bc0ebd Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:09 +0100 Subject: efi/libstub: Distinguish between native/mixed not 32/64 bit Currently, we support mixed mode by casting all boot time firmware calls to 64-bit explicitly on native 64-bit systems, and to 32-bit on 32-bit systems or 64-bit systems running with 32-bit firmware. Due to this explicit awareness of the bitness in the code, we do a lot of casting even on generic code that is shared with other architectures, where mixed mode does not even exist. This casting leads to loss of coverage of type checking by the compiler, which we should try to avoid. So instead of distinguishing between 32-bit vs 64-bit, distinguish between native vs mixed, and limit all the nasty casting and pointer mangling to the code that actually deals with mixed mode. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-10-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 5a220af263b1..e9d74e9667c0 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -49,11 +49,11 @@ typedef u64 efi_physical_addr_t; typedef void *efi_handle_t; #define efi_get_handle_at(array, idx) \ - (efi_is_64bit() ? (efi_handle_t)(unsigned long)((u64 *)(array))[idx] \ + (efi_is_native() ? (array)[idx] \ : (efi_handle_t)(unsigned long)((u32 *)(array))[idx]) #define efi_get_handle_num(size) \ - ((size) / (efi_is_64bit() ? sizeof(u64) : sizeof(u32))) + ((size) / (efi_is_native() ? sizeof(efi_handle_t) : sizeof(u32))) #define for_each_efi_handle(handle, array, size, i) \ for (i = 0; \ @@ -805,7 +805,7 @@ typedef struct { typedef union { struct { efi_guid_t guid; - unsigned long table; + void *table; }; efi_config_table_32_t mixed_mode; } efi_config_table_t; -- cgit v1.2.3 From e8bd5ddf60eedd6d584fa1e98d0cfe45abe95043 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:10 +0100 Subject: efi/libstub: Drop explicit 32/64-bit protocol definitions Now that we have incorporated the mixed mode protocol definitions into the native ones using unions, we no longer need the separate 32/64 bit struct definitions, with the exception of the EFI system table definition and the boot services, runtime services and configuration table definitions. So drop the unused ones. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-11-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 245 +--------------------------------------------------- 1 file changed, 1 insertion(+), 244 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index e9d74e9667c0..d8e987910853 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -264,54 +264,6 @@ typedef struct { u32 create_event_ex; } __packed efi_boot_services_32_t; -typedef struct { - efi_table_hdr_t hdr; - u64 raise_tpl; - u64 restore_tpl; - u64 allocate_pages; - u64 free_pages; - u64 get_memory_map; - u64 allocate_pool; - u64 free_pool; - u64 create_event; - u64 set_timer; - u64 wait_for_event; - u64 signal_event; - u64 close_event; - u64 check_event; - u64 install_protocol_interface; - u64 reinstall_protocol_interface; - u64 uninstall_protocol_interface; - u64 handle_protocol; - u64 __reserved; - u64 register_protocol_notify; - u64 locate_handle; - u64 locate_device_path; - u64 install_configuration_table; - u64 load_image; - u64 start_image; - u64 exit; - u64 unload_image; - u64 exit_boot_services; - u64 get_next_monotonic_count; - u64 stall; - u64 set_watchdog_timer; - u64 connect_controller; - u64 disconnect_controller; - u64 open_protocol; - u64 close_protocol; - u64 open_protocol_information; - u64 protocols_per_handle; - u64 locate_handle_buffer; - u64 locate_protocol; - u64 install_multiple_protocol_interfaces; - u64 uninstall_multiple_protocol_interfaces; - u64 calculate_crc32; - u64 copy_mem; - u64 set_mem; - u64 create_event_ex; -} __packed efi_boot_services_64_t; - /* * EFI Boot Services table */ @@ -399,11 +351,6 @@ typedef struct { u32 write; } efi_pci_io_protocol_access_32_t; -typedef struct { - u64 read; - u64 write; -} efi_pci_io_protocol_access_64_t; - typedef union efi_pci_io_protocol efi_pci_io_protocol_t; typedef @@ -422,46 +369,6 @@ typedef struct { efi_pci_io_protocol_cfg_t write; } efi_pci_io_protocol_config_access_t; -typedef struct { - u32 poll_mem; - u32 poll_io; - efi_pci_io_protocol_access_32_t mem; - efi_pci_io_protocol_access_32_t io; - efi_pci_io_protocol_access_32_t pci; - u32 copy_mem; - u32 map; - u32 unmap; - u32 allocate_buffer; - u32 free_buffer; - u32 flush; - u32 get_location; - u32 attributes; - u32 get_bar_attributes; - u32 set_bar_attributes; - u64 romsize; - u32 romimage; -} efi_pci_io_protocol_32_t; - -typedef struct { - u64 poll_mem; - u64 poll_io; - efi_pci_io_protocol_access_64_t mem; - efi_pci_io_protocol_access_64_t io; - efi_pci_io_protocol_access_64_t pci; - u64 copy_mem; - u64 map; - u64 unmap; - u64 allocate_buffer; - u64 free_buffer; - u64 flush; - u64 get_location; - u64 attributes; - u64 get_bar_attributes; - u64 set_bar_attributes; - u64 romsize; - u64 romimage; -} efi_pci_io_protocol_64_t; - union efi_pci_io_protocol { struct { void *poll_mem; @@ -523,22 +430,6 @@ union efi_pci_io_protocol { #define EFI_PCI_IO_ATTRIBUTE_VGA_PALETTE_IO_16 0x20000 #define EFI_PCI_IO_ATTRIBUTE_VGA_IO_16 0x40000 -typedef struct { - u32 version; - u32 get; - u32 set; - u32 del; - u32 get_all; -} apple_properties_protocol_32_t; - -typedef struct { - u64 version; - u64 get; - u64 set; - u64 del; - u64 get_all; -} apple_properties_protocol_64_t; - struct efi_dev_path; typedef union apple_properties_protocol apple_properties_protocol_t; @@ -566,26 +457,6 @@ union apple_properties_protocol { } mixed_mode; }; -typedef struct { - u32 get_capability; - u32 get_event_log; - u32 hash_log_extend_event; - u32 submit_command; - u32 get_active_pcr_banks; - u32 set_active_pcr_banks; - u32 get_result_of_set_active_pcr_banks; -} efi_tcg2_protocol_32_t; - -typedef struct { - u64 get_capability; - u64 get_event_log; - u64 hash_log_extend_event; - u64 submit_command; - u64 get_active_pcr_banks; - u64 set_active_pcr_banks; - u64 get_result_of_set_active_pcr_banks; -} efi_tcg2_protocol_64_t; - typedef u32 efi_tcg2_event_log_format; typedef union efi_tcg2_protocol efi_tcg2_protocol_t; @@ -913,38 +784,6 @@ struct efi_fdt_params { u32 desc_ver; }; -typedef struct { - u32 revision; - u32 parent_handle; - u32 system_table; - u32 device_handle; - u32 file_path; - u32 reserved; - u32 load_options_size; - u32 load_options; - u32 image_base; - __aligned_u64 image_size; - unsigned int image_code_type; - unsigned int image_data_type; - u32 unload; -} efi_loaded_image_32_t; - -typedef struct { - u32 revision; - u64 parent_handle; - u64 system_table; - u64 device_handle; - u64 file_path; - u64 reserved; - u32 load_options_size; - u64 load_options; - u64 image_base; - __aligned_u64 image_size; - unsigned int image_code_type; - unsigned int image_data_type; - u64 unload; -} efi_loaded_image_64_t; - typedef union efi_loaded_image efi_loaded_image_t; union efi_loaded_image { @@ -991,34 +830,6 @@ typedef struct { efi_char16_t filename[1]; } efi_file_info_t; -typedef struct { - u64 revision; - u32 open; - u32 close; - u32 delete; - u32 read; - u32 write; - u32 get_position; - u32 set_position; - u32 get_info; - u32 set_info; - u32 flush; -} efi_file_handle_32_t; - -typedef struct { - u64 revision; - u64 open; - u64 close; - u64 delete; - u64 read; - u64 write; - u64 get_position; - u64 set_position; - u64 get_info; - u64 set_info; - u64 flush; -} efi_file_handle_64_t; - typedef union efi_file_handle efi_file_handle_t; union efi_file_handle { @@ -1054,16 +865,6 @@ union efi_file_handle { } mixed_mode; }; -typedef struct { - u64 revision; - u32 open_volume; -} efi_file_io_interface_32_t; - -typedef struct { - u64 revision; - u64 open_volume; -} efi_file_io_interface_64_t; - typedef union efi_file_io_interface efi_file_io_interface_t; union efi_file_io_interface { @@ -1076,7 +877,7 @@ union efi_file_io_interface { u64 revision; u32 open_volume; } mixed_mode; -} ; +}; #define EFI_FILE_MODE_READ 0x0000000000000001 #define EFI_FILE_MODE_WRITE 0x0000000000000002 @@ -1536,18 +1337,6 @@ struct efivar_entry { bool deleting; }; -typedef struct { - u32 reset; - u32 output_string; - u32 test_string; -} efi_simple_text_output_protocol_32_t; - -typedef struct { - u64 reset; - u64 output_string; - u64 test_string; -} efi_simple_text_output_protocol_64_t; - typedef union efi_simple_text_output_protocol efi_simple_text_output_protocol_t; union efi_simple_text_output_protocol { @@ -1586,24 +1375,6 @@ typedef struct { u32 pixels_per_scan_line; } efi_graphics_output_mode_info_t; -typedef struct { - u32 max_mode; - u32 mode; - u32 info; - u32 size_of_info; - u64 frame_buffer_base; - u32 frame_buffer_size; -} efi_graphics_output_protocol_mode_32_t; - -typedef struct { - u32 max_mode; - u32 mode; - u64 info; - u64 size_of_info; - u64 frame_buffer_base; - u64 frame_buffer_size; -} efi_graphics_output_protocol_mode_64_t; - typedef union efi_graphics_output_protocol_mode efi_graphics_output_protocol_mode_t; union efi_graphics_output_protocol_mode { @@ -1625,20 +1396,6 @@ union efi_graphics_output_protocol_mode { } mixed_mode; }; -typedef struct { - u32 query_mode; - u32 set_mode; - u32 blt; - u32 mode; -} efi_graphics_output_protocol_32_t; - -typedef struct { - u64 query_mode; - u64 set_mode; - u64 blt; - u64 mode; -} efi_graphics_output_protocol_64_t; - typedef union efi_graphics_output_protocol efi_graphics_output_protocol_t; union efi_graphics_output_protocol { -- cgit v1.2.3 From 960a8d01834eabc4549928c60f8ce0300ad08519 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:11 +0100 Subject: efi/libstub: Use stricter typing for firmware function pointers We will soon remove another level of pointer casting, so let's make sure all type handling involving firmware calls at boot time is correct. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-12-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index d8e987910853..880077639113 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -382,7 +382,11 @@ union efi_pci_io_protocol { void *allocate_buffer; void *free_buffer; void *flush; - void *get_location; + efi_status_t (*get_location)(efi_pci_io_protocol_t *, + unsigned long *segment_nr, + unsigned long *bus_nr, + unsigned long *device_nr, + unsigned long *function_nr); void *attributes; void *get_bar_attributes; void *set_bar_attributes; @@ -730,6 +734,8 @@ typedef struct { u32 tables; } efi_system_table_32_t; +typedef union efi_simple_text_output_protocol efi_simple_text_output_protocol_t; + typedef union { struct { efi_table_hdr_t hdr; @@ -738,7 +744,7 @@ typedef union { unsigned long con_in_handle; unsigned long con_in; unsigned long con_out_handle; - unsigned long con_out; + efi_simple_text_output_protocol_t *con_out; unsigned long stderr_handle; unsigned long stderr; efi_runtime_services_t *runtime; @@ -1337,8 +1343,6 @@ struct efivar_entry { bool deleting; }; -typedef union efi_simple_text_output_protocol efi_simple_text_output_protocol_t; - union efi_simple_text_output_protocol { struct { void *reset; -- cgit v1.2.3 From 8f24f8c2fc82f701866419dcb594e2cc1d3f46ba Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:12 +0100 Subject: efi/libstub: Annotate firmware routines as __efiapi Annotate all the firmware routines (boot services, runtime services and protocol methods) called in the boot context as __efiapi, and make it expand to __attribute__((ms_abi)) on 64-bit x86. This allows us to use the compiler to generate the calls into firmware that use the MS calling convention instead of the SysV one. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-13-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 147 +++++++++++++++++++++++++++++----------------------- 1 file changed, 82 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 880077639113..2074b737aa17 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -48,6 +48,12 @@ typedef u16 efi_char16_t; /* UNICODE character */ typedef u64 efi_physical_addr_t; typedef void *efi_handle_t; +#ifdef CONFIG_X86_64 +#define __efiapi __attribute__((ms_abi)) +#else +#define __efiapi +#endif + #define efi_get_handle_at(array, idx) \ (efi_is_native() ? (array)[idx] \ : (efi_handle_t)(unsigned long)((u32 *)(array))[idx]) @@ -272,13 +278,16 @@ typedef union { efi_table_hdr_t hdr; void *raise_tpl; void *restore_tpl; - efi_status_t (*allocate_pages)(int, int, unsigned long, - efi_physical_addr_t *); - efi_status_t (*free_pages)(efi_physical_addr_t, unsigned long); - efi_status_t (*get_memory_map)(unsigned long *, void *, unsigned long *, - unsigned long *, u32 *); - efi_status_t (*allocate_pool)(int, unsigned long, void **); - efi_status_t (*free_pool)(void *); + efi_status_t (__efiapi *allocate_pages)(int, int, unsigned long, + efi_physical_addr_t *); + efi_status_t (__efiapi *free_pages)(efi_physical_addr_t, + unsigned long); + efi_status_t (__efiapi *get_memory_map)(unsigned long *, void *, + unsigned long *, + unsigned long *, u32 *); + efi_status_t (__efiapi *allocate_pool)(int, unsigned long, + void **); + efi_status_t (__efiapi *free_pool)(void *); void *create_event; void *set_timer; void *wait_for_event; @@ -288,18 +297,22 @@ typedef union { void *install_protocol_interface; void *reinstall_protocol_interface; void *uninstall_protocol_interface; - efi_status_t (*handle_protocol)(efi_handle_t, efi_guid_t *, void **); + efi_status_t (__efiapi *handle_protocol)(efi_handle_t, + efi_guid_t *, void **); void *__reserved; void *register_protocol_notify; - efi_status_t (*locate_handle)(int, efi_guid_t *, void *, - unsigned long *, efi_handle_t *); + efi_status_t (__efiapi *locate_handle)(int, efi_guid_t *, + void *, unsigned long *, + efi_handle_t *); void *locate_device_path; - efi_status_t (*install_configuration_table)(efi_guid_t *, void *); + efi_status_t (__efiapi *install_configuration_table)(efi_guid_t *, + void *); void *load_image; void *start_image; void *exit; void *unload_image; - efi_status_t (*exit_boot_services)(efi_handle_t, unsigned long); + efi_status_t (__efiapi *exit_boot_services)(efi_handle_t, + unsigned long); void *get_next_monotonic_count; void *stall; void *set_watchdog_timer; @@ -310,7 +323,8 @@ typedef union { void *open_protocol_information; void *protocols_per_handle; void *locate_handle_buffer; - efi_status_t (*locate_protocol)(efi_guid_t *, void *, void **); + efi_status_t (__efiapi *locate_protocol)(efi_guid_t *, void *, + void **); void *install_multiple_protocol_interfaces; void *uninstall_multiple_protocol_interfaces; void *calculate_crc32; @@ -354,10 +368,11 @@ typedef struct { typedef union efi_pci_io_protocol efi_pci_io_protocol_t; typedef -efi_status_t (*efi_pci_io_protocol_cfg_t)(efi_pci_io_protocol_t *, - EFI_PCI_IO_PROTOCOL_WIDTH, - u32 offset, unsigned long count, - void *buffer); +efi_status_t (__efiapi *efi_pci_io_protocol_cfg_t)(efi_pci_io_protocol_t *, + EFI_PCI_IO_PROTOCOL_WIDTH, + u32 offset, + unsigned long count, + void *buffer); typedef struct { void *read; @@ -382,11 +397,11 @@ union efi_pci_io_protocol { void *allocate_buffer; void *free_buffer; void *flush; - efi_status_t (*get_location)(efi_pci_io_protocol_t *, - unsigned long *segment_nr, - unsigned long *bus_nr, - unsigned long *device_nr, - unsigned long *function_nr); + efi_status_t (__efiapi *get_location)(efi_pci_io_protocol_t *, + unsigned long *segment_nr, + unsigned long *bus_nr, + unsigned long *device_nr, + unsigned long *func_nr); void *attributes; void *get_bar_attributes; void *set_bar_attributes; @@ -441,16 +456,17 @@ typedef union apple_properties_protocol apple_properties_protocol_t; union apple_properties_protocol { struct { unsigned long version; - efi_status_t (*get)(apple_properties_protocol_t *, - struct efi_dev_path *, efi_char16_t *, - void *, u32 *); - efi_status_t (*set)(apple_properties_protocol_t *, - struct efi_dev_path *, efi_char16_t *, - void *, u32); - efi_status_t (*del)(apple_properties_protocol_t *, - struct efi_dev_path *, efi_char16_t *); - efi_status_t (*get_all)(apple_properties_protocol_t *, - void *buffer, u32 *); + efi_status_t (__efiapi *get)(apple_properties_protocol_t *, + struct efi_dev_path *, + efi_char16_t *, void *, u32 *); + efi_status_t (__efiapi *set)(apple_properties_protocol_t *, + struct efi_dev_path *, + efi_char16_t *, void *, u32); + efi_status_t (__efiapi *del)(apple_properties_protocol_t *, + struct efi_dev_path *, + efi_char16_t *); + efi_status_t (__efiapi *get_all)(apple_properties_protocol_t *, + void *buffer, u32 *); }; struct { u32 version; @@ -468,11 +484,11 @@ typedef union efi_tcg2_protocol efi_tcg2_protocol_t; union efi_tcg2_protocol { struct { void *get_capability; - efi_status_t (*get_event_log)(efi_handle_t, - efi_tcg2_event_log_format, - efi_physical_addr_t *, - efi_physical_addr_t *, - efi_bool_t *); + efi_status_t (__efiapi *get_event_log)(efi_handle_t, + efi_tcg2_event_log_format, + efi_physical_addr_t *, + efi_physical_addr_t *, + efi_bool_t *); void *hash_log_extend_event; void *submit_command; void *get_active_pcr_banks; @@ -575,21 +591,21 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes, typedef union { struct { - efi_table_hdr_t hdr; - efi_get_time_t *get_time; - efi_set_time_t *set_time; - efi_get_wakeup_time_t *get_wakeup_time; - efi_set_wakeup_time_t *set_wakeup_time; - efi_set_virtual_address_map_t *set_virtual_address_map; - void *convert_pointer; - efi_get_variable_t *get_variable; - efi_get_next_variable_t *get_next_variable; - efi_set_variable_t *set_variable; - efi_get_next_high_mono_count_t *get_next_high_mono_count; - efi_reset_system_t *reset_system; - efi_update_capsule_t *update_capsule; - efi_query_capsule_caps_t *query_capsule_caps; - efi_query_variable_info_t *query_variable_info; + efi_table_hdr_t hdr; + efi_get_time_t __efiapi *get_time; + efi_set_time_t __efiapi *set_time; + efi_get_wakeup_time_t __efiapi *get_wakeup_time; + efi_set_wakeup_time_t __efiapi *set_wakeup_time; + efi_set_virtual_address_map_t __efiapi *set_virtual_address_map; + void *convert_pointer; + efi_get_variable_t __efiapi *get_variable; + efi_get_next_variable_t __efiapi *get_next_variable; + efi_set_variable_t __efiapi *set_variable; + efi_get_next_high_mono_count_t __efiapi *get_next_high_mono_count; + efi_reset_system_t __efiapi *reset_system; + efi_update_capsule_t __efiapi *update_capsule; + efi_query_capsule_caps_t __efiapi *query_capsule_caps; + efi_query_variable_info_t __efiapi *query_variable_info; }; efi_runtime_services_32_t mixed_mode; } efi_runtime_services_t; @@ -806,7 +822,7 @@ union efi_loaded_image { __aligned_u64 image_size; unsigned int image_code_type; unsigned int image_data_type; - efi_status_t (*unload)(efi_handle_t image_handle); + efi_status_t ( __efiapi *unload)(efi_handle_t image_handle); }; struct { u32 revision; @@ -841,18 +857,19 @@ typedef union efi_file_handle efi_file_handle_t; union efi_file_handle { struct { u64 revision; - efi_status_t (*open)(efi_file_handle_t *, - efi_file_handle_t **, - efi_char16_t *, u64, u64); - efi_status_t (*close)(efi_file_handle_t *); + efi_status_t (__efiapi *open)(efi_file_handle_t *, + efi_file_handle_t **, + efi_char16_t *, u64, u64); + efi_status_t (__efiapi *close)(efi_file_handle_t *); void *delete; - efi_status_t (*read)(efi_file_handle_t *, unsigned long *, - void *); + efi_status_t (__efiapi *read)(efi_file_handle_t *, + unsigned long *, void *); void *write; void *get_position; void *set_position; - efi_status_t (*get_info)(efi_file_handle_t *, efi_guid_t *, - unsigned long *, void *); + efi_status_t (__efiapi *get_info)(efi_file_handle_t *, + efi_guid_t *, unsigned long *, + void *); void *set_info; void *flush; }; @@ -876,8 +893,8 @@ typedef union efi_file_io_interface efi_file_io_interface_t; union efi_file_io_interface { struct { u64 revision; - int (*open_volume)(efi_file_io_interface_t *, - efi_file_handle_t **); + int (__efiapi *open_volume)(efi_file_io_interface_t *, + efi_file_handle_t **); }; struct { u64 revision; @@ -1346,8 +1363,8 @@ struct efivar_entry { union efi_simple_text_output_protocol { struct { void *reset; - efi_status_t (*output_string)(efi_simple_text_output_protocol_t *, - efi_char16_t *); + efi_status_t (__efiapi *output_string)(efi_simple_text_output_protocol_t *, + efi_char16_t *); void *test_string; }; struct { -- cgit v1.2.3 From 14e900c7e4033d6ee3398b9f133e1716cc072401 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:14 +0100 Subject: efi/libstub: Avoid protocol wrapper for file I/O routines The EFI file I/O routines built on top of the file I/O firmware services are incompatible with mixed mode, so there is no need to obfuscate them by using protocol wrappers whose only purpose is to hide the mixed mode handling. So let's switch to plain indirect calls instead. This also means we can drop the mixed_mode aliases from the various types involved. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-15-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 118 +++++++++++++++++----------------------------------- 1 file changed, 39 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 2074b737aa17..14dd08ecf8a7 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -806,40 +806,21 @@ struct efi_fdt_params { u32 desc_ver; }; -typedef union efi_loaded_image efi_loaded_image_t; - -union efi_loaded_image { - struct { - u32 revision; - efi_handle_t parent_handle; - efi_system_table_t *system_table; - efi_handle_t device_handle; - void *file_path; - void *reserved; - u32 load_options_size; - void *load_options; - void *image_base; - __aligned_u64 image_size; - unsigned int image_code_type; - unsigned int image_data_type; - efi_status_t ( __efiapi *unload)(efi_handle_t image_handle); - }; - struct { - u32 revision; - u32 parent_handle; - u32 system_table; - u32 device_handle; - u32 file_path; - u32 reserved; - u32 load_options_size; - u32 load_options; - u32 image_base; - __aligned_u64 image_size; - unsigned int image_code_type; - unsigned int image_data_type; - u32 unload; - } mixed_mode; -}; +typedef struct { + u32 revision; + efi_handle_t parent_handle; + efi_system_table_t *system_table; + efi_handle_t device_handle; + void *file_path; + void *reserved; + u32 load_options_size; + void *load_options; + void *image_base; + __aligned_u64 image_size; + unsigned int image_code_type; + unsigned int image_data_type; + efi_status_t ( __efiapi *unload)(efi_handle_t image_handle); +} efi_loaded_image_t; typedef struct { u64 size; @@ -852,54 +833,33 @@ typedef struct { efi_char16_t filename[1]; } efi_file_info_t; -typedef union efi_file_handle efi_file_handle_t; - -union efi_file_handle { - struct { - u64 revision; - efi_status_t (__efiapi *open)(efi_file_handle_t *, - efi_file_handle_t **, - efi_char16_t *, u64, u64); - efi_status_t (__efiapi *close)(efi_file_handle_t *); - void *delete; - efi_status_t (__efiapi *read)(efi_file_handle_t *, - unsigned long *, void *); - void *write; - void *get_position; - void *set_position; - efi_status_t (__efiapi *get_info)(efi_file_handle_t *, - efi_guid_t *, unsigned long *, - void *); - void *set_info; - void *flush; - }; - struct { - u64 revision; - u32 open; - u32 close; - u32 delete; - u32 read; - u32 write; - u32 get_position; - u32 set_position; - u32 get_info; - u32 set_info; - u32 flush; - } mixed_mode; +typedef struct efi_file_handle efi_file_handle_t; + +struct efi_file_handle { + u64 revision; + efi_status_t (__efiapi *open)(efi_file_handle_t *, + efi_file_handle_t **, + efi_char16_t *, u64, u64); + efi_status_t (__efiapi *close)(efi_file_handle_t *); + void *delete; + efi_status_t (__efiapi *read)(efi_file_handle_t *, + unsigned long *, void *); + void *write; + void *get_position; + void *set_position; + efi_status_t (__efiapi *get_info)(efi_file_handle_t *, + efi_guid_t *, unsigned long *, + void *); + void *set_info; + void *flush; }; -typedef union efi_file_io_interface efi_file_io_interface_t; +typedef struct efi_file_io_interface efi_file_io_interface_t; -union efi_file_io_interface { - struct { - u64 revision; - int (__efiapi *open_volume)(efi_file_io_interface_t *, - efi_file_handle_t **); - }; - struct { - u64 revision; - u32 open_volume; - } mixed_mode; +struct efi_file_io_interface { + u64 revision; + int (__efiapi *open_volume)(efi_file_io_interface_t *, + efi_file_handle_t **); }; #define EFI_FILE_MODE_READ 0x0000000000000001 -- cgit v1.2.3 From 8173ec7905b5b07c989b06a105d171c169dde93b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:18 +0100 Subject: efi/libstub: Drop sys_table_arg from printk routines As a first step towards getting rid of the need to pass around a function parameter 'sys_table_arg' pointing to the EFI system table, remove the references to it in the printing code, which is represents the majority of the use cases. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-19-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 14dd08ecf8a7..5b207db6ead0 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1493,7 +1493,7 @@ static inline int efi_runtime_map_copy(void *buf, size_t bufsz) /* prototypes shared between arch specific and generic stub code */ -void efi_printk(efi_system_table_t *sys_table_arg, char *str); +void efi_printk(char *str); void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long addr); -- cgit v1.2.3 From cd33a5c1d53e43bef1683c70dc3b68b6d9e8eca6 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 24 Dec 2019 16:10:19 +0100 Subject: efi/libstub: Remove 'sys_table_arg' from all function prototypes We have a helper efi_system_table() that gives us the address of the EFI system table in memory, so there is no longer point in passing it around from each function to the next. Signed-off-by: Ard Biesheuvel Cc: Arvind Sankar Cc: Borislav Petkov Cc: James Morse Cc: Matt Fleming Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191224151025.32482-20-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 43 ++++++++++++++++--------------------------- 1 file changed, 16 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 5b207db6ead0..726673e98990 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1495,22 +1495,17 @@ static inline int efi_runtime_map_copy(void *buf, size_t bufsz) void efi_printk(char *str); -void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, - unsigned long addr); +void efi_free(unsigned long size, unsigned long addr); -char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, - efi_loaded_image_t *image, int *cmd_line_len); +char *efi_convert_cmdline(efi_loaded_image_t *image, int *cmd_line_len); -efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, - struct efi_boot_memmap *map); +efi_status_t efi_get_memory_map(struct efi_boot_memmap *map); -efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg, - unsigned long size, unsigned long align, +efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, unsigned long *addr, unsigned long min); static inline -efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, - unsigned long size, unsigned long align, +efi_status_t efi_low_alloc(unsigned long size, unsigned long align, unsigned long *addr) { /* @@ -1518,23 +1513,20 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, * checks pointers against NULL. Skip the first 8 * bytes so we start at a nice even number. */ - return efi_low_alloc_above(sys_table_arg, size, align, addr, 0x8); + return efi_low_alloc_above(size, align, addr, 0x8); } -efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, - unsigned long size, unsigned long align, +efi_status_t efi_high_alloc(unsigned long size, unsigned long align, unsigned long *addr, unsigned long max); -efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, - unsigned long *image_addr, +efi_status_t efi_relocate_kernel(unsigned long *image_addr, unsigned long image_size, unsigned long alloc_size, unsigned long preferred_addr, unsigned long alignment, unsigned long min_addr); -efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, - efi_loaded_image_t *image, +efi_status_t handle_cmdline_files(efi_loaded_image_t *image, char *cmd_line, char *option_string, unsigned long max_addr, unsigned long *load_addr, @@ -1542,8 +1534,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, efi_status_t efi_parse_options(char const *cmdline); -efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, - struct screen_info *si, efi_guid_t *proto, +efi_status_t efi_setup_gop(struct screen_info *si, efi_guid_t *proto, unsigned long size); #ifdef CONFIG_EFI @@ -1561,18 +1552,18 @@ enum efi_secureboot_mode { efi_secureboot_mode_disabled, efi_secureboot_mode_enabled, }; -enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table); +enum efi_secureboot_mode efi_get_secureboot(void); #ifdef CONFIG_RESET_ATTACK_MITIGATION -void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg); +void efi_enable_reset_attack_mitigation(void); #else static inline void -efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg) { } +efi_enable_reset_attack_mitigation(void) { } #endif -efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg); +efi_status_t efi_random_get_seed(void); -void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table); +void efi_retrieve_tpm2_eventlog(void); /* * Arch code can implement the following three template macros, avoiding @@ -1624,12 +1615,10 @@ void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table); }) typedef efi_status_t (*efi_exit_boot_map_processing)( - efi_system_table_t *sys_table_arg, struct efi_boot_memmap *map, void *priv); -efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table, - void *handle, +efi_status_t efi_exit_boot_services(void *handle, struct efi_boot_memmap *map, void *priv, efi_exit_boot_map_processing priv_func); -- cgit v1.2.3 From 0e5dafc8a6e540c0145b61545c557c43be70af10 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 25 Dec 2019 18:16:09 -0800 Subject: net: phy: Introduce helper functions for time stamping support. Some parts of the networking stack and at least one driver test fields within the 'struct phy_device' in order to query time stamping capabilities and to invoke time stamping methods. This patch adds a functional interface around the time stamping fields. This will allow insulating the callers from future changes to the details of the time stamping implemenation. Signed-off-by: Richard Cochran Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7d530b3f8855..0248f5e9939d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -936,6 +936,66 @@ static inline bool phy_polling_mode(struct phy_device *phydev) return phydev->irq == PHY_POLL; } +/** + * phy_has_hwtstamp - Tests whether a PHY time stamp configuration. + * @phydev: the phy_device struct + */ +static inline bool phy_has_hwtstamp(struct phy_device *phydev) +{ + return phydev && phydev->drv && phydev->drv->hwtstamp; +} + +/** + * phy_has_rxtstamp - Tests whether a PHY supports receive time stamping. + * @phydev: the phy_device struct + */ +static inline bool phy_has_rxtstamp(struct phy_device *phydev) +{ + return phydev && phydev->drv && phydev->drv->rxtstamp; +} + +/** + * phy_has_tsinfo - Tests whether a PHY reports time stamping and/or + * PTP hardware clock capabilities. + * @phydev: the phy_device struct + */ +static inline bool phy_has_tsinfo(struct phy_device *phydev) +{ + return phydev && phydev->drv && phydev->drv->ts_info; +} + +/** + * phy_has_txtstamp - Tests whether a PHY supports transmit time stamping. + * @phydev: the phy_device struct + */ +static inline bool phy_has_txtstamp(struct phy_device *phydev) +{ + return phydev && phydev->drv && phydev->drv->txtstamp; +} + +static inline int phy_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) +{ + return phydev->drv->hwtstamp(phydev, ifr); +} + +static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, + int type) +{ + return phydev->drv->rxtstamp(phydev, skb, type); +} + +static inline int phy_ts_info(struct phy_device *phydev, + struct ethtool_ts_info *tsinfo) +{ + return phydev->drv->ts_info(phydev, tsinfo); +} + +static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, + int type) +{ + phydev->drv->txtstamp(phydev, skb, type); +} + /** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct -- cgit v1.2.3 From 4715f65ffa0520af0680dbfbedbe349f175adaf4 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 25 Dec 2019 18:16:15 -0800 Subject: net: Introduce a new MII time stamping interface. Currently the stack supports time stamping in PHY devices. However, there are newer, non-PHY devices that can snoop an MII bus and provide time stamps. In order to support such devices, this patch introduces a new interface to be used by both PHY and non-PHY devices. In addition, the one and only user of the old PHY time stamping API is converted to the new interface. Signed-off-by: Richard Cochran Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii_timestamper.h | 58 +++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 41 +++++++---------------------- 2 files changed, 68 insertions(+), 31 deletions(-) create mode 100644 include/linux/mii_timestamper.h (limited to 'include/linux') diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h new file mode 100644 index 000000000000..36002386029c --- /dev/null +++ b/include/linux/mii_timestamper.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Support for generic time stamping devices on MII buses. + * Copyright (C) 2018 Richard Cochran + */ +#ifndef _LINUX_MII_TIMESTAMPER_H +#define _LINUX_MII_TIMESTAMPER_H + +#include +#include +#include + +struct phy_device; + +/** + * struct mii_timestamper - Callback interface to MII time stamping devices. + * + * @rxtstamp: Requests a Rx timestamp for 'skb'. If the skb is accepted, + * the MII time stamping device promises to deliver it using + * netif_rx() as soon as a timestamp becomes available. One of + * the PTP_CLASS_ values is passed in 'type'. The function + * must return true if the skb is accepted for delivery. + * + * @txtstamp: Requests a Tx timestamp for 'skb'. The MII time stamping + * device promises to deliver it using skb_complete_tx_timestamp() + * as soon as a timestamp becomes available. One of the PTP_CLASS_ + * values is passed in 'type'. + * + * @hwtstamp: Handles SIOCSHWTSTAMP ioctl for hardware time stamping. + * + * @link_state: Allows the device to respond to changes in the link + * state. The caller invokes this function while holding + * the phy_device mutex. + * + * @ts_info: Handles ethtool queries for hardware time stamping. + * + * Drivers for PHY time stamping devices should embed their + * mii_timestamper within a private structure, obtaining a reference + * to it using container_of(). + */ +struct mii_timestamper { + bool (*rxtstamp)(struct mii_timestamper *mii_ts, + struct sk_buff *skb, int type); + + void (*txtstamp)(struct mii_timestamper *mii_ts, + struct sk_buff *skb, int type); + + int (*hwtstamp)(struct mii_timestamper *mii_ts, + struct ifreq *ifreq); + + void (*link_state)(struct mii_timestamper *mii_ts, + struct phy_device *phydev); + + int (*ts_info)(struct mii_timestamper *mii_ts, + struct ethtool_ts_info *ts_info); +}; + +#endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 0248f5e9939d..30e599c454db 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -441,6 +442,7 @@ struct phy_device { struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; + struct mii_timestamper *mii_ts; u8 mdix; u8 mdix_ctrl; @@ -546,29 +548,6 @@ struct phy_driver { */ int (*match_phy_device)(struct phy_device *phydev); - /* Handles ethtool queries for hardware time stamping. */ - int (*ts_info)(struct phy_device *phydev, struct ethtool_ts_info *ti); - - /* Handles SIOCSHWTSTAMP ioctl for hardware time stamping. */ - int (*hwtstamp)(struct phy_device *phydev, struct ifreq *ifr); - - /* - * Requests a Rx timestamp for 'skb'. If the skb is accepted, - * the phy driver promises to deliver it using netif_rx() as - * soon as a timestamp becomes available. One of the - * PTP_CLASS_ values is passed in 'type'. The function must - * return true if the skb is accepted for delivery. - */ - bool (*rxtstamp)(struct phy_device *dev, struct sk_buff *skb, int type); - - /* - * Requests a Tx timestamp for 'skb'. The phy driver promises - * to deliver it using skb_complete_tx_timestamp() as soon as a - * timestamp becomes available. One of the PTP_CLASS_ values - * is passed in 'type'. - */ - void (*txtstamp)(struct phy_device *dev, struct sk_buff *skb, int type); - /* 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. */ @@ -942,7 +921,7 @@ static inline bool phy_polling_mode(struct phy_device *phydev) */ static inline bool phy_has_hwtstamp(struct phy_device *phydev) { - return phydev && phydev->drv && phydev->drv->hwtstamp; + return phydev && phydev->mii_ts && phydev->mii_ts->hwtstamp; } /** @@ -951,7 +930,7 @@ static inline bool phy_has_hwtstamp(struct phy_device *phydev) */ static inline bool phy_has_rxtstamp(struct phy_device *phydev) { - return phydev && phydev->drv && phydev->drv->rxtstamp; + return phydev && phydev->mii_ts && phydev->mii_ts->rxtstamp; } /** @@ -961,7 +940,7 @@ static inline bool phy_has_rxtstamp(struct phy_device *phydev) */ static inline bool phy_has_tsinfo(struct phy_device *phydev) { - return phydev && phydev->drv && phydev->drv->ts_info; + return phydev && phydev->mii_ts && phydev->mii_ts->ts_info; } /** @@ -970,30 +949,30 @@ static inline bool phy_has_tsinfo(struct phy_device *phydev) */ static inline bool phy_has_txtstamp(struct phy_device *phydev) { - return phydev && phydev->drv && phydev->drv->txtstamp; + return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp; } static inline int phy_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) { - return phydev->drv->hwtstamp(phydev, ifr); + return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { - return phydev->drv->rxtstamp(phydev, skb, type); + return phydev->mii_ts->rxtstamp(phydev->mii_ts, skb, type); } static inline int phy_ts_info(struct phy_device *phydev, struct ethtool_ts_info *tsinfo) { - return phydev->drv->ts_info(phydev, tsinfo); + return phydev->mii_ts->ts_info(phydev->mii_ts, tsinfo); } static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { - phydev->drv->txtstamp(phydev, skb, type); + phydev->mii_ts->txtstamp(phydev->mii_ts, skb, type); } /** -- cgit v1.2.3 From 767ff483731502a0fc34f34a3a0851aca175eb71 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 25 Dec 2019 18:16:16 -0800 Subject: net: Add a layer for non-PHY MII time stamping drivers. While PHY time stamping drivers can simply attach their interface directly to the PHY instance, stand alone drivers require support in order to manage their services. Non-PHY MII time stamping drivers have a control interface over another bus like I2C, SPI, UART, or via a memory mapped peripheral. The controller device will be associated with one or more time stamping channels, each of which sits snoops in on a MII bus. This patch provides a glue layer that will enable time stamping channels to find their controlling device. Signed-off-by: Richard Cochran Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii_timestamper.h | 63 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h index 36002386029c..fa940bbaf8ae 100644 --- a/include/linux/mii_timestamper.h +++ b/include/linux/mii_timestamper.h @@ -33,10 +33,15 @@ struct phy_device; * the phy_device mutex. * * @ts_info: Handles ethtool queries for hardware time stamping. + * @device: Remembers the device to which the instance belongs. * * Drivers for PHY time stamping devices should embed their * mii_timestamper within a private structure, obtaining a reference * to it using container_of(). + * + * Drivers for non-PHY time stamping devices should return a pointer + * to a mii_timestamper from the probe_channel() callback of their + * mii_timestamping_ctrl interface. */ struct mii_timestamper { bool (*rxtstamp)(struct mii_timestamper *mii_ts, @@ -53,6 +58,64 @@ struct mii_timestamper { int (*ts_info)(struct mii_timestamper *mii_ts, struct ethtool_ts_info *ts_info); + + struct device *device; +}; + +/** + * struct mii_timestamping_ctrl - MII time stamping controller interface. + * + * @probe_channel: Callback into the controller driver announcing the + * presence of the 'port' channel. The 'device' field + * had been passed to register_mii_tstamp_controller(). + * The driver must return either a pointer to a valid + * MII timestamper instance or PTR_ERR. + * + * @release_channel: Releases an instance obtained via .probe_channel. + */ +struct mii_timestamping_ctrl { + struct mii_timestamper *(*probe_channel)(struct device *device, + unsigned int port); + void (*release_channel)(struct device *device, + struct mii_timestamper *mii_ts); }; +#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING + +int register_mii_tstamp_controller(struct device *device, + struct mii_timestamping_ctrl *ctrl); + +void unregister_mii_tstamp_controller(struct device *device); + +struct mii_timestamper *register_mii_timestamper(struct device_node *node, + unsigned int port); + +void unregister_mii_timestamper(struct mii_timestamper *mii_ts); + +#else + +static inline +int register_mii_tstamp_controller(struct device *device, + struct mii_timestamping_ctrl *ctrl) +{ + return -EOPNOTSUPP; +} + +static inline void unregister_mii_tstamp_controller(struct device *device) +{ +} + +static inline +struct mii_timestamper *register_mii_timestamper(struct device_node *node, + unsigned int port) +{ + return NULL; +} + +static inline void unregister_mii_timestamper(struct mii_timestamper *mii_ts) +{ +} + +#endif + #endif -- cgit v1.2.3 From f03ee2042b2dc46e3452e87324d90f147de4a944 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 5 Dec 2019 10:24:11 +0100 Subject: spi: oc-tiny: Use GPIO descriptors Switch the OC Tiny driver over to handling CS GPIOs using GPIO descriptors in the core. This driver is entirely relying on GPIOs to be used for chipselect, so let the core pick these out using either device tree or machine descriptors. There are no in-tree users of this driver so no board files need to be patched, out-of-tree boardfiles can use machine descriptor tables, c.f. commit 1dfbf334f123. Cc: Thomas Chou Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20191205092411.64341-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/spi/spi_oc_tiny.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_oc_tiny.h b/include/linux/spi/spi_oc_tiny.h index a3ecf2feadf2..284872ac130c 100644 --- a/include/linux/spi/spi_oc_tiny.h +++ b/include/linux/spi/spi_oc_tiny.h @@ -6,16 +6,12 @@ * struct tiny_spi_platform_data - platform data of the OpenCores tiny SPI * @freq: input clock freq to the core. * @baudwidth: baud rate divider width of the core. - * @gpio_cs_count: number of gpio pins used for chipselect. - * @gpio_cs: array of gpio pins used for chipselect. * * freq and baudwidth are used only if the divider is programmable. */ struct tiny_spi_platform_data { unsigned int freq; unsigned int baudwidth; - unsigned int gpio_cs_count; - int *gpio_cs; }; #endif /* _LINUX_SPI_SPI_OC_TINY_H */ -- cgit v1.2.3 From 77fb4e0a559a960eb36d0b2c50c781c5492577eb Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 13 Dec 2019 09:55:42 +0100 Subject: ACPI: processor: Export acpi_processor_evaluate_cst() The intel_idle driver will be modified to use ACPI _CST subsequently and it will need to call acpi_processor_evaluate_cst(), so move that function to acpi_processor.c so that it is always present (which is required by intel_idle) and export it to modules to allow the ACPI processor driver (which is modular) to call it. No intentional functional impact. Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ee39b05e7f76..0f24d701fbdc 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -280,10 +280,19 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ +struct acpi_processor_power; + #ifdef CONFIG_ACPI_PROCESSOR_CSTATE bool acpi_processor_claim_cst_control(void); +int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, + struct acpi_processor_power *info); #else static inline bool acpi_processor_claim_cst_control(void) { return false; } +static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, + struct acpi_processor_power *info) +{ + return -ENODEV; +} #endif #ifdef CONFIG_ACPI_HOTPLUG_CPU -- cgit v1.2.3 From 75a80267410e38ab76c4ceb39753f96d72113781 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 13 Dec 2019 09:56:13 +0100 Subject: cpuidle: Allow idle states to be disabled by default In certain situations it may be useful to prevent some idle states from being used by default while allowing user space to enable them later on. For this purpose, introduce a new state flag, CPUIDLE_FLAG_OFF, to mark idle states that should be disabled by default, make the core set CPUIDLE_STATE_DISABLED_BY_USER for those states at the initialization time and add a new state attribute in sysfs, "default_status", to inform user space of the initial status of the given idle state ("disabled" if CPUIDLE_FLAG_OFF is set for it, "enabled" otherwise). Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 1dabe36bd011..ebfb52b3ffbf 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -77,6 +77,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ #define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ +#define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; -- cgit v1.2.3 From c782937e92826af464e65111e9f7a7a774b6c276 Mon Sep 17 00:00:00 2001 From: Chen Zhou Date: Mon, 16 Dec 2019 18:58:48 +0800 Subject: crypto: api - remove unneeded semicolon Fixes coccicheck warning: ./include/linux/crypto.h:573:2-3: Unneeded semicolon Signed-off-by: Chen Zhou Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index a905e524e332..8729f957f83c 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -570,7 +570,7 @@ static inline int crypto_wait_req(int err, struct crypto_wait *wait) reinit_completion(&wait->completion); err = wait->err; break; - }; + } return err; } -- cgit v1.2.3 From 862dd2a946aa1417f013fb748e2aa0f4349b405b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 27 Dec 2019 03:24:17 +0200 Subject: spi: Don't look at TX buffer for PTP system timestamping The API for PTP system timestamping (associating a SPI transaction with the system time at which it was transferred) is flawed: it assumes that the xfer->tx_buf pointer will always be present. This is, of course, not always the case. So introduce a "progress" variable that denotes how many word have been transferred. Fix the Freescale DSPI driver, the only user of the API so far, in the same patch. Fixes: b42faeee718c ("spi: Add a PTP system timestamp to the transfer structure") Fixes: d6b71dfaeeba ("spi: spi-fsl-dspi: Implement the PTP system timestamping for TCFQ mode") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20191227012417.1057-1-olteanv@gmail.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 98fe8663033a..3a67a7e45633 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -689,10 +689,10 @@ extern void spi_finalize_current_transfer(struct spi_controller *ctlr); /* Helper calls for driver to timestamp transfer */ void spi_take_timestamp_pre(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off); + size_t progress, bool irqs_off); void spi_take_timestamp_post(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off); + size_t progress, bool irqs_off); /* the spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, -- cgit v1.2.3 From 2b4a8990b7df55875745a80a609a1ceaaf51f322 Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Fri, 27 Dec 2019 15:55:18 +0100 Subject: ethtool: introduce ethtool netlink interface Basic genetlink and init infrastructure for the netlink interface, register genetlink family "ethtool". Add CONFIG_ETHTOOL_NETLINK Kconfig option to make the build optional. Add initial overall interface description into Documentation/networking/ethtool-netlink.rst, further patches will add more detailed information. Signed-off-by: Michal Kubecek Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/ethtool_netlink.h (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h new file mode 100644 index 000000000000..f27e92b5f344 --- /dev/null +++ b/include/linux/ethtool_netlink.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _LINUX_ETHTOOL_NETLINK_H_ +#define _LINUX_ETHTOOL_NETLINK_H_ + +#include +#include + +#endif /* _LINUX_ETHTOOL_NETLINK_H_ */ -- cgit v1.2.3 From 6b08d6c146f4c5ed451c45339c10feb06d619db2 Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Fri, 27 Dec 2019 15:55:33 +0100 Subject: ethtool: support for netlink notifications Add infrastructure for ethtool netlink notifications. There is only one multicast group "monitor" which is used to notify userspace about changes and actions performed. Notification messages (types using suffix _NTF) share the format with replies to GET requests. Notifications are supposed to be broadcasted on every configuration change, whether it is done using the netlink interface or ioctl one. Netlink SET requests only trigger a notification if some data is actually changed. To trigger an ethtool notification, both ethtool netlink and external code use ethtool_notify() helper. This helper requires RTNL to be held and may sleep. Handlers sending messages for specific notification message types are registered in ethnl_notify_handlers array. As notifications can be triggered from other code, ethnl_ok flag is used to prevent an attempt to send notification before genetlink family is registered. Signed-off-by: Michal Kubecek Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 5 +++++ include/linux/netdevice.h | 9 +++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index f27e92b5f344..c98f6852c8eb 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -5,5 +5,10 @@ #include #include +#include + +enum ethtool_multicast_groups { + ETHNL_MCGRP_MONITOR, +}; #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 469a297b58c0..f007155ae8f4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4393,6 +4393,15 @@ struct netdev_notifier_bonding_info { void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info); +#if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) +void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data); +#else +static inline void ethtool_notify(struct net_device *dev, unsigned int cmd, + const void *data) +{ +} +#endif + static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { -- cgit v1.2.3 From f625aa9be8c10f2e4dc677837e240730a25feda7 Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Fri, 27 Dec 2019 15:56:08 +0100 Subject: ethtool: provide link mode information with LINKMODES_GET request Implement LINKMODES_GET netlink request to get link modes related information provided by ETHTOOL_GLINKSETTINGS and ETHTOOL_GSET ioctl commands. This request provides supported, advertised and peer advertised link modes, autonegotiation flag, speed and duplex. LINKMODES_GET request can be used with NLM_F_DUMP (without device identification) to request the information for all devices in current network namespace providing the data. Signed-off-by: Michal Kubecek Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index c98f6852c8eb..d01b77887f82 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -7,6 +7,9 @@ #include #include +#define __ETHTOOL_LINK_MODE_MASK_NWORDS \ + DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) + enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; -- cgit v1.2.3 From f6d4033d2a14b454680585d4ab974d163fcd7a47 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 11 Dec 2019 12:43:00 +0200 Subject: iio: buffer: rename 'read_first_n' callback to 'read' It is implied that 'read' will read the first n bytes and not e.g. bytes only from offsets within the buffer that are a prime number. This change is non-functional, mostly just a rename. A secondary intent with this patch is to make room later to add a write callback. Signed-off-by: Lars-Peter Clausen Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer_impl.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index d1171db23742..a4d2d8061ef6 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -18,7 +18,7 @@ struct iio_buffer; /** * struct iio_buffer_access_funcs - access functions for buffers. * @store_to: actually store stuff to the buffer - * @read_first_n: try to get a specified number of bytes (must exist) + * @read: try to get a specified number of bytes (must exist) * @data_available: indicates how much data is available for reading from * the buffer. * @request_update: if a parameter change has been marked, update underlying @@ -45,9 +45,7 @@ struct iio_buffer; **/ struct iio_buffer_access_funcs { int (*store_to)(struct iio_buffer *buffer, const void *data); - int (*read_first_n)(struct iio_buffer *buffer, - size_t n, - char __user *buf); + int (*read)(struct iio_buffer *buffer, size_t n, char __user *buf); size_t (*data_available)(struct iio_buffer *buffer); int (*request_update)(struct iio_buffer *buffer); -- cgit v1.2.3 From b76b3479dab948bea0a98b6d263eb56d8f358528 Mon Sep 17 00:00:00 2001 From: Kamil Konieczny Date: Thu, 5 Dec 2019 15:55:25 +0100 Subject: PM / devfreq: Change time stats to 64-bit Change time stats counting to bigger type by using 64-bit jiffies. This will make devfreq stats code look similar to cpufreq stats and prevents overflow (for HZ = 1000 after 49.7 days). Signed-off-by: Kamil Konieczny Acked-by: Chanwoo Choi Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index fb376b5b7281..95816a8e3d26 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -177,8 +177,8 @@ struct devfreq { /* information for device frequency transition */ unsigned int total_trans; unsigned int *trans_table; - unsigned long *time_in_state; - unsigned long last_stat_updated; + u64 *time_in_state; + u64 last_stat_updated; struct srcu_notifier_head transition_notifier_list; -- cgit v1.2.3 From 1ebd0bc0e8adbfa548335d016ead922cc85fcecd Mon Sep 17 00:00:00 2001 From: Kamil Konieczny Date: Fri, 6 Dec 2019 13:46:39 +0900 Subject: PM / devfreq: Move statistics to separate struct devfreq_stats Count time and transitions between devfreq frequencies in separate struct devfreq_stats for improved code readability and maintenance. Signed-off-by: Kamil Konieczny Reviewed-by: Matthias Kaehlcke [cw00.choi: Fix the merge conflict in trasn_stat_store and use 'devfreq->stats.*' style for consistent coding style and restore the clean-up code of 'devfreq->profile->*'] Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 95816a8e3d26..9e73c84adf50 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -107,6 +107,20 @@ struct devfreq_dev_profile { unsigned int max_state; }; +/** + * struct devfreq_stats - Statistics of devfreq device behavior + * @total_trans: Number of devfreq transitions. + * @trans_table: Statistics of devfreq transitions. + * @time_in_state: Statistics of devfreq states. + * @last_update: The last time stats were updated. + */ +struct devfreq_stats { + unsigned int total_trans; + unsigned int *trans_table; + u64 *time_in_state; + u64 last_update; +}; + /** * struct devfreq - Device devfreq structure * @node: list node - contains the devices with devfreq that have been @@ -132,10 +146,7 @@ struct devfreq_dev_profile { * @suspend_freq: frequency of a device set during suspend phase. * @resume_freq: frequency of a device set in resume phase. * @suspend_count: suspend requests counter for a device. - * @total_trans: Number of devfreq transitions - * @trans_table: Statistics of devfreq transitions - * @time_in_state: Statistics of devfreq states - * @last_stat_updated: The last time stat updated + * @stats: Statistics of devfreq device behavior * @transition_notifier_list: list head of DEVFREQ_TRANSITION_NOTIFIER notifier * @nb_min: Notifier block for DEV_PM_QOS_MIN_FREQUENCY * @nb_max: Notifier block for DEV_PM_QOS_MAX_FREQUENCY @@ -174,11 +185,8 @@ struct devfreq { unsigned long resume_freq; atomic_t suspend_count; - /* information for device frequency transition */ - unsigned int total_trans; - unsigned int *trans_table; - u64 *time_in_state; - u64 last_stat_updated; + /* information for device frequency transitions */ + struct devfreq_stats stats; struct srcu_notifier_head transition_notifier_list; -- cgit v1.2.3 From 54cb5740526a2f30d57f146d8a17364c59287187 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 14 Dec 2019 08:03:11 -0800 Subject: PM / devfreq: Fix multiple kernel-doc warnings Fix kernel-doc warnings in devfreq files. Also fix a typo. Signed-off-by: Randy Dunlap Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 9e73c84adf50..c6f82d4bec9f 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -136,6 +136,7 @@ struct devfreq_stats { * devfreq.nb to the corresponding register notifier call chain. * @work: delayed work for load monitoring. * @previous_freq: previously configured frequency value. + * @last_status: devfreq user device info, performance statistics * @data: Private data of the governor. The devfreq framework does not * touch this. * @user_min_freq_req: PM QoS minimum frequency request from user (via sysfs) @@ -151,7 +152,7 @@ struct devfreq_stats { * @nb_min: Notifier block for DEV_PM_QOS_MIN_FREQUENCY * @nb_max: Notifier block for DEV_PM_QOS_MAX_FREQUENCY * - * This structure stores the devfreq information for a give device. + * This structure stores the devfreq information for a given device. * * Note that when a governor accesses entries in struct devfreq in its * functions except for the context of callbacks defined in struct -- cgit v1.2.3 From c72bed23b9e45accdeab626cf2cb2bd08d846f3e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 16 Dec 2019 21:51:18 +0100 Subject: pinctrl: Allow modules to use pinctrl_[un]register_mappings Currently only the drivers/pinctrl/devicetree.c code allows registering pinctrl-mappings which may later be unregistered, all other mappings are assumed to be permanent. Non-dt platforms may also want to register pinctrl mappings from code which is build as a module, which requires being able to unregister the mapping when the module is unloaded to avoid dangling pointers. To allow unregistering the mappings the devicetree code uses 2 internal functions: pinctrl_register_map and pinctrl_unregister_map. pinctrl_register_map allows the devicetree code to tell the core to not memdup the mappings as it retains ownership of them and pinctrl_unregister_map does the unregistering, note this only works when the mappings where not memdupped. The only code relying on the memdup/shallow-copy done by pinctrl_register_mappings is arch/arm/mach-u300/core.c this commit replaces the __initdata with const, so that the shallow-copy is no longer necessary. After that we can get rid of the internal pinctrl_unregister_map function and just use pinctrl_register_mappings directly everywhere. This commit also renames pinctrl_unregister_map to pinctrl_unregister_mappings so that its naming matches its pinctrl_register_mappings counter-part and exports it. Together these 2 changes will allow non-dt platform code to register pinctrl-mappings from modules without breaking things on module unload (as they can now unregister the mapping on unload). Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20191216205122.1850923-2-hdegoede@redhat.com Signed-off-by: Linus Walleij --- include/linux/pinctrl/machine.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/machine.h b/include/linux/pinctrl/machine.h index ddd1b2773431..e987dc9fd2af 100644 --- a/include/linux/pinctrl/machine.h +++ b/include/linux/pinctrl/machine.h @@ -153,6 +153,7 @@ struct pinctrl_map { extern int pinctrl_register_mappings(const struct pinctrl_map *map, unsigned num_maps); +extern void pinctrl_unregister_mappings(const struct pinctrl_map *map); extern void pinctrl_provide_dummies(void); #else @@ -162,6 +163,10 @@ static inline int pinctrl_register_mappings(const struct pinctrl_map *map, return 0; } +static inline void pinctrl_unregister_mappings(const struct pinctrl_map *map) +{ +} + static inline void pinctrl_provide_dummies(void) { } -- cgit v1.2.3 From 92f983520cb82c407a091bbeabb505fc97419d3a Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Sat, 21 Dec 2019 07:50:08 +0100 Subject: USB: EHCI: ehci-mv: drop pxa_ehci_type and some device IDs This is merely a cleanup. None of these is used anywhere. Signed-off-by: Lubomir Rintel Acked-by: Alan Stern Link: https://lore.kernel.org/r/20191221065008.266445-4-lkundrak@v3.sk Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/mv_usb.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mv_usb.h b/include/linux/platform_data/mv_usb.h index 5376b6d799d5..20d239c02bf3 100644 --- a/include/linux/platform_data/mv_usb.h +++ b/include/linux/platform_data/mv_usb.h @@ -6,14 +6,6 @@ #ifndef __MV_PLATFORM_USB_H #define __MV_PLATFORM_USB_H -enum pxa_ehci_type { - EHCI_UNDEFINED = 0, - PXA_U2OEHCI, /* pxa 168, 9xx */ - PXA_SPH, /* pxa 168, 9xx SPH */ - MMP3_HSIC, /* mmp3 hsic */ - MMP3_FSIC, /* mmp3 fsic */ -}; - enum { MV_USB_MODE_OTG, MV_USB_MODE_HOST, -- cgit v1.2.3 From 3b31ec1848ec41d9501db3de61805e3ae173f485 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 17 Dec 2019 15:12:41 +0100 Subject: usb: renesas_usbhs: Switch to GPIO descriptor The Renesas USBHS driver includes a bit of surplus headers and uses the old GPIO API so let's switch it to use the GPIO descriptor. I noticed that the enable_gpio inside renesas_usbhs_driver_param isn't really referenced anywhere, and it is also the wrong type (u32) so let's just delete it and use a local variable instead. Cc: Eugeniu Rosca Cc: Veeraiyan Chidambaram Cc: Yoshihiro Shimoda Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20191217141241.57639-1-linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/renesas_usbhs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 6914475bbc86..d418c55523a7 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -170,8 +170,6 @@ struct renesas_usbhs_driver_param { */ int pio_dma_border; /* default is 64byte */ - u32 enable_gpio; - /* * option: */ -- cgit v1.2.3 From 51d22e855ea3459d4b272e46aff95de0e59e65a7 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 11 Dec 2019 15:52:26 +0100 Subject: usb: usb3503: Convert to use GPIO descriptors This converts the USB3503 to pick GPIO descriptors from the device tree instead of iteratively picking out GPIO number references and then referencing these from the global GPIO numberspace. The USB3503 is only used from device tree among the in-tree platforms. If board files would still desire to use it they can provide machine descriptor tables. Make sure to preserve semantics such as the reset delay introduced by Stefan. Cc: Chunfeng Yun Cc: Marek Szyprowski Cc: Stefan Agner Cc: Krzysztof Kozlowski Signed-off-by: Linus Walleij [mszyprow: invert the logic behind reset GPIO line] Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20191211145226.25074-1-m.szyprowski@samsung.com Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/usb3503.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/usb3503.h b/include/linux/platform_data/usb3503.h index e049d51c1353..d01ef97ddf36 100644 --- a/include/linux/platform_data/usb3503.h +++ b/include/linux/platform_data/usb3503.h @@ -17,9 +17,6 @@ enum usb3503_mode { struct usb3503_platform_data { enum usb3503_mode initial_mode; u8 port_off_mask; - int gpio_intn; - int gpio_connect; - int gpio_reset; }; #endif -- cgit v1.2.3 From 544fed47af4d2174ac0b550e9c8da15c2dfdb117 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 27 Dec 2019 15:02:28 +0200 Subject: ptp: introduce ptp_cancel_worker_sync In order to effectively use the PTP kernel thread for tasks such as timestamping packets, allow the user control over stopping it, which is needed e.g. when the timestamping queues must be drained. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 93cc4f1d444a..c64a1ef87240 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -243,6 +243,13 @@ int ptp_find_pin(struct ptp_clock *ptp, int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); +/** + * ptp_cancel_worker_sync() - cancel ptp auxiliary clock + * + * @ptp: The clock obtained from ptp_clock_register(). + */ +void ptp_cancel_worker_sync(struct ptp_clock *ptp); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -260,6 +267,8 @@ static inline int ptp_find_pin(struct ptp_clock *ptp, static inline int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay) { return -EOPNOTSUPP; } +static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) +{ } #endif -- cgit v1.2.3 From 1e762bd278d2a70bc74b9cbee7f1e93bd4704fe2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 27 Dec 2019 15:02:29 +0200 Subject: net: dsa: sja1105: Use PTP core's dedicated kernel thread for RX timestamping And move the queue of skb's waiting for RX timestamps into the ptp_data structure, since it isn't needed if PTP is not compiled. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 897e799dbcb9..c0b6a603ea8c 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -37,8 +37,6 @@ * the structure defined in struct sja1105_private. */ struct sja1105_tagger_data { - struct sk_buff_head skb_rxtstamp_queue; - struct work_struct rxtstamp_work; struct sk_buff *stampable_skb; /* Protects concurrent access to the meta state machine * from taggers running on multiple ports on SMP systems -- cgit v1.2.3 From 2f004eea0fc8f86b45dfc2007add2d4986de8d02 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 19 Dec 2019 00:11:50 +0100 Subject: x86/kasan: Print original address on #GP Make #GP exceptions caused by out-of-bounds KASAN shadow accesses easier to understand by computing the address of the original access and printing that. More details are in the comments in the patch. This turns an error like this: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault, probably for non-canonical address 0xe017577ddf75b7dd: 0000 [#1] PREEMPT SMP KASAN PTI into this: general protection fault, probably for non-canonical address 0xe017577ddf75b7dd: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: maybe wild-memory-access in range [0x00badbeefbadbee8-0x00badbeefbadbeef] The hook is placed in architecture-independent code, but is currently only wired up to the X86 exception handler because I'm not sufficiently familiar with the address space layout and exception handling mechanisms on other architectures. Signed-off-by: Jann Horn Signed-off-by: Borislav Petkov Reviewed-by: Dmitry Vyukov Cc: Alexander Potapenko Cc: Andrew Morton Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: kasan-dev@googlegroups.com Cc: linux-mm Cc: Peter Zijlstra Cc: Sean Christopherson Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/20191218231150.12139-4-jannh@google.com --- include/linux/kasan.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index e18fe54969e9..5cde9e7c2664 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -228,4 +228,10 @@ static inline void kasan_release_vmalloc(unsigned long start, unsigned long free_region_end) {} #endif +#ifdef CONFIG_KASAN_INLINE +void kasan_non_canonical_hook(unsigned long addr); +#else /* CONFIG_KASAN_INLINE */ +static inline void kasan_non_canonical_hook(unsigned long addr) { } +#endif /* CONFIG_KASAN_INLINE */ + #endif /* LINUX_KASAN_H */ -- cgit v1.2.3 From 8a4ab0b866d8aba85b9899edebf14b87b25f817f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 15 Dec 2019 13:39:47 -0800 Subject: fscrypt: constify inode parameter to filename encryption functions Constify the struct inode parameter to fscrypt_fname_disk_to_usr() and the other filename encryption functions so that users don't have to pass in a non-const inode when they are dealing with a const one, as in [1]. [1] https://lkml.kernel.org/linux-ext4/20191203051049.44573-6-drosen@google.com/ Cc: Daniel Rosenberg Link: https://lore.kernel.org/r/20191215213947.9521-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 1a7bffe78ed5..6eaa729544a3 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -153,8 +153,10 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname) extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, struct fscrypt_str *); extern void fscrypt_fname_free_buffer(struct fscrypt_str *); -extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, - const struct fscrypt_str *, struct fscrypt_str *); +extern int fscrypt_fname_disk_to_usr(const struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname); #define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32 @@ -438,7 +440,7 @@ static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) return; } -static inline int fscrypt_fname_disk_to_usr(struct inode *inode, +static inline int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, struct fscrypt_str *oname) -- cgit v1.2.3 From 56dce717950925f9d734b9e5621cbd41cbeb3e33 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 9 Dec 2019 12:50:21 -0800 Subject: fscrypt: introduce fscrypt_needs_contents_encryption() Add a function fscrypt_needs_contents_encryption() which takes an inode and returns true if it's an encrypted regular file and the kernel was built with fscrypt support. This will allow replacing duplicated checks of IS_ENCRYPTED() && S_ISREG() on the I/O paths in ext4 and f2fs, while also optimizing out unneeded code when !CONFIG_FS_ENCRYPTION. Link: https://lore.kernel.org/r/20191209205021.231767-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 6eaa729544a3..6fe8d0f96a4a 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -72,6 +72,21 @@ static inline bool fscrypt_has_encryption_key(const struct inode *inode) return READ_ONCE(inode->i_crypt_info) != NULL; } +/** + * fscrypt_needs_contents_encryption() - check whether an inode needs + * contents encryption + * + * Return: %true iff the inode is an encrypted regular file and the kernel was + * built with fscrypt support. + * + * If you need to know whether the encrypt bit is set even when the kernel was + * built without fscrypt support, you must use IS_ENCRYPTED() directly instead. + */ +static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) +{ + return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); +} + static inline bool fscrypt_dummy_context_enabled(struct inode *inode) { return inode->i_sb->s_cop->dummy_context && @@ -269,6 +284,11 @@ static inline bool fscrypt_has_encryption_key(const struct inode *inode) return false; } +static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) +{ + return false; +} + static inline bool fscrypt_dummy_context_enabled(struct inode *inode) { return false; -- cgit v1.2.3 From e7153bf70c3496bac00e7e4f395bb8d8394ac0ea Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 7 Dec 2019 19:34:18 +0100 Subject: can: can_dropped_invalid_skb(): ensure an initialized headroom in outgoing CAN sk_buffs KMSAN sysbot detected a read access to an untinitialized value in the headroom of an outgoing CAN related sk_buff. When using CAN sockets this area is filled appropriately - but when using a packet socket this initialization is missing. The problematic read access occurs in the CAN receive path which can only be triggered when the sk_buff is sent through a (virtual) CAN interface. So we check in the sending path whether we need to perform the missing initializations. Fixes: d3b58c47d330d ("can: replace timestamp as unique skb attribute") Reported-by: syzbot+b02ff0707a97e4e79ebb@syzkaller.appspotmail.com Signed-off-by: Oliver Hartkopp Tested-by: Oliver Hartkopp Cc: linux-stable # >= v4.1 Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 9b3c720a31b1..5e3d45525bd3 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -91,6 +92,36 @@ struct can_priv { #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, + struct sk_buff *skb) +{ + /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ + if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) + return false; + + /* af_packet does not apply CAN skb specific settings */ + if (skb->ip_summed == CHECKSUM_NONE) { + /* init headroom */ + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* preform proper loopback on capable devices */ + if (dev->flags & IFF_ECHO) + skb->pkt_type = PACKET_LOOPBACK; + else + skb->pkt_type = PACKET_HOST; + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + } + + return true; +} + /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ static inline bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) @@ -108,6 +139,9 @@ static inline bool can_dropped_invalid_skb(struct net_device *dev, } else goto inval_skb; + if (!can_skb_headroom_valid(dev, skb)) + goto inval_skb; + return false; inval_skb: -- cgit v1.2.3 From 49fdcd7577efe9efe863cdbb154f32a96970c1bc Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 10 Oct 2019 12:01:48 +0200 Subject: firmware: psci: Export functions to manage the OSI mode To allow subsequent changes to implement support for OSI mode through the cpuidle-psci driver, export the existing psci_has_osi_support(). Export also a new function, psci_set_osi_mode(), that allows its caller to enable the OS-initiated CPU-suspend mode in the PSCI FW. To deal with backwards compatibility for a kernel started through a kexec call, default to set the CPU-suspend mode to the Platform Coordinated mode during boot. Signed-off-by: Ulf Hansson Reviewed-by: Sudeep Holla --- include/linux/psci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psci.h b/include/linux/psci.h index ebe0a881d13d..a67712b73b6c 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -18,6 +18,8 @@ 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); +bool psci_has_osi_support(void); enum smccc_version { SMCCC_VERSION_1_0, -- cgit v1.2.3 From b9f8c26afc405a4a616e765e949bdd551151e41d Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 10 Oct 2019 12:01:48 +0200 Subject: of: base: Add of_get_cpu_state_node() to get idle states for a CPU node The CPU's idle state nodes are currently parsed at the common cpuidle DT library, but also when initializing data for specific CPU idle operations, as in the PSCI cpuidle driver case and qcom-spm cpuidle case. To avoid open-coding, let's introduce of_get_cpu_state_node(), which takes the device node for the CPU and the index to the requested idle state node, as in-parameters. In case a corresponding idle state node is found, it returns the node with the refcount incremented for it, else it returns NULL. Moreover, for PSCI there are two options to describe the CPU's idle states [1], either via a flattened description or a hierarchical layout. Hence, let's take both options into account. [1] Documentation/devicetree/bindings/arm/psci.yaml Suggested-by: Sudeep Holla Co-developed-by: Lina Iyer Signed-off-by: Lina Iyer Reviewed-by: Rob Herring Reviewed-by: Daniel Lezcano Signed-off-by: Ulf Hansson Reviewed-by: Sudeep Holla --- include/linux/of.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 844f89e1b039..c669c0a4732f 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -351,6 +351,8 @@ extern const void *of_get_property(const struct device_node *node, int *lenp); extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); extern struct device_node *of_get_next_cpu_node(struct device_node *prev); +extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, + int index); #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) @@ -765,6 +767,12 @@ static inline struct device_node *of_get_next_cpu_node(struct device_node *prev) return NULL; } +static inline struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, + int index) +{ + return NULL; +} + static inline int of_n_addr_cells(struct device_node *np) { return 0; -- cgit v1.2.3 From 9c6ceecb6541954dfc410aa8883f872469326c73 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 10 Oct 2019 12:01:48 +0200 Subject: cpuidle: psci: Support CPU hotplug for the hierarchical model When the hierarchical CPU topology is used and when a CPU is put offline, that CPU prevents its PM domain from being powered off, which is because genpd observes the corresponding attached device as being active from a runtime PM point of view. Furthermore, any potential master PM domains are also prevented from being powered off. To address this limitation, let's add add a new CPU hotplug state (CPUHP_AP_CPU_PM_STARTING) and register up/down callbacks for it, which allows us to deal with runtime PM accordingly. Signed-off-by: Ulf Hansson Reviewed-by: Sudeep Holla Acked-by: Rafael J. Wysocki --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index e51ee772b9f5..01f04ed6ad92 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -95,6 +95,7 @@ enum cpuhp_state { CPUHP_AP_OFFLINE, CPUHP_AP_SCHED_STARTING, CPUHP_AP_RCUTREE_DYING, + CPUHP_AP_CPU_PM_STARTING, CPUHP_AP_IRQ_GIC_STARTING, CPUHP_AP_IRQ_HIP04_STARTING, CPUHP_AP_IRQ_ARMADA_XP_STARTING, -- cgit v1.2.3 From dedd14925ec6f82a2840c009bc175e2b528ace8e Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 30 Dec 2019 13:59:30 +0100 Subject: PM / Domains: Introduce a genpd OF helper that removes a subdomain We already have the of_genpd_add_subdomain() helper, but no corresponding of_genpd_remove_subdomain(), so let's add it. Subsequent changes starts to make use of it. Signed-off-by: Ulf Hansson Acked-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 5a31c711b896..9ec78ee53652 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -284,6 +284,8 @@ void of_genpd_del_provider(struct device_node *np); int of_genpd_add_device(struct of_phandle_args *args, struct device *dev); int of_genpd_add_subdomain(struct of_phandle_args *parent_spec, struct of_phandle_args *subdomain_spec); +int of_genpd_remove_subdomain(struct of_phandle_args *parent_spec, + struct of_phandle_args *subdomain_spec); struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n); @@ -322,6 +324,12 @@ static inline int of_genpd_add_subdomain(struct of_phandle_args *parent_spec, return -ENODEV; } +static inline int of_genpd_remove_subdomain(struct of_phandle_args *parent_spec, + struct of_phandle_args *subdomain_spec) +{ + return -ENODEV; +} + static inline int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n) { -- cgit v1.2.3 From fef093ff7e9654eec77e79b8170485241f01d027 Mon Sep 17 00:00:00 2001 From: Stanley Chu Date: Mon, 30 Dec 2019 13:32:25 +0800 Subject: scsi: soc: mediatek: add header for SiP service interface Add a common header for the SiP service interface in MediaTek Chipsets. Cc: Alim Akhtar Cc: Avri Altman Cc: Bart Van Assche Cc: Bean Huo Cc: Can Guo Cc: Florian Fainelli Cc: Matthias Brugger Link: https://lore.kernel.org/r/1577683950-1702-2-git-send-email-stanley.chu@mediatek.com Signed-off-by: Stanley Chu Signed-off-by: Martin K. Petersen --- include/linux/soc/mediatek/mtk_sip_svc.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/soc/mediatek/mtk_sip_svc.h (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_sip_svc.h b/include/linux/soc/mediatek/mtk_sip_svc.h new file mode 100644 index 000000000000..082398e0cfb1 --- /dev/null +++ b/include/linux/soc/mediatek/mtk_sip_svc.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 MediaTek Inc. + */ +#ifndef __MTK_SIP_SVC_H +#define __MTK_SIP_SVC_H + +/* Error Code */ +#define SIP_SVC_E_SUCCESS 0 +#define SIP_SVC_E_NOT_SUPPORTED -1 +#define SIP_SVC_E_INVALID_PARAMS -2 +#define SIP_SVC_E_INVALID_RANGE -3 +#define SIP_SVC_E_PERMISSION_DENIED -4 + +#ifdef CONFIG_ARM64 +#define MTK_SIP_SMC_CONVENTION ARM_SMCCC_SMC_64 +#else +#define MTK_SIP_SMC_CONVENTION ARM_SMCCC_SMC_32 +#endif + +#define MTK_SIP_SMC_CMD(fn_id) \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, MTK_SIP_SMC_CONVENTION, \ + ARM_SMCCC_OWNER_SIP, fn_id) + +#endif -- cgit v1.2.3 From 202bf8d7583f2b6e28de2e9edf6fcd7e3667a173 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 12 Dec 2019 18:15:25 +0100 Subject: compat: provide compat_ptr() on all architectures In order to avoid needless #ifdef CONFIG_COMPAT checks, move the compat_ptr() definition to linux/compat.h where it can be seen by any file regardless of the architecture. Only s390 needs a special definition, this can use the self-#define trick we have elsewhere. Reviewed-by: Ben Hutchings Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 68f79d855c3d..11083d84eb23 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -958,4 +958,22 @@ static inline bool in_compat_syscall(void) { return false; } #endif /* CONFIG_COMPAT */ +/* + * A pointer passed in from user mode. This should not + * be used for syscall parameters, just declare them + * as pointers because the syscall entry code will have + * appropriately converted them already. + */ +#ifndef compat_ptr +static inline void __user *compat_ptr(compat_uptr_t uptr) +{ + return (void __user *)(unsigned long)uptr; +} +#endif + +static inline compat_uptr_t ptr_to_compat(void __user *uptr) +{ + return (u32)(unsigned long)uptr; +} + #endif /* _LINUX_COMPAT_H */ -- cgit v1.2.3 From ee6a129dffe10ae30b45b5a744e7c0a056291d13 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 28 Nov 2019 15:48:10 +0100 Subject: compat_ioctl: block: add blkdev_compat_ptr_ioctl A lot of block drivers need only a trivial .compat_ioctl callback. Add a helper function that can be set as the callback pointer to only convert the argument using the compat_ptr() conversion and otherwise assume all input and output data is compatible, or handled using in_compat_syscall() checks. This mirrors the compat_ptr_ioctl() helper function used in character devices. Reviewed-by: Ben Hutchings Signed-off-by: Arnd Bergmann --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 47eb22a3b7f9..3e0408618da7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1711,6 +1711,13 @@ struct block_device_operations { const struct pr_ops *pr_ops; }; +#ifdef CONFIG_COMPAT +extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, + unsigned int, unsigned long); +#else +#define blkdev_compat_ptr_ioctl NULL +#endif + extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); extern int bdev_read_page(struct block_device *, sector_t, struct page *); -- cgit v1.2.3 From c103d6ee69f93e123dd05e7d307b099b83c0d82c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 15 Mar 2019 17:26:56 +0100 Subject: compat_ioctl: ide: floppy: add handler Rather than relying on fs/compat_ioctl.c, this adds support for a compat_ioctl() callback in the ide-floppy driver directly, which lets it translate the scsi commands. Reviewed-by: Ben Hutchings Signed-off-by: Arnd Bergmann --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 46b771d6999e..06dae6438557 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -413,6 +413,8 @@ struct ide_disk_ops { sector_t); int (*ioctl)(struct ide_drive_s *, struct block_device *, fmode_t, unsigned int, unsigned long); + int (*compat_ioctl)(struct ide_drive_s *, struct block_device *, + fmode_t, unsigned int, unsigned long); }; /* ATAPI device flags */ -- cgit v1.2.3 From 77b9040195dea3fcddf19e136c9e99a501351778 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 27 Nov 2019 21:25:36 +0100 Subject: compat_ioctl: simplify the implementation Now that both native and compat ioctl syscalls are in the same file, a couple of simplifications can be made, bringing the implementation closer together: - do_vfs_ioctl(), ioctl_preallocate(), and compat_ioctl_preallocate() can become static, allowing the compiler to optimize better - slightly update the coding style for consistency between the functions. - rather than listing each command in two switch statements for the compat case, just call a single function that has all the common commands. As a side-effect, FS_IOC_RESVSP/FS_IOC_RESVSP64 are now available to x86 compat tasks, along with FS_IOC_RESVSP_32/FS_IOC_RESVSP64_32. This is harmless for i386 emulation, and can be considered a bugfix for x32 emulation, which never supported these in the past. Reviewed-by: Ben Hutchings Signed-off-by: Arnd Bergmann --- include/linux/falloc.h | 2 -- include/linux/fs.h | 4 ---- 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 8bf3d79f3e82..f3f0b97b1675 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -51,8 +51,6 @@ struct space_resv_32 { #define FS_IOC_UNRESVSP64_32 _IOW ('X', 43, struct space_resv_32) #define FS_IOC_ZERO_RANGE_32 _IOW ('X', 57, struct space_resv_32) -int compat_ioctl_preallocate(struct file *, int, struct space_resv_32 __user *); - #endif #endif /* _FALLOC_H_ */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..daf570bca42a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2552,10 +2552,6 @@ extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); -/* fs/ioctl.c */ - -extern int ioctl_preallocate(struct file *filp, int mode, void __user *argp); - /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); -- cgit v1.2.3 From 75c0b0e118b929cb8bad8ce1ab4c8be8a76c45e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Nov 2019 20:28:12 +0100 Subject: compat_ioctl: scsi: handle HDIO commands from drivers The ata_sas_scsi_ioctl() function implements a number of HDIO_* commands for SCSI devices, it is used by all libata drivers as well as a few drivers that support SAS attached SATA drives. The only command that is not safe for compat ioctls here is HDIO_GET_32BIT. Change the implementation to check for in_compat_syscall() in order to do both cases correctly, and change all callers to use it as both native and compat callback pointers, including the indirect callers through sas_ioctl and ata_scsi_ioctl. Reviewed-by: Ben Hutchings Signed-off-by: Arnd Bergmann --- include/linux/libata.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 2dbde119721d..a36bdcb8d9e9 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1109,6 +1109,11 @@ extern void ata_host_init(struct ata_host *, struct device *, struct ata_port_op extern int ata_scsi_detect(struct scsi_host_template *sht); extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, void __user *arg); +#ifdef CONFIG_COMPAT +#define ATA_SCSI_COMPAT_IOCTL .compat_ioctl = ata_scsi_ioctl, +#else +#define ATA_SCSI_COMPAT_IOCTL /* empty */ +#endif extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, unsigned int cmd, void __user *arg); @@ -1341,6 +1346,7 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .module = THIS_MODULE, \ .name = drv_name, \ .ioctl = ata_scsi_ioctl, \ + ATA_SCSI_COMPAT_IOCTL \ .queuecommand = ata_scsi_queuecmd, \ .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ -- cgit v1.2.3 From 691f50ab2742556aea467a946e10393da2e8d9ef Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Tue, 27 Aug 2019 11:09:21 +0000 Subject: fbdev: fbmem: allow overriding the number of bootup logos Probably most useful if you want no logo at all, or if you only want one logo regardless of how many CPU cores you have. Signed-off-by: Peter Rosin Reviewed-by: Geert Uytterhoeven Cc: Jonathan Corbet Cc: Matthew Wilcox Signed-off-by: Bartlomiej Zolnierkiewicz Link: https://patchwork.freedesktop.org/patch/msgid/20190827110854.12574-3-peda@axentia.se --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 6557fabdea62..3b4b2f0c6994 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -625,6 +625,7 @@ extern int fb_new_modelist(struct fb_info *info); extern struct fb_info *registered_fb[FB_MAX]; extern int num_registered_fb; extern bool fb_center_logo; +extern int fb_logo_count; extern struct class *fb_class; #define for_each_registered_fb(i) \ -- cgit v1.2.3 From 3f666c56c6b8cc40a5e9002aac484b8f5b83c402 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Fri, 3 Jan 2020 13:33:07 -0500 Subject: dax: Pass dax_dev instead of bdev to dax_writeback_mapping_range() As of now dax_writeback_mapping_range() takes "struct block_device" as a parameter and dax_dev is searched from bdev name. This also involves taking a fresh reference on dax_dev and putting that reference at the end of function. We are developing a new filesystem virtio-fs and using dax to access host page cache directly. But there is no block device. IOW, we want to make use of dax but want to get rid of this assumption that there is always a block device associated with dax_dev. So pass in "struct dax_device" as parameter instead of bdev. ext2/ext4/xfs are current users and they already have a reference on dax_device. So there is no need to take reference and drop reference to dax_device on each call of this function. Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Vivek Goyal Link: https://lore.kernel.org/r/20200103183307.GB13350@redhat.com Signed-off-by: Dan Williams --- include/linux/dax.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 9bd8528bd305..d5932e47c597 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -141,7 +141,7 @@ static inline void fs_put_dax(struct dax_device *dax_dev) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, - struct block_device *bdev, struct writeback_control *wbc); + struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); dax_entry_t dax_lock_page(struct page *page); @@ -180,7 +180,7 @@ static inline struct page *dax_layout_busy_page(struct address_space *mapping) } static inline int dax_writeback_mapping_range(struct address_space *mapping, - struct block_device *bdev, struct writeback_control *wbc) + struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } -- cgit v1.2.3 From b39c78b2aa09cae05f3a48c11f67b3add0d604de Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Fri, 3 Jan 2020 11:51:00 +0800 Subject: net: remove the check argument from __skb_gro_checksum_convert The argument is always ignored, so remove it. Signed-off-by: Li RongQing Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2fd19fb8826d..2741aa35bec6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2826,16 +2826,16 @@ static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) } static inline void __skb_gro_checksum_convert(struct sk_buff *skb, - __sum16 check, __wsum pseudo) + __wsum pseudo) { NAPI_GRO_CB(skb)->csum = ~pseudo; NAPI_GRO_CB(skb)->csum_valid = 1; } -#define skb_gro_checksum_try_convert(skb, proto, check, compute_pseudo) \ +#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_gro_checksum_convert_check(skb)) \ - __skb_gro_checksum_convert(skb, check, \ + __skb_gro_checksum_convert(skb, \ compute_pseudo(skb, proto)); \ } while (0) -- cgit v1.2.3 From 3593f69c55c53de6e2de8799e4892b8c795f3713 Mon Sep 17 00:00:00 2001 From: Eugene Crosser Date: Thu, 19 Dec 2019 15:48:47 +0200 Subject: RDMA/mlx4: Redo TX checksum offload in line with docs Ingress checksum offload was not working for IPv6 frames because the conditional expression that checks validation status passed from the hardware was not matching the algorithm described in the documentation. This patch defines L4_CSUM flag (which falls inside the badfcs_enc field in the existing definition of the CQE layout) and replaces the conditional expression with the one defined in the "ConnectX(r) Family Programmer's Manual" document. Link: https://lore.kernel.org/r/20191219134847.413582-1-leon@kernel.org Signed-off-by: Eugene Crosser Reviewed-by: Jack Wang Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx4/cq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h index 508e8cc5ee86..653d2a0aa44c 100644 --- a/include/linux/mlx4/cq.h +++ b/include/linux/mlx4/cq.h @@ -130,6 +130,11 @@ enum { MLX4_CQE_STATUS_IPOK = 1 << 12, }; +/* L4_CSUM is logically part of status, but has to checked against badfcs_enc */ +enum { + MLX4_CQE_STATUS_L4_CSUM = 1 << 2, +}; + enum { MLX4_CQE_LLC = 1, MLX4_CQE_SNAP = 1 << 1, -- cgit v1.2.3 From bade7e1fbd34f46462e6eb1db5474832a4144ac2 Mon Sep 17 00:00:00 2001 From: Rijo Thomas Date: Fri, 27 Dec 2019 10:54:02 +0530 Subject: tee: amdtee: check TEE status during driver initialization The AMD-TEE driver should check if TEE is available before registering itself with TEE subsystem. This ensures that there is a TEE which the driver can talk to before proceeding with tee device node allocation. Cc: Ard Biesheuvel Cc: Tom Lendacky Acked-by: Jens Wiklander Co-developed-by: Devaraj Rangasamy Signed-off-by: Devaraj Rangasamy Signed-off-by: Rijo Thomas Reviewed-by: Gary R Hook Signed-off-by: Herbert Xu --- include/linux/psp-tee.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp-tee.h b/include/linux/psp-tee.h index 63bb2212fce0..cb0c95d6d76b 100644 --- a/include/linux/psp-tee.h +++ b/include/linux/psp-tee.h @@ -62,6 +62,19 @@ enum tee_cmd_id { int psp_tee_process_cmd(enum tee_cmd_id cmd_id, void *buf, size_t len, u32 *status); +/** + * psp_check_tee_status() - Checks whether there is a TEE which a driver can + * talk to. + * + * This function can be used by AMD-TEE driver to query if there is TEE with + * which it can communicate. + * + * Returns: + * 0 if the device has TEE + * -%ENODEV if there is no TEE available + */ +int psp_check_tee_status(void); + #else /* !CONFIG_CRYPTO_DEV_SP_PSP */ static inline int psp_tee_process_cmd(enum tee_cmd_id cmd_id, void *buf, @@ -69,5 +82,10 @@ static inline int psp_tee_process_cmd(enum tee_cmd_id cmd_id, void *buf, { return -ENODEV; } + +static inline int psp_check_tee_status(void) +{ + return -ENODEV; +} #endif /* CONFIG_CRYPTO_DEV_SP_PSP */ #endif /* __PSP_TEE_H_ */ -- cgit v1.2.3 From 57415790f405534e5578d0106d806630c325dcb3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Jan 2020 21:09:35 -0700 Subject: block: remove unused mp_bvec_last_segment After commit 85a8ce62c2ea ("block: add bio_truncate to fix guard_bio_eod") this function is unused, remove it. Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bvec.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 679a42253170..a81c13ac1972 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -153,26 +153,4 @@ static inline void bvec_advance(const struct bio_vec *bvec, } } -/* - * Get the last single-page segment from the multi-page bvec and store it - * in @seg - */ -static inline void mp_bvec_last_segment(const struct bio_vec *bvec, - struct bio_vec *seg) -{ - unsigned total = bvec->bv_offset + bvec->bv_len; - unsigned last_page = (total - 1) / PAGE_SIZE; - - seg->bv_page = bvec->bv_page + last_page; - - /* the whole segment is inside the last page */ - if (bvec->bv_offset >= last_page * PAGE_SIZE) { - seg->bv_offset = bvec->bv_offset % PAGE_SIZE; - seg->bv_len = bvec->bv_len; - } else { - seg->bv_offset = 0; - seg->bv_len = total - last_page * PAGE_SIZE; - } -} - #endif /* __LINUX_BVEC_ITER_H */ -- cgit v1.2.3 From 9a9b5a4af066f1245d7848a5d5d5c8147c18aa28 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:12 -0700 Subject: clk: gpio: Use DT way of specifying parents Nobody has used the gpio clk registration functions nor the gpio clk_ops exposed by the basic gpio clk type. Let's remove all those APIs and move the gpio clk support into the C file. Since nothing is using the exported APIs, simplify the driver to be a platform driver that uses clk_parent_data to pick 0th or 1st cell of the node's clocks property. Cc: Simon Horman Cc: Magnus Damm Cc: Geert Uytterhoeven Cc: Enric Balletbo i Serra Cc: Tony Lindgren Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-2-sboyd@kernel.org --- include/linux/clk-provider.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index caf4b9df16eb..4bef76fab942 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -752,44 +752,6 @@ struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name, unsigned long flags); void clk_hw_unregister_composite(struct clk_hw *hw); -/** - * struct clk_gpio - gpio gated clock - * - * @hw: handle between common and hardware-specific interfaces - * @gpiod: gpio descriptor - * - * Clock with a gpio control for enabling and disabling the parent clock - * or switching between two parents by asserting or deasserting the gpio. - * - * Implements .enable, .disable and .is_enabled or - * .get_parent, .set_parent and .determine_rate depending on which clk_ops - * is used. - */ -struct clk_gpio { - struct clk_hw hw; - struct gpio_desc *gpiod; -}; - -#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw) - -extern const struct clk_ops clk_gpio_gate_ops; -struct clk *clk_register_gpio_gate(struct device *dev, const char *name, - const char *parent_name, struct gpio_desc *gpiod, - unsigned long flags); -struct clk_hw *clk_hw_register_gpio_gate(struct device *dev, const char *name, - const char *parent_name, struct gpio_desc *gpiod, - unsigned long flags); -void clk_hw_unregister_gpio_gate(struct clk_hw *hw); - -extern const struct clk_ops clk_gpio_mux_ops; -struct clk *clk_register_gpio_mux(struct device *dev, const char *name, - const char * const *parent_names, u8 num_parents, struct gpio_desc *gpiod, - unsigned long flags); -struct clk_hw *clk_hw_register_gpio_mux(struct device *dev, const char *name, - const char * const *parent_names, u8 num_parents, struct gpio_desc *gpiod, - unsigned long flags); -void clk_hw_unregister_gpio_mux(struct clk_hw *hw); - struct clk *clk_register(struct device *dev, struct clk_hw *hw); struct clk *devm_clk_register(struct device *dev, struct clk_hw *hw); -- cgit v1.2.3 From 576859dfc54897e405cd7c6ad683792737dcebfd Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:14 -0700 Subject: clk: fixed-rate: Remove clk_register_fixed_rate_with_accuracy() There aren't any users of this API anymore. Remove it. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-4-sboyd@kernel.org --- include/linux/clk-provider.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 4bef76fab942..d7082f421850 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -337,9 +337,6 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, struct clk_hw *clk_hw_register_fixed_rate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned long fixed_rate); -struct clk *clk_register_fixed_rate_with_accuracy(struct device *dev, - const char *name, const char *parent_name, unsigned long flags, - unsigned long fixed_rate, unsigned long fixed_accuracy); void clk_unregister_fixed_rate(struct clk *clk); struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev, const char *name, const char *parent_name, unsigned long flags, -- cgit v1.2.3 From 38d1e38093b7d85ed0fa3a28c13c3266db505b3b Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:15 -0700 Subject: clk: fixed-rate: Move to_clk_fixed_rate() to C file The only user of this macro is the fixed rate basic type. Move it there to avoid polluting provider drivers. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-5-sboyd@kernel.org --- include/linux/clk-provider.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index d7082f421850..db4c760e8645 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -328,8 +328,6 @@ struct clk_fixed_rate { unsigned long fixed_accuracy; }; -#define to_clk_fixed_rate(_hw) container_of(_hw, struct clk_fixed_rate, hw) - extern const struct clk_ops clk_fixed_rate_ops; struct clk *clk_register_fixed_rate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, -- cgit v1.2.3 From 32205b75414e530dc6c95ac39f70ef8e194327e0 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:16 -0700 Subject: clk: fixed-rate: Document accuracy member This member isn't documented, leading to kernel-doc warnings. Document it. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-6-sboyd@kernel.org --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index db4c760e8645..8bb517b670e3 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -321,6 +321,7 @@ struct clk_hw { * struct clk_fixed_rate - fixed-rate clock * @hw: handle between common and hardware-specific interfaces * @fixed_rate: constant frequency of clock + * @fixed_accuracy: constant accuracy of clock in ppb (parts per billion) */ struct clk_fixed_rate { struct clk_hw hw; -- cgit v1.2.3 From 2d34f09e79c9e96e9b748b320b9b0fa3d5e6b553 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:17 -0700 Subject: clk: fixed-rate: Add support for specifying parents via DT/pointers After commit fc0c209c147f ("clk: Allow parents to be specified without string names") we can use DT or direct clk_hw pointers to specify parents. Create a generic function that shouldn't be used very often to encode the multitude of ways of registering a fixed rate clk with different parent information. Then add a bunch of wrapper macros that only pass down what needs to be passed down to the generic function to support this with less arguments. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-7-sboyd@kernel.org --- include/linux/clk-provider.h | 100 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 94 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 8bb517b670e3..bb0c4c916a16 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -322,24 +322,112 @@ struct clk_hw { * @hw: handle between common and hardware-specific interfaces * @fixed_rate: constant frequency of clock * @fixed_accuracy: constant accuracy of clock in ppb (parts per billion) + * @flags: hardware specific flags */ struct clk_fixed_rate { struct clk_hw hw; unsigned long fixed_rate; unsigned long fixed_accuracy; + unsigned long flags; }; extern const struct clk_ops clk_fixed_rate_ops; +struct clk_hw *__clk_hw_register_fixed_rate(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, unsigned long flags, + unsigned long fixed_rate, unsigned long fixed_accuracy, + unsigned long clk_fixed_flags); struct clk *clk_register_fixed_rate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned long fixed_rate); -struct clk_hw *clk_hw_register_fixed_rate(struct device *dev, const char *name, - const char *parent_name, unsigned long flags, - unsigned long fixed_rate); +/** + * clk_hw_register_fixed_rate - register fixed-rate clock with the clock + * framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + */ +#define clk_hw_register_fixed_rate(dev, name, parent_name, flags, fixed_rate) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (fixed_rate), 0, 0) +/** + * clk_hw_register_fixed_rate_parent_hw - register fixed-rate clock with + * the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_hw: pointer to parent clk + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + */ +#define clk_hw_register_fixed_rate_parent_hw(dev, name, parent_hw, flags, \ + fixed_rate) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw), \ + NULL, (flags), (fixed_rate), 0, 0) +/** + * clk_hw_register_fixed_rate_parent_data - register fixed-rate clock with + * the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + */ +#define clk_hw_register_fixed_rate_parent_data(dev, name, parent_hw, flags, \ + fixed_rate) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (fixed_rate), 0, \ + 0) +/** + * clk_hw_register_fixed_rate_with_accuracy - register fixed-rate clock with + * the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + * @fixed_accuracy: non-adjustable clock rate + */ +#define clk_hw_register_fixed_rate_with_accuracy(dev, name, parent_name, \ + flags, fixed_rate, \ + fixed_accuracy) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), \ + NULL, NULL, (flags), (fixed_rate), \ + (fixed_accuracy), 0) +/** + * clk_hw_register_fixed_rate_with_accuracy_parent_hw - register fixed-rate + * clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_hw: pointer to parent clk + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + * @fixed_accuracy: non-adjustable clock accuracy + */ +#define clk_hw_register_fixed_rate_with_accuracy_parent_hw(dev, name, \ + parent_hw, flags, fixed_rate, fixed_accuracy) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw) \ + NULL, NULL, (flags), (fixed_rate), \ + (fixed_accuracy), 0) +/** + * clk_hw_register_fixed_rate_with_accuracy_parent_data - register fixed-rate + * clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + * @fixed_accuracy: non-adjustable clock accuracy + */ +#define clk_hw_register_fixed_rate_with_accuracy_parent_data(dev, name, \ + parent_data, flags, fixed_rate, fixed_accuracy) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL, \ + (parent_data), NULL, (flags), \ + (fixed_rate), (fixed_accuracy), 0) + void clk_unregister_fixed_rate(struct clk *clk); -struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev, - const char *name, const char *parent_name, unsigned long flags, - unsigned long fixed_rate, unsigned long fixed_accuracy); void clk_hw_unregister_fixed_rate(struct clk_hw *hw); void of_fixed_clk_setup(struct device_node *np); -- cgit v1.2.3 From 14a65084f9310ba6a4017c365f9c9820b099dde5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 3 Jan 2020 18:11:30 +0100 Subject: net: ethernet: sxgbe: Rename Samsung to lowercase Fix up inconsistent usage of upper and lowercase letters in "Samsung" name. "SAMSUNG" is not an abbreviation but a regular trademarked name. Therefore it should be written with lowercase letters starting with capital letter. Although advertisement materials usually use uppercase "SAMSUNG", the lowercase version is used in all legal aspects (e.g. on Wikipedia and in privacy/legal statements on https://www.samsung.com/semiconductor/privacy-global/). Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/linux/sxgbe_platform.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h index 85ec745767bd..966146f7267a 100644 --- a/include/linux/sxgbe_platform.h +++ b/include/linux/sxgbe_platform.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * 10G controller driver for Samsung EXYNOS SoCs + * 10G controller driver for Samsung Exynos SoCs * * Copyright (C) 2013 Samsung Electronics Co., Ltd. * http://www.samsung.com -- cgit v1.2.3 From c114574ebfdf42f826776f717c8056a00fa94881 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 3 Jan 2020 20:43:17 +0000 Subject: net: phy: add PHY_INTERFACE_MODE_10GBASER Recent discussion has revealed that the use of PHY_INTERFACE_MODE_10GKR is incorrect. Add a 10GBASE-R definition, document both the -R and -KR versions, and the fact that 10GKR was used incorrectly. Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 30e599c454db..5932bb8e9c35 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -100,9 +100,11 @@ typedef enum { PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, - /* 10GBASE-KR, XFI, SFI - single lane 10G Serdes */ - PHY_INTERFACE_MODE_10GKR, + /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ + PHY_INTERFACE_MODE_10GBASER, PHY_INTERFACE_MODE_USXGMII, + /* 10GBASE-KR - with Clause 73 AN */ + PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -176,10 +178,12 @@ static inline const char *phy_modes(phy_interface_t interface) return "rxaui"; case PHY_INTERFACE_MODE_XAUI: return "xaui"; - case PHY_INTERFACE_MODE_10GKR: - return "10gbase-kr"; + case PHY_INTERFACE_MODE_10GBASER: + return "10gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; + case PHY_INTERFACE_MODE_10GKR: + return "10gbase-kr"; default: return "unknown"; } -- cgit v1.2.3 From 0a51826c6e05c5b6cc423b376b81c311e9e485b0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 4 Jan 2020 02:37:09 +0200 Subject: net: dsa: sja1105: Always send through management routes in slot 0 I finally found out how the 4 management route slots are supposed to be used, but.. it's not worth it. The description from the comment I've just deleted in this commit is still true: when more than 1 management slot is active at the same time, the switch will match frames incoming [from the CPU port] on the lowest numbered management slot that matches the frame's DMAC. My issue was that one was not supposed to statically assign each port a slot. Yes, there are 4 slots and also 4 non-CPU ports, but that is a mere coincidence. Instead, the switch can be used like this: every management frame gets a slot at the right of the most recently assigned slot: Send mgmt frame 1 through S0: S0 x x x Send mgmt frame 2 through S1: S0 S1 x x Send mgmt frame 3 through S2: S0 S1 S2 x Send mgmt frame 4 through S3: S0 S1 S2 S3 The difference compared to the old usage is that the transmission of frames 1-4 doesn't need to wait until the completion of the management route. It is safe to use a slot to the right of the most recently used one, because by protocol nobody will program a slot to your left and "steal" your route towards the correct egress port. So there is a potential throughput benefit here. But mgmt frame 5 has no more free slot to use, so it has to wait until _all_ of S0, S1, S2, S3 are full, in order to use S0 again. And that's actually exactly the problem: I was looking for something that would bring more predictable transmission latency, but this is exactly the opposite: 3 out of 4 frames would be transmitted quicker, but the 4th would draw the short straw and have a worse worst-case latency than before. Useless. Things are made even worse by PTP TX timestamping, which is something I won't go deeply into here. Suffice to say that the fact there is a driver-level lock on the SPI bus offsets any potential throughput gains that parallelism might bring. So there's no going back to the multi-slot scheme, remove the "mgmt_slot" variable from sja1105_port and the dummy static assignment made at probe time. While passing by, also remove the assignment to casc_port altogether. Don't pretend that we support cascaded setups. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index c0b6a603ea8c..317e05b2584b 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -56,7 +56,6 @@ struct sja1105_port { struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; - int mgmt_slot; }; #endif /* _NET_DSA_SJA1105_H */ -- cgit v1.2.3 From a68578c20a9667463ee3000402b21644ea62d753 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 4 Jan 2020 02:37:10 +0200 Subject: net: dsa: Make deferred_xmit private to sja1105 There are 3 things that are wrong with the DSA deferred xmit mechanism: 1. Its introduction has made the DSA hotpath ever so slightly more inefficient for everybody, since DSA_SKB_CB(skb)->deferred_xmit needs to be initialized to false for every transmitted frame, in order to figure out whether the driver requested deferral or not (a very rare occasion, rare even for the only driver that does use this mechanism: sja1105). That was necessary to avoid kfree_skb from freeing the skb. 2. Because L2 PTP is a link-local protocol like STP, it requires management routes and deferred xmit with this switch. But as opposed to STP, the deferred work mechanism needs to schedule the packet rather quickly for the TX timstamp to be collected in time and sent to user space. But there is no provision for controlling the scheduling priority of this deferred xmit workqueue. Too bad this is a rather specific requirement for a feature that nobody else uses (more below). 3. Perhaps most importantly, it makes the DSA core adhere a bit too much to the NXP company-wide policy "Innovate Where It Doesn't Matter". The sja1105 is probably the only DSA switch that requires some frames sent from the CPU to be routed to the slave port via an out-of-band configuration (register write) rather than in-band (DSA tag). And there are indeed very good reasons to not want to do that: if that out-of-band register is at the other end of a slow bus such as SPI, then you limit that Ethernet flow's throughput to effectively the throughput of the SPI bus. So hardware vendors should definitely not be encouraged to design this way. We do _not_ want more widespread use of this mechanism. Luckily we have a solution for each of the 3 issues: For 1, we can just remove that variable in the skb->cb and counteract the effect of kfree_skb with skb_get, much to the same effect. The advantage, of course, being that anybody who doesn't use deferred xmit doesn't need to do any extra operation in the hotpath. For 2, we can create a kernel thread for each port's deferred xmit work. If the user switch ports are named swp0, swp1, swp2, the kernel threads will be named swp0_xmit, swp1_xmit, swp2_xmit (there appears to be a 15 character length limit on kernel thread names). With this, the user can change the scheduling priority with chrt $(pidof swp2_xmit). For 3, we can actually move the entire implementation to the sja1105 driver. So this patch deletes the generic implementation from the DSA core and adds a new one, more adequate to the requirements of PTP TX timestamping, in sja1105_main.c. Suggested-by: Florian Fainelli Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 317e05b2584b..fa5735c353cd 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -53,6 +53,9 @@ struct sja1105_skb_cb { ((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb)) struct sja1105_port { + struct kthread_worker *xmit_worker; + struct kthread_work xmit_work; + struct sk_buff_head xmit_queue; struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; -- cgit v1.2.3 From 699a8c7c4bd376aee4808e6272188319e900c8af Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Thu, 3 Oct 2019 10:28:09 +0200 Subject: leds: Add of_led_get() and led_put() This patch adds basic support for a kernel driver to get a LED device. This will be used by the led-backlight driver. Only OF version is implemented for now, and the behavior is similar to PWM's of_pwm_get() and pwm_put(). Signed-off-by: Tomi Valkeinen Signed-off-by: Jean-Jacques Hiblot Acked-by: Pavel Machek Signed-off-by: Pavel Machek --- include/linux/leds.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 242258f7d837..dcfb6a325866 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -20,6 +20,7 @@ struct device; struct led_pattern; +struct device_node; /* * LED Core */ @@ -196,6 +197,9 @@ void devm_led_classdev_unregister(struct device *parent, void led_classdev_suspend(struct led_classdev *led_cdev); void led_classdev_resume(struct led_classdev *led_cdev); +extern struct led_classdev *of_led_get(struct device_node *np, int index); +extern void led_put(struct led_classdev *led_cdev); + /** * led_blink_set - set blinking with software fallback * @led_cdev: the LED to start blinking -- cgit v1.2.3 From e389240ad99292d52a4f8ff30f16830dc9c63779 Mon Sep 17 00:00:00 2001 From: Jean-Jacques Hiblot Date: Thu, 3 Oct 2019 10:28:10 +0200 Subject: leds: Add managed API to get a LED from a device driver If the LED is acquired by a consumer device with devm_led_get(), it is automatically released when the device is detached. Signed-off-by: Jean-Jacques Hiblot Acked-by: Pavel Machek Signed-off-by: Pavel Machek --- include/linux/leds.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index dcfb6a325866..75353e5f9d13 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -199,6 +199,8 @@ void led_classdev_resume(struct led_classdev *led_cdev); extern struct led_classdev *of_led_get(struct device_node *np, int index); extern void led_put(struct led_classdev *led_cdev); +struct led_classdev *__must_check devm_of_led_get(struct device *dev, + int index); /** * led_blink_set - set blinking with software fallback -- cgit v1.2.3 From 6c930994503d9b5bd34b1329427dd7d3d6d37cd4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 6 Jan 2020 03:34:09 +0200 Subject: mii: Add helpers for parsing SGMII auto-negotiation Typically a MAC PCS auto-configures itself after it receives the negotiated copper-side link settings from the PHY, but some MAC devices are more special and need manual interpretation of the SGMII AN result. In other cases, the PCS exposes the entire tx_config_reg base page as it is transmitted on the wire during auto-negotiation, so it makes sense to be able to decode the equivalent lp_advertised bit mask from the raw u16 (of course, "lp" considering the PCS to be the local PHY). Therefore, add the bit definitions for the SGMII registers 4 and 5 (local device ability, link partner ability), as well as a link_mode conversion helper that can be used to feed the AN results into phy_resolve_aneg_linkmode. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/mii.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 4ce8901a1af6..18c6208f56fc 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -372,6 +372,56 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) return result | mii_adv_to_ethtool_adv_x(lpa); } +/** + * mii_lpa_mod_linkmode_adv_sgmii + * @lp_advertising: pointer to destination link mode. + * @lpa: value of the MII_LPA register + * + * A small helper function that translates MII_LPA bits to + * linkmode advertisement settings for SGMII. + * Leaves other bits unchanged. + */ +static inline void +mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) +{ + u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising, + speed_duplex == LPA_SGMII_1000HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising, + speed_duplex == LPA_SGMII_1000FULL); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising, + speed_duplex == LPA_SGMII_100HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising, + speed_duplex == LPA_SGMII_100FULL); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising, + speed_duplex == LPA_SGMII_10HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising, + speed_duplex == LPA_SGMII_10FULL); +} + +/** + * mii_lpa_to_linkmode_adv_sgmii + * @advertising: pointer to destination link mode. + * @lpa: value of the MII_LPA register + * + * A small helper function that translates MII_ADVERTISE bits + * to linkmode advertisement settings when in SGMII mode. + * Clears the old value of advertising. + */ +static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising, + u32 lpa) +{ + linkmode_zero(lp_advertising); + + mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa); +} + /** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. -- cgit v1.2.3 From 1511ed0a0167f523a84b4e727372a5d2ce1b6c2f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 6 Jan 2020 03:34:11 +0200 Subject: net: phylink: add support for polling MAC PCS Some MAC PCS blocks are unable to provide interrupts when their status changes. As we already have support in phylink for polling status, use this to provide a hook for MACs to enable polling mode. The patch idea was picked up from Russell King's suggestion on the macb phylink patch thread here [0] but the implementation was changed. Instead of introducing a new phylink_start_poll() function, which would make the implementation cumbersome for common PHYLINK implementations for multiple types of devices, like DSA, just add a boolean property to the phylink_config structure, which is just as backwards-compatible. https://lkml.org/lkml/2019/12/16/603 Suggested-by: Russell King Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/phylink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index fed5488e3c75..523209e70947 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -63,10 +63,12 @@ enum phylink_op_type { * struct phylink_config - PHYLINK configuration structure * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance + * @pcs_poll: MAC PCS cannot provide link change interrupt */ struct phylink_config { struct device *dev; enum phylink_op_type type; + bool pcs_poll; }; /** -- cgit v1.2.3 From 6517798dd3432a0002109809bf74e4fcf9bb0c7d Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Mon, 6 Jan 2020 03:34:13 +0200 Subject: enetc: Make MDIO accessors more generic and export to include/linux/fsl Within the LS1028A SoC, the register map for the ENETC MDIO controller is instantiated a few times: for the central (external) MDIO controller, for the internal bus of each standalone ENETC port, and for the internal bus of the Felix switch. Refactoring is needed to support multiple MDIO buses from multiple drivers. The enetc_hw structure is made an opaque type and a smaller enetc_mdio_priv is created. 'mdio_base' - MDIO registers base address - is being parameterized, to be able to work with different MDIO register bases. The ENETC MDIO bus operations are exported from the fsl-enetc-mdio kernel object, the same that registers the central MDIO controller (the dedicated PF). The ENETC main driver has been changed to select it, and use its exported helpers to further register its private MDIO bus. The DSA Felix driver will do the same. Signed-off-by: Claudiu Manoil Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/fsl/enetc_mdio.h | 55 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 include/linux/fsl/enetc_mdio.h (limited to 'include/linux') diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h new file mode 100644 index 000000000000..4875dd38af7e --- /dev/null +++ b/include/linux/fsl/enetc_mdio.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2019 NXP */ + +#ifndef _FSL_ENETC_MDIO_H_ +#define _FSL_ENETC_MDIO_H_ + +#include + +/* PCS registers */ +#define ENETC_PCS_LINK_TIMER1 0x12 +#define ENETC_PCS_LINK_TIMER1_VAL 0x06a0 +#define ENETC_PCS_LINK_TIMER2 0x13 +#define ENETC_PCS_LINK_TIMER2_VAL 0x0003 +#define ENETC_PCS_IF_MODE 0x14 +#define ENETC_PCS_IF_MODE_SGMII_EN BIT(0) +#define ENETC_PCS_IF_MODE_USE_SGMII_AN BIT(1) +#define ENETC_PCS_IF_MODE_SGMII_SPEED(x) (((x) << 2) & GENMASK(3, 2)) + +/* Not a mistake, the SerDes PLL needs to be set at 3.125 GHz by Reset + * Configuration Word (RCW, outside Linux control) for 2.5G SGMII mode. The PCS + * still thinks it's at gigabit. + */ +enum enetc_pcs_speed { + ENETC_PCS_SPEED_10 = 0, + ENETC_PCS_SPEED_100 = 1, + ENETC_PCS_SPEED_1000 = 2, + ENETC_PCS_SPEED_2500 = 2, +}; + +struct enetc_hw; + +struct enetc_mdio_priv { + struct enetc_hw *hw; + int mdio_base; +}; + +#if IS_REACHABLE(CONFIG_FSL_ENETC_MDIO) + +int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum); +int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value); +struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs); + +#else + +static inline int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +{ return -EINVAL; } +static inline int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, + u16 value) +{ return -EINVAL; } +struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) +{ return ERR_PTR(-EINVAL); } + +#endif + +#endif -- cgit v1.2.3 From a6a0bc7ca993e30e832314f5a8bd62a802f35ce9 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 3 Jan 2020 23:08:25 +0100 Subject: firmware: scm: Add stubs for OCMEM and restore_sec_cfg_available Add few more stubs (for OCMEM-related functions and qcom_scm_restore_sec_cfg_available()) in case of !CONFIG_QCOM_SCM. These are actually not necessary for builds but provide them for completeness. Reviewed-by: Brian Masney Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200103220825.28710-1-krzk@kernel.org Signed-off-by: Bjorn Andersson --- include/linux/qcom_scm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index d05ddac9a57e..2c1d20312ce0 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -105,6 +105,11 @@ static inline bool qcom_scm_is_available(void) { return false; } static inline bool qcom_scm_hdcp_available(void) { return false; } static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp) { return -ENODEV; } +static inline bool qcom_scm_ocmem_lock_available(void) { return false; } +static inline int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size, u32 mode) { return -ENODEV; } +static inline int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size) { return -ENODEV; } static inline bool qcom_scm_pas_supported(u32 peripheral) { return false; } static inline int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size) { return -ENODEV; } @@ -121,6 +126,7 @@ static inline void qcom_scm_cpu_power_down(u32 flags) {} static inline u32 qcom_scm_get_version(void) { return 0; } static inline u32 qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; } +static inline bool qcom_scm_restore_sec_cfg_available(void) { return false; } static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return -ENODEV; } 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; } -- cgit v1.2.3 From 4bdc0d676a643140bdf17dbf7eafedee3d496a3c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 6 Jan 2020 09:43:50 +0100 Subject: remove ioremap_nocache and devm_ioremap_nocache ioremap has provided non-cached semantics by default since the Linux 2.6 days, so remove the additional ioremap_nocache interface. Signed-off-by: Christoph Hellwig Acked-by: Arnd Bergmann --- include/linux/io.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index a59834bc0a11..b1c44bb4b2d7 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -66,8 +66,6 @@ void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, resource_size_t size); void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, resource_size_t size); -void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset, - resource_size_t size); void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset, resource_size_t size); void devm_iounmap(struct device *dev, void __iomem *addr); @@ -87,7 +85,7 @@ void *__devm_memremap_pages(struct device *dev, struct resource *res); * Posting") mandate non-posted configuration transactions. There is * no ioremap API in the kernel that can guarantee non-posted write * semantics across arches so provide a default implementation for - * mapping PCI config space that defaults to ioremap_nocache(); arches + * mapping PCI config space that defaults to ioremap(); arches * should override it if they have memory mapping implementations that * guarantee non-posted writes semantics to make the memory mapping * compliant with the PCI specification. @@ -97,7 +95,7 @@ void *__devm_memremap_pages(struct device *dev, struct resource *res); static inline void __iomem *pci_remap_cfgspace(phys_addr_t offset, size_t size) { - return ioremap_nocache(offset, size); + return ioremap(offset, size); } #endif #endif -- cgit v1.2.3 From 243145bc4336684c69f95de0a303b31f2e5bf264 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 6 Jan 2020 08:58:23 -0800 Subject: fs: Fix page_mkwrite off-by-one errors The check in block_page_mkwrite that is meant to determine whether an offset is within the inode size is off by one. This bug has been copied into iomap_page_mkwrite and several filesystems (ubifs, ext4, f2fs, ceph). Fix that by introducing a new page_mkwrite_check_truncate helper that checks for truncate and computes the bytes in the page up to EOF. Use the helper in iomap. NOTE from Darrick: The original patch fixed a number of filesystems, but then there were merge conflicts with the f2fs for-next tree; a subsequent re-submission of the patch had different btrfs changes with no explanation; and Christoph complained that each per-fs fix should be a separate patch. In my view that's too much risk to take on, so I decided to drop all the hunks except for iomap, since I've actually QA'd XFS. Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong [darrick: drop everything but the iomap parts] Signed-off-by: Darrick J. Wong --- include/linux/pagemap.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 37a4d9e32cd3..ccb14b6a16b5 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -636,4 +636,32 @@ static inline unsigned long dir_pages(struct inode *inode) PAGE_SHIFT; } +/** + * page_mkwrite_check_truncate - check if page was truncated + * @page: the page to check + * @inode: the inode to check the page against + * + * Returns the number of bytes in the page up to EOF, + * or -EFAULT if the page was truncated. + */ +static inline int page_mkwrite_check_truncate(struct page *page, + struct inode *inode) +{ + loff_t size = i_size_read(inode); + pgoff_t index = size >> PAGE_SHIFT; + int offset = offset_in_page(size); + + if (page->mapping != inode->i_mapping) + return -EFAULT; + + /* page is wholly inside EOF */ + if (page->index < index) + return PAGE_SIZE; + /* page is wholly past EOF */ + if (page->index > index || !offset) + return -EFAULT; + /* page is partially inside EOF */ + return offset; +} + #endif /* _LINUX_PAGEMAP_H */ -- cgit v1.2.3 From 8b41fc4454e36fbfdbb23f940d023d4dece2de29 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 19 Dec 2019 17:33:29 +0900 Subject: kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf Commit bc081dd6e9f6 ("kbuild: generate modules.builtin") added infrastructure to generate modules.builtin, the list of all builtin modules. Basically, it works like this: - Kconfig generates include/config/tristate.conf, the list of tristate CONFIG options with a value in a capital letter. - scripts/Makefile.modbuiltin makes Kbuild descend into directories to collect the information of builtin modules. I am not a big fan of it because Kbuild ends up with traversing the source tree twice. I am not sure how perfectly it should work, but this approach cannot avoid false positives; even if the relevant CONFIG option is tristate, some Makefiles forces obj-m to obj-y. Some examples are: arch/powerpc/platforms/powermac/Makefile: obj-$(CONFIG_NVRAM:m=y) += nvram.o net/ipv6/Makefile: obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o net/netlabel/Makefile: obj-$(subst m,y,$(CONFIG_IPV6)) += netlabel_calipso.o Nobody has complained about (or noticed) it, so it is probably fine to have false positives in modules.builtin. This commit simplifies the implementation. Let's exploit the fact that every module has MODULE_LICENSE(). (modpost shows a warning if MODULE_LICENSE is missing. If so, 0-day bot would already have blocked such a module.) I added MODULE_FILE to . When the code is being compiled as builtin, it will be filled with the file path of the module, and collected into modules.builtin.info. Then, scripts/link-vmlinux.sh extracts the list of builtin modules out of it. This new approach fixes the false-positives above, but adds another type of false-positives; non-modular code may have MODULE_LICENSE() by mistake. This is not a big deal, it is just the code is always orphan. We can clean it up if we like. You can see cleanup examples by: $ git log --grep='make.* explicitly non-modular' To sum up, this commits deletes lots of code, but still produces almost equivalent results. Please note it does not increase the vmlinux size at all. As you can see in include/asm-generic/vmlinux.lds.h, the .modinfo section is discarded in the link stage. Signed-off-by: Masahiro Yamada --- include/linux/module.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index bd165ba68617..6877b3b191d0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -169,6 +169,16 @@ extern void cleanup_module(void); */ #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) +/* + * MODULE_FILE is used for generating modules.builtin + * So, make it no-op when this is being built as a module + */ +#ifdef MODULE +#define MODULE_FILE +#else +#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE); +#endif + /* * The following license idents are currently accepted as indicating free * software modules @@ -213,7 +223,7 @@ extern void cleanup_module(void); * 2. So the community can ignore bug reports including proprietary modules * 3. So vendors can do likewise based on their own policies */ -#define MODULE_LICENSE(_license) MODULE_INFO(license, _license) +#define MODULE_LICENSE(_license) MODULE_FILE MODULE_INFO(license, _license) /* * Author(s), use "Name " or just "Name", for multiple -- cgit v1.2.3 From 5adcb8b18611c69577fd0f35337ab8d2573712fa Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 4 Jan 2020 16:21:06 +0100 Subject: net: ethernet: sxgbe: Rename Samsung to lowercase Fix up inconsistent usage of upper and lowercase letters in "Samsung" name. "SAMSUNG" is not an abbreviation but a regular trademarked name. Therefore it should be written with lowercase letters starting with capital letter. Although advertisement materials usually use uppercase "SAMSUNG", the lowercase version is used in all legal aspects (e.g. on Wikipedia and in privacy/legal statements on https://www.samsung.com/semiconductor/privacy-global/). Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/linux/sxgbe_platform.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h index 85ec745767bd..966146f7267a 100644 --- a/include/linux/sxgbe_platform.h +++ b/include/linux/sxgbe_platform.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * 10G controller driver for Samsung EXYNOS SoCs + * 10G controller driver for Samsung Exynos SoCs * * Copyright (C) 2013 Samsung Electronics Co., Ltd. * http://www.samsung.com -- cgit v1.2.3 From 58f0c4ba565d91bb76e8ac2a809e99bfe75b4935 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:18 -0700 Subject: clk: fixed-rate: Add clk flags for parent accuracy Some clk providers want to use the accuracy of the parent clk and use the fixed rate basic type clk to do that. This requires getting the parent clk and extracting the accuracy before registering the fixed rate clk. Let's add a flag for this and update the clk_ops to support this. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-8-sboyd@kernel.org --- include/linux/clk-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index bb0c4c916a16..1a90fa46f550 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -323,6 +323,10 @@ struct clk_hw { * @fixed_rate: constant frequency of clock * @fixed_accuracy: constant accuracy of clock in ppb (parts per billion) * @flags: hardware specific flags + * + * Flags: + * * CLK_FIXED_RATE_PARENT_ACCURACY - Use the accuracy of the parent clk + * instead of what's set in @fixed_accuracy. */ struct clk_fixed_rate { struct clk_hw hw; @@ -331,6 +335,8 @@ struct clk_fixed_rate { unsigned long flags; }; +#define CLK_FIXED_RATE_PARENT_ACCURACY BIT(0) + extern const struct clk_ops clk_fixed_rate_ops; struct clk_hw *__clk_hw_register_fixed_rate(struct device *dev, struct device_node *np, const char *name, -- cgit v1.2.3 From 1f1bb96d3a1ac8c02878a437927a00840cc62e70 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:19 -0700 Subject: clk: fixed-rate: Document that accuracy isn't a rate This kernel-doc talks about a rate for the accuracy. That's wrong. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-9-sboyd@kernel.org --- include/linux/clk-provider.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1a90fa46f550..89ca2c42763b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -394,7 +394,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, * @parent_name: name of clock's parent * @flags: framework-specific flags * @fixed_rate: non-adjustable clock rate - * @fixed_accuracy: non-adjustable clock rate + * @fixed_accuracy: non-adjustable clock accuracy */ #define clk_hw_register_fixed_rate_with_accuracy(dev, name, parent_name, \ flags, fixed_rate, \ -- cgit v1.2.3 From 9611b3aacc1c1af7cb96d35ca5f1e55fdd44f697 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:21 -0700 Subject: clk: mux: Add support for specifying parents via DT/pointers After commit fc0c209c147f ("clk: Allow parents to be specified without string names") we can use DT or direct clk_hw pointers to specify parents. Create a generic function that shouldn't be used very often to encode the multitude of ways of registering a mux clk with different parent information. Then add a bunch of wrapper macros that only pass down what needs to be passed down to the generic function to support this with less arguments. Note: the msm drm driver passes an anonymous array through the macro which seems to confuse my compiler. Adding a parenthesis around the whole thing at the call site seems to fix it but it must be wrong. Maybe it's better to split this patch and pick out the array bits there? Cc: Rob Clark Cc: Sean Paul Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-11-sboyd@kernel.org --- include/linux/clk-provider.h | 56 ++++++++++++++++++++++++++++++-------------- 1 file changed, 38 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 89ca2c42763b..cffa8dfaebf6 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -645,28 +645,48 @@ struct clk_mux { extern const struct clk_ops clk_mux_ops; extern const struct clk_ops clk_mux_ro_ops; -struct clk *clk_register_mux(struct device *dev, const char *name, - const char * const *parent_names, u8 num_parents, - unsigned long flags, - void __iomem *reg, u8 shift, u8 width, - u8 clk_mux_flags, spinlock_t *lock); -struct clk_hw *clk_hw_register_mux(struct device *dev, const char *name, - const char * const *parent_names, u8 num_parents, - unsigned long flags, - void __iomem *reg, u8 shift, u8 width, - u8 clk_mux_flags, spinlock_t *lock); - -struct clk *clk_register_mux_table(struct device *dev, const char *name, - const char * const *parent_names, u8 num_parents, - unsigned long flags, - void __iomem *reg, u8 shift, u32 mask, +struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np, + const char *name, u8 num_parents, + const char * const *parent_names, + const struct clk_hw **parent_hws, + const struct clk_parent_data *parent_data, + unsigned long flags, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, u32 *table, spinlock_t *lock); -struct clk_hw *clk_hw_register_mux_table(struct device *dev, const char *name, +struct clk *clk_register_mux_table(struct device *dev, const char *name, const char * const *parent_names, u8 num_parents, - unsigned long flags, - void __iomem *reg, u8 shift, u32 mask, + unsigned long flags, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, u32 *table, spinlock_t *lock); +#define clk_register_mux(dev, name, parent_names, num_parents, flags, reg, \ + shift, width, clk_mux_flags, lock) \ + clk_register_mux_table((dev), (name), (parent_names), (num_parents), \ + (flags), (reg), (shift), BIT((width)) - 1, \ + (clk_mux_flags), NULL, (lock)) +#define clk_hw_register_mux_table(dev, name, parent_names, num_parents, \ + flags, reg, shift, mask, clk_mux_flags, \ + table, lock) \ + __clk_hw_register_mux((dev), NULL, (name), (num_parents), \ + (parent_names), NULL, NULL, (flags), (reg), \ + (shift), (mask), (clk_mux_flags), (table), \ + (lock)) +#define clk_hw_register_mux(dev, name, parent_names, num_parents, flags, reg, \ + shift, width, clk_mux_flags, lock) \ + __clk_hw_register_mux((dev), NULL, (name), (num_parents), \ + (parent_names), NULL, NULL, (flags), (reg), \ + (shift), BIT((width)) - 1, (clk_mux_flags), \ + NULL, (lock)) +#define clk_hw_register_mux_hws(dev, name, parent_hws, num_parents, flags, \ + reg, shift, width, clk_mux_flags, lock) \ + __clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL, \ + (parent_hws), NULL, (flags), (reg), (shift), \ + BIT((width)) - 1, (clk_mux_flags), NULL, (lock)) +#define clk_hw_register_mux_parent_data(dev, name, parent_data, num_parents, \ + flags, reg, shift, width, \ + clk_mux_flags, lock) \ + __clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL, NULL, \ + (parent_data), (flags), (reg), (shift), \ + BIT((width)) - 1, (clk_mux_flags), NULL, (lock)) + int clk_mux_val_to_index(struct clk_hw *hw, u32 *table, unsigned int flags, unsigned int val); unsigned int clk_mux_index_to_val(u32 *table, unsigned int flags, u8 index); -- cgit v1.2.3 From 194efb6e2667cc226fa92a6a4ab5d2298b5b85d9 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:22 -0700 Subject: clk: gate: Add support for specifying parents via DT/pointers After commit fc0c209c147f ("clk: Allow parents to be specified without string names") we can use DT or direct clk_hw pointers to specify parents. Create a generic function that shouldn't be used very often to encode the multitude of ways of registering a gate clk with different parent information. Then add a bunch of wrapper macros that only pass down what needs to be passed down to the generic function to support this with less arguments. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-12-sboyd@kernel.org --- include/linux/clk-provider.h | 59 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 56 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index cffa8dfaebf6..152aeb5aa006 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -476,14 +476,67 @@ struct clk_gate { #define CLK_GATE_BIG_ENDIAN BIT(2) extern const struct clk_ops clk_gate_ops; -struct clk *clk_register_gate(struct device *dev, const char *name, - const char *parent_name, unsigned long flags, +struct clk_hw *__clk_hw_register_gate(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, + unsigned long flags, void __iomem *reg, u8 bit_idx, u8 clk_gate_flags, spinlock_t *lock); -struct clk_hw *clk_hw_register_gate(struct device *dev, const char *name, +struct clk *clk_register_gate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 bit_idx, u8 clk_gate_flags, spinlock_t *lock); +/** + * clk_hw_register_gate - register a gate clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of this clock's parent + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define clk_hw_register_gate(dev, name, parent_name, flags, reg, bit_idx, \ + clk_gate_flags, lock) \ + __clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) +/** + * clk_hw_register_gate_parent_hw - register a gate clock with the clock + * framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_hw: pointer to parent clk + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define clk_hw_register_gate_parent_hw(dev, name, parent_name, flags, reg, \ + bit_idx, clk_gate_flags, lock) \ + __clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) +/** + * clk_hw_register_gate_parent_data - register a gate clock with the clock + * framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define clk_hw_register_gate_parent_data(dev, name, parent_name, flags, reg, \ + bit_idx, clk_gate_flags, lock) \ + __clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); -- cgit v1.2.3 From 64c76b31774db5a0c0ce8df13aef618912136e32 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Thu, 26 Dec 2019 20:12:24 +0100 Subject: clk: clarify that clk_set_rate() does updates from top to bottom clk_set_rate() currently starts updating the rate for a clock at the top-most affected clock and then walks down the tree to update the bottom-most affected clock last. This behavior is important for protected clocks where we can switch between multiple parents to achieve the same output. An example for this is the mali clock tree on Amlogic SoCs: mali_0_mux (must not change when enabled) mali_0_div (must not change when enabled) mali_0 (gate) mali_1_mux (must not change when enabled) mali_1_div (must not change when enabled) mali_1 (gate) The final output can either use mali_0_gate or mali_1. To change the final output we must switch to the "inactive" tree. Assuming mali_0 is active, then we need to prepare mali_1 with the new desired rate and finally switch the output to the mali_1 tree. This process will then protect the mali_1 tree and at the same time unprotect the mali_0 tree. The next call to clk_set_rate() will then switch from the mali_1 tree back to mali_0. Acked-by: Stephen Boyd Signed-off-by: Martin Blumenstingl Signed-off-by: Jerome Brunet --- include/linux/clk.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 18b7b95a8253..7fd6a1febcf4 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -627,6 +627,9 @@ long clk_round_rate(struct clk *clk, unsigned long rate); * @clk: clock source * @rate: desired clock rate in Hz * + * Updating the rate starts at the top-most affected clock and then + * walks the tree down to the bottom-most clock that needs updating. + * * Returns success (0) or negative errno. */ int clk_set_rate(struct clk *clk, unsigned long rate); -- cgit v1.2.3 From 06863620edfeadbe9e0ea5eb01dd94ce07f37549 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 24 Dec 2019 13:06:59 +0100 Subject: gpiolib: convert the type of hwnum to unsigned int in gpiochip_get_desc() gpiochip_get_desc() takes a u16 hwnum, but it turns out most users don't respect that and usually pass an unsigned int. Since implicit casting to a smaller type is dangerous - let's change the type of hwnum to unsigned int in gpiochip_get_desc() and in gpiochip_request_own_desc() where the size of hwnum is not respected either and who's a user of the former. This is safe as we then check the hwnum against the number of lines before proceeding in gpiochip_get_desc(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij --- include/linux/gpio/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index e2480ef94c55..4f032de10bae 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -715,7 +715,8 @@ gpiochip_remove_pin_ranges(struct gpio_chip *chip) #endif /* CONFIG_PINCTRL */ -struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *chip, u16 hwnum, +struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *chip, + unsigned int hwnum, const char *label, enum gpio_lookup_flags lflags, enum gpiod_flags dflags); -- cgit v1.2.3 From 048ae7e8b5dbee053b208fd93d68bc2125fed03c Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Sat, 14 Dec 2019 12:49:13 +0100 Subject: fmc: remove left-over ipmi-fru.h after fmc deletion Commit 6a80b30086b8 ("fmc: Delete the FMC subsystem") from Linus Walleij deleted the obsolete FMC subsystem, but missed the MAINTAINERS entry and include/linux/ipmi-fru.h mentioned in the MAINTAINERS entry. Later, commit d5d4aa1ec198 ("MAINTAINERS: Remove FMC subsystem") from Denis Efremov cleaned up the MAINTAINERS entry, but actually also missed that include/linux/ipmi-fru.h should also be deleted while deleting its reference in MAINTAINERS. So, deleting include/linux/ipmi-fru.h slipped through the previous clean-ups. As there is no further use for include/linux/ipmi-fru.h, finally delete include/linux/ipmi-fru.h for good now. Fixes: d5d4aa1ec198 ("MAINTAINERS: Remove FMC subsystem") Fixes: 6a80b30086b8 ("fmc: Delete the FMC subsystem") Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20191214114913.8610-1-lukas.bulwahn@gmail.com Acked-by: Federico Vaga Signed-off-by: Linus Walleij --- include/linux/ipmi-fru.h | 134 ----------------------------------------------- 1 file changed, 134 deletions(-) delete mode 100644 include/linux/ipmi-fru.h (limited to 'include/linux') diff --git a/include/linux/ipmi-fru.h b/include/linux/ipmi-fru.h deleted file mode 100644 index 05c9422624c6..000000000000 --- a/include/linux/ipmi-fru.h +++ /dev/null @@ -1,134 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright (C) 2012 CERN (www.cern.ch) - * Author: Alessandro Rubini - * - * This work is part of the White Rabbit project, a research effort led - * by CERN, the European Institute for Nuclear Research. - */ -#ifndef __LINUX_IPMI_FRU_H__ -#define __LINUX_IPMI_FRU_H__ -#ifdef __KERNEL__ -# include -# include -#else -# include -# include -#endif - -/* - * These structures match the unaligned crap we have in FRU1011.pdf - * (http://download.intel.com/design/servers/ipmi/FRU1011.pdf) - */ - -/* chapter 8, page 5 */ -struct fru_common_header { - uint8_t format; /* 0x01 */ - uint8_t internal_use_off; /* multiple of 8 bytes */ - uint8_t chassis_info_off; /* multiple of 8 bytes */ - uint8_t board_area_off; /* multiple of 8 bytes */ - uint8_t product_area_off; /* multiple of 8 bytes */ - uint8_t multirecord_off; /* multiple of 8 bytes */ - uint8_t pad; /* must be 0 */ - uint8_t checksum; /* sum modulo 256 must be 0 */ -}; - -/* chapter 9, page 5 -- internal_use: not used by us */ - -/* chapter 10, page 6 -- chassis info: not used by us */ - -/* chapter 13, page 9 -- used by board_info_area below */ -struct fru_type_length { - uint8_t type_length; - uint8_t data[0]; -}; - -/* chapter 11, page 7 */ -struct fru_board_info_area { - uint8_t format; /* 0x01 */ - uint8_t area_len; /* multiple of 8 bytes */ - uint8_t language; /* I hope it's 0 */ - uint8_t mfg_date[3]; /* LSB, minutes since 1996-01-01 */ - struct fru_type_length tl[0]; /* type-length stuff follows */ - - /* - * the TL there are in order: - * Board Manufacturer - * Board Product Name - * Board Serial Number - * Board Part Number - * FRU File ID (may be null) - * more manufacturer-specific stuff - * 0xc1 as a terminator - * 0x00 pad to a multiple of 8 bytes - 1 - * checksum (sum of all stuff module 256 must be zero) - */ -}; - -enum fru_type { - FRU_TYPE_BINARY = 0x00, - FRU_TYPE_BCDPLUS = 0x40, - FRU_TYPE_ASCII6 = 0x80, - FRU_TYPE_ASCII = 0xc0, /* not ascii: depends on language */ -}; - -/* - * some helpers - */ -static inline struct fru_board_info_area *fru_get_board_area( - const struct fru_common_header *header) -{ - /* we know for sure that the header is 8 bytes in size */ - return (struct fru_board_info_area *)(header + header->board_area_off); -} - -static inline int fru_type(struct fru_type_length *tl) -{ - return tl->type_length & 0xc0; -} - -static inline int fru_length(struct fru_type_length *tl) -{ - return (tl->type_length & 0x3f) + 1; /* len of whole record */ -} - -/* assume ascii-latin1 encoding */ -static inline int fru_strlen(struct fru_type_length *tl) -{ - return fru_length(tl) - 1; -} - -static inline char *fru_strcpy(char *dest, struct fru_type_length *tl) -{ - int len = fru_strlen(tl); - memcpy(dest, tl->data, len); - dest[len] = '\0'; - return dest; -} - -static inline struct fru_type_length *fru_next_tl(struct fru_type_length *tl) -{ - return tl + fru_length(tl); -} - -static inline int fru_is_eof(struct fru_type_length *tl) -{ - return tl->type_length == 0xc1; -} - -/* - * External functions defined in fru-parse.c. - */ -extern int fru_header_cksum_ok(struct fru_common_header *header); -extern int fru_bia_cksum_ok(struct fru_board_info_area *bia); - -/* All these 4 return allocated strings by calling fru_alloc() */ -extern char *fru_get_board_manufacturer(struct fru_common_header *header); -extern char *fru_get_product_name(struct fru_common_header *header); -extern char *fru_get_serial_number(struct fru_common_header *header); -extern char *fru_get_part_number(struct fru_common_header *header); - -/* This must be defined by the caller of the above functions */ -extern void *fru_alloc(size_t size); - -#endif /* __LINUX_IMPI_FRU_H__ */ -- cgit v1.2.3 From ff3dc6521f78132eaaf62a842c3ece9060dcde26 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 2 Jan 2020 08:18:03 +0800 Subject: iommu/vt-d: Fix CPU and IOMMU SVM feature matching checks Shared Virtual Memory(SVM) is based on a collective set of hardware features detected at runtime. There are requirements for matching CPU and IOMMU capabilities. The current code checks CPU and IOMMU feature set for SVM support but the result is never stored nor used. Therefore, SVM can still be used even when these checks failed. The consequences can be: 1. CPU uses 5-level paging mode for virtual address of 57 bits, but IOMMU can only support 4-level paging mode with 48 bits address for DMA. 2. 1GB page size is used by CPU but IOMMU does not support it. VT-d unrecoverable faults may be generated. The best solution to fix these problems is to prevent them in the first place. This patch consolidates code for checking PASID, CPU vs. IOMMU paging mode compatibility, as well as provides specific error messages for each failed checks. On sane hardware configurations, these error message shall never appear in kernel log. Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 6d8bf4bdf240..aaece25c055f 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -435,6 +435,7 @@ enum { #define VTD_FLAG_TRANS_PRE_ENABLED (1 << 0) #define VTD_FLAG_IRQ_REMAP_PRE_ENABLED (1 << 1) +#define VTD_FLAG_SVM_CAPABLE (1 << 2) extern int intel_iommu_sm; @@ -658,7 +659,7 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); #ifdef CONFIG_INTEL_IOMMU_SVM -int intel_svm_init(struct intel_iommu *iommu); +extern void intel_svm_check(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); @@ -686,6 +687,8 @@ struct intel_svm { }; extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); +#else +static inline void intel_svm_check(struct intel_iommu *iommu) {} #endif #ifdef CONFIG_INTEL_IOMMU_DEBUGFS -- cgit v1.2.3 From ddf09b6d43ece8e4d5591e4957e89c4fe7714792 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 2 Jan 2020 08:18:17 +0800 Subject: iommu/vt-d: Setup pasid entries for iova over first level Intel VT-d in scalable mode supports two types of page tables for IOVA translation: first level and second level. The IOMMU driver can choose one from both for IOVA translation according to the use case. This sets up the pasid entry if a domain is selected to use the first-level page table for iova translation. Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index aaece25c055f..454c69712131 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -34,10 +34,13 @@ #define VTD_STRIDE_SHIFT (9) #define VTD_STRIDE_MASK (((u64)-1) << VTD_STRIDE_SHIFT) -#define DMA_PTE_READ (1) -#define DMA_PTE_WRITE (2) -#define DMA_PTE_LARGE_PAGE (1 << 7) -#define DMA_PTE_SNP (1 << 11) +#define DMA_PTE_READ BIT_ULL(0) +#define DMA_PTE_WRITE BIT_ULL(1) +#define DMA_PTE_LARGE_PAGE BIT_ULL(7) +#define DMA_PTE_SNP BIT_ULL(11) + +#define DMA_FL_PTE_PRESENT BIT_ULL(0) +#define DMA_FL_PTE_XD BIT_ULL(63) #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 @@ -610,10 +613,11 @@ static inline void dma_clear_pte(struct dma_pte *pte) static inline u64 dma_pte_addr(struct dma_pte *pte) { #ifdef CONFIG_64BIT - return pte->val & VTD_PAGE_MASK; + return pte->val & VTD_PAGE_MASK & (~DMA_FL_PTE_XD); #else /* Must have a full atomic 64-bit read */ - return __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK; + return __cmpxchg64(&pte->val, 0ULL, 0ULL) & + VTD_PAGE_MASK & (~DMA_FL_PTE_XD); #endif } -- cgit v1.2.3 From 33cd6e642d6a76c1d338ce25cba5fd79a5029011 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 2 Jan 2020 08:18:18 +0800 Subject: iommu/vt-d: Flush PASID-based iotlb for iova over first level When software has changed first-level tables, it should invalidate the affected IOTLB and the paging-structure-caches using the PASID- based-IOTLB Invalidate Descriptor defined in spec 6.5.2.4. Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 454c69712131..3a4708a8a414 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -650,6 +650,8 @@ extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type); extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, u16 qdep, u64 addr, unsigned mask); +void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, + unsigned long npages, bool ih); extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); extern int dmar_ir_support(void); -- cgit v1.2.3 From e2726daea583d81e447b71e09b79e67f618d6152 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 2 Jan 2020 08:18:22 +0800 Subject: iommu/vt-d: debugfs: Add support to show page table internals Export page table internals of the domain attached to each device. Example of such dump on a Skylake machine: $ sudo cat /sys/kernel/debug/iommu/intel/domain_translation_struct [ ... ] Device 0000:00:14.0 with pasid 0 @0x15f3d9000 IOVA_PFN PML5E PML4E 0x000000008ced0 | 0x0000000000000000 0x000000015f3da003 0x000000008ced1 | 0x0000000000000000 0x000000015f3da003 0x000000008ced2 | 0x0000000000000000 0x000000015f3da003 0x000000008ced3 | 0x0000000000000000 0x000000015f3da003 0x000000008ced4 | 0x0000000000000000 0x000000015f3da003 0x000000008ced5 | 0x0000000000000000 0x000000015f3da003 0x000000008ced6 | 0x0000000000000000 0x000000015f3da003 0x000000008ced7 | 0x0000000000000000 0x000000015f3da003 0x000000008ced8 | 0x0000000000000000 0x000000015f3da003 0x000000008ced9 | 0x0000000000000000 0x000000015f3da003 PDPE PDE PTE 0x000000015f3db003 0x000000015f3dc003 0x000000008ced0003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced1003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced2003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced3003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced4003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced5003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced6003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced7003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced8003 0x000000015f3db003 0x000000015f3dc003 0x000000008ced9003 [ ... ] Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3a4708a8a414..4a16b39ae353 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -441,6 +441,7 @@ enum { #define VTD_FLAG_SVM_CAPABLE (1 << 2) extern int intel_iommu_sm; +extern spinlock_t device_domain_lock; #define sm_supported(iommu) (intel_iommu_sm && ecap_smts((iommu)->ecap)) #define pasid_supported(iommu) (sm_supported(iommu) && \ @@ -663,6 +664,7 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info, void *data), void *data); void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); +struct dmar_domain *find_domain(struct device *dev); #ifdef CONFIG_INTEL_IOMMU_SVM extern void intel_svm_check(struct intel_iommu *iommu); -- cgit v1.2.3 From 11f1eabee0ba0aafe023ad92d1e3c29d0a96683e Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Tue, 3 Dec 2019 15:50:18 +0100 Subject: cros_ec: treewide: Remove 'include/linux/mfd/cros_ec.h' This header file now only includes the cros_ec_dev struct, however, is the 'include/linux/platform_data/cros_ec_proto.h' who contains the definition of all the Chrome OS EC related structs. There is no reason to have a separate include for this struct so move to the place where other structs are defined. That way, we can remove the include itself, but also simplify the common pattern #include #include for a single include #include The changes to remove the cros_ec.h include were generated with the following shell script: git grep -l "" | xargs sed -i '//d' Signed-off-by: Enric Balletbo i Serra Acked-by: Lee Jones Acked-by: Alexandre Belloni Acked-by: Jonathan Cameron Acked-by: Sebastian Reichel Acked-by: Hans Verkuil --- include/linux/mfd/cros_ec.h | 35 ----------------------------- include/linux/platform_data/cros_ec_proto.h | 23 ++++++++++++++++++- 2 files changed, 22 insertions(+), 36 deletions(-) delete mode 100644 include/linux/mfd/cros_ec.h (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h deleted file mode 100644 index 61c2875c2a40..000000000000 --- a/include/linux/mfd/cros_ec.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * ChromeOS EC multi-function device - * - * Copyright (C) 2012 Google, Inc - */ - -#ifndef __LINUX_MFD_CROS_EC_H -#define __LINUX_MFD_CROS_EC_H - -#include - -/** - * struct cros_ec_dev - ChromeOS EC device entry point. - * @class_dev: Device structure used in sysfs. - * @ec_dev: cros_ec_device structure to talk to the physical device. - * @dev: Pointer to the platform device. - * @debug_info: cros_ec_debugfs structure for debugging information. - * @has_kb_wake_angle: True if at least 2 accelerometer are connected to the EC. - * @cmd_offset: Offset to apply for each command. - * @features: Features supported by the EC. - */ -struct cros_ec_dev { - struct device class_dev; - struct cros_ec_device *ec_dev; - struct device *dev; - struct cros_ec_debugfs *debug_info; - bool has_kb_wake_angle; - u16 cmd_offset; - u32 features[2]; -}; - -#define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) - -#endif /* __LINUX_MFD_CROS_EC_H */ diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 30098a551523..119b9951c055 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -12,7 +12,6 @@ #include #include -#include #include #define CROS_EC_DEV_NAME "cros_ec" @@ -185,6 +184,28 @@ struct cros_ec_platform { u16 cmd_offset; }; +/** + * struct cros_ec_dev - ChromeOS EC device entry point. + * @class_dev: Device structure used in sysfs. + * @ec_dev: cros_ec_device structure to talk to the physical device. + * @dev: Pointer to the platform device. + * @debug_info: cros_ec_debugfs structure for debugging information. + * @has_kb_wake_angle: True if at least 2 accelerometer are connected to the EC. + * @cmd_offset: Offset to apply for each command. + * @features: Features supported by the EC. + */ +struct cros_ec_dev { + struct device class_dev; + struct cros_ec_device *ec_dev; + struct device *dev; + struct cros_ec_debugfs *debug_info; + bool has_kb_wake_angle; + u16 cmd_offset; + u32 features[2]; +}; + +#define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) + int cros_ec_suspend(struct cros_ec_device *ec_dev); int cros_ec_resume(struct cros_ec_device *ec_dev); -- cgit v1.2.3 From 8007880a2ca97c34e7ccd1fcf12daf854b792544 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Sat, 14 Dec 2019 10:51:17 +0200 Subject: net/mlx5: limit the function in local scope The function mlx5_buf_alloc_node is only used by the function in the local scope. So it is appropriate to limit this function in the local scope. Signed-off-by: Zhu Yanjun Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 27200dea0297..59cff380f41a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -928,8 +928,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); -int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, - struct mlx5_frag_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf); void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); -- cgit v1.2.3 From 945005409bfb55398d70c56178972d3750529dd6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 4 Jan 2020 16:20:52 +0100 Subject: soc: samsung: Rename Samsung and Exynos to lowercase Fix up inconsistent usage of upper and lowercase letters in "Samsung" and "Exynos" names. "SAMSUNG" and "EXYNOS" are not abbreviations but regular trademarked names. Therefore they should be written with lowercase letters starting with capital letter. The lowercase "Exynos" name is promoted by its manufacturer Samsung Electronics Co., Ltd., in advertisement materials and on website. Although advertisement materials usually use uppercase "SAMSUNG", the lowercase version is used in all legal aspects (e.g. on Wikipedia and in privacy/legal statements on https://www.samsung.com/semiconductor/privacy-global/). Signed-off-by: Krzysztof Kozlowski --- include/linux/soc/samsung/exynos-pmu.h | 2 +- include/linux/soc/samsung/exynos-regs-pmu.h | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/samsung/exynos-pmu.h b/include/linux/soc/samsung/exynos-pmu.h index fc0b445bb36b..a4f5516cc956 100644 --- a/include/linux/soc/samsung/exynos-pmu.h +++ b/include/linux/soc/samsung/exynos-pmu.h @@ -3,7 +3,7 @@ * Copyright (c) 2014 Samsung Electronics Co., Ltd. * http://www.samsung.com * - * Header for EXYNOS PMU Driver support + * Header for Exynos PMU Driver support */ #ifndef __LINUX_SOC_EXYNOS_PMU_H diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index 5addaf5ccbce..fc9250fb3133 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -3,7 +3,7 @@ * Copyright (c) 2010-2015 Samsung Electronics Co., Ltd. * http://www.samsung.com * - * EXYNOS - Power management unit definition + * Exynos - Power management unit definition * * Notice: * This is not a list of all Exynos Power Management Unit SFRs. @@ -185,7 +185,7 @@ /* Only for S5Pv210 */ #define S5PV210_EINT_WAKEUP_MASK 0xC004 -/* Only for EXYNOS4210 */ +/* Only for Exynos4210 */ #define S5P_CMU_CLKSTOP_LCD1_LOWPWR 0x1154 #define S5P_CMU_RESET_LCD1_LOWPWR 0x1174 #define S5P_MODIMIF_MEM_LOWPWR 0x11C4 @@ -193,7 +193,7 @@ #define S5P_SATA_MEM_LOWPWR 0x11E4 #define S5P_LCD1_LOWPWR 0x1394 -/* Only for EXYNOS4x12 */ +/* Only for Exynos4x12 */ #define S5P_ISP_ARM_LOWPWR 0x1050 #define S5P_DIS_IRQ_ISP_ARM_LOCAL_LOWPWR 0x1054 #define S5P_DIS_IRQ_ISP_ARM_CENTRAL_LOWPWR 0x1058 @@ -234,7 +234,7 @@ #define S5P_SECSS_MEM_OPTION 0x2EC8 #define S5P_ROTATOR_MEM_OPTION 0x2F48 -/* Only for EXYNOS4412 */ +/* Only for Exynos4412 */ #define S5P_ARM_CORE2_LOWPWR 0x1020 #define S5P_DIS_IRQ_CORE2 0x1024 #define S5P_DIS_IRQ_CENTRAL2 0x1028 @@ -242,7 +242,7 @@ #define S5P_DIS_IRQ_CORE3 0x1034 #define S5P_DIS_IRQ_CENTRAL3 0x1038 -/* Only for EXYNOS3XXX */ +/* Only for Exynos3XXX */ #define EXYNOS3_ARM_CORE0_SYS_PWR_REG 0x1000 #define EXYNOS3_DIS_IRQ_ARM_CORE0_LOCAL_SYS_PWR_REG 0x1004 #define EXYNOS3_DIS_IRQ_ARM_CORE0_CENTRAL_SYS_PWR_REG 0x1008 @@ -347,7 +347,7 @@ #define EXYNOS3_OPTION_USE_SC_FEEDBACK (1 << 1) #define EXYNOS3_OPTION_SKIP_DEACTIVATE_ACEACP_IN_PWDN (1 << 7) -/* For EXYNOS5 */ +/* For Exynos5 */ #define EXYNOS5_AUTO_WDTRESET_DISABLE 0x0408 #define EXYNOS5_MASK_WDTRESET_REQUEST 0x040C @@ -484,7 +484,7 @@ #define EXYNOS5420_SWRESET_KFC_SEL 0x3 -/* Only for EXYNOS5420 */ +/* Only for Exynos5420 */ #define EXYNOS5420_L2RSTDISABLE_VALUE BIT(3) #define EXYNOS5420_LPI_MASK 0x0004 @@ -645,7 +645,7 @@ | EXYNOS5420_KFC_USE_STANDBY_WFI2 \ | EXYNOS5420_KFC_USE_STANDBY_WFI3) -/* For EXYNOS5433 */ +/* For Exynos5433 */ #define EXYNOS5433_EINT_WAKEUP_MASK (0x060C) #define EXYNOS5433_USBHOST30_PHY_CONTROL (0x0728) #define EXYNOS5433_PAD_RETENTION_AUD_OPTION (0x3028) -- cgit v1.2.3 From 7d93aecdb58d47e8ed90b4a44c0fc9ffb8de941c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 2 Jan 2020 14:38:17 +0100 Subject: spi: Add generic support for unused native cs with cs-gpios Some SPI master controllers always drive a native chip select when performing a transfer. Hence when using both native and GPIO chip selects, at least one native chip select must be left unused, to be driven when performing transfers with slave devices using GPIO chip selects. Currently, to find an unused native chip select, SPI controller drivers need to parse and process cs-gpios theirselves. This is not only duplicated in each driver that needs it, but also duplicates part of the work done later at SPI controller registration time. Note that this cannot be done after spi_register_controller() returns, as at that time, slave devices may have been probed already. Hence add generic support to the SPI subsystem for finding an unused native chip select. Optionally, this unused native chip select, and all other in-use native chip selects, can be validated against the maximum number of native chip selects available on the controller hardware. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200102133822.29346-2-geert+renesas@glider.be Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 98fe8663033a..e4011b852fc3 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -423,6 +423,12 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * GPIO descriptors rather than using global GPIO numbers grabbed by the * driver. This will fill in @cs_gpiods and @cs_gpios should not be used, * and SPI devices will have the cs_gpiod assigned rather than cs_gpio. + * @unused_native_cs: When cs_gpiods is used, spi_register_controller() will + * fill in this field with the first unused native CS, to be used by SPI + * controller drivers that need to drive a native CS when using GPIO CS. + * @max_native_cs: When cs_gpiods is used, and this field is filled in, + * spi_register_controller() will validate all native CS (including the + * unused native CS) against this value. * @statistics: statistics for the spi_controller * @dma_tx: DMA transmit channel * @dma_rx: DMA receive channel @@ -624,6 +630,8 @@ struct spi_controller { int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; + u8 unused_native_cs; + u8 max_native_cs; /* statistics */ struct spi_statistics statistics; -- cgit v1.2.3 From 9a1108d2b001cda1af17160c78afedfff92e2202 Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Tue, 7 Jan 2020 13:04:12 -0800 Subject: firmware: qcom_scm: Remove unused qcom_scm_get_version Remove unused qcom_scm_get_version. Reviewed-by: Bjorn Andersson Reviewed-by: Vinod Koul Reviewed-by: Stephen Boyd Tested-by: Brian Masney # arm32 Tested-by: Stephan Gerhold Signed-off-by: Elliot Berman Link: https://lore.kernel.org/r/1578431066-19600-4-git-send-email-eberman@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/qcom_scm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 2c1d20312ce0..98e775d7a3ec 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -78,7 +78,6 @@ extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, const struct qcom_scm_vmperm *newvm, unsigned int dest_cnt); extern void qcom_scm_cpu_power_down(u32 flags); -extern u32 qcom_scm_get_version(void); extern int qcom_scm_set_remote_state(u32 state, u32 id); extern bool qcom_scm_restore_sec_cfg_available(void); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); @@ -123,7 +122,6 @@ static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, const struct qcom_scm_vmperm *newvm, unsigned int dest_cnt) { return -ENODEV; } static inline void qcom_scm_cpu_power_down(u32 flags) {} -static inline u32 qcom_scm_get_version(void) { return 0; } static inline u32 qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; } static inline bool qcom_scm_restore_sec_cfg_available(void) { return false; } -- cgit v1.2.3 From 65f0c90b7d468545590992c61a19f9dc0aac61ef Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Tue, 7 Jan 2020 13:04:24 -0800 Subject: firmware: qcom_scm: Order functions, definitions by service/command Definitions throughout qcom_scm are loosely grouped and loosely ordered. Sort all the functions/definitions by service ID/command ID to improve sanity when needing to add new functionality to this driver. Acked-by: Bjorn Andersson Tested-by: Brian Masney # arm32 Tested-by: Stephan Gerhold Signed-off-by: Elliot Berman Link: https://lore.kernel.org/r/1578431066-19600-16-git-send-email-eberman@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/qcom_scm.h | 123 ++++++++++++++++++++++++++--------------------- 1 file changed, 68 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 98e775d7a3ec..3d6a24697761 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2010-2015, 2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2015, 2018-2019 The Linux Foundation. All rights reserved. * Copyright (C) 2015 Linaro Ltd. */ #ifndef __QCOM_SCM_H @@ -55,81 +55,94 @@ enum qcom_scm_sec_dev_id { #define QCOM_SCM_PERM_RWX (QCOM_SCM_PERM_RW | QCOM_SCM_PERM_EXEC) #if IS_ENABLED(CONFIG_QCOM_SCM) +extern bool qcom_scm_is_available(void); + extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); -extern bool qcom_scm_is_available(void); -extern bool qcom_scm_hdcp_available(void); -extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, - u32 *resp); -extern bool qcom_scm_ocmem_lock_available(void); -extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size, u32 mode); -extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size); -extern bool qcom_scm_pas_supported(u32 peripheral); +extern void qcom_scm_cpu_power_down(u32 flags); +extern int qcom_scm_set_remote_state(u32 state, u32 id); + extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size); extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size); extern int qcom_scm_pas_auth_and_reset(u32 peripheral); extern int qcom_scm_pas_shutdown(u32 peripheral); -extern 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); -extern void qcom_scm_cpu_power_down(u32 flags); -extern int qcom_scm_set_remote_state(u32 state, u32 id); +extern bool qcom_scm_pas_supported(u32 peripheral); + +extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val); +extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); + 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_assign_mem(phys_addr_t mem_addr, size_t mem_sz, + unsigned int *src, + const struct qcom_scm_vmperm *newvm, + unsigned int dest_cnt); + +extern bool qcom_scm_ocmem_lock_available(void); +extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size, u32 mode); +extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size); + +extern bool qcom_scm_hdcp_available(void); +extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, + u32 *resp); + extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); -extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val); -extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); #else #include -static inline -int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus) -{ - return -ENODEV; -} -static inline -int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus) -{ - return -ENODEV; -} static inline bool qcom_scm_is_available(void) { return false; } -static inline bool qcom_scm_hdcp_available(void) { return false; } -static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, - u32 *resp) { return -ENODEV; } -static inline bool qcom_scm_ocmem_lock_available(void) { return false; } -static inline int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size, u32 mode) { return -ENODEV; } -static inline int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size) { return -ENODEV; } -static inline bool qcom_scm_pas_supported(u32 peripheral) { return false; } + +static inline int qcom_scm_set_cold_boot_addr(void *entry, + const cpumask_t *cpus) { return -ENODEV; } +static inline int qcom_scm_set_warm_boot_addr(void *entry, + const cpumask_t *cpus) { return -ENODEV; } +static inline void qcom_scm_cpu_power_down(u32 flags) {} +static inline u32 qcom_scm_set_remote_state(u32 state,u32 id) + { return -ENODEV; } + static inline int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size) { return -ENODEV; } + size_t size) { return -ENODEV; } static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, - phys_addr_t size) { return -ENODEV; } -static inline int -qcom_scm_pas_auth_and_reset(u32 peripheral) { return -ENODEV; } + phys_addr_t size) { return -ENODEV; } +static inline int qcom_scm_pas_auth_and_reset(u32 peripheral) + { return -ENODEV; } static inline int qcom_scm_pas_shutdown(u32 peripheral) { 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; } -static inline void qcom_scm_cpu_power_down(u32 flags) {} -static inline u32 -qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; } +static inline bool qcom_scm_pas_supported(u32 peripheral) { return false; } + +static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) + { return -ENODEV; } +static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) + { return -ENODEV; } + static inline bool qcom_scm_restore_sec_cfg_available(void) { return false; } -static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return -ENODEV; } -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; } -static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) { return -ENODEV; } -static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) { return -ENODEV; } -static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) { return -ENODEV; } +static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) + { return -ENODEV; } +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; } +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; } + +static inline bool qcom_scm_ocmem_lock_available(void) { return false; } +static inline int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size, u32 mode) { return -ENODEV; } +static inline int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, + u32 offset, u32 size) { return -ENODEV; } + +static inline bool qcom_scm_hdcp_available(void) { return false; } +static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, + u32 *resp) { return -ENODEV; } + +static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) + { return -ENODEV; } #endif #endif -- cgit v1.2.3 From ff258817137a9004e2fbee2b36df58a4fc7d0f7e Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 30 Aug 2019 08:09:23 -0700 Subject: clk: divider: Add support for specifying parents via DT/pointers After commit fc0c209c147f ("clk: Allow parents to be specified without string names") we can use DT or direct clk_hw pointers to specify parents. Create a generic function that shouldn't be used very often to encode the multitude of ways of registering a divider clk with different parent information. Then add a bunch of wrapper macros that only pass down what needs to be passed down to the generic function to support this with less arguments. Cc: Manivannan Sadhasivam Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20190830150923.259497-13-sboyd@kernel.org [sboyd@kernel.org: Export __clk_hw_register_divider] --- include/linux/clk-provider.h | 155 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 142 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 152aeb5aa006..be0d22d86590 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -626,24 +626,153 @@ int divider_get_val(unsigned long rate, unsigned long parent_rate, const struct clk_div_table *table, u8 width, unsigned long flags); -struct clk *clk_register_divider(struct device *dev, const char *name, - const char *parent_name, unsigned long flags, - void __iomem *reg, u8 shift, u8 width, - u8 clk_divider_flags, spinlock_t *lock); -struct clk_hw *clk_hw_register_divider(struct device *dev, const char *name, - const char *parent_name, unsigned long flags, - void __iomem *reg, u8 shift, u8 width, - u8 clk_divider_flags, spinlock_t *lock); +struct clk_hw *__clk_hw_register_divider(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, unsigned long flags, + void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, + const struct clk_div_table *table, spinlock_t *lock); struct clk *clk_register_divider_table(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, const struct clk_div_table *table, spinlock_t *lock); -struct clk_hw *clk_hw_register_divider_table(struct device *dev, - const char *name, const char *parent_name, unsigned long flags, - void __iomem *reg, u8 shift, u8 width, - u8 clk_divider_flags, const struct clk_div_table *table, - spinlock_t *lock); +/** + * clk_register_divider - register a divider clock with the clock framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define clk_register_divider(dev, name, parent_name, flags, reg, shift, width, \ + clk_divider_flags, lock) \ + clk_register_divider_table((dev), (name), (parent_name), (flags), \ + (reg), (shift), (width), \ + (clk_divider_flags), NULL, (lock)) +/** + * clk_hw_register_divider - register a divider clock with the clock framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define clk_hw_register_divider(dev, name, parent_name, flags, reg, shift, \ + width, clk_divider_flags, lock) \ + __clk_hw_register_divider((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (shift), (width), \ + (clk_divider_flags), NULL, (lock)) +/** + * clk_hw_register_divider_parent_hw - register a divider clock with the clock + * framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_hw: pointer to parent clk + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define clk_hw_register_divider_parent_hw(dev, name, parent_hw, flags, reg, \ + shift, width, clk_divider_flags, \ + lock) \ + __clk_hw_register_divider((dev), NULL, (name), NULL, (parent_hw), \ + NULL, (flags), (reg), (shift), (width), \ + (clk_divider_flags), NULL, (lock)) +/** + * clk_hw_register_divider_parent_data - register a divider clock with the clock + * framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define clk_hw_register_divider_parent_data(dev, name, parent_data, flags, \ + reg, shift, width, \ + clk_divider_flags, lock) \ + __clk_hw_register_divider((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (shift), \ + (width), (clk_divider_flags), NULL, (lock)) +/** + * clk_hw_register_divider_table - register a table based divider clock with + * the clock framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @table: array of divider/value pairs ending with a div set to 0 + * @lock: shared register lock for this clock + */ +#define clk_hw_register_divider_table(dev, name, parent_name, flags, reg, \ + shift, width, clk_divider_flags, table, \ + lock) \ + __clk_hw_register_divider((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (shift), (width), \ + (clk_divider_flags), (table), (lock)) +/** + * clk_hw_register_divider_table_parent_hw - register a table based divider + * clock with the clock framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_hw: pointer to parent clk + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @table: array of divider/value pairs ending with a div set to 0 + * @lock: shared register lock for this clock + */ +#define clk_hw_register_divider_table_parent_hw(dev, name, parent_hw, flags, \ + reg, shift, width, \ + clk_divider_flags, table, \ + lock) \ + __clk_hw_register_divider((dev), NULL, (name), NULL, (parent_hw), \ + NULL, (flags), (reg), (shift), (width), \ + (clk_divider_flags), (table), (lock)) +/** + * clk_hw_register_divider_table_parent_data - register a table based divider + * clock with the clock framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @table: array of divider/value pairs ending with a div set to 0 + * @lock: shared register lock for this clock + */ +#define clk_hw_register_divider_table_parent_data(dev, name, parent_data, \ + flags, reg, shift, width, \ + clk_divider_flags, table, \ + lock) \ + __clk_hw_register_divider((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (shift), \ + (width), (clk_divider_flags), (table), \ + (lock)) + void clk_unregister_divider(struct clk *clk); void clk_hw_unregister_divider(struct clk_hw *hw); -- cgit v1.2.3 From 987351e1ea7772cf2f0795e917fb33b2e282e1c1 Mon Sep 17 00:00:00 2001 From: Alexandre Torgue Date: Mon, 4 Nov 2019 15:37:13 +0100 Subject: phy: core: Add consumer device link support In order to enforce suspend/resume ordering, this commit creates link between phy consumers and phy devices. This link avoids to suspend phy before phy consumers. Signed-off-by: Alexandre Torgue [jonathanh@nvidia.com: Fix an abort when of_phy_get() returns error] Signed-off-by: Jonathan Hunter Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 56d3a100006a..19eddd64c8f6 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -234,7 +234,8 @@ struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, const char *con_id); struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, int index); -void phy_put(struct phy *phy); +void of_phy_put(struct phy *phy); +void phy_put(struct device *dev, struct phy *phy); void devm_phy_put(struct device *dev, struct phy *phy); struct phy *of_phy_get(struct device_node *np, const char *con_id); struct phy *of_phy_simple_xlate(struct device *dev, @@ -419,7 +420,11 @@ static inline struct phy *devm_of_phy_get_by_index(struct device *dev, return ERR_PTR(-ENOSYS); } -static inline void phy_put(struct phy *phy) +static inline void of_phy_put(struct phy *phy) +{ +} + +static inline void phy_put(struct device *dev, struct phy *phy) { } -- cgit v1.2.3 From 5c8b718c5a32bfa3e7a263c19b81bae9130229f1 Mon Sep 17 00:00:00 2001 From: Bibby Hsieh Date: Thu, 21 Nov 2019 09:54:07 +0800 Subject: soc: mediatek: cmdq: define the instruction struct Define an instruction structure for gce driver to append command. This structure can make the client's code more readability. Signed-off-by: Bibby Hsieh Reviewed-by: CK Hu Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index e6f54ef6698b..678760548791 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -20,6 +20,16 @@ #define CMDQ_WFE_WAIT BIT(15) #define CMDQ_WFE_WAIT_VALUE 0x1 +/* + * WFE arg_b + * bit 0-11: wait value + * bit 15: 1 - wait, 0 - no wait + * 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) + /** cmdq event maximum */ #define CMDQ_MAX_EVENT 0x3ff -- cgit v1.2.3 From b2ff2356bf93d66e7155acea63dcd503aca6c28f Mon Sep 17 00:00:00 2001 From: Bibby Hsieh Date: Thu, 21 Nov 2019 09:54:08 +0800 Subject: soc: mediatek: cmdq: add polling function add polling function in cmdq helper functions Signed-off-by: Bibby Hsieh Reviewed-by: CK Hu Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + include/linux/soc/mediatek/mtk-cmdq.h | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 678760548791..a4dc45fbec0a 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -55,6 +55,7 @@ enum cmdq_code { CMDQ_CODE_MASK = 0x02, CMDQ_CODE_WRITE = 0x04, + CMDQ_CODE_POLL = 0x08, CMDQ_CODE_JUMP = 0x10, CMDQ_CODE_WFE = 0x20, CMDQ_CODE_EOC = 0x40, diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 9618debb9ceb..92bd5b5c6341 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -99,6 +99,38 @@ int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event); */ int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event); +/** + * cmdq_pkt_poll() - Append polling command to the CMDQ packet, ask GCE to + * execute an instruction that wait for a specified + * hardware register to check for the value w/o mask. + * All GCE hardware threads will be blocked by this + * instruction. + * @pkt: the CMDQ packet + * @subsys: the CMDQ sub system code + * @offset: register offset from CMDQ sub system + * @value: the specified target register value + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value); + +/** + * cmdq_pkt_poll_mask() - Append polling command to the CMDQ packet, ask GCE to + * execute an instruction that wait for a specified + * hardware register to check for the value w/ mask. + * All GCE hardware threads will be blocked by this + * instruction. + * @pkt: the CMDQ packet + * @subsys: the CMDQ sub system code + * @offset: register offset from CMDQ sub system + * @value: the specified target register value + * @mask: the specified target register mask + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value, u32 mask); /** * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ * packet and call back at the end of done packet -- cgit v1.2.3 From d412f18c9bc791d8951e903de9a68817e3098a6a Mon Sep 17 00:00:00 2001 From: Bibby Hsieh Date: Thu, 21 Nov 2019 09:54:09 +0800 Subject: soc: mediatek: cmdq: add cmdq_dev_get_client_reg function GCE cannot know the register base address, this function can help cmdq client to get the cmdq_client_reg structure. Signed-off-by: Bibby Hsieh Reviewed-by: CK Hu Reviewed-by: Houlong Wei Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 92bd5b5c6341..a74c1d5acdf3 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -15,6 +15,12 @@ struct cmdq_pkt; +struct cmdq_client_reg { + u8 subsys; + u16 offset; + u16 size; +}; + struct cmdq_client { spinlock_t lock; u32 pkt_cnt; @@ -24,6 +30,21 @@ struct cmdq_client { u32 timeout_ms; /* in unit of microsecond */ }; +/** + * cmdq_dev_get_client_reg() - parse cmdq client reg from the device + * node of CMDQ client + * @dev: device of CMDQ mailbox client + * @client_reg: CMDQ client reg pointer + * @idx: the index of desired reg + * + * Return: 0 for success; else the error code is returned + * + * Help CMDQ client parsing the cmdq client reg + * from the device node of CMDQ client. + */ +int cmdq_dev_get_client_reg(struct device *dev, + struct cmdq_client_reg *client_reg, int idx); + /** * cmdq_mbox_create() - create CMDQ mailbox client and channel * @dev: device of CMDQ mailbox client -- cgit v1.2.3 From 885f7d6cb87eb15d62613c05d8012e9370fb5e27 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Fri, 6 Dec 2019 18:45:52 +0800 Subject: KVM: Remove duplicated declaration of kvm_vcpu_kick There are two declarations of kvm_vcpu_kick() in kvm_host.h where one of them is redundant. Remove to keep the git grep a bit cleaner. Reviewed-by: Cornelia Huck Signed-off-by: Zenghui Yu Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 538c25e778c0..0d632a75fce9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -982,7 +982,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); -void kvm_vcpu_kick(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); -- cgit v1.2.3 From 736c291c9f36b07f8889c61764c28edce20e715d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 6 Dec 2019 15:57:14 -0800 Subject: KVM: x86: Use gpa_t for cr2/gpa to fix TDP support on 32-bit KVM Convert a plethora of parameters and variables in the MMU and page fault flows from type gva_t to gpa_t to properly handle TDP on 32-bit KVM. Thanks to PSE and PAE paging, 32-bit kernels can access 64-bit physical addresses. When TDP is enabled, the fault address is a guest physical address and thus can be a 64-bit value, even when both KVM and its guest are using 32-bit virtual addressing, e.g. VMX's VMCS.GUEST_PHYSICAL is a 64-bit field, not a natural width field. Using a gva_t for the fault address means KVM will incorrectly drop the upper 32-bits of the GPA. Ditto for gva_to_gpa() when it is used to translate L2 GPAs to L1 GPAs. Opportunistically rename variables and parameters to better reflect the dual address modes, e.g. use "cr2_or_gpa" for fault addresses and plain "addr" instead of "vaddr" when the address may be either a GVA or an L2 GPA. Similarly, use "gpa" in the nonpaging_page_fault() flows to avoid a confusing "gpa_t gva" declaration; this also sets the stage for a future patch to combing nonpaging_page_fault() and tdp_page_fault() with minimal churn. Sprinkle in a few comments to document flows where an address is known to be a GVA and thus can be safely truncated to a 32-bit value. Add WARNs in kvm_handle_page_fault() and FNAME(gva_to_gpa_nested)() to help document such cases and detect bugs. Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0d632a75fce9..528ab7a814ab 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -204,7 +204,7 @@ struct kvm_async_pf { struct list_head queue; struct kvm_vcpu *vcpu; struct mm_struct *mm; - gva_t gva; + gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; @@ -212,8 +212,8 @@ struct kvm_async_pf { void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, - struct kvm_arch_async_pf *arch); +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -- cgit v1.2.3 From 96cc4b69581db68efc9749ef32e9cf8e0160c509 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jan 2020 12:30:48 -0800 Subject: macvlan: do not assume mac_header is set in macvlan_broadcast() Use of eth_hdr() in tx path is error prone. Many drivers call skb_reset_mac_header() before using it, but others do not. Commit 6d1ccff62780 ("net: reset mac header in dev_start_xmit()") attempted to fix this generically, but commit d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option") brought back the macvlan bug. Lets add a new helper, so that tx paths no longer have to call skb_reset_mac_header() only to get a pointer to skb->data. Hopefully we will be able to revert 6d1ccff62780 ("net: reset mac header in dev_start_xmit()") and save few cycles in transmit fast path. BUG: KASAN: use-after-free in __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline] BUG: KASAN: use-after-free in mc_hash drivers/net/macvlan.c:251 [inline] BUG: KASAN: use-after-free in macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277 Read of size 4 at addr ffff8880a4932401 by task syz-executor947/9579 CPU: 0 PID: 9579 Comm: syz-executor947 Not tainted 5.5.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:639 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/generic_report.c:145 __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline] mc_hash drivers/net/macvlan.c:251 [inline] macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277 macvlan_queue_xmit drivers/net/macvlan.c:520 [inline] macvlan_start_xmit+0x402/0x77f drivers/net/macvlan.c:559 __netdev_start_xmit include/linux/netdevice.h:4447 [inline] netdev_start_xmit include/linux/netdevice.h:4461 [inline] dev_direct_xmit+0x419/0x630 net/core/dev.c:4079 packet_direct_xmit+0x1a9/0x250 net/packet/af_packet.c:240 packet_snd net/packet/af_packet.c:2966 [inline] packet_sendmsg+0x260d/0x6220 net/packet/af_packet.c:2991 sock_sendmsg_nosec net/socket.c:639 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:659 __sys_sendto+0x262/0x380 net/socket.c:1985 __do_sys_sendto net/socket.c:1997 [inline] __se_sys_sendto net/socket.c:1993 [inline] __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1993 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x442639 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffc13549e08 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000442639 RDX: 000000000000000e RSI: 0000000020000080 RDI: 0000000000000003 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000403bb0 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 9389: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] __kasan_kmalloc mm/kasan/common.c:513 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527 __do_kmalloc mm/slab.c:3656 [inline] __kmalloc+0x163/0x770 mm/slab.c:3665 kmalloc include/linux/slab.h:561 [inline] tomoyo_realpath_from_path+0xc5/0x660 security/tomoyo/realpath.c:252 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129 security_inode_getattr+0xf2/0x150 security/security.c:1222 vfs_getattr+0x25/0x70 fs/stat.c:115 vfs_statx_fd+0x71/0xc0 fs/stat.c:145 vfs_fstat include/linux/fs.h:3265 [inline] __do_sys_newfstat+0x9b/0x120 fs/stat.c:378 __se_sys_newfstat fs/stat.c:375 [inline] __x64_sys_newfstat+0x54/0x80 fs/stat.c:375 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 9389: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] kasan_set_free_info mm/kasan/common.c:335 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483 __cache_free mm/slab.c:3426 [inline] kfree+0x10a/0x2c0 mm/slab.c:3757 tomoyo_realpath_from_path+0x1a7/0x660 security/tomoyo/realpath.c:289 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129 security_inode_getattr+0xf2/0x150 security/security.c:1222 vfs_getattr+0x25/0x70 fs/stat.c:115 vfs_statx_fd+0x71/0xc0 fs/stat.c:145 vfs_fstat include/linux/fs.h:3265 [inline] __do_sys_newfstat+0x9b/0x120 fs/stat.c:378 __se_sys_newfstat fs/stat.c:375 [inline] __x64_sys_newfstat+0x54/0x80 fs/stat.c:375 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8880a4932000 which belongs to the cache kmalloc-4k of size 4096 The buggy address is located 1025 bytes inside of 4096-byte region [ffff8880a4932000, ffff8880a4933000) The buggy address belongs to the page: page:ffffea0002924c80 refcount:1 mapcount:0 mapping:ffff8880aa402000 index:0x0 compound_mapcount: 0 raw: 00fffe0000010200 ffffea0002846208 ffffea00028f3888 ffff8880aa402000 raw: 0000000000000000 ffff8880a4932000 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880a4932300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a4932380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880a4932400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880a4932480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a4932500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: b863ceb7ddce ("[NET]: Add macvlan driver") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/linux/if_ether.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 76cf11e905e1..8a9792a6427a 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -24,6 +24,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_mac_header(skb); } +/* Prefer this version in TX path, instead of + * skb_reset_mac_header() + eth_hdr() + */ +static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb) +{ + return (struct ethhdr *)skb->data; +} + static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_inner_mac_header(skb); -- cgit v1.2.3 From dcfea72e79b0aa7a057c8f6024169d86a1bbc84b Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 8 Jan 2020 16:59:02 -0500 Subject: net: introduce skb_list_walk_safe for skb segment walking As part of the continual effort to remove direct usage of skb->next and skb->prev, this patch adds a helper for iterating through the singly-linked variant of skb lists, which are used for lists of GSO packet. The name "skb_list_..." has been chosen to match the existing function, "kfree_skb_list, which also operates on these singly-linked lists, and the "..._walk_safe" part is the same idiom as elsewhere in the kernel. This patch removes the helper from wireguard and puts it into linux/skbuff.h, while making it a bit more robust for general usage. In particular, parenthesis are added around the macro argument usage, and it now accounts for trying to iterate through an already-null skb pointer, which will simply run the iteration zero times. This latter enhancement means it can be used to replace both do { ... } while and while (...) open-coded idioms. This should take care of these three possible usages, which match all current methods of iterations. skb_list_walk_safe(segs, skb, next) { ... } skb_list_walk_safe(skb, skb, next) { ... } skb_list_walk_safe(segs, skb, segs) { ... } Gcc appears to generate efficient code for each of these. Signed-off-by: Jason A. Donenfeld Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e9133bcf0544..64e5b1be9ff5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1478,6 +1478,11 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb) skb->next = NULL; } +/* Iterate through singly-linked GSO fragments of an skb. */ +#define skb_list_walk_safe(first, skb, next) \ + for ((skb) = (first), (next) = (skb) ? (skb)->next : NULL; (skb); \ + (skb) = (next), (next) = (skb) ? (skb)->next : NULL) + static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); -- cgit v1.2.3 From f9d89b853ec1709345c0e2f1f51ae53188eef981 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Dec 2019 21:19:34 -0600 Subject: crypto: remove unused tfm result flags The tfm result flags CRYPTO_TFM_RES_BAD_KEY_SCHED and CRYPTO_TFM_RES_BAD_FLAGS are never used, so remove them. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 8729f957f83c..950b592947b2 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -114,9 +114,7 @@ #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 #define CRYPTO_TFM_RES_WEAK_KEY 0x00100000 #define CRYPTO_TFM_RES_BAD_KEY_LEN 0x00200000 -#define CRYPTO_TFM_RES_BAD_KEY_SCHED 0x00400000 #define CRYPTO_TFM_RES_BAD_BLOCK_LEN 0x00800000 -#define CRYPTO_TFM_RES_BAD_FLAGS 0x01000000 /* * Miscellaneous stuff. -- cgit v1.2.3 From 5c925e8b10a5f43f220755aceb9d5f14b2f4e2c5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Dec 2019 21:19:35 -0600 Subject: crypto: remove CRYPTO_TFM_RES_BAD_BLOCK_LEN The flag CRYPTO_TFM_RES_BAD_BLOCK_LEN is never checked for, and it's only set by one driver. And even that single driver's use is wrong because the driver is setting the flag from ->encrypt() and ->decrypt() with no locking, which is unsafe because ->encrypt() and ->decrypt() can be executed by many threads in parallel on the same tfm. Just remove this flag. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 950b592947b2..719a301af3f2 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -114,7 +114,6 @@ #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 #define CRYPTO_TFM_RES_WEAK_KEY 0x00100000 #define CRYPTO_TFM_RES_BAD_KEY_LEN 0x00200000 -#define CRYPTO_TFM_RES_BAD_BLOCK_LEN 0x00800000 /* * Miscellaneous stuff. -- cgit v1.2.3 From 674f368a952c48ede71784935a799a5205b92b6c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Dec 2019 21:19:36 -0600 Subject: crypto: remove CRYPTO_TFM_RES_BAD_KEY_LEN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CRYPTO_TFM_RES_BAD_KEY_LEN flag was apparently meant as a way to make the ->setkey() functions provide more information about errors. However, no one actually checks for this flag, which makes it pointless. Also, many algorithms fail to set this flag when given a bad length key. Reviewing just the generic implementations, this is the case for aes-fixed-time, cbcmac, echainiv, nhpoly1305, pcrypt, rfc3686, rfc4309, rfc7539, rfc7539esp, salsa20, seqiv, and xcbc. But there are probably many more in arch/*/crypto/ and drivers/crypto/. Some algorithms can even set this flag when the key is the correct length. For example, authenc and authencesn set it when the key payload is malformed in any way (not just a bad length), the atmel-sha and ccree drivers can set it if a memory allocation fails, and the chelsio driver sets it for bad auth tag lengths, not just bad key lengths. So even if someone actually wanted to start checking this flag (which seems unlikely, since it's been unused for a long time), there would be a lot of work needed to get it working correctly. But it would probably be much better to go back to the drawing board and just define different return values, like -EINVAL if the key is invalid for the algorithm vs. -EKEYREJECTED if the key was rejected by a policy like "no weak keys". That would be much simpler, less error-prone, and easier to test. So just remove this flag. Signed-off-by: Eric Biggers Reviewed-by: Horia Geantă Signed-off-by: Herbert Xu --- include/linux/crypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 719a301af3f2..61fccc7d0efb 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -113,7 +113,6 @@ #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 #define CRYPTO_TFM_RES_WEAK_KEY 0x00100000 -#define CRYPTO_TFM_RES_BAD_KEY_LEN 0x00200000 /* * Miscellaneous stuff. -- cgit v1.2.3 From c4c4db0d59774f6ab726edd012711490437345c2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Dec 2019 21:19:37 -0600 Subject: crypto: remove CRYPTO_TFM_RES_WEAK_KEY The CRYPTO_TFM_RES_WEAK_KEY flag was apparently meant as a way to make the ->setkey() functions provide more information about errors. However, no one actually checks for this flag, which makes it pointless. There are also no tests that verify that all algorithms actually set (or don't set) it correctly. This is also the last remaining CRYPTO_TFM_RES_* flag, which means that it's the only thing still needing all the boilerplate code which propagates these flags around from child => parent tfms. And if someone ever needs to distinguish this error in the future (which is somewhat unlikely, as it's been unneeded for a long time), it would be much better to just define a new return value like -EKEYREJECTED. That would be much simpler, less error-prone, and easier to test. So just remove this flag. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 61fccc7d0efb..accd0c8038fd 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -112,7 +112,6 @@ #define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS 0x00000100 #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 -#define CRYPTO_TFM_RES_WEAK_KEY 0x00100000 /* * Miscellaneous stuff. -- cgit v1.2.3 From af5034e8e4a5838fc77e476c1a91822e449d5869 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Dec 2019 21:19:38 -0600 Subject: crypto: remove propagation of CRYPTO_TFM_RES_* flags The CRYPTO_TFM_RES_* flags were apparently meant as a way to make the ->setkey() functions provide more information about errors. But these flags weren't actually being used or tested, and in many cases they weren't being set correctly anyway. So they've now been removed. Also, if someone ever actually needs to start better distinguishing ->setkey() errors (which is somewhat unlikely, as this has been unneeded for a long time), we'd be much better off just defining different return values, like -EINVAL if the key is invalid for the algorithm vs. -EKEYREJECTED if the key was rejected by a policy like "no weak keys". That would be much simpler, less error-prone, and easier to test. So just remove CRYPTO_TFM_RES_MASK and all the unneeded logic that propagates these flags around. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index accd0c8038fd..763863dbc079 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -107,8 +107,6 @@ #define CRYPTO_TFM_NEED_KEY 0x00000001 #define CRYPTO_TFM_REQ_MASK 0x000fff00 -#define CRYPTO_TFM_RES_MASK 0xfff00000 - #define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS 0x00000100 #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 -- cgit v1.2.3 From 8face9aa57c8335b2d698a70bcfaaaa46dd36b93 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:25:58 +0300 Subject: usb: typec: Add parameter for the VDO to typec_altmode_enter() Enter Mode Command may contain one VDO. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-3-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_altmode.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 9a88c74a1d0d..fc57fd88004f 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -55,7 +55,7 @@ static inline void *typec_altmode_get_drvdata(struct typec_altmode *altmode) * @activate: User callback for Enter/Exit Mode */ struct typec_altmode_ops { - int (*enter)(struct typec_altmode *altmode); + int (*enter)(struct typec_altmode *altmode, u32 *vdo); int (*exit)(struct typec_altmode *altmode); void (*attention)(struct typec_altmode *altmode, u32 vdo); int (*vdm)(struct typec_altmode *altmode, const u32 hdr, @@ -65,7 +65,7 @@ struct typec_altmode_ops { int (*activate)(struct typec_altmode *altmode, int activate); }; -int typec_altmode_enter(struct typec_altmode *altmode); +int typec_altmode_enter(struct typec_altmode *altmode, u32 *vdo); int typec_altmode_exit(struct typec_altmode *altmode); void typec_altmode_attention(struct typec_altmode *altmode, u32 vdo); int typec_altmode_vdm(struct typec_altmode *altmode, -- cgit v1.2.3 From b66b40ee7d0d376a725fde2b6d951a37cb3062c6 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:25:59 +0300 Subject: usb: typec: More API for cable handling Thunderbolt 3, and probable USB4 too, will need to be able to get details about the cables. Adding typec_cable_get() function that the alternate mode drivers can use to gain access to gain access to the cable. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-4-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 0f52723a11bd..d95ea0d398b8 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -230,6 +230,10 @@ struct typec_cable *typec_register_cable(struct typec_port *port, struct typec_cable_desc *desc); void typec_unregister_cable(struct typec_cable *cable); +struct typec_cable *typec_cable_get(struct typec_port *port); +void typec_cable_put(struct typec_cable *cable); +int typec_cable_is_active(struct typec_cable *cable); + struct typec_plug *typec_register_plug(struct typec_cable *cable, struct typec_plug_desc *desc); void typec_unregister_plug(struct typec_plug *plug); -- cgit v1.2.3 From 2a127da461a9d8d97782d6e82b227041393eb4d2 Mon Sep 17 00:00:00 2001 From: Khouloud Touil Date: Tue, 7 Jan 2020 10:29:19 +0100 Subject: nvmem: add support for the write-protect pin The write-protect pin handling looks like a standard property that could benefit other users if available in the core nvmem framework. Instead of modifying all the memory drivers to check this pin, make the NVMEM subsystem check if the write-protect GPIO being passed through the nvmem_config or defined in the device tree and pull it low whenever writing to the memory. There was a suggestion for introducing the gpiodesc from pdata, but as pdata is already removed it could be replaced by adding it to nvmem_config. Reference: https://lists.96boards.org/pipermail/dev/2018-August/001056.html Signed-off-by: Khouloud Touil Reviewed-by: Linus Walleij Acked-by: Srinivas Kandagatla Signed-off-by: Bartosz Golaszewski --- include/linux/nvmem-provider.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index fe051323be0a..6d6f8e5d24c9 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -11,6 +11,7 @@ #include #include +#include struct nvmem_device; struct nvmem_cell_info; @@ -45,6 +46,7 @@ enum nvmem_type { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. + * @wp-gpio: Write protect pin * * Note: A default "nvmem" name will be assigned to the device if * no name is specified in its configuration. In such case "" is @@ -58,6 +60,7 @@ struct nvmem_config { const char *name; int id; struct module *owner; + struct gpio_desc *wp_gpio; const struct nvmem_cell_info *cells; int ncells; enum nvmem_type type; -- cgit v1.2.3 From 7823905de0c6c319995d710bb67f761681dc7e4e Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:26:04 +0300 Subject: usb: pd: Add definitions for the Enter_USB message Version 2.0 of the USB Power Delivery Specification R3.0 defines a new message called Enter_USB, which is made with USB4 in mind. Enter_USB message is in practice the same as the Enter Mode command (used when entering alternate modes) that just needs to be used when entering USB4 mode. The message does also support entering USB 2.0 or USB 3.2 mode instead of USB4 mode, but it is only required with USB4. I.e. with USB2 and USB3 Enter_USB message is optional. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-9-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index 145c38e351c2..a665d7f21142 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -45,7 +45,8 @@ enum pd_data_msg_type { PD_DATA_BATT_STATUS = 5, PD_DATA_ALERT = 6, PD_DATA_GET_COUNTRY_INFO = 7, - /* 8-14 Reserved */ + PD_DATA_ENTER_USB = 8, + /* 9-14 Reserved */ PD_DATA_VENDOR_DEF = 15, /* 16-31 Reserved */ }; @@ -418,6 +419,36 @@ static inline unsigned int rdo_max_power(u32 rdo) return ((rdo >> RDO_BATT_MAX_PWR_SHIFT) & RDO_PWR_MASK) * 250; } +/* Enter_USB Data Object */ +#define EUDO_USB_MODE_MASK GENMASK(30, 28) +#define EUDO_USB_MODE_SHIFT 28 +#define EUDO_USB_MODE_USB2 0 +#define EUDO_USB_MODE_USB3 1 +#define EUDO_USB_MODE_USB4 2 +#define EUDO_USB4_DRD BIT(26) +#define EUDO_USB3_DRD BIT(25) +#define EUDO_CABLE_SPEED_MASK GENMASK(23, 21) +#define EUDO_CABLE_SPEED_SHIFT 21 +#define EUDO_CABLE_SPEED_USB2 0 +#define EUDO_CABLE_SPEED_USB3_GEN1 1 +#define EUDO_CABLE_SPEED_USB4_GEN2 2 +#define EUDO_CABLE_SPEED_USB4_GEN3 3 +#define EUDO_CABLE_TYPE_MASK GENMASK(20, 19) +#define EUDO_CABLE_TYPE_SHIFT 19 +#define EUDO_CABLE_TYPE_PASSIVE 0 +#define EUDO_CABLE_TYPE_RE_TIMER 1 +#define EUDO_CABLE_TYPE_RE_DRIVER 2 +#define EUDO_CABLE_TYPE_OPTICAL 3 +#define EUDO_CABLE_CURRENT_MASK GENMASK(18, 17) +#define EUDO_CABLE_CURRENT_SHIFT 17 +#define EUDO_CABLE_CURRENT_NOTSUPP 0 +#define EUDO_CABLE_CURRENT_3A 2 +#define EUDO_CABLE_CURRENT_5A 3 +#define EUDO_PCIE_SUPPORT BIT(16) +#define EUDO_DP_SUPPORT BIT(15) +#define EUDO_TBT_SUPPORT BIT(14) +#define EUDO_HOST_PRESENT BIT(13) + /* USB PD timers and counters */ #define PD_T_NO_RESPONSE 5000 /* 4.5 - 5.5 seconds */ #define PD_T_DB_DETECT 10000 /* 10 - 15 seconds */ -- cgit v1.2.3 From d48ece0bce2d733c1c831d64751c0acaee1e8dc9 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:26:05 +0300 Subject: usb: pd: Add definition for DFP and UFP1 VDOs The latest version of the USB Power Delivery Specification R3.0 added UFP and DFP product types for the Discover Identity message. Both types can be used for example for checking the USB capability of the partner, which means the USB modes (USB 2.0, USB 3.0 and USB4) that the partner device supports. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-10-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd_vdo.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h index 781f4e98dd23..35b8e15efaa0 100644 --- a/include/linux/usb/pd_vdo.h +++ b/include/linux/usb/pd_vdo.h @@ -139,6 +139,38 @@ #define VDO_PRODUCT(pid, bcd) (((pid) & 0xffff) << 16 | ((bcd) & 0xffff)) #define PD_PRODUCT_PID(vdo) (((vdo) >> 16) & 0xffff) +/* + * UFP VDO1 + * -------- + * <31:29> :: UFP VDO version + * <28> :: Reserved + * <27:24> :: Device capability + * <23:6> :: Reserved + * <5:3> :: Alternate modes + * <2:0> :: USB highest speed + */ +#define PD_VDO1_UFP_DEVCAP(vdo) (((vdo) & GENMASK(27, 24)) >> 24) + +#define DEV_USB2_CAPABLE BIT(0) +#define DEV_USB2_BILLBOARD BIT(1) +#define DEV_USB3_CAPABLE BIT(2) +#define DEV_USB4_CAPABLE BIT(3) + +/* + * DFP VDO + * -------- + * <31:29> :: DFP VDO version + * <28:27> :: Reserved + * <26:24> :: Host capability + * <23:5> :: Reserved + * <4:0> :: Port number + */ +#define PD_VDO_DFP_HOSTCAP(vdo) (((vdo) & GENMASK(26, 24)) >> 24) + +#define HOST_USB2_CAPABLE BIT(0) +#define HOST_USB3_CAPABLE BIT(1) +#define HOST_USB4_CAPABLE BIT(2) + /* * Cable VDO * --------- -- cgit v1.2.3 From f6c56ca91b92088cf2f4075c1aa7c57ea89f7327 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:26:06 +0300 Subject: usb: typec: Add the Product Type VDOs to struct usb_pd_identity Discover Identity command response has also 3 product type specific VDOs on top of ID Header VDO, Cert Stat VDO and Product VDO. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-11-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index d95ea0d398b8..47595e96070e 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -74,6 +74,7 @@ enum typec_orientation { * @id_header: ID Header VDO * @cert_stat: Cert Stat VDO * @product: Product VDO + * @vdo: Product Type Specific VDOs * * USB power delivery Discover Identity command response data. * @@ -84,6 +85,7 @@ struct usb_pd_identity { u32 id_header; u32 cert_stat; u32 product; + u32 vdo[3]; }; int typec_partner_set_identity(struct typec_partner *partner); -- cgit v1.2.3 From 0ac53493296801b01c326507af3db093b95f6fb0 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:26:07 +0300 Subject: usb: typec: Add definitions for the latest specification releases Adding definitions for USB Type-C Specification Release 1.3, 1.4 and 2.0. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-12-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 47595e96070e..c358b3fd05c9 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -9,6 +9,9 @@ #define USB_TYPEC_REV_1_0 0x100 /* 1.0 */ #define USB_TYPEC_REV_1_1 0x110 /* 1.1 */ #define USB_TYPEC_REV_1_2 0x120 /* 1.2 */ +#define USB_TYPEC_REV_1_3 0x130 /* 1.3 */ +#define USB_TYPEC_REV_1_4 0x140 /* 1.4 */ +#define USB_TYPEC_REV_2_0 0x200 /* 2.0 */ struct typec_partner; struct typec_cable; -- cgit v1.2.3 From 87e3daa005cfba19433b5429bfbca9b848925507 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:26:08 +0300 Subject: usb: typec: Give the mux drivers all the details regarding the port state Passing all the details that the alternate mode drivers provide to the mux drivers during mode changes. The mux drivers will in practice need to be able to make decisions on their own. It is not enough that they get only the requested port state. With the Thunderbolt 3 alternate mode for example the mux driver will need to consider also the capabilities of the cable before configuring the mux. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-13-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_mux.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/typec_mux.h b/include/linux/usb/typec_mux.h index 873ace5b0cf8..be7292c0be5e 100644 --- a/include/linux/usb/typec_mux.h +++ b/include/linux/usb/typec_mux.h @@ -8,6 +8,7 @@ struct device; struct typec_mux; struct typec_switch; +struct typec_altmode; struct fwnode_handle; typedef int (*typec_switch_set_fn_t)(struct typec_switch *sw, @@ -29,7 +30,14 @@ void typec_switch_unregister(struct typec_switch *sw); void typec_switch_set_drvdata(struct typec_switch *sw, void *data); void *typec_switch_get_drvdata(struct typec_switch *sw); -typedef int (*typec_mux_set_fn_t)(struct typec_mux *mux, int state); +struct typec_mux_state { + struct typec_altmode *alt; + unsigned long mode; + void *data; +}; + +typedef int (*typec_mux_set_fn_t)(struct typec_mux *mux, + struct typec_mux_state *state); struct typec_mux_desc { struct fwnode_handle *fwnode; -- cgit v1.2.3 From 0f37a607091c30c2270d9065e8808a7d6ff34646 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Dec 2019 17:26:09 +0300 Subject: usb: typec: Provide definitions for the USB modes Defining the USB modes from the latest USB Power Delivery Specification - USB 2.0, USB 3.2 and USB4 - as special modal states just like the Accessory Modes. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191230142611.24921-14-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_altmode.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index fc57fd88004f..923ff3af0628 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -101,6 +101,22 @@ enum { TYPEC_MODE_DEBUG, /* Debug Accessory */ }; +/* + * USB4 also requires that the pins on the connector are repurposed, just like + * Alternate Modes. USB4 mode is however not entered with the Enter Mode Command + * like the Alternate Modes are, but instead with a special Enter_USB Message. + * The Enter_USB Message can also be used for setting to connector to operate in + * USB 3.2 or in USB 2.0 mode instead of USB4. + * + * The Enter_USB specific "USB Modes" are also supplied here as special modal + * state values, just like the Accessory Modes. + */ +enum { + TYPEC_MODE_USB2 = TYPEC_MODE_DEBUG, /* USB 2.0 mode */ + TYPEC_MODE_USB3, /* USB 3.2 mode */ + TYPEC_MODE_USB4 /* USB4 mode */ +}; + #define TYPEC_MODAL_STATE(_state_) ((_state_) + TYPEC_STATE_MODAL) struct typec_altmode *typec_altmode_get_plug(struct typec_altmode *altmode, -- cgit v1.2.3 From 18bd8bff69f7fbc53903dba4a1c234a30a8fcbde Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 6 Jan 2020 04:34:00 +0300 Subject: usb: phy: tegra: Keep track of power on-off state The PHY driver should keep track of the enable state, otherwise enable refcount is screwed if USB driver tries to enable PHY when it is already enabled. This will be the case for ChipIdea and Tegra EHCI drivers once PHY driver will gain support for the init/shutdown callbacks. Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20200106013416.9604-5-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 0c5c3ea8b2d7..3ae73bdc6245 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -78,6 +78,7 @@ struct tegra_usb_phy { bool is_ulpi_phy; int reset_gpio; struct reset_control *pad_rst; + bool powered_on; }; void tegra_usb_phy_preresume(struct usb_phy *phy); -- cgit v1.2.3 From dea75ee6c98474c966bb12164cdebc1daddcd86b Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 6 Jan 2020 04:34:06 +0300 Subject: usb: ulpi: Add resource-managed variant of otg_ulpi_create() Now drivers (like NVIDIA Tegra USB PHY for example) will be able to benefit from the resource-managed variant, making driver's code a bit cleaner. Suggested-by: Thierry Reding Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20200106013416.9604-11-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ulpi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h index c515765adab7..36c2982780ad 100644 --- a/include/linux/usb/ulpi.h +++ b/include/linux/usb/ulpi.h @@ -55,12 +55,23 @@ #if IS_ENABLED(CONFIG_USB_ULPI) struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, unsigned int flags); + +struct usb_phy *devm_otg_ulpi_create(struct device *dev, + struct usb_phy_io_ops *ops, + unsigned int flags); #else static inline struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, unsigned int flags) { return NULL; } + +static inline struct usb_phy *devm_otg_ulpi_create(struct device *dev, + struct usb_phy_io_ops *ops, + unsigned int flags) +{ + return NULL; +} #endif #ifdef CONFIG_USB_ULPI_VIEWPORT -- cgit v1.2.3 From 06e60e5038fa432900ffa956307459a1aabee1db Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 6 Jan 2020 04:34:09 +0300 Subject: usb: phy: tegra: Use device-tree notion of reset-GPIO's active-state It is much more intuitive if reset is treated as asserted when GPIO value is set to 1. All NVIDIA Tegra device-trees are properly specifying active state of the reset-GPIO since 2013, let's clean up that part of the code. Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20200106013416.9604-14-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 3ae73bdc6245..c29d1b4c9381 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -17,6 +17,7 @@ #define __TEGRA_USB_PHY_H #include +#include #include #include @@ -76,7 +77,7 @@ struct tegra_usb_phy { struct usb_phy u_phy; bool is_legacy_phy; bool is_ulpi_phy; - int reset_gpio; + struct gpio_desc *reset_gpio; struct reset_control *pad_rst; bool powered_on; }; -- cgit v1.2.3 From 577a2f41f4c7aced4fed41b20ee77cedd8c197cf Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 2 Jan 2020 21:42:16 +0100 Subject: cpuidle: Drop unused cpuidle_driver_ref/unref() functions The cpuidle_driver_ref() and cpuidle_driver_unref() functions are not used and the refcnt field in struct cpuidle_driver operated by them is not updated anywhere else (so it is permanently equal to 0), so drop both of them along with refcnt. Signed-off-by: Rafael J. Wysocki Acked-by: Daniel Lezcano --- include/linux/cpuidle.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 1dabe36bd011..23744d49bc22 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -115,7 +115,6 @@ DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev); struct cpuidle_driver { const char *name; struct module *owner; - int refcnt; /* used by the cpuidle framework to setup the broadcast timer */ unsigned int bctimer:1; @@ -147,8 +146,6 @@ extern u64 cpuidle_poll_time(struct cpuidle_driver *drv, extern int cpuidle_register_driver(struct cpuidle_driver *drv); extern struct cpuidle_driver *cpuidle_get_driver(void); -extern struct cpuidle_driver *cpuidle_driver_ref(void); -extern void cpuidle_driver_unref(void); extern void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx, bool disable); extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); @@ -186,8 +183,6 @@ static inline u64 cpuidle_poll_time(struct cpuidle_driver *drv, static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; } -static inline struct cpuidle_driver *cpuidle_driver_ref(void) {return NULL; } -static inline void cpuidle_driver_unref(void) {} static inline void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx, bool disable) { } static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } -- cgit v1.2.3 From 27ae7997a66174cb8afd6a75b3989f5e0c1b9e5a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Jan 2020 16:35:03 -0800 Subject: bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com --- include/linux/bpf.h | 30 ++++++++++++++++++++++++++++++ include/linux/bpf_types.h | 4 ++++ include/linux/btf.h | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b14e51d56a82..50f3b20ae284 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -349,6 +349,10 @@ struct bpf_verifier_ops { const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); + 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); }; struct bpf_prog_offload_ops { @@ -668,6 +672,32 @@ struct bpf_array_aux { struct work_struct work; }; +struct btf_type; +struct btf_member; + +#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 +struct bpf_struct_ops { + const struct bpf_verifier_ops *verifier_ops; + int (*init)(struct btf *btf); + int (*check_member)(const struct btf_type *t, + const struct btf_member *member); + const struct btf_type *type; + const char *name; + struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; + u32 type_id; +}; + +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); +void bpf_struct_ops_init(struct btf *btf); +#else +static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +{ + return NULL; +} +static inline void bpf_struct_ops_init(struct btf *btf) { } +#endif + struct bpf_array { struct bpf_map map; u32 elem_size; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 93740b3614d7..fadd243ffa2d 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -65,6 +65,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2, BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, struct sk_reuseport_md, struct sk_reuseport_kern) #endif +#if defined(CONFIG_BPF_JIT) +BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops, + void *, void *) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/btf.h b/include/linux/btf.h index 79d4abc2556a..f74a09a7120b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -53,6 +53,18 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); +s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); +const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, + u32 id, u32 *res_id); +const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, + u32 id, u32 *res_id); +const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, + u32 id, u32 *res_id); + +#define for_each_member(i, struct_type, member) \ + for (i = 0, member = btf_type_member(struct_type); \ + i < btf_type_vlen(struct_type); \ + i++, member++) static inline bool btf_type_is_ptr(const struct btf_type *t) { @@ -84,6 +96,28 @@ 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 u16 btf_type_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline bool btf_type_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, + const struct btf_member *member) +{ + return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) + : 0; +} + +static inline const struct btf_member *btf_type_member(const struct btf_type *t) +{ + return (const struct btf_member *)(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); -- cgit v1.2.3 From 85d33df357b634649ddbe0a20fd2d0fc5732c3cb Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Jan 2020 16:35:05 -0800 Subject: bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com --- include/linux/bpf.h | 49 +++++++++++++++++++++++++++++++++++++++++++++-- include/linux/bpf_types.h | 3 +++ include/linux/btf.h | 13 +++++++++++++ 3 files changed, 63 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 50f3b20ae284..a7bfe8a388c6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -17,6 +17,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -106,6 +107,7 @@ struct bpf_map { struct btf *btf; struct bpf_map_memory memory; char name[BPF_OBJ_NAME_LEN]; + u32 btf_vmlinux_value_type_id; bool unpriv_array; bool frozen; /* write-once; write-protected by freeze_mutex */ /* 22 bytes hole */ @@ -183,7 +185,8 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map) static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { - return map->btf && map->ops->map_seq_show_elem; + return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) && + map->ops->map_seq_show_elem; } int map_check_no_btf(const struct bpf_map *map, @@ -441,7 +444,8 @@ struct btf_func_model { * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ -int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, +int arch_prepare_bpf_trampoline(void *image, void *image_end, + const struct btf_func_model *m, u32 flags, struct bpf_prog **fentry_progs, int fentry_cnt, struct bpf_prog **fexit_progs, int fexit_cnt, void *orig_call); @@ -672,6 +676,7 @@ struct bpf_array_aux { struct work_struct work; }; +struct bpf_struct_ops_value; struct btf_type; struct btf_member; @@ -681,21 +686,61 @@ struct bpf_struct_ops { int (*init)(struct btf *btf); int (*check_member)(const struct btf_type *t, const struct btf_member *member); + int (*init_member)(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata); + int (*reg)(void *kdata); + void (*unreg)(void *kdata); const struct btf_type *type; + const struct btf_type *value_type; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; u32 type_id; + u32 value_id; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +#define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); void bpf_struct_ops_init(struct btf *btf); +bool bpf_struct_ops_get(const void *kdata); +void bpf_struct_ops_put(const void *kdata); +int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, + void *value); +static inline bool bpf_try_module_get(const void *data, struct module *owner) +{ + if (owner == BPF_MODULE_OWNER) + return bpf_struct_ops_get(data); + else + return try_module_get(owner); +} +static inline void bpf_module_put(const void *data, struct module *owner) +{ + if (owner == BPF_MODULE_OWNER) + bpf_struct_ops_put(data); + else + module_put(owner); +} #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { return NULL; } static inline void bpf_struct_ops_init(struct btf *btf) { } +static inline bool bpf_try_module_get(const void *data, struct module *owner) +{ + return try_module_get(owner); +} +static inline void bpf_module_put(const void *data, struct module *owner) +{ + module_put(owner); +} +static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, + void *key, + void *value) +{ + return -EINVAL; +} #endif struct bpf_array { diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fadd243ffa2d..9f326e6ef885 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -109,3 +109,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) +#if defined(CONFIG_BPF_JIT) +BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) +#endif diff --git a/include/linux/btf.h b/include/linux/btf.h index f74a09a7120b..881e9b76ef49 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -7,6 +7,8 @@ #include #include +#define BTF_TYPE_EMIT(type) ((void)(type *)0) + struct btf; struct btf_member; struct btf_type; @@ -60,6 +62,10 @@ const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, u32 id, u32 *res_id); 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); #define for_each_member(i, struct_type, member) \ for (i = 0, member = btf_type_member(struct_type); \ @@ -106,6 +112,13 @@ static inline bool btf_type_kflag(const struct btf_type *t) return BTF_INFO_KFLAG(t->info); } +static inline u32 btf_member_bit_offset(const struct btf_type *struct_type, + const struct btf_member *member) +{ + return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) + : member->offset; +} + static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, const struct btf_member *member) { -- cgit v1.2.3 From 0baf26b0fcd74bbfcef53c5d5e8bad2b99c8d0d2 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Jan 2020 16:35:08 -0800 Subject: bpf: tcp: Support tcp_congestion_ops in bpf This patch makes "struct tcp_congestion_ops" to be the first user of BPF STRUCT_OPS. It allows implementing a tcp_congestion_ops in bpf. The BPF implemented tcp_congestion_ops can be used like regular kernel tcp-cc through sysctl and setsockopt. e.g. [root@arch-fb-vm1 bpf]# sysctl -a | egrep congestion net.ipv4.tcp_allowed_congestion_control = reno cubic bpf_cubic net.ipv4.tcp_available_congestion_control = reno bic cubic bpf_cubic net.ipv4.tcp_congestion_control = bpf_cubic There has been attempt to move the TCP CC to the user space (e.g. CCP in TCP). The common arguments are faster turn around, get away from long-tail kernel versions in production...etc, which are legit points. BPF has been the continuous effort to join both kernel and userspace upsides together (e.g. XDP to gain the performance advantage without bypassing the kernel). The recent BPF advancements (in particular BTF-aware verifier, BPF trampoline, BPF CO-RE...) made implementing kernel struct ops (e.g. tcp cc) possible in BPF. It allows a faster turnaround for testing algorithm in the production while leveraging the existing (and continue growing) BPF feature/framework instead of building one specifically for userspace TCP CC. This patch allows write access to a few fields in tcp-sock (in bpf_tcp_ca_btf_struct_access()). The optional "get_info" is unsupported now. It can be added later. One possible way is to output the info with a btf-id to describe the content. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200109003508.3856115-1-kafai@fb.com --- include/linux/filter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 70e6dd960bca..a366a0b64a57 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -843,6 +843,8 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); +const struct bpf_func_proto * +bpf_base_func_proto(enum bpf_func_id func_id); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); -- cgit v1.2.3 From ea78979d302f7de9bbd59f9dafdb070ecb05ec39 Mon Sep 17 00:00:00 2001 From: Lakshmi Ramasubramanian Date: Wed, 8 Jan 2020 08:05:08 -0800 Subject: IMA: fix measuring asymmetric keys Kconfig As a result of the asymmetric public keys subtype Kconfig option being defined as tristate, with the existing IMA Makefile, ima_asymmetric_keys.c could be built as a kernel module. To prevent this from happening, this patch defines and uses an intermediate Kconfig boolean option named IMA_MEASURE_ASYMMETRIC_KEYS. Signed-off-by: Lakshmi Ramasubramanian Suggested-by: James.Bottomley Cc: David Howells Cc: Jarkko Sakkinen Reported-by: kbuild test robot # ima_asymmetric_keys.c is built as a kernel module. Fixes: 88e70da170e8 ("IMA: Define an IMA hook to measure keys") Fixes: cb1aa3823c92 ("KEYS: Call the IMA hook to measure keys") [zohar@linux.ibm.com: updated patch description] Signed-off-by: Mimi Zohar --- include/linux/ima.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 3b89136bc218..f4644c54f648 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -101,7 +101,7 @@ static inline void ima_add_kexec_buffer(struct kimage *image) {} #endif -#if defined(CONFIG_IMA) && defined(CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE) +#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS extern void ima_post_key_create_or_update(struct key *keyring, struct key *key, const void *payload, size_t plen, @@ -113,7 +113,7 @@ static inline void ima_post_key_create_or_update(struct key *keyring, size_t plen, unsigned long flags, bool create) {} -#endif /* CONFIG_IMA && CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE */ +#endif /* CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS */ #ifdef CONFIG_IMA_APPRAISE extern bool is_ima_appraise_enabled(void); -- cgit v1.2.3 From 44f45994f438b4f4e0ba977b173980268983c60f Mon Sep 17 00:00:00 2001 From: Amir Mahdi Ghorbanian Date: Thu, 2 Jan 2020 12:10:08 -0500 Subject: mtd: onenand: omap2: Fix errors in style Correct mispelling, spacing, and coding style flaws caught by checkpatch.pl script in the Omap2 Onenand driver . Signed-off-by: Amir Mahdi Ghorbanian Signed-off-by: Miquel Raynal --- include/linux/mtd/flashchip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index ecc88a41792a..c04f690871ca 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -40,7 +40,7 @@ typedef enum { FL_READING, FL_CACHEDPRG, /* These 4 come from onenand_state_t, which has been unified here */ - FL_RESETING, + FL_RESETTING, FL_OTPING, FL_PREPARING_ERASE, FL_VERIFYING_ERASE, -- cgit v1.2.3 From 50816a4c39263913d8cfd1ee32f90102679606c6 Mon Sep 17 00:00:00 2001 From: Sameer Pujar Date: Thu, 9 Jan 2020 10:39:50 +0530 Subject: regmap: add iopoll-like atomic polling macro This patch adds a macro 'regmap_read_poll_timeout_atomic' that works similar to 'readx_poll_timeout_atomic' defined in linux/iopoll.h; This is atomic version of already available 'regmap_read_poll_timeout' macro. It should be noted that above atomic macro cannot be used by all regmaps. If the regmap is set up for atomic use (flat or no cache and MMIO) then only it can use. Signed-off-by: Sameer Pujar Link: https://lore.kernel.org/r/1578546590-24737-1-git-send-email-spujar@nvidia.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index dfe493ac692d..f0a092a1a96d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -144,6 +144,51 @@ struct reg_sequence { __ret ?: ((cond) ? 0 : -ETIMEDOUT); \ }) +/** + * regmap_read_poll_timeout_atomic - Poll until a condition is met or a timeout occurs + * + * @map: Regmap to read from + * @addr: Address to poll + * @val: Unsigned integer 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 be less than ~10us since udelay is used + * (see Documentation/timers/timers-howto.rst). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * error return value in case of a error read. In the two former cases, + * the last read value at @addr is stored in @val. + * + * This is modelled after the readx_poll_timeout_atomic macros in linux/iopoll.h. + * + * Note: In general regmap cannot be used in atomic context. If you want to use + * this macro then first setup your regmap for atomic use (flat or no cache + * and MMIO regmap). + */ +#define regmap_read_poll_timeout_atomic(map, addr, val, cond, delay_us, timeout_us) \ +({ \ + u64 __timeout_us = (timeout_us); \ + unsigned long __delay_us = (delay_us); \ + ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ + int __ret; \ + for (;;) { \ + __ret = regmap_read((map), (addr), &(val)); \ + if (__ret) \ + break; \ + if (cond) \ + break; \ + if ((__timeout_us) && \ + ktime_compare(ktime_get(), __timeout) > 0) { \ + __ret = regmap_read((map), (addr), &(val)); \ + break; \ + } \ + if (__delay_us) \ + udelay(__delay_us); \ + } \ + __ret ?: ((cond) ? 0 : -ETIMEDOUT); \ +}) + /** * regmap_field_read_poll_timeout - Poll until a condition is met or timeout * -- cgit v1.2.3 From 3ee17bc78e0f3fdeff9890993e8f3a9f5145163b Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Thu, 9 Jan 2020 07:59:19 -0800 Subject: mptcp: Add MPTCP to skb extensions Add enum value for MPTCP and update config dependencies v5 -> v6: - fixed '__unused' field size Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 64e5b1be9ff5..f5c27600b410 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4096,6 +4096,9 @@ enum skb_ext_id { #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, +#endif +#if IS_ENABLED(CONFIG_MPTCP) + SKB_EXT_MPTCP, #endif SKB_EXT_NUM, /* must be last */ }; -- cgit v1.2.3 From 8b69a803814bb8b14155ea60df83f6d57527e69e Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Jan 2020 07:59:24 -0800 Subject: skb: add helpers to allocate ext independently from sk_buff Currently we can allocate the extension only after the skb, this change allows the user to do the opposite, will simplify allocation failure handling from MPTCP. Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f5c27600b410..016b3c4ab99a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4120,6 +4120,9 @@ struct skb_ext { char data[0] __aligned(8); }; +struct skb_ext *__skb_ext_alloc(void); +void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, + struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); -- cgit v1.2.3 From fc10cca69ee8af49778ad76c1e5fddf83d5026c8 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 9 Jan 2020 14:08:41 +0000 Subject: drivers/iommu: Initialise module 'owner' field in iommu_device_set_ops() Requiring each IOMMU driver to initialise the 'owner' field of their 'struct iommu_ops' is error-prone and easily forgotten. Follow the example set by PCI and USB by assigning THIS_MODULE automatically when registering the ops structure with IOMMU core. Reviewed-by: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Will Deacon --- include/linux/iommu.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e9f94d3f7a04..90007c92ad2d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -388,12 +388,19 @@ void iommu_device_sysfs_remove(struct iommu_device *iommu); int iommu_device_link(struct iommu_device *iommu, struct device *link); void iommu_device_unlink(struct iommu_device *iommu, struct device *link); -static inline void iommu_device_set_ops(struct iommu_device *iommu, - const struct iommu_ops *ops) +static inline void __iommu_device_set_ops(struct iommu_device *iommu, + const struct iommu_ops *ops) { iommu->ops = ops; } +#define iommu_device_set_ops(iommu, ops) \ +do { \ + struct iommu_ops *__ops = (struct iommu_ops *)(ops); \ + __ops->owner = THIS_MODULE; \ + __iommu_device_set_ops(iommu, __ops); \ +} while (0) + static inline void iommu_device_set_fwnode(struct iommu_device *iommu, struct fwnode_handle *fwnode) { -- cgit v1.2.3 From 2daa86e78c494d06d0aac231e4533f3dc50fa432 Mon Sep 17 00:00:00 2001 From: Leonid Maksymchuk Date: Sun, 15 Dec 2019 16:26:34 +0200 Subject: platform/x86: asus_wmi: Support throttle thermal policy Throttle thermal policy ACPI device is used to control CPU cooling and throttling. This patch adds sysfs entry for setting current mode and Fn+F5 hotkey that switches to next. Policy modes: * 0x00 - default * 0x01 - overboost * 0x02 - silent Signed-off-by: Leonid Maksymchuk Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 60249e22e844..d39fc658c320 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -58,6 +58,7 @@ #define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ #define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 #define ASUS_WMI_DEVID_FAN_BOOST_MODE 0x00110018 +#define ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY 0x00120075 /* Misc */ #define ASUS_WMI_DEVID_CAMERA 0x00060013 -- cgit v1.2.3 From 608f43ad27ab26700677cc4d9ead3b2d9d338a21 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 2 Dec 2019 10:51:58 +0100 Subject: gpu: host1x: Rename "parent" to "host" Rename the host1x clients' parent to "host" because that more closely describes what it is. The parent can be confused with the parent device in terms of the device hierarchy. Subsequent patches will add a new member that refers to the parent in that hierarchy. Signed-off-by: Thierry Reding --- include/linux/host1x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 6f8d772591ba..b673d6198e05 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -33,7 +33,7 @@ struct host1x_client_ops { /** * struct host1x_client - host1x client structure * @list: list node for the host1x client - * @parent: pointer to struct device representing the host1x controller + * @host: pointer to struct device representing the host1x controller * @dev: pointer to struct device backing this host1x client * @group: IOMMU group that this client is a member of * @ops: host1x client operations @@ -44,7 +44,7 @@ struct host1x_client_ops { */ struct host1x_client { struct list_head list; - struct device *parent; + struct device *host; struct device *dev; struct iommu_group *group; -- cgit v1.2.3 From fd67e9c6ed5af223af0daee093593abe3dbb53d4 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 2 Dec 2019 15:29:03 +0100 Subject: drm/tegra: Do not implement runtime PM The Tegra DRM driver heavily relies on the implementations for runtime suspend/resume to be called at specific times. Unfortunately, there are some cases where that doesn't work. One example is if the user disables runtime PM for a given subdevice. Another example is that the PM core acquires a reference to runtime PM during system sleep, effectively preventing devices from going into low power modes. This is intentional to avoid nasty race conditions, but it also causes system sleep to not function properly on all Tegra systems. Fix this by not implementing runtime PM at all. Instead, a minimal, reference-counted suspend/resume infrastructure is added to the host1x bus. This has the benefit that it can be used regardless of the system power state (or any transitions we might be in), or whether or not the user allows runtime PM. Atomic modesetting guarantees that these functions will end up being called at the right point in time, so the pitfalls for the more generic runtime PM do not apply here. Signed-off-by: Thierry Reding --- include/linux/host1x.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index b673d6198e05..325dabe4dd36 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -24,10 +24,14 @@ struct iommu_group; * struct host1x_client_ops - host1x client operations * @init: host1x client initialization code * @exit: host1x client tear down code + * @suspend: host1x client suspend code + * @resume: host1x client resume code */ struct host1x_client_ops { int (*init)(struct host1x_client *client); int (*exit)(struct host1x_client *client); + int (*suspend)(struct host1x_client *client); + int (*resume)(struct host1x_client *client); }; /** @@ -55,6 +59,10 @@ struct host1x_client { struct host1x_syncpt **syncpts; unsigned int num_syncpts; + + struct host1x_client *parent; + unsigned int usecount; + struct mutex lock; }; /* @@ -322,6 +330,9 @@ int host1x_device_exit(struct host1x_device *device); int host1x_client_register(struct host1x_client *client); int host1x_client_unregister(struct host1x_client *client); +int host1x_client_suspend(struct host1x_client *client); +int host1x_client_resume(struct host1x_client *client); + struct tegra_mipi_device; struct tegra_mipi_device *tegra_mipi_request(struct device *device); -- cgit v1.2.3 From d1e5f26f14272b5039cc198569ec4fabed14e6db Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 25 Oct 2019 19:08:37 +0100 Subject: iommu/io-pgtable-arm: Rationalise TTBRn handling TTBR1 values have so far been redundant since no users implement any support for split address spaces. Crucially, though, one of the main reasons for wanting to do so is to be able to manage each half entirely independently, e.g. context-switching one set of mappings without disturbing the other. Thus it seems unlikely that tying two tables together in a single io_pgtable_cfg would ever be particularly desirable or useful. Streamline the configs to just a single conceptual TTBR value representing the allocated table. This paves the way for future users to support split address spaces by simply allocating a table and dealing with the detailed TTBRn logistics themselves. Tested-by: Jordan Crouse Signed-off-by: Robin Murphy [will: Drop change to ttbr value] Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ee21eedafe98..53bca5343f52 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -100,7 +100,7 @@ struct io_pgtable_cfg { /* Low-level data specific to the table format */ union { struct { - u64 ttbr[2]; + u64 ttbr; u64 tcr; u64 mair; } arm_lpae_s1_cfg; @@ -111,7 +111,7 @@ struct io_pgtable_cfg { } arm_lpae_s2_cfg; struct { - u32 ttbr[2]; + u32 ttbr; u32 tcr; u32 nmrr; u32 prrr; -- cgit v1.2.3 From fb485eb18e632ff1071662122b9d9b7d40c23c73 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 25 Oct 2019 19:08:38 +0100 Subject: iommu/io-pgtable-arm: Rationalise TCR handling Although it's conceptually nice for the io_pgtable_cfg to provide a standard VMSA TCR value, the reality is that no VMSA-compliant IOMMU looks exactly like an Arm CPU, and they all have various other TCR controls which io-pgtable can't be expected to understand. Thus since there is an expectation that drivers will have to add to the given TCR value anyway, let's strip it down to just the essentials that are directly relevant to io-pgtable's inner workings - namely the various sizes and the walk attributes. Tested-by: Jordan Crouse Signed-off-by: Robin Murphy [will: Add missing include of bitfield.h] Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 53bca5343f52..6ae104cedfd7 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -101,7 +101,14 @@ struct io_pgtable_cfg { union { struct { u64 ttbr; - u64 tcr; + struct { + u32 ips:3; + u32 tg:2; + u32 sh:2; + u32 orgn:2; + u32 irgn:2; + u32 tsz:6; + } tcr; u64 mair; } arm_lpae_s1_cfg; -- cgit v1.2.3 From ac4b80e5b9d0ecf906300d79e4dc4df5526579a8 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 10 Jan 2020 14:51:59 +0000 Subject: iommu/io-pgtable-arm: Rationalise VTCR handling Commit 05a648cd2dd7 ("iommu/io-pgtable-arm: Rationalise TCR handling") reworked the way in which the TCR register value is returned from the io-pgtable code when targetting the Arm long-descriptor format, in preparation for allowing page-tables to target TTBR1. As it turns out, the new interface is a lot nicer to use, so do the same conversion for the VTCR register even though there is only a single base register for stage-2 translation. Cc: Robin Murphy Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 6ae104cedfd7..40c1b7745fb6 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -114,7 +114,15 @@ struct io_pgtable_cfg { struct { u64 vttbr; - u64 vtcr; + struct { + u32 ps:3; + u32 tg:2; + u32 sh:2; + u32 orgn:2; + u32 irgn:2; + u32 sl:2; + u32 tsz:6; + } vtcr; } arm_lpae_s2_cfg; struct { -- cgit v1.2.3 From db6903010aa5b7691d8234a179f4cf71a119445a Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 25 Oct 2019 19:08:39 +0100 Subject: iommu/io-pgtable-arm: Prepare for TTBR1 usage Now that we can correctly extract top-level indices without relying on the remaining upper bits being zero, the only remaining impediments to using a given table for TTBR1 are the address validation on map/unmap and the awkward TCR translation granule format. Add a quirk so that we can do the right thing at those points. Tested-by: Jordan Crouse Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 40c1b7745fb6..53d53c6c2be9 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -83,12 +83,16 @@ struct io_pgtable_cfg { * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs * on unmap, for DMA domains using the flush queue mechanism for * delayed invalidation. + * + * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table + * for use in the upper half of a split address space. */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) #define IO_PGTABLE_QUIRK_TLBI_ON_MAP BIT(2) #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) #define IO_PGTABLE_QUIRK_NON_STRICT BIT(4) + #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; -- cgit v1.2.3 From 51c39bb1d5d105a02e29aa7960f0a395086e6342 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 9 Jan 2020 22:41:20 -0800 Subject: bpf: Introduce function-by-function verification New llvm and old llvm with libbpf help produce BTF that distinguish global and static functions. Unlike arguments of static function the arguments of global functions cannot be removed or optimized away by llvm. The compiler has to use exactly the arguments specified in a function prototype. The argument type information allows the verifier validate each global function independently. For now only supported argument types are pointer to context and scalars. In the future pointers to structures, sizes, pointer to packet data can be supported as well. Consider the following example: static int f1(int ...) { ... } int f3(int b); int f2(int a) { f1(a) + f3(a); } int f3(int b) { ... } int main(...) { f1(...) + f2(...) + f3(...); } The verifier will start its safety checks from the first global function f2(). It will recursively descend into f1() because it's static. Then it will check that arguments match for the f3() invocation inside f2(). It will not descend into f3(). It will finish f2() that has to be successfully verified for all possible values of 'a'. Then it will proceed with f3(). That function also has to be safe for all possible values of 'b'. Then it will start subprog 0 (which is main() function). It will recursively descend into f1() and will skip full check of f2() and f3(), since they are global. The order of processing global functions doesn't affect safety, since all global functions must be proven safe based on their arguments only. Such function by function verification can drastically improve speed of the verification and reduce complexity. Note that the stack limit of 512 still applies to the call chain regardless whether functions were static or global. The nested level of 8 also still applies. The same recursion prevention checks are in place as well. The type information and static/global kind is preserved after the verification hence in the above example global function f2() and f3() can be replaced later by equivalent functions with the same types that are loaded and verified later without affecting safety of this main() program. Such replacement (re-linking) of global functions is a subject of future patches. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200110064124.1760511-3-ast@kernel.org --- include/linux/bpf.h | 7 ++++++- include/linux/bpf_verifier.h | 10 ++++++++-- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a7bfe8a388c6..aed2bc39d72b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -566,6 +566,7 @@ static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, #endif struct bpf_func_info_aux { + u16 linkage; bool unreliable; }; @@ -1081,7 +1082,11 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); -int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog); +struct bpf_reg_state; +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); struct bpf_prog *bpf_prog_by_id(u32 id); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 26e40de9ef55..5406e6e96585 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -304,11 +304,13 @@ struct bpf_insn_aux_data { u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ - bool seen; /* this insn was processed by the verifier */ + u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ - bool prune_point; + + /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ + bool prune_point; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -379,6 +381,7 @@ struct bpf_verifier_env { int *insn_stack; int cur_stack; } cfg; + u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ u32 prev_insn_processed, insn_processed; @@ -428,4 +431,7 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, void 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); + #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From 8e20fc3917117b42de316e87f073a1ca43d94c9f Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Thu, 9 Jan 2020 21:54:42 +0000 Subject: serial_core: Move sysrq functions from header file It's not worth to have them in every serial driver and I'm about to add another helper function. Signed-off-by: Dmitry Safonov Link: https://lore.kernel.org/r/20200109215444.95995-2-dima@arista.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 84 +++------------------------------------------ 1 file changed, 5 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9cf1682dc580..255e86a474e9 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -460,85 +460,11 @@ extern void uart_handle_cts_change(struct uart_port *uport, extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); -static inline int -uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) -{ - if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL)) - return 0; - - if (!port->has_sysrq || !port->sysrq) - return 0; - - if (ch && time_before(jiffies, port->sysrq)) { - handle_sysrq(ch); - port->sysrq = 0; - return 1; - } - port->sysrq = 0; - - return 0; -} -static inline int -uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) -{ - if (!IS_ENABLED(CONFIG_MAGIC_SYSRQ_SERIAL)) - return 0; - - if (!port->has_sysrq || !port->sysrq) - return 0; - - if (ch && time_before(jiffies, port->sysrq)) { - port->sysrq_ch = ch; - port->sysrq = 0; - return 1; - } - port->sysrq = 0; - - return 0; -} -static inline void -uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) -{ - int sysrq_ch; - - if (!port->has_sysrq) { - spin_unlock_irqrestore(&port->lock, irqflags); - return; - } - - sysrq_ch = port->sysrq_ch; - port->sysrq_ch = 0; - - spin_unlock_irqrestore(&port->lock, irqflags); - - if (sysrq_ch) - handle_sysrq(sysrq_ch); -} - -/* - * We do the SysRQ and SAK checking like this... - */ -static inline int uart_handle_break(struct uart_port *port) -{ - struct uart_state *state = port->state; - - if (port->handle_break) - port->handle_break(port); - - if (port->has_sysrq) { - if (port->cons && port->cons->index == port->line) { - if (!port->sysrq) { - port->sysrq = jiffies + HZ*5; - return 1; - } - port->sysrq = 0; - } - } - - if (port->flags & UPF_SAK) - do_SAK(state->port.tty); - return 0; -} +extern int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch); +extern int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch); +extern void uart_unlock_and_check_sysrq(struct uart_port *port, + unsigned long irqflags); +extern int uart_handle_break(struct uart_port *port); /* * UART_ENABLE_MS - determine if port should enable modem status irqs -- cgit v1.2.3 From 89ed486532c4d155565cc4b7984a918ee3c58f80 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 3 Jan 2020 12:39:38 +0100 Subject: efi/x86: Avoid redundant cast of EFI firmware service pointer All EFI firmware call prototypes have been annotated as __efiapi, permitting us to attach attributes regarding the calling convention by overriding __efiapi to an architecture specific value. On 32-bit x86, EFI firmware calls use the plain calling convention where all arguments are passed via the stack, and cleaned up by the caller. Let's add this to the __efiapi definition so we no longer need to cast the function pointers before invoking them. Signed-off-by: Ard Biesheuvel Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arvind Sankar Cc: Matthew Garrett Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20200103113953.9571-6-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 726673e98990..952c1659dfd9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -48,8 +48,10 @@ typedef u16 efi_char16_t; /* UNICODE character */ typedef u64 efi_physical_addr_t; typedef void *efi_handle_t; -#ifdef CONFIG_X86_64 +#if defined(CONFIG_X86_64) #define __efiapi __attribute__((ms_abi)) +#elif defined(CONFIG_X86_32) +#define __efiapi __attribute__((regparm(0))) #else #define __efiapi #endif -- cgit v1.2.3 From 33b85447fa61946b94fea93dd4bc24772af14d54 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 3 Jan 2020 12:39:44 +0100 Subject: efi/x86: Drop two near identical versions of efi_runtime_init() The routines efi_runtime_init32() and efi_runtime_init64() are almost indistinguishable, and the only relevant difference is the offset in the runtime struct from where to obtain the physical address of the SetVirtualAddressMap() routine. However, this address is only used once, when installing the virtual address map that the OS will use to invoke EFI runtime services, and at the time of the call, we will necessarily be running with a 1:1 mapping, and so there is no need to do the map/unmap dance here to retrieve the address. In fact, in the preceding changes to these users, we stopped using the address recorded here entirely. So let's just get rid of all this code since it no longer serves a purpose. While at it, tweak the logic so that we handle unsupported and disable EFI runtime services in the same way, and unmap the EFI memory map in both cases. Signed-off-by: Ard Biesheuvel Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arvind Sankar Cc: Matthew Garrett Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20200103113953.9571-12-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 952c1659dfd9..ee68ea6f85ff 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -539,24 +539,6 @@ typedef struct { u32 query_variable_info; } efi_runtime_services_32_t; -typedef struct { - efi_table_hdr_t hdr; - u64 get_time; - u64 set_time; - u64 get_wakeup_time; - u64 set_wakeup_time; - u64 set_virtual_address_map; - u64 convert_pointer; - u64 get_variable; - u64 get_next_variable; - u64 set_variable; - u64 get_next_high_mono_count; - u64 reset_system; - u64 update_capsule; - u64 query_capsule_caps; - u64 query_variable_info; -} efi_runtime_services_64_t; - typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc); typedef efi_status_t efi_set_time_t (efi_time_t *tm); typedef efi_status_t efi_get_wakeup_time_t (efi_bool_t *enabled, efi_bool_t *pending, @@ -946,7 +928,6 @@ extern struct efi { efi_query_capsule_caps_t *query_capsule_caps; efi_get_next_high_mono_count_t *get_next_high_mono_count; efi_reset_system_t *reset_system; - efi_set_virtual_address_map_t *set_virtual_address_map; struct efi_memory_map memmap; unsigned long flags; } efi; -- cgit v1.2.3 From 4444f8541dad16fefd9b8807ad1451e806ef1d94 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Fri, 3 Jan 2020 12:39:50 +0100 Subject: efi: Allow disabling PCI busmastering on bridges during boot Add an option to disable the busmaster bit in the control register on all PCI bridges before calling ExitBootServices() and passing control to the runtime kernel. System firmware may configure the IOMMU to prevent malicious PCI devices from being able to attack the OS via DMA. However, since firmware can't guarantee that the OS is IOMMU-aware, it will tear down IOMMU configuration when ExitBootServices() is called. This leaves a window between where a hostile device could still cause damage before Linux configures the IOMMU again. If CONFIG_EFI_DISABLE_PCI_DMA is enabled or "efi=disable_early_pci_dma" is passed on the command line, the EFI stub will clear the busmaster bit on all PCI bridges before ExitBootServices() is called. This will prevent any malicious PCI devices from being able to perform DMA until the kernel reenables busmastering after configuring the IOMMU. This option may cause failures with some poorly behaved hardware and should not be enabled without testing. The kernel commandline options "efi=disable_early_pci_dma" or "efi=no_disable_early_pci_dma" may be used to override the default. Note that PCI devices downstream from PCI bridges are disconnected from their drivers first, using the UEFI driver model API, so that DMA can be disabled safely at the bridge level. [ardb: disconnect PCI I/O handles first, as suggested by Arvind] Co-developed-by: Matthew Garrett Signed-off-by: Matthew Garrett Signed-off-by: Ard Biesheuvel Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arvind Sankar Cc: Matthew Garrett Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20200103113953.9571-18-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index ee68ea6f85ff..7e8e25b1d11c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -319,7 +319,9 @@ typedef union { void *stall; void *set_watchdog_timer; void *connect_controller; - void *disconnect_controller; + efi_status_t (__efiapi *disconnect_controller)(efi_handle_t, + efi_handle_t, + efi_handle_t); void *open_protocol; void *close_protocol; void *open_protocol_information; @@ -1692,4 +1694,6 @@ struct linux_efi_memreserve { #define EFI_MEMRESERVE_COUNT(size) (((size) - sizeof(struct linux_efi_memreserve)) \ / sizeof(((struct linux_efi_memreserve *)0)->entry[0])) +void efi_pci_disable_bridge_busmaster(void); + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 90fbca5952436e7817910b33eb4464ddd77a8964 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 12 Dec 2019 13:09:24 +0200 Subject: net/mlx5: Add Virtio Emulation related device capabilities Add Virtio Emulation related fields to the device capabilities. It includes a general bit to indicate whether Virtio Emulation is supported and the capabilities structure itself. Signed-off-by: Yishai Hadas Reviewed-by: Shahaf Shuler Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5d54fccf87fc..c6abaf4f1c55 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -87,6 +87,7 @@ enum { enum { MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), + MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), }; enum { @@ -953,6 +954,19 @@ struct mlx5_ifc_device_event_cap_bits { u8 user_unaffiliated_events[4][0x40]; }; +struct mlx5_ifc_device_virtio_emulation_cap_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x13]; + u8 log_doorbell_stride[0x5]; + u8 reserved_at_38[0x3]; + u8 log_doorbell_bar_size[0x5]; + + u8 doorbell_bar_offset[0x40]; + + u8 reserved_at_80[0x780]; +}; + enum { MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0, MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2, @@ -2751,6 +2765,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_fpga_cap_bits fpga_cap; struct mlx5_ifc_tls_cap_bits tls_cap; struct mlx5_ifc_device_mem_cap_bits device_mem_cap; + struct mlx5_ifc_device_virtio_emulation_cap_bits virtio_emulation_cap; u8 reserved_at_0[0x8000]; }; -- cgit v1.2.3 From ca1992c62cadb6c8e1e1b47e197b550f3cd89b76 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 12 Dec 2019 13:09:25 +0200 Subject: net/mlx5: Expose vDPA emulation device capabilities Expose vDPA emulation device capabilities from the core layer. It includes reading the capabilities from the firmware and exposing helper functions to access the data. Signed-off-by: Yishai Hadas Reviewed-by: Shahaf Shuler Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index cc1c230f10ee..1a1c53f0262d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1105,6 +1105,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_MEM, MLX5_CAP_RESERVED_16, MLX5_CAP_TLS, + MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, /* NUM OF CAP Types */ MLX5_CAP_NUM @@ -1297,6 +1298,14 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_DEV_EVENT(mdev, cap)\ MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap) +#define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\ + MLX5_GET(device_virtio_emulation_cap, \ + (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) + +#define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\ + MLX5_GET64(device_virtio_emulation_cap, \ + (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, -- cgit v1.2.3 From 860c8802ace14c646864795e057349c9fb2d60ad Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 9 Nov 2019 09:42:13 -0800 Subject: rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls Eric Dumazet supplied a KCSAN report of a bug that forces use of hlist_unhashed_lockless() from sk_unhashed(): ------------------------------------------------------------------------ BUG: KCSAN: data-race in inet_unhash / inet_unhash write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1: __hlist_nulls_del include/linux/list_nulls.h:88 [inline] hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline] __sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline] inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0: sk_unhashed include/net/sock.h:607 [inline] inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 rest_init+0xec/0xf6 init/main.c:452 arch_call_rest_init+0x17/0x37 start_kernel+0x838/0x85e init/main.c:786 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ------------------------------------------------------------------------ This commit therefore replaces C-language assignments with WRITE_ONCE() in include/linux/list_nulls.h and include/linux/rculist_nulls.h. Reported-by: Eric Dumazet # For KCSAN Signed-off-by: Paul E. McKenney --- include/linux/list_nulls.h | 8 ++++---- include/linux/rculist_nulls.h | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 3ef96743db8d..1ecd35664e0d 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -72,10 +72,10 @@ static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_node *first = h->first; n->next = first; - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); } static inline void __hlist_nulls_del(struct hlist_nulls_node *n) @@ -85,13 +85,13 @@ static inline void __hlist_nulls_del(struct hlist_nulls_node *n) WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) - next->pprev = pprev; + WRITE_ONCE(next->pprev, pprev); } static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); - n->pprev = LIST_POISON2; + WRITE_ONCE(n->pprev, LIST_POISON2); } /** diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index bc8206a8f30e..517a06f36c7a 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -34,7 +34,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) { if (!hlist_nulls_unhashed(n)) { __hlist_nulls_del(n); - n->pprev = NULL; + WRITE_ONCE(n->pprev, NULL); } } @@ -66,7 +66,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n) { __hlist_nulls_del(n); - n->pprev = LIST_POISON2; + WRITE_ONCE(n->pprev, LIST_POISON2); } /** @@ -94,10 +94,10 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, struct hlist_nulls_node *first = h->first; n->next = first; - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); } /** -- cgit v1.2.3 From 46deb7449d99f37bebf5cbd7f95c136c6fafeaa5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 9 Nov 2019 10:35:13 -0800 Subject: rcu: Add and update docbook header comments in list.h [ paulmck: Fix typo found by kbuild test robot. ] Signed-off-by: Paul E. McKenney --- include/linux/list.h | 112 +++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 95 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 61f5aaf96192..4f3b7f71bdfd 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -23,6 +23,13 @@ #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) +/** + * INIT_LIST_HEAD - Initialize a list_head structure + * @list: list_head structure to be initialized. + * + * Initializes the list_head to point to itself. If it is a list header, + * the result is an empty list. + */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); @@ -120,12 +127,6 @@ static inline void __list_del_clearprev(struct list_head *entry) entry->prev = NULL; } -/** - * list_del - deletes entry from list. - * @entry: the element to delete from the list. - * Note: list_empty() on entry does not return true after this, the entry is - * in an undefined state. - */ static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) @@ -134,6 +135,12 @@ static inline void __list_del_entry(struct list_head *entry) __list_del(entry->prev, entry->next); } +/** + * list_del - deletes entry from list. + * @entry: the element to delete from the list. + * Note: list_empty() on entry does not return true after this, the entry is + * in an undefined state. + */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); @@ -157,8 +164,15 @@ static inline void list_replace(struct list_head *old, new->prev->next = new; } +/** + * list_replace_init - replace old entry by new one and initialize the old one + * @old : the element to be replaced + * @new : the new element to insert + * + * If @old was empty, it will be overwritten. + */ static inline void list_replace_init(struct list_head *old, - struct list_head *new) + struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); @@ -744,21 +758,36 @@ static inline void INIT_HLIST_NODE(struct hlist_node *h) h->pprev = NULL; } +/** + * hlist_unhashed - Has node been removed from list and reinitialized? + * @h: Node to be checked + * + * Not that not all removal functions will leave a node in unhashed + * state. For example, hlist_nulls_del_init_rcu() does leave the + * node in unhashed state, but hlist_nulls_del() does not. + */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } -/* This variant of hlist_unhashed() must be used in lockless contexts - * to avoid potential load-tearing. - * The READ_ONCE() is paired with the various WRITE_ONCE() in hlist - * helpers that are defined below. +/** + * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use + * @h: Node to be checked + * + * This variant of hlist_unhashed() must be used in lockless contexts + * to avoid potential load-tearing. The READ_ONCE() is paired with the + * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } +/** + * hlist_empty - Is the specified hlist_head structure an empty hlist? + * @h: Structure to check. + */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); @@ -774,6 +803,13 @@ static inline void __hlist_del(struct hlist_node *n) WRITE_ONCE(next->pprev, pprev); } +/** + * hlist_del - Delete the specified hlist_node from its list + * @n: Node to delete. + * + * Note that this function leaves the node in hashed state. Use + * hlist_del_init() or similar instead to unhash @n. + */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); @@ -781,6 +817,12 @@ static inline void hlist_del(struct hlist_node *n) n->pprev = LIST_POISON2; } +/** + * hlist_del_init - Delete the specified hlist_node from its list and initialize + * @n: Node to delete. + * + * Note that this function leaves the node in unhashed state. + */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { @@ -789,6 +831,14 @@ static inline void hlist_del_init(struct hlist_node *n) } } +/** + * hlist_add_head - add a new entry at the beginning of the hlist + * @n: new entry to be added + * @h: hlist head to add it after + * + * Insert a new entry after the specified head. + * This is good for implementing stacks. + */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; @@ -799,9 +849,13 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) WRITE_ONCE(n->pprev, &h->first); } -/* next must be != NULL */ +/** + * hlist_add_before - add a new entry before the one specified + * @n: new entry to be added + * @next: hlist node to add it before, which must be non-NULL + */ static inline void hlist_add_before(struct hlist_node *n, - struct hlist_node *next) + struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); @@ -809,6 +863,11 @@ static inline void hlist_add_before(struct hlist_node *n, WRITE_ONCE(*(n->pprev), n); } +/** + * hlist_add_behing - add a new entry after the one specified + * @n: new entry to be added + * @prev: hlist node to add it after, which must be non-NULL + */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { @@ -820,20 +879,35 @@ static inline void hlist_add_behind(struct hlist_node *n, WRITE_ONCE(n->next->pprev, &n->next); } -/* after that we'll appear to be on some hlist and hlist_del will work */ +/** + * hlist_add_fake - create a fake hlist consisting of a single headless node + * @n: Node to make a fake list out of + * + * This makes @n appear to be its own predecessor on a headless hlist. + * The point of this is to allow things like hlist_del() to work correctly + * in cases where there is no list. + */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } +/** + * hlist_fake: Is this node a fake hlist? + * @h: Node to check for being a self-referential fake hlist. + */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } -/* +/** + * hlist_is_singular_node - is node the only element of the specified hlist? + * @n: Node to check for singularity. + * @h: Header for potentially singular list. + * * Check whether the node is the only node of the head without - * accessing head: + * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) @@ -841,7 +915,11 @@ hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) return !n->next && n->pprev == &h->first; } -/* +/** + * hlist_move_list - Move an hlist + * @old: hlist_head for old list. + * @new: hlist_head for new list. + * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ -- cgit v1.2.3 From 02b99b38f3d96c77cf0a368d99952aa372dfe58a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 9 Nov 2019 10:45:47 -0800 Subject: rcu: Add a hlist_nulls_unhashed_lockless() function This commit adds an hlist_nulls_unhashed_lockless() to allow lockless checking for whether or note an hlist_nulls_node is hashed or not. While in the area, this commit also adds a docbook comment to the existing hlist_nulls_unhashed() function. Signed-off-by: Paul E. McKenney --- include/linux/list_nulls.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 1ecd35664e0d..fa6e8471bd22 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -56,11 +56,33 @@ static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr) return ((unsigned long)ptr) >> 1; } +/** + * hlist_nulls_unhashed - Has node been removed and reinitialized? + * @h: Node to be checked + * + * Not that not all removal functions will leave a node in unhashed state. + * For example, hlist_del_init_rcu() leaves the node in unhashed state, + * but hlist_nulls_del() does not. + */ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) { return !h->pprev; } +/** + * hlist_nulls_unhashed_lockless - Has node been removed and reinitialized? + * @h: Node to be checked + * + * Not that not all removal functions will leave a node in unhashed state. + * For example, hlist_del_init_rcu() leaves the node in unhashed state, + * but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this + * function may be used locklessly. + */ +static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h) +{ + return !READ_ONCE(h->pprev); +} + static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { return is_a_nulls(READ_ONCE(h->first)); -- cgit v1.2.3 From 7f5d51e26a471f771b8dae1b9ef417f5fd5e9c85 Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Thu, 5 Dec 2019 11:46:49 +0530 Subject: rculist_nulls: Add docbook comments This patch adds docbook comment headers for hlist_nulls_first_rcu() and hlist_nulls_next_rcu() in rculist_nulls.h. Signed-off-by: Madhuparna Bhowmik Signed-off-by: Paul E. McKenney --- include/linux/rculist_nulls.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 517a06f36c7a..25952c4f83b0 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -38,9 +38,17 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) } } +/** + * hlist_nulls_first_rcu - returns the first element of the hash list. + * @head: the head of the list. + */ #define hlist_nulls_first_rcu(head) \ (*((struct hlist_nulls_node __rcu __force **)&(head)->first)) +/** + * hlist_nulls_next_rcu - returns the element of the list after @node. + * @node: element of the list. + */ #define hlist_nulls_next_rcu(node) \ (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) -- cgit v1.2.3 From 459b5287066f53c4b91569c070780a540de90b85 Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Fri, 6 Dec 2019 00:23:52 +0530 Subject: rculist_nulls: Change docbook comment headers This patch changes the docbook comment "head for your list" to "head of the list". Signed-off-by: Madhuparna Bhowmik Signed-off-by: Paul E. McKenney --- include/linux/rculist_nulls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 25952c4f83b0..409a86bb5f25 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -112,7 +112,7 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. - * @head: the head for your list. + * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. * * The barrier() is needed to make sure compiler doesn't cache first element [1], @@ -132,7 +132,7 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, * iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. - * @head: the head for your list. + * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. */ #define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ -- cgit v1.2.3 From afa47fdfa29ffd3324e7b89551d1a6e54ccc042b Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Mon, 9 Dec 2019 13:20:43 +0530 Subject: rculist.h: Add list_tail_rcu() This patch adds the macro list_tail_rcu() and documents it. Signed-off-by: Madhuparna Bhowmik [ paulmck: Reword a bit. ] Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 4b7ae1bf50b3..9f313e4999fe 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -40,6 +40,16 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) +/** + * list_tail_rcu - returns the prev pointer of the head of the list + * @head: the head of the list + * + * Note: This should only be used with the list header, and even then + * only if list_del() and similar primitives are not also used on the + * list header. + */ +#define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) + /* * Check during list traversal that we are within an RCU reader */ -- cgit v1.2.3 From 380b107bbf9449ddea0637cefe65a6cbf7b6ca84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Tue, 7 Jan 2020 13:17:04 +0200 Subject: iio: adis: Introduce timeouts structure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The adis library only allows to define a `startup_delay` which for some devices is enough. However, other devices define different timeouts with significantly different timings which could lead to devices to not wait enough time or to wait a lot more than necessary (which is not efficient). This patch introduces a new timeout struct that must be passed into `adis_init()`. There are mainly, for now, three timeouts used. This is also an introductory patch with the goal of refactoring `adis_initial_startup()`. New driver's (eg: adis16480, adis16460) are replicating code for the device initial setup. With some changes (being this the first one) we can pass this to `adis_initial_startup()`. Signed-off-by: Nuno Sá Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 4b5bc0e06e69..853dc8c8365c 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -22,6 +22,17 @@ struct adis; struct adis_burst; +/** + * struct adis_timeouts - ADIS chip variant timeouts + * @reset_ms - Wait time after rst pin goes inactive + * @sw_reset_ms - Wait time after sw reset command + * @self_test_ms - Wait time after self test command + */ +struct adis_timeout { + u16 reset_ms; + u16 sw_reset_ms; + u16 self_test_ms; +}; /** * struct adis_data - ADIS chip variant specific data * @read_delay: SPI delay for read operations in us @@ -32,6 +43,7 @@ struct adis_burst; * @diag_stat_reg: Register address of the DIAG_STAT register * @status_error_msgs: Array of error messgaes * @status_error_mask: + * @timeouts: Chip specific delays */ struct adis_data { unsigned int read_delay; @@ -45,6 +57,7 @@ struct adis_data { unsigned int self_test_mask; bool self_test_no_autoclear; unsigned int startup_delay; + const struct adis_timeout *timeouts; const char * const *status_error_msgs; unsigned int status_error_mask; -- cgit v1.2.3 From 77038bd01ce66ae65bcb66266c9747b670b5facd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Tue, 7 Jan 2020 13:17:05 +0200 Subject: iio: adis: Remove startup_delay MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All timeouts are now handled by a dedicated timeout struct. This variable is no longer needed. Signed-off-by: Nuno Sá Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 853dc8c8365c..d2fcf45b4cef 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -56,7 +56,6 @@ struct adis_data { unsigned int self_test_mask; bool self_test_no_autoclear; - unsigned int startup_delay; const struct adis_timeout *timeouts; const char * const *status_error_msgs; -- cgit v1.2.3 From a442c2c3850dc308ab972f3d10d1077e2c8fd035 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 9 Jan 2020 11:23:17 -0800 Subject: mlx4: Bump up MAX_MSIX from 64 to 128 On modern hardware with a large number of cpus and using XDP, the current MSIX limit is insufficient. Bump the limit in order to allow more queues. Signed-off-by: Jonathan Lemon Reviewed-by: Jack Wang Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/linux/mlx4/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 36e412c3d657..20372de0b587 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -47,7 +47,7 @@ #define DEFAULT_UAR_PAGE_SHIFT 12 #define MAX_MSIX_P_PORT 17 -#define MAX_MSIX 64 +#define MAX_MSIX 128 #define MIN_MSIX_P_PORT 5 #define MLX4_IS_LEGACY_EQ_MODE(dev_cap) ((dev_cap).num_comp_vectors < \ (dev_cap).num_ports * MIN_MSIX_P_PORT) -- cgit v1.2.3 From c74f16b6034401b17bb1cf549871186a8ece5f92 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 12 Jan 2020 13:04:43 +0100 Subject: wan: ixp4xx_hss: prepare compile testing The ixp4xx_hss driver needs the platform data definition and the system clock rate to be compiled. Move both into a new platform_data header file. This is a prerequisite for compile testing, but turning on compile testing requires further patches to isolate the SoC headers. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij Signed-off-by: Jakub Kicinski --- include/linux/platform_data/wan_ixp4xx_hss.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/platform_data/wan_ixp4xx_hss.h (limited to 'include/linux') diff --git a/include/linux/platform_data/wan_ixp4xx_hss.h b/include/linux/platform_data/wan_ixp4xx_hss.h new file mode 100644 index 000000000000..d525a0feb9e1 --- /dev/null +++ b/include/linux/platform_data/wan_ixp4xx_hss.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_DATA_WAN_IXP4XX_HSS_H +#define __PLATFORM_DATA_WAN_IXP4XX_HSS_H + +#include + +/* Information about built-in HSS (synchronous serial) interfaces */ +struct hss_plat_info { + int (*set_clock)(int port, unsigned int clock_type); + int (*open)(int port, void *pdev, + void (*set_carrier_cb)(void *pdev, int carrier)); + void (*close)(int port, void *pdev); + u8 txreadyq; + u32 timer_freq; +}; + +#endif -- cgit v1.2.3 From a41a5b26d29fb0123cd3290dca453857cd8c0c66 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 12 Jan 2020 13:04:45 +0100 Subject: ixp4xx_eth: move platform_data definition The platform data is needed to compile the driver as standalone, so move it to a global location along with similar files. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij Signed-off-by: Jakub Kicinski --- include/linux/platform_data/eth_ixp4xx.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/platform_data/eth_ixp4xx.h (limited to 'include/linux') diff --git a/include/linux/platform_data/eth_ixp4xx.h b/include/linux/platform_data/eth_ixp4xx.h new file mode 100644 index 000000000000..6f652ea0c6ae --- /dev/null +++ b/include/linux/platform_data/eth_ixp4xx.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_DATA_ETH_IXP4XX +#define __PLATFORM_DATA_ETH_IXP4XX + +#include + +#define IXP4XX_ETH_NPEA 0x00 +#define IXP4XX_ETH_NPEB 0x10 +#define IXP4XX_ETH_NPEC 0x20 + +/* Information about built-in Ethernet MAC interfaces */ +struct eth_plat_info { + u8 phy; /* MII PHY ID, 0 - 31 */ + u8 rxq; /* configurable, currently 0 - 31 only */ + u8 txreadyq; + u8 hwaddr[6]; +}; + +#endif -- cgit v1.2.3 From b7365587f513540c962a734c12cf422ca9a111a5 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 13 Jan 2020 13:09:13 +0900 Subject: extcon: Remove unneeded extern keyword from extcon.h 'extern' keyword is unneeded in extcon.h because public header file of extcon defines the function prototype. Signed-off-by: Chanwoo Choi --- include/linux/extcon.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 2bdf643d8593..1b1d77ec2114 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -170,7 +170,7 @@ struct extcon_dev; * Following APIs get the connected state of each external connector. * The 'id' argument indicates the defined external connector. */ -extern int extcon_get_state(struct extcon_dev *edev, unsigned int id); +int extcon_get_state(struct extcon_dev *edev, unsigned int id); /* * Following APIs get the property of each external connector. @@ -181,10 +181,10 @@ extern int extcon_get_state(struct extcon_dev *edev, unsigned int id); * for each external connector. They are used to get the capability of the * property of each external connector based on the id and property. */ -extern int extcon_get_property(struct extcon_dev *edev, unsigned int id, +int extcon_get_property(struct extcon_dev *edev, unsigned int id, unsigned int prop, union extcon_property_value *prop_val); -extern int extcon_get_property_capability(struct extcon_dev *edev, +int extcon_get_property_capability(struct extcon_dev *edev, unsigned int id, unsigned int prop); /* @@ -196,38 +196,38 @@ extern int extcon_get_property_capability(struct extcon_dev *edev, * extcon_register_notifier_all(*edev, *nb) : Register a notifier block * for all supported external connectors of the extcon. */ -extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, +int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); -extern int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id, +int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); -extern int devm_extcon_register_notifier(struct device *dev, +int devm_extcon_register_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); -extern void devm_extcon_unregister_notifier(struct device *dev, +void devm_extcon_unregister_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); -extern int extcon_register_notifier_all(struct extcon_dev *edev, +int extcon_register_notifier_all(struct extcon_dev *edev, struct notifier_block *nb); -extern int extcon_unregister_notifier_all(struct extcon_dev *edev, +int extcon_unregister_notifier_all(struct extcon_dev *edev, struct notifier_block *nb); -extern int devm_extcon_register_notifier_all(struct device *dev, +int devm_extcon_register_notifier_all(struct device *dev, struct extcon_dev *edev, struct notifier_block *nb); -extern void devm_extcon_unregister_notifier_all(struct device *dev, +void devm_extcon_unregister_notifier_all(struct device *dev, struct extcon_dev *edev, struct notifier_block *nb); /* * Following APIs get the extcon_dev from devicetree or by through extcon name. */ -extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); -extern struct extcon_dev *extcon_find_edev_by_node(struct device_node *node); -extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, +struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); +struct extcon_dev *extcon_find_edev_by_node(struct device_node *node); +struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index); /* Following API get the name of extcon device. */ -extern const char *extcon_get_edev_name(struct extcon_dev *edev); +const char *extcon_get_edev_name(struct extcon_dev *edev); #else /* CONFIG_EXTCON */ static inline int extcon_get_state(struct extcon_dev *edev, unsigned int id) -- cgit v1.2.3 From 56de4e8f9146680bcd048a29888f7438d5e58c55 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 13 Dec 2019 13:21:30 -0500 Subject: perf: Make struct ring_buffer less ambiguous eBPF requires needing to know the size of the perf ring buffer structure. But it unfortunately has the same name as the generic ring buffer used by tracing and oprofile. To make it less ambiguous, rename the perf ring buffer structure to "perf_buffer". As other parts of the ring buffer code has "perf_" as the prefix, it only makes sense to give the ring buffer the "perf_" prefix as well. Link: https://lore.kernel.org/r/20191213153553.GE20583@krava Acked-by: Peter Zijlstra Suggested-by: Alexei Starovoitov Signed-off-by: Steven Rostedt (VMware) --- include/linux/perf_event.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6d4c22aee384..cf65763af0cb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -582,7 +582,7 @@ struct swevent_hlist { #define PERF_ATTACH_ITRACE 0x10 struct perf_cgroup; -struct ring_buffer; +struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; @@ -694,7 +694,7 @@ struct perf_event { struct mutex mmap_mutex; atomic_t mmap_count; - struct ring_buffer *rb; + struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; @@ -854,7 +854,7 @@ struct perf_cpu_context { struct perf_output_handle { struct perf_event *event; - struct ring_buffer *rb; + struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; -- cgit v1.2.3 From 1c5eb4481e0151d579f738175497f998840f7bbc Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 9 Jan 2020 18:53:48 -0500 Subject: tracing: Rename trace_buffer to array_buffer As we are working to remove the generic "ring_buffer" name that is used by both tracing and perf, the ring_buffer name for tracing will be renamed to trace_buffer, and perf's ring buffer will be renamed to perf_buffer. As there already exists a trace_buffer that is used by the trace_arrays, it needs to be first renamed to array_buffer. Link: https://lore.kernel.org/r/20191213153553.GE20583@krava Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 4c6e15605766..f70e5bc7e8db 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -11,7 +11,7 @@ #include struct trace_array; -struct trace_buffer; +struct array_buffer; struct tracer; struct dentry; struct bpf_prog; @@ -79,7 +79,7 @@ struct trace_entry { struct trace_iterator { struct trace_array *tr; struct tracer *trace; - struct trace_buffer *trace_buffer; + struct array_buffer *array_buffer; void *private; int cpu_file; struct mutex mutex; -- cgit v1.2.3 From 13292494379f92f532de71b31a54018336adc589 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 13 Dec 2019 13:58:57 -0500 Subject: tracing: Make struct ring_buffer less ambiguous As there's two struct ring_buffers in the kernel, it causes some confusion. The other one being the perf ring buffer. It was agreed upon that as neither of the ring buffers are generic enough to be used globally, they should be renamed as: perf's ring_buffer -> perf_buffer ftrace's ring_buffer -> trace_buffer This implements the changes to the ring buffer that ftrace uses. Link: https://lore.kernel.org/r/20191213140531.116b3200@gandalf.local.home Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 110 +++++++++++++++++++++---------------------- include/linux/trace_events.h | 4 +- 2 files changed, 57 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 1a40277b512c..df0124eabece 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -6,7 +6,7 @@ #include #include -struct ring_buffer; +struct trace_buffer; struct ring_buffer_iter; /* @@ -77,13 +77,13 @@ u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event); * else * ring_buffer_unlock_commit(buffer, event); */ -void ring_buffer_discard_commit(struct ring_buffer *buffer, +void ring_buffer_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event); /* * size is in bytes for each per CPU buffer. */ -struct ring_buffer * +struct trace_buffer * __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key); /* @@ -97,38 +97,38 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) -int ring_buffer_wait(struct ring_buffer *buffer, int cpu, int full); -__poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); +__poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); #define RING_BUFFER_ALL_CPUS -1 -void ring_buffer_free(struct ring_buffer *buffer); +void ring_buffer_free(struct trace_buffer *buffer); -int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, int cpu); +int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, int cpu); -void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val); +void ring_buffer_change_overwrite(struct trace_buffer *buffer, int val); -struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer, +struct ring_buffer_event *ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length); -int ring_buffer_unlock_commit(struct ring_buffer *buffer, +int ring_buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event); -int ring_buffer_write(struct ring_buffer *buffer, +int ring_buffer_write(struct trace_buffer *buffer, unsigned long length, void *data); -void ring_buffer_nest_start(struct ring_buffer *buffer); -void ring_buffer_nest_end(struct ring_buffer *buffer); +void ring_buffer_nest_start(struct trace_buffer *buffer); +void ring_buffer_nest_end(struct trace_buffer *buffer); struct ring_buffer_event * -ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts, +ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events); struct ring_buffer_event * -ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, +ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events); struct ring_buffer_iter * -ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu, gfp_t flags); +ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags); void ring_buffer_read_prepare_sync(void); void ring_buffer_read_start(struct ring_buffer_iter *iter); void ring_buffer_read_finish(struct ring_buffer_iter *iter); @@ -140,59 +140,59 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts); void ring_buffer_iter_reset(struct ring_buffer_iter *iter); int ring_buffer_iter_empty(struct ring_buffer_iter *iter); -unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu); +unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu); -void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu); -void ring_buffer_reset(struct ring_buffer *buffer); +void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu); +void ring_buffer_reset(struct trace_buffer *buffer); #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP -int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, - struct ring_buffer *buffer_b, int cpu); +int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, + struct trace_buffer *buffer_b, int cpu); #else static inline int -ring_buffer_swap_cpu(struct ring_buffer *buffer_a, - struct ring_buffer *buffer_b, int cpu) +ring_buffer_swap_cpu(struct trace_buffer *buffer_a, + struct trace_buffer *buffer_b, int cpu) { return -ENODEV; } #endif -bool ring_buffer_empty(struct ring_buffer *buffer); -bool ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu); - -void ring_buffer_record_disable(struct ring_buffer *buffer); -void ring_buffer_record_enable(struct ring_buffer *buffer); -void ring_buffer_record_off(struct ring_buffer *buffer); -void ring_buffer_record_on(struct ring_buffer *buffer); -bool ring_buffer_record_is_on(struct ring_buffer *buffer); -bool ring_buffer_record_is_set_on(struct ring_buffer *buffer); -void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); -void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); - -u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu); -unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu); -unsigned long ring_buffer_entries(struct ring_buffer *buffer); -unsigned long ring_buffer_overruns(struct ring_buffer *buffer); -unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu); -unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu); -unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu); -unsigned long ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu); -unsigned long ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu); - -u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu); -void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, +bool ring_buffer_empty(struct trace_buffer *buffer); +bool ring_buffer_empty_cpu(struct trace_buffer *buffer, int cpu); + +void ring_buffer_record_disable(struct trace_buffer *buffer); +void ring_buffer_record_enable(struct trace_buffer *buffer); +void ring_buffer_record_off(struct trace_buffer *buffer); +void ring_buffer_record_on(struct trace_buffer *buffer); +bool ring_buffer_record_is_on(struct trace_buffer *buffer); +bool ring_buffer_record_is_set_on(struct trace_buffer *buffer); +void ring_buffer_record_disable_cpu(struct trace_buffer *buffer, int cpu); +void ring_buffer_record_enable_cpu(struct trace_buffer *buffer, int cpu); + +u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_bytes_cpu(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_entries(struct trace_buffer *buffer); +unsigned long ring_buffer_overruns(struct trace_buffer *buffer); +unsigned long ring_buffer_entries_cpu(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_overrun_cpu(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_commit_overrun_cpu(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_dropped_events_cpu(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_read_events_cpu(struct trace_buffer *buffer, int cpu); + +u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu); +void ring_buffer_normalize_time_stamp(struct trace_buffer *buffer, int cpu, u64 *ts); -void ring_buffer_set_clock(struct ring_buffer *buffer, +void ring_buffer_set_clock(struct trace_buffer *buffer, u64 (*clock)(void)); -void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs); -bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer); +void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs); +bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); -size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu); -size_t ring_buffer_nr_dirty_pages(struct ring_buffer *buffer, int cpu); +size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); +size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); -void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu); -void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data); -int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page, +void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu); +void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data); +int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page, size_t len, int cpu, int full); struct trace_seq; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index f70e5bc7e8db..5f7b2b1fce24 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -153,7 +153,7 @@ void tracing_generic_entry_update(struct trace_entry *entry, struct trace_event_file; struct ring_buffer_event * -trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, +trace_event_buffer_lock_reserve(struct trace_buffer **current_buffer, struct trace_event_file *trace_file, int type, unsigned long len, unsigned long flags, int pc); @@ -210,7 +210,7 @@ extern int trace_event_reg(struct trace_event_call *event, enum trace_reg type, void *data); struct trace_event_buffer { - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct ring_buffer_event *event; struct trace_event_file *trace_file; void *entry; -- cgit v1.2.3 From 76db5a27a827c2c89e5120a3d486472da847863b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 11 Jan 2020 01:03:32 +0900 Subject: bootconfig: Add Extra Boot Config support Extra Boot Config (XBC) allows admin to pass a tree-structured boot configuration file when boot up the kernel. This extends the kernel command line in an efficient way. Boot config will contain some key-value commands, e.g. key.word = value1 another.key.word = value2 It can fold same keys with braces, also you can write array data. For example, key { word1 { setting1 = data setting2 } word2.array = "val1", "val2" } User can access these key-value pair and tree structure via SKC APIs. Link: http://lkml.kernel.org/r/157867221257.17873.1775090991929862549.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 224 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 224 insertions(+) create mode 100644 include/linux/bootconfig.h (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h new file mode 100644 index 000000000000..7e18c939663e --- /dev/null +++ b/include/linux/bootconfig.h @@ -0,0 +1,224 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_XBC_H +#define _LINUX_XBC_H +/* + * Extra Boot Config + * Copyright (C) 2019 Linaro Ltd. + * Author: Masami Hiramatsu + */ + +#include +#include + +/* XBC tree node */ +struct xbc_node { + u16 next; + u16 child; + u16 parent; + u16 data; +} __attribute__ ((__packed__)); + +#define XBC_KEY 0 +#define XBC_VALUE (1 << 15) +/* Maximum size of boot config is 32KB - 1 */ +#define XBC_DATA_MAX (XBC_VALUE - 1) + +#define XBC_NODE_MAX 1024 +#define XBC_KEYLEN_MAX 256 +#define XBC_DEPTH_MAX 16 + +/* Node tree access raw APIs */ +struct xbc_node * __init xbc_root_node(void); +int __init xbc_node_index(struct xbc_node *node); +struct xbc_node * __init xbc_node_get_parent(struct xbc_node *node); +struct xbc_node * __init xbc_node_get_child(struct xbc_node *node); +struct xbc_node * __init xbc_node_get_next(struct xbc_node *node); +const char * __init xbc_node_get_data(struct xbc_node *node); + +/** + * xbc_node_is_value() - Test the node is a value node + * @node: An XBC node. + * + * Test the @node is a value node and return true if a value node, false if not. + */ +static inline __init bool xbc_node_is_value(struct xbc_node *node) +{ + return node->data & XBC_VALUE; +} + +/** + * xbc_node_is_key() - Test the node is a key node + * @node: An XBC node. + * + * Test the @node is a key node and return true if a key node, false if not. + */ +static inline __init bool xbc_node_is_key(struct xbc_node *node) +{ + return !xbc_node_is_value(node); +} + +/** + * xbc_node_is_array() - Test the node is an arraied value node + * @node: An XBC node. + * + * Test the @node is an arraied value node. + */ +static inline __init bool xbc_node_is_array(struct xbc_node *node) +{ + return xbc_node_is_value(node) && node->next != 0; +} + +/** + * xbc_node_is_leaf() - Test the node is a leaf key node + * @node: An XBC node. + * + * Test the @node is a leaf key node which is a key node and has a value node + * or no child. Returns true if it is a leaf node, or false if not. + */ +static inline __init bool xbc_node_is_leaf(struct xbc_node *node) +{ + return xbc_node_is_key(node) && + (!node->child || xbc_node_is_value(xbc_node_get_child(node))); +} + +/* Tree-based key-value access APIs */ +struct xbc_node * __init xbc_node_find_child(struct xbc_node *parent, + const char *key); + +const char * __init xbc_node_find_value(struct xbc_node *parent, + const char *key, + struct xbc_node **vnode); + +struct xbc_node * __init xbc_node_find_next_leaf(struct xbc_node *root, + struct xbc_node *leaf); + +const char * __init xbc_node_find_next_key_value(struct xbc_node *root, + struct xbc_node **leaf); + +/** + * xbc_find_value() - Find a value which matches the key + * @key: Search key + * @vnode: A container pointer of XBC value node. + * + * Search a value whose key matches @key from whole of XBC tree and return + * the value if found. Found value node is stored in *@vnode. + * Note that this can return 0-length string and store NULL in *@vnode for + * key-only (non-value) entry. + */ +static inline const char * __init +xbc_find_value(const char *key, struct xbc_node **vnode) +{ + return xbc_node_find_value(NULL, key, vnode); +} + +/** + * xbc_find_node() - Find a node which matches the key + * @key: Search key + * + * Search a (key) node whose key matches @key from whole of XBC tree and + * return the node if found. If not found, returns NULL. + */ +static inline struct xbc_node * __init xbc_find_node(const char *key) +{ + return xbc_node_find_child(NULL, key); +} + +/** + * xbc_array_for_each_value() - Iterate value nodes on an array + * @anode: An XBC arraied value node + * @value: A value + * + * Iterate array value nodes and values starts from @anode. This is expected to + * be used with xbc_find_value() and xbc_node_find_value(), so that user can + * process each array entry node. + */ +#define xbc_array_for_each_value(anode, value) \ + for (value = xbc_node_get_data(anode); anode != NULL ; \ + anode = xbc_node_get_next(anode), \ + value = anode ? xbc_node_get_data(anode) : NULL) + +/** + * xbc_node_for_each_child() - Iterate child nodes + * @parent: An XBC node. + * @child: Iterated XBC node. + * + * Iterate child nodes of @parent. Each child nodes are stored to @child. + */ +#define xbc_node_for_each_child(parent, child) \ + for (child = xbc_node_get_child(parent); child != NULL ; \ + child = xbc_node_get_next(child)) + +/** + * xbc_node_for_each_array_value() - Iterate array entries of geven key + * @node: An XBC node. + * @key: A key string searched under @node + * @anode: Iterated XBC node of array entry. + * @value: Iterated value of array entry. + * + * Iterate array entries of given @key under @node. Each array entry node + * is stroed to @anode and @value. If the @node doesn't have @key node, + * it does nothing. + * Note that even if the found key node has only one value (not array) + * this executes block once. Hoever, if the found key node has no value + * (key-only node), this does nothing. So don't use this for testing the + * key-value pair existence. + */ +#define xbc_node_for_each_array_value(node, key, anode, value) \ + for (value = xbc_node_find_value(node, key, &anode); value != NULL; \ + anode = xbc_node_get_next(anode), \ + value = anode ? xbc_node_get_data(anode) : NULL) + +/** + * xbc_node_for_each_key_value() - Iterate key-value pairs under a node + * @node: An XBC node. + * @knode: Iterated key node + * @value: Iterated value string + * + * Iterate key-value pairs under @node. Each key node and value string are + * stored in @knode and @value respectively. + */ +#define xbc_node_for_each_key_value(node, knode, value) \ + for (knode = NULL, value = xbc_node_find_next_key_value(node, &knode);\ + knode != NULL; value = xbc_node_find_next_key_value(node, &knode)) + +/** + * xbc_for_each_key_value() - Iterate key-value pairs + * @knode: Iterated key node + * @value: Iterated value string + * + * Iterate key-value pairs in whole XBC tree. Each key node and value string + * are stored in @knode and @value respectively. + */ +#define xbc_for_each_key_value(knode, value) \ + xbc_node_for_each_key_value(NULL, knode, value) + +/* Compose partial key */ +int __init xbc_node_compose_key_after(struct xbc_node *root, + struct xbc_node *node, char *buf, size_t size); + +/** + * xbc_node_compose_key() - Compose full key string of the XBC node + * @node: An XBC node. + * @buf: A buffer to store the key. + * @size: The size of the @buf. + * + * Compose the full-length key of the @node into @buf. Returns the total + * length of the key stored in @buf. Or returns -EINVAL if @node is NULL, + * and -ERANGE if the key depth is deeper than max depth. + */ +static inline int __init xbc_node_compose_key(struct xbc_node *node, + char *buf, size_t size) +{ + return xbc_node_compose_key_after(NULL, node, buf, size); +} + +/* XBC node initializer */ +int __init xbc_init(char *buf); + +/* XBC cleanup data structures */ +void __init xbc_destroy_all(void); + +/* Debug dump functions */ +void __init xbc_debug_dump(void); + +#endif -- cgit v1.2.3 From 8cfcf15503f607e9597de19afeaa621897ae397e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 11 Jan 2020 01:05:31 +0900 Subject: tracing: kprobes: Output kprobe event to printk buffer Since kprobe-events use event_trigger_unlock_commit_regs() directly, that events doesn't show up in printk buffer if "tp_printk" is set. Use trace_event_buffer_commit() in kprobe events so that it can invoke output_printk() as same as other trace events. Link: http://lkml.kernel.org/r/157867233085.17873.5210928676787339604.stgit@devnote2 Signed-off-by: Masami Hiramatsu [ Adjusted data var declaration placement in __kretprobe_trace_func() ] Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 5f7b2b1fce24..20948ee56f8c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -216,6 +216,7 @@ struct trace_event_buffer { void *entry; unsigned long flags; int pc; + struct pt_regs *regs; }; void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, -- cgit v1.2.3 From 0e41bf06eefe969ee5092f4ec55ae1b0ff9c1ea0 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 13 Jan 2020 16:28:38 +0000 Subject: platform/mellanox: mlxreg-hotplug: Add support for new capability register Add support for capability register, which is used for detection of the actual number of interrupt capable components within the particular group, supported by the specific system. Such components could be for example the number of power units and interrupts related to these units. The motivation is to avoid adding a new code in the future in order to distinct between the systems type supported different number of the components like power supplies, FANs, ASICs, line cards. Signed-off-by: Vadim Pasternak Signed-off-by: Andy Shevchenko --- include/linux/platform_data/mlxreg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 6d54fe3bcac9..b8da8aef2446 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -101,6 +101,7 @@ struct mlxreg_core_data { * @aggr_mask: group aggregation mask; * @reg: group interrupt status register; * @mask: group interrupt mask; + * @capability: group capability register; * @cache: last status value for elements fro the same group; * @count: number of available elements in the group; * @ind: element's index inside the group; @@ -112,6 +113,7 @@ struct mlxreg_core_item { u32 aggr_mask; u32 reg; u32 mask; + u32 capability; u32 cache; u8 count; u8 ind; -- cgit v1.2.3 From 6b8651aac1dca6140dd7fb4c9fec2736ed3f6223 Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Fri, 20 Dec 2019 10:21:26 +0800 Subject: raid6/test: fix a compilation error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The compilation error is redeclaration showed as following: In file included from ../../../include/linux/limits.h:6, from /usr/include/x86_64-linux-gnu/bits/local_lim.h:38, from /usr/include/x86_64-linux-gnu/bits/posix1_lim.h:161, from /usr/include/limits.h:183, from /usr/lib/gcc/x86_64-linux-gnu/8/include-fixed/limits.h:194, from /usr/lib/gcc/x86_64-linux-gnu/8/include-fixed/syslimits.h:7, from /usr/lib/gcc/x86_64-linux-gnu/8/include-fixed/limits.h:34, from ../../../include/linux/raid/pq.h:30, from algos.c:14: ../../../include/linux/types.h:114:15: error: conflicting types for ‘int64_t’ typedef s64 int64_t; ^~~~~~~ In file included from /usr/include/stdint.h:34, from /usr/lib/gcc/x86_64-linux-gnu/8/include/stdint.h:9, from /usr/include/inttypes.h:27, from ../../../include/linux/raid/pq.h:29, from algos.c:14: /usr/include/x86_64-linux-gnu/bits/stdint-intn.h:27:19: note: previous \ declaration of ‘int64_t’ was here typedef __int64_t int64_t; Fixes: 54d50897d544 ("linux/kernel.h: split *_MAX and *_MIN macros into ") Signed-off-by: Zhengyuan Liu Signed-off-by: Song Liu --- include/linux/raid/pq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 0832c9b66852..0b6e7ad9cd2a 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -27,7 +27,6 @@ extern const char raid6_empty_zero_page[PAGE_SIZE]; #include #include -#include #include #include #include -- cgit v1.2.3 From 5e5ac01c2b8802921fee680518a986011cb59820 Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Fri, 20 Dec 2019 10:21:27 +0800 Subject: raid6/test: fix a compilation warning The compilation warning is redefination showed as following: In file included from tables.c:2: ../../../include/linux/export.h:180: warning: "EXPORT_SYMBOL" redefined #define EXPORT_SYMBOL(sym) __EXPORT_SYMBOL(sym, "") In file included from tables.c:1: ../../../include/linux/raid/pq.h:61: note: this is the location of the previous definition #define EXPORT_SYMBOL(sym) Fixes: 69a94abb82ee ("export.h, genksyms: do not make genksyms calculate CRC of trimmed symbols") Signed-off-by: Zhengyuan Liu Signed-off-by: Song Liu --- include/linux/raid/pq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 0b6e7ad9cd2a..e0ddb47f4402 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -58,7 +58,9 @@ extern const char raid6_empty_zero_page[PAGE_SIZE]; #define enable_kernel_altivec() #define disable_kernel_altivec() +#undef EXPORT_SYMBOL #define EXPORT_SYMBOL(sym) +#undef EXPORT_SYMBOL_GPL #define EXPORT_SYMBOL_GPL(sym) #define MODULE_LICENSE(licence) #define MODULE_DESCRIPTION(desc) -- cgit v1.2.3 From f591df3cc6d60cadf8ceff5d44af73ea6ba0a39a Mon Sep 17 00:00:00 2001 From: Zhengyuan Liu Date: Fri, 20 Dec 2019 10:21:28 +0800 Subject: md/raid6: fix algorithm choice under larger PAGE_SIZE There are several algorithms available for raid6 to generate xor and syndrome parity, including basic int1, int2 ... int32 and SIMD optimized implementation like sse and neon. To test and choose the best algorithms at the initial stage, we need provide enough disk data to feed the algorithms. However, the disk number we provided depends on page size and gfmul table, seeing bellow: const int disks = (65536/PAGE_SIZE) + 2; So when come to 64K PAGE_SIZE, there is only one data disk plus 2 parity disk, as a result the chosed algorithm is not reliable. For example, on my arm64 machine with 64K page enabled, it will choose intx32 as the best one, although the NEON implementation is better. This patch tries to fix the problem by defining a constant raid6 disk number to supporting arbitrary page size. Suggested-by: H. Peter Anvin Signed-off-by: Zhengyuan Liu Signed-off-by: Song Liu --- include/linux/raid/pq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index e0ddb47f4402..154e954b711d 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -28,6 +28,7 @@ extern const char raid6_empty_zero_page[PAGE_SIZE]; #include #include #include +#include #include #include #include @@ -43,6 +44,9 @@ typedef uint64_t u64; #ifndef PAGE_SIZE # define PAGE_SIZE 4096 #endif +#ifndef PAGE_SHIFT +# define PAGE_SHIFT 12 +#endif extern const char raid6_empty_zero_page[PAGE_SIZE]; #define __init -- cgit v1.2.3 From 5e876fb43dbf24c941a323139752bcb2f0a80da0 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Tue, 7 Jan 2020 09:59:24 -0800 Subject: vfs, fdtable: Add fget_task helper This introduces a function which can be used to fetch a file, given an arbitrary task. As long as the user holds a reference (refcnt) to the task_struct it is safe to call, and will either return NULL on failure, or a pointer to the file, with a refcnt. This patch is based on Oleg Nesterov's (cf. [1]) patch from September 2018. [1]: Link: https://lore.kernel.org/r/20180915160423.GA31461@redhat.com Signed-off-by: Sargun Dhillon Suggested-by: Oleg Nesterov Acked-by: Christian Brauner Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200107175927.4558-2-sargun@sargun.me Signed-off-by: Christian Brauner --- include/linux/file.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 3fcddff56bc4..c6c7b24ea9f7 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -16,6 +16,7 @@ extern void fput(struct file *); extern void fput_many(struct file *, unsigned int); struct file_operations; +struct task_struct; struct vfsmount; struct dentry; struct inode; @@ -47,6 +48,7 @@ static inline void fdput(struct fd fd) extern struct file *fget(unsigned int fd); extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); +extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); extern unsigned long __fdget_raw(unsigned int fd); extern unsigned long __fdget_pos(unsigned int fd); -- cgit v1.2.3 From 9a2cef09c801de54feecd912303ace5c27237f12 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Tue, 7 Jan 2020 09:59:26 -0800 Subject: arch: wire up pidfd_getfd syscall This wires up the pidfd_getfd syscall for all architectures. Signed-off-by: Sargun Dhillon Acked-by: Christian Brauner Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200107175927.4558-4-sargun@sargun.me Signed-off-by: Christian Brauner --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5262b7a76d39..8640af30c506 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1000,6 +1000,7 @@ asmlinkage long sys_fspick(int dfd, const char __user *path, unsigned int flags) asmlinkage long sys_pidfd_send_signal(int pidfd, int sig, siginfo_t __user *info, unsigned int flags); +asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags); /* * Architecture-specific system calls -- cgit v1.2.3 From efc78983d21aeaf692006d42b92a006cdce3ed4d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 16 Dec 2019 19:38:52 +0200 Subject: iio: st_sensors: Drop redundant parameter from st_sensors_of_name_probe() Since we have access to the struct device_driver and thus to the ID table, there is no need to supply special parameters to st_sensors_of_name_probe(). Besides that we have a common API to get driver match data, there is no need to do matching separately for OF and ACPI. Taking into consideration above, simplify the ST sensors code. Signed-off-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 12 +----------- include/linux/iio/common/st_sensors_i2c.h | 10 ---------- 2 files changed, 1 insertion(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 686be532f4cb..33e939977444 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -315,16 +315,6 @@ ssize_t st_sensors_sysfs_sampling_frequency_avail(struct device *dev, ssize_t st_sensors_sysfs_scale_avail(struct device *dev, struct device_attribute *attr, char *buf); -#ifdef CONFIG_OF -void st_sensors_of_name_probe(struct device *dev, - const struct of_device_id *match, - char *name, int len); -#else -static inline void st_sensors_of_name_probe(struct device *dev, - const struct of_device_id *match, - char *name, int len) -{ -} -#endif +void st_sensors_dev_name_probe(struct device *dev, char *name, int len); #endif /* ST_SENSORS_H */ diff --git a/include/linux/iio/common/st_sensors_i2c.h b/include/linux/iio/common/st_sensors_i2c.h index 01e424e2af4f..5f15cf01036c 100644 --- a/include/linux/iio/common/st_sensors_i2c.h +++ b/include/linux/iio/common/st_sensors_i2c.h @@ -12,18 +12,8 @@ #include #include -#include int st_sensors_i2c_configure(struct iio_dev *indio_dev, struct i2c_client *client); -#ifdef CONFIG_ACPI -int st_sensors_match_acpi_device(struct device *dev); -#else -static inline int st_sensors_match_acpi_device(struct device *dev) -{ - return -ENODEV; -} -#endif - #endif /* ST_SENSORS_I2C_H */ -- cgit v1.2.3 From 0eac8ce95bb386838121189b2aa2216cd070f143 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 13 Jan 2020 11:22:16 +0100 Subject: ptr_ring: add include of linux/mm.h Commit 0bf7800f1799 ("ptr_ring: try vmalloc() when kmalloc() fails") started to use kvmalloc_array and kvfree, which are defined in mm.h, the previous functions kcalloc and kfree, which are defined in slab.h. Add the missing include of linux/mm.h. This went unnoticed as other include files happened to include mm.h. Fixes: 0bf7800f1799 ("ptr_ring: try vmalloc() when kmalloc() fails") Signed-off-by: Jesper Dangaard Brouer Acked-by: Michael S. Tsirkin Signed-off-by: Jakub Kicinski --- include/linux/ptr_ring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 0abe9a4fc842..417db0a79a62 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -23,6 +23,7 @@ #include #include #include +#include #include #endif -- cgit v1.2.3 From 4a87e2a25dc27131c3cce5e94421622193305638 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 13 Jan 2020 16:29:16 -0800 Subject: mm: memcg/slab: fix percpu slab vmstats flushing Currently slab percpu vmstats are flushed twice: during the memcg offlining and just before freeing the memcg structure. Each time percpu counters are summed, added to the atomic counterparts and propagated up by the cgroup tree. The second flushing is required due to how recursive vmstats are implemented: counters are batched in percpu variables on a local level, and once a percpu value is crossing some predefined threshold, it spills over to atomic values on the local and each ascendant levels. It means that without flushing some numbers cached in percpu variables will be dropped on floor each time a cgroup is destroyed. And with uptime the error on upper levels might become noticeable. The first flushing aims to make counters on ancestor levels more precise. Dying cgroups may resume in the dying state for a long time. After kmem_cache reparenting which is performed during the offlining slab counters of the dying cgroup don't have any chances to be updated, because any slab operations will be performed on the parent level. It means that the inaccuracy caused by percpu batching will not decrease up to the final destruction of the cgroup. By the original idea flushing slab counters during the offlining should minimize the visible inaccuracy of slab counters on the parent level. The problem is that percpu counters are not zeroed after the first flushing. So every cached percpu value is summed twice. It creates a small error (up to 32 pages per cpu, but usually less) which accumulates on parent cgroup level. After creating and destroying of thousands of child cgroups, slab counter on parent level can be way off the real value. For now, let's just stop flushing slab counters on memcg offlining. It can't be done correctly without scheduling a work on each cpu: reading and zeroing it during css offlining can race with an asynchronous update, which doesn't expect values to be changed underneath. With this change, slab counters on parent level will become eventually consistent. Once all dying children are gone, values are correct. And if not, the error is capped by 32 * NR_CPUS pages per dying cgroup. It's not perfect, as slab are reparented, so any updates after the reparenting will happen on the parent level. It means that if a slab page was allocated, a counter on child level was bumped, then the page was reparented and freed, the annihilation of positive and negative counter values will not happen until the child cgroup is released. It makes slab counters different from others, and it might want us to implement flushing in a correct form again. But it's also a question of performance: scheduling a work on each cpu isn't free, and it's an open question if the benefit of having more accurate counters is worth it. We might also consider flushing all counters on offlining, not only slab counters. So let's fix the main problem now: make the slab counters eventually consistent, so at least the error won't grow with uptime (or more precisely the number of created and destroyed cgroups). And think about the accuracy of counters separately. Link: http://lkml.kernel.org/r/20191220042728.1045881-1-guro@fb.com Fixes: bee07b33db78 ("mm: memcontrol: flush percpu slab vmstats on kmem offlining") Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 89d8ff06c9ce..5334ad8fc7bd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -215,9 +215,8 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ - NR_SLAB_RECLAIMABLE, /* Please do not reorder this item */ - NR_SLAB_UNRECLAIMABLE, /* and this one without looking at - * memcg_flush_percpu_vmstats() first. */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, -- cgit v1.2.3 From 8e57f8acbbd121ecfb0c9dc13b8b030f86c6bd3b Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 13 Jan 2020 16:29:20 -0800 Subject: mm, debug_pagealloc: don't rely on static keys too early Commit 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") has introduced a static key to reduce overhead when debug_pagealloc is compiled in but not enabled. It relied on the assumption that jump_label_init() is called before parse_early_param() as in start_kernel(), so when the "debug_pagealloc=on" option is parsed, it is safe to enable the static key. However, it turns out multiple architectures call parse_early_param() earlier from their setup_arch(). x86 also calls jump_label_init() even earlier, so no issue was found while testing the commit, but same is not true for e.g. ppc64 and s390 where the kernel would not boot with debug_pagealloc=on as found by our QA. To fix this without tricky changes to init code of multiple architectures, this patch partially reverts the static key conversion from 96a2b03f281d. Init-time and non-fastpath calls (such as in arch code) of debug_pagealloc_enabled() will again test a simple bool variable. Fastpath mm code is converted to a new debug_pagealloc_enabled_static() variant that relies on the static key, which is enabled in a well-defined point in mm_init() where it's guaranteed that jump_label_init() has been called, regardless of architecture. [sfr@canb.auug.org.au: export _debug_pagealloc_enabled_early] Link: http://lkml.kernel.org/r/20200106164944.063ac07b@canb.auug.org.au Link: http://lkml.kernel.org/r/20191219130612.23171-1-vbabka@suse.cz Fixes: 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") Signed-off-by: Vlastimil Babka Signed-off-by: Stephen Rothwell Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Vlastimil Babka Cc: Matthew Wilcox Cc: Mel Gorman Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Qian Cai Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80a9162b406c..cfaa8feecfe8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2658,13 +2658,25 @@ static inline bool want_init_on_free(void) !page_poisoning_enabled(); } -#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT -DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); +#ifdef CONFIG_DEBUG_PAGEALLOC +extern void init_debug_pagealloc(void); #else -DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +static inline void init_debug_pagealloc(void) {} #endif +extern bool _debug_pagealloc_enabled_early; +DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) +{ + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && + _debug_pagealloc_enabled_early; +} + +/* + * For use in fast paths after init_debug_pagealloc() has run, or when a + * false negative result is not harmful when called too early. + */ +static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; -- cgit v1.2.3 From 579a25a854d482bc9d0f9ab0e07ba32fb66bd9e3 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 13 Jan 2020 17:24:09 +0100 Subject: net: stmmac: Initial support for TBS Adds the initial hooks for TBS support. This needs a 32 byte descriptor in order for it to work with current HW. Adds all the logic for Enhanced Descriptors in main core but no HW related logic for now. Changes from v2: - Use bitfield for TBS status / support (Jakub) - Remove unneeded cache alignment (Jakub) - Fix checkpatch issues Signed-off-by: Jose Abreu Signed-off-by: Jakub Kicinski --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0531afa9b21e..19190c609282 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -139,6 +139,7 @@ struct stmmac_txq_cfg { u32 low_credit; bool use_prio; u32 prio; + int tbs_en; }; struct plat_stmmacenet_data { -- cgit v1.2.3 From 42d068472ddf532f3ca2bcdd06d1ca6b53f57e5e Mon Sep 17 00:00:00 2001 From: Yuti Amonkar Date: Mon, 6 Jan 2020 13:22:40 +0100 Subject: phy: Add DisplayPort configuration options Allow DisplayPort PHYs to be configured through the generic functions through a custom structure added to the generic union. The configuration structure is used for reconfiguration of DisplayPort PHYs during link training operation. The parameters added here are the ones defined in the DisplayPort spec v1.4 which include link rate, number of lanes, voltage swing and pre-emphasis. Add the DisplayPort phy mode to the generic phy_mode enum. Signed-off-by: Yuti Amonkar Reviewed-by: Maxime Ripard Reviewed-by: Jyri Sarha Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy-dp.h | 95 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy/phy.h | 5 +++ 2 files changed, 100 insertions(+) create mode 100644 include/linux/phy/phy-dp.h (limited to 'include/linux') diff --git a/include/linux/phy/phy-dp.h b/include/linux/phy/phy-dp.h new file mode 100644 index 000000000000..18cad23642cd --- /dev/null +++ b/include/linux/phy/phy-dp.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 Cadence Design Systems Inc. + */ + +#ifndef __PHY_DP_H_ +#define __PHY_DP_H_ + +#include + +/** + * struct phy_configure_opts_dp - DisplayPort PHY configuration set + * + * This structure is used to represent the configuration state of a + * DisplayPort phy. + */ +struct phy_configure_opts_dp { + /** + * @link_rate: + * + * Link Rate, in Mb/s, of the main link. + * + * Allowed values: 1620, 2160, 2430, 2700, 3240, 4320, 5400, 8100 Mb/s + */ + unsigned int link_rate; + + /** + * @lanes: + * + * Number of active, consecutive, data lanes, starting from + * lane 0, used for the transmissions on main link. + * + * Allowed values: 1, 2, 4 + */ + unsigned int lanes; + + /** + * @voltage: + * + * Voltage swing levels, as specified by DisplayPort specification, + * to be used by particular lanes. One value per lane. + * voltage[0] is for lane 0, voltage[1] is for lane 1, etc. + * + * Maximum value: 3 + */ + unsigned int voltage[4]; + + /** + * @pre: + * + * Pre-emphasis levels, as specified by DisplayPort specification, to be + * used by particular lanes. One value per lane. + * + * Maximum value: 3 + */ + unsigned int pre[4]; + + /** + * @ssc: + * + * Flag indicating, whether or not to enable spread-spectrum clocking. + * + */ + u8 ssc : 1; + + /** + * @set_rate: + * + * Flag indicating, whether or not reconfigure link rate and SSC to + * requested values. + * + */ + u8 set_rate : 1; + + /** + * @set_lanes: + * + * Flag indicating, whether or not reconfigure lane count to + * requested value. + * + */ + u8 set_lanes : 1; + + /** + * @set_voltages: + * + * Flag indicating, whether or not reconfigure voltage swing + * and pre-emphasis to requested values. Only lanes specified + * by "lanes" parameter will be affected. + * + */ + u8 set_voltages : 1; +}; + +#endif /* __PHY_DP_H_ */ diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 19eddd64c8f6..bcee8eba62b3 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -16,6 +16,7 @@ #include #include +#include #include struct phy; @@ -40,6 +41,7 @@ enum phy_mode { PHY_MODE_MIPI_DPHY, PHY_MODE_SATA, PHY_MODE_LVDS, + PHY_MODE_DP }; /** @@ -47,9 +49,12 @@ enum phy_mode { * * @mipi_dphy: Configuration set applicable for phys supporting * the MIPI_DPHY phy mode. + * @dp: Configuration set applicable for phys supporting + * the DisplayPort protocol. */ union phy_configure_opts { struct phy_configure_opts_mipi_dphy mipi_dphy; + struct phy_configure_opts_dp dp; }; /** -- cgit v1.2.3 From fd6a3ac8e87cedd83d6aad4bbc2682a903fb5d01 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 13 Jan 2020 16:56:37 -0600 Subject: soundwire: bus: fix device number leak on errors If the programming of the dev_number fails due to an IO error, a new device_number will be assigned, resulting in a leak. Make sure we only assign a device_number once per Slave device. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20200113225637.17313-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index b7c9eca4332a..b451bb622335 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -546,7 +546,8 @@ struct sdw_slave_ops { * @debugfs: Slave debugfs * @node: node for bus list * @port_ready: Port ready completion flag for each Slave port - * @dev_num: Device Number assigned by Bus + * @dev_num: Current Device Number, values can be 0 or dev_num_sticky + * @dev_num_sticky: one-time static Device Number assigned by Bus * @probed: boolean tracking driver state * @probe_complete: completion utility to control potential races * on startup between driver probe/initialization and SoundWire @@ -575,6 +576,7 @@ struct sdw_slave { struct list_head node; struct completion *port_ready; u16 dev_num; + u16 dev_num_sticky; bool probed; struct completion probe_complete; struct completion enumeration_complete; -- cgit v1.2.3 From 769071ac9f20b6a447410c7eaa55d1a5233ef40c Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 12 Nov 2019 01:26:52 +0000 Subject: ns: Introduce Time Namespace Time Namespace isolates clock values. The kernel provides access to several clocks CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME, etc. CLOCK_REALTIME System-wide clock that measures real (i.e., wall-clock) time. CLOCK_MONOTONIC Clock that cannot be set and represents monotonic time since some unspecified starting point. CLOCK_BOOTTIME Identical to CLOCK_MONOTONIC, except it also includes any time that the system is suspended. For many users, the time namespace means the ability to changes date and time in a container (CLOCK_REALTIME). Providing per namespace notions of CLOCK_REALTIME would be complex with a massive overhead, but has a dubious value. But in the context of checkpoint/restore functionality, monotonic and boottime clocks become interesting. Both clocks are monotonic with unspecified starting points. These clocks are widely used to measure time slices and set timers. After restoring or migrating processes, it has to be guaranteed that they never go backward. In an ideal case, the behavior of these clocks should be the same as for a case when a whole system is suspended. All this means that it is required to set CLOCK_MONOTONIC and CLOCK_BOOTTIME clocks, which can be achieved by adding per-namespace offsets for clocks. A time namespace is similar to a pid namespace in the way how it is created: unshare(CLONE_NEWTIME) system call creates a new time namespace, but doesn't set it to the current process. Then all children of the process will be born in the new time namespace, or a process can use the setns() system call to join a namespace. This scheme allows setting clock offsets for a namespace, before any processes appear in it. All available clone flags have been used, so CLONE_NEWTIME uses the highest bit of CSIGNAL. It means that it can be used only with the unshare() and the clone3() system calls. [ tglx: Adjusted paragraph about clone3() to reality and massaged the changelog a bit. ] Co-developed-by: Dmitry Safonov Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://criu.org/Time_namespace Link: https://lists.openvz.org/pipermail/criu/2018-June/041504.html Link: https://lore.kernel.org/r/20191112012724.250792-4-dima@arista.com --- include/linux/nsproxy.h | 2 ++ include/linux/proc_ns.h | 3 ++ include/linux/time_namespace.h | 71 ++++++++++++++++++++++++++++++++++++++++++ include/linux/user_namespace.h | 1 + 4 files changed, 77 insertions(+) create mode 100644 include/linux/time_namespace.h (limited to 'include/linux') diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 2ae1b1a4d84d..074f395b9ad2 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -35,6 +35,8 @@ struct nsproxy { struct mnt_namespace *mnt_ns; struct pid_namespace *pid_ns_for_children; struct net *net_ns; + struct time_namespace *time_ns; + struct time_namespace *time_ns_for_children; struct cgroup_namespace *cgroup_ns; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index d31cb6215905..d312e6281e69 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -32,6 +32,8 @@ extern const struct proc_ns_operations pidns_for_children_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; extern const struct proc_ns_operations cgroupns_operations; +extern const struct proc_ns_operations timens_operations; +extern const struct proc_ns_operations timens_for_children_operations; /* * We always define these enumerators @@ -43,6 +45,7 @@ enum { PROC_USER_INIT_INO = 0xEFFFFFFDU, PROC_PID_INIT_INO = 0xEFFFFFFCU, PROC_CGROUP_INIT_INO = 0xEFFFFFFBU, + PROC_TIME_INIT_INO = 0xEFFFFFFAU, }; #ifdef CONFIG_PROC_FS diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h new file mode 100644 index 000000000000..8c74cc12ad24 --- /dev/null +++ b/include/linux/time_namespace.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TIMENS_H +#define _LINUX_TIMENS_H + + +#include +#include +#include +#include +#include + +struct user_namespace; +extern struct user_namespace init_user_ns; + +struct time_namespace { + struct kref kref; + struct user_namespace *user_ns; + struct ucounts *ucounts; + struct ns_common ns; +} __randomize_layout; + +extern struct time_namespace init_time_ns; + +#ifdef CONFIG_TIME_NS +static inline struct time_namespace *get_time_ns(struct time_namespace *ns) +{ + kref_get(&ns->kref); + return ns; +} + +struct time_namespace *copy_time_ns(unsigned long flags, + struct user_namespace *user_ns, + struct time_namespace *old_ns); +void free_time_ns(struct kref *kref); +int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); + +static inline void put_time_ns(struct time_namespace *ns) +{ + kref_put(&ns->kref, free_time_ns); +} + +#else +static inline struct time_namespace *get_time_ns(struct time_namespace *ns) +{ + return NULL; +} + +static inline void put_time_ns(struct time_namespace *ns) +{ +} + +static inline +struct time_namespace *copy_time_ns(unsigned long flags, + struct user_namespace *user_ns, + struct time_namespace *old_ns) +{ + if (flags & CLONE_NEWTIME) + return ERR_PTR(-EINVAL); + + return old_ns; +} + +static inline int timens_on_fork(struct nsproxy *nsproxy, + struct task_struct *tsk) +{ + return 0; +} + +#endif + +#endif /* _LINUX_TIMENS_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index fb9f4f799554..6ef1c7109fc4 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -45,6 +45,7 @@ enum ucount_type { UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, + UCOUNT_TIME_NAMESPACES, #ifdef CONFIG_INOTIFY_USER UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, -- cgit v1.2.3 From af993f58d69ee9c1f421dfc87c3ed231c113989c Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 12 Nov 2019 01:26:53 +0000 Subject: time: Add timens_offsets to be used for tasks in time namespace Introduce offsets for time namespace. They will contain an adjustment needed to convert clocks to/from host's. A new namespace is created with the same offsets as the time namespace of the current process. Co-developed-by: Dmitry Safonov Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-5-dima@arista.com --- include/linux/time_namespace.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 8c74cc12ad24..d7e3b4994e31 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -12,11 +12,17 @@ struct user_namespace; extern struct user_namespace init_user_ns; +struct timens_offsets { + struct timespec64 monotonic; + struct timespec64 boottime; +}; + struct time_namespace { struct kref kref; struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; + struct timens_offsets offsets; } __randomize_layout; extern struct time_namespace init_time_ns; @@ -39,6 +45,20 @@ static inline void put_time_ns(struct time_namespace *ns) kref_put(&ns->kref, free_time_ns); } +static inline void timens_add_monotonic(struct timespec64 *ts) +{ + struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; + + *ts = timespec64_add(*ts, ns_offsets->monotonic); +} + +static inline void timens_add_boottime(struct timespec64 *ts) +{ + struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; + + *ts = timespec64_add(*ts, ns_offsets->boottime); +} + #else static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { @@ -66,6 +86,8 @@ static inline int timens_on_fork(struct nsproxy *nsproxy, return 0; } +static inline void timens_add_monotonic(struct timespec64 *ts) { } +static inline void timens_add_boottime(struct timespec64 *ts) { } #endif #endif /* _LINUX_TIMENS_H */ -- cgit v1.2.3 From 89dd8eecfe961fab4924dcd14f80cf2ab2820044 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 12 Nov 2019 01:27:01 +0000 Subject: time: Add do_timens_ktime_to_host() helper The helper subtracts namespace's clock offset from the given time and ensures that the result is within [0, KTIME_MAX]. Co-developed-by: Dmitry Safonov Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-13-dima@arista.com --- include/linux/time_namespace.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index d7e3b4994e31..34ee110b5c35 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -59,6 +59,19 @@ static inline void timens_add_boottime(struct timespec64 *ts) *ts = timespec64_add(*ts, ns_offsets->boottime); } +ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, + struct timens_offsets *offsets); + +static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) +{ + struct time_namespace *ns = current->nsproxy->time_ns; + + if (likely(ns == &init_time_ns)) + return tim; + + return do_timens_ktime_to_host(clockid, tim, &ns->offsets); +} + #else static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { @@ -88,6 +101,10 @@ static inline int timens_on_fork(struct nsproxy *nsproxy, static inline void timens_add_monotonic(struct timespec64 *ts) { } static inline void timens_add_boottime(struct timespec64 *ts) { } +static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) +{ + return tim; +} #endif #endif /* _LINUX_TIMENS_H */ -- cgit v1.2.3 From ea2d1f7fce0f18b67f915c00c6a7a6860116bc92 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 12 Nov 2019 01:27:05 +0000 Subject: hrtimers: Prepare hrtimer_nanosleep() for time namespaces clock_nanosleep() accepts absolute values of expiration time when TIMER_ABSTIME flag is set. This absolute value is inside the task's time namespace, and has to be converted to the host's time. There is timens_ktime_to_host() helper for converting time, but it accepts ktime argument. As a preparation, make hrtimer_nanosleep() accept a clock value in ktime instead of timespec64. Co-developed-by: Dmitry Safonov Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-17-dima@arista.com --- include/linux/hrtimer.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 1f98b52118f0..15c8ac313678 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -508,8 +508,7 @@ static inline u64 hrtimer_forward_now(struct hrtimer *timer, /* Precise sleep: */ extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); -extern long hrtimer_nanosleep(const struct timespec64 *rqtp, - const enum hrtimer_mode mode, +extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid); extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, -- cgit v1.2.3 From 660fd04f9317172ae90f414c68b18a26ae88a829 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Nov 2019 01:27:09 +0000 Subject: lib/vdso: Prepare for time namespace support To support time namespaces in the vdso with a minimal impact on regular non time namespace affected tasks, the namespace handling needs to be hidden in a slow path. The most obvious place is vdso_seq_begin(). If a task belongs to a time namespace then the VVAR page which contains the system wide vdso data is replaced with a namespace specific page which has the same layout as the VVAR page. That page has vdso_data->seq set to 1 to enforce the slow path and vdso_data->clock_mode set to VCLOCK_TIMENS to enforce the time namespace handling path. The extra check in the case that vdso_data->seq is odd, e.g. a concurrent update of the vdso data is in progress, is not really affecting regular tasks which are not part of a time namespace as the task is spin waiting for the update to finish and vdso_data->seq to become even again. If a time namespace task hits that code path, it invokes the corresponding time getter function which retrieves the real VVAR page, reads host time and then adds the offset for the requested clock which is stored in the special VVAR page. If VDSO time namespace support is disabled the whole magic is compiled out. Initial testing shows that the disabled case is almost identical to the host case which does not take the slow timens path. With the special timens page installed the performance hit is constant time and in the range of 5-7%. For the vdso functions which are not using the sequence count an unconditional check for vdso_data->clock_mode is added which switches to the real vdso when the clock_mode is VCLOCK_TIMENS. [avagin: Make do_hres_timens() work with raw clocks too: choose vdso_data pointer by CS_RAW offset.] Suggested-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-21-dima@arista.com --- include/linux/time.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 8e10b9dbd8c2..8ef5e5cc9f57 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -110,4 +110,10 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its) * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)). */ #define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l)) + +struct timens_offset { + s64 sec; + u64 nsec; +}; + #endif -- cgit v1.2.3 From 64b302ab66c5965702693e79690823ca120288b9 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 12 Nov 2019 01:27:10 +0000 Subject: x86/vdso: Provide vdso_data offset on vvar_page VDSO support for time namespaces needs to set up a page with the same layout as VVAR. That timens page will be placed on position of VVAR page inside namespace. That page has vdso_data->seq set to 1 to enforce the slow path and vdso_data->clock_mode set to VCLOCK_TIMENS to enforce the time namespace handling path. To prepare the time namespace page the kernel needs to know the vdso_data offset. Provide arch_get_vdso_data() helper for locating vdso_data on VVAR page. Co-developed-by: Andrei Vagin Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-22-dima@arista.com --- include/linux/time_namespace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 34ee110b5c35..063a343d1d78 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -39,6 +39,7 @@ struct time_namespace *copy_time_ns(unsigned long flags, struct time_namespace *old_ns); void free_time_ns(struct kref *kref); int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); +struct vdso_data *arch_get_vdso_data(void *vvar_page); static inline void put_time_ns(struct time_namespace *ns) { -- cgit v1.2.3 From afaa7b5ac7c87479fb5a626f87d2157af30d6401 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 12 Nov 2019 01:27:12 +0000 Subject: time: Allocate per-timens vvar page VDSO support for Time namespace needs to set up a page with the same layout as VVAR. That timens page will be placed on position of VVAR page inside namespace. That page contains time namespace clock offsets and it has vdso_data->seq set to 1 to enforce the slow path and vdso_data->clock_mode set to VCLOCK_TIMENS to enforce the time namespace handling path. Allocate the timens page during namespace creation. Setup the offsets when the first task enters the ns and freeze them to guarantee the pace of monotonic/boottime clocks and to avoid breakage of applications. The design decision is to have a global offset_lock which is used during namespace offsets setup and to freeze offsets when the first task joins the new time namespace. That is better in terms of memory usage compared to having a per namespace mutex that's used only during the setup period. Suggested-by: Andy Lutomirski Based-on-work-by: Thomas Gleixner Co-developed-by: Andrei Vagin Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-24-dima@arista.com --- include/linux/time_namespace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 063a343d1d78..6b7767f7df4a 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -23,6 +23,9 @@ struct time_namespace { struct ucounts *ucounts; struct ns_common ns; struct timens_offsets offsets; + struct page *vvar_page; + /* If set prevents changing offsets after any task joined namespace. */ + bool frozen_offsets; } __randomize_layout; extern struct time_namespace init_time_ns; -- cgit v1.2.3 From 70ddf65184ec1e8989322f35193e4fde7377f0cc Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 12 Nov 2019 01:27:15 +0000 Subject: x86/vdso: Zap vvar pages when switching to a time namespace The VVAR page layout depends on whether a task belongs to the root or non-root time namespace. Whenever a task changes its namespace, the VVAR page tables are cleared and then they will be re-faulted with a corresponding layout. Co-developed-by: Andrei Vagin Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-27-dima@arista.com --- include/linux/time_namespace.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 6b7767f7df4a..04a2ba8b8a06 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -31,6 +31,9 @@ struct time_namespace { extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS +extern int vdso_join_timens(struct task_struct *task, + struct time_namespace *ns); + static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { kref_get(&ns->kref); @@ -77,6 +80,12 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) } #else +static inline int vdso_join_timens(struct task_struct *task, + struct time_namespace *ns) +{ + return 0; +} + static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { return NULL; -- cgit v1.2.3 From 04a8682a71becdb639ec9c0d82b315a2baef7a5d Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 12 Nov 2019 01:27:16 +0000 Subject: fs/proc: Introduce /proc/pid/timens_offsets API to set time namespace offsets for children processes, i.e.: echo "$clockid $offset_sec $offset_nsec" > /proc/self/timens_offsets Co-developed-by: Dmitry Safonov Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20191112012724.250792-28-dima@arista.com --- include/linux/time_namespace.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 04a2ba8b8a06..824d54e057eb 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -52,6 +52,16 @@ static inline void put_time_ns(struct time_namespace *ns) kref_put(&ns->kref, free_time_ns); } +void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m); + +struct proc_timens_offset { + int clockid; + struct timespec64 val; +}; + +int proc_timens_set_offset(struct file *file, struct task_struct *p, + struct proc_timens_offset *offsets, int n); + static inline void timens_add_monotonic(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; -- cgit v1.2.3 From 444972b2b268c3272d39105bdc8d1266177f5d42 Mon Sep 17 00:00:00 2001 From: Rhys Perry Date: Sun, 29 Dec 2019 17:18:24 +0000 Subject: misc: alcor_pci: Add AU6625 to list of supported PCI_IDs I have added the AU6625 PCI_ID to the list of supported IDs: alcor_pci.c // Added au6625s ID to the array of supported devices alcor_pci.h // Added entry to define the PCI ID Made it fit in with the already submitted code: alcor_pci.c // Added config entry to that matches the one for au6601 >From general usage there seems to be no problems. Signed-off-by: Rhys Perry Link: https://lore.kernel.org/r/20191229171824.10308-1-rhysperry111@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/alcor_pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/alcor_pci.h b/include/linux/alcor_pci.h index 4416df597526..8274ed525e9f 100644 --- a/include/linux/alcor_pci.h +++ b/include/linux/alcor_pci.h @@ -17,6 +17,7 @@ #define PCI_ID_ALCOR_MICRO 0x1AEA #define PCI_ID_AU6601 0x6601 #define PCI_ID_AU6621 0x6621 +#define PCI_ID_AU6625 0x6625 #define MHZ_TO_HZ(freq) ((freq) * 1000 * 1000) -- cgit v1.2.3 From b059b7e0ec3208ff1e17cff6387d75a9fbab4e02 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 20 Dec 2019 17:44:49 +0100 Subject: regulator: core: Add regulator_is_equal() helper Add regulator_is_equal() helper to compare whether two regulators are the same. This is useful for checking whether two separate regulators in a driver are actually the same supply. Signed-off-by: Marek Vasut Cc: Fabio Estevam Cc: Igor Opaniuk Cc: Liam Girdwood Cc: Marcel Ziswiler Cc: Mark Brown Cc: Oleksandr Suvorov Link: https://lore.kernel.org/r/20191220164450.1395038-1-marex@denx.de Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 337a46391527..2c89d886595c 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -287,6 +287,8 @@ void regulator_bulk_set_supply_names(struct regulator_bulk_data *consumers, const char *const *supply_names, unsigned int num_supplies); +bool regulator_is_equal(struct regulator *reg1, struct regulator *reg2); + #else /* @@ -593,6 +595,11 @@ regulator_bulk_set_supply_names(struct regulator_bulk_data *consumers, { } +static inline bool +regulator_is_equal(struct regulator *reg1, struct regulator *reg2); +{ + return false; +} #endif static inline int regulator_set_voltage_triplet(struct regulator *regulator, -- cgit v1.2.3 From 984cfe4e252681d516df056b982e3c47b66fba92 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 18 Dec 2019 13:40:35 -0400 Subject: mm/mmu_notifier: Rename struct mmu_notifier_mm to mmu_notifier_subscriptions The name mmu_notifier_mm implies that the thing is a mm_struct pointer, and is difficult to abbreviate. The struct is actually holding the interval tree and hlist containing the notifiers subscribed to a mm. Use 'subscriptions' as the variable name for this struct instead of the really terrible and misleading 'mmn_mm'. Signed-off-by: Jason Gunthorpe --- include/linux/mm_types.h | 2 +- include/linux/mmu_notifier.h | 18 +++++++++--------- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 270aa8fd2800..e87bb864bdb2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -490,7 +490,7 @@ struct mm_struct { /* store ref to file /proc//exe symlink points to */ struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER - struct mmu_notifier_mm *mmu_notifier_mm; + struct mmu_notifier_subscriptions *notifier_subscriptions; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page_table_lock */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 9e6caa8ecd19..a302925fbc61 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -8,7 +8,7 @@ #include #include -struct mmu_notifier_mm; +struct mmu_notifier_subscriptions; struct mmu_notifier; struct mmu_notifier_range; struct mmu_interval_notifier; @@ -265,7 +265,7 @@ struct mmu_notifier_range { static inline int mm_has_notifiers(struct mm_struct *mm) { - return unlikely(mm->mmu_notifier_mm); + return unlikely(mm->notifier_subscriptions); } struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, @@ -364,7 +364,7 @@ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *mni, return READ_ONCE(mni->invalidate_seq) != seq; } -extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); +extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, @@ -480,15 +480,15 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, __mmu_notifier_invalidate_range(mm, start, end); } -static inline void mmu_notifier_mm_init(struct mm_struct *mm) +static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { - mm->mmu_notifier_mm = NULL; + mm->notifier_subscriptions = NULL; } -static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { if (mm_has_notifiers(mm)) - __mmu_notifier_mm_destroy(mm); + __mmu_notifier_subscriptions_destroy(mm); } @@ -692,11 +692,11 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, { } -static inline void mmu_notifier_mm_init(struct mm_struct *mm) +static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { } -static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { } -- cgit v1.2.3 From 1991722a70ffb1f0199a5690a31a5c7822007b1f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 14 Jan 2020 11:11:17 -0400 Subject: mm/mmu_notifiers: Use 'subscription' as the variable name for mmu_notifier The 'subscription' is placed on the 'notifier_subscriptions' list. This eliminates the poor name 'mn' for this variable. Signed-off-by: Jason Gunthorpe --- include/linux/mmu_notifier.h | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index a302925fbc61..4342fa75dc24 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -73,7 +73,7 @@ struct mmu_notifier_ops { * through the gart alias address, so leading to memory * corruption. */ - void (*release)(struct mmu_notifier *mn, + void (*release)(struct mmu_notifier *subscription, struct mm_struct *mm); /* @@ -85,7 +85,7 @@ struct mmu_notifier_ops { * Start-end is necessary in case the secondary MMU is mapping the page * at a smaller granularity than the primary MMU. */ - int (*clear_flush_young)(struct mmu_notifier *mn, + int (*clear_flush_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -95,7 +95,7 @@ struct mmu_notifier_ops { * latter, it is supposed to test-and-clear the young/accessed bitflag * in the secondary pte, but it may omit flushing the secondary tlb. */ - int (*clear_young)(struct mmu_notifier *mn, + int (*clear_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -106,7 +106,7 @@ struct mmu_notifier_ops { * frequently used without actually clearing the flag or tearing * down the secondary mapping on the page. */ - int (*test_young)(struct mmu_notifier *mn, + int (*test_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address); @@ -114,7 +114,7 @@ struct mmu_notifier_ops { * change_pte is called in cases that pte mapping to page is changed: * for example, when ksm remaps pte to point to a new shared page. */ - void (*change_pte)(struct mmu_notifier *mn, + void (*change_pte)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address, pte_t pte); @@ -169,9 +169,9 @@ struct mmu_notifier_ops { * invalidate_range_end. * */ - int (*invalidate_range_start)(struct mmu_notifier *mn, + int (*invalidate_range_start)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); - void (*invalidate_range_end)(struct mmu_notifier *mn, + void (*invalidate_range_end)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); /* @@ -192,8 +192,10 @@ struct mmu_notifier_ops { * of what was passed to invalidate_range_start()/end(), if * called between those functions. */ - void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, - unsigned long start, unsigned long end); + void (*invalidate_range)(struct mmu_notifier *subscription, + struct mm_struct *mm, + unsigned long start, + unsigned long end); /* * These callbacks are used with the get/put interface to manage the @@ -206,7 +208,7 @@ struct mmu_notifier_ops { * and cannot sleep. */ struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm); - void (*free_notifier)(struct mmu_notifier *mn); + void (*free_notifier)(struct mmu_notifier *subscription); }; /* @@ -280,14 +282,14 @@ mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) up_write(&mm->mmap_sem); return ret; } -void mmu_notifier_put(struct mmu_notifier *mn); +void mmu_notifier_put(struct mmu_notifier *subscription); void mmu_notifier_synchronize(void); -extern int mmu_notifier_register(struct mmu_notifier *mn, +extern int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); -extern int __mmu_notifier_register(struct mmu_notifier *mn, +extern int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); -extern void mmu_notifier_unregister(struct mmu_notifier *mn, +extern void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm); unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni); -- cgit v1.2.3 From 5292e24a6acf5694e0a32c31e3321964176bc17e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 14 Jan 2020 11:29:52 -0400 Subject: mm/mmu_notifiers: Use 'interval_sub' as the variable for mmu_interval_notifier The 'interval_sub' is placed on the 'notifier_subscriptions' interval tree. This eliminates the poor name 'mni' for this variable. Signed-off-by: Jason Gunthorpe --- include/linux/mmu_notifier.h | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 4342fa75dc24..736f6918335e 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -237,7 +237,7 @@ struct mmu_notifier { * was required but mmu_notifier_range_blockable(range) is false. */ struct mmu_interval_notifier_ops { - bool (*invalidate)(struct mmu_interval_notifier *mni, + bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); }; @@ -292,20 +292,21 @@ extern int __mmu_notifier_register(struct mmu_notifier *subscription, extern void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm); -unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni); -int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni, +unsigned long +mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub); +int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); int mmu_interval_notifier_insert_locked( - struct mmu_interval_notifier *mni, struct mm_struct *mm, + struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); -void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni); +void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence - * @mni - The mni passed to invalidate + * @interval_sub - The subscription passed to invalidate * @cur_seq - The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a @@ -316,15 +317,16 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni); * If the caller does not call mmu_interval_read_begin() or * mmu_interval_read_retry() then this call is not required. */ -static inline void mmu_interval_set_seq(struct mmu_interval_notifier *mni, - unsigned long cur_seq) +static inline void +mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, + unsigned long cur_seq) { - WRITE_ONCE(mni->invalidate_seq, cur_seq); + WRITE_ONCE(interval_sub->invalidate_seq, cur_seq); } /** * mmu_interval_read_retry - End a read side critical section against a VA range - * mni: The range + * interval_sub: The subscription * seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held @@ -336,15 +338,16 @@ static inline void mmu_interval_set_seq(struct mmu_interval_notifier *mni, * Returns true if an invalidation collided with this critical section, and * the caller should retry. */ -static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *mni, - unsigned long seq) +static inline bool +mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, + unsigned long seq) { - return mni->invalidate_seq != seq; + return interval_sub->invalidate_seq != seq; } /** * mmu_interval_check_retry - Test if a collision has occurred - * mni: The range + * interval_sub: The subscription * seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() @@ -359,11 +362,12 @@ static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *mni, * This call can be used as part of loops and other expensive operations to * expedite a retry. */ -static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *mni, - unsigned long seq) +static inline bool +mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, + unsigned long seq) { /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ - return READ_ONCE(mni->invalidate_seq) != seq; + return READ_ONCE(interval_sub->invalidate_seq) != seq; } extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm); -- cgit v1.2.3 From 52bbd2dcb42c21f183a2f59ad843a8d38fb68250 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 13 Jan 2020 23:32:48 +0100 Subject: mtd: spi-nor: remove unused enum spi_nor_ops The ops aren't used in any SPI NOR controller. Therefore, remove them altogether. Signed-off-by: Michael Walle Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 7e32adce72f7..5abd91cc6dfa 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -225,14 +225,6 @@ static inline u8 spi_nor_get_protocol_width(enum spi_nor_protocol proto) return spi_nor_get_protocol_data_nbits(proto); } -enum spi_nor_ops { - SPI_NOR_OPS_READ = 0, - SPI_NOR_OPS_WRITE, - SPI_NOR_OPS_ERASE, - SPI_NOR_OPS_LOCK, - SPI_NOR_OPS_UNLOCK, -}; - enum spi_nor_option_flags { SNOR_F_USE_FSR = BIT(0), SNOR_F_HAS_SR_TB = BIT(1), @@ -485,8 +477,8 @@ struct spi_nor; * opcode via write_reg(). */ struct spi_nor_controller_ops { - int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); - void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); + int (*prepare)(struct spi_nor *nor); + void (*unprepare)(struct spi_nor *nor); int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len); int (*write_reg)(struct spi_nor *nor, u8 opcode, const u8 *buf, size_t len); -- cgit v1.2.3 From e27f178793de16ca1b421f2c3f4bc3497b2ce723 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 12 Jan 2020 09:35:38 -0800 Subject: net: phy: Added IRQ print to phylink_bringup_phy() The information about the PHY attached to the PHYLINK instance is useful but is missing the IRQ prints that phy_attached_info() adds. phy_attached_info() is a bit long and it would not be possible to use phylink_info() anyway. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 5932bb8e9c35..3a70b756ac1a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1131,6 +1131,8 @@ static inline void phy_unlock_mdio_bus(struct phy_device *phydev) void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); +char *phy_attached_info_irq(struct phy_device *phydev) + __malloc; void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ -- cgit v1.2.3 From 76564261a7db80c5f5c624e0122a28787f266bdf Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 13 Jan 2020 23:31:40 +0100 Subject: net: macsec: introduce the macsec_context structure This patch introduces the macsec_context structure. It will be used in the kernel to exchange information between the common MACsec implementation (macsec.c) and the MACsec hardware offloading implementations. This structure contains pointers to MACsec specific structures which contain the actual MACsec configuration, and to the underlying device (phydev for now). Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3a70b756ac1a..be079a7bb40a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -332,6 +332,8 @@ struct phy_c45_device_ids { u32 device_ids[8]; }; +struct macsec_context; + /* phy_device: An instance of a PHY * * drv: Pointer to the driver for this PHY instance -- cgit v1.2.3 From 2e18135845b359f26c37df38ba56565496517c10 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 13 Jan 2020 23:31:42 +0100 Subject: net: phy: add MACsec ops in phy_device This patch adds a reference to MACsec ops in the phy_device, to allow PHYs to support offloading MACsec operations. The phydev lock will be held while calling those helpers. Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- include/linux/phy.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index be079a7bb40a..2929d0bc307f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -333,6 +333,7 @@ struct phy_c45_device_ids { }; struct macsec_context; +struct macsec_ops; /* phy_device: An instance of a PHY * @@ -356,6 +357,7 @@ struct macsec_context; * 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. * * speed, duplex, pause, supported, advertising, lp_advertising, * and autoneg are used like in mii_if_info @@ -455,6 +457,11 @@ struct phy_device { void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); void (*adjust_link)(struct net_device *dev); + +#if IS_ENABLED(CONFIG_MACSEC) + /* MACsec management functions */ + const struct macsec_ops *macsec_ops; +#endif }; #define to_phy_device(d) container_of(to_mdio_device(d), \ struct phy_device, mdio) -- cgit v1.2.3 From 5eee7bd7e245914e4e050c413dfe864e31805207 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 13 Jan 2020 18:42:26 -0500 Subject: net: skbuff: disambiguate argument and member for skb_list_walk_safe helper This worked before, because we made all callers name their next pointer "next". But in trying to be more "drop-in" ready, the silliness here is revealed. This commit fixes the problem by making the macro argument and the member use different names. Signed-off-by: Jason A. Donenfeld Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 016b3c4ab99a..aaf73b34f72f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1479,9 +1479,9 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb) } /* Iterate through singly-linked GSO fragments of an skb. */ -#define skb_list_walk_safe(first, skb, next) \ - for ((skb) = (first), (next) = (skb) ? (skb)->next : NULL; (skb); \ - (skb) = (next), (next) = (skb) ? (skb)->next : NULL) +#define skb_list_walk_safe(first, skb, next_skb) \ + for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ + (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { -- cgit v1.2.3 From fd39073dba8632575b920edefba2577e1b84262a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 6 Jan 2020 12:55:33 -0800 Subject: fs-verity: implement readahead of Merkle tree pages When fs-verity verifies data pages, currently it reads each Merkle tree page synchronously using read_mapping_page(). Therefore, when the Merkle tree pages aren't already cached, fs-verity causes an extra 4 KiB I/O request for every 512 KiB of data (assuming that the Merkle tree uses SHA-256 and 4 KiB blocks). This results in more I/O requests and performance loss than is strictly necessary. Therefore, implement readahead of the Merkle tree pages. For simplicity, we take advantage of the fact that the kernel already does readahead of the file's *data*, just like it does for any other file. Due to this, we don't really need a separate readahead state (struct file_ra_state) just for the Merkle tree, but rather we just need to piggy-back on the existing data readahead requests. We also only really need to bother with the first level of the Merkle tree, since the usual fan-out factor is 128, so normally over 99% of Merkle tree I/O requests are for the first level. Therefore, make fsverity_verify_bio() enable readahead of the first Merkle tree level, for up to 1/4 the number of pages in the bio, when it sees that the REQ_RAHEAD flag is set on the bio. The readahead size is then passed down to ->read_merkle_tree_page() for the filesystem to (optionally) implement if it sees that the requested page is uncached. While we're at it, also make build_merkle_tree_level() set the Merkle tree readahead size, since it's easy to do there. However, for now don't set the readahead size in fsverity_verify_page(), since currently it's only used to verify holes on ext4 and f2fs, and it would need parameters added to know how much to read ahead. This patch significantly improves fs-verity sequential read performance. Some quick benchmarks with 'cat'-ing a 250MB file after dropping caches: On an ARM64 phone (using sha256-ce): Before: 217 MB/s After: 263 MB/s (compare to sha256sum of non-verity file: 357 MB/s) In an x86_64 VM (using sha256-avx2): Before: 173 MB/s After: 215 MB/s (compare to sha256sum of non-verity file: 223 MB/s) Link: https://lore.kernel.org/r/20200106205533.137005-1-ebiggers@kernel.org Reviewed-by: Theodore Ts'o Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 3b6b8ccebe7d..ecc604e61d61 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -77,6 +77,10 @@ struct fsverity_operations { * * @inode: the inode * @index: 0-based index of the page within the Merkle tree + * @num_ra_pages: The number of Merkle tree pages that should be + * prefetched starting at @index if the page at @index + * isn't already cached. Implementations may ignore this + * argument; it's only a performance optimization. * * This can be called at any time on an open verity file, as well as * between ->begin_enable_verity() and ->end_enable_verity(). It may be @@ -87,7 +91,8 @@ struct fsverity_operations { * Return: the page on success, ERR_PTR() on failure */ struct page *(*read_merkle_tree_page)(struct inode *inode, - pgoff_t index); + pgoff_t index, + unsigned long num_ra_pages); /** * Write a Merkle tree block to the given inode. -- cgit v1.2.3 From c64cd6e34ea340adbb2a0a2f99cc884b96dcdca5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 10 Jan 2020 17:17:19 -0500 Subject: reimplement path_mountpoint() with less magic ... and get rid of a bunch of bugs in it. Background: the reason for path_mountpoint() is that umount() really doesn't want attempts to revalidate the root of what it's trying to umount. The thing we want to avoid actually happen from complete_walk(); solution was to do something parallel to normal path_lookupat() and it both went overboard and got the boilerplate subtly (and not so subtly) wrong. A better solution is to do pretty much what the normal path_lookupat() does, but instead of complete_walk() do unlazy_walk(). All it takes to avoid that ->d_weak_revalidate() call... mountpoint_last() goes away, along with everything it got wrong, and so does the magic around LOOKUP_NO_REVAL. Another source of bugs is that when we traverse mounts at the final location (and we need to do that - umount . expects to get whatever's overmounting ., if any, out of the lookup) we really ought to take care of ->d_manage() - as it is, manual umount of autofs automount in progress can lead to unpleasant surprises for the daemon. Easily solved by using handle_lookup_down() instead of follow_mount(). Tested-by: Ian Kent Signed-off-by: Al Viro --- include/linux/namei.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 7fe7b87a3ded..07bfb0874033 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -34,7 +34,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; /* internal use only */ #define LOOKUP_PARENT 0x0010 -#define LOOKUP_NO_REVAL 0x0080 #define LOOKUP_JUMPED 0x1000 #define LOOKUP_ROOT 0x2000 #define LOOKUP_ROOT_GRABBED 0x0008 -- cgit v1.2.3 From b267ddf6a5abecad100e7139617ffb12415f9156 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 31 Dec 2019 18:42:35 +0100 Subject: usb: phy-generic: Delete unused platform data The last user of the phy generic platform data was deleted in commit 1e041b6f313aaa966612a7e415cfc09c90d6b829 ("usb: dwc3: exynos: Remove dead code"). So get rid of the platform data, which rids us of another consumer of the legacy GPIO API at the same time. Make sure we only inlcude which is all we use. Alter the usb_phy_gen_create_phy() function prototype to not pass any platform data as this is just hardcoded to NULL at all locations calling it in the kernel. Move the devm_gpiod_get* calls out of the if (of_node) parenthesis, as these calls are generic and do not depend on device tree, they are used by any hardware description. Cc: Marek Szyprowski Cc: Felipe Balbi Signed-off-by: Linus Walleij Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/usb_phy_generic.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/usb_phy_generic.h b/include/linux/usb/usb_phy_generic.h index 7408cf52c710..cd9e70a552a0 100644 --- a/include/linux/usb/usb_phy_generic.h +++ b/include/linux/usb/usb_phy_generic.h @@ -3,18 +3,6 @@ #define __LINUX_USB_NOP_XCEIV_H #include -#include - -struct usb_phy_generic_platform_data { - enum usb_phy_type type; - unsigned long clk_rate; - - /* if set fails with -EPROBE_DEFER if can't get regulator */ - unsigned int needs_vcc:1; - unsigned int needs_reset:1; /* deprecated */ - int gpio_reset; - struct gpio_desc *gpiod_vbus; -}; #if IS_ENABLED(CONFIG_NOP_USB_XCEIV) /* sometimes transceivers are accessed only through e.g. ULPI */ -- cgit v1.2.3 From 242587616710576808dc8d7cdf18cfe0d7bf9831 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 14 Jan 2020 16:28:19 +0800 Subject: gpiolib: Add support for the irqdomain which doesn't use irq_fwspec as arg Some gpio's parent irqdomain may not use the struct irq_fwspec as argument, such as msi irqdomain. So rename the callback populate_parent_fwspec() to populate_parent_alloc_arg() and make it allocate and populate the specific struct which is needed by the parent irqdomain. Signed-off-by: Kevin Hao Link: https://lore.kernel.org/r/20200114082821.14015-3-haokexin@gmail.com Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index e2480ef94c55..9bb43467ed11 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -94,16 +94,15 @@ struct gpio_irq_chip { unsigned int *parent_type); /** - * @populate_parent_fwspec: + * @populate_parent_alloc_arg : * - * This optional callback populates the &struct irq_fwspec for the - * parent's IRQ domain. If this is not specified, then + * This optional callback allocates and populates the specific struct + * for the parent's IRQ domain. If this is not specified, then * &gpiochip_populate_parent_fwspec_twocell will be used. A four-cell * variant named &gpiochip_populate_parent_fwspec_fourcell is also * available. */ - void (*populate_parent_fwspec)(struct gpio_chip *chip, - struct irq_fwspec *fwspec, + void *(*populate_parent_alloc_arg)(struct gpio_chip *chip, unsigned int parent_hwirq, unsigned int parent_type); @@ -537,26 +536,22 @@ struct bgpio_pdata { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY -void gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *chip, - struct irq_fwspec *fwspec, +void *gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *chip, unsigned int parent_hwirq, unsigned int parent_type); -void gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *chip, - struct irq_fwspec *fwspec, +void *gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *chip, unsigned int parent_hwirq, unsigned int parent_type); #else -static inline void gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *chip, - struct irq_fwspec *fwspec, +static inline void *gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *chip, unsigned int parent_hwirq, unsigned int parent_type) { } -static inline void gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *chip, - struct irq_fwspec *fwspec, +static inline void *gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *chip, unsigned int parent_hwirq, unsigned int parent_type) { -- cgit v1.2.3 From 7788f549ed8cfbecd75c10e1a1988812adba49d8 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 14 Jan 2020 17:19:12 +0000 Subject: serial_core: Remove unused member in uart_port It should remove the align-padding before @name. [yes, there's a "hole" in the structure now, but that's fine, no one cares. If they do care, the whole thing should be restructured using pahole to find a better ordering. Removing this field is good as some drivers have been known to abuse it for other things when they shouldn't have been doing that. -- gregkh] Signed-off-by: Dmitry Safonov Link: https://lore.kernel.org/r/20200114171912.261787-4-dima@arista.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 255e86a474e9..52404ef1694e 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -246,7 +246,6 @@ struct uart_port { unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char unused; 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 0468e667a5bead9c1b7ded92861b5a98d8d78745 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 15 Jan 2020 12:02:58 +1100 Subject: regulator fix for "regulator: core: Add regulator_is_equal() helper" Signed-off-by: Stephen Rothwell Link: https://lore.kernel.org/r/20200115120258.0e535fcb@canb.auug.org.au Acked-by: Marek Vasut Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 2c89d886595c..6a92fd3105a3 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -596,7 +596,7 @@ regulator_bulk_set_supply_names(struct regulator_bulk_data *consumers, } static inline bool -regulator_is_equal(struct regulator *reg1, struct regulator *reg2); +regulator_is_equal(struct regulator *reg1, struct regulator *reg2) { return false; } -- cgit v1.2.3 From a55d3297be587c6baa0242ae0fbb92489e576005 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Dec 2019 07:30:57 -0500 Subject: nfs: don't bother passing nfs_subversion to ->try_mount() and nfs_fs_mount_common() Reviewed-by: David Howells Signed-off-by: Al Viro Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 72d5695c1b47..3ee2ad642cbc 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1655,8 +1655,7 @@ struct nfs_rpc_ops { struct nfs_fsinfo *); struct vfsmount *(*submount) (struct nfs_server *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); - struct dentry *(*try_mount) (int, const char *, struct nfs_mount_info *, - struct nfs_subversion *); + struct dentry *(*try_mount) (int, const char *, struct nfs_mount_info *); int (*getattr) (struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *, struct inode *); -- cgit v1.2.3 From 0c38f2131df9865aa9fb24b7ad30a9657588e0e1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Dec 2019 07:31:00 -0500 Subject: nfs: don't pass nfs_subversion to ->create_server() pick it from mount_info Reviewed-by: David Howells Signed-off-by: Al Viro Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 3ee2ad642cbc..17527f6e6360 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1722,7 +1722,7 @@ struct nfs_rpc_ops { struct nfs_client *(*init_client) (struct nfs_client *, const struct nfs_client_initdata *); void (*free_client) (struct nfs_client *); - struct nfs_server *(*create_server)(struct nfs_mount_info *, struct nfs_subversion *); + struct nfs_server *(*create_server)(struct nfs_mount_info *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); }; -- cgit v1.2.3 From f2aedb713c284429987dc66c7aaf38decfc8da2a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 10 Dec 2019 07:31:13 -0500 Subject: NFS: Add fs_context support. Add filesystem context support to NFS, parsing the options in advance and attaching the information to struct nfs_fs_context. The highlights are: (*) Merge nfs_mount_info and nfs_clone_mount into nfs_fs_context. This structure represents NFS's superblock config. (*) Make use of the VFS's parsing support to split comma-separated lists (*) Pin the NFS protocol module in the nfs_fs_context. (*) Attach supplementary error information to fs_context. This has the downside that these strings must be static and can't be formatted. (*) Remove the auxiliary file_system_type structs since the information necessary can be conveyed in the nfs_fs_context struct instead. (*) Root mounts are made by duplicating the config for the requested mount so as to have the same parameters. Submounts pick up their parameters from the parent superblock. [AV -- retrans is u32, not string] [SM -- Renamed cfg to ctx in a few functions in an earlier patch] [SM -- Moved fs_context mount option parsing to an earlier patch] [SM -- Moved fs_context error logging to a later patch] [SM -- Fixed printks in nfs4_try_get_tree() and nfs4_get_referral_tree()] [SM -- Added is_remount_fc() helper] [SM -- Deferred some refactoring to a later patch] [SM -- Fixed referral mounts, which were broken in the original patch] [SM -- Fixed leak of nfs_fattr when fs_context is freed] Signed-off-by: David Howells Signed-off-by: Al Viro Signed-off-by: Scott Mayhew Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 17527f6e6360..574741d5418d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1639,6 +1639,7 @@ struct nfs_subversion; struct nfs_mount_info; struct nfs_client_initdata; struct nfs_pageio_descriptor; +struct fs_context; /* * RPC procedure vector for NFSv2/NFSv3 demuxing @@ -1653,9 +1654,8 @@ struct nfs_rpc_ops { int (*getroot) (struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); - struct vfsmount *(*submount) (struct nfs_server *, struct dentry *, - struct nfs_fh *, struct nfs_fattr *); - struct dentry *(*try_mount) (int, const char *, struct nfs_mount_info *); + int (*submount) (struct fs_context *, struct nfs_server *); + int (*try_get_tree) (struct fs_context *); int (*getattr) (struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *, struct inode *); -- cgit v1.2.3 From 62a55d088cd87d480a6fd67b0d63b14ccae80838 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Tue, 10 Dec 2019 07:31:14 -0500 Subject: NFS: Additional refactoring for fs_context conversion Split out from commit "NFS: Add fs_context support." This patch adds additional refactoring for the conversion of NFS to use fs_context, namely: (*) Merge nfs_mount_info and nfs_clone_mount into nfs_fs_context. nfs_clone_mount has had several fields removed, and nfs_mount_info has been removed altogether. (*) Various functions now take an fs_context as an argument instead of nfs_mount_info, nfs_fs_context, etc. Signed-off-by: Scott Mayhew Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 574741d5418d..0a36c6f62b58 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1722,7 +1722,7 @@ struct nfs_rpc_ops { struct nfs_client *(*init_client) (struct nfs_client *, const struct nfs_client_initdata *); void (*free_client) (struct nfs_client *); - struct nfs_server *(*create_server)(struct nfs_mount_info *); + struct nfs_server *(*create_server)(struct fs_context *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); }; -- cgit v1.2.3 From 52879b464a6a85ff4070786e8a5c876233ac6f67 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 11 Nov 2019 21:16:21 +0100 Subject: sunrpc: convert to time64_t for expiry Using signed 32-bit types for UTC time leads to the y2038 overflow, which is what happens in the sunrpc code at the moment. This changes the sunrpc code over to use time64_t where possible. The one exception is the gss_import_v{1,2}_context() function for kerberos5, which uses 32-bit timestamps in the protocol. Here, we can at least treat the numbers as 'unsigned', which extends the range from 2038 to 2106. Signed-off-by: Arnd Bergmann Signed-off-by: Anna Schumaker --- include/linux/sunrpc/gss_api.h | 4 ++-- include/linux/sunrpc/gss_krb5.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index bd691e08be3b..1cc6cefb1220 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -48,7 +48,7 @@ int gss_import_sec_context( size_t bufsize, struct gss_api_mech *mech, struct gss_ctx **ctx_id, - time_t *endtime, + time64_t *endtime, gfp_t gfp_mask); u32 gss_get_mic( struct gss_ctx *ctx_id, @@ -108,7 +108,7 @@ struct gss_api_ops { const void *input_token, size_t bufsize, struct gss_ctx *ctx_id, - time_t *endtime, + time64_t *endtime, gfp_t gfp_mask); u32 (*gss_get_mic)( struct gss_ctx *ctx_id, diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 02c0412e368c..c1d77dd8ed41 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -106,9 +106,9 @@ struct krb5_ctx { struct crypto_sync_skcipher *initiator_enc_aux; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; - s32 endtime; atomic_t seq_send; atomic64_t seq_send64; + time64_t endtime; struct xdr_netobj mech_used; u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; -- cgit v1.2.3 From b32d285539e061dc3961e86f825d4ded5ba6de14 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 6 Jan 2020 15:25:02 -0500 Subject: SUNRPC: Remove broken gss_mech_list_pseudoflavors() Remove gss_mech_list_pseudoflavors() and its callers. This is part of an unused API, and could leak an RCU reference if it were ever called. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/auth.h | 2 -- include/linux/sunrpc/gss_api.h | 3 --- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index e9ec742796e7..4f6b28487f28 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -113,7 +113,6 @@ struct rpc_authops { int (*hash_cred)(struct auth_cred *, unsigned int); struct rpc_cred * (*lookup_cred)(struct rpc_auth *, struct auth_cred *, int); struct rpc_cred * (*crcreate)(struct rpc_auth*, struct auth_cred *, int, gfp_t); - int (*list_pseudoflavors)(rpc_authflavor_t *, int); rpc_authflavor_t (*info2flavor)(struct rpcsec_gss_info *); int (*flavor2info)(rpc_authflavor_t, struct rpcsec_gss_info *); @@ -158,7 +157,6 @@ rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t, struct rpcsec_gss_info *); int rpcauth_get_gssinfo(rpc_authflavor_t, struct rpcsec_gss_info *); -int rpcauth_list_flavors(rpc_authflavor_t *, int); struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int, gfp_t); void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *); struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *, int); diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 1cc6cefb1220..48c1b1674cbf 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -150,9 +150,6 @@ struct gss_api_mech *gss_mech_get_by_name(const char *); /* Similar, but get by pseudoflavor. */ struct gss_api_mech *gss_mech_get_by_pseudoflavor(u32); -/* Fill in an array with a list of supported pseudoflavors */ -int gss_mech_list_pseudoflavors(rpc_authflavor_t *, int); - struct gss_api_mech * gss_mech_get(struct gss_api_mech *); /* For every successful gss_mech_get or gss_mech_get_by_* call there must be a -- cgit v1.2.3 From c74dfe97c104bda5144bfa8193d8e5ea67d5da7f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 6 Jan 2020 15:39:37 -0500 Subject: NFS: Add mount option 'softreval' Add a mount option 'softreval' that allows attribute revalidation 'getattr' calls to time out, and causes them to fall back to using the cached attributes. The use case for this option is for ensuring that we can still (slowly) traverse paths and use cached information even when the server is down. Once the server comes back up again, the getattr calls start succeeding, and the caches will revalidate as usual. The 'softreval' mount option is automatically enabled if you have specified 'softerr'. It can be turned off using the options 'nosoftreval', or 'hard'. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index c176f705bf98..465fa98258a3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -152,6 +152,7 @@ struct nfs_server { #define NFS_MOUNT_LOCAL_FLOCK 0x100000 #define NFS_MOUNT_LOCAL_FCNTL 0x200000 #define NFS_MOUNT_SOFTERR 0x400000 +#define NFS_MOUNT_SOFTREVAL 0x800000 unsigned int caps; /* server capabilities */ unsigned int rsize; /* read size */ -- cgit v1.2.3 From 89535821c04256964e266bf585cf224f65e08983 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 15 Jan 2020 13:52:29 +0100 Subject: iommu/arm-smmu-v3: Parse PASID devicetree property of platform devices For platform devices that support SubstreamID (SSID), firmware provides the number of supported SSID bits. Restrict it to what the SMMU supports and cache it into master->ssid_bits, which will also be used for PCI PASID. Reviewed-by: Eric Auger Reviewed-by: Jonathan Cameron Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- include/linux/iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 90007c92ad2d..c1ad15228447 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -579,6 +579,7 @@ struct iommu_group *fsl_mc_device_group(struct device *dev); * @ops: ops for this device's IOMMU * @iommu_fwnode: firmware handle for this device's IOMMU * @iommu_priv: IOMMU driver private data for this device + * @num_pasid_bits: number of PASID bits supported by this device * @num_ids: number of associated device IDs * @ids: IDs which this device may present to the IOMMU */ @@ -587,6 +588,7 @@ struct iommu_fwspec { struct fwnode_handle *iommu_fwnode; void *iommu_priv; u32 flags; + u32 num_pasid_bits; unsigned int num_ids; u32 ids[1]; }; -- cgit v1.2.3 From 5a4549fd790500d7db94b7d2af6d60cee42110c3 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 15 Jan 2020 13:52:38 +0100 Subject: PCI/ATS: Add PASID stubs The SMMUv3 driver, which may be built without CONFIG_PCI, will soon gain PASID support. Partially revert commit c6e9aefbf9db ("PCI/ATS: Remove unused PRI and PASID stubs") to re-introduce the PASID stubs, and avoid adding more #ifdefs to the SMMU driver. Acked-by: Bjorn Helgaas Reviewed-by: Eric Auger Reviewed-by: Jonathan Cameron Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- include/linux/pci-ats.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 5d62e78946a3..d08f0869f121 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -33,6 +33,9 @@ void pci_disable_pasid(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ +static inline int pci_enable_pasid(struct pci_dev *pdev, int features) +{ return -EINVAL; } +static inline void pci_disable_pasid(struct pci_dev *pdev) { } static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; } static inline int pci_max_pasids(struct pci_dev *pdev) -- cgit v1.2.3 From a6b0ef9a7d03bb78d37c420753741ef8a082160b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Mon, 6 Jan 2020 12:03:28 -0700 Subject: PCI/switchtec: Add support for Intercomm Notify and Upstream Error Containment Add support for the Inter Fabric Manager Communication (Intercomm) Notify event in PAX variants of Switchtec hardware and the Upstream Error Containment port in the MR1 release of Gen3 firmware. Link: https://lore.kernel.org/r/20200106190337.2428-4-logang@deltatee.com Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index e295515bc3f3..b4ba3a38f30f 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -196,7 +196,9 @@ struct part_cfg_regs { u32 mrpc_comp_async_data[5]; u32 dyn_binding_hdr; u32 dyn_binding_data[5]; - u32 reserved4[159]; + u32 intercomm_notify_hdr; + u32 intercomm_notify_data[5]; + u32 reserved4[153]; } __packed; enum { @@ -320,7 +322,8 @@ struct pff_csr_regs { u32 dpc_data[5]; u32 cts_hdr; u32 cts_data[5]; - u32 reserved3[6]; + u32 uec_hdr; + u32 uec_data[5]; u32 hotplug_hdr; u32 hotplug_data[5]; u32 ier_hdr; -- cgit v1.2.3 From fcccd282b633ab9fc7d53ff8ccf82ab5c30a0985 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Tue, 14 Jan 2020 20:56:42 -0700 Subject: PCI/switchtec: Rename generation-specific constants Gen4 hardware will have different values for the SWITCHTEC_X_RUNNING and SWITCHTEC_IOCTL_NUM_PARTITIONS, so rename them with GEN3 in their name. No functional changes intended. Link: https://lore.kernel.org/r/20200115035648.2578-2-logang@deltatee.com Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index b4ba3a38f30f..4ee450487fe4 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -98,10 +98,10 @@ struct sw_event_regs { } __packed; enum { - SWITCHTEC_CFG0_RUNNING = 0x04, - SWITCHTEC_CFG1_RUNNING = 0x05, - SWITCHTEC_IMG0_RUNNING = 0x03, - SWITCHTEC_IMG1_RUNNING = 0x07, + SWITCHTEC_GEN3_CFG0_RUNNING = 0x04, + SWITCHTEC_GEN3_CFG1_RUNNING = 0x05, + SWITCHTEC_GEN3_IMG0_RUNNING = 0x03, + SWITCHTEC_GEN3_IMG1_RUNNING = 0x07, }; struct sys_info_regs { -- cgit v1.2.3 From b13313a01a6a607bd92268822d498d5c7356ca71 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Tue, 14 Jan 2020 20:56:43 -0700 Subject: PCI/switchtec: Add 'generation' variable Add a generation variable passed through the device ID table and test for Gen3-specific registers. This will allow us to add Gen4 and other devices that extend the programming model. Link: https://lore.kernel.org/r/20200115035648.2578-3-logang@deltatee.com Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 4ee450487fe4..d0b5816549ed 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -32,6 +32,10 @@ enum { SWITCHTEC_GAS_PFF_CSR_OFFSET = 0x134000, }; +enum switchtec_gen { + SWITCHTEC_GEN3, +}; + struct mrpc_regs { u8 input_data[SWITCHTEC_MRPC_PAYLOAD_SIZE]; u8 output_data[SWITCHTEC_MRPC_PAYLOAD_SIZE]; @@ -358,6 +362,8 @@ struct switchtec_dev { struct device dev; struct cdev cdev; + enum switchtec_gen gen; + int partition; int partition_count; int pff_csr_count; -- cgit v1.2.3 From 993d208daaebebc3f3ec211e862a413a90e8d69b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Tue, 14 Jan 2020 20:56:45 -0700 Subject: PCI/switchtec: Separate Gen3 register structures into unions Since the sys_info and flash_info registers differ significantly in Gen4 hardware, separate out the Gen3 registers into their own structure with a union in the main structure. No functional changes intended. Link: https://lore.kernel.org/r/20200115035648.2578-5-logang@deltatee.com Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 41 +++++++++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index d0b5816549ed..32a20d10b02e 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -108,10 +108,7 @@ enum { SWITCHTEC_GEN3_IMG1_RUNNING = 0x07, }; -struct sys_info_regs { - u32 device_id; - u32 device_version; - u32 firmware_version; +struct sys_info_regs_gen3 { u32 reserved1; u32 vendor_table_revision; u32 table_format_version; @@ -128,26 +125,36 @@ struct sys_info_regs { u8 component_revision; } __packed; -struct flash_info_regs { +struct sys_info_regs { + u32 device_id; + u32 device_version; + u32 firmware_version; + union { + struct sys_info_regs_gen3 gen3; + }; +} __packed; + +struct partition_info { + u32 address; + u32 length; +}; + +struct flash_info_regs_gen3 { u32 flash_part_map_upd_idx; - struct active_partition_info { + struct active_partition_info_gen3 { u32 address; u32 build_version; u32 build_string; } active_img; - struct active_partition_info active_cfg; - struct active_partition_info inactive_img; - struct active_partition_info inactive_cfg; + struct active_partition_info_gen3 active_cfg; + struct active_partition_info_gen3 inactive_img; + struct active_partition_info_gen3 inactive_cfg; u32 flash_length; - struct partition_info { - u32 address; - u32 length; - } cfg0; - + struct partition_info cfg0; struct partition_info cfg1; struct partition_info img0; struct partition_info img1; @@ -155,6 +162,12 @@ struct flash_info_regs { struct partition_info vendor[8]; }; +struct flash_info_regs { + union { + struct flash_info_regs_gen3 gen3; + }; +}; + enum { SWITCHTEC_NTB_REG_INFO_OFFSET = 0x0000, SWITCHTEC_NTB_REG_CTRL_OFFSET = 0x4000, -- cgit v1.2.3 From a3321ca394082f403b447646d81c18ff6b39f4a6 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Tue, 14 Jan 2020 20:56:46 -0700 Subject: PCI/switchtec: Add Gen4 system info register support Add the Gen4-specific system info registers and ensure their usage is guarded by a check on the device's generation. Link: https://lore.kernel.org/r/20200115035648.2578-6-logang@deltatee.com Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 32a20d10b02e..d012520e5cc5 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -34,6 +34,7 @@ enum { enum switchtec_gen { SWITCHTEC_GEN3, + SWITCHTEC_GEN4, }; struct mrpc_regs { @@ -125,12 +126,54 @@ struct sys_info_regs_gen3 { u8 component_revision; } __packed; +struct sys_info_regs_gen4 { + u16 gas_layout_ver; + u8 evlist_ver; + u8 reserved1; + u16 mgmt_cmd_set_ver; + u16 fabric_cmd_set_ver; + u32 reserved2[2]; + u8 mrpc_uart_ver; + u8 mrpc_twi_ver; + u8 mrpc_eth_ver; + u8 mrpc_inband_ver; + u32 reserved3[7]; + u32 fw_update_tmo; + u32 xml_version_cfg; + u32 xml_version_img; + u32 partition_id; + u16 bl2_running; + u16 cfg_running; + u16 img_running; + u16 key_running; + u32 reserved4[43]; + u32 vendor_seeprom_twi; + u32 vendor_table_revision; + u32 vendor_specific_info[2]; + u16 p2p_vendor_id; + u16 p2p_device_id; + u8 p2p_revision_id; + u8 reserved5[3]; + u32 p2p_class_id; + u16 subsystem_vendor_id; + u16 subsystem_id; + u32 p2p_serial_number[2]; + u8 mac_addr[6]; + u8 reserved6[2]; + u32 reserved7[3]; + char vendor_id[8]; + char product_id[24]; + char product_revision[2]; + u16 reserved8; +} __packed; + struct sys_info_regs { u32 device_id; u32 device_version; u32 firmware_version; union { struct sys_info_regs_gen3 gen3; + struct sys_info_regs_gen4 gen4; }; } __packed; -- cgit v1.2.3 From 4efa1d2e36976d7b26f2e67f4c838330fbc91299 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Tue, 14 Jan 2020 20:56:47 -0700 Subject: PCI/switchtec: Add Gen4 flash information interface support Add the new flash_info registers struct and the implementation of ioctl_flash_part_info() for the new Gen4 hardware. [logang@deltatee.com: rewrote commit message] Link: https://lore.kernel.org/r/20200115035648.2578-7-logang@deltatee.com Signed-off-by: Kelvin Cao Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index d012520e5cc5..e85155244135 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -109,6 +109,30 @@ enum { SWITCHTEC_GEN3_IMG1_RUNNING = 0x07, }; +enum { + SWITCHTEC_GEN4_MAP0_RUNNING = 0x00, + SWITCHTEC_GEN4_MAP1_RUNNING = 0x01, + SWITCHTEC_GEN4_KEY0_RUNNING = 0x02, + SWITCHTEC_GEN4_KEY1_RUNNING = 0x03, + SWITCHTEC_GEN4_BL2_0_RUNNING = 0x04, + SWITCHTEC_GEN4_BL2_1_RUNNING = 0x05, + SWITCHTEC_GEN4_CFG0_RUNNING = 0x06, + SWITCHTEC_GEN4_CFG1_RUNNING = 0x07, + SWITCHTEC_GEN4_IMG0_RUNNING = 0x08, + SWITCHTEC_GEN4_IMG1_RUNNING = 0x09, +}; + +enum { + SWITCHTEC_GEN4_KEY0_ACTIVE = 0, + SWITCHTEC_GEN4_KEY1_ACTIVE = 1, + SWITCHTEC_GEN4_BL2_0_ACTIVE = 0, + SWITCHTEC_GEN4_BL2_1_ACTIVE = 1, + SWITCHTEC_GEN4_CFG0_ACTIVE = 0, + SWITCHTEC_GEN4_CFG1_ACTIVE = 1, + SWITCHTEC_GEN4_IMG0_ACTIVE = 0, + SWITCHTEC_GEN4_IMG1_ACTIVE = 1, +}; + struct sys_info_regs_gen3 { u32 reserved1; u32 vendor_table_revision; @@ -205,9 +229,37 @@ struct flash_info_regs_gen3 { struct partition_info vendor[8]; }; +struct flash_info_regs_gen4 { + u32 flash_address; + u32 flash_length; + + struct active_partition_info_gen4 { + unsigned char bl2; + unsigned char cfg; + unsigned char img; + unsigned char key; + } active_flag; + + u32 reserved[3]; + + struct partition_info map0; + struct partition_info map1; + struct partition_info key0; + struct partition_info key1; + struct partition_info bl2_0; + struct partition_info bl2_1; + struct partition_info cfg0; + struct partition_info cfg1; + struct partition_info img0; + struct partition_info img1; + struct partition_info nvlog; + struct partition_info vendor[8]; +}; + struct flash_info_regs { union { struct flash_info_regs_gen3 gen3; + struct flash_info_regs_gen4 gen4; }; }; -- cgit v1.2.3 From ce7c88600bf8ec0d12cf8e147907f96cd58eeb2e Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Mon, 6 Jan 2020 12:03:35 -0700 Subject: PCI/switchtec: Add Gen4 MRPC GAS access permission check Gen4 hardware provides new MRPC commands to read and write directly from any address in the PCI BAR (which Microsemi refers to as GAS). Since accessing BARs can be dangerous and break the driver, we don't want unprivileged users to have this ability. Therefore, require CAP_SYS_ADMIN for the local and remote GAS access MRPC commands. Privileged processes will already have access to the BAR through the sysfs resource file so this doesn't give userspace any capabilities it didn't already have. [logang@deltatee.com: rework commit message] Link: https://lore.kernel.org/r/20200106190337.2428-11-logang@deltatee.com Signed-off-by: Kelvin Cao Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index e85155244135..082f1d51957a 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -21,6 +21,11 @@ #define SWITCHTEC_EVENT_FATAL BIT(4) #define SWITCHTEC_DMA_MRPC_EN BIT(0) + +#define MRPC_GAS_READ 0x29 +#define MRPC_GAS_WRITE 0x87 +#define MRPC_CMD_ID(x) ((x) & 0xffff) + enum { SWITCHTEC_GAS_MRPC_OFFSET = 0x0000, SWITCHTEC_GAS_TOP_CFG_OFFSET = 0x1000, -- cgit v1.2.3 From 3277e8aa2504d97e022ecb9777d784ac1a439d36 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Wed, 15 Jan 2020 10:07:27 -0800 Subject: soc: ti: k3: add navss ringacc driver The Ring Accelerator (RINGACC or RA) provides hardware acceleration to enable straightforward passing of work between a producer and a consumer. There is one RINGACC module per NAVSS on TI AM65x SoCs. The RINGACC converts constant-address read and write accesses to equivalent read or write accesses to a circular data structure in memory. The RINGACC eliminates the need for each DMA controller which needs to access ring elements from having to know the current state of the ring (base address, current offset). The DMA controller performs a read or write access to a specific address range (which maps to the source interface on the RINGACC) and the RINGACC replaces the address for the transaction with a new address which corresponds to the head or tail element of the ring (head for reads, tail for writes). Since the RINGACC maintains the state, multiple DMA controllers or channels are allowed to coherently share the same rings as applicable. The RINGACC is able to place data which is destined towards software into cached memory directly. Supported ring modes: - Ring Mode - Messaging Mode - Credentials Mode - Queue Manager Mode TI-SCI integration: Texas Instrument's System Control Interface (TI-SCI) Message Protocol now has control over Ringacc module resources management (RM) and Rings configuration. The corresponding support of TI-SCI Ringacc module RM protocol introduced as option through DT parameters: - ti,sci: phandle on TI-SCI firmware controller DT node - ti,sci-dev-id: TI-SCI device identifier as per TI-SCI firmware spec if both parameters present - Ringacc driver will configure/free/reset Rings using TI-SCI Message Ringacc RM Protocol. The Ringacc driver manages Rings allocation by itself now and requests TI-SCI firmware to allocate and configure specific Rings only. It's done this way because, Linux driver implements two stage Rings allocation and configuration (allocate ring and configure ring) while TI-SCI Message Protocol supports only one combined operation (allocate+configure). Signed-off-by: Grygorii Strashko Signed-off-by: Peter Ujfalusi Reviewed-by: Tero Kristo Tested-by: Keerthy Signed-off-by: Santosh Shilimkar --- include/linux/soc/ti/k3-ringacc.h | 244 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 244 insertions(+) create mode 100644 include/linux/soc/ti/k3-ringacc.h (limited to 'include/linux') diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h new file mode 100644 index 000000000000..26f73df0a524 --- /dev/null +++ b/include/linux/soc/ti/k3-ringacc.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * K3 Ring Accelerator (RA) subsystem interface + * + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + */ + +#ifndef __SOC_TI_K3_RINGACC_API_H_ +#define __SOC_TI_K3_RINGACC_API_H_ + +#include + +struct device_node; + +/** + * enum k3_ring_mode - &struct k3_ring_cfg mode + * + * RA ring operational modes + * + * @K3_RINGACC_RING_MODE_RING: Exposed Ring mode for SW direct access + * @K3_RINGACC_RING_MODE_MESSAGE: Messaging mode. Messaging mode requires + * that all accesses to the queue must go through this IP so that all + * accesses to the memory are controlled and ordered. This IP then + * controls the entire state of the queue, and SW has no directly control, + * such as through doorbells and cannot access the storage memory directly. + * This is particularly useful when more than one SW or HW entity can be + * the producer and/or consumer at the same time + * @K3_RINGACC_RING_MODE_CREDENTIALS: Credentials mode is message mode plus + * stores credentials with each message, requiring the element size to be + * doubled to fit the credentials. Any exposed memory should be protected + * by a firewall from unwanted access + */ +enum k3_ring_mode { + K3_RINGACC_RING_MODE_RING = 0, + K3_RINGACC_RING_MODE_MESSAGE, + K3_RINGACC_RING_MODE_CREDENTIALS, + K3_RINGACC_RING_MODE_INVALID +}; + +/** + * enum k3_ring_size - &struct k3_ring_cfg elm_size + * + * RA ring element's sizes in bytes. + */ +enum k3_ring_size { + K3_RINGACC_RING_ELSIZE_4 = 0, + K3_RINGACC_RING_ELSIZE_8, + K3_RINGACC_RING_ELSIZE_16, + K3_RINGACC_RING_ELSIZE_32, + K3_RINGACC_RING_ELSIZE_64, + K3_RINGACC_RING_ELSIZE_128, + K3_RINGACC_RING_ELSIZE_256, + K3_RINGACC_RING_ELSIZE_INVALID +}; + +struct k3_ringacc; +struct k3_ring; + +/** + * enum k3_ring_cfg - RA ring configuration structure + * + * @size: Ring size, number of elements + * @elm_size: Ring element size + * @mode: Ring operational mode + * @flags: Ring configuration flags. Possible values: + * @K3_RINGACC_RING_SHARED: when set allows to request the same ring + * few times. It's usable when the same ring is used as Free Host PD ring + * for different flows, for example. + * Note: Locking should be done by consumer if required + */ +struct k3_ring_cfg { + u32 size; + enum k3_ring_size elm_size; + enum k3_ring_mode mode; +#define K3_RINGACC_RING_SHARED BIT(1) + u32 flags; +}; + +#define K3_RINGACC_RING_ID_ANY (-1) + +/** + * of_k3_ringacc_get_by_phandle - find a RA by phandle property + * @np: device node + * @propname: property name containing phandle on RA node + * + * Returns pointer on the RA - struct k3_ringacc + * or -ENODEV if not found, + * or -EPROBE_DEFER if not yet registered + */ +struct k3_ringacc *of_k3_ringacc_get_by_phandle(struct device_node *np, + const char *property); + +#define K3_RINGACC_RING_USE_PROXY BIT(1) + +/** + * k3_ringacc_request_ring - request ring from ringacc + * @ringacc: pointer on ringacc + * @id: ring id or K3_RINGACC_RING_ID_ANY for any general purpose ring + * @flags: + * @K3_RINGACC_RING_USE_PROXY: if set - proxy will be allocated and + * used to access ring memory. Sopported only for rings in + * Message/Credentials/Queue mode. + * + * Returns pointer on the Ring - struct k3_ring + * or NULL in case of failure. + */ +struct k3_ring *k3_ringacc_request_ring(struct k3_ringacc *ringacc, + int id, u32 flags); + +/** + * k3_ringacc_ring_reset - ring reset + * @ring: pointer on Ring + * + * Resets ring internal state ((hw)occ, (hw)idx). + */ +void k3_ringacc_ring_reset(struct k3_ring *ring); +/** + * k3_ringacc_ring_reset - ring reset for DMA rings + * @ring: pointer on Ring + * + * Resets ring internal state ((hw)occ, (hw)idx). Should be used for rings + * which are read by K3 UDMA, like TX or Free Host PD rings. + */ +void k3_ringacc_ring_reset_dma(struct k3_ring *ring, u32 occ); + +/** + * k3_ringacc_ring_free - ring free + * @ring: pointer on Ring + * + * Resets ring and free all alocated resources. + */ +int k3_ringacc_ring_free(struct k3_ring *ring); + +/** + * k3_ringacc_get_ring_id - Get the Ring ID + * @ring: pointer on ring + * + * Returns the Ring ID + */ +u32 k3_ringacc_get_ring_id(struct k3_ring *ring); + +/** + * k3_ringacc_get_ring_irq_num - Get the irq number for the ring + * @ring: pointer on ring + * + * Returns the interrupt number which can be used to request the interrupt + */ +int k3_ringacc_get_ring_irq_num(struct k3_ring *ring); + +/** + * k3_ringacc_ring_cfg - ring configure + * @ring: pointer on ring + * @cfg: Ring configuration parameters (see &struct k3_ring_cfg) + * + * Configures ring, including ring memory allocation. + * Returns 0 on success, errno otherwise. + */ +int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg); + +/** + * k3_ringacc_ring_get_size - get ring size + * @ring: pointer on ring + * + * Returns ring size in number of elements. + */ +u32 k3_ringacc_ring_get_size(struct k3_ring *ring); + +/** + * k3_ringacc_ring_get_free - get free elements + * @ring: pointer on ring + * + * Returns number of free elements in the ring. + */ +u32 k3_ringacc_ring_get_free(struct k3_ring *ring); + +/** + * k3_ringacc_ring_get_occ - get ring occupancy + * @ring: pointer on ring + * + * Returns total number of valid entries on the ring + */ +u32 k3_ringacc_ring_get_occ(struct k3_ring *ring); + +/** + * k3_ringacc_ring_is_full - checks if ring is full + * @ring: pointer on ring + * + * Returns true if the ring is full + */ +u32 k3_ringacc_ring_is_full(struct k3_ring *ring); + +/** + * k3_ringacc_ring_push - push element to the ring tail + * @ring: pointer on ring + * @elem: pointer on ring element buffer + * + * Push one ring element to the ring tail. Size of the ring element is + * determined by ring configuration &struct k3_ring_cfg elm_size. + * + * Returns 0 on success, errno otherwise. + */ +int k3_ringacc_ring_push(struct k3_ring *ring, void *elem); + +/** + * k3_ringacc_ring_pop - pop element from the ring head + * @ring: pointer on ring + * @elem: pointer on ring element buffer + * + * Push one ring element from the ring head. Size of the ring element is + * determined by ring configuration &struct k3_ring_cfg elm_size.. + * + * Returns 0 on success, errno otherwise. + */ +int k3_ringacc_ring_pop(struct k3_ring *ring, void *elem); + +/** + * k3_ringacc_ring_push_head - push element to the ring head + * @ring: pointer on ring + * @elem: pointer on ring element buffer + * + * Push one ring element to the ring head. Size of the ring element is + * determined by ring configuration &struct k3_ring_cfg elm_size. + * + * Returns 0 on success, errno otherwise. + * Not Supported by ring modes: K3_RINGACC_RING_MODE_RING + */ +int k3_ringacc_ring_push_head(struct k3_ring *ring, void *elem); + +/** + * k3_ringacc_ring_pop_tail - pop element from the ring tail + * @ring: pointer on ring + * @elem: pointer on ring element buffer + * + * Push one ring element from the ring tail. Size of the ring element is + * determined by ring configuration &struct k3_ring_cfg elm_size. + * + * Returns 0 on success, errno otherwise. + * Not Supported by ring modes: K3_RINGACC_RING_MODE_RING + */ +int k3_ringacc_ring_pop_tail(struct k3_ring *ring, void *elem); + +u32 k3_ringacc_get_tisci_dev_id(struct k3_ring *ring); + +#endif /* __SOC_TI_K3_RINGACC_API_H_ */ -- cgit v1.2.3 From 0af2ffc93a4b50948f9dad2786b7f1bd253bf0b9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Jan 2020 21:47:33 +0100 Subject: bpf: Fix incorrect verifier simulation of ARSH under ALU32 Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (85) call bpf_get_socket_cookie#46 1: R0_w=invP(id=0) R10=fp0 1: (57) r0 &= 808464432 2: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 2: (14) w0 -= 810299440 3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 3: (c4) w0 s>>= 1 4: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 4: (76) if w0 s>= 0x30303030 goto pc+216 221: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 221: (95) exit processed 6 insns (limit 1000000) [...] Taking a closer look, the program was xlated as follows: # ./bpftool p d x i 12 0: (85) call bpf_get_socket_cookie#7800896 1: (bf) r6 = r0 2: (57) r6 &= 808464432 3: (14) w6 -= 810299440 4: (c4) w6 s>>= 1 5: (76) if w6 s>= 0x30303030 goto pc+216 6: (05) goto pc-1 7: (05) goto pc-1 8: (05) goto pc-1 [...] 220: (05) goto pc-1 221: (05) goto pc-1 222: (95) exit Meaning, the visible effect is very similar to f54c7898ed1c ("bpf: Fix precision tracking for unbounded scalars"), that is, the fall-through branch in the instruction 5 is considered to be never taken given the conclusion from the min/max bounds tracking in w6, and therefore the dead-code sanitation rewrites it as goto pc-1. However, real-life input disagrees with verification analysis since a soft-lockup was observed. The bug sits in the analysis of the ARSH. The definition is that we shift the target register value right by K bits through shifting in copies of its sign bit. In adjust_scalar_min_max_vals(), we do first coerce the register into 32 bit mode, same happens after simulating the operation. However, for the case of simulating the actual ARSH, we don't take the mode into account and act as if it's always 64 bit, but location of sign bit is different: dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); Consider an unknown R0 where bpf_get_socket_cookie() (or others) would for example return 0xffff. With the above ARSH simulation, we'd see the following results: [...] 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP65535 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (57) r0 &= 808464432 -> R0_runtime = 0x3030 3: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 3: (14) w0 -= 810299440 -> R0_runtime = 0xcfb40000 4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 (0xffffffff) 4: (c4) w0 s>>= 1 -> R0_runtime = 0xe7da0000 5: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0x7ffbfff8) [...] In insn 3, we have a runtime value of 0xcfb40000, which is '1100 1111 1011 0100 0000 0000 0000 0000', the result after the shift has 0xe7da0000 that is '1110 0111 1101 1010 0000 0000 0000 0000', where the sign bit is correctly retained in 32 bit mode. In insn4, the umax was 0xffffffff, and changed into 0x7ffbfff8 after the shift, that is, '0111 1111 1111 1011 1111 1111 1111 1000' and means here that the simulation didn't retain the sign bit. With above logic, the updates happen on the 64 bit min/max bounds and given we coerced the register, the sign bits of the bounds are cleared as well, meaning, we need to force the simulation into s32 space for 32 bit alu mode. Verification after the fix below. We're first analyzing the fall-through branch on 32 bit signed >= test eventually leading to rejection of the program in this specific case: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r2 = 808464432 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP808464432 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (bf) r6 = r0 3: R0_w=invP(id=0) R6_w=invP(id=0) R10=fp0 3: (57) r6 &= 808464432 4: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 4: (14) w6 -= 810299440 5: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 5: (c4) w6 s>>= 1 6: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0xfffbfff8) 6: (76) if w6 s>= 0x30303030 goto pc+216 7: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 7: (30) r0 = *(u8 *)skb[808464432] BPF_LD_[ABS|IND] uses reserved fields processed 8 insns (limit 1000000) [...] Fixes: 9cbe1f5a32dc ("bpf/verifier: improve register value range tracking with ARSH") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115204733.16648-1-daniel@iogearbox.net --- include/linux/tnum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index c17af77f3fae..ea627d1ab7e3 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -30,7 +30,7 @@ struct tnum tnum_lshift(struct tnum a, u8 shift); /* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); /* Shift (arsh) a tnum right (by a fixed min_shift) */ -struct tnum tnum_arshift(struct tnum a, u8 min_shift); +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ -- cgit v1.2.3 From cb4d03ab499d4c040f4ab6fd4389d2b49f42b5a5 Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Wed, 15 Jan 2020 10:43:01 -0800 Subject: bpf: Add generic support for lookup batch op This commit introduces generic support for the bpf_map_lookup_batch. This implementation can be used by almost all the bpf maps since its core implementation is relying on the existing map_get_next_key and map_lookup_elem. The bpf syscall subcommand introduced is: BPF_MAP_LOOKUP_BATCH The UAPI attribute is: struct { /* struct used by BPF_MAP_*_BATCH commands */ __aligned_u64 in_batch; /* start batch, * NULL to start from beginning */ __aligned_u64 out_batch; /* output: next start batch */ __aligned_u64 keys; __aligned_u64 values; __u32 count; /* input/output: * input: # of key/value * elements * output: # of filled elements */ __u32 map_fd; __u64 elem_flags; __u64 flags; } batch; in_batch/out_batch are opaque values use to communicate between user/kernel space, in_batch/out_batch must be of key_size length. To start iterating from the beginning in_batch must be null, count is the # of key/value elements to retrieve. Note that the 'keys' buffer must be a buffer of key_size * count size and the 'values' buffer must be value_size * count, where value_size must be aligned to 8 bytes by userspace if it's dealing with percpu maps. 'count' will contain the number of keys/values successfully retrieved. Note that 'count' is an input/output variable and it can contain a lower value after a call. If there's no more entries to retrieve, ENOENT will be returned. If error is ENOENT, count might be > 0 in case it copied some values but there were no more entries to retrieve. Note that if the return code is an error and not -EFAULT, count indicates the number of elements successfully processed. Suggested-by: Stanislav Fomichev Signed-off-by: Brian Vazquez Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-3-brianvv@google.com --- include/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aed2bc39d72b..807744ecaa5a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -44,6 +44,8 @@ struct bpf_map_ops { int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); + int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); @@ -982,6 +984,9 @@ void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); +int generic_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From aa2e93b8e58e18442edfb2427446732415bc215e Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Wed, 15 Jan 2020 10:43:02 -0800 Subject: bpf: Add generic support for update and delete batch ops This commit adds generic support for update and delete batch ops that can be used for almost all the bpf maps. These commands share the same UAPI attr that lookup and lookup_and_delete batch ops use and the syscall commands are: BPF_MAP_UPDATE_BATCH BPF_MAP_DELETE_BATCH The main difference between update/delete and lookup batch ops is that for update/delete keys/values must be specified for userspace and because of that, neither in_batch nor out_batch are used. Suggested-by: Stanislav Fomichev Signed-off-by: Brian Vazquez Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-4-brianvv@google.com --- include/linux/bpf.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 807744ecaa5a..05466ad6cf1c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -46,6 +46,10 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); + int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); @@ -987,6 +991,12 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); +int generic_map_update_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); +int generic_map_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 057996380a42bb64ccc04383cfa9c0ace4ea11f0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 15 Jan 2020 10:43:04 -0800 Subject: bpf: Add batch ops to all htab bpf map htab can't use generic batch support due some problematic behaviours inherent to the data structre, i.e. while iterating the bpf map a concurrent program might delete the next entry that batch was about to use, in that case there's no easy solution to retrieve the next entry, the issue has been discussed multiple times (see [1] and [2]). The only way hmap can be traversed without the problem previously exposed is by making sure that the map is traversing entire buckets. This commit implements those strict requirements for hmap, the implementation follows the same interaction that generic support with some exceptions: - If keys/values buffer are not big enough to traverse a bucket, ENOSPC will be returned. - out_batch contains the value of the next bucket in the iteration, not the next key, but this is transparent for the user since the user should never use out_batch for other than bpf batch syscalls. This commits implements BPF_MAP_LOOKUP_BATCH and adds support for new command BPF_MAP_LOOKUP_AND_DELETE_BATCH. Note that for update/delete batch ops it is possible to use the generic implementations. [1] https://lore.kernel.org/bpf/20190724165803.87470-1-brianvv@google.com/ [2] https://lore.kernel.org/bpf/20190906225434.3635421-1-yhs@fb.com/ Signed-off-by: Yonghong Song Signed-off-by: Brian Vazquez Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-6-brianvv@google.com --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 05466ad6cf1c..3517e32149a4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -46,6 +46,9 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_lookup_and_delete_batch)(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, -- cgit v1.2.3 From 4da6a196f93b1af7612340e8c1ad8ce71e18f955 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 11 Jan 2020 06:11:59 +0000 Subject: bpf: Sockmap/tls, during free we may call tcp_bpf_unhash() in loop When a sockmap is free'd and a socket in the map is enabled with tls we tear down the bpf context on the socket, the psock struct and state, and then call tcp_update_ulp(). The tcp_update_ulp() call is to inform the tls stack it needs to update its saved sock ops so that when the tls socket is later destroyed it doesn't try to call the now destroyed psock hooks. This is about keeping stacked ULPs in good shape so they always have the right set of stacked ops. However, recently unhash() hook was removed from TLS side. But, the sockmap/bpf side is not doing any extra work to update the unhash op when is torn down instead expecting TLS side to manage it. So both TLS and sockmap believe the other side is managing the op and instead no one updates the hook so it continues to point at tcp_bpf_unhash(). When unhash hook is called we call tcp_bpf_unhash() which detects the psock has already been destroyed and calls sk->sk_prot_unhash() which calls tcp_bpf_unhash() yet again and so on looping and hanging the core. To fix have sockmap tear down logic fixup the stale pointer. Fixes: 5d92e631b8be ("net/tls: partially revert fix transition through disconnect with close") Reported-by: syzbot+83979935eb6304f8cd46@syzkaller.appspotmail.com Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Song Liu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20200111061206.8028-2-john.fastabend@gmail.com --- include/linux/skmsg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ef7031f8a304..b6afe01f8592 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -358,6 +358,7 @@ static inline void sk_psock_update_proto(struct sock *sk, static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { + sk->sk_prot->unhash = psock->saved_unhash; sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { -- cgit v1.2.3 From 33bfe20dd7117dd81fd896a53f743a233e1ad64f Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 11 Jan 2020 06:12:01 +0000 Subject: bpf: Sockmap/tls, push write_space updates through ulp updates When sockmap sock with TLS enabled is removed we cleanup bpf/psock state and call tcp_update_ulp() to push updates to TLS ULP on top. However, we don't push the write_space callback up and instead simply overwrite the op with the psock stored previous op. This may or may not be correct so to ensure we don't overwrite the TLS write space hook pass this field to the ULP and have it fixup the ctx. This completes a previous fix that pushed the ops through to the ULP but at the time missed doing this for write_space, presumably because write_space TLS hook was added around the same time. Fixes: 95fa145479fbc ("bpf: sockmap/tls, close can race with map free") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Jonathan Lemon Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20200111061206.8028-4-john.fastabend@gmail.com --- include/linux/skmsg.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index b6afe01f8592..14d61bba0b79 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -359,17 +359,21 @@ static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { sk->sk_prot->unhash = psock->saved_unhash; - sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { struct inet_connection_sock *icsk = inet_csk(sk); bool has_ulp = !!icsk->icsk_ulp_data; - if (has_ulp) - tcp_update_ulp(sk, psock->sk_proto); - else + if (has_ulp) { + tcp_update_ulp(sk, psock->sk_proto, + psock->saved_write_space); + } else { sk->sk_prot = psock->sk_proto; + sk->sk_write_space = psock->saved_write_space; + } psock->sk_proto = NULL; + } else { + sk->sk_write_space = psock->saved_write_space; } } -- cgit v1.2.3 From 7c1ef338705fb5c53e6f574ae5eb19fdfacb3d26 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 6 Jan 2020 13:58:15 -0500 Subject: scsi: drivers: base: Support atomic version of attribute_container_device_trigger attribute_container_device_trigger invokes callbacks that may fail for one or more classdevs, for instance, the transport_add_class_device callback, called during transport creation, does memory allocation. This information, though, is not propagated to upper layers, and any driver using the attribute_container_device_trigger API will not know whether any, some, or all callbacks succeeded. This patch implements a safe version of this dispatcher, to either succeed all the callbacks or revert to the original state. Link: https://lore.kernel.org/r/20200106185817.640331-2-krisman@collabora.com Reviewed-by: Greg Kroah-Hartman Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Martin K. Petersen --- include/linux/attribute_container.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index d12bb2153cd6..e4004d1e6725 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -54,6 +54,13 @@ void attribute_container_device_trigger(struct device *dev, int (*fn)(struct attribute_container *, struct device *, struct device *)); +int attribute_container_device_trigger_safe(struct device *dev, + int (*fn)(struct attribute_container *, + struct device *, + struct device *), + int (*undo)(struct attribute_container *, + struct device *, + struct device *)); void attribute_container_trigger(struct device *dev, int (*fn)(struct attribute_container *, struct device *)); -- cgit v1.2.3 From cd7ea70bb00aac8f7ab1b0635edc669e12f53891 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 6 Jan 2020 13:58:16 -0500 Subject: scsi: drivers: base: Propagate errors through the transport component The transport registration may fail. Make sure the errors are propagated to the callers. Link: https://lore.kernel.org/r/20200106185817.640331-3-krisman@collabora.com Reviewed-by: Greg Kroah-Hartman Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Martin K. Petersen --- include/linux/transport_class.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/transport_class.h b/include/linux/transport_class.h index a9c59761927b..63076fb835e3 100644 --- a/include/linux/transport_class.h +++ b/include/linux/transport_class.h @@ -62,16 +62,16 @@ struct transport_container { container_of(x, struct transport_container, ac) void transport_remove_device(struct device *); -void transport_add_device(struct device *); +int transport_add_device(struct device *); void transport_setup_device(struct device *); void transport_configure_device(struct device *); void transport_destroy_device(struct device *); -static inline void +static inline int transport_register_device(struct device *dev) { transport_setup_device(dev); - transport_add_device(dev); + return transport_add_device(dev); } static inline void -- cgit v1.2.3 From ad6bf88a6c19a39fb3b0045d78ea880325dfcf15 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 15 Jan 2020 08:35:25 -0500 Subject: block: fix an integer overflow in logical block size Logical block size has type unsigned short. That means that it can be at most 32768. However, there are architectures that can run with 64k pages (for example arm64) and on these architectures, it may be possible to create block devices with 64k block size. For exmaple (run this on an architecture with 64k pages): Mount will fail with this error because it tries to read the superblock using 2-sector access: device-mapper: writecache: I/O is not aligned, sector 2, size 1024, block size 65536 EXT4-fs (dm-0): unable to read superblock This patch changes the logical block size from unsigned short to unsigned int to avoid the overflow. Cc: stable@vger.kernel.org Reviewed-by: Martin K. Petersen Reviewed-by: Ming Lei Signed-off-by: Mikulas Patocka Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 47eb22a3b7f9..4c636c42ad68 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -328,6 +328,7 @@ struct queue_limits { unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; + unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; @@ -338,7 +339,6 @@ struct queue_limits { unsigned int discard_granularity; unsigned int discard_alignment; - unsigned short logical_block_size; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; @@ -1077,7 +1077,7 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); -extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); +extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); 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); @@ -1291,7 +1291,7 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned short queue_logical_block_size(const struct request_queue *q) +static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1301,7 +1301,7 @@ static inline unsigned short queue_logical_block_size(const struct request_queue return retval; } -static inline unsigned short bdev_logical_block_size(struct block_device *bdev) +static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } -- cgit v1.2.3 From 574c5b3d0e4c0803d3094fd27f83e161345ebe2f Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 22 Nov 2019 09:25:12 +0100 Subject: mm: Add a vmf_insert_mixed_prot() function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The TTM module today uses a hack to be able to set a different page protection than struct vm_area_struct::vm_page_prot. To be able to do this properly, add the needed vm functionality as vmf_insert_mixed_prot(). Cc: Andrew Morton Cc: Michal Hocko Cc: "Matthew Wilcox (Oracle)" Cc: "Kirill A. Shutemov" Cc: Ralph Campbell Cc: "Jérôme Glisse" Cc: "Christian König" Signed-off-by: Thomas Hellstrom Acked-by: Christian König Acked-by: Michal Hocko Acked-by: Andrew Morton --- include/linux/mm.h | 2 ++ include/linux/mm_types.h | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c97ea3b694e6..0157d293935f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2533,6 +2533,8 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); +vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 270aa8fd2800..e5f0080b4e15 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -312,7 +312,12 @@ struct vm_area_struct { /* Second cache line starts here. */ struct mm_struct *vm_mm; /* The address space we belong to. */ - pgprot_t vm_page_prot; /* Access permissions of this VMA. */ + + /* + * Access permissions of this VMA. + * See vmf_insert_mixed_prot() for discussion. + */ + pgprot_t vm_page_prot; unsigned long vm_flags; /* Flags, see mm.h. */ /* -- cgit v1.2.3 From 9c6722d85e92233082da2b3623685bba54d6093e Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Thu, 16 Jan 2020 17:50:03 +0800 Subject: gpio: Fix the no return statement warning In commit 242587616710 ("gpiolib: Add support for the irqdomain which doesn't use irq_fwspec as arg") we have changed the return type of gpiochip_populate_parent_fwspec_twocell/fourcell() from void to void *, but forgot to add a return statement for these two dummy functions. Add "return NULL" to fix the build warnings. Reported-by: kbuild test robot Signed-off-by: Kevin Hao Link: https://lore.kernel.org/r/20200116095003.30324-1-haokexin@gmail.com Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 9bb43467ed11..00d9f5b464c7 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -549,12 +549,14 @@ static inline void *gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *ch unsigned int parent_hwirq, unsigned int parent_type) { + return NULL; } static inline void *gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *chip, unsigned int parent_hwirq, unsigned int parent_type) { + return NULL; } #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ -- cgit v1.2.3 From 92f622bc276a0b9281df3d145ebaffb904f0d290 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Fri, 10 Jan 2020 16:00:16 -0600 Subject: soundwire: intel: report slave_ids for each link to SOF driver The existing link_mask flag is no longer sufficient to detect the hardware and identify which topology file and a machine driver to load. By reporting the slave_ids exposed in ACPI tables, the parent SOF driver will be able to compare against a set of static configurations. This patch only adds the interface change, the functionality is added in future patches. Signed-off-by: Bard Liao Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20200110220016.30887-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 93b83bdf8035..979b41b5dcb4 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -5,6 +5,7 @@ #define __SDW_INTEL_H #include +#include /** * struct sdw_intel_stream_params_data: configuration passed during @@ -93,6 +94,11 @@ struct sdw_intel_link_res; */ #define SDW_INTEL_CLK_STOP_BUS_RESET BIT(3) +struct sdw_intel_slave_id { + int link_id; + struct sdw_slave_id id; +}; + /** * struct sdw_intel_ctx - context allocated by the controller * driver probe @@ -101,9 +107,12 @@ struct sdw_intel_link_res; * hardware capabilities after all power dependencies are settled. * @link_mask: bit-wise mask listing SoundWire links reported by the * Controller + * @num_slaves: total number of devices exposed across all enabled links * @handle: ACPI parent handle * @links: information for each link (controller-specific and kept * opaque here) + * @ids: array of slave_id, representing Slaves exposed across all enabled + * links * @link_list: list to handle interrupts across all links * @shim_lock: mutex to handle concurrent rmw access to shared SHIM registers. */ @@ -111,8 +120,10 @@ struct sdw_intel_ctx { int count; void __iomem *mmio_base; u32 link_mask; + int num_slaves; acpi_handle handle; struct sdw_intel_link_res *links; + struct sdw_intel_slave_id *ids; struct list_head link_list; struct mutex shim_lock; /* lock for access to shared SHIM registers */ }; -- cgit v1.2.3 From b3f79ae45904ae987a7c06a9e8d6084d7b73e67f Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Fri, 10 Jan 2020 01:56:49 +0000 Subject: x86/amd_nb: Add Family 19h PCI IDs Add the new PCI Device 18h IDs for AMD Family 19h systems. Note that Family 19h systems will not have a new PCI root device ID. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200110015651.14887-4-Yazen.Ghannam@amd.com --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2302d133af6f..352c0d708720 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -549,6 +549,7 @@ #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 +#define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 -- cgit v1.2.3 From f01b16a85bfae2e6b4f32de0a1f37ac4050dc316 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Mon, 6 Jan 2020 13:11:17 -0500 Subject: dax: Get rid of fs_dax_get_by_host() helper Looks like nobody is using fs_dax_get_by_host() except fs_dax_get_by_bdev() and it can easily use dax_get_by_host() instead. IIUC, fs_dax_get_by_host() was only introduced so that one could compile with CONFIG_FS_DAX=n and CONFIG_DAX=m. fs_dax_get_by_bdev() achieves the same purpose and hence it looks like fs_dax_get_by_host() is not needed anymore. Signed-off-by: Vivek Goyal Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20200106181117.GA16248@redhat.com Signed-off-by: Dan Williams --- include/linux/dax.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index d5932e47c597..328c2dbb4409 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -129,11 +129,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, sectors); } -static inline struct dax_device *fs_dax_get_by_host(const char *host) -{ - return dax_get_by_host(host); -} - static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); @@ -160,11 +155,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } -static inline struct dax_device *fs_dax_get_by_host(const char *host) -{ - return NULL; -} - static inline void fs_put_dax(struct dax_device *dax_dev) { } -- cgit v1.2.3 From 8fd5b75d979bd8483b7e015c85834fbc82d499ac Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 15 Jan 2020 16:54:58 +0200 Subject: net/mlx5: Add RoCE accelerator counters Add RoCE accelerator definitions. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c6abaf4f1c55..73d1a6a049fb 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1197,7 +1197,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_at_140[0xa]; + u8 reserved_at_140[0x9]; + u8 roce_accl[0x1]; u8 log_max_ra_req_qp[0x6]; u8 reserved_at_150[0xa]; u8 log_max_ra_res_qp[0x6]; @@ -4746,7 +4747,19 @@ struct mlx5_ifc_query_q_counter_out_bits { u8 req_cqe_flush_error[0x20]; - u8 reserved_at_620[0x1e0]; + u8 reserved_at_620[0x20]; + + u8 roce_adp_retrans[0x20]; + + u8 roce_adp_retrans_to[0x20]; + + u8 roce_slow_restart[0x20]; + + u8 roce_slow_restart_cnps[0x20]; + + u8 roce_slow_restart_trans[0x20]; + + u8 reserved_at_6e0[0x120]; }; struct mlx5_ifc_query_q_counter_in_bits { -- cgit v1.2.3 From a880a6dd853713e02a2804dd7ecaf39c7d3d9b18 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Wed, 8 Jan 2020 20:05:31 +0200 Subject: net/mlx5: Expose relaxed ordering bits Expose relaxed ordering bits in HCA capability and mkey context structs. Signed-off-by: Yishai Hadas Signed-off-by: Michael Guralnik Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 73d1a6a049fb..55bb42a79157 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1174,7 +1174,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_cq[0x5]; u8 log_max_eq_sz[0x8]; - u8 reserved_at_e8[0x2]; + u8 relaxed_ordering_write[0x1]; + u8 relaxed_ordering_read[0x1]; u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x8]; u8 dump_fill_mkey[0x1]; @@ -3287,7 +3288,9 @@ struct mlx5_ifc_mkc_bits { u8 translations_octword_size[0x20]; - u8 reserved_at_1c0[0x1b]; + u8 reserved_at_1c0[0x19]; + u8 relaxed_ordering_read[0x1]; + u8 reserved_at_1d9[0x1]; u8 log_page_size[0x5]; u8 reserved_at_1e0[0x20]; -- cgit v1.2.3 From c052bf82c6b00ca27aab0859addc4b3159dfd3a4 Mon Sep 17 00:00:00 2001 From: Jonas Meurer Date: Thu, 16 Jan 2020 12:53:54 +0100 Subject: PM: suspend: Add sysfs attribute to control the "sync on suspend" behavior The sysfs attribute `/sys/power/sync_on_suspend` controls, whether or not filesystems are synced by the kernel before system suspend. Congruously, the behaviour of build-time switch CONFIG_SUSPEND_SKIP_SYNC is slightly changed: It now defines the run-tim default for the new sysfs attribute `/sys/power/sync_on_suspend`. The run-time attribute is added because the existing corresponding build-time Kconfig flag for (`CONFIG_SUSPEND_SKIP_SYNC`) is not flexible enough. E.g. Linux distributions that provide pre-compiled kernels usually want to stick with the default (sync filesystems before suspend) but under special conditions this needs to be changed. One example for such a special condition is user-space handling of suspending block devices (e.g. using `cryptsetup luksSuspend` or `dmsetup suspend`) before system suspend. The Kernel trying to sync filesystems after the underlying block device already got suspended obviously leads to dead-locks. Be aware that you have to take care of the filesystem sync yourself before suspending the system in those scenarios. Signed-off-by: Jonas Meurer Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 6fc8843f1c9e..4a230c2f1c31 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -329,6 +329,7 @@ extern void arch_suspend_disable_irqs(void); extern void arch_suspend_enable_irqs(void); extern int pm_suspend(suspend_state_t state); +extern bool sync_on_suspend_enabled; #else /* !CONFIG_SUSPEND */ #define suspend_valid_only_mem NULL @@ -342,6 +343,7 @@ static inline bool pm_suspend_default_s2idle(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } +static inline bool sync_on_suspend_enabled(void) { return true; } static inline bool idle_should_enter_s2idle(void) { return false; } static inline void __init pm_states_init(void) {} static inline void s2idle_set_ops(const struct platform_s2idle_ops *ops) {} -- cgit v1.2.3 From f397464eb7c25bda903ec8b9cf5701e72a1f7b16 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 7 Oct 2019 10:29:46 +0300 Subject: net/mlx5: Add structures layout for new MCAM access reg groups MCAM has 3 access_reg_groups (0-2). Defines data structures in order to read and parse access_reg_groups #1 and #2. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c6abaf4f1c55..43cdf9211747 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8832,6 +8832,28 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_31_to_0[0x20]; }; +struct mlx5_ifc_mcam_access_reg_bits1 { + u8 regs_127_to_96[0x20]; + + u8 regs_95_to_64[0x20]; + + u8 regs_63_to_32[0x20]; + + u8 regs_31_to_0[0x20]; +}; + +struct mlx5_ifc_mcam_access_reg_bits2 { + u8 regs_127_to_99[0x1d]; + u8 mirc[0x1]; + u8 regs_97_to_96[0x2]; + + u8 regs_95_to_64[0x20]; + + u8 regs_63_to_32[0x20]; + + u8 regs_31_to_0[0x20]; +}; + struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_0[0x8]; u8 feature_group[0x8]; @@ -8842,6 +8864,8 @@ struct mlx5_ifc_mcam_reg_bits { union { struct mlx5_ifc_mcam_access_reg_bits access_regs; + struct mlx5_ifc_mcam_access_reg_bits1 access_regs1; + struct mlx5_ifc_mcam_access_reg_bits2 access_regs2; u8 reserved_at_0[0x80]; } mng_access_reg_cap_mask; -- cgit v1.2.3 From 932ef155117cc5caf1108bd27664dab974ba6e89 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 7 Oct 2019 10:31:42 +0300 Subject: net/mlx5: Read MCAM register groups 1 and 2 On load, Driver caches MCAM (Management Capabilities Mask Register) registers. in addition to the only MCAM register group (0) the driver already reads, here we add support for reading groups 1 and 2. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 14 +++++++++++++- include/linux/mlx5/driver.h | 2 +- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 1a1c53f0262d..0e62c3db45e5 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1121,6 +1121,9 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, + MLX5_MCAM_REGS_0x9080_0x90FF = 0x1, + MLX5_MCAM_REGS_0x9100_0x917F = 0x2, + MLX5_MCAM_REGS_NUM = 0x3, }; enum mlx5_mcam_feature_groups { @@ -1269,7 +1272,16 @@ enum mlx5_qcam_feature_groups { MLX5_GET(pcam_reg, (mdev)->caps.pcam, port_access_reg_cap_mask.regs_5000_to_507f.reg) #define MLX5_CAP_MCAM_REG(mdev, reg) \ - MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_access_reg_cap_mask.access_regs.reg) + MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_FIRST_128], \ + mng_access_reg_cap_mask.access_regs.reg) + +#define MLX5_CAP_MCAM_REG1(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9080_0x90FF], \ + mng_access_reg_cap_mask.access_regs1.reg) + +#define MLX5_CAP_MCAM_REG2(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ + mng_access_reg_cap_mask.access_regs2.reg) #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 27200dea0297..54431256af42 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -684,7 +684,7 @@ struct mlx5_core_dev { u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; - u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; + u32 mcam[MLX5_MCAM_REGS_NUM][MLX5_ST_SZ_DW(mcam_reg)]; u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; u8 embedded_cpu; -- cgit v1.2.3 From bab58ba10ecfa39c46d280d2acbca6054e1e863d Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 7 Oct 2019 10:30:32 +0300 Subject: net/mlx5: Add structures and defines for MIRC register Add needed structures, layouts and defines for MIRC (Management Image Re-activation Control) register. This structure will be used for the FSM reactivation flow in the downstream patches. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 54431256af42..7848b9858587 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -145,6 +145,7 @@ enum { MLX5_REG_MCC = 0x9062, MLX5_REG_MCDA = 0x9063, MLX5_REG_MCAM = 0x907f, + MLX5_REG_MIRC = 0x9162, }; enum mlx5_qpts_trust_state { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 43cdf9211747..a133583c3e4f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9471,6 +9471,13 @@ struct mlx5_ifc_mcda_reg_bits { u8 data[0][0x20]; }; +struct mlx5_ifc_mirc_reg_bits { + u8 reserved_at_0[0x18]; + u8 status_code[0x8]; + + u8 reserved_at_20[0x20]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -9526,6 +9533,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mcqi_reg_bits mcqi_reg; struct mlx5_ifc_mcc_reg_bits mcc_reg; struct mlx5_ifc_mcda_reg_bits mcda_reg; + struct mlx5_ifc_mirc_reg_bits mirc_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From 609b82727f719b41b50440c4028d48d0b2e04913 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 4 Nov 2019 14:51:55 +0200 Subject: net/mlx5: Expose resource dump register mapping Add new register enumeration for resource dump. Add layout mapping for resource dump: access command and response. Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 130 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 130 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7848b9858587..c821fa4d7475 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -146,6 +146,7 @@ enum { MLX5_REG_MCDA = 0x9063, MLX5_REG_MCAM = 0x907f, MLX5_REG_MIRC = 0x9162, + MLX5_REG_RESOURCE_DUMP = 0xC000, }; enum mlx5_qpts_trust_state { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a133583c3e4f..6fe0431e11ec 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -823,7 +823,9 @@ struct mlx5_ifc_qos_cap_bits { struct mlx5_ifc_debug_cap_bits { u8 core_dump_general[0x1]; u8 core_dump_qp[0x1]; - u8 reserved_at_2[0x1e]; + u8 reserved_at_2[0x7]; + u8 resource_dump[0x1]; + u8 reserved_at_a[0x16]; u8 reserved_at_20[0x2]; u8 stall_detect[0x1]; @@ -1767,6 +1769,132 @@ struct mlx5_ifc_resize_field_select_bits { u8 resize_field_select[0x20]; }; +struct mlx5_ifc_resource_dump_bits { + u8 more_dump[0x1]; + u8 inline_dump[0x1]; + u8 reserved_at_2[0xa]; + u8 seq_num[0x4]; + u8 segment_type[0x10]; + + u8 reserved_at_20[0x10]; + u8 vhca_id[0x10]; + + u8 index1[0x20]; + + u8 index2[0x20]; + + u8 num_of_obj1[0x10]; + u8 num_of_obj2[0x10]; + + u8 reserved_at_a0[0x20]; + + u8 device_opaque[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; + + u8 address[0x40]; + + u8 inline_data[52][0x20]; +}; + +struct mlx5_ifc_resource_dump_menu_record_bits { + u8 reserved_at_0[0x4]; + u8 num_of_obj2_supports_active[0x1]; + u8 num_of_obj2_supports_all[0x1]; + u8 must_have_num_of_obj2[0x1]; + u8 support_num_of_obj2[0x1]; + u8 num_of_obj1_supports_active[0x1]; + u8 num_of_obj1_supports_all[0x1]; + u8 must_have_num_of_obj1[0x1]; + u8 support_num_of_obj1[0x1]; + u8 must_have_index2[0x1]; + u8 support_index2[0x1]; + u8 must_have_index1[0x1]; + u8 support_index1[0x1]; + u8 segment_type[0x10]; + + u8 segment_name[4][0x20]; + + u8 index1_name[4][0x20]; + + u8 index2_name[4][0x20]; +}; + +struct mlx5_ifc_resource_dump_segment_header_bits { + u8 length_dw[0x10]; + u8 segment_type[0x10]; +}; + +struct mlx5_ifc_resource_dump_command_segment_bits { + struct mlx5_ifc_resource_dump_segment_header_bits segment_header; + + u8 segment_called[0x10]; + u8 vhca_id[0x10]; + + u8 index1[0x20]; + + u8 index2[0x20]; + + u8 num_of_obj1[0x10]; + u8 num_of_obj2[0x10]; +}; + +struct mlx5_ifc_resource_dump_error_segment_bits { + struct mlx5_ifc_resource_dump_segment_header_bits segment_header; + + u8 reserved_at_20[0x10]; + u8 syndrome_id[0x10]; + + u8 reserved_at_40[0x40]; + + u8 error[8][0x20]; +}; + +struct mlx5_ifc_resource_dump_info_segment_bits { + struct mlx5_ifc_resource_dump_segment_header_bits segment_header; + + u8 reserved_at_20[0x18]; + u8 dump_version[0x8]; + + u8 hw_version[0x20]; + + u8 fw_version[0x20]; +}; + +struct mlx5_ifc_resource_dump_menu_segment_bits { + struct mlx5_ifc_resource_dump_segment_header_bits segment_header; + + u8 reserved_at_20[0x10]; + u8 num_of_records[0x10]; + + struct mlx5_ifc_resource_dump_menu_record_bits record[0]; +}; + +struct mlx5_ifc_resource_dump_resource_segment_bits { + struct mlx5_ifc_resource_dump_segment_header_bits segment_header; + + u8 reserved_at_20[0x20]; + + u8 index1[0x20]; + + u8 index2[0x20]; + + u8 payload[0][0x20]; +}; + +struct mlx5_ifc_resource_dump_terminate_segment_bits { + struct mlx5_ifc_resource_dump_segment_header_bits segment_header; +}; + +struct mlx5_ifc_menu_resource_dump_response_bits { + struct mlx5_ifc_resource_dump_info_segment_bits info; + struct mlx5_ifc_resource_dump_command_segment_bits cmd; + struct mlx5_ifc_resource_dump_menu_segment_bits menu; + struct mlx5_ifc_resource_dump_terminate_segment_bits terminate; +}; + enum { MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_PERIOD = 0x1, MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_MAX_COUNT = 0x2, -- cgit v1.2.3 From 31d8bde1c8812c9b44065dcd98e554488c6a98d2 Mon Sep 17 00:00:00 2001 From: Hamdan Igbaria Date: Thu, 9 Jan 2020 13:26:53 +0200 Subject: net/mlx5: Add copy header action struct layout Add definition for copy header action, copy action is used to copy header fields from source to destination. Signed-off-by: Hamdan Igbaria Signed-off-by: Alex Vesker Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6fe0431e11ec..23613a6ea51c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5609,6 +5609,21 @@ struct mlx5_ifc_add_action_in_bits { u8 data[0x20]; }; +struct mlx5_ifc_copy_action_in_bits { + u8 action_type[0x4]; + u8 src_field[0xc]; + u8 reserved_at_10[0x3]; + u8 src_offset[0x5]; + u8 reserved_at_18[0x3]; + u8 length[0x5]; + + u8 reserved_at_20[0x4]; + u8 dst_field[0xc]; + u8 reserved_at_30[0x3]; + u8 dst_offset[0x5]; + u8 reserved_at_38[0x8]; +}; + union mlx5_ifc_set_action_in_add_action_in_auto_bits { struct mlx5_ifc_set_action_in_bits set_action_in; struct mlx5_ifc_add_action_in_bits add_action_in; @@ -5618,6 +5633,7 @@ union mlx5_ifc_set_action_in_add_action_in_auto_bits { enum { MLX5_ACTION_TYPE_SET = 0x1, MLX5_ACTION_TYPE_ADD = 0x2, + MLX5_ACTION_TYPE_COPY = 0x3, }; enum { -- cgit v1.2.3 From 822e114b50641d3b57d2eb30939e60d8b4758288 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 1 Apr 2019 13:31:32 +0300 Subject: net/mlx5: Add mlx5_ifc definitions for connection tracking support Add the required hardware definitions to mlx5_ifc: ignore_flow_level, registers, copy_header, and fwd_and_modify cap. Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Reviewed-by: Oz Sholomo Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 23613a6ea51c..e9c165ffe3f9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -375,8 +375,17 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_esp_spi[0x1]; u8 reserved_at_58[0x2]; u8 bth_dst_qp[0x1]; + u8 reserved_at_5b[0x5]; - u8 reserved_at_5b[0x25]; + u8 reserved_at_60[0x18]; + u8 metadata_reg_c_7[0x1]; + u8 metadata_reg_c_6[0x1]; + u8 metadata_reg_c_5[0x1]; + u8 metadata_reg_c_4[0x1]; + u8 metadata_reg_c_3[0x1]; + u8 metadata_reg_c_2[0x1]; + u8 metadata_reg_c_1[0x1]; + u8 metadata_reg_c_0[0x1]; }; struct mlx5_ifc_flow_table_prop_layout_bits { @@ -401,7 +410,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reformat_l3_tunnel_to_l2[0x1]; u8 reformat_l2_to_l3_tunnel[0x1]; u8 reformat_and_modify_action[0x1]; - u8 reserved_at_15[0x2]; + u8 ignore_flow_level[0x1]; + u8 reserved_at_16[0x1]; u8 table_miss_action_domain[0x1]; u8 termination_table[0x1]; u8 reserved_at_19[0x7]; @@ -722,7 +732,9 @@ enum { struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 fdb_to_vport_reg_c_id[0x8]; - u8 reserved_at_8[0xf]; + u8 reserved_at_8[0xd]; + u8 fdb_modify_header_fwd_to_table[0x1]; + u8 reserved_at_16[0x1]; u8 flow_source[0x1]; u8 reserved_at_18[0x2]; u8 multi_fdb_encap[0x1]; @@ -4141,7 +4153,8 @@ struct mlx5_ifc_set_fte_in_bits { u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_at_c0[0x18]; + u8 ignore_flow_level[0x1]; + u8 reserved_at_c1[0x17]; u8 modify_enable_mask[0x8]; u8 reserved_at_e0[0x20]; @@ -5627,6 +5640,7 @@ struct mlx5_ifc_copy_action_in_bits { union mlx5_ifc_set_action_in_add_action_in_auto_bits { struct mlx5_ifc_set_action_in_bits set_action_in; struct mlx5_ifc_add_action_in_bits add_action_in; + struct mlx5_ifc_copy_action_in_bits copy_action_in; u8 reserved_at_0[0x40]; }; @@ -5669,6 +5683,8 @@ enum { MLX5_ACTION_IN_FIELD_METADATA_REG_C_3 = 0x54, MLX5_ACTION_IN_FIELD_METADATA_REG_C_4 = 0x55, MLX5_ACTION_IN_FIELD_METADATA_REG_C_5 = 0x56, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_6 = 0x57, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_7 = 0x58, MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, }; -- cgit v1.2.3 From a58837f52d432f32995b1c00e803cc4db18762d3 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 30 Dec 2019 14:22:57 +0200 Subject: net/mlx5e: Expose FEC feilds and related capability bit Introduce 50G per lane FEC modes capability bit and newly supported fields in PPLM register which allow this configuration. Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e9c165ffe3f9..2ab4562b4851 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8581,6 +8581,18 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_50g[0x4]; u8 fec_override_admin_25g[0x4]; u8 fec_override_admin_10g_40g[0x4]; + + u8 fec_override_cap_400g_8x[0x10]; + u8 fec_override_cap_200g_4x[0x10]; + + u8 fec_override_cap_100g_2x[0x10]; + u8 fec_override_cap_50g_1x[0x10]; + + u8 fec_override_admin_400g_8x[0x10]; + u8 fec_override_admin_200g_4x[0x10]; + + u8 fec_override_admin_100g_2x[0x10]; + u8 fec_override_admin_50g_1x[0x10]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -8907,7 +8919,9 @@ struct mlx5_ifc_mpegc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x6d]; + u8 reserved_at_0[0x68]; + u8 fec_50G_per_lane_in_pplm[0x1]; + u8 reserved_at_69[0x4]; u8 rx_icrc_encapsulated_counter[0x1]; u8 reserved_at_6e[0x4]; u8 ptys_extended_ethernet[0x1]; -- cgit v1.2.3 From 827a8cb2dd2b72848652b2a425bba3262808ff44 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Mon, 16 Dec 2019 12:50:13 +0200 Subject: net/mlx5e: Add discard counters per priority Add counters that count (per priority) the number of received packets that dropped due to lack of buffers on a physical port. If this counter is increasing, it implies that the adapter is congested and cannot absorb the traffic coming from the network. Signed-off-by: Aharon Landau Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2ab4562b4851..ee0a34d66c7c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2180,7 +2180,9 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { u8 rx_pause_transition_low[0x20]; - u8 reserved_at_3c0[0x40]; + u8 rx_discards_high[0x20]; + + u8 rx_discards_low[0x20]; u8 device_stall_minor_watermark_cnt_high[0x20]; -- cgit v1.2.3 From 61dc7b0141c51f5fa4aed97e49f9cf102ec51479 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 14 Nov 2019 16:59:58 +0200 Subject: net/mlx5: Refactor mlx5_create_auto_grouped_flow_table Refactor mlx5_create_auto_grouped_flow_table() to use ft_attr param which already carries the max_fte, prio and flags memebers, and is used the same in similar mlx5_create_flow_table() function. Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Reviewed-by: Oz Shlomo Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 4e5b84e66822..a3f8b63839de 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -145,25 +145,25 @@ mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type, int vport); -struct mlx5_flow_table * -mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, - int prio, - int num_flow_table_entries, - int max_num_groups, - u32 level, - u32 flags); - struct mlx5_flow_table_attr { int prio; int max_fte; u32 level; u32 flags; + + struct { + int max_num_groups; + } autogroup; }; struct mlx5_flow_table * mlx5_create_flow_table(struct mlx5_flow_namespace *ns, struct mlx5_flow_table_attr *ft_attr); +struct mlx5_flow_table * +mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, + struct mlx5_flow_table_attr *ft_attr); + struct mlx5_flow_table * mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, int prio, -- cgit v1.2.3 From 5281a0c909194c477656e89401ac11dd7b29ad2d Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 23 Jul 2019 11:43:57 +0300 Subject: net/mlx5: fs_core: Introduce unmanaged flow tables Currently, Most of the steering tree is statically declared ahead of time, with steering prios instances allocated for each fdb chain to assign max number of levels for each of them. This allows fs_core to manage the connections and levels of the flow tables hierarcy to prevent loops, but restricts us with the number of supported chains and priorities. Introduce unmananged flow tables, allowing the user to manage the flow table connections. A unamanged table is detached from the fs_core flow table hierarcy, and is only connected back to the hierarchy by explicit FTEs forward actions. This will be used together with firmware that supports ignoring the flow table levels to increase the number of supported chains and prios. Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Reviewed-by: Oz Shlomo Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index a3f8b63839de..de2c838bae90 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -48,6 +48,7 @@ enum { MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0), MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), MLX5_FLOW_TABLE_TERMINATION = BIT(2), + MLX5_FLOW_TABLE_UNMANAGED = BIT(3), }; #define LEFTOVERS_RULE_NUM 2 @@ -150,6 +151,7 @@ struct mlx5_flow_table_attr { int max_fte; u32 level; u32 flags; + struct mlx5_flow_table *next_ft; struct { int max_num_groups; -- cgit v1.2.3 From ff189b43568216c6211e9e7ddd9026cb8295e744 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Sun, 5 Jan 2020 15:15:54 +0200 Subject: net/mlx5: Add ignore level support fwd to table rules If user sets ignore flow level flag on a rule, that rule can point to a flow table of any level, including those with levels equal or less than the level of the flow table it is added on. This with unamanged tables will be used to create a FDB chain/prio hierarchy much larger than currently supported level range. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index de2c838bae90..81f393fb7d96 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -196,6 +196,7 @@ struct mlx5_fs_vlan { enum { FLOW_ACT_NO_APPEND = BIT(0), + FLOW_ACT_IGNORE_FLOW_LEVEL = BIT(1), }; struct mlx5_flow_act { -- cgit v1.2.3 From 79cdb0aaea8b5478db34afa1d4d5ecc808689a67 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 14 Nov 2019 17:02:59 +0200 Subject: net/mlx5: Allow creating autogroups with reserved entries Exclude the last n entries for an autogrouped flow table. Reserving entries at the end of the FT will ensure that this FG will be the last to be evaluated. This will be used in the next patch to create a miss group enabling custom actions on FT miss. Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Reviewed-by: Oz Shlomo Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 81f393fb7d96..4cae16016b2b 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -155,6 +155,7 @@ struct mlx5_flow_table_attr { struct { int max_num_groups; + int num_reserved_entries; } autogroup; }; -- cgit v1.2.3 From 75ccae62cb8d42a619323a85c577107b8b37d797 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Thu, 16 Jan 2020 16:14:44 +0100 Subject: xdp: Move devmap bulk queue into struct net_device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: Björn Töpel Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk --- include/linux/netdevice.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2741aa35bec6..5ec3537fbdb1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -876,6 +876,7 @@ enum bpf_netdev_command { struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; +struct xdp_dev_bulk_queue; struct netdev_bpf { enum bpf_netdev_command command; @@ -1986,12 +1987,10 @@ struct net_device { unsigned int num_tx_queues; unsigned int real_num_tx_queues; struct Qdisc *qdisc; -#ifdef CONFIG_NET_SCHED - DECLARE_HASHTABLE (qdisc_hash, 4); -#endif unsigned int tx_queue_len; spinlock_t tx_global_lock; - int watchdog_timeo; + + struct xdp_dev_bulk_queue __percpu *xdp_bulkq; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_cpus_map; @@ -2001,11 +2000,15 @@ struct net_device { struct mini_Qdisc __rcu *miniq_egress; #endif +#ifdef CONFIG_NET_SCHED + DECLARE_HASHTABLE (qdisc_hash, 4); +#endif /* These may be needed for future network-power-down code. */ struct timer_list watchdog_timer; + int watchdog_timeo; - int __percpu *pcpu_refcnt; struct list_head todo_list; + int __percpu *pcpu_refcnt; struct list_head link_watch_list; -- cgit v1.2.3 From 1d233886dd904edbf239eeffe435c3308ae97625 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Thu, 16 Jan 2020 16:14:45 +0100 Subject: xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk --- include/linux/bpf.h | 13 +++++++++++-- include/linux/filter.h | 10 ++++++++-- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3517e32149a4..8e3b8f4ad183 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1056,7 +1056,9 @@ struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_flush(void); +void __dev_flush(void); +int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, @@ -1169,13 +1171,20 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map return NULL; } -static inline void __dev_map_flush(void) +static inline void __dev_flush(void) { } struct xdp_buff; struct bpf_dtab_netdev; +static inline +int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return 0; +} + static inline int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx) diff --git a/include/linux/filter.h b/include/linux/filter.h index a366a0b64a57..f349e2c0884c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -918,7 +918,7 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd, return 0; } -/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the +/* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. @@ -929,7 +929,13 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); -void xdp_do_flush_map(void); +void xdp_do_flush(void); + +/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as + * it is no longer only flushing maps. Keep this define for compatibility + * until all drivers are updated - do not use xdp_do_flush_map() in new code! + */ +#define xdp_do_flush_map xdp_do_flush void bpf_warn_invalid_xdp_action(u32 act); -- cgit v1.2.3 From 35f4cd96f5551dc1b2641159e7bb7bf91de6600f Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sat, 28 Dec 2019 16:19:12 +0000 Subject: stop_machine: Make stop_cpus() static The function stop_cpus() is only used internally by the stop_machine for stop multiple cpus. Make it static. Signed-off-by: Yangtao Li Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191228161912.24082-1-tiny.windzz@gmail.com --- include/linux/stop_machine.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 648298f877da..76d8b09384a7 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -32,7 +32,6 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg); bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); -int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); void stop_machine_park(int cpu); void stop_machine_unpark(int cpu); void stop_machine_yield(const struct cpumask *cpumask); @@ -81,14 +80,6 @@ static inline bool stop_one_cpu_nowait(unsigned int cpu, return false; } -static inline int stop_cpus(const struct cpumask *cpumask, - cpu_stop_fn_t fn, void *arg) -{ - if (cpumask_test_cpu(raw_smp_processor_id(), cpumask)) - return stop_one_cpu(raw_smp_processor_id(), fn, arg); - return -ENOENT; -} - #endif /* CONFIG_SMP */ /* -- cgit v1.2.3 From a4f9a0e51bbf89cb461b1985a1a570e6b87da3b5 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 15 Jan 2020 11:20:20 +0100 Subject: sched/fair: Remove redundant call to cpufreq_update_util() With commit bef69dd87828 ("sched/cpufreq: Move the cfs_rq_util_change() call to cpufreq_update_util()") update_load_avg() has become the central point for calling cpufreq (not including the update of blocked load). This change helps to simplify further the number of calls to cpufreq_update_util() and to remove last redundant ones. With update_load_avg(), we are now sure that cpufreq_update_util() will be called after every task attachment to a cfs_rq and especially after propagating this event down to the util_avg of the root cfs_rq, which is the level that is used by cpufreq governors like schedutil to set the frequency of a CPU. The SCHED_CPUFREQ_MIGRATION flag forces an early call to cpufreq when the migration happens in a cgroup whereas util_avg of root cfs_rq is not yet updated and this call is duplicated with the one that happens immediately after when the migration event reaches the root cfs_rq. The dedicated flag SCHED_CPUFREQ_MIGRATION is now useless and can be removed. The interface of attach_entity_load_avg() can also be simplified accordingly. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Rafael J. Wysocki Link: https://lkml.kernel.org/r/1579083620-24943-1-git-send-email-vincent.guittot@linaro.org --- include/linux/sched/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index cc6bcc1e96bc..3ed5aa18593f 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -9,7 +9,6 @@ */ #define SCHED_CPUFREQ_IOWAIT (1U << 0) -#define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ struct cpufreq_policy; -- cgit v1.2.3 From 080bb352fad00d04995102f681b134e3754bfb6e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 15 Jan 2020 20:48:50 -0800 Subject: net: phy: Maintain MDIO device and bus statistics We maintain global statistics for an entire MDIO bus, as well as broken down, per MDIO bus address statistics. Given that it is possible for MDIO devices such as switches to access MDIO bus addresses for which there is not a mdio_device instance created (therefore not a a corresponding device directory in sysfs either), we also maintain per-address statistics under the statistics folder. The layout looks like this: /sys/class/mdio_bus/../statistics/ transfers errrors writes reads transfers_ errors_ writes_ reads_ When a mdio_device instance is registered, a statistics/ folder is created with the tranfers, errors, writes and reads attributes which point to the appropriate MDIO bus statistics structure. Statistics are 64-bit unsigned quantities and maintained through the u64_stats_sync.h helper functions. Signed-off-by: Florian Fainelli Tested-by: Andrew Lunn Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2929d0bc307f..99a87f02667f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -212,6 +213,15 @@ struct sfp_bus; struct sfp_upstream_ops; struct sk_buff; +struct mdio_bus_stats { + u64_stats_t transfers; + u64_stats_t errors; + u64_stats_t writes; + u64_stats_t reads; + /* Must be last, add new statistics above */ + struct u64_stats_sync syncp; +}; + /* * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure @@ -224,6 +234,7 @@ struct mii_bus { int (*read)(struct mii_bus *bus, int addr, int regnum); int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); int (*reset)(struct mii_bus *bus); + struct mdio_bus_stats stats[PHY_MAX_ADDR]; /* * A lock to ensure that only one thing can read/write -- cgit v1.2.3 From 4c8ff7095bef64fc47e996a938f7d57f9e077da3 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 1 Nov 2019 18:07:14 +0800 Subject: f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 284738996028..ac3f4888b3df 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -23,6 +23,7 @@ #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ #define NEW_ADDR ((block_t)-1) /* used as block_t addresses */ +#define COMPRESS_ADDR ((block_t)-2) /* used as compressed data flag */ #define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS) #define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS) @@ -271,6 +272,10 @@ struct f2fs_inode { __le32 i_inode_checksum;/* inode meta checksum */ __le64 i_crtime; /* creation time */ __le32 i_crtime_nsec; /* creation time in nano scale */ + __le64 i_compr_blocks; /* # of compressed blocks */ + __u8 i_compress_algorithm; /* compress algorithm */ + __u8 i_log_cluster_size; /* log of cluster size */ + __le16 i_padding; /* padding */ __le32 i_extra_end[0]; /* for attribute size calculation */ } __packed; __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ -- cgit v1.2.3 From 82a958497dc9120e0e8043da82273baedd255aaf Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 17 Jan 2020 12:36:32 -0500 Subject: XArray: Add wrappers for nested spinlocks Some users need to take an xarray lock while holding another xarray lock. Reported-by: Doug Gilbert Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 86eecbd98e84..736afd3aa56f 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -508,6 +508,14 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +#define xa_lock_nested(xa, subclass) \ + spin_lock_nested(&(xa)->xa_lock, subclass) +#define xa_lock_bh_nested(xa, subclass) \ + spin_lock_bh_nested(&(xa)->xa_lock, subclass) +#define xa_lock_irq_nested(xa, subclass) \ + spin_lock_irq_nested(&(xa)->xa_lock, subclass) +#define xa_lock_irqsave_nested(xa, flags, subclass) \ + spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the -- cgit v1.2.3 From 00ed452c210a0bc1ff3ee79e1ce6b199f00a0638 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 12 Jan 2020 15:54:10 -0500 Subject: XArray: Add xa_for_each_range This function supports iterating over a range of an array. Also add documentation links for xa_for_each_start(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 37 ++++++++++++++++++++++++++++++++----- 1 file changed, 32 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 736afd3aa56f..f73e1775ded0 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -416,6 +416,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) return xa->xa_flags & XA_FLAGS_MARK(mark); } +/** + * xa_for_each_range() - Iterate over a portion of an XArray. + * @xa: XArray. + * @index: Index of @entry. + * @entry: Entry retrieved from array. + * @start: First index to retrieve from array. + * @last: Last index to retrieve from array. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you + * want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set + * to NULL and @index will have a value less than or equal to max. + * + * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_range() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each() iterator instead. + * The xas_for_each() iterator will expand into more inline code than + * xa_for_each_range(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_range(xa, index, entry, start, last) \ + for (index = start, \ + entry = xa_find(xa, &index, last, XA_PRESENT); \ + entry; \ + entry = xa_find_after(xa, &index, last, XA_PRESENT)) + /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. @@ -439,11 +469,8 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) * * Context: Any context. Takes and releases the RCU lock. */ -#define xa_for_each_start(xa, index, entry, start) \ - for (index = start, \ - entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT); \ - entry; \ - entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT)) +#define xa_for_each_start(xa, index, entry, start) \ + xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. -- cgit v1.2.3 From da4d3d6bb9f6047217d549c233303161bb4678d9 Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Mon, 13 Jan 2020 12:26:52 +0200 Subject: iio: adc: ad-sigma-delta: Allow custom IRQ flags Before this patch the ad_sigma_delta implementation hardcoded the irq trigger type to low, assuming that all Sigma-Delta ADCs have the same interrupt-type. This patch allows all drivers using the ad_sigma_delta layer to set the irq trigger type to the one specified in the datasheet. Signed-off-by: Alexandru Tachici Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 8a4e25a7080c..5a127c0ed200 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -40,6 +40,7 @@ struct iio_dev; * @read_mask: Mask for the communications register having the read bit set. * @data_reg: Address of the data register, if 0 the default address of 0x3 will * be used. + * @irq_flags: flags for the interrupt used by the triggered buffer */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); @@ -49,6 +50,7 @@ struct ad_sigma_delta_info { unsigned int addr_shift; unsigned int read_mask; unsigned int data_reg; + unsigned long irq_flags; }; /** -- cgit v1.2.3 From 608184788502fd475e7bca4b1692fda5f0fef5b6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Jan 2020 19:44:24 +0200 Subject: iio: magnetometer: ak8975: Get rid of platform data Since IIO framework supports device property API and driver has been moved already to the use of GPIO descriptors the logical continuation is to get rid of platform data completely. We are on the safe side here since there are no users of it in the kernel. Signed-off-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/magnetometer/ak8975.h | 15 --------------- 1 file changed, 15 deletions(-) delete mode 100644 include/linux/iio/magnetometer/ak8975.h (limited to 'include/linux') diff --git a/include/linux/iio/magnetometer/ak8975.h b/include/linux/iio/magnetometer/ak8975.h deleted file mode 100644 index df3697183800..000000000000 --- a/include/linux/iio/magnetometer/ak8975.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IIO_MAGNETOMETER_AK8975_H__ -#define __IIO_MAGNETOMETER_AK8975_H__ - -#include - -/** - * struct ak8975_platform_data - AK8975 magnetometer driver platform data - * @orientation: mounting matrix relative to main hardware - */ -struct ak8975_platform_data { - struct iio_mount_matrix orientation; -}; - -#endif -- cgit v1.2.3 From fddb5d430ad9fa91b49b1d34d0202ffe2fa0e179 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 18 Jan 2020 23:07:59 +1100 Subject: open: introduce openat2(2) syscall /* Background. */ For a very long time, extending openat(2) with new features has been incredibly frustrating. This stems from the fact that openat(2) is possibly the most famous counter-example to the mantra "don't silently accept garbage from userspace" -- it doesn't check whether unknown flags are present[1]. This means that (generally) the addition of new flags to openat(2) has been fraught with backwards-compatibility issues (O_TMPFILE has to be defined as __O_TMPFILE|O_DIRECTORY|[O_RDWR or O_WRONLY] to ensure old kernels gave errors, since it's insecure to silently ignore the flag[2]). All new security-related flags therefore have a tough road to being added to openat(2). Userspace also has a hard time figuring out whether a particular flag is supported on a particular kernel. While it is now possible with contemporary kernels (thanks to [3]), older kernels will expose unknown flag bits through fcntl(F_GETFL). Giving a clear -EINVAL during openat(2) time matches modern syscall designs and is far more fool-proof. In addition, the newly-added path resolution restriction LOOKUP flags (which we would like to expose to user-space) don't feel related to the pre-existing O_* flag set -- they affect all components of path lookup. We'd therefore like to add a new flag argument. Adding a new syscall allows us to finally fix the flag-ignoring problem, and we can make it extensible enough so that we will hopefully never need an openat3(2). /* Syscall Prototype. */ /* * open_how is an extensible structure (similar in interface to * clone3(2) or sched_setattr(2)). The size parameter must be set to * sizeof(struct open_how), to allow for future extensions. All future * extensions will be appended to open_how, with their zero value * acting as a no-op default. */ struct open_how { /* ... */ }; int openat2(int dfd, const char *pathname, struct open_how *how, size_t size); /* Description. */ The initial version of 'struct open_how' contains the following fields: flags Used to specify openat(2)-style flags. However, any unknown flag bits or otherwise incorrect flag combinations (like O_PATH|O_RDWR) will result in -EINVAL. In addition, this field is 64-bits wide to allow for more O_ flags than currently permitted with openat(2). mode The file mode for O_CREAT or O_TMPFILE. Must be set to zero if flags does not contain O_CREAT or O_TMPFILE. resolve Restrict path resolution (in contrast to O_* flags they affect all path components). The current set of flags are as follows (at the moment, all of the RESOLVE_ flags are implemented as just passing the corresponding LOOKUP_ flag). RESOLVE_NO_XDEV => LOOKUP_NO_XDEV RESOLVE_NO_SYMLINKS => LOOKUP_NO_SYMLINKS RESOLVE_NO_MAGICLINKS => LOOKUP_NO_MAGICLINKS RESOLVE_BENEATH => LOOKUP_BENEATH RESOLVE_IN_ROOT => LOOKUP_IN_ROOT open_how does not contain an embedded size field, because it is of little benefit (userspace can figure out the kernel open_how size at runtime fairly easily without it). It also only contains u64s (even though ->mode arguably should be a u16) to avoid having padding fields which are never used in the future. Note that as a result of the new how->flags handling, O_PATH|O_TMPFILE is no longer permitted for openat(2). As far as I can tell, this has always been a bug and appears to not be used by userspace (and I've not seen any problems on my machines by disallowing it). If it turns out this breaks something, we can special-case it and only permit it for openat(2) but not openat2(2). After input from Florian Weimer, the new open_how and flag definitions are inside a separate header from uapi/linux/fcntl.h, to avoid problems that glibc has with importing that header. /* Testing. */ In a follow-up patch there are over 200 selftests which ensure that this syscall has the correct semantics and will correctly handle several attack scenarios. In addition, I've written a userspace library[4] which provides convenient wrappers around openat2(RESOLVE_IN_ROOT) (this is necessary because no other syscalls support RESOLVE_IN_ROOT, and thus lots of care must be taken when using RESOLVE_IN_ROOT'd file descriptors with other syscalls). During the development of this patch, I've run numerous verification tests using libpathrs (showing that the API is reasonably usable by userspace). /* Future Work. */ Additional RESOLVE_ flags have been suggested during the review period. These can be easily implemented separately (such as blocking auto-mount during resolution). Furthermore, there are some other proposed changes to the openat(2) interface (the most obvious example is magic-link hardening[5]) which would be a good opportunity to add a way for userspace to restrict how O_PATH file descriptors can be re-opened. Another possible avenue of future work would be some kind of CHECK_FIELDS[6] flag which causes the kernel to indicate to userspace which openat2(2) flags and fields are supported by the current kernel (to avoid userspace having to go through several guesses to figure it out). [1]: https://lwn.net/Articles/588444/ [2]: https://lore.kernel.org/lkml/CA+55aFyyxJL1LyXZeBsf2ypriraj5ut1XkNDsunRBqgVjZU_6Q@mail.gmail.com [3]: commit 629e014bb834 ("fs: completely ignore unknown open flags") [4]: https://sourceware.org/bugzilla/show_bug.cgi?id=17523 [5]: https://lore.kernel.org/lkml/20190930183316.10190-2-cyphar@cyphar.com/ [6]: https://youtu.be/ggD-eb3yPVs Suggested-by: Christian Brauner Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/fcntl.h | 16 +++++++++++++++- include/linux/syscalls.h | 3 +++ 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index d019df946cb2..7bcdcf4f6ab2 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -2,15 +2,29 @@ #ifndef _LINUX_FCNTL_H #define _LINUX_FCNTL_H +#include #include -/* list of all valid flags for the open/openat flags argument: */ +/* 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 | \ FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \ O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE) +/* List of all valid flags for the how->upgrade_mask argument: */ +#define VALID_UPGRADE_FLAGS \ + (UPGRADE_NOWRITE | UPGRADE_NOREAD) + +/* List of all valid flags for the how->resolve argument: */ +#define VALID_RESOLVE_FLAGS \ + (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ + RESOLVE_BENEATH | RESOLVE_IN_ROOT) + +/* List of all open_how "versions". */ +#define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ +#define OPEN_HOW_SIZE_LATEST OPEN_HOW_SIZE_VER0 + #ifndef force_o_largefile #define force_o_largefile() (!IS_ENABLED(CONFIG_ARCH_32BIT_OFF_T)) #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d0391cc2dae9..cd9f27cbc567 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -69,6 +69,7 @@ struct rseq; union bpf_attr; struct io_uring_params; struct clone_args; +struct open_how; #include #include @@ -439,6 +440,8 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); +asmlinkage long sys_openat2(int dfd, const char __user *filename, + struct open_how *how, size_t size); asmlinkage long sys_close(unsigned int fd); asmlinkage long sys_vhangup(void); -- cgit v1.2.3 From 1bde330ca0e8173d9a735a8a0a590a6e87a366cf Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sun, 12 Jan 2020 23:33:00 +0300 Subject: iio: accel: kxcjk1013: Support orientation matrix Hardware could be physically mounted in any possible direction and userpspace needs to be aware of the mounting orientation in order to process sensor's data correctly. In particular this helps iio-sensor-proxy to report display's orientation properly on a phone/tablet devices. Signed-off-by: Dmitry Osipenko Acked-by: Srinivas Pandruvada Signed-off-by: Jonathan Cameron --- include/linux/iio/accel/kxcjk_1013.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/accel/kxcjk_1013.h b/include/linux/iio/accel/kxcjk_1013.h index 8c3c78bc9f91..ea0ecb774371 100644 --- a/include/linux/iio/accel/kxcjk_1013.h +++ b/include/linux/iio/accel/kxcjk_1013.h @@ -7,8 +7,11 @@ #ifndef __IIO_KXCJK_1013_H__ #define __IIO_KXCJK_1013_H__ +#include + struct kxcjk_1013_platform_data { bool active_high_intr; + struct iio_mount_matrix orientation; }; #endif -- cgit v1.2.3 From 26c0e44a213b272abec0e8fba4a5a2801f95208e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 13 Jan 2020 18:22:42 +0100 Subject: efi: Add a flags parameter to efi_memory_map In preparation for garbage collecting dynamically allocated EFI memory maps, where the allocation method of memblock vs slab needs to be recalled, convert the existing 'late' flag into a 'flags' bitmask. Arrange for the flag to be passed via 'struct efi_memory_map_data'. This structure grows additional flags in follow-on changes. Signed-off-by: Dan Williams Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200113172245.27925-11-ardb@kernel.org --- include/linux/efi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 7e8e25b1d11c..f117d68c314e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -767,6 +767,7 @@ struct efi_memory_map_data { unsigned long size; unsigned long desc_version; unsigned long desc_size; + unsigned long flags; }; struct efi_memory_map { @@ -776,7 +777,8 @@ struct efi_memory_map { int nr_map; unsigned long desc_version; unsigned long desc_size; - bool late; +#define EFI_MEMMAP_LATE (1UL << 0) + unsigned long flags; }; struct efi_mem_range { -- cgit v1.2.3 From 1db91035d01aa8bfa2350c00ccb63d629b4041ad Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 13 Jan 2020 18:22:43 +0100 Subject: efi: Add tracking for dynamically allocated memmaps In preparation for fixing efi_memmap_alloc() leaks, add support for recording whether the memmap was dynamically allocated from slab, memblock, or is the original physical memmap provided by the platform. Given this tracking is established in efi_memmap_alloc() and needs to be carried to efi_memmap_install(), use 'struct efi_memory_map_data' to convey the flags. Some small cleanups result from this reorganization, specifically the removal of local variables for 'phys' and 'size' that are already tracked in @data. Signed-off-by: Dan Williams Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200113172245.27925-12-ardb@kernel.org --- include/linux/efi.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index f117d68c314e..adbe421835c1 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -759,8 +759,8 @@ typedef union { /* * Architecture independent structure for describing a memory map for the - * benefit of efi_memmap_init_early(), saving us the need to pass four - * parameters. + * benefit of efi_memmap_init_early(), and for passing context between + * efi_memmap_alloc() and efi_memmap_install(). */ struct efi_memory_map_data { phys_addr_t phys_map; @@ -778,6 +778,8 @@ struct efi_memory_map { unsigned long desc_version; unsigned long desc_size; #define EFI_MEMMAP_LATE (1UL << 0) +#define EFI_MEMMAP_MEMBLOCK (1UL << 1) +#define EFI_MEMMAP_SLAB (1UL << 2) unsigned long flags; }; @@ -972,11 +974,12 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); -extern phys_addr_t __init efi_memmap_alloc(unsigned int num_entries); +extern int __init efi_memmap_alloc(unsigned int num_entries, + struct efi_memory_map_data *data); extern int __init efi_memmap_init_early(struct efi_memory_map_data *data); extern int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size); extern void __init efi_memmap_unmap(void); -extern int __init efi_memmap_install(phys_addr_t addr, unsigned int nr_map); +extern int __init efi_memmap_install(struct efi_memory_map_data *data); extern int __init efi_memmap_split_count(efi_memory_desc_t *md, struct range *range); extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap, -- cgit v1.2.3 From 484a418d075488c6999528247cc711d12c373447 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 13 Jan 2020 18:22:45 +0100 Subject: efi: Fix handling of multiple efi_fake_mem= entries Dave noticed that when specifying multiple efi_fake_mem= entries only the last entry was successfully being reflected in the efi memory map. This is due to the fact that the efi_memmap_insert() is being called multiple times, but on successive invocations the insertion should be applied to the last new memmap rather than the original map at efi_fake_memmap() entry. Rework efi_fake_memmap() to install the new memory map after each efi_fake_mem= entry is parsed. This also fixes an issue in efi_fake_memmap() that caused it to litter emtpy entries into the end of the efi memory map. An empty entry causes efi_memmap_insert() to attempt more memmap splits / copies than efi_memmap_split_count() accounted for when sizing the new map. When that happens efi_memmap_insert() may overrun its allocation, and if you are lucky will spill over to an unmapped page leading to crash signature like the following rather than silent corruption: BUG: unable to handle page fault for address: ffffffffff281000 [..] RIP: 0010:efi_memmap_insert+0x11d/0x191 [..] Call Trace: ? bgrt_init+0xbe/0xbe ? efi_arch_mem_reserve+0x1cb/0x228 ? acpi_parse_bgrt+0xa/0xd ? acpi_table_parse+0x86/0xb8 ? acpi_boot_init+0x494/0x4e3 ? acpi_parse_x2apic+0x87/0x87 ? setup_acpi_sci+0xa2/0xa2 ? setup_arch+0x8db/0x9e1 ? start_kernel+0x6a/0x547 ? secondary_startup_64+0xb6/0xc0 Commit af1648984828 "x86/efi: Update e820 with reserved EFI boot services data to fix kexec breakage" introduced more occurrences where efi_memmap_insert() is invoked after an efi_fake_mem= configuration has been parsed. Previously the side effects of vestigial empty entries were benign, but with commit af1648984828 that follow-on efi_memmap_insert() invocation triggers efi_memmap_insert() overruns. Reported-by: Dave Young Signed-off-by: Dan Williams Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20191231014630.GA24942@dhcp-128-65.nay.redhat.com Link: https://lore.kernel.org/r/20200113172245.27925-14-ardb@kernel.org --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index adbe421835c1..7efd7072cca5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -976,6 +976,8 @@ extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern int __init efi_memmap_alloc(unsigned int num_entries, struct efi_memory_map_data *data); +extern void __efi_memmap_free(u64 phys, unsigned long size, + unsigned long flags); extern int __init efi_memmap_init_early(struct efi_memory_map_data *data); extern int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size); extern void __init efi_memmap_unmap(void); -- cgit v1.2.3 From b01ecceaf2c0c4b3f2d24aa0adcf096ab1648253 Mon Sep 17 00:00:00 2001 From: Yash Shah Date: Tue, 10 Dec 2019 16:41:09 +0530 Subject: genirq: Introduce irq_domain_translate_onecell Add a new function irq_domain_translate_onecell() that is to be used as the translate function in struct irq_domain_ops. Signed-off-by: Yash Shah Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1575976274-13487-2-git-send-email-yash.shah@sifive.com --- include/linux/irqdomain.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 3c340dbc5a1f..698749f42ced 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -427,6 +427,11 @@ int irq_domain_translate_twocell(struct irq_domain *d, unsigned long *out_hwirq, unsigned int *out_type); +int irq_domain_translate_onecell(struct irq_domain *d, + struct irq_fwspec *fwspec, + unsigned long *out_hwirq, + unsigned int *out_type); + /* IPI functions */ int irq_reserve_ipi(struct irq_domain *domain, const struct cpumask *dest); int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest); -- cgit v1.2.3 From 2ab1d925aa4c0c179dd1eb492e8c03536972707b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 19 Jan 2020 14:31:55 +0100 Subject: net: phy: add generic ndo_do_ioctl handler phy_do_ioctl A number of network drivers has the same glue code to use phy_mii_ioctl as ndo_do_ioctl handler. So let's add such a generic ndo_do_ioctl handler to phylib. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 99a87f02667f..be6b3a1b03da 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1242,6 +1242,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); +int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -- cgit v1.2.3 From e79f15a4598c1f3f3f7f3319ca308c63c91fdaf2 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Wed, 15 Jan 2020 17:28:51 +0800 Subject: x86/resctrl: Add task resctrl information display Monitoring tools that want to find out which resctrl control and monitor groups a task belongs to must currently read the "tasks" file in every group until they locate the process ID. Add an additional file /proc/{pid}/cpu_resctrl_groups to provide this information: 1) res: mon: resctrl is not available. 2) res:/ mon: Task is part of the root resctrl control group, and it is not associated to any monitor group. 3) res:/ mon:mon0 Task is part of the root resctrl control group and monitor group mon0. 4) res:group0 mon: Task is part of resctrl control group group0, and it is not associated to any monitor group. 5) res:group0 mon:mon1 Task is part of resctrl control group group0 and monitor group mon1. Signed-off-by: Chen Yu Signed-off-by: Borislav Petkov Tested-by: Jinshi Chen Link: https://lkml.kernel.org/r/20200115092851.14761-1-yu.c.chen@intel.com --- include/linux/resctrl.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/resctrl.h (limited to 'include/linux') diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h new file mode 100644 index 000000000000..daf5cf64c6a6 --- /dev/null +++ b/include/linux/resctrl.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _RESCTRL_H +#define _RESCTRL_H + +#ifdef CONFIG_PROC_CPU_RESCTRL + +int proc_resctrl_show(struct seq_file *m, + struct pid_namespace *ns, + struct pid *pid, + struct task_struct *tsk); + +#endif + +#endif /* _RESCTRL_H */ -- cgit v1.2.3 From e837dfde15a49c97dcbb059757d96c71e9e7bd54 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Fri, 13 Dec 2019 16:22:10 -0800 Subject: bitmap: genericize percpu bitmap region iterators Bitmaps are fairly popular for their space efficiency, but we don't have generic iterators available. Make percpu's bitmap region iterators available to everyone. Reviewed-by: Josef Bacik Signed-off-by: Dennis Zhou Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/bitmap.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index ff335b22f23c..cb63feb3cfbe 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -456,6 +456,41 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen, return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); } +static inline void bitmap_next_clear_region(unsigned long *bitmap, + unsigned int *rs, unsigned int *re, + unsigned int end) +{ + *rs = find_next_zero_bit(bitmap, end, *rs); + *re = find_next_bit(bitmap, end, *rs + 1); +} + +static inline void bitmap_next_set_region(unsigned long *bitmap, + unsigned int *rs, unsigned int *re, + unsigned int end) +{ + *rs = find_next_bit(bitmap, end, *rs); + *re = find_next_zero_bit(bitmap, end, *rs + 1); +} + +/* + * Bitmap region iterators. Iterates over the bitmap between [@start, @end). + * @rs and @re should be integer variables and will be set to start and end + * index of the current clear or set region. + */ +#define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ + for ((rs) = (start), \ + bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ + (rs) < (re); \ + (rs) = (re) + 1, \ + bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) + +#define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ + for ((rs) = (start), \ + bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ + (rs) < (re); \ + (rs) = (re) + 1, \ + bitmap_next_set_region((bitmap), &(rs), &(re), (end))) + /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value -- cgit v1.2.3 From 32c72165dbd0e246e69d16a3ad348a4851afd415 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Kadlecsik=20J=C3=B3zsef?= Date: Sun, 19 Jan 2020 22:06:49 +0100 Subject: netfilter: ipset: use bitmap infrastructure completely The bitmap allocation did not use full unsigned long sizes when calculating the required size and that was triggered by KASAN as slab-out-of-bounds read in several places. The patch fixes all of them. Reported-by: syzbot+fabca5cbf5e54f3fe2de@syzkaller.appspotmail.com Reported-by: syzbot+827ced406c9a1d9570ed@syzkaller.appspotmail.com Reported-by: syzbot+190d63957b22ef673ea5@syzkaller.appspotmail.com Reported-by: syzbot+dfccdb2bdb4a12ad425e@syzkaller.appspotmail.com Reported-by: syzbot+df0d0f5895ef1f41a65b@syzkaller.appspotmail.com Reported-by: syzbot+b08bd19bb37513357fd4@syzkaller.appspotmail.com Reported-by: syzbot+53cdd0ec0bbabd53370a@syzkaller.appspotmail.com Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 4d8b1eaf7708..908d38dbcb91 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -426,13 +426,6 @@ ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr) sizeof(*addr)); } -/* Calculate the bytes required to store the inclusive range of a-b */ -static inline int -bitmap_bytes(u32 a, u32 b) -{ - return 4 * ((((b - a + 8) / 8) + 3) / 4); -} - /* How often should the gc be run by default */ #define IPSET_GC_TIME (3 * 60) -- cgit v1.2.3 From 63c13d61eafe4606f1c16c54da40c4eee78e9edf Mon Sep 17 00:00:00 2001 From: Erin Lo Date: Tue, 12 Nov 2019 19:03:25 +0800 Subject: remoteproc/mediatek: add SCP support for mt8183 Provide a basic driver to control Cortex M4 co-processor Signed-off-by: Erin Lo Signed-off-by: Nicolas Boichat Signed-off-by: Pi-Hsun Shih Link: https://lore.kernel.org/r/20191112110330.179649-3-pihsun@chromium.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc/mtk_scp.h | 65 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/remoteproc/mtk_scp.h (limited to 'include/linux') diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h new file mode 100644 index 000000000000..80f5eab2ac2d --- /dev/null +++ b/include/linux/remoteproc/mtk_scp.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2019 MediaTek Inc. + */ + +#ifndef _MTK_SCP_H +#define _MTK_SCP_H + +#include + +typedef void (*scp_ipi_handler_t) (void *data, + unsigned int len, + void *priv); +struct mtk_scp; + +/** + * enum ipi_id - the id of inter-processor interrupt + * + * @SCP_IPI_INIT: The interrupt from scp is to notfiy kernel + * SCP initialization completed. + * IPI_SCP_INIT is sent from SCP when firmware is + * loaded. AP doesn't need to send IPI_SCP_INIT + * command to SCP. + * For other IPI below, AP should send the request + * to SCP to trigger the interrupt. + * @SCP_IPI_MAX: The maximum IPI number + */ + +enum scp_ipi_id { + SCP_IPI_INIT = 0, + SCP_IPI_VDEC_H264, + SCP_IPI_VDEC_VP8, + SCP_IPI_VDEC_VP9, + SCP_IPI_VENC_H264, + SCP_IPI_VENC_VP8, + SCP_IPI_MDP_INIT, + SCP_IPI_MDP_DEINIT, + SCP_IPI_MDP_FRAME, + SCP_IPI_DIP, + SCP_IPI_ISP_CMD, + SCP_IPI_ISP_FRAME, + SCP_IPI_FD_CMD, + SCP_IPI_CROS_HOST_CMD, + SCP_IPI_MAX, +}; + +struct mtk_scp *scp_get(struct platform_device *pdev); +void scp_put(struct mtk_scp *scp); + +struct device *scp_get_device(struct mtk_scp *scp); +struct rproc *scp_get_rproc(struct mtk_scp *scp); + +int scp_ipi_register(struct mtk_scp *scp, u32 id, scp_ipi_handler_t handler, + void *priv); +void scp_ipi_unregister(struct mtk_scp *scp, u32 id); + +int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len, + unsigned int wait); + +unsigned int scp_get_vdec_hw_capa(struct mtk_scp *scp); +unsigned int scp_get_venc_hw_capa(struct mtk_scp *scp); + +void *scp_mapping_dm_addr(struct mtk_scp *scp, u32 mem_addr); + +#endif /* _MTK_SCP_H */ -- cgit v1.2.3 From 7017996951fde84698ddfe7fd47f92bd9d9eb85d Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Tue, 12 Nov 2019 19:03:26 +0800 Subject: rpmsg: add rpmsg support for mt8183 SCP. Add a simple rpmsg support for mt8183 SCP, that use IPI / IPC directly. Signed-off-by: Pi-Hsun Shih Link: https://lore.kernel.org/r/20191112110330.179649-4-pihsun@chromium.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc/mtk_scp.h | 3 ++- include/linux/rpmsg/mtk_rpmsg.h | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 1 deletion(-) create mode 100644 include/linux/rpmsg/mtk_rpmsg.h (limited to 'include/linux') diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h index 80f5eab2ac2d..b47416f7aeb8 100644 --- a/include/linux/remoteproc/mtk_scp.h +++ b/include/linux/remoteproc/mtk_scp.h @@ -41,7 +41,8 @@ enum scp_ipi_id { SCP_IPI_ISP_FRAME, SCP_IPI_FD_CMD, SCP_IPI_CROS_HOST_CMD, - SCP_IPI_MAX, + SCP_IPI_NS_SERVICE = 0xFF, + SCP_IPI_MAX = 0x100, }; struct mtk_scp *scp_get(struct platform_device *pdev); diff --git a/include/linux/rpmsg/mtk_rpmsg.h b/include/linux/rpmsg/mtk_rpmsg.h new file mode 100644 index 000000000000..363b60178040 --- /dev/null +++ b/include/linux/rpmsg/mtk_rpmsg.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2019 Google LLC. + */ + +#ifndef __LINUX_RPMSG_MTK_RPMSG_H +#define __LINUX_RPMSG_MTK_RPMSG_H + +#include +#include + +typedef void (*ipi_handler_t)(void *data, unsigned int len, void *priv); + +/* + * struct mtk_rpmsg_info - IPI functions tied to the rpmsg device. + * @register_ipi: register IPI handler for an IPI id. + * @unregister_ipi: unregister IPI handler for a registered IPI id. + * @send_ipi: send IPI to an IPI id. wait is the timeout (in msecs) to wait + * until response, or 0 if there's no timeout. + * @ns_ipi_id: the IPI id used for name service, or -1 if name service isn't + * supported. + */ +struct mtk_rpmsg_info { + int (*register_ipi)(struct platform_device *pdev, u32 id, + ipi_handler_t handler, void *priv); + void (*unregister_ipi)(struct platform_device *pdev, u32 id); + int (*send_ipi)(struct platform_device *pdev, u32 id, + void *buf, unsigned int len, unsigned int wait); + int ns_ipi_id; +}; + +struct rproc_subdev * +mtk_rpmsg_create_rproc_subdev(struct platform_device *pdev, + struct mtk_rpmsg_info *info); + +void mtk_rpmsg_destroy_rproc_subdev(struct rproc_subdev *subdev); + +#endif -- cgit v1.2.3 From db08ca25253d56f1f76eb4b3fe32a7ac1fbab741 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 25 Dec 2019 22:14:54 -0700 Subject: mm: make do_madvise() available internally This is in preparation for enabling this functionality through io_uring. Add a helper that is just exporting what sys_madvise() does, and have the system call use it. No functional changes in this patch. Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index cfaa8feecfe8..b4ba5b3bb54b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2328,6 +2328,7 @@ 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); static inline unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, -- cgit v1.2.3 From 4e5ef02317b12e2ed3d604281ffb6b75261f7612 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 28 Dec 2019 14:13:02 +0300 Subject: pcpu_ref: add percpu_ref_tryget_many() Add percpu_ref_tryget_many(), which works the same way as percpu_ref_tryget(), but grabs specified number of refs. Signed-off-by: Pavel Begunkov Acked-by: Tejun Heo Acked-by: Dennis Zhou Cc: Christoph Lameter Signed-off-by: Jens Axboe --- include/linux/percpu-refcount.h | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 390031e816dc..22d9d183950d 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -210,15 +210,17 @@ static inline void percpu_ref_get(struct percpu_ref *ref) } /** - * percpu_ref_tryget - try to increment a percpu refcount + * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get + * @nr: number of references to get * - * Increment a percpu refcount unless its count already reached zero. + * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ -static inline bool percpu_ref_tryget(struct percpu_ref *ref) +static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, + unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; @@ -226,10 +228,10 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { - this_cpu_inc(*percpu_count); + this_cpu_add(*percpu_count, nr); ret = true; } else { - ret = atomic_long_inc_not_zero(&ref->count); + ret = atomic_long_add_unless(&ref->count, nr, 0); } rcu_read_unlock(); @@ -237,6 +239,20 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) return ret; } +/** + * percpu_ref_tryget - try to increment a percpu refcount + * @ref: percpu_ref to try-get + * + * Increment a percpu refcount unless its count already reached zero. + * Returns %true on success; %false on failure. + * + * This function is safe to call as long as @ref is between init and exit. + */ +static inline bool percpu_ref_tryget(struct percpu_ref *ref) +{ + return percpu_ref_tryget_many(ref, 1); +} + /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get -- cgit v1.2.3 From 4db8fd32ed2be7cc510e51e43ec3349aa64074a9 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 23 Dec 2019 13:04:44 +0200 Subject: dmaengine: Add metadata_ops for dma_async_tx_descriptor The metadata is best described as side band data or parameters traveling alongside the data DMAd by the DMA engine. It is data which is understood by the peripheral and the peripheral driver only, the DMA engine see it only as data block and it is not interpreting it in any way. The metadata can be different per descriptor as it is a parameter for the data being transferred. If the DMA supports per descriptor metadata it can implement the attach, get_ptr/set_len callbacks. Client drivers must only use either attach or get_ptr/set_len to avoid misconfiguration. Client driver can check if a given metadata mode is supported by the channel during probe time with dmaengine_is_metadata_mode_supported(chan, DESC_METADATA_CLIENT); dmaengine_is_metadata_mode_supported(chan, DESC_METADATA_ENGINE); and based on this information can use either mode. Wrappers are also added for the metadata_ops. To be used in DESC_METADATA_CLIENT mode: dmaengine_desc_attach_metadata() To be used in DESC_METADATA_ENGINE mode: dmaengine_desc_get_metadata_ptr() dmaengine_desc_set_metadata_len() Signed-off-by: Peter Ujfalusi Reviewed-by: Tero Kristo Tested-by: Keerthy Reviewed-by: Grygorii Strashko Link: https://lore.kernel.org/r/20191223110458.30766-5-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 112 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 112 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 7927731e3716..68b361891a61 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -219,6 +219,62 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; * @bytes_transferred: byte counter */ +/** + * enum dma_desc_metadata_mode - per descriptor metadata mode types supported + * @DESC_METADATA_CLIENT - the metadata buffer is allocated/provided by the + * client driver and it is attached (via the dmaengine_desc_attach_metadata() + * helper) to the descriptor. + * + * Client drivers interested to use this mode can follow: + * - DMA_MEM_TO_DEV / DEV_MEM_TO_MEM: + * 1. prepare the descriptor (dmaengine_prep_*) + * construct the metadata in the client's buffer + * 2. use dmaengine_desc_attach_metadata() to attach the buffer to the + * descriptor + * 3. submit the transfer + * - DMA_DEV_TO_MEM: + * 1. prepare the descriptor (dmaengine_prep_*) + * 2. use dmaengine_desc_attach_metadata() to attach the buffer to the + * descriptor + * 3. submit the transfer + * 4. when the transfer is completed, the metadata should be available in the + * attached buffer + * + * @DESC_METADATA_ENGINE - the metadata buffer is allocated/managed by the DMA + * driver. The client driver can ask for the pointer, maximum size and the + * currently used size of the metadata and can directly update or read it. + * dmaengine_desc_get_metadata_ptr() and dmaengine_desc_set_metadata_len() is + * provided as helper functions. + * + * Note: the metadata area for the descriptor is no longer valid after the + * transfer has been completed (valid up to the point when the completion + * callback returns if used). + * + * Client drivers interested to use this mode can follow: + * - DMA_MEM_TO_DEV / DEV_MEM_TO_MEM: + * 1. prepare the descriptor (dmaengine_prep_*) + * 2. use dmaengine_desc_get_metadata_ptr() to get the pointer to the engine's + * metadata area + * 3. update the metadata at the pointer + * 4. use dmaengine_desc_set_metadata_len() to tell the DMA engine the amount + * of data the client has placed into the metadata buffer + * 5. submit the transfer + * - DMA_DEV_TO_MEM: + * 1. prepare the descriptor (dmaengine_prep_*) + * 2. submit the transfer + * 3. on transfer completion, use dmaengine_desc_get_metadata_ptr() to get the + * pointer to the engine's metadata area + * 4. Read out the metadata from the pointer + * + * Note: the two mode is not compatible and clients must use one mode for a + * descriptor. + */ +enum dma_desc_metadata_mode { + DESC_METADATA_NONE = 0, + DESC_METADATA_CLIENT = BIT(0), + DESC_METADATA_ENGINE = BIT(1), +}; + struct dma_chan_percpu { /* stats */ unsigned long memcpy_count; @@ -475,6 +531,18 @@ struct dmaengine_unmap_data { dma_addr_t addr[0]; }; +struct dma_async_tx_descriptor; + +struct dma_descriptor_metadata_ops { + int (*attach)(struct dma_async_tx_descriptor *desc, void *data, + size_t len); + + void *(*get_ptr)(struct dma_async_tx_descriptor *desc, + size_t *payload_len, size_t *max_len); + int (*set_len)(struct dma_async_tx_descriptor *desc, + size_t payload_len); +}; + /** * struct dma_async_tx_descriptor - async transaction descriptor * ---dma generic offload fields--- @@ -488,6 +556,11 @@ struct dmaengine_unmap_data { * descriptor pending. To be pushed on .issue_pending() call * @callback: routine to call after this operation is complete * @callback_param: general parameter to pass to the callback routine + * @desc_metadata_mode: core managed metadata mode to protect mixed use of + * DESC_METADATA_CLIENT or DESC_METADATA_ENGINE. Otherwise + * DESC_METADATA_NONE + * @metadata_ops: DMA driver provided metadata mode ops, need to be set by the + * DMA driver if metadata mode is supported with the descriptor * ---async_tx api specific fields--- * @next: at completion submit this descriptor * @parent: pointer to the next level up in the dependency chain @@ -504,6 +577,8 @@ struct dma_async_tx_descriptor { dma_async_tx_callback_result callback_result; void *callback_param; struct dmaengine_unmap_data *unmap; + enum dma_desc_metadata_mode desc_metadata_mode; + struct dma_descriptor_metadata_ops *metadata_ops; #ifdef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH struct dma_async_tx_descriptor *next; struct dma_async_tx_descriptor *parent; @@ -666,6 +741,7 @@ struct dma_filter { * @global_node: list_head for global dma_device_list * @filter: information for device/slave to filter function/param mapping * @cap_mask: one or more dma_capability flags + * @desc_metadata_modes: supported metadata modes by the DMA device * @max_xor: maximum number of xor sources, 0 if no capability * @max_pq: maximum number of PQ sources and PQ-continue capability * @copy_align: alignment shift for memcpy operations @@ -733,6 +809,7 @@ struct dma_device { struct list_head global_node; struct dma_filter filter; dma_cap_mask_t cap_mask; + enum dma_desc_metadata_mode desc_metadata_modes; unsigned short max_xor; unsigned short max_pq; enum dmaengine_alignment copy_align; @@ -910,6 +987,41 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( len, flags); } +static inline bool dmaengine_is_metadata_mode_supported(struct dma_chan *chan, + enum dma_desc_metadata_mode mode) +{ + if (!chan) + return false; + + return !!(chan->device->desc_metadata_modes & mode); +} + +#ifdef CONFIG_DMA_ENGINE +int dmaengine_desc_attach_metadata(struct dma_async_tx_descriptor *desc, + void *data, size_t len); +void *dmaengine_desc_get_metadata_ptr(struct dma_async_tx_descriptor *desc, + size_t *payload_len, size_t *max_len); +int dmaengine_desc_set_metadata_len(struct dma_async_tx_descriptor *desc, + size_t payload_len); +#else /* CONFIG_DMA_ENGINE */ +static inline int dmaengine_desc_attach_metadata( + struct dma_async_tx_descriptor *desc, void *data, size_t len) +{ + return -EINVAL; +} +static inline void *dmaengine_desc_get_metadata_ptr( + struct dma_async_tx_descriptor *desc, size_t *payload_len, + size_t *max_len) +{ + return NULL; +} +static inline int dmaengine_desc_set_metadata_len( + struct dma_async_tx_descriptor *desc, size_t payload_len) +{ + return -EINVAL; +} +#endif /* CONFIG_DMA_ENGINE */ + /** * dmaengine_terminate_all() - Terminate all active DMA transfers * @chan: The channel for which to terminate the transfers -- cgit v1.2.3 From 6755ec06d1333765d2b935e4e4a5bd011332bac6 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 23 Dec 2019 13:04:45 +0200 Subject: dmaengine: Add support for reporting DMA cached data amount A DMA hardware can have big cache or FIFO and the amount of data sitting in the DMA fabric can be an interest for the clients. For example in audio we want to know the delay in the data flow and in case the DMA have significantly large FIFO/cache, it can affect the latenc/delay Signed-off-by: Peter Ujfalusi Reviewed-by: Tero Kristo Tested-by: Keerthy Reviewed-by: Grygorii Strashko Link: https://lore.kernel.org/r/20191223110458.30766-6-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 68b361891a61..b44b9c608709 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -686,11 +686,13 @@ static inline struct dma_async_tx_descriptor *txd_next(struct dma_async_tx_descr * @residue: the remaining number of bytes left to transmit * on the selected transfer for states DMA_IN_PROGRESS and * DMA_PAUSED if this is implemented in the driver, else 0 + * @in_flight_bytes: amount of data in bytes cached by the DMA. */ struct dma_tx_state { dma_cookie_t last; dma_cookie_t used; u32 residue; + u32 in_flight_bytes; }; /** -- cgit v1.2.3 From 816ebf48442eef1c61db26d2ec055f5c8ac83b21 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 23 Dec 2019 13:04:46 +0200 Subject: dmaengine: Add helper function to convert direction value to text dmaengine_get_direction_text() can be useful when the direction is printed out. The text is easier to comprehend than the number. Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20191223110458.30766-7-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index b44b9c608709..62225d46908b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1545,4 +1545,23 @@ static inline struct dma_chan return __dma_request_channel(mask, fn, fn_param, NULL); } + +static inline char * +dmaengine_get_direction_text(enum dma_transfer_direction dir) +{ + switch (dir) { + case DMA_DEV_TO_MEM: + return "DEV_TO_MEM"; + case DMA_MEM_TO_DEV: + return "MEM_TO_DEV"; + case DMA_MEM_TO_MEM: + return "MEM_TO_MEM"; + case DMA_DEV_TO_DEV: + return "DEV_TO_DEV"; + default: + break; + } + + return "invalid"; +} #endif /* DMAENGINE_H */ -- cgit v1.2.3 From 69bafc318560d02dc07e3b52af0d7cf5fc036bfe Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 23 Dec 2019 13:04:47 +0200 Subject: dmaengine: ti: Add cppi5 header for K3 NAVSS/UDMA The K3 DMA architecture uses CPPI5 (Communications Port Programming Interface) specified descriptors over PSI-L bus within NAVSS. The header provides helpers, macros to work with these descriptors in a consistent way. Signed-off-by: Peter Ujfalusi Tested-by: Keerthy Reviewed-by: Grygorii Strashko Link: https://lore.kernel.org/r/20191223110458.30766-8-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dma/ti-cppi5.h | 1059 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1059 insertions(+) create mode 100644 include/linux/dma/ti-cppi5.h (limited to 'include/linux') diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h new file mode 100644 index 000000000000..579356ae447e --- /dev/null +++ b/include/linux/dma/ti-cppi5.h @@ -0,0 +1,1059 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * CPPI5 descriptors interface + * + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + */ + +#ifndef __TI_CPPI5_H__ +#define __TI_CPPI5_H__ + +#include +#include +#include + +/** + * struct cppi5_desc_hdr_t - Descriptor header, present in all types of + * descriptors + * @pkt_info0: Packet info word 0 (n/a in Buffer desc) + * @pkt_info0: Packet info word 1 (n/a in Buffer desc) + * @pkt_info0: Packet info word 2 (n/a in Buffer desc) + * @src_dst_tag: Packet info word 3 (n/a in Buffer desc) + */ +struct cppi5_desc_hdr_t { + u32 pkt_info0; + u32 pkt_info1; + u32 pkt_info2; + u32 src_dst_tag; +} __packed; + +/** + * struct cppi5_host_desc_t - Host-mode packet and buffer descriptor definition + * @hdr: Descriptor header + * @next_desc: word 4/5: Linking word + * @buf_ptr: word 6/7: Buffer pointer + * @buf_info1: word 8: Buffer valid data length + * @org_buf_len: word 9: Original buffer length + * @org_buf_ptr: word 10/11: Original buffer pointer + * @epib[0]: Extended Packet Info Data (optional, 4 words), and/or + * Protocol Specific Data (optional, 0-128 bytes in + * multiples of 4), and/or + * Other Software Data (0-N bytes, optional) + */ +struct cppi5_host_desc_t { + struct cppi5_desc_hdr_t hdr; + u64 next_desc; + u64 buf_ptr; + u32 buf_info1; + u32 org_buf_len; + u64 org_buf_ptr; + u32 epib[0]; +} __packed; + +#define CPPI5_DESC_MIN_ALIGN (16U) + +#define CPPI5_INFO0_HDESC_EPIB_SIZE (16U) +#define CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE (128U) + +#define CPPI5_INFO0_HDESC_TYPE_SHIFT (30U) +#define CPPI5_INFO0_HDESC_TYPE_MASK GENMASK(31, 30) +#define CPPI5_INFO0_DESC_TYPE_VAL_HOST (1U) +#define CPPI5_INFO0_DESC_TYPE_VAL_MONO (2U) +#define CPPI5_INFO0_DESC_TYPE_VAL_TR (3U) +#define CPPI5_INFO0_HDESC_EPIB_PRESENT BIT(29) +/* + * Protocol Specific Words location: + * 0 - located in the descriptor, + * 1 = located in the SOP Buffer immediately prior to the data. + */ +#define CPPI5_INFO0_HDESC_PSINFO_LOCATION BIT(28) +#define CPPI5_INFO0_HDESC_PSINFO_SIZE_SHIFT (22U) +#define CPPI5_INFO0_HDESC_PSINFO_SIZE_MASK GENMASK(27, 22) +#define CPPI5_INFO0_HDESC_PKTLEN_SHIFT (0) +#define CPPI5_INFO0_HDESC_PKTLEN_MASK GENMASK(21, 0) + +#define CPPI5_INFO1_DESC_PKTERROR_SHIFT (28U) +#define CPPI5_INFO1_DESC_PKTERROR_MASK GENMASK(31, 28) +#define CPPI5_INFO1_HDESC_PSFLGS_SHIFT (24U) +#define CPPI5_INFO1_HDESC_PSFLGS_MASK GENMASK(27, 24) +#define CPPI5_INFO1_DESC_PKTID_SHIFT (14U) +#define CPPI5_INFO1_DESC_PKTID_MASK GENMASK(23, 14) +#define CPPI5_INFO1_DESC_FLOWID_SHIFT (0) +#define CPPI5_INFO1_DESC_FLOWID_MASK GENMASK(13, 0) +#define CPPI5_INFO1_DESC_FLOWID_DEFAULT CPPI5_INFO1_DESC_FLOWID_MASK + +#define CPPI5_INFO2_HDESC_PKTTYPE_SHIFT (27U) +#define CPPI5_INFO2_HDESC_PKTTYPE_MASK GENMASK(31, 27) +/* Return Policy: 0 - Entire packet 1 - Each buffer */ +#define CPPI5_INFO2_HDESC_RETPOLICY BIT(18) +/* + * Early Return: + * 0 = desc pointers should be returned after all reads have been completed + * 1 = desc pointers should be returned immediately upon fetching + * the descriptor and beginning to transfer data. + */ +#define CPPI5_INFO2_HDESC_EARLYRET BIT(17) +/* + * Return Push Policy: + * 0 = Descriptor must be returned to tail of queue + * 1 = Descriptor must be returned to head of queue + */ +#define CPPI5_INFO2_DESC_RETPUSHPOLICY BIT(16) +#define CPPI5_INFO2_DESC_RETP_MASK GENMASK(18, 16) + +#define CPPI5_INFO2_DESC_RETQ_SHIFT (0) +#define CPPI5_INFO2_DESC_RETQ_MASK GENMASK(15, 0) + +#define CPPI5_INFO3_DESC_SRCTAG_SHIFT (16U) +#define CPPI5_INFO3_DESC_SRCTAG_MASK GENMASK(31, 16) +#define CPPI5_INFO3_DESC_DSTTAG_SHIFT (0) +#define CPPI5_INFO3_DESC_DSTTAG_MASK GENMASK(15, 0) + +#define CPPI5_BUFINFO1_HDESC_DATA_LEN_SHIFT (0) +#define CPPI5_BUFINFO1_HDESC_DATA_LEN_MASK GENMASK(27, 0) + +#define CPPI5_OBUFINFO0_HDESC_BUF_LEN_SHIFT (0) +#define CPPI5_OBUFINFO0_HDESC_BUF_LEN_MASK GENMASK(27, 0) + +/** + * struct cppi5_desc_epib_t - Host Packet Descriptor Extended Packet Info Block + * @timestamp: word 0: application specific timestamp + * @sw_info0: word 1: Software Info 0 + * @sw_info1: word 1: Software Info 1 + * @sw_info2: word 1: Software Info 2 + */ +struct cppi5_desc_epib_t { + u32 timestamp; /* w0: application specific timestamp */ + u32 sw_info0; /* w1: Software Info 0 */ + u32 sw_info1; /* w2: Software Info 1 */ + u32 sw_info2; /* w3: Software Info 2 */ +}; + +/** + * struct cppi5_monolithic_desc_t - Monolithic-mode packet descriptor + * @hdr: Descriptor header + * @epib[0]: Extended Packet Info Data (optional, 4 words), and/or + * Protocol Specific Data (optional, 0-128 bytes in + * multiples of 4), and/or + * Other Software Data (0-N bytes, optional) + */ +struct cppi5_monolithic_desc_t { + struct cppi5_desc_hdr_t hdr; + u32 epib[0]; +}; + +#define CPPI5_INFO2_MDESC_DATA_OFFSET_SHIFT (18U) +#define CPPI5_INFO2_MDESC_DATA_OFFSET_MASK GENMASK(26, 18) + +/* + * Reload Count: + * 0 = Finish the packet and place the descriptor back on the return queue + * 1-0x1ff = Vector to the Reload Index and resume processing + * 0x1ff indicates perpetual loop, infinite reload until the channel is stopped + */ +#define CPPI5_INFO0_TRDESC_RLDCNT_SHIFT (20U) +#define CPPI5_INFO0_TRDESC_RLDCNT_MASK GENMASK(28, 20) +#define CPPI5_INFO0_TRDESC_RLDCNT_MAX (0x1ff) +#define CPPI5_INFO0_TRDESC_RLDCNT_INFINITE CPPI5_INFO0_TRDESC_RLDCNT_MAX +#define CPPI5_INFO0_TRDESC_RLDIDX_SHIFT (14U) +#define CPPI5_INFO0_TRDESC_RLDIDX_MASK GENMASK(19, 14) +#define CPPI5_INFO0_TRDESC_RLDIDX_MAX (0x3f) +#define CPPI5_INFO0_TRDESC_LASTIDX_SHIFT (0) +#define CPPI5_INFO0_TRDESC_LASTIDX_MASK GENMASK(13, 0) + +#define CPPI5_INFO1_TRDESC_RECSIZE_SHIFT (24U) +#define CPPI5_INFO1_TRDESC_RECSIZE_MASK GENMASK(26, 24) +#define CPPI5_INFO1_TRDESC_RECSIZE_VAL_16B (0) +#define CPPI5_INFO1_TRDESC_RECSIZE_VAL_32B (1U) +#define CPPI5_INFO1_TRDESC_RECSIZE_VAL_64B (2U) +#define CPPI5_INFO1_TRDESC_RECSIZE_VAL_128B (3U) + +static inline void cppi5_desc_dump(void *desc, u32 size) +{ + print_hex_dump(KERN_ERR, "dump udmap_desc: ", DUMP_PREFIX_NONE, + 32, 4, desc, size, false); +} + +#define CPPI5_TDCM_MARKER (0x1) +/** + * cppi5_desc_is_tdcm - check if the paddr indicates Teardown Complete Message + * @paddr: Physical address of the packet popped from the ring + * + * Returns true if the address indicates TDCM + */ +static inline bool cppi5_desc_is_tdcm(dma_addr_t paddr) +{ + return (paddr & CPPI5_TDCM_MARKER) ? true : false; +} + +/** + * cppi5_desc_get_type - get descriptor type + * @desc_hdr: packet descriptor/TR header + * + * Returns descriptor type: + * CPPI5_INFO0_DESC_TYPE_VAL_HOST + * CPPI5_INFO0_DESC_TYPE_VAL_MONO + * CPPI5_INFO0_DESC_TYPE_VAL_TR + */ +static inline u32 cppi5_desc_get_type(struct cppi5_desc_hdr_t *desc_hdr) +{ + return (desc_hdr->pkt_info0 & CPPI5_INFO0_HDESC_TYPE_MASK) >> + CPPI5_INFO0_HDESC_TYPE_SHIFT; +} + +/** + * cppi5_desc_get_errflags - get Error Flags from Desc + * @desc_hdr: packet/TR descriptor header + * + * Returns Error Flags from Packet/TR Descriptor + */ +static inline u32 cppi5_desc_get_errflags(struct cppi5_desc_hdr_t *desc_hdr) +{ + return (desc_hdr->pkt_info1 & CPPI5_INFO1_DESC_PKTERROR_MASK) >> + CPPI5_INFO1_DESC_PKTERROR_SHIFT; +} + +/** + * cppi5_desc_get_pktids - get Packet and Flow ids from Desc + * @desc_hdr: packet/TR descriptor header + * @pkt_id: Packet ID + * @flow_id: Flow ID + * + * Returns Packet and Flow ids from packet/TR descriptor + */ +static inline void cppi5_desc_get_pktids(struct cppi5_desc_hdr_t *desc_hdr, + u32 *pkt_id, u32 *flow_id) +{ + *pkt_id = (desc_hdr->pkt_info1 & CPPI5_INFO1_DESC_PKTID_MASK) >> + CPPI5_INFO1_DESC_PKTID_SHIFT; + *flow_id = (desc_hdr->pkt_info1 & CPPI5_INFO1_DESC_FLOWID_MASK) >> + CPPI5_INFO1_DESC_FLOWID_SHIFT; +} + +/** + * cppi5_desc_set_pktids - set Packet and Flow ids in Desc + * @desc_hdr: packet/TR descriptor header + * @pkt_id: Packet ID + * @flow_id: Flow ID + */ +static inline void cppi5_desc_set_pktids(struct cppi5_desc_hdr_t *desc_hdr, + u32 pkt_id, u32 flow_id) +{ + desc_hdr->pkt_info1 &= ~(CPPI5_INFO1_DESC_PKTID_MASK | + CPPI5_INFO1_DESC_FLOWID_MASK); + desc_hdr->pkt_info1 |= (pkt_id << CPPI5_INFO1_DESC_PKTID_SHIFT) & + CPPI5_INFO1_DESC_PKTID_MASK; + desc_hdr->pkt_info1 |= (flow_id << CPPI5_INFO1_DESC_FLOWID_SHIFT) & + CPPI5_INFO1_DESC_FLOWID_MASK; +} + +/** + * cppi5_desc_set_retpolicy - set Packet Return Policy in Desc + * @desc_hdr: packet/TR descriptor header + * @flags: fags, supported values + * CPPI5_INFO2_HDESC_RETPOLICY + * CPPI5_INFO2_HDESC_EARLYRET + * CPPI5_INFO2_DESC_RETPUSHPOLICY + * @return_ring_id: Packet Return Queue/Ring id, value 0xFFFF reserved + */ +static inline void cppi5_desc_set_retpolicy(struct cppi5_desc_hdr_t *desc_hdr, + u32 flags, u32 return_ring_id) +{ + desc_hdr->pkt_info2 &= ~(CPPI5_INFO2_DESC_RETP_MASK | + CPPI5_INFO2_DESC_RETQ_MASK); + desc_hdr->pkt_info2 |= flags & CPPI5_INFO2_DESC_RETP_MASK; + desc_hdr->pkt_info2 |= return_ring_id & CPPI5_INFO2_DESC_RETQ_MASK; +} + +/** + * cppi5_desc_get_tags_ids - get Packet Src/Dst Tags from Desc + * @desc_hdr: packet/TR descriptor header + * @src_tag_id: Source Tag + * @dst_tag_id: Dest Tag + * + * Returns Packet Src/Dst Tags from packet/TR descriptor + */ +static inline void cppi5_desc_get_tags_ids(struct cppi5_desc_hdr_t *desc_hdr, + u32 *src_tag_id, u32 *dst_tag_id) +{ + if (src_tag_id) + *src_tag_id = (desc_hdr->src_dst_tag & + CPPI5_INFO3_DESC_SRCTAG_MASK) >> + CPPI5_INFO3_DESC_SRCTAG_SHIFT; + if (dst_tag_id) + *dst_tag_id = desc_hdr->src_dst_tag & + CPPI5_INFO3_DESC_DSTTAG_MASK; +} + +/** + * cppi5_desc_set_tags_ids - set Packet Src/Dst Tags in HDesc + * @desc_hdr: packet/TR descriptor header + * @src_tag_id: Source Tag + * @dst_tag_id: Dest Tag + * + * Returns Packet Src/Dst Tags from packet/TR descriptor + */ +static inline void cppi5_desc_set_tags_ids(struct cppi5_desc_hdr_t *desc_hdr, + u32 src_tag_id, u32 dst_tag_id) +{ + desc_hdr->src_dst_tag = (src_tag_id << CPPI5_INFO3_DESC_SRCTAG_SHIFT) & + CPPI5_INFO3_DESC_SRCTAG_MASK; + desc_hdr->src_dst_tag |= dst_tag_id & CPPI5_INFO3_DESC_DSTTAG_MASK; +} + +/** + * cppi5_hdesc_calc_size - Calculate Host Packet Descriptor size + * @epib: is EPIB present + * @psdata_size: PSDATA size + * @sw_data_size: SWDATA size + * + * Returns required Host Packet Descriptor size + * 0 - if PSDATA > CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE + */ +static inline u32 cppi5_hdesc_calc_size(bool epib, u32 psdata_size, + u32 sw_data_size) +{ + u32 desc_size; + + if (psdata_size > CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE) + return 0; + + desc_size = sizeof(struct cppi5_host_desc_t) + psdata_size + + sw_data_size; + + if (epib) + desc_size += CPPI5_INFO0_HDESC_EPIB_SIZE; + + return ALIGN(desc_size, CPPI5_DESC_MIN_ALIGN); +} + +/** + * cppi5_hdesc_init - Init Host Packet Descriptor size + * @desc: Host packet descriptor + * @flags: supported values + * CPPI5_INFO0_HDESC_EPIB_PRESENT + * CPPI5_INFO0_HDESC_PSINFO_LOCATION + * @psdata_size: PSDATA size + * + * Returns required Host Packet Descriptor size + * 0 - if PSDATA > CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE + */ +static inline void cppi5_hdesc_init(struct cppi5_host_desc_t *desc, u32 flags, + u32 psdata_size) +{ + desc->hdr.pkt_info0 = (CPPI5_INFO0_DESC_TYPE_VAL_HOST << + CPPI5_INFO0_HDESC_TYPE_SHIFT) | (flags); + desc->hdr.pkt_info0 |= ((psdata_size >> 2) << + CPPI5_INFO0_HDESC_PSINFO_SIZE_SHIFT) & + CPPI5_INFO0_HDESC_PSINFO_SIZE_MASK; + desc->next_desc = 0; +} + +/** + * cppi5_hdesc_update_flags - Replace descriptor flags + * @desc: Host packet descriptor + * @flags: supported values + * CPPI5_INFO0_HDESC_EPIB_PRESENT + * CPPI5_INFO0_HDESC_PSINFO_LOCATION + */ +static inline void cppi5_hdesc_update_flags(struct cppi5_host_desc_t *desc, + u32 flags) +{ + desc->hdr.pkt_info0 &= ~(CPPI5_INFO0_HDESC_EPIB_PRESENT | + CPPI5_INFO0_HDESC_PSINFO_LOCATION); + desc->hdr.pkt_info0 |= flags; +} + +/** + * cppi5_hdesc_update_psdata_size - Replace PSdata size + * @desc: Host packet descriptor + * @psdata_size: PSDATA size + */ +static inline void +cppi5_hdesc_update_psdata_size(struct cppi5_host_desc_t *desc, u32 psdata_size) +{ + desc->hdr.pkt_info0 &= ~CPPI5_INFO0_HDESC_PSINFO_SIZE_MASK; + desc->hdr.pkt_info0 |= ((psdata_size >> 2) << + CPPI5_INFO0_HDESC_PSINFO_SIZE_SHIFT) & + CPPI5_INFO0_HDESC_PSINFO_SIZE_MASK; +} + +/** + * cppi5_hdesc_get_psdata_size - get PSdata size in bytes + * @desc: Host packet descriptor + */ +static inline u32 cppi5_hdesc_get_psdata_size(struct cppi5_host_desc_t *desc) +{ + u32 psdata_size = 0; + + if (!(desc->hdr.pkt_info0 & CPPI5_INFO0_HDESC_PSINFO_LOCATION)) + psdata_size = (desc->hdr.pkt_info0 & + CPPI5_INFO0_HDESC_PSINFO_SIZE_MASK) >> + CPPI5_INFO0_HDESC_PSINFO_SIZE_SHIFT; + + return (psdata_size << 2); +} + +/** + * cppi5_hdesc_get_pktlen - get Packet Length from HDesc + * @desc: Host packet descriptor + * + * Returns Packet Length from Host Packet Descriptor + */ +static inline u32 cppi5_hdesc_get_pktlen(struct cppi5_host_desc_t *desc) +{ + return (desc->hdr.pkt_info0 & CPPI5_INFO0_HDESC_PKTLEN_MASK); +} + +/** + * cppi5_hdesc_set_pktlen - set Packet Length in HDesc + * @desc: Host packet descriptor + */ +static inline void cppi5_hdesc_set_pktlen(struct cppi5_host_desc_t *desc, + u32 pkt_len) +{ + desc->hdr.pkt_info0 &= ~CPPI5_INFO0_HDESC_PKTLEN_MASK; + desc->hdr.pkt_info0 |= (pkt_len & CPPI5_INFO0_HDESC_PKTLEN_MASK); +} + +/** + * cppi5_hdesc_get_psflags - get Protocol Specific Flags from HDesc + * @desc: Host packet descriptor + * + * Returns Protocol Specific Flags from Host Packet Descriptor + */ +static inline u32 cppi5_hdesc_get_psflags(struct cppi5_host_desc_t *desc) +{ + return (desc->hdr.pkt_info1 & CPPI5_INFO1_HDESC_PSFLGS_MASK) >> + CPPI5_INFO1_HDESC_PSFLGS_SHIFT; +} + +/** + * cppi5_hdesc_set_psflags - set Protocol Specific Flags in HDesc + * @desc: Host packet descriptor + */ +static inline void cppi5_hdesc_set_psflags(struct cppi5_host_desc_t *desc, + u32 ps_flags) +{ + desc->hdr.pkt_info1 &= ~CPPI5_INFO1_HDESC_PSFLGS_MASK; + desc->hdr.pkt_info1 |= (ps_flags << + CPPI5_INFO1_HDESC_PSFLGS_SHIFT) & + CPPI5_INFO1_HDESC_PSFLGS_MASK; +} + +/** + * cppi5_hdesc_get_errflags - get Packet Type from HDesc + * @desc: Host packet descriptor + */ +static inline u32 cppi5_hdesc_get_pkttype(struct cppi5_host_desc_t *desc) +{ + return (desc->hdr.pkt_info2 & CPPI5_INFO2_HDESC_PKTTYPE_MASK) >> + CPPI5_INFO2_HDESC_PKTTYPE_SHIFT; +} + +/** + * cppi5_hdesc_get_errflags - set Packet Type in HDesc + * @desc: Host packet descriptor + * @pkt_type: Packet Type + */ +static inline void cppi5_hdesc_set_pkttype(struct cppi5_host_desc_t *desc, + u32 pkt_type) +{ + desc->hdr.pkt_info2 &= ~CPPI5_INFO2_HDESC_PKTTYPE_MASK; + desc->hdr.pkt_info2 |= + (pkt_type << CPPI5_INFO2_HDESC_PKTTYPE_SHIFT) & + CPPI5_INFO2_HDESC_PKTTYPE_MASK; +} + +/** + * cppi5_hdesc_attach_buf - attach buffer to HDesc + * @desc: Host packet descriptor + * @buf: Buffer physical address + * @buf_data_len: Buffer length + * @obuf: Original Buffer physical address + * @obuf_len: Original Buffer length + * + * Attaches buffer to Host Packet Descriptor + */ +static inline void cppi5_hdesc_attach_buf(struct cppi5_host_desc_t *desc, + dma_addr_t buf, u32 buf_data_len, + dma_addr_t obuf, u32 obuf_len) +{ + desc->buf_ptr = buf; + desc->buf_info1 = buf_data_len & CPPI5_BUFINFO1_HDESC_DATA_LEN_MASK; + desc->org_buf_ptr = obuf; + desc->org_buf_len = obuf_len & CPPI5_OBUFINFO0_HDESC_BUF_LEN_MASK; +} + +static inline void cppi5_hdesc_get_obuf(struct cppi5_host_desc_t *desc, + dma_addr_t *obuf, u32 *obuf_len) +{ + *obuf = desc->org_buf_ptr; + *obuf_len = desc->org_buf_len & CPPI5_OBUFINFO0_HDESC_BUF_LEN_MASK; +} + +static inline void cppi5_hdesc_reset_to_original(struct cppi5_host_desc_t *desc) +{ + desc->buf_ptr = desc->org_buf_ptr; + desc->buf_info1 = desc->org_buf_len; +} + +/** + * cppi5_hdesc_link_hbdesc - link Host Buffer Descriptor to HDesc + * @desc: Host Packet Descriptor + * @buf_desc: Host Buffer Descriptor physical address + * + * add and link Host Buffer Descriptor to HDesc + */ +static inline void cppi5_hdesc_link_hbdesc(struct cppi5_host_desc_t *desc, + dma_addr_t hbuf_desc) +{ + desc->next_desc = hbuf_desc; +} + +static inline dma_addr_t +cppi5_hdesc_get_next_hbdesc(struct cppi5_host_desc_t *desc) +{ + return (dma_addr_t)desc->next_desc; +} + +static inline void cppi5_hdesc_reset_hbdesc(struct cppi5_host_desc_t *desc) +{ + desc->hdr = (struct cppi5_desc_hdr_t) { 0 }; + desc->next_desc = 0; +} + +/** + * cppi5_hdesc_epib_present - check if EPIB present + * @desc_hdr: packet descriptor/TR header + * + * Returns true if EPIB present in the packet + */ +static inline bool cppi5_hdesc_epib_present(struct cppi5_desc_hdr_t *desc_hdr) +{ + return !!(desc_hdr->pkt_info0 & CPPI5_INFO0_HDESC_EPIB_PRESENT); +} + +/** + * cppi5_hdesc_get_psdata - Get pointer on PSDATA + * @desc: Host packet descriptor + * + * Returns pointer on PSDATA in HDesc. + * NULL - if ps_data placed at the start of data buffer. + */ +static inline void *cppi5_hdesc_get_psdata(struct cppi5_host_desc_t *desc) +{ + u32 psdata_size; + void *psdata; + + if (desc->hdr.pkt_info0 & CPPI5_INFO0_HDESC_PSINFO_LOCATION) + return NULL; + + psdata_size = (desc->hdr.pkt_info0 & + CPPI5_INFO0_HDESC_PSINFO_SIZE_MASK) >> + CPPI5_INFO0_HDESC_PSINFO_SIZE_SHIFT; + + if (!psdata_size) + return NULL; + + psdata = &desc->epib; + + if (cppi5_hdesc_epib_present(&desc->hdr)) + psdata += CPPI5_INFO0_HDESC_EPIB_SIZE; + + return psdata; +} + +/** + * cppi5_hdesc_get_swdata - Get pointer on swdata + * @desc: Host packet descriptor + * + * Returns pointer on SWDATA in HDesc. + * NOTE. It's caller responsibility to be sure hdesc actually has swdata. + */ +static inline void *cppi5_hdesc_get_swdata(struct cppi5_host_desc_t *desc) +{ + u32 psdata_size = 0; + void *swdata; + + if (!(desc->hdr.pkt_info0 & CPPI5_INFO0_HDESC_PSINFO_LOCATION)) + psdata_size = (desc->hdr.pkt_info0 & + CPPI5_INFO0_HDESC_PSINFO_SIZE_MASK) >> + CPPI5_INFO0_HDESC_PSINFO_SIZE_SHIFT; + + swdata = &desc->epib; + + if (cppi5_hdesc_epib_present(&desc->hdr)) + swdata += CPPI5_INFO0_HDESC_EPIB_SIZE; + + swdata += (psdata_size << 2); + + return swdata; +} + +/* ================================== TR ================================== */ + +#define CPPI5_TR_TYPE_SHIFT (0U) +#define CPPI5_TR_TYPE_MASK GENMASK(3, 0) +#define CPPI5_TR_STATIC BIT(4) +#define CPPI5_TR_WAIT BIT(5) +#define CPPI5_TR_EVENT_SIZE_SHIFT (6U) +#define CPPI5_TR_EVENT_SIZE_MASK GENMASK(7, 6) +#define CPPI5_TR_TRIGGER0_SHIFT (8U) +#define CPPI5_TR_TRIGGER0_MASK GENMASK(9, 8) +#define CPPI5_TR_TRIGGER0_TYPE_SHIFT (10U) +#define CPPI5_TR_TRIGGER0_TYPE_MASK GENMASK(11, 10) +#define CPPI5_TR_TRIGGER1_SHIFT (12U) +#define CPPI5_TR_TRIGGER1_MASK GENMASK(13, 12) +#define CPPI5_TR_TRIGGER1_TYPE_SHIFT (14U) +#define CPPI5_TR_TRIGGER1_TYPE_MASK GENMASK(15, 14) +#define CPPI5_TR_CMD_ID_SHIFT (16U) +#define CPPI5_TR_CMD_ID_MASK GENMASK(23, 16) +#define CPPI5_TR_CSF_FLAGS_SHIFT (24U) +#define CPPI5_TR_CSF_FLAGS_MASK GENMASK(31, 24) +#define CPPI5_TR_CSF_SA_INDIRECT BIT(0) +#define CPPI5_TR_CSF_DA_INDIRECT BIT(1) +#define CPPI5_TR_CSF_SUPR_EVT BIT(2) +#define CPPI5_TR_CSF_EOL_ADV_SHIFT (4U) +#define CPPI5_TR_CSF_EOL_ADV_MASK GENMASK(6, 4) +#define CPPI5_TR_CSF_EOP BIT(7) + +/** + * enum cppi5_tr_types - TR types + * @CPPI5_TR_TYPE0: One dimensional data move + * @CPPI5_TR_TYPE1: Two dimensional data move + * @CPPI5_TR_TYPE2: Three dimensional data move + * @CPPI5_TR_TYPE3: Four dimensional data move + * @CPPI5_TR_TYPE4: Four dimensional data move with data formatting + * @CPPI5_TR_TYPE5: Four dimensional Cache Warm + * @CPPI5_TR_TYPE8: Four Dimensional Block Move + * @CPPI5_TR_TYPE9: Four Dimensional Block Move with Repacking + * @CPPI5_TR_TYPE10: Two Dimensional Block Move + * @CPPI5_TR_TYPE11: Two Dimensional Block Move with Repacking + * @CPPI5_TR_TYPE15: Four Dimensional Block Move with Repacking and + * Indirection + */ +enum cppi5_tr_types { + CPPI5_TR_TYPE0 = 0, + CPPI5_TR_TYPE1, + CPPI5_TR_TYPE2, + CPPI5_TR_TYPE3, + CPPI5_TR_TYPE4, + CPPI5_TR_TYPE5, + /* type6-7: Reserved */ + CPPI5_TR_TYPE8 = 8, + CPPI5_TR_TYPE9, + CPPI5_TR_TYPE10, + CPPI5_TR_TYPE11, + /* type12-14: Reserved */ + CPPI5_TR_TYPE15 = 15, + CPPI5_TR_TYPE_MAX +}; + +/** + * enum cppi5_tr_event_size - TR Flags EVENT_SIZE field specifies when an event + * is generated for each TR. + * @CPPI5_TR_EVENT_SIZE_COMPLETION: When TR is complete and all status for + * the TR has been received + * @CPPI5_TR_EVENT_SIZE_ICNT1_DEC: Type 0: when the last data transaction + * is sent for the TR + * Type 1-11: when ICNT1 is decremented + * @CPPI5_TR_EVENT_SIZE_ICNT2_DEC: Type 0-1,10-11: when the last data + * transaction is sent for the TR + * All other types: when ICNT2 is + * decremented + * @CPPI5_TR_EVENT_SIZE_ICNT3_DEC: Type 0-2,10-11: when the last data + * transaction is sent for the TR + * All other types: when ICNT3 is + * decremented + */ +enum cppi5_tr_event_size { + CPPI5_TR_EVENT_SIZE_COMPLETION, + CPPI5_TR_EVENT_SIZE_ICNT1_DEC, + CPPI5_TR_EVENT_SIZE_ICNT2_DEC, + CPPI5_TR_EVENT_SIZE_ICNT3_DEC, + CPPI5_TR_EVENT_SIZE_MAX +}; + +/** + * enum cppi5_tr_trigger - TR Flags TRIGGERx field specifies the type of trigger + * used to enable the TR to transfer data as specified + * by TRIGGERx_TYPE field. + * @CPPI5_TR_TRIGGER_NONE: No trigger + * @CPPI5_TR_TRIGGER_GLOBAL0: Global trigger 0 + * @CPPI5_TR_TRIGGER_GLOBAL1: Global trigger 1 + * @CPPI5_TR_TRIGGER_LOCAL_EVENT: Local Event + */ +enum cppi5_tr_trigger { + CPPI5_TR_TRIGGER_NONE, + CPPI5_TR_TRIGGER_GLOBAL0, + CPPI5_TR_TRIGGER_GLOBAL1, + CPPI5_TR_TRIGGER_LOCAL_EVENT, + CPPI5_TR_TRIGGER_MAX +}; + +/** + * enum cppi5_tr_trigger_type - TR Flags TRIGGERx_TYPE field specifies the type + * of data transfer that will be enabled by + * receiving a trigger as specified by TRIGGERx. + * @CPPI5_TR_TRIGGER_TYPE_ICNT1_DEC: The second inner most loop (ICNT1) will + * be decremented by 1 + * @CPPI5_TR_TRIGGER_TYPE_ICNT2_DEC: The third inner most loop (ICNT2) will + * be decremented by 1 + * @CPPI5_TR_TRIGGER_TYPE_ICNT3_DEC: The outer most loop (ICNT3) will be + * decremented by 1 + * @CPPI5_TR_TRIGGER_TYPE_ALL: The entire TR will be allowed to + * complete + */ +enum cppi5_tr_trigger_type { + CPPI5_TR_TRIGGER_TYPE_ICNT1_DEC, + CPPI5_TR_TRIGGER_TYPE_ICNT2_DEC, + CPPI5_TR_TRIGGER_TYPE_ICNT3_DEC, + CPPI5_TR_TRIGGER_TYPE_ALL, + CPPI5_TR_TRIGGER_TYPE_MAX +}; + +typedef u32 cppi5_tr_flags_t; + +/** + * struct cppi5_tr_type0_t - Type 0 (One dimensional data move) TR (16 byte) + * @flags: TR flags (type, triggers, event, configuration) + * @icnt0: Total loop iteration count for level 0 (innermost) + * @_reserved: Not used + * @addr: Starting address for the source data or destination data + */ +struct cppi5_tr_type0_t { + cppi5_tr_flags_t flags; + u16 icnt0; + u16 _reserved; + u64 addr; +} __aligned(16) __packed; + +/** + * struct cppi5_tr_type1_t - Type 1 (Two dimensional data move) TR (32 byte) + * @flags: TR flags (type, triggers, event, configuration) + * @icnt0: Total loop iteration count for level 0 (innermost) + * @icnt1: Total loop iteration count for level 1 + * @addr: Starting address for the source data or destination data + * @dim1: Signed dimension for loop level 1 + */ +struct cppi5_tr_type1_t { + cppi5_tr_flags_t flags; + u16 icnt0; + u16 icnt1; + u64 addr; + s32 dim1; +} __aligned(32) __packed; + +/** + * struct cppi5_tr_type2_t - Type 2 (Three dimensional data move) TR (32 byte) + * @flags: TR flags (type, triggers, event, configuration) + * @icnt0: Total loop iteration count for level 0 (innermost) + * @icnt1: Total loop iteration count for level 1 + * @addr: Starting address for the source data or destination data + * @dim1: Signed dimension for loop level 1 + * @icnt2: Total loop iteration count for level 2 + * @_reserved: Not used + * @dim2: Signed dimension for loop level 2 + */ +struct cppi5_tr_type2_t { + cppi5_tr_flags_t flags; + u16 icnt0; + u16 icnt1; + u64 addr; + s32 dim1; + u16 icnt2; + u16 _reserved; + s32 dim2; +} __aligned(32) __packed; + +/** + * struct cppi5_tr_type3_t - Type 3 (Four dimensional data move) TR (32 byte) + * @flags: TR flags (type, triggers, event, configuration) + * @icnt0: Total loop iteration count for level 0 (innermost) + * @icnt1: Total loop iteration count for level 1 + * @addr: Starting address for the source data or destination data + * @dim1: Signed dimension for loop level 1 + * @icnt2: Total loop iteration count for level 2 + * @icnt3: Total loop iteration count for level 3 (outermost) + * @dim2: Signed dimension for loop level 2 + * @dim3: Signed dimension for loop level 3 + */ +struct cppi5_tr_type3_t { + cppi5_tr_flags_t flags; + u16 icnt0; + u16 icnt1; + u64 addr; + s32 dim1; + u16 icnt2; + u16 icnt3; + s32 dim2; + s32 dim3; +} __aligned(32) __packed; + +/** + * struct cppi5_tr_type15_t - Type 15 (Four Dimensional Block Copy with + * Repacking and Indirection Support) TR (64 byte) + * @flags: TR flags (type, triggers, event, configuration) + * @icnt0: Total loop iteration count for level 0 (innermost) for + * source + * @icnt1: Total loop iteration count for level 1 for source + * @addr: Starting address for the source data + * @dim1: Signed dimension for loop level 1 for source + * @icnt2: Total loop iteration count for level 2 for source + * @icnt3: Total loop iteration count for level 3 (outermost) for + * source + * @dim2: Signed dimension for loop level 2 for source + * @dim3: Signed dimension for loop level 3 for source + * @_reserved: Not used + * @ddim1: Signed dimension for loop level 1 for destination + * @daddr: Starting address for the destination data + * @ddim2: Signed dimension for loop level 2 for destination + * @ddim3: Signed dimension for loop level 3 for destination + * @dicnt0: Total loop iteration count for level 0 (innermost) for + * destination + * @dicnt1: Total loop iteration count for level 1 for destination + * @dicnt2: Total loop iteration count for level 2 for destination + * @sicnt3: Total loop iteration count for level 3 (outermost) for + * destination + */ +struct cppi5_tr_type15_t { + cppi5_tr_flags_t flags; + u16 icnt0; + u16 icnt1; + u64 addr; + s32 dim1; + u16 icnt2; + u16 icnt3; + s32 dim2; + s32 dim3; + u32 _reserved; + s32 ddim1; + u64 daddr; + s32 ddim2; + s32 ddim3; + u16 dicnt0; + u16 dicnt1; + u16 dicnt2; + u16 dicnt3; +} __aligned(64) __packed; + +/** + * struct cppi5_tr_resp_t - TR response record + * @status: Status type and info + * @_reserved: Not used + * @cmd_id: Command ID for the TR for TR identification + * @flags: Configuration Specific Flags + */ +struct cppi5_tr_resp_t { + u8 status; + u8 _reserved; + u8 cmd_id; + u8 flags; +} __packed; + +#define CPPI5_TR_RESPONSE_STATUS_TYPE_SHIFT (0U) +#define CPPI5_TR_RESPONSE_STATUS_TYPE_MASK GENMASK(3, 0) +#define CPPI5_TR_RESPONSE_STATUS_INFO_SHIFT (4U) +#define CPPI5_TR_RESPONSE_STATUS_INFO_MASK GENMASK(7, 4) +#define CPPI5_TR_RESPONSE_CMDID_SHIFT (16U) +#define CPPI5_TR_RESPONSE_CMDID_MASK GENMASK(23, 16) +#define CPPI5_TR_RESPONSE_CFG_SPECIFIC_SHIFT (24U) +#define CPPI5_TR_RESPONSE_CFG_SPECIFIC_MASK GENMASK(31, 24) + +/** + * enum cppi5_tr_resp_status_type - TR Response Status Type field is used to + * determine what type of status is being + * returned. + * @CPPI5_TR_RESPONSE_STATUS_NONE: No error, completion: completed + * @CPPI5_TR_RESPONSE_STATUS_TRANSFER_ERR: Transfer Error, completion: none + * or partially completed + * @CPPI5_TR_RESPONSE_STATUS_ABORTED_ERR: Aborted Error, completion: none + * or partially completed + * @CPPI5_TR_RESPONSE_STATUS_SUBMISSION_ERR: Submission Error, completion: + * none + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_ERR: Unsupported Error, completion: + * none + * @CPPI5_TR_RESPONSE_STATUS_TRANSFER_EXCEPTION: Transfer Exception, completion: + * partially completed + * @CPPI5_TR_RESPONSE_STATUS__TEARDOWN_FLUSH: Teardown Flush, completion: none + */ +enum cppi5_tr_resp_status_type { + CPPI5_TR_RESPONSE_STATUS_NONE, + CPPI5_TR_RESPONSE_STATUS_TRANSFER_ERR, + CPPI5_TR_RESPONSE_STATUS_ABORTED_ERR, + CPPI5_TR_RESPONSE_STATUS_SUBMISSION_ERR, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_ERR, + CPPI5_TR_RESPONSE_STATUS_TRANSFER_EXCEPTION, + CPPI5_TR_RESPONSE_STATUS__TEARDOWN_FLUSH, + CPPI5_TR_RESPONSE_STATUS_MAX +}; + +/** + * enum cppi5_tr_resp_status_submission - TR Response Status field values which + * corresponds Submission Error + * @CPPI5_TR_RESPONSE_STATUS_SUBMISSION_ICNT0: ICNT0 was 0 + * @CPPI5_TR_RESPONSE_STATUS_SUBMISSION_FIFO_FULL: Channel FIFO was full when TR + * received + * @CPPI5_TR_RESPONSE_STATUS_SUBMISSION_OWN: Channel is not owned by the + * submitter + */ +enum cppi5_tr_resp_status_submission { + CPPI5_TR_RESPONSE_STATUS_SUBMISSION_ICNT0, + CPPI5_TR_RESPONSE_STATUS_SUBMISSION_FIFO_FULL, + CPPI5_TR_RESPONSE_STATUS_SUBMISSION_OWN, + CPPI5_TR_RESPONSE_STATUS_SUBMISSION_MAX +}; + +/** + * enum cppi5_tr_resp_status_unsupported - TR Response Status field values which + * corresponds Unsupported Error + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_TR_TYPE: TR Type not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_STATIC: STATIC not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_EOL: EOL not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_CFG_SPECIFIC: CONFIGURATION SPECIFIC + * not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_AMODE: AMODE not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_ELTYPE: ELTYPE not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_DFMT: DFMT not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_SECTR: SECTR not supported + * @CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_AMODE_SPECIFIC: AMODE SPECIFIC field + * not supported + */ +enum cppi5_tr_resp_status_unsupported { + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_TR_TYPE, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_STATIC, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_EOL, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_CFG_SPECIFIC, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_AMODE, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_ELTYPE, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_DFMT, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_SECTR, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_AMODE_SPECIFIC, + CPPI5_TR_RESPONSE_STATUS_UNSUPPORTED_MAX +}; + +/** + * cppi5_trdesc_calc_size - Calculate TR Descriptor size + * @tr_count: number of TR records + * @tr_size: Nominal size of TR record (max) [16, 32, 64, 128] + * + * Returns required TR Descriptor size + */ +static inline size_t cppi5_trdesc_calc_size(u32 tr_count, u32 tr_size) +{ + /* + * The Size of a TR descriptor is: + * 1 x tr_size : the first 16 bytes is used by the packet info block + + * tr_count x tr_size : Transfer Request Records + + * tr_count x sizeof(struct cppi5_tr_resp_t) : Transfer Response Records + */ + return tr_size * (tr_count + 1) + + sizeof(struct cppi5_tr_resp_t) * tr_count; +} + +/** + * cppi5_trdesc_init - Init TR Descriptor + * @desc: TR Descriptor + * @tr_count: number of TR records + * @tr_size: Nominal size of TR record (max) [16, 32, 64, 128] + * @reload_idx: Absolute index to jump to on the 2nd and following passes + * through the TR packet. + * @reload_count: Number of times to jump from last entry to reload_idx. 0x1ff + * indicates infinite looping. + * + * Init TR Descriptor + */ +static inline void cppi5_trdesc_init(struct cppi5_desc_hdr_t *desc_hdr, + u32 tr_count, u32 tr_size, u32 reload_idx, + u32 reload_count) +{ + desc_hdr->pkt_info0 = CPPI5_INFO0_DESC_TYPE_VAL_TR << + CPPI5_INFO0_HDESC_TYPE_SHIFT; + desc_hdr->pkt_info0 |= + (reload_count << CPPI5_INFO0_TRDESC_RLDCNT_SHIFT) & + CPPI5_INFO0_TRDESC_RLDCNT_MASK; + desc_hdr->pkt_info0 |= + (reload_idx << CPPI5_INFO0_TRDESC_RLDIDX_SHIFT) & + CPPI5_INFO0_TRDESC_RLDIDX_MASK; + desc_hdr->pkt_info0 |= (tr_count - 1) & CPPI5_INFO0_TRDESC_LASTIDX_MASK; + + desc_hdr->pkt_info1 |= ((ffs(tr_size >> 4) - 1) << + CPPI5_INFO1_TRDESC_RECSIZE_SHIFT) & + CPPI5_INFO1_TRDESC_RECSIZE_MASK; +} + +/** + * cppi5_tr_init - Init TR record + * @flags: Pointer to the TR's flags + * @type: TR type + * @static_tr: TR is static + * @wait: Wait for TR completion before allow the next TR to start + * @event_size: output event generation cfg + * @cmd_id: TR identifier (application specifics) + * + * Init TR record + */ +static inline void cppi5_tr_init(cppi5_tr_flags_t *flags, + enum cppi5_tr_types type, bool static_tr, + bool wait, enum cppi5_tr_event_size event_size, + u32 cmd_id) +{ + *flags = type; + *flags |= (event_size << CPPI5_TR_EVENT_SIZE_SHIFT) & + CPPI5_TR_EVENT_SIZE_MASK; + + *flags |= (cmd_id << CPPI5_TR_CMD_ID_SHIFT) & + CPPI5_TR_CMD_ID_MASK; + + if (static_tr && (type == CPPI5_TR_TYPE8 || type == CPPI5_TR_TYPE9)) + *flags |= CPPI5_TR_STATIC; + + if (wait) + *flags |= CPPI5_TR_WAIT; +} + +/** + * cppi5_tr_set_trigger - Configure trigger0/1 and trigger0/1_type + * @flags: Pointer to the TR's flags + * @trigger0: trigger0 selection + * @trigger0_type: type of data transfer that will be enabled by trigger0 + * @trigger1: trigger1 selection + * @trigger1_type: type of data transfer that will be enabled by trigger1 + * + * Configure the triggers for the TR + */ +static inline void cppi5_tr_set_trigger(cppi5_tr_flags_t *flags, + enum cppi5_tr_trigger trigger0, + enum cppi5_tr_trigger_type trigger0_type, + enum cppi5_tr_trigger trigger1, + enum cppi5_tr_trigger_type trigger1_type) +{ + *flags &= ~(CPPI5_TR_TRIGGER0_MASK | CPPI5_TR_TRIGGER0_TYPE_MASK | + CPPI5_TR_TRIGGER1_MASK | CPPI5_TR_TRIGGER1_TYPE_MASK); + *flags |= (trigger0 << CPPI5_TR_TRIGGER0_SHIFT) & + CPPI5_TR_TRIGGER0_MASK; + *flags |= (trigger0_type << CPPI5_TR_TRIGGER0_TYPE_SHIFT) & + CPPI5_TR_TRIGGER0_TYPE_MASK; + + *flags |= (trigger1 << CPPI5_TR_TRIGGER1_SHIFT) & + CPPI5_TR_TRIGGER1_MASK; + *flags |= (trigger1_type << CPPI5_TR_TRIGGER1_TYPE_SHIFT) & + CPPI5_TR_TRIGGER1_TYPE_MASK; +} + +/** + * cppi5_tr_cflag_set - Update the Configuration specific flags + * @flags: Pointer to the TR's flags + * @csf: Configuration specific flags + * + * Set a bit in Configuration Specific Flags section of the TR flags. + */ +static inline void cppi5_tr_csf_set(cppi5_tr_flags_t *flags, u32 csf) +{ + *flags &= ~CPPI5_TR_CSF_FLAGS_MASK; + *flags |= (csf << CPPI5_TR_CSF_FLAGS_SHIFT) & + CPPI5_TR_CSF_FLAGS_MASK; +} + +#endif /* __TI_CPPI5_H__ */ -- cgit v1.2.3 From 8c6bb62f6b4a24c446511e8f894251946dcc2ef1 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 23 Dec 2019 13:04:48 +0200 Subject: dmaengine: ti: k3 PSI-L remote endpoint configuration In K3 architecture the DMA operates within threads. One end of the thread is UDMAP, the other is on the peripheral side. The UDMAP channel configuration depends on the needs of the remote endpoint and it can be differ from peripheral to peripheral. This patch adds database for am654 and j721e and small API to fetch the PSI-L endpoint configuration from the database which should only used by the DMA driver(s). Another API is added for native peripherals to give possibility to pass new configuration for the threads they are using, which is needed to be able to handle changes caused by different firmware loaded for the peripheral for example. Signed-off-by: Peter Ujfalusi Tested-by: Keerthy Reviewed-by: Grygorii Strashko Link: https://lore.kernel.org/r/20191223110458.30766-9-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dma/k3-psil.h | 71 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 include/linux/dma/k3-psil.h (limited to 'include/linux') diff --git a/include/linux/dma/k3-psil.h b/include/linux/dma/k3-psil.h new file mode 100644 index 000000000000..61d5cc0ad601 --- /dev/null +++ b/include/linux/dma/k3-psil.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + */ + +#ifndef K3_PSIL_H_ +#define K3_PSIL_H_ + +#include + +#define K3_PSIL_DST_THREAD_ID_OFFSET 0x8000 + +struct device; + +/** + * enum udma_tp_level - Channel Throughput Levels + * @UDMA_TP_NORMAL: Normal channel + * @UDMA_TP_HIGH: High Throughput channel + * @UDMA_TP_ULTRAHIGH: Ultra High Throughput channel + */ +enum udma_tp_level { + UDMA_TP_NORMAL = 0, + UDMA_TP_HIGH, + UDMA_TP_ULTRAHIGH, + UDMA_TP_LAST, +}; + +/** + * enum psil_endpoint_type - PSI-L Endpoint type + * @PSIL_EP_NATIVE: Normal channel + * @PSIL_EP_PDMA_XY: XY mode PDMA + * @PSIL_EP_PDMA_MCAN: MCAN mode PDMA + * @PSIL_EP_PDMA_AASRC: AASRC mode PDMA + */ +enum psil_endpoint_type { + PSIL_EP_NATIVE = 0, + PSIL_EP_PDMA_XY, + PSIL_EP_PDMA_MCAN, + PSIL_EP_PDMA_AASRC, +}; + +/** + * struct psil_endpoint_config - PSI-L Endpoint configuration + * @ep_type: PSI-L endpoint type + * @pkt_mode: If set, the channel must be in Packet mode, otherwise in + * TR mode + * @notdpkt: TDCM must be suppressed on the TX channel + * @needs_epib: Endpoint needs EPIB + * @psd_size: If set, PSdata is used by the endpoint + * @channel_tpl: Desired throughput level for the channel + * @pdma_acc32: ACC32 must be enabled on the PDMA side + * @pdma_burst: BURST must be enabled on the PDMA side + */ +struct psil_endpoint_config { + enum psil_endpoint_type ep_type; + + unsigned pkt_mode:1; + unsigned notdpkt:1; + unsigned needs_epib:1; + u32 psd_size; + enum udma_tp_level channel_tpl; + + /* PDMA properties, valid for PSIL_EP_PDMA_* */ + unsigned pdma_acc32:1; + unsigned pdma_burst:1; +}; + +int psil_set_new_ep_config(struct device *dev, const char *name, + struct psil_endpoint_config *ep_config); + +#endif /* K3_PSIL_H_ */ -- cgit v1.2.3 From d702419134133db1eab2067dc6ea5723467fd917 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Mon, 23 Dec 2019 13:04:51 +0200 Subject: dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko Signed-off-by: Peter Ujfalusi Tested-by: Keerthy Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul --- include/linux/dma/k3-udma-glue.h | 134 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 134 insertions(+) create mode 100644 include/linux/dma/k3-udma-glue.h (limited to 'include/linux') diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h new file mode 100644 index 000000000000..caadbab1632a --- /dev/null +++ b/include/linux/dma/k3-udma-glue.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + */ + +#ifndef K3_UDMA_GLUE_H_ +#define K3_UDMA_GLUE_H_ + +#include +#include +#include + +struct k3_udma_glue_tx_channel_cfg { + struct k3_ring_cfg tx_cfg; + struct k3_ring_cfg txcq_cfg; + + bool tx_pause_on_err; + bool tx_filt_einfo; + bool tx_filt_pswords; + bool tx_supr_tdpkt; + u32 swdata_size; +}; + +struct k3_udma_glue_tx_channel; + +struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev, + const char *name, struct k3_udma_glue_tx_channel_cfg *cfg); + +void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn); +int k3_udma_glue_push_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + struct cppi5_host_desc_t *desc_tx, + dma_addr_t desc_dma); +int k3_udma_glue_pop_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + dma_addr_t *desc_dma); +int k3_udma_glue_enable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn); +void k3_udma_glue_disable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn); +void k3_udma_glue_tdown_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + bool sync); +void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + void *data, void (*cleanup)(void *data, dma_addr_t desc_dma)); +u32 k3_udma_glue_tx_get_hdesc_size(struct k3_udma_glue_tx_channel *tx_chn); +u32 k3_udma_glue_tx_get_txcq_id(struct k3_udma_glue_tx_channel *tx_chn); +int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn); + +enum { + K3_UDMA_GLUE_SRC_TAG_LO_KEEP = 0, + K3_UDMA_GLUE_SRC_TAG_LO_USE_FLOW_REG = 1, + K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_FLOW_ID = 2, + K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_SRC_TAG = 4, +}; + +/** + * k3_udma_glue_rx_flow_cfg - UDMA RX flow cfg + * + * @rx_cfg: RX ring configuration + * @rxfdq_cfg: RX free Host PD ring configuration + * @ring_rxq_id: RX ring id (or -1 for any) + * @ring_rxfdq0_id: RX free Host PD ring (FDQ) if (or -1 for any) + * @rx_error_handling: Rx Error Handling Mode (0 - drop, 1 - re-try) + * @src_tag_lo_sel: Rx Source Tag Low Byte Selector in Host PD + */ +struct k3_udma_glue_rx_flow_cfg { + struct k3_ring_cfg rx_cfg; + struct k3_ring_cfg rxfdq_cfg; + int ring_rxq_id; + int ring_rxfdq0_id; + bool rx_error_handling; + int src_tag_lo_sel; +}; + +/** + * k3_udma_glue_rx_channel_cfg - UDMA RX channel cfg + * + * @psdata_size: SW Data is present in Host PD of @swdata_size bytes + * @flow_id_base: first flow_id used by channel. + * if @flow_id_base = -1 - range of GP rflows will be + * allocated dynamically. + * @flow_id_num: number of RX flows used by channel + * @flow_id_use_rxchan_id: use RX channel id as flow id, + * used only if @flow_id_num = 1 + * @remote indication that RX channel is remote - some remote CPU + * core owns and control the RX channel. Linux Host only + * allowed to attach and configure RX Flow within RX + * channel. if set - not RX channel operation will be + * performed by K3 NAVSS DMA glue interface. + * @def_flow_cfg default RX flow configuration, + * used only if @flow_id_num = 1 + */ +struct k3_udma_glue_rx_channel_cfg { + u32 swdata_size; + int flow_id_base; + int flow_id_num; + bool flow_id_use_rxchan_id; + bool remote; + + struct k3_udma_glue_rx_flow_cfg *def_flow_cfg; +}; + +struct k3_udma_glue_rx_channel; + +struct k3_udma_glue_rx_channel *k3_udma_glue_request_rx_chn( + struct device *dev, + const char *name, + struct k3_udma_glue_rx_channel_cfg *cfg); + +void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn); +int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn); +void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn); +void k3_udma_glue_tdown_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + bool sync); +int k3_udma_glue_push_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num, struct cppi5_host_desc_t *desc_tx, + dma_addr_t desc_dma); +int k3_udma_glue_pop_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num, dma_addr_t *desc_dma); +int k3_udma_glue_rx_flow_init(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx, struct k3_udma_glue_rx_flow_cfg *flow_cfg); +u32 k3_udma_glue_rx_flow_get_fdq_id(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx); +u32 k3_udma_glue_rx_get_flow_id_base(struct k3_udma_glue_rx_channel *rx_chn); +int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num); +void k3_udma_glue_rx_put_irq(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num); +void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num, void *data, + void (*cleanup)(void *data, dma_addr_t desc_dma), + bool skip_fdq); +int k3_udma_glue_rx_flow_enable(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx); +int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx); + +#endif /* K3_UDMA_GLUE_H_ */ -- cgit v1.2.3 From 71ca5b78235e79c36f774773491064d7921d1942 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 21 Jan 2020 10:33:10 +0100 Subject: dmaengine: Remove dma_request_slave_channel_compat() wrapper At its original introduction, dma_request_slave_channel_compat() used a wrapper, to accommodate filter functions that modify the mask passed. Filter functions can no longer modify masks, and the mask parameter was made const in commit a53e28da574a40bc ("dma: Make the 'mask' parameter of __dma_request_channel const") consecutively. Hence remove the wrapper, and rename __dma_request_slave_channel_compat() to dma_request_slave_channel_compat(), to get rid of one more function name starting with a double underscore. Signed-off-by: Geert Uytterhoeven Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200121093311.28639-3-geert+renesas@glider.be Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 62225d46908b..230d50ef7360 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1526,11 +1526,9 @@ struct dma_chan *dma_get_slave_channel(struct dma_chan *chan); struct dma_chan *dma_get_any_slave_channel(struct dma_device *device); #define dma_request_channel(mask, x, y) \ __dma_request_channel(&(mask), x, y, NULL) -#define dma_request_slave_channel_compat(mask, x, y, dev, name) \ - __dma_request_slave_channel_compat(&(mask), x, y, dev, name) static inline struct dma_chan -*__dma_request_slave_channel_compat(const dma_cap_mask_t *mask, +*dma_request_slave_channel_compat(const dma_cap_mask_t mask, dma_filter_fn fn, void *fn_param, struct device *dev, const char *name) { @@ -1543,7 +1541,7 @@ static inline struct dma_chan if (!fn || !fn_param) return NULL; - return __dma_request_channel(mask, fn, fn_param, NULL); + return __dma_request_channel(&mask, fn, fn_param, NULL); } static inline char * -- cgit v1.2.3 From c3c431de99c068e3f64d01335c1532b22e4b1d1b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 21 Jan 2020 10:33:11 +0100 Subject: dmaengine: Move dma_get_{,any_}slave_channel() to private dmaengine.h The functions dma_get_slave_channel() and dma_get_any_slave_channel() are called from DMA engine drivers only. Hence move their declarations from the public header file to the private header file drivers/dma/dmaengine.h. Signed-off-by: Geert Uytterhoeven Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200121093311.28639-4-geert+renesas@glider.be Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 230d50ef7360..9cc0e70e7c35 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1522,8 +1522,6 @@ int dma_async_device_register(struct dma_device *device); int dmaenginem_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); -struct dma_chan *dma_get_slave_channel(struct dma_chan *chan); -struct dma_chan *dma_get_any_slave_channel(struct dma_device *device); #define dma_request_channel(mask, x, y) \ __dma_request_channel(&(mask), x, y, NULL) -- cgit v1.2.3 From 3231e5d2228a2078ce5982d63ea9a617e4972c00 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 20 Jan 2020 22:16:07 +0100 Subject: net: phy: rename phy_do_ioctl to phy_do_ioctl_running We just added phy_do_ioctl, but it turned out that we need another version of this function that doesn't check whether net_device is running. So rename phy_do_ioctl to phy_do_ioctl_running. Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index be6b3a1b03da..f6e714da37d8 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1242,7 +1242,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); -int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -- cgit v1.2.3 From bbbf8430afe6906abbf879352fe10d24d380e588 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 20 Jan 2020 22:17:11 +0100 Subject: net: phy: add new version of phy_do_ioctl Add a new version of phy_do_ioctl that doesn't check whether net_device is running. It will typically be used if suitable drivers attach the PHY in probe already. Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index f6e714da37d8..c570e162e05e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1242,6 +1242,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); +int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); -- cgit v1.2.3 From 9167bd96346473de5b61124f4589949fdf3026cf Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Wed, 15 Jan 2020 11:07:50 -0500 Subject: sparc/console: kill off obsolete declarations commit 09d3f3f0e02c ("sparc: Kill PROM console driver.") missed removing the declarations of the deleted prom_con structure and prom_con_init function from console.h. Kill them off now. Signed-off-by: Arvind Sankar Signed-off-by: David S. Miller --- include/linux/console.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index d09951d5a94e..f33016b3a401 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -101,7 +101,6 @@ extern const struct consw *conswitchp; extern const struct consw dummy_con; /* dummy console buffer */ extern const struct consw vga_con; /* VGA text console */ extern const struct consw newport_con; /* SGI Newport console */ -extern const struct consw prom_con; /* SPARC PROM console */ int con_is_bound(const struct consw *csw); int do_unregister_con_driver(const struct consw *csw); @@ -201,7 +200,6 @@ extern void suspend_console(void); extern void resume_console(void); int mda_console_init(void); -void prom_con_init(void); void vcs_make_sysfs(int index); void vcs_remove_sysfs(int index); -- cgit v1.2.3 From 09cbcef6c60e77af11c3f27e62ea3f291a5d436c Mon Sep 17 00:00:00 2001 From: Milan Pandurov Date: Fri, 13 Dec 2019 14:07:21 +0100 Subject: kvm: Refactor handling of VM debugfs files We can store reference to kvm_stats_debugfs_item instead of copying its values to kvm_stat_data. This allows us to remove duplicated code and usage of temporary kvm_stat_data inside vm_stat_get et al. Signed-off-by: Milan Pandurov Reviewed-by: Alexander Graf Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 528ab7a814ab..5e2ec7e295db 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1108,9 +1108,8 @@ enum kvm_stat_kind { }; struct kvm_stat_data { - int offset; - int mode; struct kvm *kvm; + struct kvm_stats_debugfs_item *dbgfs_item; }; struct kvm_stats_debugfs_item { @@ -1119,6 +1118,10 @@ struct kvm_stats_debugfs_item { enum kvm_stat_kind kind; int mode; }; + +#define KVM_DBGFS_GET_MODE(dbgfs_item) \ + ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; -- cgit v1.2.3 From b46f36c05ab40d8339ec08809f89e45b1817cf86 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 15 Jan 2020 12:53:53 +0000 Subject: crypto: atmel-{aes,sha,tdes} - Retire crypto_platform_data These drivers no longer need it as they are only probed via DT. crypto_platform_data was allocated but unused, so remove it. This is a follow up for: commit 45a536e3a7e0 ("crypto: atmel-tdes - Retire dma_request_slave_channel_compat()") commit db28512f48e2 ("crypto: atmel-sha - Retire dma_request_slave_channel_compat()") commit 62f72cbdcf02 ("crypto: atmel-aes - Retire dma_request_slave_channel_compat()") Signed-off-by: Tudor Ambarus Signed-off-by: Herbert Xu --- include/linux/platform_data/crypto-atmel.h | 23 ----------------------- 1 file changed, 23 deletions(-) delete mode 100644 include/linux/platform_data/crypto-atmel.h (limited to 'include/linux') diff --git a/include/linux/platform_data/crypto-atmel.h b/include/linux/platform_data/crypto-atmel.h deleted file mode 100644 index 0471aaf6999b..000000000000 --- a/include/linux/platform_data/crypto-atmel.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_CRYPTO_ATMEL_H -#define __LINUX_CRYPTO_ATMEL_H - -#include - -/** - * struct crypto_dma_data - DMA data for AES/TDES/SHA - */ -struct crypto_dma_data { - struct at_dma_slave txdata; - struct at_dma_slave rxdata; -}; - -/** - * struct crypto_platform_data - board-specific AES/TDES/SHA configuration - * @dma_slave: DMA slave interface to use in data transfers. - */ -struct crypto_platform_data { - struct crypto_dma_data *dma_slave; -}; - -#endif /* __LINUX_CRYPTO_ATMEL_H */ -- cgit v1.2.3 From b25319d279b63781b972c4966b4082193e69afac Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:24 +0000 Subject: irqchip/gic-v3: Detect GICv4.1 supporting RVPEID GICv4.1 supports the RVPEID ("Residency per vPE ID"), which allows for a much efficient way of making virtual CPUs resident (to allow direct injection of interrupts). The functionnality needs to be discovered on each and every redistributor in the system, and disabled if the settings are inconsistent. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-2-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index de991d6633a5..9a5f85d30701 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -234,6 +234,7 @@ #define GICR_TYPER_VLPIS (1U << 1) #define GICR_TYPER_DirectLPIS (1U << 3) #define GICR_TYPER_LAST (1U << 4) +#define GICR_TYPER_RVPEID (1U << 7) #define GIC_V3_REDIST_SIZE 0x20000 @@ -615,6 +616,7 @@ struct rdists { u64 flags; u32 gicd_typer; bool has_vlpis; + bool has_rvpeid; bool has_direct_lpi; }; -- cgit v1.2.3 From f2d834092ee276610ccb6637e5109b61fc79ab89 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:25 +0000 Subject: irqchip/gic-v3: Add GICv4.1 VPEID size discovery While GICv4.0 mandates 16 bit worth of VPEIDs, GICv4.1 allows smaller implementations to be built. Add the required glue to dynamically compute the limit. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-3-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 9a5f85d30701..9dfe64189d99 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -13,6 +13,7 @@ #define GICD_CTLR 0x0000 #define GICD_TYPER 0x0004 #define GICD_IIDR 0x0008 +#define GICD_TYPER2 0x000C #define GICD_STATUSR 0x0010 #define GICD_SETSPI_NSR 0x0040 #define GICD_CLRSPI_NSR 0x0048 @@ -89,6 +90,9 @@ #define GICD_TYPER_ESPIS(typer) \ (((typer) & GICD_TYPER_ESPI) ? GICD_TYPER_SPIS((typer) >> 27) : 0) +#define GICD_TYPER2_VIL (1U << 7) +#define GICD_TYPER2_VID GENMASK(4, 0) + #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) #define GICD_IROUTER_SPI_MODE_ANY (1U << 31) @@ -615,6 +619,7 @@ struct rdists { void *prop_table_va; u64 flags; u32 gicd_typer; + u32 gicd_typer2; bool has_vlpis; bool has_rvpeid; bool has_direct_lpi; -- cgit v1.2.3 From 5e5168461c22c8738d31d4ee12a5cbc2ab0aa440 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:28 +0000 Subject: irqchip/gic-v4.1: VPE table (aka GICR_VPROPBASER) allocation GICv4.1 defines a new VPE table that is potentially shared between both the ITSs and the redistributors, following complicated affinity rules. To make things more confusing, the programming of this table at the redistributor level is reusing the GICv4.0 GICR_VPROPBASER register for something completely different. The code flow is somewhat complexified by the need to respect the affinities required by the HW, meaning that tables can either be inherited from a previously discovered ITS or redistributor. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-6-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 9dfe64189d99..db0a11193d92 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -102,6 +102,11 @@ #define GIC_V3_DIST_SIZE 0x10000 +#define GIC_PAGE_SIZE_4K 0ULL +#define GIC_PAGE_SIZE_16K 1ULL +#define GIC_PAGE_SIZE_64K 2ULL +#define GIC_PAGE_SIZE_MASK 3ULL + /* * Re-Distributor registers, offsets from RD_base */ @@ -239,6 +244,8 @@ #define GICR_TYPER_DirectLPIS (1U << 3) #define GICR_TYPER_LAST (1U << 4) #define GICR_TYPER_RVPEID (1U << 7) +#define GICR_TYPER_COMMON_LPI_AFF GENMASK_ULL(25, 24) +#define GICR_TYPER_AFFINITY GENMASK_ULL(63, 32) #define GIC_V3_REDIST_SIZE 0x20000 @@ -277,6 +284,18 @@ #define GICR_VPROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt) #define GICR_VPROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb) +/* + * GICv4.1 VPROPBASER reinvention. A subtle mix between the old + * VPROPBASER and ITS_BASER. Just not quite any of the two. + */ +#define GICR_VPROPBASER_4_1_VALID (1ULL << 63) +#define GICR_VPROPBASER_4_1_ENTRY_SIZE GENMASK_ULL(61, 59) +#define GICR_VPROPBASER_4_1_INDIRECT (1ULL << 55) +#define GICR_VPROPBASER_4_1_PAGE_SIZE GENMASK_ULL(54, 53) +#define GICR_VPROPBASER_4_1_Z (1ULL << 52) +#define GICR_VPROPBASER_4_1_ADDR GENMASK_ULL(51, 12) +#define GICR_VPROPBASER_4_1_SIZE GENMASK_ULL(6, 0) + #define GICR_VPENDBASER 0x0078 #define GICR_VPENDBASER_SHAREABILITY_SHIFT (10) @@ -314,6 +333,7 @@ #define GITS_CTLR 0x0000 #define GITS_IIDR 0x0004 #define GITS_TYPER 0x0008 +#define GITS_MPIDR 0x0018 #define GITS_CBASER 0x0080 #define GITS_CWRITER 0x0088 #define GITS_CREADR 0x0090 @@ -347,6 +367,8 @@ #define GITS_TYPER_HCC_SHIFT 24 #define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & 0xff) #define GITS_TYPER_VMOVP (1ULL << 37) +#define GITS_TYPER_VMAPP (1ULL << 40) +#define GITS_TYPER_SVPET GENMASK_ULL(42, 41) #define GITS_IIDR_REV_SHIFT 12 #define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT) @@ -417,10 +439,11 @@ #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) #define GITS_BASER_PAGE_SIZE_SHIFT (8) -#define GITS_BASER_PAGE_SIZE_4K (0ULL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_16K (1ULL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_64K (2ULL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_MASK (3ULL << GITS_BASER_PAGE_SIZE_SHIFT) +#define __GITS_BASER_PSZ(sz) (GIC_PAGE_SIZE_ ## sz << GITS_BASER_PAGE_SIZE_SHIFT) +#define GITS_BASER_PAGE_SIZE_4K __GITS_BASER_PSZ(4K) +#define GITS_BASER_PAGE_SIZE_16K __GITS_BASER_PSZ(16K) +#define GITS_BASER_PAGE_SIZE_64K __GITS_BASER_PSZ(64K) +#define GITS_BASER_PAGE_SIZE_MASK __GITS_BASER_PSZ(MASK) #define GITS_BASER_PAGES_MAX 256 #define GITS_BASER_PAGES_SHIFT (0) #define GITS_BASER_NR_PAGES(r) (((r) & 0xff) + 1) @@ -612,8 +635,10 @@ struct rdists { struct { void __iomem *rd_base; struct page *pend_page; + struct page *vpe_l1_page; phys_addr_t phys_base; bool lpi_enabled; + cpumask_t *vpe_table_mask; } __percpu *rdist; phys_addr_t prop_table_pa; void *prop_table_va; -- cgit v1.2.3 From 64edfaa9a2342a3ce34f8cb982c2c2df84db4de3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:29 +0000 Subject: irqchip/gic-v4.1: Implement the v4.1 flavour of VMAPP The ITS VMAPP command gains some new fields with GICv4.1: - a default doorbell, which allows a single doorbell to be used for all the VLPIs routed to a given VPE - a pointer to the configuration table (instead of having it in a register that gets context switched) - a flag indicating whether this is the first map or the last unmap for this particular VPE - a flag indicating whether the pending table is known to be zeroed, or not Plumb in the new fields in the VMAPP builder, and add the map/unmap refcounting so that the ITS can do the right thing. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-7-maz@kernel.org --- include/linux/irqchip/arm-gic-v4.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 5dbcfc65f21e..498e523085a7 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -39,8 +39,20 @@ struct its_vpe { irq_hw_number_t vpe_db_lpi; /* VPE resident */ bool resident; - /* VPE proxy mapping */ - int vpe_proxy_event; + union { + /* GICv4.0 implementations */ + struct { + /* VPE proxy mapping */ + int vpe_proxy_event; + /* Implementation Defined Area Invalid */ + bool idai; + }; + /* GICv4.1 implementations */ + struct { + atomic_t vmapp_count; + }; + }; + /* * This collection ID is used to indirect the target * redistributor for this VPE. The ID itself isn't involved in @@ -49,8 +61,6 @@ struct its_vpe { u16 col_idx; /* Unique (system-wide) VPE identifier */ u16 vpe_id; - /* Implementation Defined Area Invalid */ - bool idai; /* Pending VLPIs on schedule out? */ bool pending_last; }; -- cgit v1.2.3 From d97c97baa214486cc3d64c996a2214475f6cc83c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:33 +0000 Subject: irqchip/gic-v4.1: Add mask/unmask doorbell callbacks masking/unmasking doorbells on GICv4.1 relies on a new INVDB command, which broadcasts the invalidation to all RDs. Implement the new command as well as the masking callbacks, and plug the whole thing into the v4.1 VPE irqchip. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-11-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index db0a11193d92..1f17181a9f7e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -484,8 +484,9 @@ #define GITS_CMD_VMAPTI GITS_CMD_GICv4(GITS_CMD_MAPTI) #define GITS_CMD_VMOVI GITS_CMD_GICv4(GITS_CMD_MOVI) #define GITS_CMD_VSYNC GITS_CMD_GICv4(GITS_CMD_SYNC) -/* VMOVP is the odd one, as it doesn't have a physical counterpart */ +/* VMOVP and INVDB are the odd ones, as they dont have a physical counterpart */ #define GITS_CMD_VMOVP GITS_CMD_GICv4(2) +#define GITS_CMD_INVDB GITS_CMD_GICv4(0xe) /* * ITS error numbers -- cgit v1.2.3 From 91bf6395f7b8614a5a9934a0ae9c8b5312d77b29 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:34 +0000 Subject: irqchip/gic-v4.1: Add VPE residency callback Making a VPE resident on GICv4.1 is pretty simple, as it is just a single write to the local redistributor. We just need extra information about which groups to enable, which the KVM code will have to provide. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-12-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 9 +++++++++ include/linux/irqchip/arm-gic-v4.h | 5 +++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 1f17181a9f7e..822dae6abf75 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -327,6 +327,15 @@ #define GICR_VPENDBASER_IDAI (1ULL << 62) #define GICR_VPENDBASER_Valid (1ULL << 63) +/* + * GICv4.1 VPENDBASER, used for VPE residency. On top of these fields, + * also use the above Valid, PendingLast and Dirty. + */ +#define GICR_VPENDBASER_4_1_DB (1ULL << 62) +#define GICR_VPENDBASER_4_1_VGRP0EN (1ULL << 59) +#define GICR_VPENDBASER_4_1_VGRP1EN (1ULL << 58) +#define GICR_VPENDBASER_4_1_VPEID GENMASK_ULL(15, 0) + /* * ITS registers, offsets from ITS_base */ diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 498e523085a7..d9c34968467a 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -100,6 +100,11 @@ struct its_cmd_info { union { struct its_vlpi_map *map; u8 config; + bool req_db; + struct { + bool g0en; + bool g1en; + }; }; }; -- cgit v1.2.3 From b4a4bd0f2629ec2ece7690de1b4721529da29871 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:36 +0000 Subject: irqchip/gic-v4.1: Add VPE INVALL callback GICv4.1 redistributors have a VPE-aware INVALL register. Progress! We can now emulate a guest-requested INVALL without emiting a VINVALL command. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-14-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 822dae6abf75..49ed6fa5e293 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -247,6 +247,12 @@ #define GICR_TYPER_COMMON_LPI_AFF GENMASK_ULL(25, 24) #define GICR_TYPER_AFFINITY GENMASK_ULL(63, 32) +#define GICR_INVLPIR_VPEID GENMASK_ULL(47, 32) +#define GICR_INVLPIR_V GENMASK_ULL(63, 63) + +#define GICR_INVALLR_VPEID GICR_INVLPIR_VPEID +#define GICR_INVALLR_V GICR_INVLPIR_V + #define GIC_V3_REDIST_SIZE 0x20000 #define LPI_PROP_GROUP1 (1 << 1) -- cgit v1.2.3 From f4a81f5a853e0b7c38bfad3afd6d0365d654e777 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 24 Dec 2019 11:10:38 +0000 Subject: irqchip/gic-v4.1: Allow direct invalidation of VLPIs Just like for INVALL, GICv4.1 has grown a VPE-aware INVLPI register. Let's plumb it in and make use of the DirectLPI code in that case. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191224111055.11836-16-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 49ed6fa5e293..f0b8ca766e7d 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -247,6 +247,7 @@ #define GICR_TYPER_COMMON_LPI_AFF GENMASK_ULL(25, 24) #define GICR_TYPER_AFFINITY GENMASK_ULL(63, 32) +#define GICR_INVLPIR_INTID GENMASK_ULL(31, 0) #define GICR_INVLPIR_VPEID GENMASK_ULL(47, 32) #define GICR_INVLPIR_V GENMASK_ULL(63, 63) -- cgit v1.2.3 From 11ea68f553e244851d15793a7fa33a97c46d8271 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 20 Jan 2020 17:16:25 +0800 Subject: genirq, sched/isolation: Isolate from handling managed interrupts The affinity of managed interrupts is completely handled in the kernel and cannot be changed via the /proc/irq/* interfaces from user space. As the kernel tries to spread out interrupts evenly accross CPUs on x86 to prevent vector exhaustion, it can happen that a managed interrupt whose affinity mask contains both isolated and housekeeping CPUs is routed to an isolated CPU. As a consequence IO submitted on a housekeeping CPU causes interrupts on the isolated CPU. Add a new sub-parameter 'managed_irq' for 'isolcpus' and the corresponding logic in the interrupt affinity selection code. The subparameter indicates to the interrupt affinity selection logic that it should try to avoid the above scenario. This isolation is best effort and only effective if the automatically assigned interrupt mask of a device queue contains isolated and housekeeping CPUs. If housekeeping CPUs are online then such interrupts are directed to the housekeeping CPU so that IO submitted on the housekeeping CPU cannot disturb the isolated CPU. If a queue's affinity mask contains only isolated CPUs then this parameter has no effect on the interrupt routing decision, though interrupts are only happening when tasks running on those isolated CPUs submit IO. IO submitted on housekeeping CPUs has no influence on those queues. If the affinity mask contains both housekeeping and isolated CPUs, but none of the contained housekeeping CPUs is online, then the interrupt is also routed to an isolated CPU. Interrupts are only delivered when one of the isolated CPUs in the affinity mask submits IO. If one of the contained housekeeping CPUs comes online, the CPU hotplug logic migrates the interrupt automatically back to the upcoming housekeeping CPU. Depending on the type of interrupt controller, this can require that at least one interrupt is delivered to the isolated CPU in order to complete the migration. [ tglx: Removed unused parameter, added and edited comments/documentation and rephrased the changelog so it contains more details. ] Signed-off-by: Ming Lei Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20200120091625.17912-1-ming.lei@redhat.com --- include/linux/sched/isolation.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 6c8512d3be88..0fbcbacd1b29 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -13,6 +13,7 @@ enum hk_flags { HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), HK_FLAG_WQ = (1 << 6), + HK_FLAG_MANAGED_IRQ = (1 << 7), }; #ifdef CONFIG_CPU_ISOLATION -- cgit v1.2.3 From 6beea7afcc72b86986080ea1d228a42f2000f2a9 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 13 Jan 2020 10:42:44 +0100 Subject: ima: add the ability to query the cached hash of a given file This allows other parts of the kernel (perhaps a stacked LSM allowing system monitoring, eg. the proposed KRSI LSM [1]) to retrieve the hash of a given file from IMA if it's present in the iint cache. It's true that the existence of the hash means that it's also in the audit logs or in /sys/kernel/security/ima/ascii_runtime_measurements, but it can be difficult to pull that information out for every subsequent exec. This is especially true if a given host has been up for a long time and the file was first measured a long time ago. It should be kept in mind that this function gives access to cached entries which can be removed, for instance on security_inode_free(). This is based on Peter Moody's patch: https://sourceforge.net/p/linux-ima/mailman/message/33036180/ [1] https://lkml.org/lkml/2019/9/10/393 Signed-off-by: Florent Revest Reviewed-by: KP Singh Signed-off-by: Mimi Zohar --- include/linux/ima.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index f4644c54f648..1659217e9b60 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -23,6 +23,7 @@ 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); extern void ima_post_path_mknod(struct dentry *dentry); +extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern void ima_kexec_cmdline(const void *buf, int size); #ifdef CONFIG_IMA_KEXEC @@ -91,6 +92,11 @@ static inline void ima_post_path_mknod(struct dentry *dentry) return; } +static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size) +{ + return -EOPNOTSUPP; +} + static inline void ima_kexec_cmdline(const void *buf, int size) {} #endif /* CONFIG_IMA */ -- cgit v1.2.3 From be8704ff07d2374bcc5c675526f95e70c6459683 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 20 Jan 2020 16:53:46 -0800 Subject: bpf: Introduce dynamic program extensions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce dynamic program extensions. The users can load additional BPF functions and replace global functions in previously loaded BPF programs while these programs are executing. Global functions are verified individually by the verifier based on their types only. Hence the global function in the new program which types match older function can safely replace that corresponding function. This new function/program is called 'an extension' of old program. At load time the verifier uses (attach_prog_fd, attach_btf_id) pair to identify the function to be replaced. The BPF program type is derived from the target program into extension program. Technically bpf_verifier_ops is copied from target program. The BPF_PROG_TYPE_EXT program type is a placeholder. It has empty verifier_ops. The extension program can call the same bpf helper functions as target program. Single BPF_PROG_TYPE_EXT type is used to extend XDP, SKB and all other program types. The verifier allows only one level of replacement. Meaning that the extension program cannot recursively extend an extension. That also means that the maximum stack size is increasing from 512 to 1024 bytes and maximum function nesting level from 8 to 16. The programs don't always consume that much. The stack usage is determined by the number of on-stack variables used by the program. The verifier could have enforced 512 limit for combined original plus extension program, but it makes for difficult user experience. The main use case for extensions is to provide generic mechanism to plug external programs into policy program or function call chaining. BPF trampoline is used to track both fentry/fexit and program extensions because both are using the same nop slot at the beginning of every BPF function. Attaching fentry/fexit to a function that was replaced is not allowed. The opposite is true as well. Replacing a function that currently being analyzed with fentry/fexit is not allowed. The executable page allocated by BPF trampoline is not used by program extensions. This inefficiency will be optimized in future patches. Function by function verification of global function supports scalars and pointer to context only. Hence program extensions are supported for such class of global functions only. In the future the verifier will be extended with support to pointers to structures, arrays with sizes, etc. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20200121005348.2769920-2-ast@kernel.org --- include/linux/bpf.h | 10 +++++++++- include/linux/bpf_types.h | 2 ++ include/linux/btf.h | 5 +++++ 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8e3b8f4ad183..05d16615054c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -465,7 +465,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, - BPF_TRAMP_MAX + BPF_TRAMP_MAX, + BPF_TRAMP_REPLACE, /* more than MAX */ }; struct bpf_trampoline { @@ -480,6 +481,11 @@ struct bpf_trampoline { void *addr; bool ftrace_managed; } func; + /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF + * program by replacing one of its functions. func.addr is the address + * of the function it replaced. + */ + struct bpf_prog *extension_prog; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; /* Number of attached programs. A counter per kind. */ @@ -1107,6 +1113,8 @@ 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, + struct btf *btf, const struct btf_type *t); struct bpf_prog *bpf_prog_by_id(u32 id); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9f326e6ef885..c81d4ece79a4 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -68,6 +68,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, #if defined(CONFIG_BPF_JIT) BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops, void *, void *) +BPF_PROG_TYPE(BPF_PROG_TYPE_EXT, bpf_extension, + void *, void *) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) diff --git a/include/linux/btf.h b/include/linux/btf.h index 881e9b76ef49..5c1ea99b480f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -107,6 +107,11 @@ static inline u16 btf_type_vlen(const struct btf_type *t) return BTF_INFO_VLEN(t->info); } +static inline u16 btf_func_linkage(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + static inline bool btf_type_kflag(const struct btf_type *t) { return BTF_INFO_KFLAG(t->info); -- cgit v1.2.3 From 6e1918cfb263acacd3fc9239127732b69de64695 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 20 Jan 2020 14:31:56 -0800 Subject: fscrypt: don't allow v1 policies with casefolding Casefolded encrypted directories will use a new dirhash method that requires a secret key. If the directory uses a v2 encryption policy, it's easy to derive this key from the master key using HKDF. However, v1 encryption policies don't provide a way to derive additional keys. Therefore, don't allow casefolding on directories that use a v1 policy. Specifically, make it so that trying to enable casefolding on a directory that has a v1 policy fails, trying to set a v1 policy on a casefolded directory fails, and trying to open a casefolded directory that has a v1 policy (if one somehow exists on-disk) fails. Signed-off-by: Daniel Rosenberg [EB: improved commit message, updated fscrypt.rst, and other cleanups] Link: https://lore.kernel.org/r/20200120223201.241390-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 6fe8d0f96a4a..3984eadd7023 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -263,6 +263,8 @@ extern int __fscrypt_prepare_rename(struct inode *old_dir, unsigned int flags); extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname); +extern int fscrypt_prepare_setflags(struct inode *inode, + unsigned int oldflags, unsigned int flags); extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, unsigned int max_len, struct fscrypt_str *disk_link); @@ -519,6 +521,13 @@ static inline int __fscrypt_prepare_lookup(struct inode *dir, return -EOPNOTSUPP; } +static inline int fscrypt_prepare_setflags(struct inode *inode, + unsigned int oldflags, + unsigned int flags) +{ + return 0; +} + static inline int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, unsigned int max_len, -- cgit v1.2.3 From aa408f835d025a839033988d3f5a2866314414ef Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 20 Jan 2020 14:31:57 -0800 Subject: fscrypt: derive dirhash key for casefolded directories When we allow indexed directories to use both encryption and casefolding, for the dirhash we can't just hash the ciphertext filenames that are stored on-disk (as is done currently) because the dirhash must be case insensitive, but the stored names are case-preserving. Nor can we hash the plaintext names with an unkeyed hash (or a hash keyed with a value stored on-disk like ext4's s_hash_seed), since that would leak information about the names that encryption is meant to protect. Instead, if we can accept a dirhash that's only computable when the fscrypt key is available, we can hash the plaintext names with a keyed hash using a secret key derived from the directory's fscrypt master key. We'll use SipHash-2-4 for this purpose. Prepare for this by deriving a SipHash key for each casefolded encrypted directory. Make sure to handle deriving the key not only when setting up the directory's fscrypt_info, but also in the case where the casefold flag is enabled after the fscrypt_info was already set up. (We could just always derive the key regardless of casefolding, but that would introduce unnecessary overhead for people not using casefolding.) Signed-off-by: Daniel Rosenberg [EB: improved commit message, updated fscrypt.rst, squashed with change that avoids unnecessarily deriving the key, and many other cleanups] Link: https://lore.kernel.org/r/20200120223201.241390-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 3984eadd7023..34bc5f73200c 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -247,6 +247,9 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); } +extern u64 fscrypt_fname_siphash(const struct inode *dir, + const struct qstr *name); + /* bio.c */ extern void fscrypt_decrypt_bio(struct bio *); extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, @@ -479,6 +482,13 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); } +static inline u64 fscrypt_fname_siphash(const struct inode *dir, + const struct qstr *name) +{ + WARN_ON_ONCE(1); + return 0; +} + /* bio.c */ static inline void fscrypt_decrypt_bio(struct bio *bio) { -- cgit v1.2.3 From edc440e3d27fb31e6f9663cf413fad97d714c060 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 20 Jan 2020 14:32:01 -0800 Subject: fscrypt: improve format of no-key names When an encrypted directory is listed without the key, the filesystem must show "no-key names" that uniquely identify directory entries, are at most 255 (NAME_MAX) bytes long, and don't contain '/' or '\0'. Currently, for short names the no-key name is the base64 encoding of the ciphertext filename, while for long names it's the base64 encoding of the ciphertext filename's dirhash and second-to-last 16-byte block. This format has the following problems: - Since it doesn't always include the dirhash, it's incompatible with directories that will use a secret-keyed dirhash over the plaintext filenames. In this case, the dirhash won't be computable from the ciphertext name without the key, so it instead must be retrieved from the directory entry and always included in the no-key name. Casefolded encrypted directories will use this type of dirhash. - It's ambiguous: it's possible to craft two filenames that map to the same no-key name, since the method used to abbreviate long filenames doesn't use a proper cryptographic hash function. Solve both these problems by switching to a new no-key name format that is the base64 encoding of a variable-length structure that contains the dirhash, up to 149 bytes of the ciphertext filename, and (if any bytes remain) the SHA-256 of the remaining bytes of the ciphertext filename. This ensures that each no-key name contains everything needed to find the directory entry again, contains only legal characters, doesn't exceed NAME_MAX, is unambiguous unless there's a SHA-256 collision, and that we only take the performance hit of SHA-256 on very long filenames. Note: this change does *not* address the existing issue where users can modify the 'dirhash' part of a no-key name and the filesystem may still accept the name. Signed-off-by: Daniel Rosenberg [EB: improved comments and commit message, fixed checking return value of base64_decode(), check for SHA-256 error, continue to set disk_name for short names to keep matching simpler, and many other cleanups] Link: https://lore.kernel.org/r/20200120223201.241390-7-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 77 ++----------------------------------------------- 1 file changed, 2 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 34bc5f73200c..556f4adf5dc5 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -172,81 +172,8 @@ extern int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, struct fscrypt_str *oname); - -#define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32 - -/* Extracts the second-to-last ciphertext block; see explanation below */ -#define FSCRYPT_FNAME_DIGEST(name, len) \ - ((name) + round_down((len) - FS_CRYPTO_BLOCK_SIZE - 1, \ - FS_CRYPTO_BLOCK_SIZE)) - -#define FSCRYPT_FNAME_DIGEST_SIZE FS_CRYPTO_BLOCK_SIZE - -/** - * fscrypt_digested_name - alternate identifier for an on-disk filename - * - * When userspace lists an encrypted directory without access to the key, - * filenames whose ciphertext is longer than FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE - * bytes are shown in this abbreviated form (base64-encoded) rather than as the - * full ciphertext (base64-encoded). This is necessary to allow supporting - * filenames up to NAME_MAX bytes, since base64 encoding expands the length. - * - * To make it possible for filesystems to still find the correct directory entry - * despite not knowing the full on-disk name, we encode any filesystem-specific - * 'hash' and/or 'minor_hash' which the filesystem may need for its lookups, - * followed by the second-to-last ciphertext block of the filename. Due to the - * use of the CBC-CTS encryption mode, the second-to-last ciphertext block - * depends on the full plaintext. (Note that ciphertext stealing causes the - * last two blocks to appear "flipped".) This makes accidental collisions very - * unlikely: just a 1 in 2^128 chance for two filenames to collide even if they - * share the same filesystem-specific hashes. - * - * However, this scheme isn't immune to intentional collisions, which can be - * created by anyone able to create arbitrary plaintext filenames and view them - * without the key. Making the "digest" be a real cryptographic hash like - * SHA-256 over the full ciphertext would prevent this, although it would be - * less efficient and harder to implement, especially since the filesystem would - * need to calculate it for each directory entry examined during a search. - */ -struct fscrypt_digested_name { - u32 hash; - u32 minor_hash; - u8 digest[FSCRYPT_FNAME_DIGEST_SIZE]; -}; - -/** - * fscrypt_match_name() - test whether the given name matches a directory entry - * @fname: the name being searched for - * @de_name: the name from the directory entry - * @de_name_len: the length of @de_name in bytes - * - * Normally @fname->disk_name will be set, and in that case we simply compare - * that to the name stored in the directory entry. The only exception is that - * if we don't have the key for an encrypted directory and a filename in it is - * very long, then we won't have the full disk_name and we'll instead need to - * match against the fscrypt_digested_name. - * - * Return: %true if the name matches, otherwise %false. - */ -static inline bool fscrypt_match_name(const struct fscrypt_name *fname, - const u8 *de_name, u32 de_name_len) -{ - if (unlikely(!fname->disk_name.name)) { - const struct fscrypt_digested_name *n = - (const void *)fname->crypto_buf.name; - if (WARN_ON_ONCE(fname->usr_fname->name[0] != '_')) - return false; - if (de_name_len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) - return false; - return !memcmp(FSCRYPT_FNAME_DIGEST(de_name, de_name_len), - n->digest, FSCRYPT_FNAME_DIGEST_SIZE); - } - - if (de_name_len != fname->disk_name.len) - return false; - return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); -} - +extern bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len); extern u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); -- cgit v1.2.3 From 5576b991e9c1a11d2cc21c4b94fc75ec27603896 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 22 Jan 2020 15:36:46 -0800 Subject: bpf: Add BPF_FUNC_jiffies64 This patch adds a helper to read the 64bit jiffies. It will be used in a later patch to implement the bpf_cubic.c. The helper is inlined for jit_requested and 64 BITS_PER_LONG as the map_gen_lookup(). Other cases could be considered together with map_gen_lookup() if needed. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200122233646.903260-1-kafai@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 05d16615054c..a9687861fd7e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1414,6 +1414,7 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; +extern const struct bpf_func_proto bpf_jiffies64_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); -- cgit v1.2.3 From 17a0184ca17e288decdca8b2841531e34d49285f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 22 Jan 2020 11:15:27 +0100 Subject: USB: serial: ir-usb: fix link-speed handling Commit e0d795e4f36c ("usb: irda: cleanup on ir-usb module") added a USB IrDA header with common defines, but mistakingly switched to using the class-descriptor baud-rate bitmask values for the outbound header. This broke link-speed handling for rates above 9600 baud, but a device would also be able to operate at the default 9600 baud until a link-speed request was issued (e.g. using the TCGETS ioctl). Fixes: e0d795e4f36c ("usb: irda: cleanup on ir-usb module") Cc: stable # 2.6.27 Cc: Felipe Balbi Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/usb/irda.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/irda.h b/include/linux/usb/irda.h index 396d2b043e64..556a801efce3 100644 --- a/include/linux/usb/irda.h +++ b/include/linux/usb/irda.h @@ -119,11 +119,22 @@ struct usb_irda_cs_descriptor { * 6 - 115200 bps * 7 - 576000 bps * 8 - 1.152 Mbps - * 9 - 5 mbps + * 9 - 4 Mbps * 10..15 - Reserved */ #define USB_IRDA_STATUS_LINK_SPEED 0x0f +#define USB_IRDA_LS_NO_CHANGE 0 +#define USB_IRDA_LS_2400 1 +#define USB_IRDA_LS_9600 2 +#define USB_IRDA_LS_19200 3 +#define USB_IRDA_LS_38400 4 +#define USB_IRDA_LS_57600 5 +#define USB_IRDA_LS_115200 6 +#define USB_IRDA_LS_576000 7 +#define USB_IRDA_LS_1152000 8 +#define USB_IRDA_LS_4000000 9 + /* The following is a 4-bit value used only for * outbound header: * -- cgit v1.2.3 From d836f5c69d87473ff65c06a6123e5b2cf5e56f5b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Jan 2020 22:47:29 -0800 Subject: net: rtnetlink: validate IFLA_MTU attribute in rtnl_create_link() rtnl_create_link() needs to apply dev->min_mtu and dev->max_mtu checks that we apply in do_setlink() Otherwise malicious users can crash the kernel, for example after an integer overflow : BUG: KASAN: use-after-free in memset include/linux/string.h:365 [inline] BUG: KASAN: use-after-free in __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238 Write of size 32 at addr ffff88819f20b9c0 by task swapper/0/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.5.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:639 check_memory_region_inline mm/kasan/generic.c:185 [inline] check_memory_region+0x134/0x1a0 mm/kasan/generic.c:192 memset+0x24/0x40 mm/kasan/common.c:108 memset include/linux/string.h:365 [inline] __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238 alloc_skb include/linux/skbuff.h:1049 [inline] alloc_skb_with_frags+0x93/0x590 net/core/skbuff.c:5664 sock_alloc_send_pskb+0x7ad/0x920 net/core/sock.c:2242 sock_alloc_send_skb+0x32/0x40 net/core/sock.c:2259 mld_newpack+0x1d7/0x7f0 net/ipv6/mcast.c:1609 add_grhead.isra.0+0x299/0x370 net/ipv6/mcast.c:1713 add_grec+0x7db/0x10b0 net/ipv6/mcast.c:1844 mld_send_cr net/ipv6/mcast.c:1970 [inline] mld_ifc_timer_expire+0x3d3/0x950 net/ipv6/mcast.c:2477 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0x6c3/0x1790 kernel/time/timer.c:1786 __do_softirq+0x262/0x98c kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0x19b/0x1e0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x1a3/0x610 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829 RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61 Code: 98 6b ea f9 eb 8a cc cc cc cc cc cc e9 07 00 00 00 0f 00 2d 44 1c 60 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 34 1c 60 00 fb f4 cc 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 4e 5d 9a f9 e8 79 RSP: 0018:ffffffff89807ce8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13 RAX: 1ffffffff13266ae RBX: ffffffff8987a1c0 RCX: 0000000000000000 RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffffffff8987aa54 RBP: ffffffff89807d18 R08: ffffffff8987a1c0 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: dffffc0000000000 R13: ffffffff8a799980 R14: 0000000000000000 R15: 0000000000000000 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:690 default_idle_call+0x84/0xb0 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x3c8/0x6e0 kernel/sched/idle.c:269 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:361 rest_init+0x23b/0x371 init/main.c:451 arch_call_rest_init+0xe/0x1b start_kernel+0x904/0x943 init/main.c:784 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x77/0x7b arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:242 The buggy address belongs to the page: page:ffffea00067c82c0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 raw: 057ffe0000000000 ffffea00067c82c8 ffffea00067c82c8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88819f20b880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff88819f20b900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff88819f20b980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff88819f20ba00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff88819f20ba80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ae5e260911e2..cac56fb59af8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3698,6 +3698,8 @@ int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); +int dev_validate_mtu(struct net_device *dev, int mtu, + struct netlink_ext_ack *extack); int dev_set_mtu_ext(struct net_device *dev, int mtu, struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); -- cgit v1.2.3 From 72780ce5f1a4189f3c8dcfb1c596c65146452668 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 13 Jan 2020 23:08:00 +0100 Subject: gpio: Drop the chained IRQ handler assign function gpiochip_set_chained_irqchip() would assign a chained handler to a GPIO chip. We now populate struct gpio_irq_chip for all chained GPIO irqchips so drop this function. Cc: Andy Shevchenko Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20200113220800.77817-1-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index e2480ef94c55..7067bc70a473 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -585,11 +585,6 @@ int gpiochip_irq_domain_activate(struct irq_domain *domain, void gpiochip_irq_domain_deactivate(struct irq_domain *domain, struct irq_data *data); -void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip, - struct irq_chip *irqchip, - unsigned int parent_irq, - irq_flow_handler_t parent_handler); - void gpiochip_set_nested_irqchip(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int parent_irq); -- cgit v1.2.3 From 6080d608eeff7cb5090a2ddbaf723bfb0ff133fc Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Wed, 22 Jan 2020 22:34:47 +0530 Subject: module.h: Annotate mod_kallsyms with __rcu This patch fixes the following sparse errors: kernel/module.c:3623:9: error: incompatible types in comparison expression kernel/module.c:4060:41: error: incompatible types in comparison expression kernel/module.c:4203:28: error: incompatible types in comparison expression kernel/module.c:4225:41: error: incompatible types in comparison expression Signed-off-by: Madhuparna Bhowmik Signed-off-by: Jessica Yu --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index bd165ba68617..dfdc8863e26a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -429,7 +429,7 @@ struct module { #ifdef CONFIG_KALLSYMS /* Protected by RCU and/or module_mutex: use rcu_dereference() */ - struct mod_kallsyms *kallsyms; + struct mod_kallsyms __rcu *kallsyms; struct mod_kallsyms core_kallsyms; /* Section attributes */ -- cgit v1.2.3 From fdabc466f335bc3cbda8eca2270a8af783cae7eb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 23 Jan 2020 16:50:13 +0100 Subject: usb: phy: phy-gpio-vbus-usb: Convert to GPIO descriptors Instead of using the legacy GPIO API and keeping track on polarity inversion semantics in the driver, switch to use GPIO descriptors for this driver and change all consumers in the process. This makes it possible to retire platform data completely: the only remaining platform data member was "wakeup" which was intended to make the vbus interrupt wakeup capable, but was not set by any users and thus remained unused. VBUS was not waking any devices up. Leave a comment about it so later developers using the platform can consider setting it to always enabled so plugging in USB wakes up the platform. Cc: Daniel Mack Cc: Haojian Zhuang Acked-by: Robert Jarzmik Acked-by: Felipe Balbi Acked-by: Sylwester Nawrocki Acked-by: Philipp Zabel Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20200123155013.93249-1-linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gpio_vbus.h | 33 --------------------------------- 1 file changed, 33 deletions(-) delete mode 100644 include/linux/usb/gpio_vbus.h (limited to 'include/linux') diff --git a/include/linux/usb/gpio_vbus.h b/include/linux/usb/gpio_vbus.h deleted file mode 100644 index 804fb06cf6d6..000000000000 --- a/include/linux/usb/gpio_vbus.h +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * A simple GPIO VBUS sensing driver for B peripheral only devices - * with internal transceivers. - * Optionally D+ pullup can be controlled by a second GPIO. - * - * Copyright (c) 2008 Philipp Zabel - * - * 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. - * - */ - -/** - * struct gpio_vbus_mach_info - configuration for gpio_vbus - * @gpio_vbus: VBUS sensing GPIO - * @gpio_pullup: optional D+ or D- pullup GPIO (else negative/invalid) - * @gpio_vbus_inverted: true if gpio_vbus is active low - * @gpio_pullup_inverted: true if gpio_pullup is active low - * @wakeup: configure gpio_vbus as a wake-up source - * - * The VBUS sensing GPIO should have a pulldown, which will normally be - * part of a resistor ladder turning a 4.0V-5.25V level on VBUS into a - * value the GPIO detects as active. Some systems will use comparators. - */ -struct gpio_vbus_mach_info { - int gpio_vbus; - int gpio_pullup; - bool gpio_vbus_inverted; - bool gpio_pullup_inverted; - bool wakeup; -}; -- cgit v1.2.3 From 4413405f931ef97ab1263ae3588e6f656ec220b7 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Sun, 24 Nov 2019 20:20:29 +0000 Subject: hwmon: Add intrusion templates Add templates for intrusion%d_alarm and intrusion%d_beep. Note, these start at 0. Signed-off-by: Dr. David Alan Gilbert Link: https://lore.kernel.org/r/20191124202030.45360-2-linux@treblig.org Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 72579168189d..dcda9589cdaf 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -27,6 +27,7 @@ enum hwmon_sensor_types { hwmon_humidity, hwmon_fan, hwmon_pwm, + hwmon_intrusion, hwmon_max, }; @@ -306,6 +307,13 @@ enum hwmon_pwm_attributes { #define HWMON_PWM_MODE BIT(hwmon_pwm_mode) #define HWMON_PWM_FREQ BIT(hwmon_pwm_freq) +enum hwmon_intrusion_attributes { + hwmon_intrusion_alarm, + hwmon_intrusion_beep, +}; +#define HWMON_INTRUSION_ALARM BIT(hwmon_intrusion_alarm) +#define HWMON_INTRUSION_BEEP BIT(hwmon_intrusion_beep) + /** * struct hwmon_ops - hwmon device operations * @is_visible: Callback to return attribute visibility. Mandatory. -- cgit v1.2.3 From 002c6b545b85676539add33add8aa7f1f49cbfff Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 17 Jul 2018 10:17:19 -0700 Subject: hwmon: Add support for enable attributes to hwmon core The hwmon ABI supports enable attributes since commit fb41a710f84e ("hwmon: Document the sensor enable attribute"), but did not add support for those attributes to the hwmon core. Do that now. Since the enable attributes are logically the most important attributes, they are added as first attribute to the attribute list. Move hwmon_in_enable from last to first place for consistency. Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index dcda9589cdaf..5e609f25878c 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -60,7 +60,8 @@ enum hwmon_chip_attributes { #define HWMON_C_TEMP_SAMPLES BIT(hwmon_chip_temp_samples) enum hwmon_temp_attributes { - hwmon_temp_input = 0, + hwmon_temp_enable, + hwmon_temp_input, hwmon_temp_type, hwmon_temp_lcrit, hwmon_temp_lcrit_hyst, @@ -86,6 +87,7 @@ enum hwmon_temp_attributes { hwmon_temp_reset_history, }; +#define HWMON_T_ENABLE BIT(hwmon_temp_enable) #define HWMON_T_INPUT BIT(hwmon_temp_input) #define HWMON_T_TYPE BIT(hwmon_temp_type) #define HWMON_T_LCRIT BIT(hwmon_temp_lcrit) @@ -112,6 +114,7 @@ enum hwmon_temp_attributes { #define HWMON_T_RESET_HISTORY BIT(hwmon_temp_reset_history) enum hwmon_in_attributes { + hwmon_in_enable, hwmon_in_input, hwmon_in_min, hwmon_in_max, @@ -127,9 +130,9 @@ enum hwmon_in_attributes { hwmon_in_max_alarm, hwmon_in_lcrit_alarm, hwmon_in_crit_alarm, - hwmon_in_enable, }; +#define HWMON_I_ENABLE BIT(hwmon_in_enable) #define HWMON_I_INPUT BIT(hwmon_in_input) #define HWMON_I_MIN BIT(hwmon_in_min) #define HWMON_I_MAX BIT(hwmon_in_max) @@ -145,9 +148,9 @@ 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_ENABLE BIT(hwmon_in_enable) enum hwmon_curr_attributes { + hwmon_curr_enable, hwmon_curr_input, hwmon_curr_min, hwmon_curr_max, @@ -165,6 +168,7 @@ enum hwmon_curr_attributes { hwmon_curr_crit_alarm, }; +#define HWMON_C_ENABLE BIT(hwmon_curr_enable) #define HWMON_C_INPUT BIT(hwmon_curr_input) #define HWMON_C_MIN BIT(hwmon_curr_min) #define HWMON_C_MAX BIT(hwmon_curr_max) @@ -182,6 +186,7 @@ enum hwmon_curr_attributes { #define HWMON_C_CRIT_ALARM BIT(hwmon_curr_crit_alarm) enum hwmon_power_attributes { + hwmon_power_enable, hwmon_power_average, hwmon_power_average_interval, hwmon_power_average_interval_max, @@ -212,6 +217,7 @@ enum hwmon_power_attributes { hwmon_power_crit_alarm, }; +#define HWMON_P_ENABLE BIT(hwmon_power_enable) #define HWMON_P_AVERAGE BIT(hwmon_power_average) #define HWMON_P_AVERAGE_INTERVAL BIT(hwmon_power_average_interval) #define HWMON_P_AVERAGE_INTERVAL_MAX BIT(hwmon_power_average_interval_max) @@ -242,14 +248,17 @@ enum hwmon_power_attributes { #define HWMON_P_CRIT_ALARM BIT(hwmon_power_crit_alarm) enum hwmon_energy_attributes { + hwmon_energy_enable, hwmon_energy_input, hwmon_energy_label, }; +#define HWMON_E_ENABLE BIT(hwmon_energy_enable) #define HWMON_E_INPUT BIT(hwmon_energy_input) #define HWMON_E_LABEL BIT(hwmon_energy_label) enum hwmon_humidity_attributes { + hwmon_humidity_enable, hwmon_humidity_input, hwmon_humidity_label, hwmon_humidity_min, @@ -260,6 +269,7 @@ enum hwmon_humidity_attributes { hwmon_humidity_fault, }; +#define HWMON_H_ENABLE BIT(hwmon_humidity_enable) #define HWMON_H_INPUT BIT(hwmon_humidity_input) #define HWMON_H_LABEL BIT(hwmon_humidity_label) #define HWMON_H_MIN BIT(hwmon_humidity_min) @@ -270,6 +280,7 @@ enum hwmon_humidity_attributes { #define HWMON_H_FAULT BIT(hwmon_humidity_fault) enum hwmon_fan_attributes { + hwmon_fan_enable, hwmon_fan_input, hwmon_fan_label, hwmon_fan_min, @@ -283,6 +294,7 @@ enum hwmon_fan_attributes { hwmon_fan_fault, }; +#define HWMON_F_ENABLE BIT(hwmon_fan_enable) #define HWMON_F_INPUT BIT(hwmon_fan_input) #define HWMON_F_LABEL BIT(hwmon_fan_label) #define HWMON_F_MIN BIT(hwmon_fan_min) -- cgit v1.2.3 From 9e347728c4fe0f0661194243384ac9f61d7a5c73 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 12 Dec 2019 09:14:34 -0800 Subject: hwmon: (pmbus) Detect if chip is write protected If a chip is write protected, we can not change any limits, and we can not clear status flags. This may be the reason why clearing status flags is reported to not work for some chips. Detect the condition in the pmbus core. If the chip is write protected, set limit attributes as read-only, and set the flag indicating that the status flag should be ignored. Signed-off-by: Guenter Roeck --- include/linux/pmbus.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index 08468fca5ea2..1ea5bae708a1 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -8,6 +8,8 @@ #ifndef _PMBUS_H_ #define _PMBUS_H_ +#include + /* flags */ /* @@ -23,7 +25,14 @@ * communication errors for no explicable reason. For such chips, checking * the status register must be disabled. */ -#define PMBUS_SKIP_STATUS_CHECK (1 << 0) +#define PMBUS_SKIP_STATUS_CHECK BIT(0) + +/* + * PMBUS_WRITE_PROTECTED + * Set if the chip is write protected and write protection is not determined + * by the standard WRITE_PROTECT command. + */ +#define PMBUS_WRITE_PROTECTED BIT(1) struct pmbus_platform_data { u32 flags; /* Device specific flags */ -- cgit v1.2.3 From df2a4d94f1720e24643a9870a01a1c2895d13b20 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 4 Dec 2019 22:35:56 -0800 Subject: clk: zynqmp: Warn user if clock user are more than allowed Warn user if clock is used by more than allowed devices. This check is done by firmware and returns respective error code. Upon receiving error code for excessive user, warn user for the same. This change is done to restrict VPLL use count. It is assumed that VPLL is used by one user only. Signed-off-by: Michal Simek Signed-off-by: Rajan Vaja Link: https://lkml.kernel.org/r/1575527759-26452-4-git-send-email-rajan.vaja@xilinx.com Acked-by: Michal Simek Signed-off-by: Stephen Boyd --- include/linux/firmware/xlnx-zynqmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index e41ad9e37136..1827d30e86f1 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -89,6 +89,7 @@ enum pm_ret_status { XST_PM_INVALID_NODE, XST_PM_DOUBLE_REQ, XST_PM_ABORT_SUSPEND, + XST_PM_MULT_USER = 2008, }; enum pm_ioctl_id { -- cgit v1.2.3 From e942171bbb762977afaa1eb24a312c3bd56386a5 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 4 Dec 2019 22:35:57 -0800 Subject: clk: zynqmp: Add support for get max divider To achieve best possible rate, maximum limit of divider is required while computation. Get maximum supported divisor from firmware. To maintain backward compatibility assign maximum possible value(0xFFFF) if query for max divisor is not successful. Signed-off-by: Rajan Vaja Link: https://lkml.kernel.org/r/1575527759-26452-5-git-send-email-rajan.vaja@xilinx.com Acked-by: Michal Simek [sboyd@kernel.org: Remove else return and just return] Signed-off-by: Stephen Boyd --- include/linux/firmware/xlnx-zynqmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 1827d30e86f1..1b9549d02544 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -108,6 +108,7 @@ enum pm_query_id { PM_QID_CLOCK_GET_PARENTS, PM_QID_CLOCK_GET_ATTRIBUTES, PM_QID_CLOCK_GET_NUM_CLOCKS = 12, + PM_QID_CLOCK_GET_MAX_DIVISOR, }; enum zynqmp_pm_reset_action { -- cgit v1.2.3 From e81274cd6b5264809384066e09a5253708822522 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 21 Jan 2020 16:43:53 -0700 Subject: dmaengine: add support to dynamic register/unregister of channels With the channel registration routines broken out, now add support code to allow independent registering and unregistering of channels in a hotplug fashion. Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/157965023364.73301.7821862091077299040.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9cc0e70e7c35..f52f274773ed 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1521,6 +1521,10 @@ static inline int dmaengine_desc_free(struct dma_async_tx_descriptor *desc) int dma_async_device_register(struct dma_device *device); int dmaenginem_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); +int dma_async_device_channel_register(struct dma_device *device, + struct dma_chan *chan); +void dma_async_device_channel_unregister(struct dma_device *device, + struct dma_chan *chan); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); #define dma_request_channel(mask, x, y) \ __dma_request_channel(&(mask), x, y, NULL) -- cgit v1.2.3 From 71723a96b8b1367fefc18f60025dae792477d602 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 17 Jan 2020 16:30:56 +0100 Subject: dmaengine: Create symlinks between DMA channels and slaves MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently it is not easy to find out which DMA channels are in use, and which slave devices are using which channels. Fix this by creating two symlinks between the DMA channel and the actual slave device when a channel is requested: 1. A "slave" symlink from DMA channel to slave device, 2. A "dma:" symlink slave device to DMA channel. When the channel is released, the symlinks are removed again. The latter requires keeping track of the slave device and the channel name in the dma_chan structure. Note that this is limited to channel request functions for requesting an exclusive slave channel that take a device pointer (dma_request_chan() and dma_request_slave_channel*()). Signed-off-by: Geert Uytterhoeven Tested-by: Niklas Söderlund Link: https://lore.kernel.org/r/20200117153056.31363-1-geert+renesas@glider.be Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index f52f274773ed..fef69a9c5824 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -294,10 +294,12 @@ struct dma_router { /** * struct dma_chan - devices supply DMA channels, clients use them * @device: ptr to the dma device who supplies this channel, always !%NULL + * @slave: ptr to the device using this channel * @cookie: last cookie value returned to client * @completed_cookie: last completed cookie for this channel * @chan_id: channel ID for sysfs * @dev: class device for sysfs + * @name: backlink name for sysfs * @device_node: used to add this to the device chan list * @local: per-cpu pointer to a struct dma_chan_percpu * @client_count: how many clients are using this channel @@ -308,12 +310,14 @@ struct dma_router { */ struct dma_chan { struct dma_device *device; + struct device *slave; dma_cookie_t cookie; dma_cookie_t completed_cookie; /* sysfs */ int chan_id; struct dma_chan_dev *dev; + const char *name; struct list_head device_node; struct dma_chan_percpu __percpu *local; -- cgit v1.2.3 From 1b1c26b24a6e75d96967515e55fba6c9954d4009 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 20 Jan 2020 15:42:38 +0200 Subject: mfd: Rohm PMICs: Use platform_device_id to match MFD sub-devices Thanks to Stephen Boyd I today learned we can use platform_device_id to do device and module matching for MFD sub-devices! Do device matching using the platform_device_id instead of using explicit module_aliases to load modules and custom parent-data field to do module loading and sub-device matching. Cc: Stephen Boyd Signed-off-by: Matti Vaittinen Acked-by: Mark Brown Signed-off-by: Lee Jones --- include/linux/mfd/rohm-generic.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index bff15ac26f2c..922f88008232 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -4,7 +4,7 @@ #ifndef __LINUX_MFD_ROHM_H__ #define __LINUX_MFD_ROHM_H__ -enum { +enum rohm_chip_type { ROHM_CHIP_TYPE_BD71837 = 0, ROHM_CHIP_TYPE_BD71847, ROHM_CHIP_TYPE_BD70528, @@ -12,7 +12,6 @@ enum { }; struct rohm_regmap_dev { - unsigned int chip_type; struct device *dev; struct regmap *regmap; }; -- cgit v1.2.3 From 1c743ad523bb2f77a43a740a43c3b5bb9cbd82cd Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 20 Jan 2020 15:43:28 +0200 Subject: mfd: bd71828: Support ROHM BD71828 PMIC - core BD71828GW is a single-chip power management IC for battery-powered portable devices. The IC integrates 7 buck converters, 7 LDOs, and a 1500 mA single-cell linear charger. Also included is a Coulomb counter, a real-time clock (RTC), 3 GPO/regulator control pins, HALL input and a 32.768 kHz clock gate. Add MFD core driver providing interrupt controller facilities and i2c access to sub device drivers. Signed-off-by: Matti Vaittinen Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd71828.h | 425 +++++++++++++++++++++++++++++++++++++++ include/linux/mfd/rohm-generic.h | 1 + 2 files changed, 426 insertions(+) create mode 100644 include/linux/mfd/rohm-bd71828.h (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h new file mode 100644 index 000000000000..eb0557eb5314 --- /dev/null +++ b/include/linux/mfd/rohm-bd71828.h @@ -0,0 +1,425 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (C) 2019 ROHM Semiconductors */ + +#ifndef __LINUX_MFD_BD71828_H__ +#define __LINUX_MFD_BD71828_H__ + +#include + +/* Regulator IDs */ +enum { + BD71828_BUCK1, + BD71828_BUCK2, + BD71828_BUCK3, + BD71828_BUCK4, + BD71828_BUCK5, + BD71828_BUCK6, + BD71828_BUCK7, + BD71828_LDO1, + BD71828_LDO2, + BD71828_LDO3, + BD71828_LDO4, + BD71828_LDO5, + BD71828_LDO6, + BD71828_LDO_SNVS, + BD71828_REGULATOR_AMOUNT, +}; + +#define BD71828_BUCK1267_VOLTS 0xEF +#define BD71828_BUCK3_VOLTS 0x10 +#define BD71828_BUCK4_VOLTS 0x20 +#define BD71828_BUCK5_VOLTS 0x10 +#define BD71828_LDO_VOLTS 0x32 +/* LDO6 is fixed 1.8V voltage */ +#define BD71828_LDO_6_VOLTAGE 1800000 + +/* Registers and masks*/ + +/* MODE control */ +#define BD71828_REG_PS_CTRL_1 0x04 +#define BD71828_REG_PS_CTRL_2 0x05 +#define BD71828_REG_PS_CTRL_3 0x06 + +//#define BD71828_REG_SWRESET 0x06 +#define BD71828_MASK_RUN_LVL_CTRL 0x30 + +/* Regulator control masks */ + +#define BD71828_MASK_RAMP_DELAY 0x6 + +#define BD71828_MASK_RUN_EN 0x08 +#define BD71828_MASK_SUSP_EN 0x04 +#define BD71828_MASK_IDLE_EN 0x02 +#define BD71828_MASK_LPSR_EN 0x01 + +#define BD71828_MASK_RUN0_EN 0x01 +#define BD71828_MASK_RUN1_EN 0x02 +#define BD71828_MASK_RUN2_EN 0x04 +#define BD71828_MASK_RUN3_EN 0x08 + +#define BD71828_MASK_DVS_BUCK1_CTRL 0x10 +#define BD71828_DVS_BUCK1_CTRL_I2C 0 +#define BD71828_DVS_BUCK1_USE_RUNLVL 0x10 + +#define BD71828_MASK_DVS_BUCK2_CTRL 0x20 +#define BD71828_DVS_BUCK2_CTRL_I2C 0 +#define BD71828_DVS_BUCK2_USE_RUNLVL 0x20 + +#define BD71828_MASK_DVS_BUCK6_CTRL 0x40 +#define BD71828_DVS_BUCK6_CTRL_I2C 0 +#define BD71828_DVS_BUCK6_USE_RUNLVL 0x40 + +#define BD71828_MASK_DVS_BUCK7_CTRL 0x80 +#define BD71828_DVS_BUCK7_CTRL_I2C 0 +#define BD71828_DVS_BUCK7_USE_RUNLVL 0x80 + +#define BD71828_MASK_BUCK1267_VOLT 0xff +#define BD71828_MASK_BUCK3_VOLT 0x1f +#define BD71828_MASK_BUCK4_VOLT 0x3f +#define BD71828_MASK_BUCK5_VOLT 0x1f +#define BD71828_MASK_LDO_VOLT 0x3f + +/* Regulator control regs */ +#define BD71828_REG_BUCK1_EN 0x08 +#define BD71828_REG_BUCK1_CTRL 0x09 +#define BD71828_REG_BUCK1_MODE 0x0a +#define BD71828_REG_BUCK1_IDLE_VOLT 0x0b +#define BD71828_REG_BUCK1_SUSP_VOLT 0x0c +#define BD71828_REG_BUCK1_VOLT 0x0d + +#define BD71828_REG_BUCK2_EN 0x12 +#define BD71828_REG_BUCK2_CTRL 0x13 +#define BD71828_REG_BUCK2_MODE 0x14 +#define BD71828_REG_BUCK2_IDLE_VOLT 0x15 +#define BD71828_REG_BUCK2_SUSP_VOLT 0x16 +#define BD71828_REG_BUCK2_VOLT 0x17 + +#define BD71828_REG_BUCK3_EN 0x1c +#define BD71828_REG_BUCK3_MODE 0x1d +#define BD71828_REG_BUCK3_VOLT 0x1e + +#define BD71828_REG_BUCK4_EN 0x1f +#define BD71828_REG_BUCK4_MODE 0x20 +#define BD71828_REG_BUCK4_VOLT 0x21 + +#define BD71828_REG_BUCK5_EN 0x22 +#define BD71828_REG_BUCK5_MODE 0x23 +#define BD71828_REG_BUCK5_VOLT 0x24 + +#define BD71828_REG_BUCK6_EN 0x25 +#define BD71828_REG_BUCK6_CTRL 0x26 +#define BD71828_REG_BUCK6_MODE 0x27 +#define BD71828_REG_BUCK6_IDLE_VOLT 0x28 +#define BD71828_REG_BUCK6_SUSP_VOLT 0x29 +#define BD71828_REG_BUCK6_VOLT 0x2a + +#define BD71828_REG_BUCK7_EN 0x2f +#define BD71828_REG_BUCK7_CTRL 0x30 +#define BD71828_REG_BUCK7_MODE 0x31 +#define BD71828_REG_BUCK7_IDLE_VOLT 0x32 +#define BD71828_REG_BUCK7_SUSP_VOLT 0x33 +#define BD71828_REG_BUCK7_VOLT 0x34 + +#define BD71828_REG_LDO1_EN 0x39 +#define BD71828_REG_LDO1_VOLT 0x3a +#define BD71828_REG_LDO2_EN 0x3b +#define BD71828_REG_LDO2_VOLT 0x3c +#define BD71828_REG_LDO3_EN 0x3d +#define BD71828_REG_LDO3_VOLT 0x3e +#define BD71828_REG_LDO4_EN 0x3f +#define BD71828_REG_LDO4_VOLT 0x40 +#define BD71828_REG_LDO5_EN 0x41 +#define BD71828_REG_LDO5_VOLT 0x43 +#define BD71828_REG_LDO5_VOLT_OPT 0x42 +#define BD71828_REG_LDO6_EN 0x44 +//#define BD71828_REG_LDO6_VOLT 0x4 +#define BD71828_REG_LDO7_EN 0x45 +#define BD71828_REG_LDO7_VOLT 0x46 + +/* GPIO */ + +#define BD71828_GPIO_DRIVE_MASK 0x2 +#define BD71828_GPIO_OPEN_DRAIN 0x0 +#define BD71828_GPIO_PUSH_PULL 0x2 +#define BD71828_GPIO_OUT_HI 0x1 +#define BD71828_GPIO_OUT_LO 0x0 +#define BD71828_GPIO_OUT_MASK 0x1 + +#define BD71828_REG_GPIO_CTRL1 0x47 +#define BD71828_REG_GPIO_CTRL2 0x48 +#define BD71828_REG_GPIO_CTRL3 0x49 +#define BD71828_REG_IO_STAT 0xed + +/* RTC */ +#define BD71828_REG_RTC_SEC 0x4c +#define BD71828_REG_RTC_MINUTE 0x4d +#define BD71828_REG_RTC_HOUR 0x4e +#define BD71828_REG_RTC_WEEK 0x4f +#define BD71828_REG_RTC_DAY 0x50 +#define BD71828_REG_RTC_MONTH 0x51 +#define BD71828_REG_RTC_YEAR 0x52 + +#define BD71828_REG_RTC_ALM0_SEC 0x53 +#define BD71828_REG_RTC_ALM0_MINUTE 0x54 +#define BD71828_REG_RTC_ALM0_HOUR 0x55 +#define BD71828_REG_RTC_ALM0_WEEK 0x56 +#define BD71828_REG_RTC_ALM0_DAY 0x57 +#define BD71828_REG_RTC_ALM0_MONTH 0x58 +#define BD71828_REG_RTC_ALM0_YEAR 0x59 +#define BD71828_REG_RTC_ALM0_MASK 0x61 + +#define BD71828_REG_RTC_ALM1_SEC 0x5a +#define BD71828_REG_RTC_ALM1_MINUTE 0x5b +#define BD71828_REG_RTC_ALM1_HOUR 0x5c +#define BD71828_REG_RTC_ALM1_WEEK 0x5d +#define BD71828_REG_RTC_ALM1_DAY 0x5e +#define BD71828_REG_RTC_ALM1_MONTH 0x5f +#define BD71828_REG_RTC_ALM1_YEAR 0x60 +#define BD71828_REG_RTC_ALM1_MASK 0x62 + +#define BD71828_REG_RTC_ALM2 0x63 + +/* Charger/Battey */ +#define BD71828_REG_CHG_STATE 0x65 +#define BD71828_REG_CHG_FULL 0xd2 + +/* CLK */ +#define BD71828_REG_OUT32K 0x4B + +/* LEDs */ +#define BD71828_REG_LED_CTRL 0x4A +#define BD71828_MASK_LED_AMBER 0x80 +#define BD71828_MASK_LED_GREEN 0x40 +#define BD71828_LED_ON 0xff +#define BD71828_LED_OFF 0x0 + +/* IRQ registers */ +#define BD71828_REG_INT_MASK_BUCK 0xd3 +#define BD71828_REG_INT_MASK_DCIN1 0xd4 +#define BD71828_REG_INT_MASK_DCIN2 0xd5 +#define BD71828_REG_INT_MASK_VSYS 0xd6 +#define BD71828_REG_INT_MASK_CHG 0xd7 +#define BD71828_REG_INT_MASK_BAT 0xd8 +#define BD71828_REG_INT_MASK_BAT_MON1 0xd9 +#define BD71828_REG_INT_MASK_BAT_MON2 0xda +#define BD71828_REG_INT_MASK_BAT_MON3 0xdb +#define BD71828_REG_INT_MASK_BAT_MON4 0xdc +#define BD71828_REG_INT_MASK_TEMP 0xdd +#define BD71828_REG_INT_MASK_RTC 0xde + + +#define BD71828_REG_INT_MAIN 0xdf +#define BD71828_REG_INT_BUCK 0xe0 +#define BD71828_REG_INT_DCIN1 0xe1 +#define BD71828_REG_INT_DCIN2 0xe2 +#define BD71828_REG_INT_VSYS 0xe3 +#define BD71828_REG_INT_CHG 0xe4 +#define BD71828_REG_INT_BAT 0xe5 +#define BD71828_REG_INT_BAT_MON1 0xe6 +#define BD71828_REG_INT_BAT_MON2 0xe7 +#define BD71828_REG_INT_BAT_MON3 0xe8 +#define BD71828_REG_INT_BAT_MON4 0xe9 +#define BD71828_REG_INT_TEMP 0xea +#define BD71828_REG_INT_RTC 0xeb +#define BD71828_REG_INT_UPDATE 0xec + +#define BD71828_MAX_REGISTER BD71828_REG_IO_STAT + +/* Masks for main IRQ register bits */ +enum { + BD71828_INT_BUCK, +#define BD71828_INT_BUCK_MASK BIT(BD71828_INT_BUCK) + BD71828_INT_DCIN, +#define BD71828_INT_DCIN_MASK BIT(BD71828_INT_DCIN) + BD71828_INT_VSYS, +#define BD71828_INT_VSYS_MASK BIT(BD71828_INT_VSYS) + BD71828_INT_CHG, +#define BD71828_INT_CHG_MASK BIT(BD71828_INT_CHG) + BD71828_INT_BAT, +#define BD71828_INT_BAT_MASK BIT(BD71828_INT_BAT) + BD71828_INT_BAT_MON, +#define BD71828_INT_BAT_MON_MASK BIT(BD71828_INT_BAT_MON) + BD71828_INT_TEMP, +#define BD71828_INT_TEMP_MASK BIT(BD71828_INT_TEMP) + BD71828_INT_RTC, +#define BD71828_INT_RTC_MASK BIT(BD71828_INT_RTC) +}; + +/* Interrupts */ +enum { + /* BUCK reg interrupts */ + BD71828_INT_BUCK1_OCP, + BD71828_INT_BUCK2_OCP, + BD71828_INT_BUCK3_OCP, + BD71828_INT_BUCK4_OCP, + BD71828_INT_BUCK5_OCP, + BD71828_INT_BUCK6_OCP, + BD71828_INT_BUCK7_OCP, + BD71828_INT_PGFAULT, + /* DCIN1 interrupts */ + BD71828_INT_DCIN_DET, + BD71828_INT_DCIN_RMV, + BD71828_INT_CLPS_OUT, + BD71828_INT_CLPS_IN, + /* DCIN2 interrupts */ + BD71828_INT_DCIN_MON_RES, + BD71828_INT_DCIN_MON_DET, + BD71828_INT_LONGPUSH, + BD71828_INT_MIDPUSH, + BD71828_INT_SHORTPUSH, + BD71828_INT_PUSH, + BD71828_INT_WDOG, + BD71828_INT_SWRESET, + /* Vsys */ + BD71828_INT_VSYS_UV_RES, + BD71828_INT_VSYS_UV_DET, + BD71828_INT_VSYS_LOW_RES, + BD71828_INT_VSYS_LOW_DET, + BD71828_INT_VSYS_HALL_IN, + BD71828_INT_VSYS_HALL_TOGGLE, + BD71828_INT_VSYS_MON_RES, + BD71828_INT_VSYS_MON_DET, + /* Charger */ + BD71828_INT_CHG_DCIN_ILIM, + BD71828_INT_CHG_TOPOFF_TO_DONE, + BD71828_INT_CHG_WDG_TEMP, + BD71828_INT_CHG_WDG_TIME, + BD71828_INT_CHG_RECHARGE_RES, + BD71828_INT_CHG_RECHARGE_DET, + BD71828_INT_CHG_RANGED_TEMP_TRANSITION, + BD71828_INT_CHG_STATE_TRANSITION, + /* Battery */ + BD71828_INT_BAT_TEMP_NORMAL, + BD71828_INT_BAT_TEMP_ERANGE, + BD71828_INT_BAT_TEMP_WARN, + BD71828_INT_BAT_REMOVED, + BD71828_INT_BAT_DETECTED, + BD71828_INT_THERM_REMOVED, + BD71828_INT_THERM_DETECTED, + /* Battery Mon 1 */ + BD71828_INT_BAT_DEAD, + BD71828_INT_BAT_SHORTC_RES, + BD71828_INT_BAT_SHORTC_DET, + BD71828_INT_BAT_LOW_VOLT_RES, + BD71828_INT_BAT_LOW_VOLT_DET, + BD71828_INT_BAT_OVER_VOLT_RES, + BD71828_INT_BAT_OVER_VOLT_DET, + /* Battery Mon 2 */ + BD71828_INT_BAT_MON_RES, + BD71828_INT_BAT_MON_DET, + /* Battery Mon 3 (Coulomb counter) */ + BD71828_INT_BAT_CC_MON1, + BD71828_INT_BAT_CC_MON2, + BD71828_INT_BAT_CC_MON3, + /* Battery Mon 4 */ + BD71828_INT_BAT_OVER_CURR_1_RES, + BD71828_INT_BAT_OVER_CURR_1_DET, + BD71828_INT_BAT_OVER_CURR_2_RES, + BD71828_INT_BAT_OVER_CURR_2_DET, + BD71828_INT_BAT_OVER_CURR_3_RES, + BD71828_INT_BAT_OVER_CURR_3_DET, + /* Temperature */ + BD71828_INT_TEMP_BAT_LOW_RES, + BD71828_INT_TEMP_BAT_LOW_DET, + BD71828_INT_TEMP_BAT_HI_RES, + BD71828_INT_TEMP_BAT_HI_DET, + BD71828_INT_TEMP_CHIP_OVER_125_RES, + BD71828_INT_TEMP_CHIP_OVER_125_DET, + BD71828_INT_TEMP_CHIP_OVER_VF_DET, + BD71828_INT_TEMP_CHIP_OVER_VF_RES, + /* RTC Alarm */ + BD71828_INT_RTC0, + BD71828_INT_RTC1, + BD71828_INT_RTC2, +}; + +#define BD71828_INT_BUCK1_OCP_MASK 0x1 +#define BD71828_INT_BUCK2_OCP_MASK 0x2 +#define BD71828_INT_BUCK3_OCP_MASK 0x4 +#define BD71828_INT_BUCK4_OCP_MASK 0x8 +#define BD71828_INT_BUCK5_OCP_MASK 0x10 +#define BD71828_INT_BUCK6_OCP_MASK 0x20 +#define BD71828_INT_BUCK7_OCP_MASK 0x40 +#define BD71828_INT_PGFAULT_MASK 0x80 + +#define BD71828_INT_DCIN_DET_MASK 0x1 +#define BD71828_INT_DCIN_RMV_MASK 0x2 +#define BD71828_INT_CLPS_OUT_MASK 0x4 +#define BD71828_INT_CLPS_IN_MASK 0x8 + /* DCIN2 interrupts */ +#define BD71828_INT_DCIN_MON_RES_MASK 0x1 +#define BD71828_INT_DCIN_MON_DET_MASK 0x2 +#define BD71828_INT_LONGPUSH_MASK 0x4 +#define BD71828_INT_MIDPUSH_MASK 0x8 +#define BD71828_INT_SHORTPUSH_MASK 0x10 +#define BD71828_INT_PUSH_MASK 0x20 +#define BD71828_INT_WDOG_MASK 0x40 +#define BD71828_INT_SWRESET_MASK 0x80 + /* Vsys */ +#define BD71828_INT_VSYS_UV_RES_MASK 0x1 +#define BD71828_INT_VSYS_UV_DET_MASK 0x2 +#define BD71828_INT_VSYS_LOW_RES_MASK 0x4 +#define BD71828_INT_VSYS_LOW_DET_MASK 0x8 +#define BD71828_INT_VSYS_HALL_IN_MASK 0x10 +#define BD71828_INT_VSYS_HALL_TOGGLE_MASK 0x20 +#define BD71828_INT_VSYS_MON_RES_MASK 0x40 +#define BD71828_INT_VSYS_MON_DET_MASK 0x80 + /* Charger */ +#define BD71828_INT_CHG_DCIN_ILIM_MASK 0x1 +#define BD71828_INT_CHG_TOPOFF_TO_DONE_MASK 0x2 +#define BD71828_INT_CHG_WDG_TEMP_MASK 0x4 +#define BD71828_INT_CHG_WDG_TIME_MASK 0x8 +#define BD71828_INT_CHG_RECHARGE_RES_MASK 0x10 +#define BD71828_INT_CHG_RECHARGE_DET_MASK 0x20 +#define BD71828_INT_CHG_RANGED_TEMP_TRANSITION_MASK 0x40 +#define BD71828_INT_CHG_STATE_TRANSITION_MASK 0x80 + /* Battery */ +#define BD71828_INT_BAT_TEMP_NORMAL_MASK 0x1 +#define BD71828_INT_BAT_TEMP_ERANGE_MASK 0x2 +#define BD71828_INT_BAT_TEMP_WARN_MASK 0x4 +#define BD71828_INT_BAT_REMOVED_MASK 0x10 +#define BD71828_INT_BAT_DETECTED_MASK 0x20 +#define BD71828_INT_THERM_REMOVED_MASK 0x40 +#define BD71828_INT_THERM_DETECTED_MASK 0x80 + /* Battery Mon 1 */ +#define BD71828_INT_BAT_DEAD_MASK 0x2 +#define BD71828_INT_BAT_SHORTC_RES_MASK 0x4 +#define BD71828_INT_BAT_SHORTC_DET_MASK 0x8 +#define BD71828_INT_BAT_LOW_VOLT_RES_MASK 0x10 +#define BD71828_INT_BAT_LOW_VOLT_DET_MASK 0x20 +#define BD71828_INT_BAT_OVER_VOLT_RES_MASK 0x40 +#define BD71828_INT_BAT_OVER_VOLT_DET_MASK 0x80 + /* Battery Mon 2 */ +#define BD71828_INT_BAT_MON_RES_MASK 0x1 +#define BD71828_INT_BAT_MON_DET_MASK 0x2 + /* Battery Mon 3 (Coulomb counter) */ +#define BD71828_INT_BAT_CC_MON1_MASK 0x1 +#define BD71828_INT_BAT_CC_MON2_MASK 0x2 +#define BD71828_INT_BAT_CC_MON3_MASK 0x4 + /* Battery Mon 4 */ +#define BD71828_INT_BAT_OVER_CURR_1_RES_MASK 0x1 +#define BD71828_INT_BAT_OVER_CURR_1_DET_MASK 0x2 +#define BD71828_INT_BAT_OVER_CURR_2_RES_MASK 0x4 +#define BD71828_INT_BAT_OVER_CURR_2_DET_MASK 0x8 +#define BD71828_INT_BAT_OVER_CURR_3_RES_MASK 0x10 +#define BD71828_INT_BAT_OVER_CURR_3_DET_MASK 0x20 + /* Temperature */ +#define BD71828_INT_TEMP_BAT_LOW_RES_MASK 0x1 +#define BD71828_INT_TEMP_BAT_LOW_DET_MASK 0x2 +#define BD71828_INT_TEMP_BAT_HI_RES_MASK 0x4 +#define BD71828_INT_TEMP_BAT_HI_DET_MASK 0x8 +#define BD71828_INT_TEMP_CHIP_OVER_125_RES_MASK 0x10 +#define BD71828_INT_TEMP_CHIP_OVER_125_DET_MASK 0x20 +#define BD71828_INT_TEMP_CHIP_OVER_VF_RES_MASK 0x40 +#define BD71828_INT_TEMP_CHIP_OVER_VF_DET_MASK 0x80 + /* RTC Alarm */ +#define BD71828_INT_RTC0_MASK 0x1 +#define BD71828_INT_RTC1_MASK 0x2 +#define BD71828_INT_RTC2_MASK 0x4 + +#define BD71828_OUT32K_EN 0x1 +#define BD71828_OUT_TYPE_MASK 0x2 +#define BD71828_OUT_TYPE_OPEN_DRAIN 0x0 +#define BD71828_OUT_TYPE_CMOS 0x2 + +#endif /* __LINUX_MFD_BD71828_H__ */ diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 922f88008232..ff3dd7578fd3 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -8,6 +8,7 @@ enum rohm_chip_type { ROHM_CHIP_TYPE_BD71837 = 0, ROHM_CHIP_TYPE_BD71847, ROHM_CHIP_TYPE_BD70528, + ROHM_CHIP_TYPE_BD71828, ROHM_CHIP_TYPE_AMOUNT }; -- cgit v1.2.3 From ae866dec742687b0bff407013b91badba524f7ee Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 20 Jan 2020 15:44:19 +0200 Subject: clk: bd718x7: Support ROHM BD71828 clk block BD71828GW is a single-chip power management IC for battery-powered portable devices. Add support for controlling BD71828 clk using bd718x7 driver. Signed-off-by: Matti Vaittinen Acked-by: Stephen Boyd Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd70528.h | 6 ------ include/linux/mfd/rohm-bd71828.h | 4 ---- include/linux/mfd/rohm-bd718x7.h | 6 ------ 3 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h index 1013e60c5b25..2ad2320d0a96 100644 --- a/include/linux/mfd/rohm-bd70528.h +++ b/include/linux/mfd/rohm-bd70528.h @@ -89,10 +89,6 @@ struct bd70528_data { #define BD70528_REG_GPIO3_OUT 0x52 #define BD70528_REG_GPIO4_OUT 0x54 -/* clk control */ - -#define BD70528_REG_CLK_OUT 0x2c - /* RTC */ #define BD70528_REG_RTC_COUNT_H 0x2d @@ -309,8 +305,6 @@ enum { #define BD70528_GPIO_IN_STATE_BASE 1 -#define BD70528_CLK_OUT_EN_MASK 0x1 - /* RTC masks to mask out reserved bits */ #define BD70528_MASK_RTC_SEC 0x7f diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index eb0557eb5314..d013e03f742d 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -183,9 +183,6 @@ enum { #define BD71828_REG_CHG_STATE 0x65 #define BD71828_REG_CHG_FULL 0xd2 -/* CLK */ -#define BD71828_REG_OUT32K 0x4B - /* LEDs */ #define BD71828_REG_LED_CTRL 0x4A #define BD71828_MASK_LED_AMBER 0x80 @@ -417,7 +414,6 @@ enum { #define BD71828_INT_RTC1_MASK 0x2 #define BD71828_INT_RTC2_MASK 0x4 -#define BD71828_OUT32K_EN 0x1 #define BD71828_OUT_TYPE_MASK 0x2 #define BD71828_OUT_TYPE_OPEN_DRAIN 0x0 #define BD71828_OUT_TYPE_CMOS 0x2 diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index 7f2dbde402a1..bee2474a8f9f 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -191,12 +191,6 @@ enum { #define IRQ_ON_REQ 0x02 #define IRQ_STBY_REQ 0x01 -/* BD718XX_REG_OUT32K bits */ -#define BD718XX_OUT32K_EN 0x01 - -/* BD7183XX gated clock rate */ -#define BD718XX_CLK_RATE 32768 - /* ROHM BD718XX irqs */ enum { BD718XX_INT_STBY_REQ, -- cgit v1.2.3 From 21b72156ede8b7da0367c6338574c1bc40439157 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 20 Jan 2020 15:44:45 +0200 Subject: regulator: bd718x7: Split driver to common and bd718x7 specific parts Few ROHM PMICs allow setting the voltage states for different system states like RUN, IDLE, SUSPEND and LPSR. States are then changed via SoC specific mechanisms. bd718x7 driver implemented device-tree parsing functions for these state specific voltages. The parsing functions can be re-used by other ROHM chip drivers like bd71828. Split the generic functions from bd718x7-regulator.c to rohm-regulator.c and export them for other modules to use. Signed-off-by: Matti Vaittinen Acked-by: Mark Brown Signed-off-by: Lee Jones --- include/linux/mfd/rohm-generic.h | 66 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index ff3dd7578fd3..4283b5b33e04 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -4,6 +4,9 @@ #ifndef __LINUX_MFD_ROHM_H__ #define __LINUX_MFD_ROHM_H__ +#include +#include + enum rohm_chip_type { ROHM_CHIP_TYPE_BD71837 = 0, ROHM_CHIP_TYPE_BD71847, @@ -17,4 +20,67 @@ struct rohm_regmap_dev { struct regmap *regmap; }; +enum { + ROHM_DVS_LEVEL_UNKNOWN, + ROHM_DVS_LEVEL_RUN, + ROHM_DVS_LEVEL_IDLE, + ROHM_DVS_LEVEL_SUSPEND, + ROHM_DVS_LEVEL_LPSR, + ROHM_DVS_LEVEL_MAX = ROHM_DVS_LEVEL_LPSR, +}; + +/** + * struct rohm_dvs_config - dynamic voltage scaling register descriptions + * + * @level_map: bitmap representing supported run-levels for this + * regulator + * @run_reg: register address for regulator config at 'run' state + * @run_mask: value mask for regulator voltages at 'run' state + * @run_on_mask: enable mask for regulator at 'run' state + * @idle_reg: register address for regulator config at 'idle' state + * @idle_mask: value mask for regulator voltages at 'idle' state + * @idle_on_mask: enable mask for regulator at 'idle' state + * @suspend_reg: register address for regulator config at 'suspend' state + * @suspend_mask: value mask for regulator voltages at 'suspend' state + * @suspend_on_mask: enable mask for regulator at 'suspend' state + * @lpsr_reg: register address for regulator config at 'lpsr' state + * @lpsr_mask: value mask for regulator voltages at 'lpsr' state + * @lpsr_on_mask: enable mask for regulator at 'lpsr' state + * + * Description of ROHM PMICs voltage configuration registers for different + * system states. This is used to correctly configure the PMIC at startup + * based on values read from DT. + */ +struct rohm_dvs_config { + uint64_t level_map; + unsigned int run_reg; + unsigned int run_mask; + unsigned int run_on_mask; + unsigned int idle_reg; + unsigned int idle_mask; + unsigned int idle_on_mask; + unsigned int suspend_reg; + unsigned int suspend_mask; + unsigned int suspend_on_mask; + unsigned int lpsr_reg; + unsigned int lpsr_mask; + unsigned int lpsr_on_mask; +}; + +#if IS_ENABLED(CONFIG_REGULATOR_ROHM) +int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, + struct device_node *np, + const struct regulator_desc *desc, + struct regmap *regmap); + +#else +static inline int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, + struct device_node *np, + const struct regulator_desc *desc, + struct regmap *regmap) +{ + return 0; +} +#endif + #endif -- cgit v1.2.3 From 6c883472e1c11cb05561b6dd0c28bb037c2bf2de Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 20 Jan 2020 15:45:11 +0200 Subject: mfd: bd70528: Fix hour register mask When RTC is used in 24H mode (and it is by this driver) the maximum hour value is 24 in BCD. This occupies bits [5:0] - which means correct mask for HOUR register is 0x3f not 0x1f. Fix the mask Fixes: 32a4a4ebf768 ("rtc: bd70528: Initial support for ROHM bd70528 RTC") Signed-off-by: Matti Vaittinen Acked-by: Alexandre Belloni Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd70528.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h index 2ad2320d0a96..edae6f7afd8e 100644 --- a/include/linux/mfd/rohm-bd70528.h +++ b/include/linux/mfd/rohm-bd70528.h @@ -311,7 +311,7 @@ enum { #define BD70528_MASK_RTC_MINUTE 0x7f #define BD70528_MASK_RTC_HOUR_24H 0x80 #define BD70528_MASK_RTC_HOUR_PM 0x20 -#define BD70528_MASK_RTC_HOUR 0x1f +#define BD70528_MASK_RTC_HOUR 0x3f #define BD70528_MASK_RTC_DAY 0x3f #define BD70528_MASK_RTC_WEEK 0x07 #define BD70528_MASK_RTC_MONTH 0x1f -- cgit v1.2.3 From fe5a591b7814ffbc90aff661aeb8264937002f54 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 20 Jan 2020 15:45:36 +0200 Subject: rtc: bd70528: add BD71828 support ROHM BD71828 PMIC RTC block is from many parts similar to one on BD70528. Support BD71828 RTC using BD70528 RTC driver and avoid re-inventing the wheel. Signed-off-by: Matti Vaittinen Acked-by: Alexandre Belloni Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd70528.h | 13 +------------ include/linux/mfd/rohm-bd71828.h | 4 +++- include/linux/mfd/rohm-shared.h | 21 +++++++++++++++++++++ 3 files changed, 25 insertions(+), 13 deletions(-) create mode 100644 include/linux/mfd/rohm-shared.h (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h index edae6f7afd8e..a57af878fd0c 100644 --- a/include/linux/mfd/rohm-bd70528.h +++ b/include/linux/mfd/rohm-bd70528.h @@ -7,6 +7,7 @@ #include #include #include +#include #include enum { @@ -307,17 +308,6 @@ enum { /* RTC masks to mask out reserved bits */ -#define BD70528_MASK_RTC_SEC 0x7f -#define BD70528_MASK_RTC_MINUTE 0x7f -#define BD70528_MASK_RTC_HOUR_24H 0x80 -#define BD70528_MASK_RTC_HOUR_PM 0x20 -#define BD70528_MASK_RTC_HOUR 0x3f -#define BD70528_MASK_RTC_DAY 0x3f -#define BD70528_MASK_RTC_WEEK 0x07 -#define BD70528_MASK_RTC_MONTH 0x1f -#define BD70528_MASK_RTC_YEAR 0xff -#define BD70528_MASK_RTC_COUNT_L 0x7f - #define BD70528_MASK_ELAPSED_TIMER_EN 0x1 /* Mask second, min and hour fields * HW would support ALM irq for over 24h @@ -326,7 +316,6 @@ enum { * wake-up we limit ALM to 24H and only * unmask sec, min and hour */ -#define BD70528_MASK_ALM_EN 0x7 #define BD70528_MASK_WAKE_EN 0x1 /* WDT masks */ diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index d013e03f742d..017a4c01cb31 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -5,6 +5,7 @@ #define __LINUX_MFD_BD71828_H__ #include +#include /* Regulator IDs */ enum { @@ -160,6 +161,7 @@ enum { #define BD71828_REG_RTC_YEAR 0x52 #define BD71828_REG_RTC_ALM0_SEC 0x53 +#define BD71828_REG_RTC_ALM_START BD71828_REG_RTC_ALM0_SEC #define BD71828_REG_RTC_ALM0_MINUTE 0x54 #define BD71828_REG_RTC_ALM0_HOUR 0x55 #define BD71828_REG_RTC_ALM0_WEEK 0x56 @@ -178,6 +180,7 @@ enum { #define BD71828_REG_RTC_ALM1_MASK 0x62 #define BD71828_REG_RTC_ALM2 0x63 +#define BD71828_REG_RTC_START BD71828_REG_RTC_SEC /* Charger/Battey */ #define BD71828_REG_CHG_STATE 0x65 @@ -204,7 +207,6 @@ enum { #define BD71828_REG_INT_MASK_TEMP 0xdd #define BD71828_REG_INT_MASK_RTC 0xde - #define BD71828_REG_INT_MAIN 0xdf #define BD71828_REG_INT_BUCK 0xe0 #define BD71828_REG_INT_DCIN1 0xe1 diff --git a/include/linux/mfd/rohm-shared.h b/include/linux/mfd/rohm-shared.h new file mode 100644 index 000000000000..53dd7f638bfd --- /dev/null +++ b/include/linux/mfd/rohm-shared.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (C) 2020 ROHM Semiconductors */ + + +#ifndef __LINUX_MFD_ROHM_SHARED_H__ +#define __LINUX_MFD_ROHM_SHARED_H__ + +/* RTC definitions shared between BD70528 and BD71828 */ + +#define BD70528_MASK_RTC_SEC 0x7f +#define BD70528_MASK_RTC_MINUTE 0x7f +#define BD70528_MASK_RTC_HOUR_24H 0x80 +#define BD70528_MASK_RTC_HOUR_PM 0x20 +#define BD70528_MASK_RTC_HOUR 0x3f +#define BD70528_MASK_RTC_DAY 0x3f +#define BD70528_MASK_RTC_WEEK 0x07 +#define BD70528_MASK_RTC_MONTH 0x1f +#define BD70528_MASK_RTC_YEAR 0xff +#define BD70528_MASK_ALM_EN 0x7 + +#endif /* __LINUX_MFD_ROHM_SHARED_H__ */ -- cgit v1.2.3 From f41810921bdca37161a63f689cdcb36155f0fad6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 28 Dec 2019 23:26:14 +0100 Subject: mfd: dbx500-prcmu: Drop set_display_clocks() The display clocks are handled by the generic clock framework since ages, this code is completely unused and misleading. Delete it. Cc: Stephan Gerhold Cc: Ulf Hansson Signed-off-by: Linus Walleij Signed-off-by: Lee Jones --- include/linux/mfd/db8500-prcmu.h | 6 ------ include/linux/mfd/dbx500-prcmu.h | 10 ---------- 2 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h index 1fc75d2b4a38..7d0c442e0c25 100644 --- a/include/linux/mfd/db8500-prcmu.h +++ b/include/linux/mfd/db8500-prcmu.h @@ -525,7 +525,6 @@ u8 db8500_prcmu_get_power_state_result(void); void db8500_prcmu_enable_wakeups(u32 wakeups); int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state); int db8500_prcmu_request_clock(u8 clock, bool enable); -int db8500_prcmu_set_display_clocks(void); int db8500_prcmu_disable_dsipll(void); int db8500_prcmu_enable_dsipll(void); void db8500_prcmu_config_abb_event_readout(u32 abb_events); @@ -682,11 +681,6 @@ static inline int db8500_prcmu_request_clock(u8 clock, bool enable) return 0; } -static inline int db8500_prcmu_set_display_clocks(void) -{ - return 0; -} - static inline int db8500_prcmu_disable_dsipll(void) { return 0; diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index e2571040c7e8..812b6c3c4ef6 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -321,11 +321,6 @@ static inline bool prcmu_is_ac_wake_requested(void) return db8500_prcmu_is_ac_wake_requested(); } -static inline int prcmu_set_display_clocks(void) -{ - return db8500_prcmu_set_display_clocks(); -} - static inline int prcmu_disable_dsipll(void) { return db8500_prcmu_disable_dsipll(); @@ -511,11 +506,6 @@ static inline bool prcmu_is_ac_wake_requested(void) return false; } -static inline int prcmu_set_display_clocks(void) -{ - return 0; -} - static inline int prcmu_disable_dsipll(void) { return 0; -- cgit v1.2.3 From 2cce09eb11228386260a1b73133aee41f4bb33b1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 28 Dec 2019 23:26:15 +0100 Subject: mfd: dbx500-prcmu: Drop DSI pll clock functions The DSI PLLs are handled by the generic clock framework since ages, this code is completely unused and misleading. Delete it. Cc: Stephan Gerhold Cc: Ulf Hansson Signed-off-by: Linus Walleij Signed-off-by: Lee Jones --- include/linux/mfd/db8500-prcmu.h | 12 ------------ include/linux/mfd/dbx500-prcmu.h | 20 -------------------- 2 files changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h index 7d0c442e0c25..4b63d3ecdcff 100644 --- a/include/linux/mfd/db8500-prcmu.h +++ b/include/linux/mfd/db8500-prcmu.h @@ -525,8 +525,6 @@ u8 db8500_prcmu_get_power_state_result(void); void db8500_prcmu_enable_wakeups(u32 wakeups); int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state); int db8500_prcmu_request_clock(u8 clock, bool enable); -int db8500_prcmu_disable_dsipll(void); -int db8500_prcmu_enable_dsipll(void); void db8500_prcmu_config_abb_event_readout(u32 abb_events); void db8500_prcmu_get_abb_event_buffer(void __iomem **buf); int db8500_prcmu_config_esram0_deep_sleep(u8 state); @@ -681,16 +679,6 @@ static inline int db8500_prcmu_request_clock(u8 clock, bool enable) return 0; } -static inline int db8500_prcmu_disable_dsipll(void) -{ - return 0; -} - -static inline int db8500_prcmu_enable_dsipll(void) -{ - return 0; -} - static inline int db8500_prcmu_config_esram0_deep_sleep(u8 state) { return 0; diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index 812b6c3c4ef6..e6ee2ec35de9 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -321,16 +321,6 @@ static inline bool prcmu_is_ac_wake_requested(void) return db8500_prcmu_is_ac_wake_requested(); } -static inline int prcmu_disable_dsipll(void) -{ - return db8500_prcmu_disable_dsipll(); -} - -static inline int prcmu_enable_dsipll(void) -{ - return db8500_prcmu_enable_dsipll(); -} - static inline int prcmu_config_esram0_deep_sleep(u8 state) { return db8500_prcmu_config_esram0_deep_sleep(state); @@ -506,16 +496,6 @@ static inline bool prcmu_is_ac_wake_requested(void) return false; } -static inline int prcmu_disable_dsipll(void) -{ - return 0; -} - -static inline int prcmu_enable_dsipll(void) -{ - return 0; -} - static inline int prcmu_config_esram0_deep_sleep(u8 state) { return 0; -- cgit v1.2.3 From 6a24f567af4accef6d73b0be407227c537b94a1f Mon Sep 17 00:00:00 2001 From: Orson Zhai Date: Tue, 21 Jan 2020 15:09:38 +0800 Subject: mfd: syscon: Add arguments support for syscon reference There are a lot of similar global registers being used across multiple SoCs from Unisoc. But most of these registers are assigned with different offset for different SoCs. It is hard to handle all of them in an all-in-one kernel image. Add a helper function to get regmap with arguments where we could put some extra information such as the offset value. Signed-off-by: Orson Zhai Tested-by: Baolin Wang Reviewed-by: Arnd Bergmann Signed-off-by: Lee Jones --- include/linux/mfd/syscon.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index 112dc66262cc..714cab1e09d3 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -23,6 +23,11 @@ extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s); extern struct regmap *syscon_regmap_lookup_by_phandle( struct device_node *np, const char *property); +extern struct regmap *syscon_regmap_lookup_by_phandle_args( + struct device_node *np, + const char *property, + int arg_count, + unsigned int *out_args); #else static inline struct regmap *device_node_to_regmap(struct device_node *np) { @@ -45,6 +50,15 @@ static inline struct regmap *syscon_regmap_lookup_by_phandle( { return ERR_PTR(-ENOTSUPP); } + +static struct regmap *syscon_regmap_lookup_by_phandle_args( + struct device_node *np, + const char *property, + int arg_count, + unsigned int *out_args) +{ + return ERR_PTR(-ENOTSUPP); +} #endif #endif /* __LINUX_MFD_SYSCON_H__ */ -- cgit v1.2.3 From fe931f12277186d1a9d38ba6729b42e8edb68988 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 18 Dec 2019 13:55:08 -0800 Subject: KVM: Remove kvm_arch_vcpu_free() declaration Remove KVM's declaration of kvm_arch_vcpu_free() now that the function is gone from all architectures (several architectures were relying on the forward declaration). Acked-by: Christoffer Dall Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5e2ec7e295db..4f7c8e2f378d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -872,7 +872,6 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu); void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id); -- cgit v1.2.3 From 897cc38eaab96d006ab17edd0f50a2f432f584cf Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 18 Dec 2019 13:55:09 -0800 Subject: KVM: Add kvm_arch_vcpu_precreate() to handle pre-allocation issues Add a pre-allocation arch hook to handle checks that are currently done by arch specific code prior to allocating the vCPU object. This paves the way for moving the allocation to common KVM code. Acked-by: Christoffer Dall Signed-off-by: Sean Christopherson Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4f7c8e2f378d..59ac53423361 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -874,6 +874,7 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id); int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 4543bdc08857e8026475a477e7ba88e461f38271 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 18 Dec 2019 13:55:14 -0800 Subject: KVM: Introduce kvm_vcpu_destroy() Add kvm_vcpu_destroy() and wire up all architectures to call the common function instead of their arch specific implementation. The common destruction function will be used by future patches to move allocation and initialization of vCPUs to common KVM code, i.e. to free resources that are allocated by arch agnostic code. No functional change intended. Acked-by: Christoffer Dall Signed-off-by: Sean Christopherson Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 59ac53423361..432827ab7623 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -581,6 +581,7 @@ static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); +void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 5dcdc43e24a1810d3c3f4959af3d0c8e0026d863 Mon Sep 17 00:00:00 2001 From: Jiufei Xue Date: Wed, 20 Nov 2019 17:45:25 +0800 Subject: vfs: add vfs_iocb_iter_[read|write] helper functions This doesn't cause any behavior changes and will be used by overlay async IO implementation. Signed-off-by: Jiufei Xue Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..28315a286bab 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2078,6 +2078,18 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) }; } +static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, + struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + .ki_flags = kiocb_src->ki_flags, + .ki_hint = kiocb_src->ki_hint, + .ki_ioprio = kiocb_src->ki_ioprio, + .ki_pos = kiocb_src->ki_pos, + }; +} + /* * Inode state bits. Protected by inode->i_lock * @@ -3108,6 +3120,10 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); +ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, + struct iov_iter *iter); +ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, + struct iov_iter *iter); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); -- cgit v1.2.3 From eda7acddf8080bb2d022a8d4b8b2345eb80c63ec Mon Sep 17 00:00:00 2001 From: Peter Krystad Date: Tue, 21 Jan 2020 16:56:16 -0800 Subject: mptcp: Handle MPTCP TCP options Add hooks to parse and format the MP_CAPABLE option. This option is handled according to MPTCP version 0 (RFC6824). MPTCP version 1 MP_CAPABLE (RFC6824bis/RFC8684) will be added later in coordination with related code changes. Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Co-developed-by: Florian Westphal Signed-off-by: Florian Westphal Co-developed-by: Davide Caratti Signed-off-by: Davide Caratti Signed-off-by: Peter Krystad Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ca6f01531e64..52798ab00394 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -78,6 +78,16 @@ struct tcp_sack_block { #define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */ #define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/ +#if IS_ENABLED(CONFIG_MPTCP) +struct mptcp_options_received { + u64 sndr_key; + u64 rcvr_key; + u8 mp_capable : 1, + mp_join : 1, + dss : 1; +}; +#endif + struct tcp_options_received { /* PAWS/RTTM data */ int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ @@ -95,6 +105,9 @@ struct tcp_options_received { 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 */ +#if IS_ENABLED(CONFIG_MPTCP) + struct mptcp_options_received mptcp; +#endif }; static inline void tcp_clear_options(struct tcp_options_received *rx_opt) @@ -104,6 +117,11 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) #if IS_ENABLED(CONFIG_SMC) rx_opt->smc_ok = 0; #endif +#if IS_ENABLED(CONFIG_MPTCP) + rx_opt->mptcp.mp_capable = 0; + rx_opt->mptcp.mp_join = 0; + rx_opt->mptcp.dss = 0; +#endif } /* This is the max number of SACKS that we'll generate and process. It's safe -- cgit v1.2.3 From 2303f994b3e187091fd08148066688b08f837efc Mon Sep 17 00:00:00 2001 From: Peter Krystad Date: Tue, 21 Jan 2020 16:56:17 -0800 Subject: mptcp: Associate MPTCP context with TCP socket Use ULP to associate a subflow_context structure with each TCP subflow socket. Creating these sockets requires new bind and connect functions to make sure ULP is set up immediately when the subflow sockets are created. Co-developed-by: Florian Westphal Signed-off-by: Florian Westphal Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Co-developed-by: Davide Caratti Signed-off-by: Davide Caratti Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Signed-off-by: Peter Krystad Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 52798ab00394..877947475814 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -397,6 +397,9 @@ struct tcp_sock { u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG * while socket was owned by user. */ +#if IS_ENABLED(CONFIG_MPTCP) + bool is_mptcp; +#endif #ifdef CONFIG_TCP_MD5SIG /* TCP AF-Specific parts; only used by MD5 Signature support so far */ -- cgit v1.2.3 From cec37a6e41aae7bf3df9a3da783380a4d9325fd8 Mon Sep 17 00:00:00 2001 From: Peter Krystad Date: Tue, 21 Jan 2020 16:56:18 -0800 Subject: mptcp: Handle MP_CAPABLE options for outgoing connections Add hooks to tcp_output.c to add MP_CAPABLE to an outgoing SYN request, to capture the MP_CAPABLE in the received SYN-ACK, to add MP_CAPABLE to the final ACK of the three-way handshake. Use the .sk_rx_dst_set() handler in the subflow proto to capture when the responding SYN-ACK is received and notify the MPTCP connection layer. Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Co-developed-by: Florian Westphal Signed-off-by: Florian Westphal Signed-off-by: Peter Krystad Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 877947475814..e9ee06d887fa 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -137,6 +137,9 @@ struct tcp_request_sock { const struct tcp_request_sock_ops *af_specific; u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; +#if IS_ENABLED(CONFIG_MPTCP) + bool is_mptcp; +#endif u32 txhash; u32 rcv_isn; u32 snt_isn; -- cgit v1.2.3 From 648ef4b88673dadb8463bf0d4b10fbf33d55def8 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Tue, 21 Jan 2020 16:56:24 -0800 Subject: mptcp: Implement MPTCP receive path Parses incoming DSS options and populates outgoing MPTCP ACK fields. MPTCP fields are parsed from the TCP option header and placed in an skb extension, allowing the upper MPTCP layer to access MPTCP options after the skb has gone through the TCP stack. The subflow implements its own data_ready() ops, which ensures that the pending data is in sequence - according to MPTCP seq number - dropping out-of-seq skbs. The DATA_READY bit flag is set if this is the case. This allows the MPTCP socket layer to determine if more data is available without having to consult the individual subflows. It additionally validates the current mapping and propagates EoF events to the connection socket. Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Co-developed-by: Peter Krystad Signed-off-by: Peter Krystad Co-developed-by: Davide Caratti Signed-off-by: Davide Caratti Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Co-developed-by: Florian Westphal Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e9ee06d887fa..0d00dad4b85d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -82,9 +82,19 @@ struct tcp_sack_block { struct mptcp_options_received { u64 sndr_key; u64 rcvr_key; + u64 data_ack; + u64 data_seq; + u32 subflow_seq; + u16 data_len; u8 mp_capable : 1, mp_join : 1, dss : 1; + u8 use_map:1, + dsn64:1, + data_fin:1, + use_ack:1, + ack64:1, + __unused:3; }; #endif -- cgit v1.2.3 From cc7972ea1932335e0a0ee00ac8a24b3e8304630d Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Tue, 21 Jan 2020 16:56:31 -0800 Subject: mptcp: parse and emit MP_CAPABLE option according to v1 spec This implements MP_CAPABLE options parsing and writing according to RFC 6824 bis / RFC 8684: MPTCP v1. Local key is sent on syn/ack, and both keys are sent on 3rd ack. MP_CAPABLE messages len are updated accordingly. We need the skbuff to correctly emit the above, so we push the skbuff struct as an argument all the way from tcp code to the relevant mptcp callbacks. When processing incoming MP_CAPABLE + data, build a full blown DSS-like map info, to simplify later processing. On child socket creation, we need to record the remote key, if available. Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 0d00dad4b85d..4e2124607d32 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -94,7 +94,8 @@ struct mptcp_options_received { data_fin:1, use_ack:1, ack64:1, - __unused:3; + mpc_map:1, + __unused:2; }; #endif -- cgit v1.2.3 From a35d16905efc6ad5523d864a5c6efcb1e657e386 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Mon, 5 Aug 2019 18:22:27 -0400 Subject: rcu: Add basic support for kfree_rcu() batching Recently a discussion about stability and performance of a system involving a high rate of kfree_rcu() calls surfaced on the list [1] which led to another discussion how to prepare for this situation. This patch adds basic batching support for kfree_rcu(). It is "basic" because we do none of the slab management, dynamic allocation, code moving or any of the other things, some of which previous attempts did [2]. These fancier improvements can be follow-up patches and there are different ideas being discussed in those regards. This is an effort to start simple, and build up from there. In the future, an extension to use kfree_bulk and possibly per-slab batching could be done to further improve performance due to cache-locality and slab-specific bulk free optimizations. By using an array of pointers, the worker thread processing the work would need to read lesser data since it does not need to deal with large rcu_head(s) any longer. Torture tests follow in the next patch and show improvements of around 5x reduction in number of grace periods on a 16 CPU system. More details and test data are in that patch. There is an implication with rcu_barrier() with this patch. Since the kfree_rcu() calls can be batched, and may not be handed yet to the RCU machinery in fact, the monitor may not have even run yet to do the queue_rcu_work(), there seems no easy way of implementing rcu_barrier() to wait for those kfree_rcu()s that are already made. So this means a kfree_rcu() followed by an rcu_barrier() does not imply that memory will be freed once rcu_barrier() returns. Another implication is higher active memory usage (although not run-away..) until the kfree_rcu() flooding ends, in comparison to without batching. More details about this are in the second patch which adds an rcuperf test. Finally, in the near future we will get rid of kfree_rcu() special casing within RCU such as in rcu_do_batch and switch everything to just batching. Currently we don't do that since timer subsystem is not yet up and we cannot schedule the kfree_rcu() monitor as the timer subsystem's lock are not initialized. That would also mean getting rid of kfree_call_rcu_nobatch() entirely. [1] http://lore.kernel.org/lkml/20190723035725-mutt-send-email-mst@kernel.org [2] https://lkml.org/lkml/2017/12/19/824 Cc: kernel-team@android.com Cc: kernel-team@lge.com Co-developed-by: Byungchul Park Signed-off-by: Byungchul Park Signed-off-by: Joel Fernandes (Google) [ paulmck: Applied 0day and Paul Walmsley feedback on ->monitor_todo. ] [ paulmck: Make it work during early boot. ] [ paulmck: Add a crude early boot self-test. ] [ paulmck: Style adjustments and experimental docbook structure header. ] Link: https://lore.kernel.org/lkml/alpine.DEB.2.21.9999.1908161931110.32497@viisi.sifive.com/T/#me9956f66cb611b95d26ae92700e1d901f46e8c59 Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 6 ++++++ include/linux/rcutree.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 37b6f0c2b79d..1bd166aab6f3 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -39,6 +39,11 @@ static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) call_rcu(head, func); } +static inline void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + void rcu_qs(void); static inline void rcu_softirq_qs(void) @@ -85,6 +90,7 @@ static inline void rcu_scheduler_starting(void) { } static inline void rcu_end_inkernel_boot(void) { } 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) { } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index c5147de885ec..6a65d3a16dbd 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -34,10 +34,12 @@ static inline void rcu_virt_note_context_switch(int cpu) void synchronize_rcu_expedited(void); void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); +void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); void rcu_momentary_dyntick_idle(void); +void kfree_rcu_scheduler_running(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); -- cgit v1.2.3 From 77a40f97030b27b3fc1640a3ed203870f0817f57 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Fri, 30 Aug 2019 12:36:32 -0400 Subject: rcu: Remove kfree_rcu() special casing and lazy-callback handling This commit removes kfree_rcu() special-casing and the lazy-callback handling from Tree RCU. It moves some of this special casing to Tiny RCU, the removal of which will be the subject of later commits. This results in a nice negative delta. Suggested-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) [ paulmck: Add slab.h #include, thanks to kbuild test robot . ] Signed-off-by: Paul E. McKenney --- include/linux/rcu_segcblist.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 646759042333..b36afe7b22c9 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -22,7 +22,6 @@ struct rcu_cblist { struct rcu_head *head; struct rcu_head **tail; long len; - long len_lazy; }; #define RCU_CBLIST_INITIALIZER(n) { .head = NULL, .tail = &n.head } @@ -73,7 +72,6 @@ struct rcu_segcblist { #else long len; #endif - long len_lazy; u8 enabled; u8 offloaded; }; -- cgit v1.2.3 From 189a6883dcf7fa70e17403ae4225c60ffc9e404b Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Fri, 30 Aug 2019 12:36:33 -0400 Subject: rcu: Remove kfree_call_rcu_nobatch() Now that the kfree_rcu() special-casing has been removed from tree RCU, this commit removes kfree_call_rcu_nobatch() since it is no longer needed. Signed-off-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 5 ----- include/linux/rcutree.h | 1 - 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 1bd166aab6f3..b2b2dc990da9 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -39,11 +39,6 @@ static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) call_rcu(head, func); } -static inline void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func) -{ - call_rcu(head, func); -} - void rcu_qs(void); static inline void rcu_softirq_qs(void) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 6a65d3a16dbd..2f787b9029d1 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -34,7 +34,6 @@ static inline void rcu_virt_note_context_switch(int cpu) void synchronize_rcu_expedited(void); void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); -void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); -- cgit v1.2.3 From e1350e8e0ea5d959c23c5e593ff3026a67dbb049 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 15 Oct 2019 14:48:22 +0100 Subject: rcu: Move rcu_{expedited,normal} definitions into rcupdate.h This commit moves the rcu_{expedited,normal} definitions from kernel/rcu/update.c to include/linux/rcupdate.h to make sure they are in sync, and also to avoid the following warning from sparse: kernel/ksysfs.c:150:5: warning: symbol 'rcu_expedited' was not declared. Should it be static? kernel/ksysfs.c:167:5: warning: symbol 'rcu_normal' was not declared. Should it be static? Signed-off-by: Ben Dooks Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index fe470243acdd..bb36379606d0 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -896,4 +896,8 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) return false; } +/* kernel/ksysfs.c definitions */ +extern int rcu_expedited; +extern int rcu_normal; + #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From 5671d814dbd204b4ecc705045b5f1a647bff6f3b Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 17 Jan 2020 10:01:35 +0100 Subject: smp: Use smp_cond_func_t as type for the conditional function Use a typdef for the conditional function instead defining it each time in the function prototype. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20200117090137.1205765-2-bigeasy@linutronix.de --- include/linux/smp.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 6fc856c9eda5..4734416855aa 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -15,6 +15,7 @@ #include typedef void (*smp_call_func_t)(void *info); +typedef bool (*smp_cond_func_t)(int cpu, void *info); struct __call_single_data { struct llist_node llist; smp_call_func_t func; @@ -49,13 +50,12 @@ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, * cond_func returns a positive value. This may include the local * processor. */ -void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags); +void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait, gfp_t gfp_flags); -void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags, const struct cpumask *mask); +void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait, gfp_t gfp_flags, + const struct cpumask *mask); int smp_call_function_single_async(int cpu, call_single_data_t *csd); -- cgit v1.2.3 From cb923159bbb8cc8fe09c19a3435ee11fd546f3d3 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 17 Jan 2020 10:01:37 +0100 Subject: smp: Remove allocation mask from on_each_cpu_cond.*() The allocation mask is no longer used by on_each_cpu_cond() and on_each_cpu_cond_mask() and can be removed. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20200117090137.1205765-4-bigeasy@linutronix.de --- include/linux/smp.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 4734416855aa..cbc9162689d0 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -51,11 +51,10 @@ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, * processor. */ void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, - void *info, bool wait, gfp_t gfp_flags); + void *info, bool wait); void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, - void *info, bool wait, gfp_t gfp_flags, - const struct cpumask *mask); + void *info, bool wait, const struct cpumask *mask); int smp_call_function_single_async(int cpu, call_single_data_t *csd); -- cgit v1.2.3 From eb014de4fd418de1a277913cba244e47274fe392 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Jan 2020 16:48:03 +0100 Subject: netfilter: nf_tables: autoload modules from the abort path This patch introduces a list of pending module requests. This new module list is composed of nft_module_request objects that contain the module name and one status field that tells if the module has been already loaded (the 'done' field). In the first pass, from the preparation phase, the netlink command finds that a module is missing on this list. Then, a module request is allocated and added to this list and nft_request_module() returns -EAGAIN. This triggers the abort path with the autoload parameter set on from nfnetlink, request_module() is called and the module request enters the 'done' state. Since the mutex is released when loading modules from the abort phase, the module list is zapped so this is iteration occurs over a local list. Therefore, the request_module() calls happen when object lists are in consistent state (after fulling aborting the transaction) and the commit list is empty. On the second pass, the netlink command will find that it already tried to load the module, so it does not request it again and nft_request_module() returns 0. Then, there is a look up to find the object that the command was missing. If the module was successfully loaded, the command proceeds normally since it finds the missing object in place, otherwise -ENOENT is reported to userspace. This patch also updates nfnetlink to include the reason to enter the abort phase, which is required for this new autoload module rationale. Fixes: ec7470b834fe ("netfilter: nf_tables: store transaction list locally while requesting module") Reported-by: syzbot+29125d208b3dae9a7019@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index cf09ab37b45b..851425c3178f 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -31,7 +31,7 @@ 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); + int (*abort)(struct net *net, struct sk_buff *skb, bool autoload); void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; -- cgit v1.2.3 From fd928f3e32ba09381b287f8b732418434d932855 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 23 Jan 2020 21:58:48 -0800 Subject: alarmtimer: Make alarmtimer_get_rtcdev() a stub when CONFIG_RTC_CLASS=n The stubbed version of alarmtimer_get_rtcdev() is not exported. so this won't work if this function is used in a module when CONFIG_RTC_CLASS=n. Move the stub function to the header file and make it inline so that callers don't have to worry about linking against this symbol. rtcdev isn't used outside of this ifdef so it's not required to be redefined to NULL. Drop that while touching this area. Signed-off-by: Stephen Boyd Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20200124055849.154411-4-swboyd@chromium.org --- include/linux/alarmtimer.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 74748e306f4b..05e758b8b894 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -60,7 +60,11 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval); u64 alarm_forward_now(struct alarm *alarm, ktime_t interval); ktime_t alarm_expires_remaining(const struct alarm *alarm); +#ifdef CONFIG_RTC_CLASS /* Provide way to access the rtc device being used by alarmtimers */ struct rtc_device *alarmtimer_get_rtcdev(void); +#else +static inline struct rtc_device *alarmtimer_get_rtcdev(void) { return NULL; } +#endif #endif -- cgit v1.2.3 From 2856ba6020fc5cbf051d5a75b2abb3046072c144 Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Tue, 21 Jan 2020 06:37:47 -0700 Subject: PCI: Introduce pci_real_dma_dev() The current DMA alias implementation requires the aliased device be on the same PCI bus as the requester ID. Add an arch-specific mechanism to point to another PCI device when doing mapping and PCI DMA alias search. The default case returns the actual device. Link: https://lore.kernel.org/r/1579613871-301529-4-git-send-email-jonathan.derrick@intel.com Signed-off-by: Jon Derrick Signed-off-by: Bjorn Helgaas Cc: Christoph Hellwig --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c393dff2d66f..7f4e80666972 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1202,6 +1202,7 @@ int __must_check pci_resize_resource(struct pci_dev *dev, int i, int size); int pci_select_bars(struct pci_dev *dev, unsigned long flags); bool pci_device_is_present(struct pci_dev *pdev); void pci_ignore_hotplug(struct pci_dev *dev); +struct pci_dev *pci_real_dma_dev(struct pci_dev *dev); int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr, irq_handler_t handler, irq_handler_t thread_fn, void *dev_id, -- cgit v1.2.3 From f7b37b8b139860ed786bf8ce4358290c6053d94d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Jan 2020 12:06:34 -0500 Subject: NFS: Add softreval behaviour to nfs_lookup_revalidate() If the server is unavaliable, we want to allow the revalidating lookup to time out, and to default to validating the cached dentry if the 'softreval' mount option is set. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0a36c6f62b58..94c77ed55ce1 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1661,7 +1661,7 @@ struct nfs_rpc_ops { struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct inode *, const struct qstr *, + int (*lookup) (struct inode *, struct dentry *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); int (*lookupp) (struct inode *, struct nfs_fh *, -- cgit v1.2.3 From 7f6225e446cc8dfa4c3c7959a4de3dd03ec277bf Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Wed, 4 Dec 2019 20:46:14 +0800 Subject: jbd2: clean __jbd2_journal_abort_hard() and __journal_abort_soft() __jbd2_journal_abort_hard() is no longer used, so now we can merge __jbd2_journal_abort_hard() and __journal_abort_soft() these two functions into jbd2_journal_abort() and remove them. Signed-off-by: zhangyi (F) Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20191204124614.45424-5-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index ce44b687d02b..f613d8529863 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1403,7 +1403,6 @@ extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, int); -extern void __jbd2_journal_abort_hard (journal_t *); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); -- cgit v1.2.3 From ef6aadcc76c97e25f62adc4e9d19684d3e5d0b87 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Fri, 24 Jan 2020 15:23:06 +0200 Subject: net: sched: Make TBF Qdisc offloadable Invoke ndo_setup_tc as appropriate to signal init / replacement, destroying and dumping of TBF Qdisc. Signed-off-by: Petr Machata Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ec3537fbdb1..11bdf6cb30bd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -850,6 +850,7 @@ enum tc_setup_type { TC_SETUP_QDISC_TAPRIO, TC_SETUP_FT, TC_SETUP_QDISC_ETS, + TC_SETUP_QDISC_TBF, }; /* These structures hold the attributes of bpf state that are being passed -- cgit v1.2.3 From e9b4e606c2289d6610113253922bb8c9ac7f68b0 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 23 Jan 2020 17:15:07 +0100 Subject: bpf: Allow to resolve bpf trampoline and dispatcher in unwind When unwinding the stack we need to identify each address to successfully continue. Adding latch tree to keep trampolines for quick lookup during the unwind. The patch uses first 48 bytes for latch tree node, leaving 4048 bytes from the rest of the page for trampoline or dispatcher generated code. It's still enough not to affect trampoline and dispatcher progs maximum counts. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200123161508.915203-3-jolsa@kernel.org --- include/linux/bpf.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a9687861fd7e..8e9ad3943cd9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -525,7 +525,6 @@ 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); void bpf_trampoline_put(struct bpf_trampoline *tr); -void *bpf_jit_alloc_exec_page(void); #define BPF_DISPATCHER_INIT(name) { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .func = &name##func, \ @@ -557,6 +556,13 @@ void *bpf_jit_alloc_exec_page(void); #define BPF_DISPATCHER_PTR(name) (&name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); +struct bpf_image { + struct latch_tree_node tnode; + unsigned char data[]; +}; +#define BPF_IMAGE_SIZE (PAGE_SIZE - sizeof(struct bpf_image)) +bool is_bpf_image_address(unsigned long address); +void *bpf_image_alloc(void); #else static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { @@ -578,6 +584,10 @@ static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) {} +static inline bool is_bpf_image_address(unsigned long address) +{ + return false; +} #endif struct bpf_func_info_aux { -- cgit v1.2.3 From 647f50d5d9d933b644b29c54f13ac52af1b1774d Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Fri, 10 Jan 2020 14:54:16 +0000 Subject: linux/random.h: Remove arch_has_random, arch_has_random_seed The arm64 version of archrandom.h will need to be able to test for support and read the random number without preemption, so a separate query predicate is not practical. Since this part of the generic interface is unused, remove it. Signed-off-by: Richard Henderson Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20200110145422.49141-5-broonie@kernel.org Signed-off-by: Theodore Ts'o --- include/linux/random.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index f189c927fdea..7fd0360908d2 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -175,10 +175,6 @@ static inline bool arch_get_random_int(unsigned int *v) { return 0; } -static inline bool arch_has_random(void) -{ - return 0; -} static inline bool arch_get_random_seed_long(unsigned long *v) { return 0; @@ -187,10 +183,6 @@ static inline bool arch_get_random_seed_int(unsigned int *v) { return 0; } -static inline bool arch_has_random_seed(void) -{ - return 0; -} #endif /* Pseudo random number generator from numerical recipes. */ -- cgit v1.2.3 From 66f5ae899ada79c0e9a3d8d954f93a72344cd350 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Fri, 10 Jan 2020 14:54:17 +0000 Subject: linux/random.h: Use false with bool Keep the generic fallback versions in sync with the other architecture specific implementations and use the proper name for false. Suggested-by: Ard Biesheuvel Signed-off-by: Richard Henderson Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20200110145422.49141-6-broonie@kernel.org Signed-off-by: Theodore Ts'o --- include/linux/random.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 7fd0360908d2..ea0e2f5f1ec5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -169,19 +169,19 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) #else static inline bool arch_get_random_long(unsigned long *v) { - return 0; + return false; } static inline bool arch_get_random_int(unsigned int *v) { - return 0; + return false; } static inline bool arch_get_random_seed_long(unsigned long *v) { - return 0; + return false; } static inline bool arch_get_random_seed_int(unsigned int *v) { - return 0; + return false; } #endif -- cgit v1.2.3 From 904caa6413c87aacbf7d0682da617c39ca18cf1a Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Fri, 10 Jan 2020 14:54:18 +0000 Subject: linux/random.h: Mark CONFIG_ARCH_RANDOM functions __must_check We must not use the pointer output without validating the success of the random read. Reviewed-by: Ard Biesheuvel Signed-off-by: Richard Henderson Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20200110145422.49141-7-broonie@kernel.org Signed-off-by: Theodore Ts'o --- include/linux/random.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index ea0e2f5f1ec5..d319f9a1e429 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -167,19 +167,19 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) #ifdef CONFIG_ARCH_RANDOM # include #else -static inline bool arch_get_random_long(unsigned long *v) +static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; } -static inline bool arch_get_random_int(unsigned int *v) +static inline bool __must_check arch_get_random_int(unsigned int *v) { return false; } -static inline bool arch_get_random_seed_long(unsigned long *v) +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return false; } -static inline bool arch_get_random_seed_int(unsigned int *v) +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return false; } -- cgit v1.2.3 From 4bbd4923d1f5627b0c47a9d7dfb5cc91224cfe0c Mon Sep 17 00:00:00 2001 From: Danit Goldberg Date: Thu, 16 Jan 2020 14:00:48 +0200 Subject: IB/mlx5: Return the administrative GUID if exists A user can change the operational GUID (a.k.a affective GUID) through link/infiniband. Therefore it is preferred to return the currently set GUID if it exists instead of the operational. This way the PF can query which VF GUID will be set in the next bind. In order to align with MAC address, zero is returned if administrative GUID is not set. For example, before setting administrative GUID: $ ip link show ib0: mtu 4092 qdisc mq state UP mode DEFAULT group default qlen 256 link/infiniband 00:00:00:08:fe:80:00:00:00:00:00:00:52:54:00:c0:fe:12:34:55 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff vf 0 link/infiniband 00:00:00:08:fe:80:00:00:00:00:00:00:52:54:00:c0:fe:12:34:55 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff, spoof checking off, NODE_GUID 00:00:00:00:00:00:00:00, PORT_GUID 00:00:00:00:00:00:00:00, link-state auto, trust off, query_rss off Then: $ ip link set ib0 vf 0 node_guid 11:00:af:21:cb:05:11:00 $ ip link set ib0 vf 0 port_guid 22:11:af:21:cb:05:11:00 After setting administrative GUID: $ ip link show ib0: mtu 4092 qdisc mq state UP mode DEFAULT group default qlen 256 link/infiniband 00:00:00:08:fe:80:00:00:00:00:00:00:52:54:00:c0:fe:12:34:55 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff vf 0 link/infiniband 00:00:00:08:fe:80:00:00:00:00:00:00:52:54:00:c0:fe:12:34:55 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff, spoof checking off, NODE_GUID 11:00:af:21:cb:05:11:00, PORT_GUID 22:11:af:21:cb:05:11:00, link-state auto, trust off, query_rss off Fixes: 9c0015ef0928 ("IB/mlx5: Implement callbacks for getting VFs GUID attributes") Link: https://lore.kernel.org/r/20200116120048.12744-1-leon@kernel.org Signed-off-by: Danit Goldberg Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/driver.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 27200dea0297..a24937fc56b9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -461,6 +461,11 @@ struct mlx5_vf_context { int enabled; u64 port_guid; u64 node_guid; + /* Valid bits are used to validate administrative guid only. + * Enabled after ndo_set_vf_guid + */ + u8 port_guid_valid:1; + u8 node_guid_valid:1; enum port_state_policy policy; }; -- cgit v1.2.3 From ddc9d357b991838c2d975e8d7e4e9db26f37a7ff Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Sun, 19 Jan 2020 15:29:22 -0800 Subject: Drivers: hv: vmbus: Ignore CHANNELMSG_TL_CONNECT_RESULT(23) When a Linux hv_sock app tries to connect to a Service GUID on which no host app is listening, a recent host (RS3+) sends a CHANNELMSG_TL_CONNECT_RESULT (23) message to Linux and this triggers such a warning: unknown msgtype=23 WARNING: CPU: 2 PID: 0 at drivers/hv/vmbus_drv.c:1031 vmbus_on_msg_dpc Actually Linux can safely ignore the message because the Linux app's connect() will time out in 2 seconds: see VSOCK_DEFAULT_CONNECT_TIMEOUT and vsock_stream_connect(). We don't bother to make use of the message because: 1) it's only supported on recent hosts; 2) a non-trivial effort is required to use the message in Linux, but the benefit is small. So, let's not see the warning by silently ignoring the message. Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Signed-off-by: Sasha Levin --- include/linux/hyperv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 26f3aeeae1ca..41c58011431e 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -425,6 +425,8 @@ enum vmbus_channel_message_type { CHANNELMSG_19 = 19, CHANNELMSG_20 = 20, CHANNELMSG_TL_CONNECT_REQUEST = 21, + CHANNELMSG_22 = 22, + CHANNELMSG_TL_CONNECT_RESULT = 23, CHANNELMSG_COUNT }; -- cgit v1.2.3 From 913292c97d750fe4188b4f5aa770e5e0ca1e5a91 Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Fri, 24 Jan 2020 10:29:08 +0530 Subject: sched.h: Annotate sighand_struct with __rcu This patch fixes the following sparse errors by annotating the sighand_struct with __rcu kernel/fork.c:1511:9: error: incompatible types in comparison expression kernel/exit.c:100:19: error: incompatible types in comparison expression kernel/signal.c:1370:27: error: incompatible types in comparison expression This fix introduces the following sparse error in signal.c due to checking the sighand pointer without rcu primitives: kernel/signal.c:1386:21: error: incompatible types in comparison expression This new sparse error is also fixed in this patch. Signed-off-by: Madhuparna Bhowmik Acked-by: Paul E. McKenney Link: https://lore.kernel.org/r/20200124045908.26389-1-madhuparnabhowmik10@gmail.com Signed-off-by: Christian Brauner --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 467d26046416..ef60aa15097a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -917,7 +917,7 @@ struct task_struct { /* Signal handlers: */ struct signal_struct *signal; - struct sighand_struct *sighand; + struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ -- cgit v1.2.3 From 32efcc06d2a15fa87585614d12d6c2308cc2d3f3 Mon Sep 17 00:00:00 2001 From: Abdul Kabbani Date: Fri, 24 Jan 2020 16:34:02 -0500 Subject: tcp: export count for rehash attempts Using IPv6 flow-label to swiftly route around avoid congested or disconnected network path can greatly improve TCP reliability. This patch adds SNMP counters and a OPT_STATS counter to track both host-level and connection-level statistics. Network administrators can use these counters to evaluate the impact of this new ability better. Export count for rehash attempts to 1) two SNMP counters: TcpTimeoutRehash (rehash due to timeouts), and TcpDuplicateDataRehash (rehash due to receiving duplicate packets) 2) Timestamping API SOF_TIMESTAMPING_OPT_STATS. Signed-off-by: Abdul Kabbani Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Kevin(Yudong) Yang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4e2124607d32..1cf73e6f85ca 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -386,6 +386,8 @@ struct tcp_sock { #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0 #endif + u16 timeout_rehash; /* Timeout-triggered rehash attempts */ + u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */ /* Receiver side RTT estimation */ -- cgit v1.2.3 From b72053072c0bbe9f1cdfe2ffa3c201c185da2201 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 26 Jan 2020 14:05:43 +0100 Subject: block: allow partitions on host aware zone devices Host-aware SMR drives can be used with the commands to explicitly manage zone state, but they can also be used as normal disks. In the former case it makes perfect sense to allow partitions on them, in the latter it does not, just like for host managed devices. Add a check to add_partition to allow partitions on host aware devices, but give up any zone management capabilities in that case, which also catches the previously missed case of adding a partition vs just scanning it. Because sd can rescan the attribute at runtime it needs to check if a disk has partitions, for which a new helper is added to genhd.h. Fixes: 5eac3eb30c9a ("block: Remove partition support for zoned block devices") Reported-by: Borislav Petkov Signed-off-by: Christoph Hellwig Tested-by: Damien Le Moal Reviewed-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/genhd.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8bb63027e4d6..ea4c133b4139 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -245,6 +245,18 @@ static inline bool disk_part_scan_enabled(struct gendisk *disk) !(disk->flags & GENHD_FL_NO_PART_SCAN); } +static inline bool disk_has_partitions(struct gendisk *disk) +{ + bool ret = false; + + rcu_read_lock(); + if (rcu_dereference(disk->part_tbl)->len > 1) + ret = true; + rcu_read_unlock(); + + return ret; +} + static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); -- cgit v1.2.3 From 54e19d34011fea26d39aa74781131de0ce642a01 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Sat, 25 Jan 2020 21:49:44 -0800 Subject: hv_utils: Add the support of hibernation Add util_pre_suspend() and util_pre_resume() for some hv_utils devices (e.g. kvp/vss/fcopy), because they need special handling before util_suspend() calls vmbus_close(). For kvp, all the possible pending work items should be cancelled. For vss and fcopy, some extra clean-up needs to be done, i.e. fake a THAW message for hv_vss_daemon and fake a CANCEL_FCOPY message for hv_fcopy_daemon, otherwise when the VM resums back, the daemons can end up in an inconsistent state (i.e. the file systems are frozen but will never be thawed; the file transmitted via fcopy may not be complete). Note: there is an extra patch for the daemons: "Tools: hv: Reopen the devices if read() or write() returns errors", because the hv_utils driver can not guarantee the whole transaction finishes completely once util_suspend() starts to run (at this time, all the userspace processes are frozen). util_probe() disables channel->callback_event to avoid the race with the channel callback. Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Signed-off-by: Sasha Levin --- include/linux/hyperv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 41c58011431e..692c89ccf5df 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1435,6 +1435,8 @@ struct hv_util_service { void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); void (*util_deinit)(void); + int (*util_pre_suspend)(void); + int (*util_pre_resume)(void); }; struct vmbuspipe_hdr { -- cgit v1.2.3 From 2092767168f0681aa03727448b801600a364c013 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Wed, 22 Jan 2020 00:17:54 +0100 Subject: bitmap: Introduce bitmap_cut(): cut bits and shift remaining The new bitmap function bitmap_cut() copies bits from source to destination by removing the region specified by parameters first and cut, and remapping the bits above the cut region by right shifting them. Signed-off-by: Stefano Brivio Signed-off-by: Pablo Neira Ayuso --- include/linux/bitmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index ff335b22f23c..f0f3a9fffa6a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -53,6 +53,7 @@ * bitmap_find_next_zero_area_off(buf, len, pos, n, mask) as above * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n + * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) @@ -133,6 +134,9 @@ extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); +extern void bitmap_cut(unsigned long *dst, const unsigned long *src, + unsigned int first, unsigned int cut, + unsigned int nbits); extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, -- cgit v1.2.3 From 2b586feab44f41db605924db15c5b039535b1f9b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 4 Dec 2019 16:39:27 +0100 Subject: thermal/drivers/Kconfig: Convert the CPU cooling device to a choice The next changes will add a new way to cool down a CPU by injecting idle cycles. With the current configuration, a CPU cooling device is the cpufreq cooling device. As we want to add a new CPU cooling device, let's convert the CPU cooling to a choice giving a list of CPU cooling devices. At this point, there is obviously only one CPU cooling device. There is no functional changes. Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Link: https://lore.kernel.org/r/20191204153930.9128-1-daniel.lezcano@linaro.org --- include/linux/cpu_cooling.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index b74732535e4b..3cdd85f987d7 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -19,7 +19,7 @@ struct cpufreq_policy; -#ifdef CONFIG_CPU_THERMAL +#ifdef CONFIG_CPU_FREQ_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. * @policy: cpufreq policy. @@ -40,7 +40,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); struct thermal_cooling_device * of_cpufreq_cooling_register(struct cpufreq_policy *policy); -#else /* !CONFIG_CPU_THERMAL */ +#else /* !CONFIG_CPU_FREQ_THERMAL */ static inline struct thermal_cooling_device * cpufreq_cooling_register(struct cpufreq_policy *policy) { @@ -58,6 +58,6 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) { return NULL; } -#endif /* CONFIG_CPU_THERMAL */ +#endif /* CONFIG_CPU_FREQ_THERMAL */ #endif /* __CPU_COOLING_H__ */ -- cgit v1.2.3 From a4c428e523490bf53e9c4ba2d809130c58c06ac7 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 19 Dec 2019 23:53:16 +0100 Subject: thermal/drivers/cpu_cooling: Introduce the cpu idle cooling driver The cpu idle cooling device offers a new method to cool down a CPU by injecting idle cycles at runtime. It has some similarities with the intel power clamp driver but it is actually designed to be more generic and relying on the idle injection powercap framework. The idle injection duration is fixed while the running duration is variable. That allows to have control on the device reactivity for the user experience. An idle state powering down the CPU or the cluster will allow to drop the static leakage, thus restoring the heat capacity of the SoC. It can be set with a trip point between the hot and the critical points, giving the opportunity to prevent a hard reset of the system when the cpufreq cooling fails to cool down the CPU. With more sophisticated boards having a per core sensor, the idle cooling device allows to cool down a single core without throttling the compute capacity of several cpus belonging to the same clock line, so it could be used in collaboration with the cpufreq cooling device. Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Link: https://lore.kernel.org/r/20191219225317.17158-2-daniel.lezcano@linaro.org --- include/linux/cpu_cooling.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 3cdd85f987d7..65501d8f9778 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -60,4 +60,22 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) } #endif /* CONFIG_CPU_FREQ_THERMAL */ +struct cpuidle_driver; + +#ifdef CONFIG_CPU_IDLE_THERMAL +int cpuidle_cooling_register(struct cpuidle_driver *drv); +int cpuidle_of_cooling_register(struct device_node *np, + struct cpuidle_driver *drv); +#else /* CONFIG_CPU_IDLE_THERMAL */ +static inline int cpuidle_cooling_register(struct cpuidle_driver *drv) +{ + return 0; +} +static inline int cpuidle_of_cooling_register(struct device_node *np, + struct cpuidle_driver *drv) +{ + return 0; +} +#endif /* CONFIG_CPU_IDLE_THERMAL */ + #endif /* __CPU_COOLING_H__ */ -- cgit v1.2.3 From 23affa2e29c5faa8cb59778f71e3bce2c8b3aa5c Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 19 Dec 2019 23:53:17 +0100 Subject: thermal/drivers/cpu_cooling: Rename to cpufreq_cooling As we introduced the idle injection cooling device called cpuidle_cooling, let's be consistent and rename the cpu_cooling to cpufreq_cooling as this one mitigates with OPPs changes. Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Reviewed-by: Amit Kucheria Link: https://lore.kernel.org/r/20191219225317.17158-3-daniel.lezcano@linaro.org --- include/linux/clock_cooling.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clock_cooling.h b/include/linux/clock_cooling.h index b5cebf766e02..4b0a69863656 100644 --- a/include/linux/clock_cooling.h +++ b/include/linux/clock_cooling.h @@ -7,7 +7,7 @@ * Copyright (C) 2013 Texas Instruments Inc. * Contact: Eduardo Valentin * - * Highly based on cpu_cooling.c. + * Highly based on cpufreq_cooling.c. * Copyright (C) 2012 Samsung Electronics Co., Ltd(http://www.samsung.com) * Copyright (C) 2012 Amit Daniel */ -- cgit v1.2.3 From 1e4f63aecb53e48468661e922fc2fa3b83e55722 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 26 Jan 2020 23:40:11 +0100 Subject: cpufreq: Avoid creating excessively large stack frames In the process of modifying a cpufreq policy, the cpufreq core makes a copy of it including all of the internals which is stored on the CPU stack. Because struct cpufreq_policy is relatively large, this may cause the size of the stack frame to exceed the 2 KB limit and so the GCC complains when -Wframe-larger-than= is used. In fact, it is not necessary to copy the entire policy structure in order to modify it, however. First, because cpufreq_set_policy() obtains the min and max policy limits from frequency QoS now, it is not necessary to pass the limits to it from the callers. The only things that need to be passed to it from there are the new governor pointer or (if there is a built-in governor in the driver) the "policy" value representing the governor choice. They both can be passed as individual arguments, though, so make cpufreq_set_policy() take them this way and rework its callers accordingly. This avoids making copies of cpufreq policies in the callers of cpufreq_set_policy(). Second, cpufreq_set_policy() still needs to pass the new policy data to the ->verify() callback of the cpufreq driver whose task is to sanitize the min and max policy limits. It still does not need to make a full copy of struct cpufreq_policy for this purpose, but it needs to pass a few items from it to the driver in case they are needed (different drivers have different needs in that respect and all of them have to be covered). For this reason, introduce struct cpufreq_policy_data to hold copies of the members of struct cpufreq_policy used by the existing ->verify() driver callbacks and pass a pointer to a temporary structure of that type to ->verify() (instead of passing a pointer to full struct cpufreq_policy to it). While at it, notice that intel_pstate and longrun don't really need to verify the "policy" value in struct cpufreq_policy, so drop those check from them to avoid copying "policy" into struct cpufreq_policy_data (which allows it to be slightly smaller). Also while at it fix up white space in a couple of places and make cpufreq_set_policy() static (as it can be so). Fixes: 3000ce3c52f8 ("cpufreq: Use per-policy frequency QoS") Link: https://lore.kernel.org/linux-pm/CAMuHMdX6-jb1W8uC2_237m8ctCpsnGp=JCxqt8pCWVqNXHmkVg@mail.gmail.com Reported-by: kbuild test robot Reported-by: Geert Uytterhoeven Cc: 5.4+ # 5.4+ Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 31b1b0e03df8..018dce868de6 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -148,6 +148,20 @@ struct cpufreq_policy { struct notifier_block nb_max; }; +/* + * Used for passing new cpufreq policy data to the cpufreq driver's ->verify() + * callback for sanitization. That callback is only expected to modify the min + * and max values, if necessary, and specifically it must not update the + * frequency table. + */ +struct cpufreq_policy_data { + struct cpufreq_cpuinfo cpuinfo; + struct cpufreq_frequency_table *freq_table; + unsigned int cpu; + unsigned int min; /* in kHz */ + unsigned int max; /* in kHz */ +}; + struct cpufreq_freqs { struct cpufreq_policy *policy; unsigned int old; @@ -201,8 +215,6 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu); void cpufreq_cpu_release(struct cpufreq_policy *policy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); -int cpufreq_set_policy(struct cpufreq_policy *policy, - struct cpufreq_policy *new_policy); void refresh_frequency_limits(struct cpufreq_policy *policy); void cpufreq_update_policy(unsigned int cpu); void cpufreq_update_limits(unsigned int cpu); @@ -284,7 +296,7 @@ struct cpufreq_driver { /* needed by all drivers */ int (*init)(struct cpufreq_policy *policy); - int (*verify)(struct cpufreq_policy *policy); + int (*verify)(struct cpufreq_policy_data *policy); /* define one out of two */ int (*setpolicy)(struct cpufreq_policy *policy); @@ -415,8 +427,9 @@ static inline int cpufreq_thermal_control_enabled(struct cpufreq_driver *drv) (drv->flags & CPUFREQ_IS_COOLING_DEV); } -static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, - unsigned int min, unsigned int max) +static inline void cpufreq_verify_within_limits(struct cpufreq_policy_data *policy, + unsigned int min, + unsigned int max) { if (policy->min < min) policy->min = min; @@ -432,10 +445,10 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, } static inline void -cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy) +cpufreq_verify_within_cpu_limits(struct cpufreq_policy_data *policy) { cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, - policy->cpuinfo.max_freq); + policy->cpuinfo.max_freq); } #ifdef CONFIG_CPU_FREQ @@ -513,6 +526,7 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, * CPUFREQ GOVERNORS * *********************************************************************/ +#define CPUFREQ_POLICY_UNKNOWN (0) /* * If (cpufreq_driver->target) exists, the ->governor decides what frequency * within the limits is used. If (cpufreq_driver->setpolicy> exists, these @@ -684,9 +698,9 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); -int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, +int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy, struct cpufreq_frequency_table *table); -int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy); +int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy); int cpufreq_table_index_unsorted(struct cpufreq_policy *policy, unsigned int target_freq, -- cgit v1.2.3 From 3b33583265ed3b0ae76eddbabf9d038b4076d1a9 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Sat, 25 Jan 2020 11:26:42 +0100 Subject: net: Add fraglist GRO/GSO feature flags This adds new Fraglist GRO/GSO feature flags. They will be used to configure fraglist GRO/GSO what will be implemented with some followup paches. Signed-off-by: Steffen Klassert Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 6 +++++- include/linux/netdevice.h | 1 + include/linux/skbuff.h | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 4b19c544c59a..b239507da2a0 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -53,8 +53,9 @@ enum { NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */ + NETIF_F_GSO_FRAGLIST_BIT, /* ... Fraglist GSO */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_UDP_L4_BIT, + NETIF_F_GSO_FRAGLIST_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -80,6 +81,7 @@ enum { NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */ + NETIF_F_GRO_FRAGLIST_BIT, /* Fraglist GRO */ /* * Add your fresh new feature above and remember to update @@ -150,6 +152,8 @@ enum { #define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) #define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) #define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX) +#define NETIF_F_GRO_FRAGLIST __NETIF_F(GRO_FRAGLIST) +#define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST) /* Finds the next feature with the highest number of the range of start till 0. */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 78e9c6c1b131..fcc76b890f50 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4570,6 +4570,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 26beae7db264..23aaaf08e1e9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -592,6 +592,8 @@ enum { SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, + + SKB_GSO_FRAGLIST = 1 << 18, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From 1a3c998f3a27ab6ecf56bdbb17e27e55fd6d47cd Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Sat, 25 Jan 2020 11:26:43 +0100 Subject: net: Add a netdev software feature set that defaults to off. The previous patch added the NETIF_F_GRO_FRAGLIST feature. This is a software feature that should default to off. Current software features default to on, so add a new feature set that defaults to off. Signed-off-by: Steffen Klassert Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index b239507da2a0..34d050bb1ae6 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -230,6 +230,9 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) /* changeable features with no special hardware requirements */ #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) +/* Changeable features with no special hardware requirements that defaults to off. */ +#define NETIF_F_SOFT_FEATURES_OFF NETIF_F_GRO_FRAGLIST + #define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | \ -- cgit v1.2.3 From 3a1296a38d0cf62bffb9a03c585cbd5dbf15d596 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Sat, 25 Jan 2020 11:26:44 +0100 Subject: net: Support GRO/GSO fraglist chaining. This patch adds the core functions to chain/unchain GSO skbs at the frag_list pointer. This also adds a new GSO type SKB_GSO_FRAGLIST and a is_flist flag to napi_gro_cb which indicates that this flow will be GROed by fraglist chaining. Signed-off-by: Steffen Klassert Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- include/linux/skbuff.h | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fcc76b890f50..20445f94eb1c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2326,7 +2326,8 @@ struct napi_gro_cb { /* Number of gro_receive callbacks this packet already went through */ u8 recursion_counter:4; - /* 1 bit hole */ + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -2694,6 +2695,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 23aaaf08e1e9..3d13a4b717e9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3535,6 +3535,8 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet); bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu); bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); +struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, + unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); -- cgit v1.2.3 From 93642e14bd50e59b11cf6389ce3fc243e932777a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 25 Jan 2020 12:17:08 +0100 Subject: net: introduce dev_net notifier register/unregister variants Introduce dev_net variants of netdev notifier register/unregister functions and allow per-net notifier to follow the netdevice into the namespace it is moved to. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 20445f94eb1c..4626188a754b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -939,6 +939,11 @@ struct netdev_name_node { int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); +struct netdev_net_notifier { + struct list_head list; + struct notifier_block *nb; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1793,6 +1798,10 @@ enum netdev_priv_flags { * * @wol_enabled: Wake-on-LAN is enabled * + * @net_notifier_list: List of per-net netdev notifier block + * that follow this device when it is moved + * to another network namespace. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2085,6 +2094,8 @@ struct net_device { struct lock_class_key addr_list_lock_key; bool proto_down; unsigned wol_enabled:1; + + struct list_head net_notifier_list; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2529,6 +2540,12 @@ int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +int register_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn); +int unregister_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn); struct netdev_notifier_info { struct net_device *dev; -- cgit v1.2.3 From a85dd3a5170c8812cd835ea968ccadf0ebf1648e Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 25 Jan 2020 13:42:14 +0100 Subject: net: remove eth_change_mtu All usage of this function was removed three years ago, and the function was marked as deprecated: a52ad514fdf3 ("net: deprecate eth_change_mtu, remove usage") So I think we can remove it now. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index f6564b572d77..8801f1f986e5 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -43,7 +43,6 @@ __be16 eth_header_parse_protocol(const struct sk_buff *skb); int eth_prepare_mac_addr_change(struct net_device *dev, void *p); void eth_commit_mac_addr_change(struct net_device *dev, void *p); int eth_mac_addr(struct net_device *dev, void *p); -int eth_change_mtu(struct net_device *dev, int new_mtu); int eth_validate_addr(struct net_device *dev); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, -- cgit v1.2.3 From 6a94b8ccf6b77f005ab1b36a878e1d81df0c033e Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Sun, 26 Jan 2020 23:11:04 +0100 Subject: ethtool: provide message mask with DEBUG_GET request Implement DEBUG_GET request to get debugging settings for a device. At the moment, only message mask corresponding to message level as reported by ETHTOOL_GMSGLVL ioctl request is provided. (It is called message level in ioctl interface but almost all drivers interpret it as a bit mask.) As part of the implementation, provide symbolic names for message mask bits as ETH_SS_MSG_CLASSES string set. Signed-off-by: Michal Kubecek Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 56 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 41 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4626188a754b..a9c6b5c61d27 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3913,22 +3913,48 @@ void netif_device_attach(struct net_device *dev); */ enum { - NETIF_MSG_DRV = 0x0001, - NETIF_MSG_PROBE = 0x0002, - NETIF_MSG_LINK = 0x0004, - NETIF_MSG_TIMER = 0x0008, - NETIF_MSG_IFDOWN = 0x0010, - NETIF_MSG_IFUP = 0x0020, - NETIF_MSG_RX_ERR = 0x0040, - NETIF_MSG_TX_ERR = 0x0080, - NETIF_MSG_TX_QUEUED = 0x0100, - NETIF_MSG_INTR = 0x0200, - NETIF_MSG_TX_DONE = 0x0400, - NETIF_MSG_RX_STATUS = 0x0800, - NETIF_MSG_PKTDATA = 0x1000, - NETIF_MSG_HW = 0x2000, - NETIF_MSG_WOL = 0x4000, + NETIF_MSG_DRV_BIT, + NETIF_MSG_PROBE_BIT, + NETIF_MSG_LINK_BIT, + NETIF_MSG_TIMER_BIT, + NETIF_MSG_IFDOWN_BIT, + NETIF_MSG_IFUP_BIT, + NETIF_MSG_RX_ERR_BIT, + NETIF_MSG_TX_ERR_BIT, + NETIF_MSG_TX_QUEUED_BIT, + NETIF_MSG_INTR_BIT, + NETIF_MSG_TX_DONE_BIT, + NETIF_MSG_RX_STATUS_BIT, + NETIF_MSG_PKTDATA_BIT, + NETIF_MSG_HW_BIT, + NETIF_MSG_WOL_BIT, + + /* When you add a new bit above, update netif_msg_class_names array + * in net/ethtool/common.c + */ + NETIF_MSG_CLASS_COUNT, }; +/* Both ethtool_ops interface and internal driver implementation use u32 */ +static_assert(NETIF_MSG_CLASS_COUNT <= 32); + +#define __NETIF_MSG_BIT(bit) ((u32)1 << (bit)) +#define __NETIF_MSG(name) __NETIF_MSG_BIT(NETIF_MSG_ ## name ## _BIT) + +#define NETIF_MSG_DRV __NETIF_MSG(DRV) +#define NETIF_MSG_PROBE __NETIF_MSG(PROBE) +#define NETIF_MSG_LINK __NETIF_MSG(LINK) +#define NETIF_MSG_TIMER __NETIF_MSG(TIMER) +#define NETIF_MSG_IFDOWN __NETIF_MSG(IFDOWN) +#define NETIF_MSG_IFUP __NETIF_MSG(IFUP) +#define NETIF_MSG_RX_ERR __NETIF_MSG(RX_ERR) +#define NETIF_MSG_TX_ERR __NETIF_MSG(TX_ERR) +#define NETIF_MSG_TX_QUEUED __NETIF_MSG(TX_QUEUED) +#define NETIF_MSG_INTR __NETIF_MSG(INTR) +#define NETIF_MSG_TX_DONE __NETIF_MSG(TX_DONE) +#define NETIF_MSG_RX_STATUS __NETIF_MSG(RX_STATUS) +#define NETIF_MSG_PKTDATA __NETIF_MSG(PKTDATA) +#define NETIF_MSG_HW __NETIF_MSG(HW) +#define NETIF_MSG_WOL __NETIF_MSG(WOL) #define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV) #define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE) -- cgit v1.2.3 From 2924e0699963b839f88f8c4e855929ea49185870 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 27 Jan 2020 15:26:07 +0200 Subject: qed: FW 8.42.2.0 Internal ram offsets modifications IRO stands for internal RAM offsets. Updating the FW binary produces different iro offsets. This file contains the different values, and a new representation of the values. Update the FW version Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 03f59a28fefd..3f437e826a4c 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -109,8 +109,8 @@ #define MAX_NUM_LL2_TX_STATS_COUNTERS 48 #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 37 -#define FW_REVISION_VERSION 7 +#define FW_MINOR_VERSION 42 +#define FW_REVISION_VERSION 2 #define FW_ENGINEERING_VERSION 0 /***********************/ -- cgit v1.2.3 From 997af5df230e3288ec1f5b332955f9be643e450b Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 27 Jan 2020 15:26:12 +0200 Subject: qed: FW 8.42.2.0 Additional ll2 type LL2 queues were a limited resource due to FW constraints. This FW introduced a new resource which is a context based ll2 queue (memory on host). The additional ll2 queues are required for RDMA SRIOV. The code refers to the previous ll2 queues as ram-based or legacy, and the new queues as ctx-based. This change decreased the "legacy" ram-based queues therefore the first ll2 queue used for iWARP was converted to the ctx-based ll2 queue. This feature also exposed a bug in the DIRECT_REG_WR64 macro implementation which didn't have an effect in other use cases. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 15 +++++++++++++-- include/linux/qed/qed_if.h | 4 +++- include/linux/qed/qed_ll2_if.h | 7 +++++++ 3 files changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 3f437e826a4c..a2b7826b36f0 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -105,8 +105,15 @@ #define CORE_SPQE_PAGE_SIZE_BYTES 4096 -#define MAX_NUM_LL2_RX_QUEUES 48 -#define MAX_NUM_LL2_TX_STATS_COUNTERS 48 +/* Number of LL2 RAM based queues */ +#define MAX_NUM_LL2_RX_RAM_QUEUES 32 + +/* Number of LL2 context based queues */ +#define MAX_NUM_LL2_RX_CTX_QUEUES 208 +#define MAX_NUM_LL2_RX_QUEUES \ + (MAX_NUM_LL2_RX_RAM_QUEUES + MAX_NUM_LL2_RX_CTX_QUEUES) + +#define MAX_NUM_LL2_TX_STATS_COUNTERS 48 #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 42 @@ -340,6 +347,10 @@ #define DQ_PWM_OFFSET_TCM_ROCE_RQ_PROD (DQ_PWM_OFFSET_TCM16_BASE + 1) #define DQ_PWM_OFFSET_TCM_IWARP_RQ_PROD (DQ_PWM_OFFSET_TCM16_BASE + 3) +/* DQ_DEMS_AGG_VAL_BASE */ +#define DQ_PWM_OFFSET_TCM_LL2_PROD_UPDATE \ + (DQ_PWM_OFFSET_TCM32_BASE + DQ_TCM_AGG_VAL_SEL_REG9 - 4) + #define DQ_REGION_SHIFT (12) /* DPM */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b5db1ee96d78..9bcb2f419004 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -463,7 +463,7 @@ enum qed_db_rec_space { #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) -#define DIRECT_REG_WR64(reg_addr, val) writeq((u32)val, \ +#define DIRECT_REG_WR64(reg_addr, val) writeq((u64)val, \ (void __iomem *)(reg_addr)) #define QED_COALESCE_MAX 0x1FF @@ -1177,6 +1177,8 @@ struct qed_common_ops { #define GET_FIELD(value, name) \ (((value) >> (name ## _SHIFT)) & name ## _MASK) +#define DB_ADDR_SHIFT(addr) ((addr) << DB_PWM_ADDR_OFFSET_SHIFT) + /* Debug print definitions */ #define DP_ERR(cdev, fmt, ...) \ do { \ diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 5eb022953aca..1313c34d9a68 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -52,6 +52,12 @@ enum qed_ll2_conn_type { QED_LL2_TYPE_ROCE, QED_LL2_TYPE_IWARP, QED_LL2_TYPE_RESERVED3, + MAX_QED_LL2_CONN_TYPE +}; + +enum qed_ll2_rx_conn_type { + QED_LL2_RX_TYPE_LEGACY, + QED_LL2_RX_TYPE_CTX, MAX_QED_LL2_RX_CONN_TYPE }; @@ -165,6 +171,7 @@ struct qed_ll2_cbs { }; struct qed_ll2_acquire_data_inputs { + enum qed_ll2_rx_conn_type rx_conn_type; enum qed_ll2_conn_type conn_type; u16 mtu; u16 rx_num_desc; -- cgit v1.2.3 From 1392d19ff1d6ddd370cefa73b552a0262f9c35ea Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 27 Jan 2020 15:26:13 +0200 Subject: qed: Add abstraction for different hsi values per chip The number of BTB blocks was modified to be different between the two chip flavors supported (BB/K2) as a result, this lead to a re-write of selecting the default hsi value based on the chip. This patch creates a lookup table for hsi values per chip rather than ask again and again for every value. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index a2b7826b36f0..718ce72e5965 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -663,8 +663,8 @@ #define PBF_MAX_CMD_LINES 3328 /* Number of BTB blocks. Each block is 256B. */ -#define BTB_MAX_BLOCKS 1440 - +#define BTB_MAX_BLOCKS_BB 1440 +#define BTB_MAX_BLOCKS_K2 1840 /*****************/ /* PRS CONSTANTS */ /*****************/ -- cgit v1.2.3 From 6459d93619b5bc21f775e7eb12bc4d051743d7aa Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 27 Jan 2020 15:26:14 +0200 Subject: qed: FW 8.42.2.0 iscsi/fcoe changes - Remove struct iscsi_slow_path_hdr and field fw_cid from several structs - Remove struct iscsi_spe_func_dstry - Remove fields pbe_page_size_log and pbl_page_size_log from struct iscsi_conn_offload_param Signed-off-by: Manish Rangankar Signed-off-by: Saurav Kashyap Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/iscsi_common.h | 64 ++++++++++++++------------------------ include/linux/qed/storage_common.h | 3 +- 2 files changed, 26 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 66aba505ec56..2f0a771a9176 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -999,7 +999,6 @@ struct iscsi_conn_offload_params { struct regpair r2tq_pbl_addr; struct regpair xhq_pbl_addr; struct regpair uhq_pbl_addr; - __le32 initial_ack; __le16 physical_q0; __le16 physical_q1; u8 flags; @@ -1011,10 +1010,10 @@ struct iscsi_conn_offload_params { #define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 #define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x1F #define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 3 - u8 pbl_page_size_log; - u8 pbe_page_size_log; u8 default_cq; + __le16 reserved0; __le32 stat_sn; + __le32 initial_ack; }; /* iSCSI connection statistics */ @@ -1029,25 +1028,14 @@ struct iscsi_conn_stats_params { __le32 reserved; }; -/* spe message header */ -struct iscsi_slow_path_hdr { - u8 op_code; - u8 flags; -#define ISCSI_SLOW_PATH_HDR_RESERVED0_MASK 0xF -#define ISCSI_SLOW_PATH_HDR_RESERVED0_SHIFT 0 -#define ISCSI_SLOW_PATH_HDR_LAYER_CODE_MASK 0x7 -#define ISCSI_SLOW_PATH_HDR_LAYER_CODE_SHIFT 4 -#define ISCSI_SLOW_PATH_HDR_RESERVED1_MASK 0x1 -#define ISCSI_SLOW_PATH_HDR_RESERVED1_SHIFT 7 -}; /* iSCSI connection update params passed by driver to FW in ISCSI update *ramrod. */ struct iscsi_conn_update_ramrod_params { - struct iscsi_slow_path_hdr hdr; + __le16 reserved0; __le16 conn_id; - __le32 fw_cid; + __le32 reserved1; u8 flags; #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN_MASK 0x1 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN_SHIFT 0 @@ -1065,7 +1053,7 @@ struct iscsi_conn_update_ramrod_params { #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_IMM_EN_SHIFT 6 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_LUN_MAPPER_EN_MASK 0x1 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_LUN_MAPPER_EN_SHIFT 7 - u8 reserved0[3]; + u8 reserved3[3]; __le32 max_seq_size; __le32 max_send_pdu_length; __le32 max_recv_pdu_length; @@ -1251,22 +1239,22 @@ enum iscsi_ramrod_cmd_id { /* iSCSI connection termination request */ struct iscsi_spe_conn_mac_update { - struct iscsi_slow_path_hdr hdr; + __le16 reserved0; __le16 conn_id; - __le32 fw_cid; + __le32 reserved1; __le16 remote_mac_addr_lo; __le16 remote_mac_addr_mid; __le16 remote_mac_addr_hi; - u8 reserved0[2]; + u8 reserved2[2]; }; /* iSCSI and TCP connection (Option 1) offload params passed by driver to FW in * iSCSI offload ramrod. */ struct iscsi_spe_conn_offload { - struct iscsi_slow_path_hdr hdr; + __le16 reserved0; __le16 conn_id; - __le32 fw_cid; + __le32 reserved1; struct iscsi_conn_offload_params iscsi; struct tcp_offload_params tcp; }; @@ -1275,44 +1263,36 @@ struct iscsi_spe_conn_offload { * iSCSI offload ramrod. */ struct iscsi_spe_conn_offload_option2 { - struct iscsi_slow_path_hdr hdr; + __le16 reserved0; __le16 conn_id; - __le32 fw_cid; + __le32 reserved1; struct iscsi_conn_offload_params iscsi; struct tcp_offload_params_opt2 tcp; }; /* iSCSI collect connection statistics request */ struct iscsi_spe_conn_statistics { - struct iscsi_slow_path_hdr hdr; + __le16 reserved0; __le16 conn_id; - __le32 fw_cid; + __le32 reserved1; u8 reset_stats; - u8 reserved0[7]; + u8 reserved2[7]; struct regpair stats_cnts_addr; }; /* iSCSI connection termination request */ struct iscsi_spe_conn_termination { - struct iscsi_slow_path_hdr hdr; + __le16 reserved0; __le16 conn_id; - __le32 fw_cid; + __le32 reserved1; u8 abortive; - u8 reserved0[7]; + u8 reserved2[7]; struct regpair queue_cnts_addr; struct regpair query_params_addr; }; -/* iSCSI firmware function destroy parameters */ -struct iscsi_spe_func_dstry { - struct iscsi_slow_path_hdr hdr; - __le16 reserved0; - __le32 reserved1; -}; - /* iSCSI firmware function init parameters */ struct iscsi_spe_func_init { - struct iscsi_slow_path_hdr hdr; __le16 half_way_close_timeout; u8 num_sq_pages_in_ring; u8 num_r2tq_pages_in_ring; @@ -1324,8 +1304,12 @@ struct iscsi_spe_func_init { #define ISCSI_SPE_FUNC_INIT_RESERVED0_MASK 0x7F #define ISCSI_SPE_FUNC_INIT_RESERVED0_SHIFT 1 struct iscsi_debug_modes debug_mode; - __le16 reserved1; - __le32 reserved2; + u8 params; +#define ISCSI_SPE_FUNC_INIT_MAX_SYN_RT_MASK 0xF +#define ISCSI_SPE_FUNC_INIT_MAX_SYN_RT_SHIFT 0 +#define ISCSI_SPE_FUNC_INIT_RESERVED1_MASK 0xF +#define ISCSI_SPE_FUNC_INIT_RESERVED1_SHIFT 4 + u8 reserved2[7]; struct scsi_init_func_params func_params; struct scsi_init_func_queues q_params; }; diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 505c0b48a761..9a973ffbbff5 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -107,8 +107,9 @@ struct scsi_drv_cmdq { struct scsi_init_func_params { __le16 num_tasks; u8 log_page_size; + u8 log_page_size_conn; u8 debug_mode; - u8 reserved2[12]; + u8 reserved2[11]; }; /* SCSI RQ/CQ/CMDQ firmware function init parameters */ -- cgit v1.2.3 From 0500a70d6e071040ffdaadebb966986afa83c5e9 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 27 Jan 2020 15:26:15 +0200 Subject: qed: FW 8.42.2.0 HSI changes This patch contains several HSI changes. The changes are part of features like RDMA VF and OVS, the patch also contains a fix to how the init code determines if the dmae is ready to be used. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 21 +++++++----- include/linux/qed/eth_common.h | 78 ++++++++++++++++++++++++++++++------------ 2 files changed, 68 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 718ce72e5965..2c4737e6694a 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -76,7 +76,6 @@ #define FW_ASSERT_GENERAL_ATTN_IDX 32 -#define MAX_PINNED_CCFC 32 /* Queue Zone sizes in bytes */ #define TSTORM_QZONE_SIZE 8 @@ -139,10 +138,10 @@ #define MAX_NUM_VFS (MAX_NUM_VFS_K2) #define MAX_NUM_FUNCTIONS_BB (MAX_NUM_PFS_BB + MAX_NUM_VFS_BB) -#define MAX_NUM_FUNCTIONS (MAX_NUM_PFS + MAX_NUM_VFS) #define MAX_FUNCTION_NUMBER_BB (MAX_NUM_PFS + MAX_NUM_VFS_BB) -#define MAX_FUNCTION_NUMBER (MAX_NUM_PFS + MAX_NUM_VFS) +#define MAX_FUNCTION_NUMBER_K2 (MAX_NUM_PFS + MAX_NUM_VFS_K2) +#define MAX_NUM_FUNCTIONS (MAX_FUNCTION_NUMBER_K2) #define MAX_NUM_VPORTS_K2 (208) #define MAX_NUM_VPORTS_BB (160) @@ -229,6 +228,7 @@ #define DQ_XCM_TOE_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 #define DQ_XCM_TOE_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3 #define DQ_XCM_TOE_LOCAL_ADV_WND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG4 +#define DQ_XCM_ROCE_ACK_EDPM_DORQ_SEQ_CMD DQ_XCM_AGG_VAL_SEL_WORD5 /* UCM agg val selection (HW) */ #define DQ_UCM_AGG_VAL_SEL_WORD0 0 @@ -406,6 +406,7 @@ /* Number of Protocol Indices per Status Block */ #define PIS_PER_SB_E4 12 +#define MAX_PIS_PER_SB PIS_PER_SB #define CAU_HC_STOPPED_STATE 3 #define CAU_HC_DISABLE_STATE 4 @@ -436,8 +437,6 @@ #define IGU_MEM_PBA_MSIX_RESERVED_UPPER 0x03ff #define IGU_CMD_INT_ACK_BASE 0x0400 -#define IGU_CMD_INT_ACK_UPPER (IGU_CMD_INT_ACK_BASE + \ - MAX_TOT_SB_PER_PATH - 1) #define IGU_CMD_INT_ACK_RESERVED_UPPER 0x05ff #define IGU_CMD_ATTN_BIT_UPD_UPPER 0x05f0 @@ -450,8 +449,6 @@ #define IGU_REG_SISR_MDPC_WOMASK_UPPER 0x05f6 #define IGU_CMD_PROD_UPD_BASE 0x0600 -#define IGU_CMD_PROD_UPD_UPPER (IGU_CMD_PROD_UPD_BASE +\ - MAX_TOT_SB_PER_PATH - 1) #define IGU_CMD_PROD_UPD_RESERVED_UPPER 0x07ff /*****************/ @@ -741,6 +738,8 @@ enum protocol_type { PROTOCOLID_PREROCE, PROTOCOLID_COMMON, PROTOCOLID_RESERVED1, + PROTOCOLID_RDMA, + PROTOCOLID_SCSI, MAX_PROTOCOL_TYPE }; @@ -761,6 +760,10 @@ union rdma_eqe_data { struct rdma_eqe_destroy_qp rdma_destroy_qp_data; }; +struct tstorm_queue_zone { + __le32 reserved[2]; +}; + /* Ustorm Queue Zone */ struct ustorm_eth_queue_zone { struct coalescing_timeset int_coalescing_timeset; @@ -883,8 +886,8 @@ struct db_l2_dpm_data { #define DB_L2_DPM_DATA_RESERVED0_SHIFT 27 #define DB_L2_DPM_DATA_SGE_NUM_MASK 0x7 #define DB_L2_DPM_DATA_SGE_NUM_SHIFT 28 -#define DB_L2_DPM_DATA_GFS_SRC_EN_MASK 0x1 -#define DB_L2_DPM_DATA_GFS_SRC_EN_SHIFT 31 +#define DB_L2_DPM_DATA_TGFS_SRC_EN_MASK 0x1 +#define DB_L2_DPM_DATA_TGFS_SRC_EN_SHIFT 31 }; /* Structure for SGE in a DPM doorbell of type DPM_L2_BD */ diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index d9416ad5ef59..95f5fd615852 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -38,9 +38,11 @@ /********************/ #define ETH_HSI_VER_MAJOR 3 -#define ETH_HSI_VER_MINOR 10 +#define ETH_HSI_VER_MINOR 11 -#define ETH_HSI_VER_NO_PKT_LEN_TUNN 5 +#define ETH_HSI_VER_NO_PKT_LEN_TUNN 5 +/* Maximum number of pinned L2 connections (CIDs) */ +#define ETH_PINNED_CONN_MAX_NUM 32 #define ETH_CACHE_LINE_SIZE 64 #define ETH_RX_CQE_GAP 32 @@ -61,6 +63,7 @@ #define ETH_TX_MIN_BDS_PER_TUNN_IPV6_WITH_EXT_PKT 3 #define ETH_TX_MIN_BDS_PER_IPV6_WITH_EXT_PKT 2 #define ETH_TX_MIN_BDS_PER_PKT_W_LOOPBACK_MODE 2 +#define ETH_TX_MIN_BDS_PER_PKT_W_VPORT_FORWARDING 4 #define ETH_TX_MAX_NON_LSO_PKT_LEN (9700 - (4 + 4 + 12 + 8)) #define ETH_TX_MAX_LSO_HDR_BYTES 510 #define ETH_TX_LSO_WINDOW_BDS_NUM (18 - 1) @@ -75,9 +78,8 @@ #define ETH_NUM_STATISTIC_COUNTERS_QUAD_VF_ZONE \ (ETH_NUM_STATISTIC_COUNTERS - 3 * MAX_NUM_VFS / 4) -/* Maximum number of buffers, used for RX packet placement */ #define ETH_RX_MAX_BUFF_PER_PKT 5 -#define ETH_RX_BD_THRESHOLD 12 +#define ETH_RX_BD_THRESHOLD 16 /* Num of MAC/VLAN filters */ #define ETH_NUM_MAC_FILTERS 512 @@ -96,24 +98,24 @@ #define ETH_RSS_ENGINE_NUM_BB 127 /* TPA constants */ -#define ETH_TPA_MAX_AGGS_NUM 64 -#define ETH_TPA_CQE_START_LEN_LIST_SIZE ETH_RX_MAX_BUFF_PER_PKT -#define ETH_TPA_CQE_CONT_LEN_LIST_SIZE 6 -#define ETH_TPA_CQE_END_LEN_LIST_SIZE 4 +#define ETH_TPA_MAX_AGGS_NUM 64 +#define ETH_TPA_CQE_START_BW_LEN_LIST_SIZE 2 +#define ETH_TPA_CQE_CONT_LEN_LIST_SIZE 6 +#define ETH_TPA_CQE_END_LEN_LIST_SIZE 4 /* Control frame check constants */ -#define ETH_CTL_FRAME_ETH_TYPE_NUM 4 +#define ETH_CTL_FRAME_ETH_TYPE_NUM 4 /* GFS constants */ #define ETH_GFT_TRASHCAN_VPORT 0x1FF /* GFT drop flow vport number */ /* Destination port mode */ -enum dest_port_mode { - DEST_PORT_PHY, - DEST_PORT_LOOPBACK, - DEST_PORT_PHY_LOOPBACK, - DEST_PORT_DROP, - MAX_DEST_PORT_MODE +enum dst_port_mode { + DST_PORT_PHY, + DST_PORT_LOOPBACK, + DST_PORT_PHY_LOOPBACK, + DST_PORT_DROP, + MAX_DST_PORT_MODE }; /* Ethernet address type */ @@ -167,8 +169,8 @@ struct eth_tx_data_2nd_bd { #define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_SHIFT 0 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_MASK 0x3 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_SHIFT 4 -#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_MASK 0x3 -#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_SHIFT 6 +#define ETH_TX_DATA_2ND_BD_DST_PORT_MODE_MASK 0x3 +#define ETH_TX_DATA_2ND_BD_DST_PORT_MODE_SHIFT 6 #define ETH_TX_DATA_2ND_BD_START_BD_MASK 0x1 #define ETH_TX_DATA_2ND_BD_START_BD_SHIFT 8 #define ETH_TX_DATA_2ND_BD_TUNN_TYPE_MASK 0x3 @@ -244,8 +246,9 @@ struct eth_fast_path_rx_reg_cqe { struct eth_tunnel_parsing_flags tunnel_pars_flags; u8 bd_num; u8 reserved; - __le16 flow_id; - u8 reserved1[11]; + __le16 reserved2; + __le32 flow_id_or_resource_id; + u8 reserved1[7]; struct eth_pmd_flow_flags pmd_flags; }; @@ -296,9 +299,10 @@ struct eth_fast_path_rx_tpa_start_cqe { struct eth_tunnel_parsing_flags tunnel_pars_flags; u8 tpa_agg_index; u8 header_len; - __le16 ext_bd_len_list[ETH_TPA_CQE_START_LEN_LIST_SIZE]; - __le16 flow_id; - u8 reserved; + __le16 bw_ext_bd_len_list[ETH_TPA_CQE_START_BW_LEN_LIST_SIZE]; + __le16 reserved2; + __le32 flow_id_or_resource_id; + u8 reserved[3]; struct eth_pmd_flow_flags pmd_flags; }; @@ -407,6 +411,29 @@ struct eth_tx_3rd_bd { struct eth_tx_data_3rd_bd data; }; +/* The parsing information data for the forth tx bd of a given packet. */ +struct eth_tx_data_4th_bd { + u8 dst_vport_id; + u8 reserved4; + __le16 bitfields; +#define ETH_TX_DATA_4TH_BD_DST_VPORT_ID_VALID_MASK 0x1 +#define ETH_TX_DATA_4TH_BD_DST_VPORT_ID_VALID_SHIFT 0 +#define ETH_TX_DATA_4TH_BD_RESERVED1_MASK 0x7F +#define ETH_TX_DATA_4TH_BD_RESERVED1_SHIFT 1 +#define ETH_TX_DATA_4TH_BD_START_BD_MASK 0x1 +#define ETH_TX_DATA_4TH_BD_START_BD_SHIFT 8 +#define ETH_TX_DATA_4TH_BD_RESERVED2_MASK 0x7F +#define ETH_TX_DATA_4TH_BD_RESERVED2_SHIFT 9 + __le16 reserved3; +}; + +/* The forth tx bd of a given packet */ +struct eth_tx_4th_bd { + struct regpair addr; /* Single continuous buffer */ + __le16 nbytes; /* Number of bytes in this BD */ + struct eth_tx_data_4th_bd data; /* Parsing information data */ +}; + /* Complementary information for the regular tx bd of a given packet */ struct eth_tx_data_bd { __le16 reserved0; @@ -431,6 +458,7 @@ union eth_tx_bd_types { struct eth_tx_1st_bd first_bd; struct eth_tx_2nd_bd second_bd; struct eth_tx_3rd_bd third_bd; + struct eth_tx_4th_bd fourth_bd; struct eth_tx_bd reg_bd; }; @@ -443,6 +471,12 @@ enum eth_tx_tunn_type { MAX_ETH_TX_TUNN_TYPE }; +/* Mstorm Queue Zone */ +struct mstorm_eth_queue_zone { + struct eth_rx_prod_data rx_producers; + __le32 reserved[3]; +}; + /* Ystorm Queue Zone */ struct xstorm_eth_queue_zone { struct coalescing_timeset int_coalescing_timeset; -- cgit v1.2.3 From 8a52bbab39c9791480cbae86c69ad0d47f62972e Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 27 Jan 2020 15:26:17 +0200 Subject: qed: Debug feature: ilt and mdump Part of the FW drop includes new debug capabilities implemented in the qed_debug file. This patch dumps additional information during ethtool -d for better debugging. The data dumped is the ilt (internal logical table) and information gathered by the management firmware incase there was a crash and driver was not able to extract the information (mdump). Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 9bcb2f419004..1b27c22d39af 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -159,6 +159,7 @@ struct qed_dcbx_get { enum qed_nvm_images { QED_NVM_IMAGE_ISCSI_CFG, QED_NVM_IMAGE_FCOE_CFG, + QED_NVM_IMAGE_MDUMP, QED_NVM_IMAGE_NVM_CFG1, QED_NVM_IMAGE_DEFAULT_CFG, QED_NVM_IMAGE_NVM_META, -- cgit v1.2.3 From 2d22bc8354b15abe413dff76cfe0f7aeb88ef9aa Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 27 Jan 2020 15:26:19 +0200 Subject: qed: FW 8.42.2.0 debug features Add to debug dump more information on the platform it was collected from (pci func, path id). Provide human readable reg fifo erros. Removed static debug arrays from HSI Functions, and move them to the hwfn. Some structures were slightly changed (removing reserved chip id for example) which lead to many long initializations being modified with one parameter less during initialization. This leads to some long diffs that don't really change anything. Signed-off-by: Ariel Elior 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/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 1b27c22d39af..8f29e0d8a7b3 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1178,6 +1178,15 @@ struct qed_common_ops { #define GET_FIELD(value, name) \ (((value) >> (name ## _SHIFT)) & name ## _MASK) +#define GET_MFW_FIELD(name, field) \ + (((name) & (field ## _MASK)) >> (field ## _OFFSET)) + +#define SET_MFW_FIELD(name, field, value) \ + do { \ + (name) &= ~(field ## _MASK); \ + (name) |= (((value) << (field ## _OFFSET)) & (field ## _MASK));\ + } while (0) + #define DB_ADDR_SHIFT(addr) ((addr) << DB_PWM_ADDR_OFFSET_SHIFT) /* Debug print definitions */ -- cgit v1.2.3 From 4d7ace02ba5c6ef1f8eeb32a86fef7c528bd7f36 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 26 Nov 2019 07:24:21 -0500 Subject: ceph: fix mdsmap cluster available check based on laggy number In case the max_mds > 1 in MDS cluster and there is no any standby MDS and all the max_mds MDSs are in up:active state, if one of the up:active MDSs is dead, the m->m_num_laggy in kclient will be 1. Then the mount will fail without considering other healthy MDSs. There manybe some MDSs still "in" the cluster but not in up:active state, we will ignore them. Only when all the up:active MDSs in the cluster are laggy will treat the cluster as not be available. In case decreasing the max_mds, the cluster will not stop the extra up:active MDSs immediately and there will be a latency. During it the up:active MDS number will be larger than the max_mds, so later the m_info memories will 100% be reallocated. Here will pick out the up:active MDSs as the m_num_mds and allocate the needed memories once. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/mdsmap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 0067d767c9ae..3a66f4f926ce 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -25,8 +25,9 @@ struct ceph_mdsmap { u32 m_session_timeout; /* seconds */ u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; - u32 m_max_mds; /* size of m_addr, m_state arrays */ - int m_num_mds; + u32 m_max_mds; /* expected up:active mds number */ + int m_num_active_mds; /* actual up:active mds number */ + int m_num_mds; /* size of m_info array */ struct ceph_mds_info *m_info; /* which object pools file data can be stored in */ -- cgit v1.2.3 From b38c9eb4757d5bac1eb8634a9516ef918fca2525 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 4 Dec 2019 06:57:39 -0500 Subject: ceph: add possible_max_rank and make the code more readable The m_num_mds here is actually the number for MDSs which are in up:active status, and it will be duplicated to m_num_active_mds, so remove it. Add possible_max_rank to the mdsmap struct and this will be the correctly possible largest rank boundary. Remove the special case for one mds in __mdsmap_get_random_mds(), because the validate mds rank may not always be 0. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/mdsmap.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 3a66f4f926ce..35d385296fbb 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -26,8 +26,8 @@ struct ceph_mdsmap { u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; u32 m_max_mds; /* expected up:active mds number */ - int m_num_active_mds; /* actual up:active mds number */ - int m_num_mds; /* size of m_info array */ + u32 m_num_active_mds; /* actual up:active mds number */ + u32 possible_max_rank; /* possible max rank index */ struct ceph_mds_info *m_info; /* which object pools file data can be stored in */ @@ -43,7 +43,7 @@ struct ceph_mdsmap { static inline struct ceph_entity_addr * ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) { - if (w >= m->m_num_mds) + if (w >= m->possible_max_rank) return NULL; return &m->m_info[w].addr; } @@ -51,14 +51,14 @@ ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w) { BUG_ON(w < 0); - if (w >= m->m_num_mds) + if (w >= m->possible_max_rank) return CEPH_MDS_STATE_DNE; return m->m_info[w].state; } static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w) { - if (w >= 0 && w < m->m_num_mds) + if (w >= 0 && w < m->possible_max_rank) return m->m_info[w].laggy; return false; } -- cgit v1.2.3 From 78beb0ff2feceb1d7568333f93195e1a4d95a49a Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Wed, 8 Jan 2020 10:03:53 +0000 Subject: ceph: use copy-from2 op in copy_file_range Instead of using the copy-from operation, switch copy_file_range to the new copy-from2 operation, which allows to send the truncate_seq and truncate_size parameters. If an OSD does not support the copy-from2 operation it will return -EOPNOTSUPP. In that case, the kernel client will stop trying to do remote object copies for this fs client and will always use the generic VFS copy_file_range. Signed-off-by: Luis Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 1 + include/linux/ceph/rados.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index eaffbdddf89a..5a62dbd3f4c2 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -534,6 +534,7 @@ int ceph_osdc_copy_from(struct ceph_osd_client *osdc, struct ceph_object_id *dst_oid, struct ceph_object_locator *dst_oloc, u32 dst_fadvise_flags, + u32 truncate_seq, u64 truncate_size, u8 copy_from_flags); /* watch/notify */ diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 3eb0e55665b4..59bdfd470100 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -256,6 +256,7 @@ extern const char *ceph_osd_state_name(int s); \ /* tiering */ \ f(COPY_FROM, __CEPH_OSD_OP(WR, DATA, 26), "copy-from") \ + f(COPY_FROM2, __CEPH_OSD_OP(WR, DATA, 45), "copy-from2") \ f(COPY_GET_CLASSIC, __CEPH_OSD_OP(RD, DATA, 27), "copy-get-classic") \ f(UNDIRTY, __CEPH_OSD_OP(WR, DATA, 28), "undirty") \ f(ISDIRTY, __CEPH_OSD_OP(RD, DATA, 29), "isdirty") \ @@ -446,6 +447,7 @@ enum { CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to * cloneid */ CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */ + CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ = 32, /* send truncate_{seq,size} */ }; enum { -- cgit v1.2.3 From e529ef66e6b53b34f9b8caac55950c8a55c79dac Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 18 Dec 2019 13:55:15 -0800 Subject: KVM: Move vcpu alloc and init invocation to common code Now that all architectures tightly couple vcpu allocation/free with the mandatory calls to kvm_{un}init_vcpu(), move the sequences verbatim to common KVM code. Move both allocation and initialization in a single patch to eliminate thrash in arch specific code. The bisection benefits of moving the two pieces in separate patches is marginal at best, whereas the odds of introducing a transient arch specific bug are non-zero. Acked-by: Christoffer Dall Signed-off-by: Sean Christopherson Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 432827ab7623..405ea07068f1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -876,7 +876,7 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id); +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From aaba298c6bca8d8625880a8016e5b80adc8a11af Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 18 Dec 2019 13:55:16 -0800 Subject: KVM: Unexport kvm_vcpu_cache and kvm_vcpu_{un}init() Unexport kvm_vcpu_cache and kvm_vcpu_{un}init() and make them static now that they are referenced only in kvm_main.c. Acked-by: Christoffer Dall Signed-off-by: Sean Christopherson Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 405ea07068f1..521f17cd2b26 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -157,8 +157,6 @@ static inline bool is_error_page(struct page *page) #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -extern struct kmem_cache *kvm_vcpu_cache; - extern struct mutex kvm_lock; extern struct list_head vm_list; @@ -579,8 +577,6 @@ static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ memslot++) -int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); -void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); void vcpu_load(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From afede96df55e9cba948c8cc8a682e962244285b4 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 18 Dec 2019 13:55:22 -0800 Subject: KVM: Drop kvm_arch_vcpu_setup() Remove kvm_arch_vcpu_setup() now that all arch specific implementations are nops. Acked-by: Christoffer Dall Signed-off-by: Sean Christopherson Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 521f17cd2b26..87ca40f62b06 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -873,7 +873,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From ddd259c9aaba08244dba8877687ee856f79c4f45 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 18 Dec 2019 13:55:28 -0800 Subject: KVM: Drop kvm_arch_vcpu_init() and kvm_arch_vcpu_uninit() Remove kvm_arch_vcpu_init() and kvm_arch_vcpu_uninit() now that all arch specific implementations are nops. Acked-by: Christoffer Dall Signed-off-by: Sean Christopherson Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 87ca40f62b06..a654cf6df078 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -864,9 +864,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); int kvm_arch_init(void *opaque); void kvm_arch_exit(void); -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu); -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu); - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); -- cgit v1.2.3 From ef82eddc0e3179b4529a67ed102fe4f7efba2e65 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 9 Jan 2020 09:57:11 -0500 Subject: KVM: Remove kvm_read_guest_atomic() Remove kvm_read_guest_atomic() because it's not used anywhere. Signed-off-by: Peter Xu Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a654cf6df078..83bd60f0af01 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -722,8 +722,6 @@ void kvm_get_pfn(kvm_pfn_t pfn); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); -int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, - unsigned long len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); -- cgit v1.2.3 From 7495e22bb165e7030bae4d9c6e84addb5ea17b29 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 9 Jan 2020 09:57:19 -0500 Subject: KVM: Move running VCPU from ARM to common code For ring-based dirty log tracking, it will be more efficient to account writes during schedule-out or schedule-in to the currently running VCPU. We would like to do it even if the write doesn't use the current VCPU's address space, as is the case for cached writes (see commit 4e335d9e7ddb, "Revert "KVM: Support vCPU-based gfn->hva cache"", 2017-05-02). Therefore, add a mechanism to track the currently-loaded kvm_vcpu struct. There is already something similar in KVM/ARM; one important difference is that kvm_arch_vcpu_{load,put} have two callers in virt/kvm/kvm_main.c: we have to update both the architecture-independent vcpu_{load,put} and the preempt notifiers. Another change made in the process is to allow using kvm_get_running_vcpu() in preemptible code. This is allowed because preempt notifiers ensure that the value does not change even after the VCPU thread is migrated. Signed-off-by: Paolo Bonzini Reviewed-by: Paolo Bonzini Signed-off-by: Peter Xu Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 83bd60f0af01..48e139c293c2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1335,6 +1335,9 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ +struct kvm_vcpu *kvm_get_running_vcpu(void); +struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); + #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, -- cgit v1.2.3 From e174bb94831e792a50877754c78c1f340543bb64 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Thu, 16 Jan 2020 11:32:39 +0800 Subject: KVM: remove unused guest_enter After commit 61bd0f66ff92 ("KVM: PPC: Book3S HV: Fix guest time accounting with VIRT_CPU_ACCOUNTING_GEN"), no one use this function anymore, So better to remove it. Signed-off-by: Alex Shi Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Frederic Weisbecker Cc: linux-kernel@vger.kernel.org Signed-off-by: Paolo Bonzini --- include/linux/context_tracking.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 64ec82851aa3..8150f5ac176c 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -154,15 +154,6 @@ static inline void guest_exit_irqoff(void) } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -static inline void guest_enter(void) -{ - unsigned long flags; - - local_irq_save(flags); - guest_enter_irqoff(); - local_irq_restore(flags); -} - static inline void guest_exit(void) { unsigned long flags; -- cgit v1.2.3 From 005ba37cb89bcc0cf63c2029a41f8db165aeb615 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 8 Jan 2020 12:24:36 -0800 Subject: mm: thp: KVM: Explicitly check for THP when populating secondary MMU Add a helper, is_transparent_hugepage(), to explicitly check whether a compound page is a THP and use it when populating KVM's secondary MMU. The explicit check fixes a bug where a remapped compound page, e.g. for an XDP Rx socket, is mapped into a KVM guest and is mistaken for a THP, which results in KVM incorrectly creating a huge page in its secondary MMU. Fixes: 936a5fe6e6148 ("thp: kvm mmu transparent hugepage support") Reported-by: syzbot+c9d1fb51ac9d0d10c39d@syzkaller.appspotmail.com Cc: Andrea Arcangeli Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/huge_mm.h | 6 ++++++ include/linux/kvm_host.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 0b84e13e88e2..5aca3d1bdb32 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -160,6 +160,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp, extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); +bool is_transparent_hugepage(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); @@ -308,6 +309,11 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, static inline void prep_transhuge_page(struct page *page) {} +static inline bool is_transparent_hugepage(struct page *page) +{ + return false; +} + #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 48e139c293c2..46fdb7533678 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -976,6 +976,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); +bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; -- cgit v1.2.3 From f9b84e19221efc5f493156ee0329df3142085f28 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 8 Jan 2020 12:24:37 -0800 Subject: KVM: Use vcpu-specific gva->hva translation when querying host page size Use kvm_vcpu_gfn_to_hva() when retrieving the host page size so that the correct set of memslots is used when handling x86 page faults in SMM. Fixes: 54bf36aac520 ("KVM: x86: use vcpu-specific functions to read/write/translate GFNs") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 46fdb7533678..6d5331b0d937 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -762,7 +762,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); -unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); +unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, 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 f1ec3a517b4352e78dbef6b1e591f43202ecb3fe Mon Sep 17 00:00:00 2001 From: Benjamin Thiel Date: Thu, 9 Jan 2020 14:13:51 +0100 Subject: kernel/events: Add a missing prototype for arch_perf_update_userpage() ... in order to fix a -Wmissing-prototype warning. No functional changes. Signed-off-by: Benjamin Thiel Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20200109131351.9468-1-b.thiel@posteo.de --- include/linux/perf_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6d4c22aee384..52928e089bc7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1544,4 +1544,8 @@ int perf_event_exit_cpu(unsigned int cpu); #define perf_event_exit_cpu NULL #endif +extern void __weak arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, + u64 now); + #endif /* _LINUX_PERF_EVENT_H */ -- cgit v1.2.3 From ebc0f83c78a2d26384401ecf2d2fa48063c0ee27 Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Sat, 11 Jan 2020 04:53:39 -0500 Subject: timers/nohz: Update NOHZ load in remote tick The way loadavg is tracked during nohz only pays attention to the load upon entering nohz. This can be particularly noticeable if full nohz is entered while non-idle, and then the cpu goes idle and stays that way for a long time. Use the remote tick to ensure that full nohz cpus report their deltas within a reasonable time. [ swood: Added changelog and removed recheck of stopped tick. ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Scott Wood Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/1578736419-14628-3-git-send-email-swood@redhat.com --- include/linux/sched/nohz.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 1abe91ff6e4a..6d67e9a5af6b 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -15,9 +15,11 @@ static inline void nohz_balance_enter_idle(int cpu) { } #ifdef CONFIG_NO_HZ_COMMON void calc_load_nohz_start(void); +void calc_load_nohz_remote(struct rq *rq); void calc_load_nohz_stop(void); #else static inline void calc_load_nohz_start(void) { } +static inline void calc_load_nohz_remote(struct rq *rq) { } static inline void calc_load_nohz_stop(void) { } #endif /* CONFIG_NO_HZ_COMMON */ -- cgit v1.2.3 From 73ef657275c01928c30c8cec5878834d44af9685 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 3 Jan 2020 00:10:59 +0100 Subject: clk: composite: add _register_composite_pdata() variants Add support for the new way of specifying the clock parents. Add the two new functions clk_hw_register_composite_pdata() clk_register_composite_pdata() to let the driver provide parent_data instead of the parent_names. Signed-off-by: Michael Walle Link: https://lkml.kernel.org/r/20200102231101.11834-1-michael@walle.cc Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index caf4b9df16eb..e2e9d867df36 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -743,6 +743,12 @@ struct clk *clk_register_composite(struct device *dev, const char *name, struct clk_hw *rate_hw, const struct clk_ops *rate_ops, struct clk_hw *gate_hw, const struct clk_ops *gate_ops, unsigned long flags); +struct clk *clk_register_composite_pdata(struct device *dev, const char *name, + const struct clk_parent_data *parent_data, int num_parents, + struct clk_hw *mux_hw, const struct clk_ops *mux_ops, + struct clk_hw *rate_hw, const struct clk_ops *rate_ops, + struct clk_hw *gate_hw, const struct clk_ops *gate_ops, + unsigned long flags); void clk_unregister_composite(struct clk *clk); struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name, const char * const *parent_names, int num_parents, @@ -750,6 +756,13 @@ struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name, struct clk_hw *rate_hw, const struct clk_ops *rate_ops, struct clk_hw *gate_hw, const struct clk_ops *gate_ops, unsigned long flags); +struct clk_hw *clk_hw_register_composite_pdata(struct device *dev, + const char *name, + const struct clk_parent_data *parent_data, int num_parents, + struct clk_hw *mux_hw, const struct clk_ops *mux_ops, + struct clk_hw *rate_hw, const struct clk_ops *rate_ops, + struct clk_hw *gate_hw, const struct clk_ops *gate_ops, + unsigned long flags); void clk_hw_unregister_composite(struct clk_hw *hw); /** -- cgit v1.2.3 From 6ac7e4d7ad70640310feedc2e5f1cb712685cb05 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 19 Dec 2019 10:31:44 +0000 Subject: mfd: wcd934x: Add support to wcd9340/wcd9341 codec Qualcomm WCD9340/WCD9341 Codec is a standalone Hi-Fi audio codec IC. This codec has integrated SoundWire controller, pin controller and interrupt controller. Signed-off-by: Srinivas Kandagatla Reviewed-by: Pierre-Louis Bossart Signed-off-by: Lee Jones --- include/linux/mfd/wcd934x/registers.h | 531 ++++++++++++++++++++++++++++++++++ include/linux/mfd/wcd934x/wcd934x.h | 31 ++ 2 files changed, 562 insertions(+) create mode 100644 include/linux/mfd/wcd934x/registers.h create mode 100644 include/linux/mfd/wcd934x/wcd934x.h (limited to 'include/linux') diff --git a/include/linux/mfd/wcd934x/registers.h b/include/linux/mfd/wcd934x/registers.h new file mode 100644 index 000000000000..bb8d2e276668 --- /dev/null +++ b/include/linux/mfd/wcd934x/registers.h @@ -0,0 +1,531 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _WCD934X_REGISTERS_H +#define _WCD934X_REGISTERS_H + +#define WCD934X_CODEC_RPM_CLK_GATE 0x0002 +#define WCD934X_CODEC_RPM_CLK_GATE_MASK GENMASK(1, 0) +#define WCD934X_CODEC_RPM_CLK_MCLK_CFG 0x0003 +#define WCD934X_CODEC_RPM_CLK_MCLK_CFG_9P6MHZ BIT(0) +#define WCD934X_CODEC_RPM_CLK_MCLK_CFG_12P288MHZ BIT(1) +#define WCD934X_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK GENMASK(1, 0) +#define WCD934X_CODEC_RPM_RST_CTL 0x0009 +#define WCD934X_CODEC_RPM_PWR_CDC_DIG_HM_CTL 0x0011 +#define WCD934X_CHIP_TIER_CTRL_CHIP_ID_BYTE0 0x0021 +#define WCD934X_CHIP_TIER_CTRL_CHIP_ID_BYTE2 0x0023 +#define WCD934X_CHIP_TIER_CTRL_EFUSE_CTL 0x0025 +#define WCD934X_EFUSE_SENSE_STATE_MASK GENMASK(4, 1) +#define WCD934X_EFUSE_SENSE_STATE_DEF 0x10 +#define WCD934X_EFUSE_SENSE_EN_MASK BIT(0) +#define WCD934X_EFUSE_SENSE_ENABLE BIT(0) +#define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT14 0x0037 +#define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT15 0x0038 +#define WCD934X_CHIP_TIER_CTRL_EFUSE_STATUS 0x0039 +#define WCD934X_DATA_HUB_SB_TX10_INP_CFG 0x006b +#define WCD934X_DATA_HUB_SB_TX11_INP_CFG 0x006c +#define WCD934X_DATA_HUB_SB_TX13_INP_CFG 0x006e +#define WCD934X_CPE_FLL_CONFIG_CTL_2 0x0111 +#define WCD934X_CPE_SS_CPARMAD_BUFRDY_INT_PERIOD 0x0213 +#define WCD934X_CPE_SS_SVA_CFG 0x0214 +#define WCD934X_CPE_SS_DMIC0_CTL 0x0218 +#define WCD934X_CPE_SS_DMIC1_CTL 0x0219 +#define WCD934X_DMIC_RATE_MASK GENMASK(3, 1) +#define WCD934X_CPE_SS_DMIC2_CTL 0x021a +#define WCD934X_CPE_SS_DMIC_CFG 0x021b +#define WCD934X_CPE_SS_DMIC_CFG 0x021b +#define WCD934X_CPE_SS_CPAR_CFG 0x021c +#define WCD934X_INTR_PIN1_MASK0 0x0409 +#define WCD934X_INTR_PIN1_STATUS0 0x0411 +#define WCD934X_INTR_PIN1_CLEAR0 0x0419 +#define WCD934X_INTR_PIN2_CLEAR3 0x0434 +#define WCD934X_INTR_LEVEL0 0x0461 +/* INTR_REG 0 */ +#define WCD934X_IRQ_SLIMBUS 0 +#define WCD934X_IRQ_MISC 1 +#define WCD934X_IRQ_HPH_PA_OCPL_FAULT 2 +#define WCD934X_IRQ_HPH_PA_OCPR_FAULT 3 +#define WCD934X_IRQ_EAR_PA_OCP_FAULT 4 +#define WCD934X_IRQ_HPH_PA_CNPL_COMPLETE 5 +#define WCD934X_IRQ_HPH_PA_CNPR_COMPLETE 6 +#define WCD934X_IRQ_EAR_PA_CNP_COMPLETE 7 +/* INTR_REG 1 */ +#define WCD934X_IRQ_MBHC_SW_DET 8 +#define WCD934X_IRQ_MBHC_ELECT_INS_REM_DET 9 +#define WCD934X_IRQ_MBHC_BUTTON_PRESS_DET 10 +#define WCD934X_IRQ_MBHC_BUTTON_RELEASE_DET 11 +#define WCD934X_IRQ_MBHC_ELECT_INS_REM_LEG_DET 12 +#define WCD934X_IRQ_RESERVED_0 13 +#define WCD934X_IRQ_RESERVED_1 14 +#define WCD934X_IRQ_RESERVED_2 15 +/* INTR_REG 2 */ +#define WCD934X_IRQ_LINE_PA1_CNP_COMPLETE 16 +#define WCD934X_IRQ_LINE_PA2_CNP_COMPLETE 17 +#define WCD934X_IRQ_SLNQ_ANALOG_ERROR 18 +#define WCD934X_IRQ_RESERVED_3 19 +#define WCD934X_IRQ_SOUNDWIRE 20 +#define WCD934X_IRQ_VDD_DIG_RAMP_COMPLETE 21 +#define WCD934X_IRQ_RCO_ERROR 22 +#define WCD934X_IRQ_CPE_ERROR 23 +/* INTR_REG 3 */ +#define WCD934X_IRQ_MAD_AUDIO 24 +#define WCD934X_IRQ_MAD_BEACON 25 +#define WCD934X_IRQ_MAD_ULTRASOUND 26 +#define WCD934X_IRQ_VBAT_ATTACK 27 +#define WCD934X_IRQ_VBAT_RESTORE 28 +#define WCD934X_IRQ_CPE1_INTR 29 +#define WCD934X_IRQ_RESERVED_4 30 +#define WCD934X_IRQ_SLNQ_DIGITAL 31 +#define WCD934X_NUM_IRQS 32 +#define WCD934X_ANA_BIAS 0x0601 +#define WCD934X_ANA_BIAS_EN_MASK BIT(7) +#define WCD934X_ANA_BIAS_EN BIT(7) +#define WCD934X_ANA_PRECHRG_EN_MASK BIT(6) +#define WCD934X_ANA_PRECHRG_EN BIT(6) +#define WCD934X_ANA_PRECHRG_MODE_MASK BIT(5) +#define WCD934X_ANA_PRECHRG_MODE_AUTO BIT(5) +#define WCD934X_ANA_RCO 0x0603 +#define WCD934X_ANA_RCO_BG_EN_MASK BIT(7) +#define WCD934X_ANA_RCO_BG_ENABLE BIT(7) +#define WCD934X_ANA_BUCK_CTL 0x0606 +#define WCD934X_ANA_BUCK_HI_ACCU_PRE_ENX_MASK GENMASK(1, 0) +#define WCD934X_ANA_BUCK_PRE_EN2_MASK BIT(0) +#define WCD934X_ANA_BUCK_PRE_EN2_ENABLE BIT(0) +#define WCD934X_ANA_BUCK_PRE_EN1_MASK BIT(1) +#define WCD934X_ANA_BUCK_PRE_EN1_ENABLE BIT(1) +#define WCD934X_ANA_BUCK_HI_ACCU_EN_MASK BIT(2) +#define WCD934X_ANA_BUCK_HI_ACCU_ENABLE BIT(2) +#define WCD934X_ANA_RX_SUPPLIES 0x0608 +#define WCD934X_ANA_HPH 0x0609 +#define WCD934X_ANA_EAR 0x060a +#define WCD934X_ANA_LO_1_2 0x060b +#define WCD934X_ANA_AMIC1 0x060e +#define WCD934X_ANA_AMIC2 0x060f +#define WCD934X_ANA_AMIC3 0x0610 +#define WCD934X_ANA_AMIC4 0x0611 +#define WCD934X_ANA_MBHC_MECH 0x0614 +#define WCD934X_ANA_MBHC_ELECT 0x0615 +#define WCD934X_ANA_MBHC_ZDET 0x0616 +#define WCD934X_ANA_MBHC_RESULT_1 0x0617 +#define WCD934X_ANA_MBHC_RESULT_2 0x0618 +#define WCD934X_ANA_MBHC_RESULT_3 0x0619 +#define WCD934X_ANA_MICB1 0x0622 +#define WCD934X_MICB_VAL_MASK GENMASK(5, 0) +#define WCD934X_ANA_MICB_EN_MASK GENMASK(7, 6) +#define WCD934X_ANA_MICB_PULL_UP 0x80 +#define WCD934X_ANA_MICB_ENABLE 0x40 +#define WCD934X_ANA_MICB_DISABLE 0x0 +#define WCD934X_ANA_MICB2 0x0623 +#define WCD934X_ANA_MICB3 0x0625 +#define WCD934X_ANA_MICB4 0x0626 +#define WCD934X_BIAS_VBG_FINE_ADJ 0x0629 +#define WCD934X_MICB1_TEST_CTL_1 0x066b +#define WCD934X_MICB1_TEST_CTL_2 0x066c +#define WCD934X_MICB2_TEST_CTL_1 0x066e +#define WCD934X_MICB3_TEST_CTL_1 0x0671 +#define WCD934X_MICB4_TEST_CTL_1 0x0674 +#define WCD934X_CLASSH_MODE_1 0x0697 +#define WCD934X_CLASSH_MODE_2 0x0698 +#define WCD934X_CLASSH_MODE_3 0x0699 +#define WCD934X_CLASSH_CTRL_VCL_1 0x069a +#define WCD934X_CLASSH_CTRL_VCL_2 0x069b +#define WCD934X_CLASSH_CTRL_CCL_1 0x069c +#define WCD934X_CLASSH_CTRL_CCL_2 0x069d +#define WCD934X_CLASSH_CTRL_CCL_3 0x069e +#define WCD934X_CLASSH_CTRL_CCL_4 0x069f +#define WCD934X_CLASSH_CTRL_CCL_5 0x06a0 +#define WCD934X_CLASSH_BUCK_TMUX_A_D 0x06a1 +#define WCD934X_CLASSH_BUCK_SW_DRV_CNTL 0x06a2 +#define WCD934X_RX_OCP_CTL 0x06b6 +#define WCD934X_RX_OCP_COUNT 0x06b7 +#define WCD934X_HPH_CNP_EN 0x06cb +#define WCD934X_HPH_CNP_WG_CTL 0x06cc +#define WCD934X_HPH_GM3_BOOST_EN_MASK BIT(7) +#define WCD934X_HPH_GM3_BOOST_ENABLE BIT(7) +#define WCD934X_HPH_OCP_CTL 0x06ce +#define WCD934X_HPH_L_EN 0x06d3 +#define WCD934X_HPH_GAIN_SRC_SEL_MASK BIT(5) +#define WCD934X_HPH_GAIN_SRC_SEL_COMPANDER 0 +#define WCD934X_HPH_GAIN_SRC_SEL_REGISTER BIT(5) +#define WCD934X_HPH_L_TEST 0x06d4 +#define WCD934X_HPH_R_EN 0x06d6 +#define WCD934X_HPH_R_TEST 0x06d7 +#define WCD934X_HPH_OCP_DET_MASK BIT(0) +#define WCD934X_HPH_OCP_DET_ENABLE BIT(0) +#define WCD934X_HPH_OCP_DET_DISABLE 0 +#define WCD934X_DIFF_LO_LO2_COMPANDER 0x06ea +#define WCD934X_DIFF_LO_LO1_COMPANDER 0x06eb +#define WCD934X_CLK_SYS_MCLK_PRG 0x0711 +#define WCD934X_EXT_CLK_BUF_EN_MASK BIT(7) +#define WCD934X_EXT_CLK_BUF_EN BIT(7) +#define WCD934X_EXT_CLK_DIV_RATIO_MASK GENMASK(5, 4) +#define WCD934X_EXT_CLK_DIV_BY_2 0x10 +#define WCD934X_MCLK_SRC_MASK BIT(1) +#define WCD934X_MCLK_SRC_EXT_CLK 0 +#define WCD934X_MCLK_SRC_MASK BIT(1) +#define WCD934X_MCLK_EN_MASK BIT(0) +#define WCD934X_MCLK_EN BIT(0) +#define WCD934X_CLK_SYS_MCLK2_PRG1 0x0712 +#define WCD934X_CLK_SYS_MCLK2_PRG2 0x0713 +#define WCD934X_SIDO_NEW_VOUT_A_STARTUP 0x071b +#define WCD934X_SIDO_NEW_VOUT_D_STARTUP 0x071c +#define WCD934X_SIDO_NEW_VOUT_D_FREQ1 0x071d +#define WCD934X_SIDO_NEW_VOUT_D_FREQ2 0x071e +#define WCD934X_SIDO_RIPPLE_FREQ_EN_MASK BIT(0) +#define WCD934X_SIDO_RIPPLE_FREQ_ENABLE BIT(0) +#define WCD934X_MBHC_NEW_CTL_2 0x0721 +#define WCD934X_TX_NEW_AMIC_4_5_SEL 0x0727 +#define WCD934X_HPH_NEW_INT_RDAC_HD2_CTL_L 0x0733 +#define WCD934X_HPH_NEW_INT_RDAC_OVERRIDE_CTL 0x0735 +#define WCD934X_HPH_NEW_INT_RDAC_HD2_CTL_R 0x0736 +#define WCD934X_HPH_NEW_INT_HPH_TIMER1 0x073a +#define WCD934X_HPH_AUTOCHOP_TIMER_EN_MASK BIT(1) +#define WCD934X_HPH_AUTOCHOP_TIMER_ENABLE BIT(1) +#define WCD934X_CDC_TX0_TX_PATH_CTL 0x0a31 +#define WCD934X_CDC_TX_PATH_CTL_PCM_RATE_MASK GENMASK(3, 0) +#define WCD934X_CDC_TX_PATH_CTL(dec) (0xa31 + dec * 0x10) +#define WCD934X_CDC_TX0_TX_PATH_CFG0 0x0a32 +#define WCD934X_CDC_TX0_TX_PATH_CFG1 0x0a33 +#define WCD934X_CDC_TX0_TX_VOL_CTL 0x0a34 +#define WCD934X_CDC_TX0_TX_PATH_192_CTL 0x0a35 +#define WCD934X_CDC_TX0_TX_PATH_192_CFG 0x0a36 +#define WCD934X_CDC_TX0_TX_PATH_SEC2 0x0a39 +#define WCD934X_HPH_CUTOFF_FREQ_CHANGE_REQ_MASK BIT(1) +#define WCD934X_HPH_CUTOFF_FREQ_CHANGE_REQ BIT(1) +#define WCD934X_CDC_TX1_TX_PATH_CTL 0x0a41 +#define WCD934X_CDC_TX1_TX_PATH_CFG0 0x0a42 +#define WCD934X_CDC_TX1_TX_PATH_CFG1 0x0a43 +#define WCD934X_CDC_TX1_TX_VOL_CTL 0x0a44 +#define WCD934X_CDC_TX2_TX_PATH_CTL 0x0a51 +#define WCD934X_CDC_TX2_TX_PATH_CFG0 0x0a52 +#define WCD934X_CDC_TX2_TX_PATH_CFG1 0x0a53 +#define WCD934X_CDC_TX2_TX_VOL_CTL 0x0a54 +#define WCD934X_CDC_TX3_TX_PATH_CTL 0x0a61 +#define WCD934X_CDC_TX3_TX_PATH_CFG0 0x0a62 +#define WCD934X_CDC_TX3_TX_PATH_CFG1 0x0a63 +#define WCD934X_CDC_TX3_TX_VOL_CTL 0x0a64 +#define WCD934X_CDC_TX3_TX_PATH_192_CTL 0x0a65 +#define WCD934X_CDC_TX3_TX_PATH_192_CFG 0x0a66 +#define WCD934X_CDC_TX4_TX_PATH_CTL 0x0a71 +#define WCD934X_CDC_TX4_TX_PATH_CFG0 0x0a72 +#define WCD934X_CDC_TX4_TX_PATH_CFG1 0x0a73 +#define WCD934X_CDC_TX4_TX_VOL_CTL 0x0a74 +#define WCD934X_CDC_TX4_TX_PATH_192_CTL 0x0a75 +#define WCD934X_CDC_TX4_TX_PATH_192_CFG 0x0a76 +#define WCD934X_CDC_TX5_TX_PATH_CTL 0x0a81 +#define WCD934X_CDC_TX5_TX_PATH_CFG0 0x0a82 +#define WCD934X_CDC_TX5_TX_PATH_CFG1 0x0a83 +#define WCD934X_CDC_TX5_TX_VOL_CTL 0x0a84 +#define WCD934X_CDC_TX5_TX_PATH_192_CTL 0x0a85 +#define WCD934X_CDC_TX5_TX_PATH_192_CFG 0x0a86 +#define WCD934X_CDC_TX6_TX_PATH_CTL 0x0a91 +#define WCD934X_CDC_TX6_TX_PATH_CFG0 0x0a92 +#define WCD934X_CDC_TX6_TX_PATH_CFG1 0x0a93 +#define WCD934X_CDC_TX6_TX_VOL_CTL 0x0a94 +#define WCD934X_CDC_TX6_TX_PATH_192_CTL 0x0a95 +#define WCD934X_CDC_TX6_TX_PATH_192_CFG 0x0a96 +#define WCD934X_CDC_TX7_TX_PATH_CTL 0x0aa1 +#define WCD934X_CDC_TX7_TX_PATH_CFG0 0x0aa2 +#define WCD934X_CDC_TX7_TX_PATH_CFG1 0x0aa3 +#define WCD934X_CDC_TX7_TX_VOL_CTL 0x0aa4 +#define WCD934X_CDC_TX7_TX_PATH_192_CTL 0x0aa5 +#define WCD934X_CDC_TX7_TX_PATH_192_CFG 0x0aa6 +#define WCD934X_CDC_TX8_TX_PATH_CTL 0x0ab1 +#define WCD934X_CDC_TX8_TX_PATH_CFG0 0x0ab2 +#define WCD934X_CDC_TX8_TX_PATH_CFG1 0x0ab3 +#define WCD934X_CDC_TX8_TX_VOL_CTL 0x0ab4 +#define WCD934X_CDC_TX8_TX_PATH_192_CTL 0x0ab5 +#define WCD934X_CDC_TX8_TX_PATH_192_CFG 0x0ab6 +#define WCD934X_CDC_TX9_SPKR_PROT_PATH_CFG0 0x0ac3 +#define WCD934X_CDC_TX10_SPKR_PROT_PATH_CFG0 0x0ac7 +#define WCD934X_CDC_TX11_SPKR_PROT_PATH_CFG0 0x0acb +#define WCD934X_CDC_TX12_SPKR_PROT_PATH_CFG0 0x0acf +#define WCD934X_CDC_COMPANDER1_CTL0 0x0b01 +#define WCD934X_COMP_CLK_EN_MASK BIT(0) +#define WCD934X_COMP_CLK_ENABLE BIT(0) +#define WCD934X_COMP_SOFT_RST_MASK BIT(1) +#define WCD934X_COMP_SOFT_RST_ENABLE BIT(1) +#define WCD934X_COMP_HALT_MASK BIT(2) +#define WCD934X_COMP_HALT BIT(2) +#define WCD934X_COMP_SOFT_RST_DISABLE 0 +#define WCD934X_CDC_COMPANDER1_CTL7 0x0b08 +#define WCD934X_HPH_LOW_PWR_MODE_EN_MASK BIT(5) +#define WCD934X_CDC_COMPANDER2_CTL7 0x0b10 +#define WCD934X_CDC_COMPANDER7_CTL3 0x0b34 +#define WCD934X_CDC_COMPANDER7_CTL7 0x0b38 +#define WCD934X_CDC_COMPANDER8_CTL3 0x0b3c +#define WCD934X_CDC_COMPANDER8_CTL7 0x0b40 +#define WCD934X_CDC_RX0_RX_PATH_CTL 0x0b41 +#define WCD934X_CDC_RX_PGA_MUTE_EN_MASK BIT(4) +#define WCD934X_CDC_RX_PGA_MUTE_ENABLE BIT(4) +#define WCD934X_CDC_RX_PGA_MUTE_DISABLE 0 +#define WCD934X_RX_CLK_EN_MASK BIT(5) +#define WCD934X_RX_CLK_ENABLE BIT(5) +#define WCD934X_RX_RESET_MASK BIT(6) +#define WCD934X_RX_RESET_ENABLE BIT(6) +#define WCD934X_RX_RESET_DISABLE 0 +#define WCD934X_RX_PCM_RATE_MASK GENMASK(3, 0) +#define WCD934X_RX_PCM_RATE_F_48K 0x04 +#define WCD934X_CDC_RX_PATH_CTL(rx) (0xb41 + rx * 0x14) +#define WCD934X_CDC_MIX_PCM_RATE_MASK GENMASK(3, 0) +#define WCD934X_CDC_RX0_RX_PATH_CFG0 0x0b42 +#define WCD934X_RX_DLY_ZN_EN_MASK BIT(3) +#define WCD934X_RX_DLY_ZN_ENABLE BIT(3) +#define WCD934X_RX_DLY_ZN_DISABLE 0 +#define WCD934X_CDC_RX0_RX_PATH_CFG1 0x0b43 +#define WCD934X_CDC_RX0_RX_PATH_CFG2 0x0b44 +#define WCD934X_CDC_RX0_RX_VOL_CTL 0x0b45 +#define WCD934X_CDC_RX0_RX_PATH_MIX_CTL 0x0b46 +#define WCD934X_CDC_RX_MIX_CLK_EN_MASK BIT(5) +#define WCD934X_CDC_RX_MIX_CLK_ENABLE BIT(5) +#define WCD934X_CDC_RX_PATH_MIX_CTL(rx) (0xb46 + rx * 0x14) +#define WCD934X_CDC_RX0_RX_PATH_MIX_CFG 0x0b47 +#define WCD934X_CDC_RX0_RX_VOL_MIX_CTL 0x0b48 +#define WCD934X_CDC_RX0_RX_PATH_SEC0 0x0b49 +#define WCD934X_CDC_RX0_RX_PATH_DSMDEM_CTL 0x0b53 +#define WCD934X_CDC_RX1_RX_PATH_CTL 0x0b55 +#define WCD934X_RX_PATH_PGA_MUTE_EN_MASK BIT(4) +#define WCD934X_RX_PATH_PGA_MUTE_ENABLE BIT(4) +#define WCD934X_CDC_RX_PATH_PGA_MUTE_DISABLE 0 +#define WCD934X_CDC_RX_PATH_CLK_EN_MASK BIT(5) +#define WCD934X_CDC_RX_PATH_CLK_ENABLE BIT(5) +#define WCD934X_CDC_RX_PATH_CLK_DISABLE 0 +#define WCD934X_CDC_RX1_RX_PATH_CFG0 0x0b56 +#define WCD934X_HPH_CMP_EN_MASK BIT(1) +#define WCD934X_HPH_CMP_ENABLE BIT(1) +#define WCD934X_HPH_CMP_DISABLE 0 +#define WCD934X_CDC_RX1_RX_PATH_CFG2 0x0b58 +#define WCD934X_CDC_RX1_RX_VOL_CTL 0x0b59 +#define WCD934X_CDC_RX1_RX_PATH_MIX_CTL 0x0b5a +#define WCD934X_CDC_RX1_RX_PATH_MIX_CFG 0x0b5b +#define WCD934X_CDC_RX1_RX_VOL_MIX_CTL 0x0b5c +#define WCD934X_CDC_RX1_RX_PATH_SEC0 0x0b5d +#define WCD934X_CDC_RX1_RX_PATH_SEC3 0x0b60 +#define WCD934X_CDC_RX_PATH_SEC_HD2_ALPHA_MASK GENMASK(5, 2) +#define WCD934X_CDC_RX_PATH_SEC_HD2_ALPHA_0P3125 0x14 +#define WCD934X_CDC_RX_PATH_SEC_HD2_ALPHA_0P0000 0 +#define WCD934X_CDC_RX1_RX_PATH_DSMDEM_CTL 0x0b67 +#define WCD934X_CDC_RX2_RX_PATH_CTL 0x0b69 +#define WCD934X_CDC_RX2_RX_PATH_CFG0 0x0b6a +#define WCD934X_CDC_RX_PATH_CFG_HD2_EN_MASK BIT(2) +#define WCD934X_CDC_RX_PATH_CFG_HD2_ENABLE BIT(2) +#define WCD934X_CDC_RX_PATH_CFG_HD2_DISABLE 0 +#define WCD934X_CDC_RX2_RX_PATH_CFG2 0x0b6c +#define WCD934X_CDC_RX2_RX_VOL_CTL 0x0b6d +#define WCD934X_CDC_RX2_RX_PATH_MIX_CTL 0x0b6e +#define WCD934X_CDC_RX2_RX_PATH_MIX_CFG 0x0b6f +#define WCD934X_CDC_RX2_RX_VOL_MIX_CTL 0x0b70 +#define WCD934X_CDC_RX2_RX_PATH_SEC0 0x0b71 +#define WCD934X_CDC_RX2_RX_PATH_SEC3 0x0b74 +#define WCD934X_CDC_RX2_RX_PATH_DSMDEM_CTL 0x0b7b +#define WCD934X_CDC_RX3_RX_PATH_CTL 0x0b7d +#define WCD934X_CDC_RX3_RX_PATH_CFG0 0x0b6e +#define WCD934X_CDC_RX3_RX_PATH_CFG2 0x0b80 +#define WCD934X_CDC_RX3_RX_VOL_CTL 0x0b81 +#define WCD934X_CDC_RX3_RX_PATH_MIX_CTL 0x0b82 +#define WCD934X_CDC_RX3_RX_PATH_MIX_CFG 0x0b83 +#define WCD934X_CDC_RX3_RX_VOL_MIX_CTL 0x0b84 +#define WCD934X_CDC_RX3_RX_PATH_SEC0 0x0b85 +#define WCD934X_CDC_RX3_RX_PATH_DSMDEM_CTL 0x0b8f +#define WCD934X_CDC_RX4_RX_PATH_CTL 0x0b91 +#define WCD934X_CDC_RX4_RX_PATH_CFG0 0x0b92 +#define WCD934X_CDC_RX4_RX_PATH_CFG2 0x0b94 +#define WCD934X_CDC_RX4_RX_VOL_CTL 0x0b95 +#define WCD934X_CDC_RX4_RX_PATH_MIX_CTL 0x0b96 +#define WCD934X_CDC_RX4_RX_PATH_MIX_CFG 0x0b97 +#define WCD934X_CDC_RX4_RX_VOL_MIX_CTL 0x0b98 +#define WCD934X_CDC_RX4_RX_PATH_SEC0 0x0b99 +#define WCD934X_CDC_RX4_RX_PATH_DSMDEM_CTL 0x0ba3 +#define WCD934X_CDC_RX7_RX_PATH_CTL 0x0bcd +#define WCD934X_CDC_RX7_RX_PATH_CFG0 0x0bce +#define WCD934X_CDC_RX7_RX_PATH_CFG1 0x0bcf +#define WCD934X_CDC_RX7_RX_PATH_CFG2 0x0bd0 +#define WCD934X_CDC_RX7_RX_VOL_CTL 0x0bd1 +#define WCD934X_CDC_RX7_RX_PATH_MIX_CTL 0x0bd2 +#define WCD934X_CDC_RX7_RX_PATH_MIX_CFG 0x0bd3 +#define WCD934X_CDC_RX7_RX_VOL_MIX_CTL 0x0bd4 +#define WCD934X_CDC_RX7_RX_PATH_SEC1 0x0bd6 +#define WCD934X_CDC_RX7_RX_PATH_MIX_SEC0 0x0bdd +#define WCD934X_CDC_RX7_RX_PATH_DSMDEM_CTL 0x0bdf +#define WCD934X_CDC_RX8_RX_PATH_CTL 0x0be1 +#define WCD934X_CDC_RX8_RX_PATH_CFG0 0x0be2 +#define WCD934X_CDC_RX8_RX_PATH_CFG1 0x0be3 +#define WCD934X_RX_SMART_BOOST_EN_MASK BIT(0) +#define WCD934X_RX_SMART_BOOST_ENABLE BIT(0) +#define WCD934X_RX_SMART_BOOST_DISABLE 0 +#define WCD934X_CDC_RX8_RX_PATH_CFG2 0x0be4 +#define WCD934X_CDC_RX8_RX_VOL_CTL 0x0be5 +#define WCD934X_CDC_RX8_RX_PATH_MIX_CTL 0x0be6 +#define WCD934X_CDC_RX8_RX_PATH_MIX_CFG 0x0be7 +#define WCD934X_CDC_RX8_RX_VOL_MIX_CTL 0x0be8 +#define WCD934X_CDC_RX8_RX_PATH_SEC1 0x0bea +#define WCD934X_CDC_RX8_RX_PATH_MIX_SEC0 0x0bf1 +#define WCD934X_CDC_RX8_RX_PATH_DSMDEM_CTL 0x0bf3 +#define WCD934X_CDC_CLSH_DECAY_CTRL 0x0c03 +#define WCD934X_CDC_CLSH_K2_MSB 0x0c0a +#define WCD934X_CDC_CLSH_K2_LSB 0x0c0b +#define WCD934X_CDC_CLSH_TEST0 0x0c0f +#define WCD934X_CDC_BOOST0_BOOST_PATH_CTL 0x0c19 +#define WCD934X_BOOST_PATH_CLK_EN_MASK BIT(4) +#define WCD934X_BOOST_PATH_CLK_ENABLE BIT(4) +#define WCD934X_BOOST_PATH_CLK_DISABLE 0 +#define WCD934X_CDC_BOOST0_BOOST_CTL 0x0c1a +#define WCD934X_CDC_BOOST0_BOOST_CFG1 0x0c1b +#define WCD934X_CDC_BOOST0_BOOST_CFG2 0x0c1c +#define WCD934X_CDC_BOOST1_BOOST_PATH_CTL 0x0c21 +#define WCD934X_CDC_BOOST1_BOOST_CTL 0x0c22 +#define WCD934X_CDC_BOOST1_BOOST_CFG1 0x0c23 +#define WCD934X_CDC_BOOST1_BOOST_CFG2 0x0c24 +#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_0 0x0c91 +#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_1 0x0c92 +#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_2 0x0c93 +#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_3 0x0c94 +#define WCD934X_SWR_AHB_BRIDGE_ACCESS_STATUS 0x0c96 +#define WCD934X_CDC_SIDETONE_SRC0_ST_SRC_PATH_CTL 0x0cb5 +#define WCD934X_CDC_SIDETONE_SRC1_ST_SRC_PATH_CTL 0x0cb9 +#define WCD934X_CDC_RX_INP_MUX_RX_INT0_CFG0 0x0d01 +#define WCD934X_CDC_RX_INP_MUX_RX_INT_CFG0(i) (0xd01 + i * 0x2) +#define WCD934X_CDC_RX_INP_MUX_RX_INT_SEL_MASK GENMASK(3, 0) +#define WCD934X_CDC_RX_INP_MUX_RX_INT0_CFG1 0x0d02 +#define WCD934X_CDC_RX_INP_MUX_RX_INT_CFG1(i) (0xd02 + i * 0x2) +#define WCD934X_CDC_RX_INP_MUX_RX_INT1_CFG0 0x0d03 +#define WCD934X_CDC_RX_INP_MUX_RX_INT1_CFG1 0x0d04 +#define WCD934X_CDC_RX_INP_MUX_RX_INT2_CFG0 0x0d05 +#define WCD934X_CDC_RX_INP_MUX_RX_INT2_CFG1 0x0d06 +#define WCD934X_CDC_RX_INP_MUX_RX_INT3_CFG0 0x0d07 +#define WCD934X_CDC_RX_INP_MUX_RX_INT3_CFG1 0x0d08 +#define WCD934X_CDC_RX_INP_MUX_RX_INT4_CFG0 0x0d09 +#define WCD934X_CDC_RX_INP_MUX_RX_INT4_CFG1 0x0d0a +#define WCD934X_CDC_RX_INP_MUX_RX_INT7_CFG0 0x0d0f +#define WCD934X_CDC_RX_INP_MUX_RX_INT7_CFG1 0x0d10 +#define WCD934X_CDC_RX_INP_MUX_RX_INT8_CFG0 0x0d11 +#define WCD934X_CDC_RX_INP_MUX_RX_INT8_CFG1 0x0d12 +#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG0 0x0d13 +#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG1 0x0d14 +#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG2 0x0d15 +#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG3 0x0d16 +#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG4 0x0d17 +#define WCD934X_CDC_RX_INP_MUX_SIDETONE_SRC_CFG0 0x0d18 +#define WCD934X_CDC_RX_INP_MUX_SIDETONE_SRC_CFG1 0x0d19 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX0_CFG0 0x0d1d +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX0_CFG1 0x0d1e +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX1_CFG0 0x0d1f +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX1_CFG1 0x0d20 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX2_CFG0 0x0d21 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX2_CFG1 0x0d22 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX3_CFG0 0x0d23 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX3_CFG1 0x0d25 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX4_CFG0 0x0d26 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX5_CFG0 0x0d27 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX6_CFG0 0x0d28 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX7_CFG0 0x0d29 +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX8_CFG0 0x0d2a +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX10_CFG0 0x0d2b +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX11_CFG0 0x0d2c +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX12_CFG0 0x0d2d +#define WCD934X_CDC_TX_INP_MUX_ADC_MUX13_CFG0 0x0d2e +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG0 0x0d31 +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG1 0x0d32 +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG2 0x0d33 +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG3 0x0d34 +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG0 0x0d35 +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG1 0x0d36 +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG2 0x0d37 +#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG3 0x0d38 +#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG0 0x0d3a +#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG1 0x0d3b +#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG2 0x0d3c +#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG3 0x0d3d +#define WCD934X_CDC_CLK_RST_CTRL_MCLK_CONTROL 0x0d41 +#define WCD934X_CDC_MCLK_EN_MASK BIT(0) +#define WCD934X_CDC_MCLK_EN_ENABLE BIT(0) +#define WCD934X_CDC_CLK_RST_CTRL_FS_CNT_CONTROL 0x0d42 +#define WCD934X_CDC_FS_MCLK_CNT_EN_MASK BIT(0) +#define WCD934X_CDC_FS_MCLK_CNT_ENABLE BIT(0) +#define WCD934X_CDC_CLK_RST_CTRL_SWR_CONTROL 0x0d43 +#define WCD934X_CDC_SWR_CLK_EN_MASK BIT(0) +#define WCD934X_CDC_SWR_CLK_ENABLE BIT(0) +#define WCD934X_CDC_CLK_RST_CTRL_DSD_CONTROL 0x0d44 +#define WCD934X_CDC_CLK_RST_CTRL_ASRC_SHARE_CONTROL 0x0d45 +#define WCD934X_CDC_CLK_RST_CTRL_GFM_CONTROL 0x0d46 +#define WCD934X_CDC_SIDETONE_IIR0_IIR_PATH_CTL 0x0d55 +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B1_CTL 0x0d56 +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B2_CTL 0x0d57 +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B3_CTL 0x0d58 +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B4_CTL 0x0d59 +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B5_CTL 0x0d5a +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B6_CTL 0x0d5b +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B7_CTL 0x0d5c +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B8_CTL 0x0d5d +#define WCD934X_CDC_SIDETONE_IIR0_IIR_CTL 0x0d5e +#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_TIMER_CTL 0x0d5f +#define WCD934X_CDC_SIDETONE_IIR0_IIR_COEF_B1_CTL 0x0d60 +#define WCD934X_CDC_SIDETONE_IIR0_IIR_COEF_B2_CTL 0x0d61 +#define WCD934X_CDC_SIDETONE_IIR1_IIR_PATH_CTL 0x0d65 +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B1_CTL 0x0d66 +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B2_CTL 0x0d67 +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B3_CTL 0x0d68 +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B4_CTL 0x0d69 +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B5_CTL 0x0d6a +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B6_CTL 0x0d6b +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B7_CTL 0x0d6c +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B8_CTL 0x0d6d +#define WCD934X_CDC_SIDETONE_IIR1_IIR_CTL 0x0d6e +#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_TIMER_CTL 0x0d6f +#define WCD934X_CDC_SIDETONE_IIR1_IIR_COEF_B1_CTL 0x0d70 +#define WCD934X_CDC_SIDETONE_IIR1_IIR_COEF_B2_CTL 0x0d71 +#define WCD934X_CDC_TOP_TOP_CFG1 0x0d82 +#define WCD934X_CDC_TOP_TOP_CFG7 0x0d88 +#define WCD934X_CDC_TOP_HPHL_COMP_LUT 0x0d8b +#define WCD934X_CDC_TOP_HPHR_COMP_LUT 0x0d90 +#define WCD934X_HPH_LUT_BYPASS_MASK BIT(7) +#define WCD934X_HPH_LUT_BYPASS_ENABLE BIT(7) +#define WCD934X_HPH_LUT_BYPASS_DISABLE 0 +#define WCD934X_CODEC_CPR_WR_DATA_0 0x5001 +#define WCD934X_CODEC_CPR_WR_ADDR_0 0x5005 +#define WCD934X_CODEC_CPR_SVS_CX_VDD 0x5022 +#define WCD934X_CODEC_CPR_SVS2_CX_VDD 0x5023 +#define WCD934X_CODEC_CPR_SVS2_MIN_CX_VDD 0x5027 +#define WCD934X_TLMM_DMIC1_CLK_PINCFG 0x8015 +#define WCD934X_TLMM_DMIC1_DATA_PINCFG 0x8016 +#define WCD934X_TLMM_DMIC2_CLK_PINCFG 0x8017 +#define WCD934X_TLMM_DMIC2_DATA_PINCFG 0x8018 +#define WCD934X_TLMM_DMIC3_CLK_PINCFG 0x8019 +#define WCD934X_TLMM_DMIC3_DATA_PINCFG 0x801a +#define WCD934X_TEST_DEBUG_PAD_DRVCTL_0 0x803b +#define WCD934X_TEST_DEBUG_NPL_DLY_TEST_1 0x803e + +#define WCD934X_MAX_REGISTER 0xffff +#define WCD934X_SEL_REGISTER 0x800 +#define WCD934X_SEL_MASK 0xff +#define WCD934X_SEL_SHIFT 0x0 +#define WCD934X_WINDOW_START 0x800 +#define WCD934X_WINDOW_LENGTH 0x100 + +/* SLIMBUS Slave Registers */ +#define WCD934X_SLIM_PGD_PORT_INT_EN0 0x30 +#define WCD934X_SLIM_PGD_PORT_INT_STATUS_RX_0 0x34 +#define WCD934X_SLIM_PGD_PORT_INT_STATUS_RX_1 0x35 +#define WCD934X_SLIM_PGD_PORT_INT_STATUS_TX_0 0x36 +#define WCD934X_SLIM_PGD_PORT_INT_STATUS_TX_1 0x37 +#define WCD934X_SLIM_PGD_PORT_INT_CLR_RX_0 0x38 +#define WCD934X_SLIM_PGD_PORT_INT_CLR_RX_1 0x39 +#define WCD934X_SLIM_PGD_PORT_INT_CLR_TX_0 0x3A +#define WCD934X_SLIM_PGD_PORT_INT_CLR_TX_1 0x3B +#define WCD934X_SLIM_PGD_PORT_INT_RX_SOURCE0 0x60 +#define WCD934X_SLIM_PGD_PORT_INT_TX_SOURCE0 0x70 +#define WCD934X_SLIM_PGD_RX_PORT_CFG(p) (0x30 + p) +#define WCD934X_SLIM_PGD_PORT_CFG(p) (0x40 + p) +#define WCD934X_SLIM_PGD_TX_PORT_CFG(p) (0x50 + p) +#define WCD934X_SLIM_PGD_PORT_INT_SRC(p) (0x60 + p) +#define WCD934X_SLIM_PGD_PORT_INT_STATUS(p) (0x80 + p) +#define WCD934X_SLIM_PGD_TX_PORT_MULTI_CHNL_0(p) (0x100 + 4 * p) +/* ports range from 10-16 */ +#define WCD934X_SLIM_PGD_TX_PORT_MULTI_CHNL_1(p) (0x101 + 4 * p) +#define WCD934X_SLIM_PGD_RX_PORT_MULTI_CHNL_0(p) (0x140 + 4 * p) + +#define SLIM_MANF_ID_QCOM 0x217 +#define SLIM_PROD_CODE_WCD9340 0x250 +#define SLIM_DEV_IDX_WCD9340 0x1 +#define SLIM_DEV_INSTANCE_ID_WCD9340 0 + +#endif diff --git a/include/linux/mfd/wcd934x/wcd934x.h b/include/linux/mfd/wcd934x/wcd934x.h new file mode 100644 index 000000000000..f3c65a035150 --- /dev/null +++ b/include/linux/mfd/wcd934x/wcd934x.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __WCD934X_H__ +#define __WCD934X_H__ +#include +#include +#include +#include + +#define WCD934X_MAX_SUPPLY 5 + +/** + * struct wcd934x_ddata - wcd934x driver data + * + * @supplies: wcd934x regulator supplies + * @irq_data: wcd934x irq_chip data + * @regmap: wcd934x regmap pointer + * @extclk: External clock + * @dev: device instance of wcd934x slim device + * @irq: irq for wcd934x. + */ +struct wcd934x_ddata { + struct regulator_bulk_data supplies[WCD934X_MAX_SUPPLY]; + struct regmap_irq_chip_data *irq_data; + struct regmap *regmap; + struct clk *extclk; + struct device *dev; + int irq; +}; + +#endif /* __WCD934X_H__ */ -- cgit v1.2.3 From d3e42bb0a329fadff98fcb927714d0a486840e3b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 27 Jan 2020 09:51:45 -0800 Subject: bpf: Reuse log from btf_prase_vmlinux() in btf_struct_ops_init() Instead of using a locally defined "struct bpf_verifier_log log = {}", btf_struct_ops_init() should reuse the "log" from its calling function "btf_parse_vmlinux()". It should also resolve the frame-size too large compiler warning in some ARCH. Fixes: 27ae7997a661 ("bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS") Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200127175145.1154438-1-kafai@fb.com --- include/linux/bpf.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8e9ad3943cd9..49b1a70e12c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -728,7 +728,7 @@ struct bpf_struct_ops { #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); -void bpf_struct_ops_init(struct btf *btf); +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -752,7 +752,10 @@ static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { return NULL; } -static inline void bpf_struct_ops_init(struct btf *btf) { } +static inline void bpf_struct_ops_init(struct btf *btf, + struct bpf_verifier_log *log) +{ +} static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); -- cgit v1.2.3 From ae2dd7164943e03644293af92802550d052632e6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 29 Jan 2020 15:54:46 +0100 Subject: mptcp: handle tcp fallback when using syn cookies We can't deal with syncookie mode yet, the syncookie rx path will create tcp reqsk, i.e. we get OOB access because we treat tcp reqsk as mptcp reqsk one: TCP: SYN flooding on port 20002. Sending cookies. BUG: KASAN: slab-out-of-bounds in subflow_syn_recv_sock+0x451/0x4d0 net/mptcp/subflow.c:191 Read of size 1 at addr ffff8881167bc148 by task syz-executor099/2120 subflow_syn_recv_sock+0x451/0x4d0 net/mptcp/subflow.c:191 tcp_get_cookie_sock+0xcf/0x520 net/ipv4/syncookies.c:209 cookie_v6_check+0x15a5/0x1e90 net/ipv6/syncookies.c:252 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1123 [inline] [..] Bug can be reproduced via "sysctl net.ipv4.tcp_syncookies=2". Note that MPTCP should work with syncookies (4th ack would carry needed state), but it appears better to sort that out in -next so do tcp fallback for now. I removed the MPTCP ifdef for tcp_rsk "is_mptcp" member because if (IS_ENABLED()) is easier to read than "#ifdef IS_ENABLED()/#endif" pair. Cc: Eric Dumazet Fixes: cec37a6e41aae7bf ("mptcp: Handle MP_CAPABLE options for outgoing connections") Reported-by: Christoph Paasch Tested-by: Christoph Paasch Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1cf73e6f85ca..3dc964010fef 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -148,9 +148,7 @@ struct tcp_request_sock { const struct tcp_request_sock_ops *af_specific; u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; -#if IS_ENABLED(CONFIG_MPTCP) bool is_mptcp; -#endif u32 txhash; u32 rcv_isn; u32 snt_isn; -- cgit v1.2.3 From 39220e8d4a2aaab045ea03cc16d737e85d0817bf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 8 Jan 2020 15:05:37 -0700 Subject: eventpoll: support non-blocking do_epoll_ctl() calls Also make it available outside of epoll, along with the helper that decides if we need to copy the passed in epoll_event. Signed-off-by: Jens Axboe --- include/linux/eventpoll.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index bc6d79b00c4e..8f000fada5a4 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -61,6 +61,15 @@ static inline void eventpoll_release(struct file *file) eventpoll_release_file(file); } +int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, + bool nonblock); + +/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ +static inline int ep_op_has_event(int op) +{ + return op != EPOLL_CTL_DEL; +} + #else static inline void eventpoll_init_file(struct file *file) {} -- cgit v1.2.3 From 10a663a1b15134a5a714aa515e11425a44d4fdf7 Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Sat, 25 Jan 2020 03:37:29 +0000 Subject: ata: ahci: Add shutdown to freeze hardware resources of ahci device_shutdown() called from reboot or power_shutdown expect all devices to be shutdown. Same is true for even ahci pci driver. As no ahci shutdown function is implemented, the ata subsystem always remains alive with DMA & interrupt support. File system related calls should not be honored after device_shutdown(). So defining ahci pci driver shutdown to freeze hardware (mask interrupt, stop DMA engine and free DMA resources). Signed-off-by: Prabhakar Kushwaha Signed-off-by: Jens Axboe --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 2dbde119721d..bff539918d82 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1221,6 +1221,7 @@ struct pci_bits { }; extern int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits); +extern void ata_pci_shutdown_one(struct pci_dev *pdev); extern void ata_pci_remove_one(struct pci_dev *pdev); #ifdef CONFIG_PM -- cgit v1.2.3 From 2fd3c5c617937cde5aafa48db4f4056e1f705987 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 21 Jan 2020 16:06:42 +0300 Subject: ide: make drive->dn read only The IDE core always sets ->dn correctly so changing it is never required. Setting it to a different value than assigned by IDE core is very likely to result in data corruption (due to wrong transfer timings being set on the controller etc.) Signed-off-by: Dan Carpenter Acked-by: Bartlomiej Zolnierkiewicz Tested-by: Bartlomiej Zolnierkiewicz Signed-off-by: David S. Miller --- include/linux/ide.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 46b771d6999e..25046ffa5a4a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -943,6 +943,10 @@ ide_devset_get(_name, _field); \ ide_devset_set(_name, _field); \ IDE_DEVSET(_name, DS_SYNC, get_##_name, set_##_name) +#define ide_devset_ro_field(_name, _field) \ +ide_devset_get(_name, _field); \ +IDE_DEVSET(_name, 0, get_##_name, NULL) + #define ide_devset_rw_flag(_name, _field) \ ide_devset_get_flag(_name, _field); \ ide_devset_set_flag(_name, _field); \ -- cgit v1.2.3 From e3e2a2cc9c96725457ad6f31712ea7681a55666e Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Wed, 29 Jan 2020 12:59:22 -0600 Subject: tracing: Add trace_get/put_event_file() Add a function to get an event file and prevent it from going away on module or instance removal. trace_get_event_file() will find an event file in a given instance (if instance is NULL, it assumes the top trace array) and return it, pinning the instance's trace array as well as the event's module, if applicable, so they won't go away while in use. trace_put_event_file() does the matching release. Link: http://lkml.kernel.org/r/bb31ac4bdda168d5ed3c4b5f5a4c8f633e8d9118.1580323897.git.zanussi@kernel.org Acked-by: Masami Hiramatsu Signed-off-by: Tom Zanussi [ Moved trace_array_put() to end of trace_put_event_file() ] Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 20948ee56f8c..8d621a73c97e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -349,6 +349,11 @@ enum { EVENT_FILE_FL_WAS_ENABLED_BIT, }; +extern struct trace_event_file *trace_get_event_file(const char *instance, + const char *system, + const char *event); +extern void trace_put_event_file(struct trace_event_file *file); + /* * Event file flags: * ENABLED - The event is enabled -- cgit v1.2.3 From f5f6b255a253e2c3132ca283e9090a6343bfb719 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Wed, 29 Jan 2020 12:59:23 -0600 Subject: tracing: Add synth_event_delete() create_or_delete_synth_event() contains code to delete a synthetic event, which would be useful on its own - specifically, it would be useful to allow event-creating modules to call it separately. Separate out the delete code from that function and create an exported function named synth_event_delete(). Link: http://lkml.kernel.org/r/050db3b06df7f0a4b8a2922da602d1d879c7c1c2.1580323897.git.zanussi@kernel.org Acked-by: Masami Hiramatsu Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8d621a73c97e..25fe743bcbaf 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -354,6 +354,8 @@ extern struct trace_event_file *trace_get_event_file(const char *instance, const char *event); extern void trace_put_event_file(struct trace_event_file *file); +extern int synth_event_delete(const char *name); + /* * Event file flags: * ENABLED - The event is enabled -- cgit v1.2.3 From 86c5426baddae9ff192e3159b9c2e7c14e3964c6 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Wed, 29 Jan 2020 12:59:24 -0600 Subject: tracing: Add dynamic event command creation interface Add an interface used to build up dynamic event creation commands, such as synthetic and kprobe events. Interfaces specific to those particular types of events and others can be built on top of this interface. Command creation is started by first using the dynevent_cmd_init() function to initialize the dynevent_cmd object. Following that, args are appended and optionally checked by the dynevent_arg_add() and dynevent_arg_pair_add() functions, which use objects representing arguments and pairs of arguments, initialized respectively by dynevent_arg_init() and dynevent_arg_pair_init(). Finally, once all args have been successfully added, the command is finalized and actually created using dynevent_create(). The code here for actually printing into the dyn_event->cmd buffer using snprintf() etc was adapted from v4 of Masami's 'tracing/boot: Add synthetic event support' patch. Link: http://lkml.kernel.org/r/1f65fa44390b6f238f6036777c3784ced1dcc6a0.1580323897.git.zanussi@kernel.org Signed-off-by: Tom Zanussi Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 25fe743bcbaf..651b03d5e272 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -354,6 +354,29 @@ extern struct trace_event_file *trace_get_event_file(const char *instance, const char *event); extern void trace_put_event_file(struct trace_event_file *file); +#define MAX_DYNEVENT_CMD_LEN (2048) + +enum dynevent_type { + DYNEVENT_TYPE_NONE, +}; + +struct dynevent_cmd; + +typedef int (*dynevent_create_fn_t)(struct dynevent_cmd *cmd); + +struct dynevent_cmd { + char *buf; + const char *event_name; + int maxlen; + int remaining; + unsigned int n_fields; + enum dynevent_type type; + dynevent_create_fn_t run_command; + void *private_data; +}; + +extern int dynevent_create(struct dynevent_cmd *cmd); + extern int synth_event_delete(const char *name); /* -- cgit v1.2.3 From 35ca5207c2d111abb9e072f028945d5c12b20836 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Wed, 29 Jan 2020 12:59:25 -0600 Subject: tracing: Add synthetic event command generation functions Add functions used to generate synthetic event commands, built on top of the dynevent_cmd interface. synth_event_gen_cmd_start() is used to create a synthetic event command using a variable arg list and synth_event_gen_cmd_array_start() does the same thing but using an array of field descriptors. synth_event_add_field(), synth_event_add_field_str() and synth_event_add_fields() can be used to add single fields one by one or as a group. Once all desired fields are added, synth_event_gen_cmd_end() is used to actually execute the command and create the event. synth_event_create() does everything, including creating the event, in a single call. Link: http://lkml.kernel.org/r/38fef702fad5ef208009f459552f34a94befd860.1580323897.git.zanussi@kernel.org Acked-by: Masami Hiramatsu Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 651b03d5e272..07b83532a3c6 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -357,6 +357,7 @@ extern void trace_put_event_file(struct trace_event_file *file); #define MAX_DYNEVENT_CMD_LEN (2048) enum dynevent_type { + DYNEVENT_TYPE_SYNTH = 1, DYNEVENT_TYPE_NONE, }; @@ -379,6 +380,42 @@ extern int dynevent_create(struct dynevent_cmd *cmd); extern int synth_event_delete(const char *name); +extern void synth_event_cmd_init(struct dynevent_cmd *cmd, + char *buf, int maxlen); + +extern int __synth_event_gen_cmd_start(struct dynevent_cmd *cmd, + const char *name, + struct module *mod, ...); + +#define synth_event_gen_cmd_start(cmd, name, mod, ...) \ + __synth_event_gen_cmd_start(cmd, name, mod, ## __VA_ARGS__, NULL) + +struct synth_field_desc { + const char *type; + const char *name; +}; + +extern int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, + const char *name, + struct module *mod, + struct synth_field_desc *fields, + unsigned int n_fields); +extern int synth_event_create(const char *name, + struct synth_field_desc *fields, + unsigned int n_fields, struct module *mod); + +extern int synth_event_add_field(struct dynevent_cmd *cmd, + const char *type, + const char *name); +extern int synth_event_add_field_str(struct dynevent_cmd *cmd, + const char *type_name); +extern int synth_event_add_fields(struct dynevent_cmd *cmd, + struct synth_field_desc *fields, + unsigned int n_fields); + +#define synth_event_gen_cmd_end(cmd) \ + dynevent_create(cmd) + /* * Event file flags: * ENABLED - The event is enabled -- cgit v1.2.3 From 8dcc53ad956d2caf4c5c2dda196e6801b71a3154 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Wed, 29 Jan 2020 12:59:27 -0600 Subject: tracing: Add synth_event_trace() and related functions Add an exported function named synth_event_trace(), allowing modules or other kernel code to trace synthetic events. Also added are several functions that allow the same functionality to be broken out in a piecewise fashion, which are useful in situations where tracing an event from a full array of values would be cumbersome. Those functions are synth_event_trace_start/end() and synth_event_add_(next)_val(). Link: http://lkml.kernel.org/r/7a84de5f1854acf4144b57efe835ca645afa764f.1580323897.git.zanussi@kernel.org Acked-by: Masami Hiramatsu Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 07b83532a3c6..bf03d12efb28 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -416,6 +416,32 @@ extern int synth_event_add_fields(struct dynevent_cmd *cmd, #define synth_event_gen_cmd_end(cmd) \ dynevent_create(cmd) +struct synth_event; + +struct synth_event_trace_state { + struct trace_event_buffer fbuffer; + struct synth_trace_event *entry; + struct trace_buffer *buffer; + struct synth_event *event; + unsigned int cur_field; + unsigned int n_u64; + bool enabled; + bool add_next; + bool add_name; +}; + +extern int synth_event_trace(struct trace_event_file *file, + unsigned int n_vals, ...); +extern int synth_event_trace_array(struct trace_event_file *file, u64 *vals, + unsigned int n_vals); +extern int synth_event_trace_start(struct trace_event_file *file, + struct synth_event_trace_state *trace_state); +extern int synth_event_add_next_val(u64 val, + struct synth_event_trace_state *trace_state); +extern int synth_event_add_val(const char *field_name, u64 val, + struct synth_event_trace_state *trace_state); +extern int synth_event_trace_end(struct synth_event_trace_state *trace_state); + /* * Event file flags: * ENABLED - The event is enabled -- cgit v1.2.3 From 2a588dd1d5d649a183a2ff6fa1b80e870cf821d8 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Wed, 29 Jan 2020 12:59:29 -0600 Subject: tracing: Add kprobe event command generation functions Add functions used to generate kprobe event commands, built on top of the dynevent_cmd interface. kprobe_event_gen_cmd_start() is used to create a kprobe event command using a variable arg list, and kretprobe_event_gen_cmd_start() does the same for kretprobe event commands. kprobe_event_add_fields() can be used to add single fields one by one or as a group. Once all desired fields are added, kprobe_event_gen_cmd_end() or kretprobe_event_gen_cmd_end() respectively are used to actually execute the command and create the event. Link: http://lkml.kernel.org/r/95cc4696502bb6017f9126f306a45ad19b4cc14f.1580323897.git.zanussi@kernel.org Acked-by: Masami Hiramatsu Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index bf03d12efb28..7c307a7c9c6a 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -358,6 +358,7 @@ extern void trace_put_event_file(struct trace_event_file *file); enum dynevent_type { DYNEVENT_TYPE_SYNTH = 1, + DYNEVENT_TYPE_KPROBE, DYNEVENT_TYPE_NONE, }; @@ -442,6 +443,36 @@ extern int synth_event_add_val(const char *field_name, u64 val, struct synth_event_trace_state *trace_state); extern int synth_event_trace_end(struct synth_event_trace_state *trace_state); +extern int kprobe_event_delete(const char *name); + +extern void kprobe_event_cmd_init(struct dynevent_cmd *cmd, + char *buf, int maxlen); + +#define kprobe_event_gen_cmd_start(cmd, name, loc, ...) \ + __kprobe_event_gen_cmd_start(cmd, false, name, loc, ## __VA_ARGS__, NULL) + +#define kretprobe_event_gen_cmd_start(cmd, name, loc, ...) \ + __kprobe_event_gen_cmd_start(cmd, true, name, loc, ## __VA_ARGS__, NULL) + +extern int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, + bool kretprobe, + const char *name, + const char *loc, ...); + +#define kprobe_event_add_fields(cmd, ...) \ + __kprobe_event_add_fields(cmd, ## __VA_ARGS__, NULL) + +#define kprobe_event_add_field(cmd, field) \ + __kprobe_event_add_fields(cmd, field, NULL) + +extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...); + +#define kprobe_event_gen_cmd_end(cmd) \ + dynevent_create(cmd) + +#define kretprobe_event_gen_cmd_end(cmd) \ + dynevent_create(cmd) + /* * Event file flags: * ENABLED - The event is enabled -- cgit v1.2.3 From 1eff70a9abd46f175defafd29bc17ad456f398a7 Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Tue, 12 Nov 2019 16:35:06 +0000 Subject: x86/kvm: Introduce kvm_(un)map_gfn() kvm_vcpu_(un)map operates on gfns from any current address space. In certain cases we want to make sure we are not mapping SMRAM and for that we can use kvm_(un)map_gfn() that we are introducing in this patch. This is part of CVE-2019-3016. Signed-off-by: Boris Ostrovsky Reviewed-by: Joao Martins Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 538c25e778c0..0cb78f55b92c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -775,8 +775,10 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); +int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); +int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, -- cgit v1.2.3 From 917248144db5d7320655dbb41d3af0b8a0f3d589 Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Thu, 5 Dec 2019 01:30:51 +0000 Subject: x86/kvm: Cache gfn to pfn translation __kvm_map_gfn()'s call to gfn_to_pfn_memslot() is * relatively expensive * in certain cases (such as when done from atomic context) cannot be called Stashing gfn-to-pfn mapping should help with both cases. This is part of CVE-2019-3016. Signed-off-by: Boris Ostrovsky Reviewed-by: Joao Martins Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 7 +++++-- include/linux/kvm_types.h | 9 ++++++++- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0cb78f55b92c..71cb9cc105f0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -723,6 +723,7 @@ void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); void kvm_get_pfn(kvm_pfn_t pfn); +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, @@ -775,10 +776,12 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map); +int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, + struct gfn_to_pfn_cache *cache, bool atomic); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); +int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, + struct gfn_to_pfn_cache *cache, bool dirty, bool atomic); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 1c88e69db3d9..68e84cf42a3f 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -18,7 +18,7 @@ struct kvm_memslots; enum kvm_mr_change; -#include +#include /* * Address types: @@ -51,4 +51,11 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; +struct gfn_to_pfn_cache { + u64 generation; + gfn_t gfn; + kvm_pfn_t pfn; + bool dirty; +}; + #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3 From c67c10a67f6b2edcc7804317947cbfdeab71048c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Sat, 9 Nov 2019 11:16:41 -0800 Subject: kdb: kdb_current_regs should be private As of the patch ("MIPS: kdb: Remove old workaround for backtracing on other CPUs") there is no reason for kdb_current_regs to be in the public "kdb.h". Let's move it next to kdb_current_task. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20191109111623.2.Iadbfb484e90b557cc4b5ac9890bfca732cd99d77@changeid Signed-off-by: Daniel Thompson --- include/linux/kdb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 68bd88223417..24cd447659e0 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -183,8 +183,6 @@ int kdb_process_cpu(const struct task_struct *p) return cpu; } -/* kdb access to register set for stack dumping */ -extern struct pt_regs *kdb_current_regs; #ifdef CONFIG_KALLSYMS extern const char *kdb_walk_kallsyms(loff_t *pos); #else /* ! CONFIG_KALLSYMS */ -- cgit v1.2.3 From 68f23b89067fdf187763e75a56087550624fdbee Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 30 Jan 2020 22:11:04 -0800 Subject: memcg: fix a crash in wb_workfn when a device disappears Without memcg, there is a one-to-one mapping between the bdi and bdi_writeback structures. In this world, things are fairly straightforward; the first thing bdi_unregister() does is to shutdown the bdi_writeback structure (or wb), and part of that writeback ensures that no other work queued against the wb, and that the wb is fully drained. With memcg, however, there is a one-to-many relationship between the bdi and bdi_writeback structures; that is, there are multiple wb objects which can all point to a single bdi. There is a refcount which prevents the bdi object from being released (and hence, unregistered). So in theory, the bdi_unregister() *should* only get called once its refcount goes to zero (bdi_put will drop the refcount, and when it is zero, release_bdi gets called, which calls bdi_unregister). Unfortunately, del_gendisk() in block/gen_hd.c never got the memo about the Brave New memcg World, and calls bdi_unregister directly. It does this without informing the file system, or the memcg code, or anything else. This causes the root wb associated with the bdi to be unregistered, but none of the memcg-specific wb's are shutdown. So when one of these wb's are woken up to do delayed work, they try to dereference their wb->bdi->dev to fetch the device name, but unfortunately bdi->dev is now NULL, thanks to the bdi_unregister() called by del_gendisk(). As a result, *boom*. Fortunately, it looks like the rest of the writeback path is perfectly happy with bdi->dev and bdi->owner being NULL, so the simplest fix is to create a bdi_dev_name() function which can handle bdi->dev being NULL. This also allows us to bulletproof the writeback tracepoints to prevent them from dereferencing a NULL pointer and crashing the kernel if one is tracing with memcg's enabled, and an iSCSI device dies or a USB storage stick is pulled. The most common way of triggering this will be hotremoval of a device while writeback with memcg enabled is going on. It was triggering several times a day in a heavily loaded production environment. Google Bug Id: 145475544 Link: https://lore.kernel.org/r/20191227194829.150110-1-tytso@mit.edu Link: http://lkml.kernel.org/r/20191228005211.163952-1-tytso@mit.edu Signed-off-by: Theodore Ts'o Cc: Chris Mason Cc: Tejun Heo Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 97967ce06de3..f88197c1ffc2 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -504,4 +505,13 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << WB_async_congested)); } +extern const char *bdi_unknown_name; + +static inline const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return dev_name(bdi->dev); +} + #endif /* _LINUX_BACKING_DEV_H */ -- cgit v1.2.3 From dd3e7cba16274831f5a69f071ed3cf13ffb352ea Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Jan 2020 22:11:47 -0800 Subject: ocfs2/dlm: move BITS_TO_BYTES() to bitops.h for wider use There are users already and will be more of BITS_TO_BYTES() macro. Move it to bitops.h for wider use. In the case of ocfs2 the replacement is identical. As for bnx2x, there are two places where floor version is used. In the first case to calculate the amount of structures that can fit one memory page. In this case obviously the ceiling variant is correct and original code might have a potential bug, if amount of bits % 8 is not 0. In the second case the macro is used to calculate bytes transmitted in one microsecond. This will work for all speeds which is multiply of 1Gbps without any change, for the rest new code will give ceiling value, for instance 100Mbps will give 13 bytes, while old code gives 12 bytes and the arithmetically correct one is 12.5 bytes. Further the value is used to setup timer threshold which in any case has its own margins due to certain resolution. I don't see here an issue with slightly shifting thresholds for low speed connections, the card is supposed to utilize highest available rate, which is usually 10Gbps. Link: http://lkml.kernel.org/r/20200108121316.22411-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Joseph Qi Acked-by: Sudarsana Reddy Kalluru Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index e479067c202c..6c7c4133c25c 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -13,6 +13,7 @@ #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); -- cgit v1.2.3 From ddf8f376d137ba41ca67347a0b80ba0c357a1018 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Jan 2020 22:12:07 -0800 Subject: mm/filemap.c: clean up filemap_write_and_wait() At some point filemap_write_and_wait() and filemap_write_and_wait_range() got the exact same implementation with the exception of the range being specified in *_range() Similar to other functions in fs.h which call *_range(..., 0, LLONG_MAX), change filemap_write_and_wait() to be a static inline which calls filemap_write_and_wait_range() Link: http://lkml.kernel.org/r/20191129160713.30892-1-ira.weiny@intel.com Signed-off-by: Ira Weiny Reviewed-by: Nikolay Borisov Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 40be2ccb87f3..41584f50af0d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2737,7 +2737,6 @@ static inline int filemap_fdatawait(struct address_space *mapping) extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); -extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); extern int __filemap_fdatawrite_range(struct address_space *mapping, @@ -2747,6 +2746,11 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, extern int filemap_check_errors(struct address_space *mapping); extern void __filemap_set_wb_err(struct address_space *mapping, int err); +static inline int filemap_write_and_wait(struct address_space *mapping) +{ + return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); +} + extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); -- cgit v1.2.3 From 07d8026995287c2a2f03e28c69cdd8152fa69107 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 30 Jan 2020 22:12:28 -0800 Subject: mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An upcoming patch changes and complicates the refcounting and especially the "put page" aspects of it. In order to keep everything clean, refactor the devmap page release routines: * Rename put_devmap_managed_page() to page_is_devmap_managed(), and limit the functionality to "read only": return a bool, with no side effects. * Add a new routine, put_devmap_managed_page(), to handle decrementing the refcount for ZONE_DEVICE pages. * Change callers (just release_pages() and put_page()) to check page_is_devmap_managed() before calling the new put_devmap_managed_page() routine. This is a performance point: put_page() is a hot path, so we need to avoid non- inline function calls where possible. * Rename __put_devmap_managed_page() to free_devmap_managed_page(), and limit the functionality to unconditionally freeing a devmap page. This is originally based on a separate patch by Ira Weiny, which applied to an early version of the put_user_page() experiments. Since then, Jérôme Glisse suggested the refactoring described above. Link: http://lkml.kernel.org/r/20200107224558.2362728-5-jhubbard@nvidia.com Signed-off-by: Ira Weiny Signed-off-by: John Hubbard Suggested-by: Jérôme Glisse Reviewed-by: Dan Williams Reviewed-by: Jan Kara Cc: Christoph Hellwig Cc: Kirill A. Shutemov Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Björn Töpel Cc: Daniel Vetter Cc: Hans Verkuil Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Jonathan Corbet Cc: Leon Romanovsky Cc: Mauro Carvalho Chehab Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1233bf45164d..3b88618e361a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -947,9 +947,10 @@ static inline bool is_zone_device_page(const struct page *page) #endif #ifdef CONFIG_DEV_PAGEMAP_OPS -void __put_devmap_managed_page(struct page *page); +void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool put_devmap_managed_page(struct page *page) + +static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; @@ -958,7 +959,6 @@ static inline bool put_devmap_managed_page(struct page *page) switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX: - __put_devmap_managed_page(page); return true; default: break; @@ -966,11 +966,17 @@ static inline bool put_devmap_managed_page(struct page *page) return false; } +void put_devmap_managed_page(struct page *page); + #else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool put_devmap_managed_page(struct page *page) +static inline bool page_is_devmap_managed(struct page *page) { return false; } + +static inline void put_devmap_managed_page(struct page *page) +{ +} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) @@ -1023,8 +1029,10 @@ static inline void put_page(struct page *page) * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (put_devmap_managed_page(page)) + if (page_is_devmap_managed(page)) { + put_devmap_managed_page(page); return; + } if (put_page_testzero(page)) __put_page(page); -- cgit v1.2.3 From eddb1c228f7951d399240a0cc57455dccc7f8777 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 30 Jan 2020 22:12:54 -0800 Subject: mm/gup: introduce pin_user_pages*() and FOLL_PIN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce pin_user_pages*() variations of get_user_pages*() calls, and also pin_longterm_pages*() variations. For now, these are placeholder calls, until the various call sites are converted to use the correct get_user_pages*() or pin_user_pages*() API. These variants will eventually all set FOLL_PIN, which is also introduced, and thoroughly documented. pin_user_pages() pin_user_pages_remote() pin_user_pages_fast() All pages that are pinned via the above calls, must be unpinned via put_user_page(). The underlying rules are: * FOLL_PIN is a gup-internal flag, so the call sites should not directly set it. That behavior is enforced with assertions. * Call sites that want to indicate that they are going to do DirectIO ("DIO") or something with similar characteristics, should call a get_user_pages()-like wrapper call that sets FOLL_PIN. These wrappers will: * Start with "pin_user_pages" instead of "get_user_pages". That makes it easy to find and audit the call sites. * Set FOLL_PIN * For pages that are received via FOLL_PIN, those pages must be returned via put_user_page(). Thanks to Jan Kara and Vlastimil Babka for explaining the 4 cases in this documentation. (I've reworded it and expanded upon it.) Link: http://lkml.kernel.org/r/20200107224558.2362728-12-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Jan Kara Reviewed-by: Mike Rapoport [Documentation] Reviewed-by: Jérôme Glisse Cc: Jonathan Corbet Cc: Ira Weiny Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Björn Töpel Cc: Christoph Hellwig Cc: Daniel Vetter Cc: Dan Williams Cc: Hans Verkuil Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Leon Romanovsky Cc: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 63 +++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 50 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3b88618e361a..79ca557349c6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1042,16 +1042,14 @@ static inline void put_page(struct page *page) * put_user_page() - release a gup-pinned page * @page: pointer to page to be released * - * Pages that were pinned via get_user_pages*() must be released via - * either put_user_page(), or one of the put_user_pages*() routines - * below. This is so that eventually, pages that are pinned via - * get_user_pages*() can be separately tracked and uniquely handled. In - * particular, interactions with RDMA and filesystems need special - * handling. + * Pages that were pinned via pin_user_pages*() must be released via either + * put_user_page(), or one of the put_user_pages*() routines. This is so that + * eventually such pages can be separately tracked and uniquely handled. In + * particular, interactions with RDMA and filesystems need special handling. * * put_user_page() and put_page() are not interchangeable, despite this early * implementation that makes them look the same. put_user_page() calls must - * be perfectly matched up with get_user_page() calls. + * be perfectly matched up with pin*() calls. */ static inline void put_user_page(struct page *page) { @@ -1509,9 +1507,16 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1519,6 +1524,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +int pin_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, @@ -2583,13 +2590,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ +#define FOLL_PIN 0x40000 /* pages must be released via put_user_page() */ /* - * NOTE on FOLL_LONGTERM: + * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each + * other. Here is what they mean, and how to use them: * * FOLL_LONGTERM indicates that the page will be held for an indefinite time - * period _often_ under userspace control. This is contrasted with - * iov_iter_get_pages() where usages which are transient. + * period _often_ under userspace control. This is in contrast to + * iov_iter_get_pages(), whose usages are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm @@ -2604,11 +2613,39 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * Currently only get_user_pages() and get_user_pages_fast() support this flag * and calls to get_user_pages_[un]locked are specifically not allowed. This * is due to an incompatibility with the FS DAX check and - * FAULT_FLAG_ALLOW_RETRY + * FAULT_FLAG_ALLOW_RETRY. * - * In the CMA case: longterm pins in a CMA region would unnecessarily fragment - * that region. And so CMA attempts to migrate the page before pinning when + * In the CMA case: long term pins in a CMA region would unnecessarily fragment + * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. + * + * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, + * but an additional pin counting system) will be invoked. This is intended for + * anything that gets a page reference and then touches page data (for example, + * Direct IO). This lets the filesystem know that some non-file-system entity is + * potentially changing the pages' data. In contrast to FOLL_GET (whose pages + * are released via put_page()), FOLL_PIN pages must be released, ultimately, by + * a call to put_user_page(). + * + * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different + * and separate refcounting mechanisms, however, and that means that each has + * its own acquire and release mechanisms: + * + * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. + * + * FOLL_PIN: pin_user_pages*() to acquire, and put_user_pages to release. + * + * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. + * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based + * calls applied to them, and that's perfectly OK. This is a constraint on the + * callers, not on the pages.) + * + * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never + * directly by the caller. That's in order to help avoid mismatches when + * releasing pages: get_user_pages*() pages must be released via put_page(), + * while pin_user_pages*() pages must be released via put_user_page(). + * + * Please see Documentation/vm/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) -- cgit v1.2.3 From f1f6a7dd9b53aafd81b696b9017036e7b08e57ea Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 30 Jan 2020 22:13:35 -0800 Subject: mm, tree-wide: rename put_user_page*() to unpin_user_page*() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to provide a clearer, more symmetric API for pinning and unpinning DMA pages. This way, pin_user_pages*() calls match up with unpin_user_pages*() calls, and the API is a lot closer to being self-explanatory. Link: http://lkml.kernel.org/r/20200107224558.2362728-23-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Jan Kara Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Björn Töpel Cc: Christoph Hellwig Cc: Daniel Vetter Cc: Dan Williams Cc: Hans Verkuil Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Jerome Glisse Cc: Jonathan Corbet Cc: Kirill A. Shutemov Cc: Leon Romanovsky Cc: Mauro Carvalho Chehab Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 79ca557349c6..fc543eb45de1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1039,27 +1039,27 @@ static inline void put_page(struct page *page) } /** - * put_user_page() - release a gup-pinned page + * unpin_user_page() - release a gup-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either - * put_user_page(), or one of the put_user_pages*() routines. This is so that - * eventually such pages can be separately tracked and uniquely handled. In + * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so + * that eventually such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. * - * put_user_page() and put_page() are not interchangeable, despite this early - * implementation that makes them look the same. put_user_page() calls must + * unpin_user_page() and put_page() are not interchangeable, despite this early + * implementation that makes them look the same. unpin_user_page() calls must * be perfectly matched up with pin*() calls. */ -static inline void put_user_page(struct page *page) +static inline void unpin_user_page(struct page *page) { put_page(page); } -void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, - bool make_dirty); +void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty); -void put_user_pages(struct page **pages, unsigned long npages); +void unpin_user_pages(struct page **pages, unsigned long npages); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS @@ -2590,7 +2590,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ -#define FOLL_PIN 0x40000 /* pages must be released via put_user_page() */ +#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each @@ -2625,7 +2625,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by - * a call to put_user_page(). + * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has @@ -2633,7 +2633,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * - * FOLL_PIN: pin_user_pages*() to acquire, and put_user_pages to release. + * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based @@ -2643,7 +2643,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), - * while pin_user_pages*() pages must be released via put_user_page(). + * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/vm/pin_user_pages.rst for more information. */ -- cgit v1.2.3 From 3f9903b9ca5e981b5862d7b10086d0e8caa20298 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Jan 2020 22:14:01 -0800 Subject: mm: remove the memory isolate notifier Luckily, we have no users left, so we can get rid of it. Cleanup set_migratetype_isolate() a little bit. Link: http://lkml.kernel.org/r/20191114131911.11783-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Greg Kroah-Hartman Acked-by: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Pavel Tatashin Cc: Dan Williams Cc: Oscar Salvador Cc: Qian Cai Cc: Anshuman Khandual Cc: Pingfan Liu Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 4c75dae8dd29..de6bccb28f07 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -55,19 +55,6 @@ struct memory_notify { int status_change_nid; }; -/* - * During pageblock isolation, count the number of pages within the - * range [start_pfn, start_pfn + nr_pages) which are owned by code - * in the notifier chain. - */ -#define MEM_ISOLATE_COUNT (1<<0) - -struct memory_isolate_notify { - unsigned long start_pfn; /* Start of range to check */ - unsigned int nr_pages; /* # pages in range to check */ - unsigned int pages_found; /* # pages owned found by callbacks */ -}; - struct notifier_block; struct mem_section; @@ -94,27 +81,13 @@ static inline int memory_notify(unsigned long val, void *v) { return 0; } -static inline int register_memory_isolate_notifier(struct notifier_block *nb) -{ - return 0; -} -static inline void unregister_memory_isolate_notifier(struct notifier_block *nb) -{ -} -static inline int memory_isolate_notify(unsigned long val, void *v) -{ - return 0; -} #else extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -extern int register_memory_isolate_notifier(struct notifier_block *nb); -extern void unregister_memory_isolate_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size); void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); -extern int memory_isolate_notify(unsigned long val, void *v); extern struct memory_block *find_memory_block(struct mem_section *); typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, -- cgit v1.2.3 From fe4c86c916d9151113372369f322e7436167e6f3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Jan 2020 22:14:04 -0800 Subject: mm: remove "count" parameter from has_unmovable_pages() Now that the memory isolate notifier is gone, the parameter is always 0. Drop it and cleanup has_unmovable_pages(). Link: http://lkml.kernel.org/r/20191114131911.11783-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Anshuman Khandual Cc: Qian Cai Cc: Pingfan Liu Cc: Stephen Rothwell Cc: Dan Williams Cc: Pavel Tatashin Cc: Vlastimil Babka Cc: Mel Gorman Cc: Mike Rapoport Cc: Wei Yang Cc: Alexander Duyck Cc: Alexander Potapenko Cc: Arun KS Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-isolation.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 6861df759fad..148e65a9c606 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -bool has_unmovable_pages(struct zone *zone, struct page *page, int count, - int migratetype, int flags); +bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, + int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); -- cgit v1.2.3 From 02634a44b8aba2d4f16ea09d3c17400d9320327e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 30 Jan 2020 22:14:20 -0800 Subject: mm/memblock: define memblock_physmem_add() On the s390 platform memblock.physmem array is being built by directly calling into memblock_add_range() which is a low level function not intended to be used outside of memblock. Hence lets conditionally add helper functions for physmem array when HAVE_MEMBLOCK_PHYS_MAP is enabled. Also use MAX_NUMNODES instead of 0 as node ID similar to memblock_add() and memblock_reserve(). Make memblock_add_range() a static function as it is no longer getting used outside of memblock. Link: http://lkml.kernel.org/r/1578283835-21969-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Mike Rapoport Acked-by: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Martin Schwidefsky Cc: Collin Walling Cc: Gerald Schaefer Cc: Philipp Rudo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b38bbefabfab..079d17d96410 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -113,6 +113,9 @@ int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +int memblock_physmem_add(phys_addr_t base, phys_addr_t size); +#endif void memblock_trim_memory(phys_addr_t align); bool memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); @@ -127,10 +130,6 @@ void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); /* Low level functions */ -int memblock_add_range(struct memblock_type *type, - phys_addr_t base, phys_addr_t size, - int nid, enum memblock_flags flags); - void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, -- cgit v1.2.3 From bd5c2344f9eb1ebf7ff2501ddb13d83151939780 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Jan 2020 22:14:54 -0800 Subject: mm/memory_hotplug: pass in nid to online_pages() Patch series "mm/memory_hotplug: pass in nid to online_pages()". Simplify onlining code and get rid of find_memory_block(). Pass in the nid from the memory block we are trying to online directly, instead of manually looking it up. This patch (of 2): No need to lookup the memory block, we can directly pass in the nid. Link: http://lkml.kernel.org/r/20200113113354.6341-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Michal Hocko Cc: Oscar Salvador Cc: Anshuman Khandual Cc: Dan Williams Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ba0dca6aac6e..ffa6ad12d84a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -94,7 +94,8 @@ extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* VM interface that may be used by firmware interface */ -extern int online_pages(unsigned long, unsigned long, int); +extern int online_pages(unsigned long pfn, unsigned long nr_pages, + int online_type, int nid); extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, unsigned long *valid_start, unsigned long *valid_end); extern unsigned long __offline_isolated_pages(unsigned long start_pfn, -- cgit v1.2.3 From 4a55c0474a92d5c418bcbbe122368de0910aeac2 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 30 Jan 2020 22:14:57 -0800 Subject: mm/hotplug: silence a lockdep splat with printk() It is not that hard to trigger lockdep splats by calling printk from under zone->lock. Most of them are false positives caused by lock chains introduced early in the boot process and they do not cause any real problems (although most of the early boot lock dependencies could happen after boot as well). There are some console drivers which do allocate from the printk context as well and those should be fixed. In any case, false positives are not that trivial to workaround and it is far from optimal to lose lockdep functionality for something that is a non-issue. So change has_unmovable_pages() so that it no longer calls dump_page() itself - instead it returns a "struct page *" of the unmovable page back to the caller so that in the case of a has_unmovable_pages() failure, the caller can call dump_page() after releasing zone->lock. Also, make dump_page() is able to report a CMA page as well, so the reason string from has_unmovable_pages() can be removed. Even though has_unmovable_pages doesn't hold any reference to the returned page this should be reasonably safe for the purpose of reporting the page (dump_page) because it cannot be hotremoved in the context of memory unplug. The state of the page might change but that is the case even with the existing code as zone->lock only plays role for free pages. While at it, remove a similar but unnecessary debug-only printk() as well. A sample of one of those lockdep splats is, WARNING: possible circular locking dependency detected ------------------------------------------------------ test.sh/8653 is trying to acquire lock: ffffffff865a4460 (console_owner){-.-.}, at: console_unlock+0x207/0x750 but task is already holding lock: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&(&zone->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock+0x2f/0x40 rmqueue_bulk.constprop.21+0xb6/0x1160 get_page_from_freelist+0x898/0x22c0 __alloc_pages_nodemask+0x2f3/0x1cd0 alloc_pages_current+0x9c/0x110 allocate_slab+0x4c6/0x19c0 new_slab+0x46/0x70 ___slab_alloc+0x58b/0x960 __slab_alloc+0x43/0x70 __kmalloc+0x3ad/0x4b0 __tty_buffer_request_room+0x100/0x250 tty_insert_flip_string_fixed_flag+0x67/0x110 pty_write+0xa2/0xf0 n_tty_write+0x36b/0x7b0 tty_write+0x284/0x4c0 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 redirected_tty_write+0x6a/0xc0 do_iter_write+0x248/0x2a0 vfs_writev+0x106/0x1e0 do_writev+0xd4/0x180 __x64_sys_writev+0x45/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #2 (&(&port->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 tty_port_tty_get+0x20/0x60 tty_port_default_wakeup+0xf/0x30 tty_port_tty_wakeup+0x39/0x40 uart_write_wakeup+0x2a/0x40 serial8250_tx_chars+0x22e/0x440 serial8250_handle_irq.part.8+0x14a/0x170 serial8250_default_handle_irq+0x5c/0x90 serial8250_interrupt+0xa6/0x130 __handle_irq_event_percpu+0x78/0x4f0 handle_irq_event_percpu+0x70/0x100 handle_irq_event+0x5a/0x8b handle_edge_irq+0x117/0x370 do_IRQ+0x9e/0x1e0 ret_from_intr+0x0/0x2a cpuidle_enter_state+0x156/0x8e0 cpuidle_enter+0x41/0x70 call_cpuidle+0x5e/0x90 do_idle+0x333/0x370 cpu_startup_entry+0x1d/0x1f start_secondary+0x290/0x330 secondary_startup_64+0xb6/0xc0 -> #1 (&port_lock_key){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 serial8250_console_write+0x3e4/0x450 univ8250_console_write+0x4b/0x60 console_unlock+0x501/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 -> #0 (console_owner){-.-.}: check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Chain exists of: console_owner --> &(&port->lock)->rlock --> &(&zone->lock)->rlock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&(&zone->lock)->rlock); lock(&(&port->lock)->rlock); lock(&(&zone->lock)->rlock); lock(console_owner); *** DEADLOCK *** 9 locks held by test.sh/8653: #0: ffff88839ba7d408 (sb_writers#4){.+.+}, at: vfs_write+0x25f/0x290 #1: ffff888277618880 (&of->mutex){+.+.}, at: kernfs_fop_write+0x128/0x240 #2: ffff8898131fc218 (kn->count#115){.+.+}, at: kernfs_fop_write+0x138/0x240 #3: ffffffff86962a80 (device_hotplug_lock){+.+.}, at: lock_device_hotplug_sysfs+0x16/0x50 #4: ffff8884374f4990 (&dev->mutex){....}, at: device_offline+0x70/0x110 #5: ffffffff86515250 (cpu_hotplug_lock.rw_sem){++++}, at: __offline_pages+0xbf/0xa10 #6: ffffffff867405f0 (mem_hotplug_lock.rw_sem){++++}, at: percpu_down_write+0x87/0x2f0 #7: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 #8: ffffffff865a4920 (console_lock){+.+.}, at: vprintk_emit+0x100/0x340 stack backtrace: Hardware name: HPE ProLiant DL560 Gen10/ProLiant DL560 Gen10, BIOS U34 05/21/2019 Call Trace: dump_stack+0x86/0xca print_circular_bug.cold.31+0x243/0x26e check_noncircular+0x29e/0x2e0 check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe Link: http://lkml.kernel.org/r/20200117181200.20299-1-cai@lca.pw Signed-off-by: Qian Cai Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Sergey Senozhatsky Cc: Petr Mladek Cc: Steven Rostedt (VMware) Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-isolation.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 148e65a9c606..572458016331 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, - int flags); +struct page *has_unmovable_pages(struct zone *zone, struct page *page, + int migratetype, int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); -- cgit v1.2.3 From 26b56e116a69e70cc13976a1b0b818036f539f53 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 30 Jan 2020 22:15:10 -0800 Subject: include/linux/mm.h: clean up obsolete check on space in page->flags The check was intended to make sure we don't overrun page flags. But it's obsolete because it doesn't include LAST_CPUPID_WIDTH nor KASAN_TAG_WIDTH. Just remove check since we already have it covered in linux/page-flags-layout.h (near the end of the file). Link: http://lkml.kernel.org/r/20191208183508.89177-1-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: David Hildenbrand Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index fc543eb45de1..ddfc217bc026 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -916,10 +916,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) -#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS -#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS -#endif - #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) -- cgit v1.2.3 From ca023a92c8f753a78c37cc8290bd8e3c54f1a936 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 30 Jan 2020 22:15:13 -0800 Subject: include/linux/mm.h: remove dead code totalram_pages_set() totalram_pages_set() was introduced in commit ca79b0c211af ("mm: convert totalram_pages and totalhigh_pages variables to atomic"), but no one uses it. Link: http://lkml.kernel.org/r/20191218005543.24146-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ddfc217bc026..73a044ed6981 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -70,11 +70,6 @@ static inline void totalram_pages_add(long count) atomic_long_add(count, &_totalram_pages); } -static inline void totalram_pages_set(long val) -{ - atomic_long_set(&_totalram_pages, val); -} - extern void * high_memory; extern int page_cluster; -- cgit v1.2.3 From 068964541db6dbacce26e75b390e87e63ad1c100 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 30 Jan 2020 22:15:16 -0800 Subject: include/linux/memory.h: drop fields 'hw' and 'phys_callback' from struct memory_block memory_block structure elements 'hw' and 'phys_callback' are not getting used. This was originally added with commit 3947be1969a9 ("[PATCH] memory hotplug: sysfs and add/remove functions") but never seem to have been used. Just drop them now. Link: http://lkml.kernel.org/r/1576728650-13867-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Dan Williams Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index de6bccb28f07..0b8d791b6669 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -29,8 +29,6 @@ struct memory_block { int section_count; /* serialized by mem_sysfs_mutex */ int online_type; /* for passing data to online routine */ int phys_device; /* to which fru does this belong? */ - void *hw; /* optional pointer to fw/hw data */ - int (*phys_callback)(struct memory_block *); struct device dev; int nid; /* NID for this memory block */ }; -- cgit v1.2.3 From 0a3c57729768e08de690ba872dd52ee9c3c11e8b Mon Sep 17 00:00:00 2001 From: Hao Lee Date: Thu, 30 Jan 2020 22:15:19 -0800 Subject: mm: fix comments related to node reclaim As zone reclaim has been replaced by node reclaim, this patch fixes related comments. Link: http://lkml.kernel.org/r/20191126141346.GA22665@haolee.github.io Signed-off-by: Hao Lee Reviewed-by: Andrew Morton Cc: Anshuman Khandual Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5334ad8fc7bd..c2bc309d1634 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -758,7 +758,7 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA /* - * zone reclaim becomes active if more unmapped pages exist. + * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; -- cgit v1.2.3 From 23331e4893614deb555c65cdf115c8a28ed32471 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 30 Jan 2020 22:15:28 -0800 Subject: include/linux/units.h: add helpers for kelvin to/from Celsius conversion Patch series "add header file for kelvin to/from Celsius conversion helpers", v4. There are several helper macros to convert kelvin to/from Celsius in for thermal drivers. These are useful for any other drivers or subsystems, but it's odd to include just for the helpers. This adds a new that provides the equivalent inline functions for any drivers or subsystems, and switches all the users of conversion helpers in to use helpers. This patch (of 12): There are several helper macros to convert kelvin to/from Celsius in for thermal drivers. These are useful for any other drivers or subsystems, but it's odd to include just for the helpers. This adds a new that provides the equivalent inline functions for any drivers or subsystems. It is intended to replace the helpers in . Link: http://lkml.kernel.org/r/1576386975-7941-2-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita Reviewed-by: Andy Shevchenko Cc: Sujith Thomas Cc: Darren Hart Cc: Zhang Rui Cc: Daniel Lezcano Cc: Amit Kucheria Cc: Jean Delvare Cc: Guenter Roeck Cc: Keith Busch Cc: Jens Axboe Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Kalle Valo Cc: Stanislaw Gruszka Cc: Johannes Berg Cc: Emmanuel Grumbach Cc: Luca Coelho Cc: Jonathan Cameron Cc: Hartmut Knaack Cc: Lars-Peter Clausen Cc: Peter Meerwald-Stadler Cc: Andy Shevchenko Cc: Jonathan Cameron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/units.h | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 include/linux/units.h (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h new file mode 100644 index 000000000000..aaf716364ec3 --- /dev/null +++ b/include/linux/units.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNITS_H +#define _LINUX_UNITS_H + +#include + +#define ABSOLUTE_ZERO_MILLICELSIUS -273150 + +static inline long milli_kelvin_to_millicelsius(long t) +{ + return t + ABSOLUTE_ZERO_MILLICELSIUS; +} + +static inline long millicelsius_to_milli_kelvin(long t) +{ + return t - ABSOLUTE_ZERO_MILLICELSIUS; +} + +#define MILLIDEGREE_PER_DEGREE 1000 +#define MILLIDEGREE_PER_DECIDEGREE 100 + +static inline long kelvin_to_millicelsius(long t) +{ + return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DEGREE); +} + +static inline long millicelsius_to_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE); +} + +static inline long deci_kelvin_to_celsius(long t) +{ + t = milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE); +} + +static inline long celsius_to_deci_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t * MILLIDEGREE_PER_DEGREE); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE); +} + +/** + * deci_kelvin_to_millicelsius_with_offset - convert Kelvin to Celsius + * @t: temperature value in decidegrees Kelvin + * @offset: difference between Kelvin and Celsius in millidegrees + * + * Return: temperature value in millidegrees Celsius + */ +static inline long deci_kelvin_to_millicelsius_with_offset(long t, long offset) +{ + return t * MILLIDEGREE_PER_DECIDEGREE - offset; +} + +static inline long deci_kelvin_to_millicelsius(long t) +{ + return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE); +} + +static inline long millicelsius_to_deci_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE); +} + +static inline long kelvin_to_celsius(long t) +{ + return t + DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS, + MILLIDEGREE_PER_DEGREE); +} + +static inline long celsius_to_kelvin(long t) +{ + return t - DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS, + MILLIDEGREE_PER_DEGREE); +} + +#endif /* _LINUX_UNITS_H */ -- cgit v1.2.3 From cdf309fb38ad419aadb8f5856a088864688fad90 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 30 Jan 2020 22:15:57 -0800 Subject: thermal: remove kelvin to/from Celsius conversion helpers from This removes the kelvin to/from Celsius conversion helper macros in which were switched to the inline helper functions in . Link: http://lkml.kernel.org/r/1576386975-7941-9-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita Reviewed-by: Andy Shevchenko Cc: Sujith Thomas Cc: Darren Hart Cc: Andy Shevchenko Cc: Zhang Rui Cc: Daniel Lezcano Cc: Amit Kucheria Cc: Jean Delvare Cc: Guenter Roeck Cc: Keith Busch Cc: Jens Axboe Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Emmanuel Grumbach Cc: Hartmut Knaack Cc: Johannes Berg Cc: Jonathan Cameron Cc: Jonathan Cameron Cc: Kalle Valo Cc: Lars-Peter Clausen Cc: Luca Coelho Cc: Peter Meerwald-Stadler Cc: Stanislaw Gruszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/thermal.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index d9111aebb97d..126913c6a53b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -32,17 +32,6 @@ /* use value, which < 0K, to indicate an invalid/uninitialized temperature */ #define THERMAL_TEMP_INVALID -274000 -/* Unit conversion macros */ -#define DECI_KELVIN_TO_CELSIUS(t) ({ \ - long _t = (t); \ - ((_t-2732 >= 0) ? (_t-2732+5)/10 : (_t-2732-5)/10); \ -}) -#define CELSIUS_TO_DECI_KELVIN(t) ((t)*10+2732) -#define DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, off) (((t) - (off)) * 100) -#define DECI_KELVIN_TO_MILLICELSIUS(t) DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, 2732) -#define MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, off) (((t) / 100) + (off)) -#define MILLICELSIUS_TO_DECI_KELVIN(t) MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, 2732) - /* Default Thermal Governor */ #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE) #define DEFAULT_THERMAL_GOVERNOR "step_wise" -- cgit v1.2.3 From 803521b149c8c71a712445a32bd9316e074df76a Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 30 Jan 2020 22:16:30 -0800 Subject: lib/zlib: add zlib_deflate_dfltcc_enabled() function Add a new function to zlib.h checking if s390 Deflate-Conversion facility is installed and enabled. Link: http://lkml.kernel.org/r/20200103223334.20669-6-zaslonko@linux.ibm.com Signed-off-by: Mikhail Zaslonko Cc: Chris Mason Cc: Christian Borntraeger Cc: David Sterba Cc: Eduard Shishkin Cc: Heiko Carstens Cc: Ilya Leoshkevich Cc: Josef Bacik Cc: Richard Purdie Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zlib.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/zlib.h b/include/linux/zlib.h index 92dbbd3f6c75..c757d848a758 100644 --- a/include/linux/zlib.h +++ b/include/linux/zlib.h @@ -191,6 +191,12 @@ extern int zlib_deflate_workspacesize (int windowBits, int memLevel); exceed those passed here. */ +extern int zlib_deflate_dfltcc_enabled (void); +/* + Returns 1 if Deflate-Conversion facility is installed and enabled, + otherwise 0. +*/ + /* extern int deflateInit (z_streamp strm, int level); -- cgit v1.2.3 From d5767057c9a76a29f073dad66b7fa12a90e8c748 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 30 Jan 2020 22:16:40 -0800 Subject: uapi: rename ext2_swab() to swab() and share globally in swab.h ext2_swab() is defined locally in lib/find_bit.c However it is not specific to ext2, neither to bitmaps. There are many potential users of it, so rename it to just swab() and move to include/uapi/linux/swab.h ABI guarantees that size of unsigned long corresponds to BITS_PER_LONG, therefore drop unneeded cast. Link: http://lkml.kernel.org/r/20200103202846.21616-1-yury.norov@gmail.com Signed-off-by: Yury Norov Cc: Allison Randal Cc: Joe Perches Cc: Thomas Gleixner Cc: William Breathitt Gray Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swab.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swab.h b/include/linux/swab.h index e466fd159c85..bcff5149861a 100644 --- a/include/linux/swab.h +++ b/include/linux/swab.h @@ -7,6 +7,7 @@ # define swab16 __swab16 # define swab32 __swab32 # define swab64 __swab64 +# define swab __swab # define swahw32 __swahw32 # define swahb32 __swahb32 # define swab16p __swab16p -- cgit v1.2.3 From 2b755626cad6d9dcbad09d022ba7bdfc39ed773d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Jan 2020 22:17:32 -0800 Subject: include/linux/io-mapping.h-mapping: use PHYS_PFN() macro in io_mapping_map_atomic_wc() Use PHYS_PFN() macro in io_mapping_map_atomic_wc() instead of open coded variant. Link: http://lkml.kernel.org/r/20191209165624.56351-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io-mapping.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 6e125e9b4187..837058bc1c9f 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -28,6 +28,7 @@ struct io_mapping { #ifdef CONFIG_HAVE_ATOMIC_IOMAP +#include #include /* * For small address space machines, mapping large objects @@ -64,12 +65,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) { resource_size_t phys_addr; - unsigned long pfn; BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; - pfn = (unsigned long) (phys_addr >> PAGE_SHIFT); - return iomap_atomic_prot_pfn(pfn, mapping->prot); + return iomap_atomic_prot_pfn(PHYS_PFN(phys_addr), mapping->prot); } static inline void -- cgit v1.2.3 From 264b0d2bee148073c117e7bbbde5be7125a53be1 Mon Sep 17 00:00:00 2001 From: Erdem Aktas Date: Fri, 13 Dec 2019 13:31:46 -0800 Subject: percpu: Separate decrypted varaibles anytime encryption can be enabled CONFIG_VIRTUALIZATION may not be enabled for memory encrypted guests. If disabled, decrypted per-CPU variables may end up sharing the same page with variables that should be left encrypted. Always separate per-CPU variables that should be decrypted into their own page anytime memory encryption can be enabled in the guest rather than rely on any other config option that may not be enabled. Fixes: ac26963a1175 ("percpu: Introduce DEFINE_PER_CPU_DECRYPTED") Cc: stable@vger.kernel.org # 4.15+ Signed-off-by: Erdem Aktas Signed-off-by: David Rientjes Signed-off-by: Dennis Zhou --- include/linux/percpu-defs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index a6fabd865211..176bfbd52d97 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -175,8 +175,7 @@ * Declaration/definition used for per-CPU variables that should be accessed * as decrypted when memory encryption is enabled in the guest. */ -#if defined(CONFIG_VIRTUALIZATION) && defined(CONFIG_AMD_MEM_ENCRYPT) - +#ifdef CONFIG_AMD_MEM_ENCRYPT #define DECLARE_PER_CPU_DECRYPTED(type, name) \ DECLARE_PER_CPU_SECTION(type, name, "..decrypted") -- cgit v1.2.3 From 6f1a4891a5928a5969c87fa5a584844c983ec823 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 31 Jan 2020 15:26:52 +0100 Subject: x86/apic/msi: Plug non-maskable MSI affinity race Evan tracked down a subtle race between the update of the MSI message and the device raising an interrupt internally on PCI devices which do not support MSI masking. The update of the MSI message is non-atomic and consists of either 2 or 3 sequential 32bit wide writes to the PCI config space. - Write address low 32bits - Write address high 32bits (If supported by device) - Write data When an interrupt is migrated then both address and data might change, so the kernel attempts to mask the MSI interrupt first. But for MSI masking is optional, so there exist devices which do not provide it. That means that if the device raises an interrupt internally between the writes then a MSI message is sent built from half updated state. On x86 this can lead to spurious interrupts on the wrong interrupt vector when the affinity setting changes both address and data. As a consequence the device interrupt can be lost causing the device to become stuck or malfunctioning. Evan tried to handle that by disabling MSI accross an MSI message update. That's not feasible because disabling MSI has issues on its own: If MSI is disabled the PCI device is routing an interrupt to the legacy INTx mechanism. The INTx delivery can be disabled, but the disablement is not working on all devices. Some devices lose interrupts when both MSI and INTx delivery are disabled. Another way to solve this would be to enforce the allocation of the same vector on all CPUs in the system for this kind of screwed devices. That could be done, but it would bring back the vector space exhaustion problems which got solved a few years ago. Fortunately the high address (if supported by the device) is only relevant when X2APIC is enabled which implies interrupt remapping. In the interrupt remapping case the affinity setting is happening at the interrupt remapping unit and the PCI MSI message is programmed only once when the PCI device is initialized. That makes it possible to solve it with a two step update: 1) Target the MSI msg to the new vector on the current target CPU 2) Target the MSI msg to the new vector on the new target CPU In both cases writing the MSI message is only changing a single 32bit word which prevents the issue of inconsistency. After writing the final destination it is necessary to check whether the device issued an interrupt while the intermediate state #1 (new vector, current CPU) was in effect. This is possible because the affinity change is always happening on the current target CPU. The code runs with interrupts disabled, so the interrupt can be detected by checking the IRR of the local APIC. If the vector is pending in the IRR then the interrupt is retriggered on the new target CPU by sending an IPI for the associated vector on the target CPU. This can cause spurious interrupts on both the local and the new target CPU. 1) If the new vector is not in use on the local CPU and the device affected by the affinity change raised an interrupt during the transitional state (step #1 above) then interrupt entry code will ignore that spurious interrupt. The vector is marked so that the 'No irq handler for vector' warning is supressed once. 2) If the new vector is in use already on the local CPU then the IRR check might see an pending interrupt from the device which is using this vector. The IPI to the new target CPU will then invoke the handler of the device, which got the affinity change, even if that device did not issue an interrupt 3) If the new vector is in use already on the local CPU and the device affected by the affinity change raised an interrupt during the transitional state (step #1 above) then the handler of the device which uses that vector on the local CPU will be invoked. expose issues in device driver interrupt handlers which are not prepared to handle a spurious interrupt correctly. This not a regression, it's just exposing something which was already broken as spurious interrupts can happen for a lot of reasons and all driver handlers need to be able to deal with them. Reported-by: Evan Green Debugged-by: Evan Green Signed-off-by: Thomas Gleixner Tested-by: Evan Green Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87imkr4s7n.fsf@nanos.tec.linutronix.de --- include/linux/irq.h | 18 ++++++++++++++++++ include/linux/irqdomain.h | 7 +++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 7853eb9301f2..3ed5a055b5f4 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -209,6 +209,8 @@ struct irq_data { * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target * IRQD_DEFAULT_TRIGGER_SET - Expected trigger already been set * IRQD_CAN_RESERVE - Can use reservation mode + * IRQD_MSI_NOMASK_QUIRK - Non-maskable MSI quirk for affinity change + * required */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -231,6 +233,7 @@ enum { IRQD_SINGLE_TARGET = (1 << 24), IRQD_DEFAULT_TRIGGER_SET = (1 << 25), IRQD_CAN_RESERVE = (1 << 26), + IRQD_MSI_NOMASK_QUIRK = (1 << 27), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -390,6 +393,21 @@ static inline bool irqd_can_reserve(struct irq_data *d) return __irqd_to_state(d) & IRQD_CAN_RESERVE; } +static inline void irqd_set_msi_nomask_quirk(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK; +} + +static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK; +} + +static inline bool irqd_msi_nomask_quirk(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 3c340dbc5a1f..4da8df57618a 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -206,6 +206,13 @@ enum { /* Irq domain implements MSI remapping */ IRQ_DOMAIN_FLAG_MSI_REMAP = (1 << 5), + /* + * Quirk to handle MSI implementations which do not provide + * masking. Currently known to affect x86, but partially + * handled in core code. + */ + IRQ_DOMAIN_MSI_NOMASK_QUIRK = (1 << 6), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the -- cgit v1.2.3 From 2b90927c77c973771cc658d639724d5b247a83eb Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Fri, 31 Jan 2020 15:55:34 -0600 Subject: tracing: Use seq_buf for building dynevent_cmd string The dynevent_cmd commands that build up the command string don't need to do that themselves - there's a seq_buf facility that does pretty much the same thing those command are doing manually, so use it instead. Link: http://lkml.kernel.org/r/eb8a6e835c964d0ab8a38cbf5ffa60746b54a465.1580506712.git.zanussi@kernel.org Reviewed-by: Masami Hiramatsu Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 7c307a7c9c6a..67f528ecb9e5 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -367,10 +367,8 @@ struct dynevent_cmd; typedef int (*dynevent_create_fn_t)(struct dynevent_cmd *cmd); struct dynevent_cmd { - char *buf; + struct seq_buf seq; const char *event_name; - int maxlen; - int remaining; unsigned int n_fields; enum dynevent_type type; dynevent_create_fn_t run_command; -- cgit v1.2.3 From 5312f321a67cfee1fe4de245bc558fa857dce33b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Jan 2020 13:55:29 +0100 Subject: mfd: syscon: Fix syscon_regmap_lookup_by_phandle_args() dummy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If CONFIG_MFD_SYSCON=n: include/linux/mfd/syscon.h:54:23: warning: ‘syscon_regmap_lookup_by_phandle_args’ defined but not used [-Wunused-function] Fix this by adding the missing inline keyword. Fixes: 6a24f567af4accef ("mfd: syscon: Add arguments support for syscon reference") Signed-off-by: Geert Uytterhoeven Signed-off-by: Lee Jones --- include/linux/mfd/syscon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index 714cab1e09d3..7f20e9b502a5 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -51,7 +51,7 @@ static inline struct regmap *syscon_regmap_lookup_by_phandle( return ERR_PTR(-ENOTSUPP); } -static struct regmap *syscon_regmap_lookup_by_phandle_args( +static inline struct regmap *syscon_regmap_lookup_by_phandle_args( struct device_node *np, const char *property, int arg_count, -- cgit v1.2.3 From 30460e1ea3e62f8457e087db9a309ed1031630da Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Thu, 9 Jan 2020 14:30:41 +0100 Subject: fs: Enable bmap() function to properly return errors By now, bmap() will either return the physical block number related to the requested file offset or 0 in case of error or the requested offset maps into a hole. This patch makes the needed changes to enable bmap() to proper return errors, using the return value as an error return, and now, a pointer must be passed to bmap() to be filled with the mapped physical block. It will change the behavior of bmap() on return: - negative value in case of error - zero on success or map fell into a hole In case of a hole, the *block will be zero too Since this is a prep patch, by now, the only error return is -EINVAL if ->bmap doesn't exist. Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino Signed-off-by: Al Viro --- include/linux/fs.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..f762e07ea589 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2865,9 +2865,16 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) extern void emergency_sync(void); extern void emergency_remount(void); + #ifdef CONFIG_BLOCK -extern sector_t bmap(struct inode *, sector_t); +extern int bmap(struct inode *inode, sector_t *block); +#else +static inline int bmap(struct inode *inode, sector_t *block) +{ + return -EINVAL; +} #endif + extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); -- cgit v1.2.3 From 183edb20e60a73925bf3b60e2f4796898167262f Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Mon, 3 Feb 2020 15:45:17 +0000 Subject: cpufreq: Make cpufreq_global_kobject static The cpufreq_global_kobject is only used internally by cpufreq.c after commit 2361be236662 ("cpufreq: Don't create empty /sys/devices/system/cpu/cpufreq directory"). Make it static. Signed-off-by: Yangtao Li [ rjw: Add empty line after cpufreq_global_kobject definition ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 018dce868de6..0fb561d1b524 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -201,9 +201,6 @@ static inline bool policy_is_shared(struct cpufreq_policy *policy) return cpumask_weight(policy->cpus) > 1; } -/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ -extern struct kobject *cpufreq_global_kobject; - #ifdef CONFIG_CPU_FREQ unsigned int cpufreq_get(unsigned int cpu); unsigned int cpufreq_quick_get(unsigned int cpu); -- cgit v1.2.3 From 034dbec179e5d2820480f477c43acbc50245e56d Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 22 Jan 2020 10:07:01 +0100 Subject: platform/chrome: cros_ec: Match implementation with headers The 'cros_ec' core driver is the common interface for the cros_ec transport drivers to do the shared operations to register, unregister, suspend, resume and handle_event. The interface is provided by including the header 'include/linux/platform_data/cros_ec_proto.h', however, instead of have the implementation of these functions in cros_ec_proto.c, it is in 'cros_ec.c', which is a different kernel module. Apart from being a bad practice, this can induce confusions allowing the users of the cros_ec protocol to call these functions. The register, unregister, suspend, resume and handle_event functions *should* only be called by the different transport drivers (i2c, spi, lpc, etc.), so make this a bit less confusing by moving these functions from the public in-kernel space to a private include in platform/chrome, and then, the interface for cros_ec module and for the cros_ec_proto module is clean. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- include/linux/platform_data/cros_ec_proto.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 119b9951c055..ba5914770191 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -206,10 +206,6 @@ struct cros_ec_dev { #define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) -int cros_ec_suspend(struct cros_ec_device *ec_dev); - -int cros_ec_resume(struct cros_ec_device *ec_dev); - int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); @@ -222,10 +218,6 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -int cros_ec_register(struct cros_ec_device *ec_dev); - -int cros_ec_unregister(struct cros_ec_device *ec_dev); - int cros_ec_query_all(struct cros_ec_device *ec_dev); int cros_ec_get_next_event(struct cros_ec_device *ec_dev, @@ -238,8 +230,6 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -bool cros_ec_handle_event(struct cros_ec_device *ec_dev); - /** * cros_ec_get_time_ns() - Return time in ns. * -- cgit v1.2.3 From b5e683d5cab8cd433b06ae178621f083cabd4f63 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 2 Feb 2020 08:23:03 -0700 Subject: eventfd: track eventfd_signal() recursion depth eventfd use cases from aio and io_uring can deadlock due to circular or resursive calling, when eventfd_signal() tries to grab the waitqueue lock. On top of that, it's also possible to construct notification chains that are deep enough that we could blow the stack. Add a percpu counter that tracks the percpu recursion depth, warn if we exceed it. The counter is also exposed so that users of eventfd_signal() can do the right thing if it's non-zero in the context where it is called. Cc: stable@vger.kernel.org # 4.19+ Signed-off-by: Jens Axboe --- include/linux/eventfd.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index ffcc7724ca21..dc4fd8a6644d 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -12,6 +12,8 @@ #include #include #include +#include +#include /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining @@ -40,6 +42,13 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); +DECLARE_PER_CPU(int, eventfd_wake_count); + +static inline bool eventfd_signal_count(void) +{ + return this_cpu_read(eventfd_wake_count); +} + #else /* CONFIG_EVENTFD */ /* @@ -68,6 +77,11 @@ static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, return -ENOSYS; } +static inline bool eventfd_signal_count(void) +{ + return false; +} + #endif #endif /* _LINUX_EVENTFD_H */ -- cgit v1.2.3 From 4b094b7851bf4bf551ad456195d3f26e1c03bd74 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Feb 2020 17:33:55 -0800 Subject: mm/page_alloc.c: initialize memmap of unavailable memory directly Let's make sure that all memory holes are actually marked PageReserved(), that page_to_pfn() produces reliable results, and that these pages are not detected as "mmap" pages due to the mapcount. E.g., booting a x86-64 QEMU guest with 4160 MB: [ 0.010585] Early memory node ranges [ 0.010586] node 0: [mem 0x0000000000001000-0x000000000009efff] [ 0.010588] node 0: [mem 0x0000000000100000-0x00000000bffdefff] [ 0.010589] node 0: [mem 0x0000000100000000-0x0000000143ffffff] max_pfn is 0x144000. Before this change: [root@localhost ~]# ./page-types -r -a 0x144000, flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000800 16384 64 ___________M_______________________________ mmap total 16384 64 After this change: [root@localhost ~]# ./page-types -r -a 0x144000, flags page-count MB symbolic-flags long-symbolic-flags 0x0000000100000000 16384 64 ___________________________r_______________ reserved total 16384 64 IOW, especially the unavailable physical memory ("memory hole") in the last section would not get properly marked PageReserved() and is indicated to be "mmap" memory. Drop the trace of that function from include/linux/mm.h - nobody else needs it, and rename it accordingly. Note: The fake zone/node might not be covered by the zone/node span. This is not an urgent issue (for now, we had the same node/zone due to the zeroing). We'll need a clean way to mark memory holes (e.g., using a page type PageHole() if possible or a fake ZONE_INVALID) and eventually stop marking these memory holes PageReserved(). Link: http://lkml.kernel.org/r/20191211163201.17179-4-david@redhat.com Signed-off-by: David Hildenbrand Cc: Oscar Salvador Cc: Michal Hocko Cc: Dan Williams Cc: Alexey Dobriyan Cc: Bob Picco Cc: Daniel Jordan Cc: Michal Hocko Cc: Naoya Horiguchi Cc: Pavel Tatashin Cc: Stephen Rothwell Cc: Steven Sistare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a044ed6981..080f8ac8bfb7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2182,12 +2182,6 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if !defined(CONFIG_FLAT_NODE_MEM_MAP) -void zero_resv_unavail(void); -#else -static inline void zero_resv_unavail(void) {} -#endif - 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 *); -- cgit v1.2.3 From 4c6058814ec4460c25111e29452ef596acdcd61b Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Feb 2020 17:34:02 -0800 Subject: mm: factor out next_present_section_nr() Let's move it to the header and use the shorter variant from mm/page_alloc.c (the original one will also check "__highest_present_section_nr + 1", which is not necessary). While at it, make the section_nr in next_pfn() const. In next_pfn(), we now return section_nr_to_pfn(-1) instead of -1 once we exceed __highest_present_section_nr, which doesn't make a difference in the caller as it is big enough (>= all sane end_pfn). Link: http://lkml.kernel.org/r/20200113144035.10848-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Kirill A. Shutemov Cc: Baoquan He Cc: Dan Williams Cc: "Jin, Zhi" Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Michal Hocko Cc: Michal Hocko Cc: Oscar Salvador Cc: Pavel Tatashin Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c2bc309d1634..462f6873905a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1379,6 +1379,16 @@ static inline int pfn_present(unsigned long pfn) return present_section(__nr_to_section(pfn_to_section_nr(pfn))); } +static inline unsigned long next_present_section_nr(unsigned long section_nr) +{ + while (++section_nr <= __highest_present_section_nr) { + if (present_section_nr(section_nr)) + return section_nr; + } + + return -1; +} + /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate -- cgit v1.2.3 From 92917998849eea951707c8fea2dc3007bb2ad2cd Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Feb 2020 17:34:26 -0800 Subject: mm/memory_hotplug: drop valid_start/valid_end from test_pages_in_a_zone() The callers are only interested in the actual zone, they don't care about boundaries. Return the zone instead to simplify. Link: http://lkml.kernel.org/r/20200110183308.11849-1-david@redhat.com Signed-off-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ffa6ad12d84a..f4d59155f3d4 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -96,8 +96,8 @@ extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* VM interface that may be used by firmware interface */ extern int online_pages(unsigned long pfn, unsigned long nr_pages, int online_type, int nid); -extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, - unsigned long *valid_start, unsigned long *valid_end); +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); -- cgit v1.2.3 From 1c948715a159d0d02c1e1c9228327ba3c408795c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 3 Feb 2020 17:34:58 -0800 Subject: mm: remove __krealloc Since 5.5-rc1 the last user of this function is gone, so remove the functionality. See commit 2ad9d7747c10 ("netfilter: conntrack: free extension area immediately") for details. Link: http://lkml.kernel.org/r/20191212223442.22141-1-fw@strlen.de Signed-off-by: Florian Westphal Acked-by: Andrew Morton Acked-by: David Rientjes Reviewed-by: David Hildenbrand Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 877a95c6a2d2..03a389358562 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -184,7 +184,6 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *); /* * Common kmalloc functions provided by all allocators */ -void * __must_check __krealloc(const void *, size_t, gfp_t); void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kzfree(const void *); -- cgit v1.2.3 From 3afc423632a194d7d6afef34e4bb98f804cd071d Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 3 Feb 2020 17:35:45 -0800 Subject: mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price Signed-off-by: Arnd Bergmann Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Zong Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagewalk.h | 34 ++++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 6ec82e92c87f..aa6a0b63964e 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -8,15 +8,15 @@ struct mm_walk; /** * mm_walk_ops - callbacks for walk_page_range - * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry - * this handler should only handle pud_trans_huge() puds. - * the pmd_entry or pte_entry callbacks will be used for - * regular PUDs. - * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry + * @pgd_entry: if set, called for each non-empty PGD (top-level) entry + * @p4d_entry: if set, called for each non-empty P4D entry + * @pud_entry: if set, called for each non-empty PUD entry + * @pmd_entry: if set, called for each non-empty PMD entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each non-empty PTE (4th-level) entry + * @pte_entry: if set, called for each non-empty PTE (lowest-level) + * entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether @@ -27,8 +27,15 @@ struct mm_walk; * @pre_vma: if set, called before starting walk on a non-null vma. * @post_vma: if set, called after a walk on a non-null vma, provided * that @pre_vma and the vma walk succeeded. + * + * p?d_entry callbacks are called even if those levels are folded on a + * particular architecture/configuration. */ struct mm_walk_ops { + int (*pgd_entry)(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*p4d_entry)(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk); int (*pud_entry)(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, @@ -47,11 +54,25 @@ struct mm_walk_ops { void (*post_vma)(struct mm_walk *walk); }; +/* + * Action for pud_entry / pmd_entry callbacks. + * ACTION_SUBTREE is the default + */ +enum page_walk_action { + /* Descend to next level, splitting huge pages if needed and possible */ + ACTION_SUBTREE = 0, + /* Continue to next entry at this level (ignoring any subtree) */ + ACTION_CONTINUE = 1, + /* Call again for this entry */ + ACTION_AGAIN = 2 +}; + /** * mm_walk - walk_page_range data * @ops: operation to call during the walk * @mm: mm_struct representing the target process of page table walk * @vma: vma currently walked (NULL if walking outside vmas) + * @action: next action to perform (see enum page_walk_action) * @private: private data for callbacks' usage * * (see the comment on walk_page_range() for more details) @@ -60,6 +81,7 @@ struct mm_walk { const struct mm_walk_ops *ops; struct mm_struct *mm; struct vm_area_struct *vma; + enum page_walk_action action; void *private; }; -- cgit v1.2.3 From 488ae6a2b933cb538b5d91b1c0a3420188d28771 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 3 Feb 2020 17:35:50 -0800 Subject: mm: pagewalk: allow walking without vma Since 48684a65b4e3: "mm: pagewalk: fix misbehavior of walk_page_range for vma(VM_PFNMAP)", page_table_walk() will report any kernel area as a hole, because it lacks a vma. This means each arch has re-implemented page table walking when needed, for example in the per-arch ptdump walker. Remove the requirement to have a vma in the generic code and add a new function walk_page_range_novma() which ignores the VMAs and simply walks the page tables. Link: http://lkml.kernel.org/r/20191218162402.45610-13-steven.price@arm.com Signed-off-by: Steven Price Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Zong Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagewalk.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index aa6a0b63964e..d5d07f7a9c14 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -73,6 +73,7 @@ enum page_walk_action { * @mm: mm_struct representing the target process of page table walk * @vma: vma currently walked (NULL if walking outside vmas) * @action: next action to perform (see enum page_walk_action) + * @no_vma: walk ignoring vmas (vma will always be NULL) * @private: private data for callbacks' usage * * (see the comment on walk_page_range() for more details) @@ -82,12 +83,16 @@ struct mm_walk { struct mm_struct *mm; struct vm_area_struct *vma; enum page_walk_action action; + bool no_vma; void *private; }; int walk_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); +int walk_page_range_novma(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private); int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private); int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, -- cgit v1.2.3 From b7a16c7ad790d0ecb44dcb08a6a75d0d0455ab5f Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 3 Feb 2020 17:36:03 -0800 Subject: mm: pagewalk: add 'depth' parameter to pte_hole The pte_hole() callback is called at multiple levels of the page tables. Code dumping the kernel page tables needs to know what at what depth the missing entry is. Add this is an extra parameter to pte_hole(). When the depth isn't know (e.g. processing a vma) then -1 is passed. The depth that is reported is the actual level where the entry is missing (ignoring any folding that is in place), i.e. any levels where PTRS_PER_P?D is set to 1 are ignored. Note that depth starts at 0 for a PGD so that PUD/PMD/PTE retain their natural numbers as levels 2/3/4. Link: http://lkml.kernel.org/r/20191218162402.45610-16-steven.price@arm.com Signed-off-by: Steven Price Tested-by: Zong Li Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagewalk.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index d5d07f7a9c14..745a654c6ea7 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -17,7 +17,10 @@ struct mm_walk; * split_huge_page() instead of handling it explicitly. * @pte_entry: if set, called for each non-empty PTE (lowest-level) * entry - * @pte_hole: if set, called for each hole at all levels + * @pte_hole: if set, called for each hole at all levels, + * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD + * 4:PTE. Any folded depths (where PTRS_PER_P?D is equal + * to 1) are skipped. * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 means @@ -43,7 +46,7 @@ struct mm_walk_ops { int (*pte_entry)(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_hole)(unsigned long addr, unsigned long next, - struct mm_walk *walk); + int depth, struct mm_walk *walk); int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long next, struct mm_walk *walk); -- cgit v1.2.3 From 30d621f6723b1c98a142861f7a52849d286bc7fa Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 3 Feb 2020 17:36:20 -0800 Subject: mm: add generic ptdump Add a generic version of page table dumping that architectures can opt-in to. Link: http://lkml.kernel.org/r/20191218162402.45610-20-steven.price@arm.com Signed-off-by: Steven Price Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Zong Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptdump.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/ptdump.h (limited to 'include/linux') diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h new file mode 100644 index 000000000000..a0fb8dd2be97 --- /dev/null +++ b/include/linux/ptdump.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PTDUMP_H +#define _LINUX_PTDUMP_H + +#include + +struct ptdump_range { + unsigned long start; + unsigned long end; +}; + +struct ptdump_state { + void (*note_page)(struct ptdump_state *st, unsigned long addr, + int level, unsigned long val); + const struct ptdump_range *range; +}; + +void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm); + +#endif /* _LINUX_PTDUMP_H */ -- cgit v1.2.3 From f8f0d0b6fa203bfa363d30f34f6fecce9e5cc2f7 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 3 Feb 2020 17:36:38 -0800 Subject: mm: ptdump: reduce level numbers by 1 in note_page() Rather than having to increment the 'depth' number by 1 in ptdump_hole(), let's change the meaning of 'level' in note_page() since that makes the code simplier. Note that for x86, the level numbers were previously increased by 1 in commit 45dcd2091363 ("x86/mm/dump_pagetables: Fix printout of p4d level") and the comment "Bit 7 has a different meaning" was not updated, so this change also makes the code match the comment again. Link: http://lkml.kernel.org/r/20191218162402.45610-24-steven.price@arm.com Signed-off-by: Steven Price Reviewed-by: Catalin Marinas Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Zong Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptdump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h index a0fb8dd2be97..b28f3f2acf90 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -11,6 +11,7 @@ struct ptdump_range { }; struct ptdump_state { + /* level is 0:PGD to 4:PTE, or -1 if unknown */ void (*note_page)(struct ptdump_state *st, unsigned long addr, int level, unsigned long val); const struct ptdump_range *range; -- cgit v1.2.3 From e47690d756a760579141560ded06ec1020dd85e8 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 3 Feb 2020 17:36:42 -0800 Subject: x86: mm: avoid allocating struct mm_struct on the stack struct mm_struct is quite large (~1664 bytes) and so allocating on the stack may cause problems as the kernel stack size is small. Since ptdump_walk_pgd_level_core() was only allocating the structure so that it could modify the pgd argument we can instead introduce a pgd override in struct mm_walk and pass this down the call stack to where it is needed. Since the correct mm_struct is now being passed down, it is now also unnecessary to take the mmap_sem semaphore because ptdump_walk_pgd() will now take the semaphore on the real mm. [steven.price@arm.com: restore missed arm64 changes] Link: http://lkml.kernel.org/r/20200108145710.34314-1-steven.price@arm.com Link: http://lkml.kernel.org/r/20200108145710.34314-1-steven.price@arm.com Signed-off-by: Steven Price Reported-by: Stephen Rothwell Cc: Catalin Marinas Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Zong Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagewalk.h | 3 +++ include/linux/ptdump.h | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 745a654c6ea7..b1cb6b753abb 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -74,6 +74,7 @@ enum page_walk_action { * mm_walk - walk_page_range data * @ops: operation to call during the walk * @mm: mm_struct representing the target process of page table walk + * @pgd: pointer to PGD; only valid with no_vma (otherwise set to NULL) * @vma: vma currently walked (NULL if walking outside vmas) * @action: next action to perform (see enum page_walk_action) * @no_vma: walk ignoring vmas (vma will always be NULL) @@ -84,6 +85,7 @@ enum page_walk_action { struct mm_walk { const struct mm_walk_ops *ops; struct mm_struct *mm; + pgd_t *pgd; struct vm_area_struct *vma; enum page_walk_action action; bool no_vma; @@ -95,6 +97,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, void *private); int walk_page_range_novma(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, + pgd_t *pgd, void *private); int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private); diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h index b28f3f2acf90..a67065c403c3 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -17,6 +17,6 @@ struct ptdump_state { const struct ptdump_range *range; }; -void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm); +void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd); #endif /* _LINUX_PTDUMP_H */ -- cgit v1.2.3 From d56c0d45f0e27f814e87a1676b6bdccccbc252e9 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 3 Feb 2020 17:37:14 -0800 Subject: proc: decouple proc from VFS with "struct proc_ops" Currently core /proc code uses "struct file_operations" for custom hooks, however, VFS doesn't directly call them. Every time VFS expands file_operations hook set, /proc code bloats for no reason. Introduce "struct proc_ops" which contains only those hooks which /proc allows to call into (open, release, read, write, ioctl, mmap, poll). It doesn't contain module pointer as well. Save ~184 bytes per usage: add/remove: 26/26 grow/shrink: 1/4 up/down: 1922/-6674 (-4752) Function old new delta sysvipc_proc_ops - 72 +72 ... config_gz_proc_ops - 72 +72 proc_get_inode 289 339 +50 proc_reg_get_unmapped_area 110 107 -3 close_pdeo 227 224 -3 proc_reg_open 289 284 -5 proc_create_data 60 53 -7 rt_cpu_seq_fops 256 - -256 ... default_affinity_proc_fops 256 - -256 Total: Before=5430095, After=5425343, chg -0.09% Link: http://lkml.kernel.org/r/20191225172228.GA13378@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0640be56dcbd..3dfa92633af3 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -12,6 +12,21 @@ struct proc_dir_entry; struct seq_file; struct seq_operations; +struct proc_ops { + int (*proc_open)(struct inode *, struct file *); + ssize_t (*proc_read)(struct file *, char __user *, size_t, loff_t *); + 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 *); + __poll_t (*proc_poll)(struct file *, struct poll_table_struct *); + long (*proc_ioctl)(struct file *, unsigned int, unsigned long); +#ifdef CONFIG_COMPAT + long (*proc_compat_ioctl)(struct file *, unsigned int, unsigned long); +#endif + int (*proc_mmap)(struct file *, struct vm_area_struct *); + unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); +}; + #ifdef CONFIG_PROC_FS typedef int (*proc_write_t)(struct file *, char *, size_t); @@ -43,10 +58,10 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, - const struct file_operations *, + const struct proc_ops *, void *); -struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops); +struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); extern void *PDE_DATA(const struct inode *); @@ -108,8 +123,8 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create_single(name, mode, parent, show) ({NULL;}) #define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) -#define proc_create(name, mode, parent, proc_fops) ({NULL;}) -#define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;}) +#define proc_create(name, mode, parent, proc_ops) ({NULL;}) +#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;}) static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} -- cgit v1.2.3 From 97a32539b9568bb653683349e5a76d02ff3c3e2c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 3 Feb 2020 17:37:17 -0800 Subject: proc: convert everything to "struct proc_ops" The most notable change is DEFINE_SHOW_ATTRIBUTE macro split in seq_file.h. Conversion rule is: llseek => proc_lseek unlocked_ioctl => proc_ioctl xxx => proc_xxx delete ".owner = THIS_MODULE" line [akpm@linux-foundation.org: fix drivers/isdn/capi/kcapi_proc.c] [sfr@canb.auug.org.au: fix kernel/sched/psi.c] Link: http://lkml.kernel.org/r/20200122180545.36222f50@canb.auug.org.au Link: http://lkml.kernel.org/r/20191225172546.GB13378@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 13 +++++++++++++ include/linux/sunrpc/stats.h | 4 ++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 5998e1f4ff06..770c2bf3aa43 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -160,6 +160,19 @@ static const struct file_operations __name ## _fops = { \ .release = single_release, \ } +#define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __name ## _show, inode->i_private); \ +} \ + \ +static const struct proc_ops __name ## _proc_ops = { \ + .proc_open = __name ## _open, \ + .proc_read = seq_read, \ + .proc_lseek = seq_lseek, \ + .proc_release = single_release, \ +} + static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { #ifdef CONFIG_USER_NS diff --git a/include/linux/sunrpc/stats.h b/include/linux/sunrpc/stats.h index 84b92b4ad1c0..d94d4f410507 100644 --- a/include/linux/sunrpc/stats.h +++ b/include/linux/sunrpc/stats.h @@ -63,7 +63,7 @@ struct proc_dir_entry * rpc_proc_register(struct net *,struct rpc_stat *); void rpc_proc_unregister(struct net *,const char *); void rpc_proc_zero(const struct rpc_program *); struct proc_dir_entry * svc_proc_register(struct net *, struct svc_stat *, - const struct file_operations *); + const struct proc_ops *); void svc_proc_unregister(struct net *, const char *); void svc_seq_show(struct seq_file *, @@ -75,7 +75,7 @@ static inline void rpc_proc_unregister(struct net *net, const char *p) {} static inline void rpc_proc_zero(const struct rpc_program *p) {} static inline struct proc_dir_entry *svc_proc_register(struct net *net, struct svc_stat *s, - const struct file_operations *f) { return NULL; } + const struct proc_ops *proc_ops) { return NULL; } static inline void svc_proc_unregister(struct net *net, const char *p) {} static inline void svc_seq_show(struct seq_file *seq, -- cgit v1.2.3 From 0bee0cece2a6a71ccc347fdc1d46cf638cd5fd1c Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 3 Feb 2020 17:37:20 -0800 Subject: lib/string: add strnchrnul() Patch series "lib: rework bitmap_parse", v5. Similarl to the recently revisited bitmap_parselist(), bitmap_parse() is ineffective and overcomplicated. This series reworks it, aligns its interface with bitmap_parselist() and makes it simpler to use. The series also adds a test for the function and fixes usage of it in cpumask_parse() according to the new design - drops the calculating of length of an input string. bitmap_parse() takes the array of numbers to be put into the map in the BE order which is reversed to the natural LE order for bitmaps. For example, to construct bitmap containing a bit on the position 42, we have to put a line '400,0'. Current implementation reads chunk one by one from the beginning ('400' before '0') and makes bitmap shift after each successful parse. It makes the complexity of the whole process as O(n^2). We can do it in reverse direction ('0' before '400') and avoid shifting, but it requires reverse parsing helpers. This patch (of 7): New function works like strchrnul() with a length limited string. Link: http://lkml.kernel.org/r/20200102043031.30357-2-yury.norov@gmail.com Signed-off-by: Yury Norov Reviewed-by: Andy Shevchenko Cc: Rasmus Villemoes Cc: Amritha Nambiar Cc: Willem de Bruijn Cc: Kees Cook Cc: Matthew Wilcox Cc: "Tobin C . Harding" Cc: Will Deacon Cc: Miklos Szeredi Cc: Vineet Gupta Cc: Chris Wilson Cc: Arnaldo Carvalho de Melo Cc: Steffen Klassert Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 02894e417565..6dfbb2efa815 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -62,6 +62,7 @@ extern char * strchr(const char *,int); #ifndef __HAVE_ARCH_STRCHRNUL extern char * strchrnul(const char *,int); #endif +extern char * strnchrnul(const char *, size_t, int); #ifndef __HAVE_ARCH_STRNCHR extern char * strnchr(const char *, size_t, int); #endif -- cgit v1.2.3 From 0bddc1bd05d6973fee9303005abab6567f743ea7 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 3 Feb 2020 17:37:24 -0800 Subject: bitops: more BITS_TO_* macros Introduce BITS_TO_U64, BITS_TO_U32 and BITS_TO_BYTES as they are handy in the following patches (BITS_TO_U32 specifically). Reimplement tools/ version of the macros according to the kernel implementation. Also fix indentation for BITS_PER_TYPE definition. Link: http://lkml.kernel.org/r/20200102043031.30357-3-yury.norov@gmail.com Signed-off-by: Yury Norov Reviewed-by: Andy Shevchenko Cc: Amritha Nambiar Cc: Arnaldo Carvalho de Melo Cc: Chris Wilson Cc: Kees Cook Cc: Matthew Wilcox Cc: Miklos Szeredi Cc: Rasmus Villemoes Cc: Steffen Klassert Cc: "Tobin C . Harding" Cc: Vineet Gupta Cc: Will Deacon Cc: Willem de Bruijn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 6c7c4133c25c..47f54b459c26 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -11,8 +11,10 @@ # define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) #endif -#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) +#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) +#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) extern unsigned int __sw_hweight8(unsigned int w); -- cgit v1.2.3 From 2d6261583be005a91e4933aa53bbd678ef98e4c4 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 3 Feb 2020 17:37:34 -0800 Subject: lib: rework bitmap_parse() bitmap_parse() is ineffective and full of opaque variables and opencoded parts. It leads to hard understanding and usage of it. This rework includes: - remove bitmap_shift_left() call from the cycle. Now it makes the complexity of the algorithm as O(nbits^2). In the suggested approach the input string is parsed in reverse direction, so no shifts needed; - relax requirement on a single comma and no white spaces between chunks. It is considered useful in scripting, and it aligns with bitmap_parselist(); - split bitmap_parse() to small readable helpers; - make an explicit calculation of the end of input line at the beginning, so users of the bitmap_parse() won't bother doing this. Link: http://lkml.kernel.org/r/20200102043031.30357-6-yury.norov@gmail.com Signed-off-by: Yury Norov Cc: Amritha Nambiar Cc: Andy Shevchenko Cc: Arnaldo Carvalho de Melo Cc: Chris Wilson Cc: Kees Cook Cc: Matthew Wilcox Cc: Miklos Szeredi Cc: Rasmus Villemoes Cc: Steffen Klassert Cc: "Tobin C . Harding" Cc: Vineet Gupta Cc: Will Deacon Cc: Willem de Bruijn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 80ad521116d7..e52ceb1a73d3 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -186,7 +186,7 @@ bitmap_find_next_zero_area(unsigned long *map, align_mask, 0); } -extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, +extern int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); @@ -454,12 +454,6 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } -static inline int bitmap_parse(const char *buf, unsigned int buflen, - unsigned long *maskp, int nmaskbits) -{ - return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); -} - static inline void bitmap_next_clear_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) -- cgit v1.2.3 From 190535f7cf50f2d6d6e603715201c58cd6ec696b Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 3 Feb 2020 17:37:41 -0800 Subject: include/linux/cpumask.h: don't calculate length of the input string New design of inner bitmap_parse() allows to avoid calculating the size of a null-terminated string. Link: http://lkml.kernel.org/r/20200102043031.30357-8-yury.norov@gmail.com Signed-off-by: Yury Norov Reviewed-by: Andy Shevchenko Cc: Amritha Nambiar Cc: Arnaldo Carvalho de Melo Cc: Chris Wilson Cc: Kees Cook Cc: Matthew Wilcox Cc: Miklos Szeredi Cc: Rasmus Villemoes Cc: Steffen Klassert Cc: "Tobin C . Harding" Cc: Vineet Gupta Cc: Will Deacon Cc: Willem de Bruijn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 78a73eba64dd..d5cc88514aee 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -663,9 +663,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, */ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) { - unsigned int len = strchrnul(buf, '\n') - buf; - - return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits); + return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** -- cgit v1.2.3 From 227823d2074da0c138d2abc0074b2dd281bbf923 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Wed, 22 Jan 2020 20:45:39 -0500 Subject: nfs: optimise readdir cache page invalidation When the directory is large and it's being modified by one client while another client is doing the 'ls -l' on the same directory then the cache page invalidation from nfs_force_use_readdirplus causes the reading client to keep restarting READDIRPLUS from cookie 0 which causes the 'ls -l' to take a very long time to complete, possibly never completing. Currently when nfs_force_use_readdirplus is called to switch from READDIR to READDIRPLUS, it invalidates all the cached pages of the directory. This cache page invalidation causes the next nfs_readdir to re-read the directory content from cookie 0. This patch is to optimise the cache invalidation in nfs_force_use_readdirplus by only truncating the cached pages from last page index accessed to the end the file. It also marks the inode to delay invalidating all the cached page of the directory until the next initial nfs_readdir of the next 'ls' instance. Signed-off-by: Dai Ngo Reviewed-by: Trond Myklebust [Anna - Fix conflicts with Trond's readdir patches] [Anna - Remove redundant call to nfs_zap_mapping()] [Anna - Replace d_inode(file_dentry(desc->file)) with file_inode(desc->file)] Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c06b1fd130f3..a5f8f03ecd59 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -168,6 +168,9 @@ struct nfs_inode { struct rw_semaphore rmdir_sem; struct mutex commit_mutex; + /* track last access to cached pages */ + unsigned long page_index; + #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ -- cgit v1.2.3 From e22e0790595dad409d610651f4eb17742607e35d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 5 Feb 2020 11:29:02 +0200 Subject: net: dsa: b53: Platform data shan't include kernel.h Replace with appropriate types.h. Signed-off-by: Andy Shevchenko Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/b53.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/b53.h b/include/linux/platform_data/b53.h index c3b61ead41f2..6f6fed2b171d 100644 --- a/include/linux/platform_data/b53.h +++ b/include/linux/platform_data/b53.h @@ -19,7 +19,7 @@ #ifndef __B53_H #define __B53_H -#include +#include #include struct b53_platform_data { -- cgit v1.2.3 From 8b7a07c7d4420c7d684f661697c6a878040c8b65 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 5 Feb 2020 11:29:03 +0200 Subject: net: dsa: microchip: Platform data shan't include kernel.h Replace with appropriate types.h. Signed-off-by: Andy Shevchenko Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/microchip-ksz.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index 84789ca634aa..ea1cc6d829e9 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -19,7 +19,7 @@ #ifndef __MICROCHIP_KSZ_H #define __MICROCHIP_KSZ_H -#include +#include struct ksz_platform_data { u32 chip_id; -- cgit v1.2.3 From 4a47cbae04844f0c5e2365aa6c217b61850bb832 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Feb 2020 14:44:38 +0100 Subject: dma-direct: improve swiotlb error reporting Untangle the way how dma_direct_map_page calls into swiotlb to be able to properly report errors where the swiotlb DMA address overflows the mask separately from overflows in the !swiotlb case. This means that siotlb_map now has to do a little more work that duplicates dma_direct_map_page, but doing so greatly simplifies the calling convention. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index cde3dc18e21a..046bb94bd4d6 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -64,6 +64,9 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, size_t size, enum dma_data_direction dir, enum dma_sync_target target); +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); + #ifdef CONFIG_SWIOTLB extern enum swiotlb_force swiotlb_force; extern phys_addr_t io_tlb_start, io_tlb_end; @@ -73,8 +76,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) return paddr >= io_tlb_start && paddr < io_tlb_end; } -bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs); void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -85,12 +86,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) { return false; } -static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys, - dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - return false; -} static inline void swiotlb_exit(void) { } -- cgit v1.2.3 From 5df867145f8adad9e5cdf9d67db1fbc0f71351e9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 5 Feb 2020 20:46:49 +0100 Subject: of: clk: Make self-contained MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Depending on include order: include/linux/of_clk.h:11:45: warning: ‘struct device_node’ declared inside parameter list will not be visible outside of this definition or declaration unsigned int of_clk_get_parent_count(struct device_node *np); ^~~~~~~~~~~ include/linux/of_clk.h:12:43: warning: ‘struct device_node’ declared inside parameter list will not be visible outside of this definition or declaration const char *of_clk_get_parent_name(struct device_node *np, int index); ^~~~~~~~~~~ include/linux/of_clk.h:13:31: warning: ‘struct of_device_id’ declared inside parameter list will not be visible outside of this definition or declaration void of_clk_init(const struct of_device_id *matches); ^~~~~~~~~~~~ Fix this by adding forward declarations for struct device_node and struct of_device_id. Signed-off-by: Geert Uytterhoeven Link: https://lkml.kernel.org/r/20200205194649.31309-1-geert+renesas@glider.be Signed-off-by: Stephen Boyd --- include/linux/of_clk.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_clk.h b/include/linux/of_clk.h index b27da9f164cb..c86fcad23fc2 100644 --- a/include/linux/of_clk.h +++ b/include/linux/of_clk.h @@ -6,6 +6,9 @@ #ifndef __LINUX_OF_CLK_H #define __LINUX_OF_CLK_H +struct device_node; +struct of_device_id; + #if defined(CONFIG_COMMON_CLK) && defined(CONFIG_OF) unsigned int of_clk_get_parent_count(struct device_node *np); -- cgit v1.2.3 From 86b18aaa2b5b5bb48e609cd591b3d2d0fdbe0442 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Tue, 4 Feb 2020 13:40:29 -0500 Subject: skbuff: fix a data race in skb_queue_len() sk_buff.qlen can be accessed concurrently as noticed by KCSAN, BUG: KCSAN: data-race in __skb_try_recv_from_queue / unix_dgram_sendmsg read to 0xffff8a1b1d8a81c0 of 4 bytes by task 5371 on cpu 96: unix_dgram_sendmsg+0x9a9/0xb70 include/linux/skbuff.h:1821 net/unix/af_unix.c:1761 ____sys_sendmsg+0x33e/0x370 ___sys_sendmsg+0xa6/0xf0 __sys_sendmsg+0x69/0xf0 __x64_sys_sendmsg+0x51/0x70 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe write to 0xffff8a1b1d8a81c0 of 4 bytes by task 1 on cpu 99: __skb_try_recv_from_queue+0x327/0x410 include/linux/skbuff.h:2029 __skb_try_recv_datagram+0xbe/0x220 unix_dgram_recvmsg+0xee/0x850 ____sys_recvmsg+0x1fb/0x210 ___sys_recvmsg+0xa2/0xf0 __sys_recvmsg+0x66/0xf0 __x64_sys_recvmsg+0x51/0x70 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe Since only the read is operating as lockless, it could introduce a logic bug in unix_recvq_full() due to the load tearing. Fix it by adding a lockless variant of skb_queue_len() and unix_recvq_full() where READ_ONCE() is on the read while WRITE_ONCE() is on the write similar to the commit d7d16a89350a ("net: add skb_queue_empty_lockless()"). Signed-off-by: Qian Cai Signed-off-by: David S. Miller --- include/linux/skbuff.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3d13a4b717e9..ca8806b69388 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1821,6 +1821,18 @@ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) return list_->qlen; } +/** + * skb_queue_len_lockless - get queue length + * @list_: list to measure + * + * Return the length of an &sk_buff queue. + * This variant can be used in lockless contexts. + */ +static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) +{ + return READ_ONCE(list_->qlen); +} + /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize @@ -2026,7 +2038,7 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; - list->qlen--; + WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; -- cgit v1.2.3 From e4e8276a4f652be2c7bb783a0155d4adb85f5d7d Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Tue, 4 Feb 2020 18:18:15 +0530 Subject: spi: spi-omap2-mcspi: Handle DMA size restriction on AM65x On AM654, McSPI can only support 4K - 1 bytes per transfer when DMA is enabled. Therefore populate master->max_transfer_size callback to inform client drivers of this restriction when DMA channels are available. Signed-off-by: Vignesh Raghavendra Link: https://lore.kernel.org/r/20200204124816.16735-2-vigneshr@ti.com Signed-off-by: Mark Brown --- include/linux/platform_data/spi-omap2-mcspi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h index 0bf9fddb8306..3b400b1919a9 100644 --- a/include/linux/platform_data/spi-omap2-mcspi.h +++ b/include/linux/platform_data/spi-omap2-mcspi.h @@ -11,6 +11,7 @@ struct omap2_mcspi_platform_config { unsigned short num_cs; unsigned int regs_offset; unsigned int pin_dir:1; + size_t max_xfer_len; }; struct omap2_mcspi_device_config { -- cgit v1.2.3 From 61c00cca41aeeaa8e5263c2f81f28534bc1efafb Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 27 Jan 2020 14:18:14 +0200 Subject: net/mlx5: Deprecate usage of generic TLS HW capability bit Deprecate the generic TLS cap bit, use the new TX-specific TLS cap bit instead. Fixes: a12ff35e0fb7 ("net/mlx5: Introduce TLS TX offload hardware bits and structures") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 032cd6630720..ff8c9d527bb4 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1448,14 +1448,15 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_440[0x20]; - u8 tls[0x1]; - u8 reserved_at_461[0x2]; + u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5]; u8 reserved_at_468[0x3]; u8 log_max_umem[0x5]; u8 max_num_eqs[0x10]; - u8 reserved_at_480[0x3]; + u8 reserved_at_480[0x1]; + u8 tls_tx[0x1]; + u8 reserved_at_482[0x1]; u8 log_max_l2_table[0x5]; u8 reserved_at_488[0x8]; u8 log_uar_page_sz[0x10]; -- cgit v1.2.3 From 0f89589a8c6f1033cb847a606517998efb0da8ee Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 17 Dec 2019 14:15:04 -0500 Subject: Pass consistent param->type to fs_parse() As it is, vfs_parse_fs_string() makes "foo" and "foo=" indistinguishable; both get fs_value_is_string for ->type and NULL for ->string. To make it even more unpleasant, that combination is impossible to produce with fsconfig(). Much saner rules would be "foo" => fs_value_is_flag, NULL "foo=" => fs_value_is_string, "" "foo=bar" => fs_value_is_string, "bar" All cases are distinguishable, all results are expressable by fsconfig(), ->has_value checks are much simpler that way (to the point of the field being useless) and quite a few regressions go away (gfs2 has no business accepting -o nodebug=, for example). Partially based upon patches from Miklos. Signed-off-by: Al Viro --- include/linux/fs_parser.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index dee140db6240..45323203128b 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -72,7 +72,6 @@ struct fs_parameter_description { */ struct fs_parse_result { bool negated; /* T if param was "noxxx" */ - bool has_value; /* T if value supplied to param */ union { bool boolean; /* For spec_bool */ int int_32; /* For spec_s32/spec_enum */ -- cgit v1.2.3 From 2710c957a8ef4fb00f21acb306e3bd6bcf80c81f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 6 Sep 2019 22:12:08 -0400 Subject: fs_parse: get rid of ->enums Don't do a single array; attach them to fsparam_enum() entry instead. And don't bother trying to embed the names into those - it actually loses memory, with no real speedup worth mentioning. Simplifies validation as well. Signed-off-by: Al Viro --- include/linux/fs_parser.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 45323203128b..498cba1bbf6e 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -53,18 +53,17 @@ struct fs_parameter_spec { #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ #define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ + const void *data; }; struct fs_parameter_enum { - u8 opt; /* Option number (as fs_parameter_spec::opt) */ - char name[14]; + const char *name; u8 value; }; struct fs_parameter_description { const char name[16]; /* Name for logging purposes */ const struct fs_parameter_spec *specs; /* List of param specifications */ - const struct fs_parameter_enum *enums; /* Enum values */ }; /* @@ -114,33 +113,34 @@ static inline bool fs_validate_description(const struct fs_parameter_description * work, but any such case is probably a sign that new helper is needed. * Helpers will remain stable; low-level implementation may change. */ -#define __fsparam(TYPE, NAME, OPT, FLAGS) \ +#define __fsparam(TYPE, NAME, OPT, FLAGS, DATA) \ { \ .name = NAME, \ .opt = OPT, \ .type = TYPE, \ - .flags = FLAGS \ + .flags = FLAGS, \ + .data = DATA \ } -#define fsparam_flag(NAME, OPT) __fsparam(fs_param_is_flag, NAME, OPT, 0) +#define fsparam_flag(NAME, OPT) __fsparam(fs_param_is_flag, NAME, OPT, 0, NULL) #define fsparam_flag_no(NAME, OPT) \ __fsparam(fs_param_is_flag, NAME, OPT, \ - fs_param_neg_with_no) -#define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0) -#define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0) + fs_param_neg_with_no, NULL) +#define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0, NULL) +#define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0, NULL) #define fsparam_u32oct(NAME, OPT) \ - __fsparam(fs_param_is_u32_octal, NAME, OPT, 0) + __fsparam(fs_param_is_u32_octal, NAME, OPT, 0, NULL) #define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0) -#define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0) -#define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0) -#define fsparam_enum(NAME, OPT) __fsparam(fs_param_is_enum, NAME, OPT, 0) + __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, NULL) +#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) #define fsparam_string(NAME, OPT) \ - __fsparam(fs_param_is_string, NAME, OPT, 0) -#define fsparam_blob(NAME, OPT) __fsparam(fs_param_is_blob, NAME, OPT, 0) -#define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0) -#define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0) -#define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0) + __fsparam(fs_param_is_string, NAME, OPT, 0, NULL) +#define fsparam_blob(NAME, OPT) __fsparam(fs_param_is_blob, NAME, OPT, 0, NULL) +#define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) +#define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) +#define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) #endif /* _LINUX_FS_PARSER_H */ -- cgit v1.2.3 From 5eede625297f4d21dc12ea7a7418fd21672f131d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 16 Dec 2019 13:33:32 -0500 Subject: fold struct fs_parameter_enum into struct constant_table no real difference now Signed-off-by: Al Viro --- include/linux/fs_parser.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 498cba1bbf6e..5c91a0ac4446 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -56,11 +56,6 @@ struct fs_parameter_spec { const void *data; }; -struct fs_parameter_enum { - const char *name; - u8 value; -}; - struct fs_parameter_description { const char name[16]; /* Name for logging purposes */ const struct fs_parameter_spec *specs; /* List of param specifications */ -- cgit v1.2.3 From 34264ae3fa22429ec4fd9151602342d1f21486eb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 16 Dec 2019 13:45:41 -0500 Subject: don't bother with explicit length argument for __lookup_constant() Have the arrays of constant_table self-terminated (by NULL ->name in the final entry). Simplifies lookup_constant() and allows to reuse the search for enum params as well. Signed-off-by: Al Viro --- include/linux/fs_parser.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 5c91a0ac4446..14bdaacf1218 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -83,9 +83,7 @@ extern int fs_lookup_param(struct fs_context *fc, bool want_bdev, struct path *_path); -extern int __lookup_constant(const struct constant_table tbl[], size_t tbl_size, - const char *name, int not_found); -#define lookup_constant(t, n, nf) __lookup_constant(t, ARRAY_SIZE(t), (n), (nf)) +extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found); #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, -- cgit v1.2.3 From aa1918f9491442a007a0cbe41a31539233209777 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 17 Dec 2019 20:09:08 -0500 Subject: get rid of fs_value_is_filename_empty Its behaviour is identical to that of fs_value_is_filename. It makes no sense, anyway - LOOKUP_EMPTY affects nothing whatsoever once the pathname has been imported from userland. And both fs_value_is_filename and fs_value_is_filename_empty carry an already imported pathname. Signed-off-by: Al Viro --- include/linux/fs_context.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index e5c14e2c53d3..c7c69640a6c6 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -54,7 +54,6 @@ enum fs_value_type { fs_value_is_string, /* Value is a string */ fs_value_is_blob, /* Value is a binary blob */ fs_value_is_filename, /* Value is a filename* + dirfd */ - fs_value_is_filename_empty, /* Value is a filename* + dirfd + AT_EMPTY_PATH */ fs_value_is_file, /* Value is a file* */ }; -- cgit v1.2.3 From 9f09f649ca3350cdb49c81f7d5ac6e64a4d7e1a1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 20 Dec 2019 22:10:36 -0500 Subject: teach logfc() to handle prefices, give it saner calling conventions Signed-off-by: Al Viro --- include/linux/fs_context.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c7c69640a6c6..d18ff422e942 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -181,9 +181,13 @@ struct fc_log { char *buffer[8]; }; -extern __attribute__((format(printf, 2, 3))) -void logfc(struct fs_context *fc, const char *fmt, ...); +extern __attribute__((format(printf, 4, 5))) +void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...); +#define __logfc(fc, l, fmt, ...) ({ \ + struct fs_context *__fc = (fc); \ + logfc(__fc ? __fc->log : NULL, NULL, \ + l, fmt, ## __VA_ARGS__);}) /** * infof - Store supplementary informational message * @fc: The context in which to log the informational message @@ -192,7 +196,7 @@ void logfc(struct fs_context *fc, const char *fmt, ...); * Store the supplementary informational message for the process if the process * has enabled the facility. */ -#define infof(fc, fmt, ...) ({ logfc(fc, "i "fmt, ## __VA_ARGS__); }) +#define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message @@ -202,7 +206,7 @@ void logfc(struct fs_context *fc, const char *fmt, ...); * Store the supplementary warning message for the process if the process has * enabled the facility. */ -#define warnf(fc, fmt, ...) ({ logfc(fc, "w "fmt, ## __VA_ARGS__); }) +#define warnf(fc, fmt, ...) __logfc(fc, 'w', fmt, ## __VA_ARGS__) /** * errorf - Store supplementary error message @@ -212,7 +216,7 @@ void logfc(struct fs_context *fc, const char *fmt, ...); * Store the supplementary error message for the process if the process has * enabled the facility. */ -#define errorf(fc, fmt, ...) ({ logfc(fc, "e "fmt, ## __VA_ARGS__); }) +#define errorf(fc, fmt, ...) __logfc(fc, 'e', fmt, ## __VA_ARGS__) /** * invalf - Store supplementary invalid argument error message @@ -222,6 +226,6 @@ void logfc(struct fs_context *fc, const char *fmt, ...); * Store the supplementary error message for the process if the process has * enabled the facility and return -EINVAL. */ -#define invalf(fc, fmt, ...) ({ errorf(fc, fmt, ## __VA_ARGS__); -EINVAL; }) +#define invalf(fc, fmt, ...) (errorf(fc, fmt, ## __VA_ARGS__), -EINVAL) #endif /* _LINUX_FS_CONTEXT_H */ -- cgit v1.2.3 From 3fbb8d5554a1481d9c5f54ee7dc59f416650efb1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 20 Dec 2019 23:43:32 -0500 Subject: struct p_log, variants of warnf() et.al. taking that one instead primitives for prefixed logging Signed-off-by: Al Viro --- include/linux/fs_context.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index d18ff422e942..6a7eeb252084 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -73,6 +73,11 @@ struct fs_parameter { int dirfd; }; +struct p_log { + const char *prefix; + struct fc_log *log; +}; + /* * Filesystem context for holding the parameters used in the creation or * reconfiguration of a superblock. @@ -188,6 +193,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, struct fs_context *__fc = (fc); \ logfc(__fc ? __fc->log : NULL, NULL, \ l, fmt, ## __VA_ARGS__);}) +#define __plog(p, l, fmt, ...) logfc((p)->log, (p)->prefix, \ + l, fmt, ## __VA_ARGS__) /** * infof - Store supplementary informational message * @fc: The context in which to log the informational message @@ -197,6 +204,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, * has enabled the facility. */ #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) +#define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message @@ -207,6 +215,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, * enabled the facility. */ #define warnf(fc, fmt, ...) __logfc(fc, 'w', fmt, ## __VA_ARGS__) +#define warn_plog(p, fmt, ...) __plog(p, 'w', fmt, ## __VA_ARGS__) /** * errorf - Store supplementary error message @@ -217,6 +226,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, * enabled the facility. */ #define errorf(fc, fmt, ...) __logfc(fc, 'e', fmt, ## __VA_ARGS__) +#define error_plog(p, fmt, ...) __plog(p, 'e', fmt, ## __VA_ARGS__) /** * invalf - Store supplementary invalid argument error message @@ -227,5 +237,6 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, * enabled the facility and return -EINVAL. */ #define invalf(fc, fmt, ...) (errorf(fc, fmt, ## __VA_ARGS__), -EINVAL) +#define inval_plog(p, fmt, ...) (error_plog(p, fmt, ## __VA_ARGS__), -EINVAL) #endif /* _LINUX_FS_CONTEXT_H */ -- cgit v1.2.3 From 7f5d38141e309bb4ba995d9726928af85a299c50 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 20 Dec 2019 23:52:55 -0500 Subject: new primitive: __fs_parse() fs_parse() analogue taking p_log instead of fs_context. fs_parse() turned into a wrapper, callers in ceph_common and rbd switched to __fs_parse(). As the result, fs_parse() never gets NULL fs_context and neither do fs_context-based logging primitives Signed-off-by: Al Viro --- include/linux/fs_context.h | 6 ++---- include/linux/fs_parser.h | 4 ++++ 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 6a7eeb252084..41f37d33e358 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -189,10 +189,8 @@ struct fc_log { extern __attribute__((format(printf, 4, 5))) void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...); -#define __logfc(fc, l, fmt, ...) ({ \ - struct fs_context *__fc = (fc); \ - logfc(__fc ? __fc->log : NULL, NULL, \ - l, fmt, ## __VA_ARGS__);}) +#define __logfc(fc, l, fmt, ...) logfc((fc)->log, NULL, \ + l, fmt, ## __VA_ARGS__) #define __plog(p, l, fmt, ...) logfc((p)->log, (p)->prefix, \ l, fmt, ## __VA_ARGS__) /** diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 14bdaacf1218..b0fba26a4ffe 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -74,6 +74,10 @@ struct fs_parse_result { }; }; +extern int __fs_parse(struct p_log *log, + const struct fs_parameter_description *desc, + struct fs_parameter *value, + struct fs_parse_result *result); extern int fs_parse(struct fs_context *fc, const struct fs_parameter_description *desc, struct fs_parameter *value, -- cgit v1.2.3 From c80c98f0dc5dc709b04254b5f30145c6ab8800a4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 21 Dec 2019 00:06:01 -0500 Subject: ceph_parse_param(), ceph_parse_mon_ips(): switch to passing fc_log ... and now errorf() et.al. are never called with NULL fs_context, so we can get rid of conditional in those. Signed-off-by: Al Viro --- include/linux/ceph/libceph.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 8fe9b80e80a5..ec73ebc4827d 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -281,11 +281,12 @@ extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); extern void *ceph_kvmalloc(size_t size, gfp_t flags); struct fs_parameter; +struct fc_log; struct ceph_options *ceph_alloc_options(void); int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, - struct fs_context *fc); + struct fc_log *l); int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, - struct fs_context *fc); + struct fc_log *l); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, bool show_all); extern void ceph_destroy_options(struct ceph_options *opt); -- cgit v1.2.3 From cc3c0b533ab9142eac2e291628fbfca3685f38cd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 21 Dec 2019 00:16:49 -0500 Subject: add prefix to fs_context->log ... turning it into struct p_log embedded into fs_context. Initialize the prefix with fs_type->name, turning fs_parse() into a trivial inline wrapper for __fs_parse(). This makes fs_parameter_description->name completely unused. Signed-off-by: Al Viro --- include/linux/fs_context.h | 4 ++-- include/linux/fs_parser.h | 13 +++++++++---- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 41f37d33e358..b2ad9b0a7af4 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -97,7 +97,7 @@ struct fs_context { struct user_namespace *user_ns; /* The user namespace for this mount */ struct net *net_ns; /* The network namespace for this mount */ const struct cred *cred; /* The mounter's credentials */ - struct fc_log *log; /* Logging buffer */ + struct p_log log; /* Logging buffer */ const char *source; /* The source name (eg. dev path) */ void *security; /* Linux S&M options */ void *s_fs_info; /* Proposed s_fs_info */ @@ -189,7 +189,7 @@ struct fc_log { extern __attribute__((format(printf, 4, 5))) void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...); -#define __logfc(fc, l, fmt, ...) logfc((fc)->log, NULL, \ +#define __logfc(fc, l, fmt, ...) logfc((fc)->log.log, NULL, \ l, fmt, ## __VA_ARGS__) #define __plog(p, l, fmt, ...) logfc((p)->log, (p)->prefix, \ l, fmt, ## __VA_ARGS__) diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index b0fba26a4ffe..37459124c1c1 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -78,10 +78,15 @@ extern int __fs_parse(struct p_log *log, const struct fs_parameter_description *desc, struct fs_parameter *value, struct fs_parse_result *result); -extern int fs_parse(struct fs_context *fc, - const struct fs_parameter_description *desc, - struct fs_parameter *value, - struct fs_parse_result *result); + +static inline int fs_parse(struct fs_context *fc, + const struct fs_parameter_description *desc, + struct fs_parameter *param, + struct fs_parse_result *result) +{ + return __fs_parse(&fc->log, desc, param, result); +} + extern int fs_lookup_param(struct fs_context *fc, struct fs_parameter *param, bool want_bdev, -- cgit v1.2.3 From 96cafb9ccb153f6a82ff2c9bde68916d9d65501e Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 6 Dec 2019 10:45:01 -0600 Subject: fs_parser: remove fs_parameter_description name field Unused now. Signed-off-by: Eric Sandeen Acked-by: David Howells Signed-off-by: Al Viro --- include/linux/fs_parser.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 37459124c1c1..ac439ee50aab 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -57,7 +57,6 @@ struct fs_parameter_spec { }; struct fs_parameter_description { - const char name[16]; /* Name for logging purposes */ const struct fs_parameter_spec *specs; /* List of param specifications */ }; @@ -97,12 +96,14 @@ extern int lookup_constant(const struct constant_table tbl[], const char *name, #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); -extern bool fs_validate_description(const struct fs_parameter_description *desc); +extern bool fs_validate_description(const char *name, + const struct fs_parameter_description *desc); #else static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special) { return true; } -static inline bool fs_validate_description(const struct fs_parameter_description *desc) +static inline bool fs_validate_description(const char *name, + const struct fs_parameter_description *desc) { return true; } #endif -- cgit v1.2.3 From d7167b149943e38ad610191ecbb0800c78bbced9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 7 Sep 2019 07:23:15 -0400 Subject: fs_parse: fold fs_parameter_desc/fs_parameter_spec The former contains nothing but a pointer to an array of the latter... Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- include/linux/fs_parser.h | 12 ++++-------- include/linux/ramfs.h | 4 +++- include/linux/shmem_fs.h | 3 ++- 4 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..5ace552a2a23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -67,7 +67,7 @@ struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fs_context; -struct fs_parameter_description; +struct fs_parameter_spec; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -2224,7 +2224,7 @@ struct file_system_type { #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #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_description *parameters; + const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index ac439ee50aab..dcbac245e7a3 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -56,10 +56,6 @@ struct fs_parameter_spec { const void *data; }; -struct fs_parameter_description { - const struct fs_parameter_spec *specs; /* List of param specifications */ -}; - /* * Result of parse. */ @@ -74,12 +70,12 @@ struct fs_parse_result { }; extern int __fs_parse(struct p_log *log, - const struct fs_parameter_description *desc, + const struct fs_parameter_spec *desc, struct fs_parameter *value, struct fs_parse_result *result); static inline int fs_parse(struct fs_context *fc, - const struct fs_parameter_description *desc, + const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { @@ -97,13 +93,13 @@ extern int lookup_constant(const struct constant_table tbl[], const char *name, extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); extern bool fs_validate_description(const char *name, - const struct fs_parameter_description *desc); + const struct fs_parameter_spec *desc); #else static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special) { return true; } static inline bool fs_validate_description(const char *name, - const struct fs_parameter_description *desc) + const struct fs_parameter_spec *desc) { return true; } #endif diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index b806a0ff6554..917528d102c4 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -2,6 +2,8 @@ #ifndef _LINUX_RAMFS_H #define _LINUX_RAMFS_H +#include // bleh... + struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev); extern int ramfs_init_fs_context(struct fs_context *fc); @@ -16,7 +18,7 @@ ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) extern int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize); #endif -extern const struct fs_parameter_description ramfs_fs_parameters; +extern const struct fs_parameter_spec ramfs_fs_parameters[]; extern const struct file_operations ramfs_file_operations; extern const struct vm_operations_struct generic_file_vm_ops; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index de8e4b71e3ba..d56fefef8905 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -8,6 +8,7 @@ #include #include #include +#include /* inode in-kernel data */ @@ -49,7 +50,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) /* * Functions in mm/shmem.c called directly from elsewhere: */ -extern const struct fs_parameter_description shmem_fs_parameters; +extern const struct fs_parameter_spec shmem_fs_parameters[]; extern int shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, -- cgit v1.2.3 From 48ce73b1bef20331007b35de7ade8fe26cd55e84 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 17 Dec 2019 20:03:59 -0500 Subject: fs_parse: handle optional arguments sanely Don't bother with "mixed" options that would allow both the form with and without argument (i.e. both -o foo and -o foo=bar). Rather than trying to shove both into a single fs_parameter_spec, allow having with-argument and no-argument specs with the same name and teach fs_parse to handle that. There are very few options of that sort, and they are actually easier to handle that way - callers end up with less postprocessing. Signed-off-by: Al Viro --- include/linux/fs_parser.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index dcbac245e7a3..2e1e15f0cf4a 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -49,7 +49,6 @@ struct fs_parameter_spec { u8 opt; /* Option number (returned by fs_parse()) */ enum fs_parameter_type type:8; /* The desired parameter type */ unsigned short flags; -#define fs_param_v_optional 0x0001 /* The value is optional */ #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ #define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ -- cgit v1.2.3 From 328de5287b10abc967c517461cf2948bd8a5b4e9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 18 Dec 2019 00:02:31 -0500 Subject: turn fs_param_is_... into functions Signed-off-by: Al Viro --- include/linux/fs_parser.h | 38 ++++++++++++++------------------------ 1 file changed, 14 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 2e1e15f0cf4a..2eab6d5f6736 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -17,26 +17,18 @@ struct constant_table { int value; }; +struct fs_parameter_spec; +struct fs_parse_result; +typedef int fs_param_type(struct p_log *, + const struct fs_parameter_spec *, + struct fs_parameter *, + struct fs_parse_result *); /* * The type of parameter expected. */ -enum fs_parameter_type { - __fs_param_wasnt_defined, - fs_param_is_flag, - fs_param_is_bool, - fs_param_is_u32, - fs_param_is_u32_octal, - fs_param_is_u32_hex, - fs_param_is_s32, - fs_param_is_u64, - fs_param_is_enum, - fs_param_is_string, - fs_param_is_blob, - fs_param_is_blockdev, - fs_param_is_path, - fs_param_is_fd, - nr__fs_parameter_type, -}; +fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, + fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, + fs_param_is_path, fs_param_is_fd; /* * Specification of the type of value a parameter wants. @@ -46,8 +38,8 @@ enum fs_parameter_type { */ struct fs_parameter_spec { const char *name; + fs_param_type *type; /* The desired parameter type */ u8 opt; /* Option number (returned by fs_parse()) */ - enum fs_parameter_type type:8; /* The desired parameter type */ unsigned short flags; #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ #define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ @@ -120,16 +112,15 @@ static inline bool fs_validate_description(const char *name, .data = DATA \ } -#define fsparam_flag(NAME, OPT) __fsparam(fs_param_is_flag, NAME, OPT, 0, NULL) +#define fsparam_flag(NAME, OPT) __fsparam(NULL, NAME, OPT, 0, NULL) #define fsparam_flag_no(NAME, OPT) \ - __fsparam(fs_param_is_flag, NAME, OPT, \ - fs_param_neg_with_no, NULL) + __fsparam(NULL, NAME, OPT, fs_param_neg_with_no, NULL) #define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0, NULL) #define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0, NULL) #define fsparam_u32oct(NAME, OPT) \ - __fsparam(fs_param_is_u32_octal, NAME, OPT, 0, NULL) + __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, NULL) + __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) @@ -140,5 +131,4 @@ static inline bool fs_validate_description(const char *name, #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) - #endif /* _LINUX_FS_PARSER_H */ -- cgit v1.2.3 From a3ff937b33d9dfd0923ac5279d87723048599057 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 21 Dec 2019 21:30:50 -0500 Subject: prefix-handling analogues of errorf() and friends called errorfc/infofc/warnfc/invalfc Signed-off-by: Al Viro --- include/linux/fs_context.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index b2ad9b0a7af4..e6c3e4c61dad 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -203,6 +203,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, */ #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__) +#define infofc(p, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message @@ -214,6 +215,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, */ #define warnf(fc, fmt, ...) __logfc(fc, 'w', fmt, ## __VA_ARGS__) #define warn_plog(p, fmt, ...) __plog(p, 'w', fmt, ## __VA_ARGS__) +#define warnfc(fc, fmt, ...) __plog((&(fc)->log), 'w', fmt, ## __VA_ARGS__) /** * errorf - Store supplementary error message @@ -225,6 +227,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, */ #define errorf(fc, fmt, ...) __logfc(fc, 'e', fmt, ## __VA_ARGS__) #define error_plog(p, fmt, ...) __plog(p, 'e', fmt, ## __VA_ARGS__) +#define errorfc(fc, fmt, ...) __plog((&(fc)->log), 'e', fmt, ## __VA_ARGS__) /** * invalf - Store supplementary invalid argument error message @@ -236,5 +239,6 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, */ #define invalf(fc, fmt, ...) (errorf(fc, fmt, ## __VA_ARGS__), -EINVAL) #define inval_plog(p, fmt, ...) (error_plog(p, fmt, ## __VA_ARGS__), -EINVAL) +#define invalfc(fc, fmt, ...) (errorfc(fc, fmt, ## __VA_ARGS__), -EINVAL) #endif /* _LINUX_FS_CONTEXT_H */ -- cgit v1.2.3 From 8b718d403c5cdc7f0ea492c33ec88169f3e76462 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 6 Feb 2020 15:57:07 +0800 Subject: irqchip/gic-v4.1: Set vpe_l1_base for all redistributors Currently, we will not set vpe_l1_page for the current RD if we can inherit the vPE configuration table from another RD (or ITS), which results in an inconsistency between RDs within the same CommonLPIAff group. Let's rename it to vpe_l1_base to indicate the base address of the vPE configuration table of this RD, and set it properly for *all* v4.1 redistributors. Signed-off-by: Zenghui Yu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20200206075711.1275-3-yuzenghui@huawei.com --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index f0b8ca766e7d..83439bfb6c5b 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -652,10 +652,10 @@ struct rdists { struct { void __iomem *rd_base; struct page *pend_page; - struct page *vpe_l1_page; phys_addr_t phys_base; bool lpi_enabled; cpumask_t *vpe_table_mask; + void *vpe_l1_base; } __percpu *rdist; phys_addr_t prop_table_pa; void *prop_table_va; -- cgit v1.2.3 From 0ddad21d3e99c743a3aa473121dc5561679e26bb Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 9 Dec 2019 09:48:27 -0800 Subject: pipe: use exclusive waits when reading or writing This makes the pipe code use separate wait-queues and exclusive waiting for readers and writers, avoiding a nasty thundering herd problem when there are lots of readers waiting for data on a pipe (or, less commonly, lots of writers waiting for a pipe to have space). While this isn't a common occurrence in the traditional "use a pipe as a data transport" case, where you typically only have a single reader and a single writer process, there is one common special case: using a pipe as a source of "locking tokens" rather than for data communication. In particular, the GNU make jobserver code ends up using a pipe as a way to limit parallelism, where each job consumes a token by reading a byte from the jobserver pipe, and releases the token by writing a byte back to the pipe. This pattern is fairly traditional on Unix, and works very well, but will waste a lot of time waking up a lot of processes when only a single reader needs to be woken up when a writer releases a new token. A simplified test-case of just this pipe interaction is to create 64 processes, and then pass a single token around between them (this test-case also intentionally passes another token that gets ignored to test the "wake up next" logic too, in case anybody wonders about it): #include int main(int argc, char **argv) { int fd[2], counters[2]; pipe(fd); counters[0] = 0; counters[1] = -1; write(fd[1], counters, sizeof(counters)); /* 64 processes */ fork(); fork(); fork(); fork(); fork(); fork(); do { int i; read(fd[0], &i, sizeof(i)); if (i < 0) continue; counters[0] = i+1; write(fd[1], counters, (1+(i & 1)) *sizeof(int)); } while (counters[0] < 1000000); return 0; } and in a perfect world, passing that token around should only cause one context switch per transfer, when the writer of a token causes a directed wakeup of just a single reader. But with the "writer wakes all readers" model we traditionally had, on my test box the above case causes more than an order of magnitude more scheduling: instead of the expected ~1M context switches, "perf stat" shows 231,852.37 msec task-clock # 15.857 CPUs utilized 11,250,961 context-switches # 0.049 M/sec 616,304 cpu-migrations # 0.003 M/sec 1,648 page-faults # 0.007 K/sec 1,097,903,998,514 cycles # 4.735 GHz 120,781,778,352 instructions # 0.11 insn per cycle 27,997,056,043 branches # 120.754 M/sec 283,581,233 branch-misses # 1.01% of all branches 14.621273891 seconds time elapsed 0.018243000 seconds user 3.611468000 seconds sys before this commit. After this commit, I get 5,229.55 msec task-clock # 3.072 CPUs utilized 1,212,233 context-switches # 0.232 M/sec 103,951 cpu-migrations # 0.020 M/sec 1,328 page-faults # 0.254 K/sec 21,307,456,166 cycles # 4.074 GHz 12,947,819,999 instructions # 0.61 insn per cycle 2,881,985,678 branches # 551.096 M/sec 64,267,015 branch-misses # 2.23% of all branches 1.702148350 seconds time elapsed 0.004868000 seconds user 0.110786000 seconds sys instead. Much better. [ Note! This kernel improvement seems to be very good at triggering a race condition in the make jobserver (in GNU make 4.2.1) for me. It's a long known bug that was fixed back in June 2017 by GNU make commit b552b0525198 ("[SV 51159] Use a non-blocking read with pselect to avoid hangs."). But there wasn't a new release of GNU make until 4.3 on Jan 19 2020, so a number of distributions may still have the buggy version. Some have backported the fix to their 4.2.1 release, though, and even without the fix it's quite timing-dependent whether the bug actually is hit. ] Josh Triplett says: "I've been hammering on your pipe fix patch (switching to exclusive wait queues) for a month or so, on several different systems, and I've run into no issues with it. The patch *substantially* improves parallel build times on large (~100 CPU) systems, both with parallel make and with other things that use make's pipe-based jobserver. All current distributions (including stable and long-term stable distributions) have versions of GNU make that no longer have the jobserver bug" Tested-by: Josh Triplett Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index dbcfa6892384..d5765039652a 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -47,7 +47,7 @@ struct pipe_buffer { **/ struct pipe_inode_info { struct mutex mutex; - wait_queue_head_t wait; + wait_queue_head_t rd_wait, wr_wait; unsigned int head; unsigned int tail; unsigned int max_usage; -- cgit v1.2.3 From e7598fac323aad0e502415edeffd567315994dd6 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 10 Feb 2020 10:36:56 +0100 Subject: iommu/vt-d: Fix compile warning from intel-svm.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The intel_svm_is_pasid_valid() needs to be marked inline, otherwise it causes the compile warning below: CC [M] drivers/dma/idxd/cdev.o In file included from drivers/dma/idxd/cdev.c:9:0: ./include/linux/intel-svm.h:125:12: warning: ‘intel_svm_is_pasid_valid’ defined but not used [-Wunused-function] static int intel_svm_is_pasid_valid(struct device *dev, int pasid) ^~~~~~~~~~~~~~~~~~~~~~~~ Reported-by: Borislav Petkov Fixes: 15060aba71711 ('iommu/vt-d: Helper function to query if a pasid has any active users') Signed-off-by: Joerg Roedel --- include/linux/intel-svm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 94f047a8a845..d7c403d0dd27 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -122,7 +122,7 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid) BUG(); } -static int intel_svm_is_pasid_valid(struct device *dev, int pasid) +static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid) { return -EINVAL; } -- cgit v1.2.3 From 73f8bda9b5dc1c69df2bc55c0cbb24461a6391a9 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 3 Feb 2020 16:38:28 +0100 Subject: USB: core: add endpoint-blacklist quirk Add a new device quirk that can be used to blacklist endpoints. Since commit 3e4f8e21c4f2 ("USB: core: fix check for duplicate endpoints") USB core ignores any duplicate endpoints found during descriptor parsing. In order to handle devices where the first interfaces with duplicate endpoints are the ones that should have their endpoints ignored, we need to add a blacklist. Tested-by: edes Cc: stable Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20200203153830.26394-2-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index a1be64c9940f..22c1f579afe3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -69,4 +69,7 @@ /* Hub needs extra delay after resetting its port. */ #define USB_QUIRK_HUB_SLOW_RESET BIT(14) +/* device has blacklisted endpoints */ +#define USB_QUIRK_ENDPOINT_BLACKLIST BIT(15) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 0c5aae59270fb1f827acce182786094c9ccf598e Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 10 Feb 2020 15:57:30 +0100 Subject: serdev: ttyport: restore client ops on deregistration The serdev tty-port controller driver should reset the tty-port client operations also on deregistration to avoid a NULL-pointer dereference in case the port is later re-registered as a normal tty device. Note that this can only happen with tty drivers such as 8250 which have statically allocated port structures that can end up being reused and where a later registration would not register a serdev controller (e.g. due to registration errors or if the devicetree has been changed in between). Specifically, this can be an issue for any statically defined ports that would be registered by 8250 core when an 8250 driver is being unbound. Fixes: bed35c6dfa6a ("serdev: add a tty port controller driver") Cc: stable # 4.11 Reported-by: Loic Poulain Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20200210145730.22762-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index bfa4e2ee94a9..bd5fe0e907e8 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -225,6 +225,8 @@ struct tty_port_client_operations { void (*write_wakeup)(struct tty_port *port); }; +extern const struct tty_port_client_operations tty_port_default_client_ops; + struct tty_port { struct tty_bufhead buf; /* Locked internally */ struct tty_struct *tty; /* Back pointer */ -- cgit v1.2.3 From ae91c92565494a37c30ce9a691c87890f800d826 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 22 Nov 2019 11:44:53 +0100 Subject: debugfs: remove return value of debugfs_create_regset32() No one checks the return value of debugfs_create_regset32(), 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/20191122104453.GA2017837@kroah.com Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 3d013de64f70..43efcc49f061 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -127,9 +127,9 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, struct debugfs_blob_wrapper *blob); -struct dentry *debugfs_create_regset32(const char *name, umode_t mode, - struct dentry *parent, - struct debugfs_regset32 *regset); +void debugfs_create_regset32(const char *name, umode_t mode, + struct dentry *parent, + struct debugfs_regset32 *regset); void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); @@ -304,11 +304,10 @@ static inline struct dentry *debugfs_create_blob(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } -static inline struct dentry *debugfs_create_regset32(const char *name, - umode_t mode, struct dentry *parent, - struct debugfs_regset32 *regset) +static inline void debugfs_create_regset32(const char *name, umode_t mode, + struct dentry *parent, + struct debugfs_regset32 *regset) { - return ERR_PTR(-ENODEV); } static inline void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, -- cgit v1.2.3 From 7276531d4036f5db2af15c8b6caa02e7741f5d80 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Mon, 10 Feb 2020 17:06:50 -0600 Subject: tracing: Consolidate trace() functions Move the checking, buffer reserve and buffer commit code in synth_event_trace_start/end() into inline functions __synth_event_trace_start/end() so they can also be used by synth_event_trace() and synth_event_trace_array(), and then have all those functions use them. Also, change synth_event_trace_state.enabled to disabled so it only needs to be set if the event is disabled, which is not normally the case. Link: http://lkml.kernel.org/r/b1f3108d0f450e58192955a300e31d0405ab4149.1581374549.git.zanussi@kernel.org Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 67f528ecb9e5..21098298b49b 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -424,7 +424,7 @@ struct synth_event_trace_state { struct synth_event *event; unsigned int cur_field; unsigned int n_u64; - bool enabled; + bool disabled; bool add_next; bool add_name; }; -- cgit v1.2.3 From e3728b50cd9be7d4b1469447cdf1feb93e3b7adb Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 11 Feb 2020 10:11:02 +0100 Subject: ACPI: PM: s2idle: Avoid possible race related to the EC GPE It is theoretically possible for the ACPI EC GPE to be set after the s2idle_ops->wake() called from s2idle_loop() has returned and before the subsequent pm_wakeup_pending() check is carried out. If that happens, the resulting wakeup event will cause the system to resume even though it may be a spurious one. To avoid that race, first make the ->wake() callback in struct platform_s2idle_ops return a bool value indicating whether or not to let the system resume and rearrange s2idle_loop() to use that value instad of the direct pm_wakeup_pending() call if ->wake() is present. Next, rework acpi_s2idle_wake() to process EC events and check pm_wakeup_pending() before re-arming the SCI for system wakeup to prevent it from triggering prematurely and add comments to that function to explain the rationale for the new code flow. Fixes: 56b991849009 ("PM: sleep: Simplify suspend-to-idle control flow") Cc: 5.4+ # 5.4+ Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 4a230c2f1c31..2b2055b035ee 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -191,7 +191,7 @@ struct platform_s2idle_ops { int (*begin)(void); int (*prepare)(void); int (*prepare_late)(void); - void (*wake)(void); + bool (*wake)(void); void (*restore_early)(void); void (*restore)(void); void (*end)(void); -- cgit v1.2.3 From 84a4062632462c4320704fcdf8e99e89e94c0aba Mon Sep 17 00:00:00 2001 From: Johan Korsnes Date: Fri, 17 Jan 2020 13:08:36 +0100 Subject: HID: core: increase HID report buffer size to 8KiB We have a HID touch device that reports its opens and shorts test results in HID buffers of size 8184 bytes. The maximum size of the HID buffer is currently set to 4096 bytes, causing probe of this device to fail. With this patch we increase the maximum size of the HID buffer to 8192 bytes, making device probe and acquisition of said buffers succeed. Signed-off-by: Johan Korsnes Cc: Alan Stern Cc: Armando Visconti Cc: Jiri Kosina Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index cd41f209043f..875f71132b14 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -492,7 +492,7 @@ struct hid_report_enum { }; #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ -#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ +#define HID_MAX_BUFFER_SIZE 8192 /* 8kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ #define HID_OUTPUT_FIFO_SIZE 64 -- cgit v1.2.3 From efeda80da38d0b4afd77a12bd4a44f657567d26c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 5 Feb 2020 09:01:54 -0500 Subject: NFSv4: Fix revalidation of dentries with delegations If a dentry was not initially looked up while we were holding a delegation, then we do still need to revalidate that it still holds the same name. If there are multiple hard links to the same file, then all the hard links need validation. Reported-by: Benjamin Coddington Signed-off-by: Trond Myklebust Reviewed-by: Benjamin Coddington Tested-by: Benjamin Coddington [Anna: Put nfs_unset_verifier_delegated() under CONFIG_NFS_V4] Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 26 ++++++-------------------- 1 file changed, 6 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a5f8f03ecd59..5d5b91e54f73 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -337,35 +337,17 @@ static inline int nfs_server_capable(struct inode *inode, int cap) return NFS_SERVER(inode)->caps & cap; } -static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf) -{ - dentry->d_time = verf; -} - /** * nfs_save_change_attribute - Returns the inode attribute change cookie * @dir - pointer to parent directory inode - * The "change attribute" is updated every time we finish an operation - * that will result in a metadata change on the server. + * The "cache change attribute" is updated when we need to revalidate + * our dentry cache after a directory was seen to change on the server. */ static inline unsigned long nfs_save_change_attribute(struct inode *dir) { return NFS_I(dir)->cache_change_attribute; } -/** - * nfs_verify_change_attribute - Detects NFS remote directory changes - * @dir - pointer to parent directory inode - * @chattr - previously saved change attribute - * Return "false" if the verifiers doesn't match the change attribute. - * This would usually indicate that the directory contents have changed on - * the server, and that any dentries need revalidating. - */ -static inline int nfs_verify_change_attribute(struct inode *dir, unsigned long chattr) -{ - return chattr == NFS_I(dir)->cache_change_attribute; -} - /* * linux/fs/nfs/inode.c */ @@ -495,6 +477,10 @@ extern const struct file_operations nfs_dir_operations; extern const struct dentry_operations nfs_dentry_operations; extern void nfs_force_lookup_revalidate(struct inode *dir); +extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); +#if IS_ENABLED(CONFIG_NFS_V4) +extern void nfs_clear_verifier_delegated(struct inode *inode); +#endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label); -- cgit v1.2.3 From 0bf999f9c5e74c7ecf9dafb527146601e5c848b9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 9 Feb 2020 19:36:14 -0800 Subject: linux/pipe_fs_i.h: fix kernel-doc warnings after @wait was split Fix kernel-doc warnings in struct pipe_inode_info after @wait was split into @rd_wait and @wr_wait. include/linux/pipe_fs_i.h:66: warning: Function parameter or member 'rd_wait' not described in 'pipe_inode_info' include/linux/pipe_fs_i.h:66: warning: Function parameter or member 'wr_wait' not described in 'pipe_inode_info' Fixes: 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing") Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index d5765039652a..ae58fad7f1e0 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -29,7 +29,8 @@ struct pipe_buffer { /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing - * @wait: reader/writer wait point in case of empty/full pipe + * @rd_wait: reader wait point in case of empty pipe + * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption * @max_usage: The maximum number of slots that may be used in the ring -- cgit v1.2.3 From 4a4472fdc098fb78f52a0848788faf46674a8423 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 12 Feb 2020 10:43:17 +0100 Subject: of: clk: Make of_clk_get_parent_{count,name}() parameter const of_clk_get_parent_count() and of_clk_get_parent_name() never modify the device nodes passed, so they can be const. Signed-off-by: Geert Uytterhoeven Link: https://lkml.kernel.org/r/20200212094317.1150-1-geert+renesas@glider.be Signed-off-by: Stephen Boyd --- include/linux/of_clk.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_clk.h b/include/linux/of_clk.h index c86fcad23fc2..31b73a0da9db 100644 --- a/include/linux/of_clk.h +++ b/include/linux/of_clk.h @@ -11,17 +11,17 @@ struct of_device_id; #if defined(CONFIG_COMMON_CLK) && defined(CONFIG_OF) -unsigned int of_clk_get_parent_count(struct device_node *np); -const char *of_clk_get_parent_name(struct device_node *np, int index); +unsigned int of_clk_get_parent_count(const struct device_node *np); +const char *of_clk_get_parent_name(const struct device_node *np, int index); void of_clk_init(const struct of_device_id *matches); #else /* !CONFIG_COMMON_CLK || !CONFIG_OF */ -static inline unsigned int of_clk_get_parent_count(struct device_node *np) +static inline unsigned int of_clk_get_parent_count(const struct device_node *np) { return 0; } -static inline const char *of_clk_get_parent_name(struct device_node *np, +static inline const char *of_clk_get_parent_name(const struct device_node *np, int index) { return NULL; -- cgit v1.2.3 From dbb92f88648d6206bf22fcb764fb9fe2939d401a Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Wed, 22 Jan 2020 19:39:52 +0100 Subject: workqueue: Document (some) memory-ordering properties of {queue,schedule}_work() It's desirable to be able to rely on the following property: All stores preceding (in program order) a call to a successful queue_work() will be visible from the CPU which will execute the queued work by the time such work executes, e.g., { x is initially 0 } CPU0 CPU1 WRITE_ONCE(x, 1); [ "work" is being executed ] r0 = queue_work(wq, work); r1 = READ_ONCE(x); Forbids: r0 == true && r1 == 0 The current implementation of queue_work() provides such memory-ordering property: - In __queue_work(), the ->lock spinlock is acquired. - On the other side, in worker_thread(), this same ->lock is held when dequeueing work. So the locking ordering makes things work out. Add this property to the DocBook headers of {queue,schedule}_work(). Suggested-by: Paul E. McKenney Signed-off-by: Andrea Parri Acked-by: Paul E. McKenney Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4261d1c6e87b..e48554e6526c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -487,6 +487,19 @@ extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. + * + * Memory-ordering properties: If it returns %true, guarantees that all stores + * preceding the call to queue_work() in the program order will be visible from + * the CPU which will execute @work by the time such work executes, e.g., + * + * { x is initially 0 } + * + * CPU0 CPU1 + * + * WRITE_ONCE(x, 1); [ @work is being executed ] + * r0 = queue_work(wq, work); r1 = READ_ONCE(x); + * + * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) @@ -546,6 +559,9 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work) * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. + * + * Shares the same memory-ordering properties of queue_work(), cf. the + * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { -- cgit v1.2.3 From 9c974c77246460fa6a92c18554c3311c8c83c160 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Koutn=C3=BD?= Date: Fri, 24 Jan 2020 12:40:15 +0100 Subject: cgroup: Iterate tasks that did not finish do_exit() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PF_EXITING is set earlier than actual removal from css_set when a task is exitting. This can confuse cgroup.procs readers who see no PF_EXITING tasks, however, rmdir is checking against css_set membership so it can transitionally fail with EBUSY. Fix this by listing tasks that weren't unlinked from css_set active lists. It may happen that other users of the task iterator (without CSS_TASK_ITER_PROCS) spot a PF_EXITING task before cgroup_exit(). This is equal to the state before commit c03cd7738a83 ("cgroup: Include dying leaders with live threads in PROCS iterations") but it may be reviewed later. Reported-by: Suren Baghdasaryan Fixes: c03cd7738a83 ("cgroup: Include dying leaders with live threads in PROCS iterations") Signed-off-by: Michal Koutný Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index d7ddebd0cdec..e75d2191226b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -62,6 +62,7 @@ struct css_task_iter { struct list_head *mg_tasks_head; struct list_head *dying_tasks_head; + struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; -- cgit v1.2.3 From 0b41713b606694257b90d61ba7e2712d8457648b Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 11 Feb 2020 20:47:05 +0100 Subject: icmp: introduce helper for nat'd source address in network device context This introduces a helper function to be called only by network drivers that wraps calls to icmp[v6]_send in a conntrack transformation, in case NAT has been used. We don't want to pollute the non-driver path, though, so we introduce this as a helper to be called by places that actually make use of this, as suggested by Florian. Signed-off-by: Jason A. Donenfeld Cc: Florian Westphal Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index ef1cbb5f454f..93338fd54af8 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -31,6 +31,12 @@ static inline void icmpv6_send(struct sk_buff *skb, } #endif +#if IS_ENABLED(CONFIG_NF_NAT) +void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); +#else +#define icmpv6_ndo_send icmpv6_send +#endif + extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); -- cgit v1.2.3 From a1fa83bdab784fa0ff2e92870011c0dcdbd2f680 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 12 Feb 2020 22:28:20 -0800 Subject: netdevice.h: fix all kernel-doc and Sphinx warnings Eliminate all kernel-doc and Sphinx warnings in . Fixes these warnings: ../include/linux/netdevice.h:2100: warning: Function parameter or member 'gso_partial_features' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'l3mdev_ops' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'xfrmdev_ops' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'tlsdev_ops' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'name_assign_type' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'ieee802154_ptr' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'mpls_ptr' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'xdp_prog' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'gro_flush_timeout' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'xdp_bulkq' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'xps_cpus_map' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'xps_rxqs_map' not described in 'net_device' ../include/linux/netdevice.h:2100: warning: Function parameter or member 'qdisc_hash' not described in 'net_device' ../include/linux/netdevice.h:3552: WARNING: Inline emphasis start-string without end-string. ../include/linux/netdevice.h:3552: WARNING: Inline emphasis start-string without end-string. Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/netdevice.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a9c6b5c61d27..9f1f633235f6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1616,6 +1616,7 @@ enum netdev_priv_flags { * and drivers will need to set them appropriately. * * @mpls_features: Mask of features inheritable by MPLS + * @gso_partial_features: value(s) from NETIF_F_GSO\* * * @ifindex: interface index * @group: The group the device belongs to @@ -1640,8 +1641,11 @@ enum netdev_priv_flags { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations + * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour * discovery handling. Necessary for e.g. 6LoWPAN. + * @xfrmdev_ops: Transformation offload operations + * @tlsdev_ops: Transport Layer Security offload operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * @@ -1680,6 +1684,7 @@ enum netdev_priv_flags { * @dev_port: Used to differentiate devices that share * the same function * @addr_list_lock: XXX: need comments on this one + * @name_assign_type: network interface name assignment type * @uc_promisc: Counter that indicates promiscuous mode * has been enabled due to the need to listen to * additional unicast addresses in a device that @@ -1702,6 +1707,9 @@ enum netdev_priv_flags { * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering + * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network + * device struct + * @mpls_ptr: mpls_dev struct pointer * * @dev_addr: Hw address (before bcast, * because most packets are unicast) @@ -1710,6 +1718,8 @@ enum netdev_priv_flags { * @num_rx_queues: Number of RX queues * allocated at register_netdev() time * @real_num_rx_queues: Number of RX queues currently active in device + * @xdp_prog: XDP sockets filter program pointer + * @gro_flush_timeout: timeout for GRO layer in NAPI * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one @@ -1731,10 +1741,14 @@ enum netdev_priv_flags { * @qdisc: Root qdisc from userspace point of view * @tx_queue_len: Max frames per queue allowed * @tx_global_lock: XXX: need comments on this one + * @xdp_bulkq: XDP device bulk queue + * @xps_cpus_map: all CPUs map for XPS device + * @xps_rxqs_map: all RXQs map for XPS device * * @xps_maps: XXX: need comments on this one * @miniq_egress: clsact qdisc specific data for * egress processing + * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers @@ -3548,7 +3562,7 @@ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, } /** - * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p + * netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p * @n: CPU/Rx queue index * @src1p: the first CPUs/Rx queues mask pointer * @src2p: the second CPUs/Rx queues mask pointer -- cgit v1.2.3 From 7151affeef8d527f50b4b68a871fd28bd660023f Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sat, 15 Feb 2020 10:50:21 +0000 Subject: net: export netdev_next_lower_dev_rcu() netdev_next_lower_dev_rcu() will be used to implement a function, which is to walk all lower interfaces. There are already functions that they walk their lower interface. (netdev_walk_all_lower_dev_rcu, netdev_walk_all_lower_dev()). But, there would be cases that couldn't be covered by given netdev_walk_all_lower_dev_{rcu}() function. So, some modules would want to implement own function, which is to walk all lower interfaces. In the next patch, netdev_next_lower_dev_rcu() will be used. In addition, this patch removes two unused prototypes in netdevice.h. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9f1f633235f6..6c3f7032e8d9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +#define MAX_NEST_DEV 8 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -4389,11 +4391,8 @@ void *netdev_lower_get_next(struct net_device *dev, ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) -struct net_device *netdev_all_lower_get_next(struct net_device *dev, +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_lower_get_next_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), -- cgit v1.2.3 From d2f273f0a9205257b91af1d3d461ee29688c2f24 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 15 Feb 2020 15:34:07 -0800 Subject: skbuff.h: fix all kernel-doc warnings Fix all kernel-doc warnings in . Fixes these warnings: ../include/linux/skbuff.h:890: warning: Function parameter or member 'list' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'dev_scratch' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'ip_defrag_offset' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'skb_mstamp_ns' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member '__cloned_offset' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'head_frag' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member '__pkt_type_offset' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'encapsulation' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'encap_hdr_csum' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'csum_valid' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member '__pkt_vlan_present_offset' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'vlan_present' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'csum_complete_sw' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'csum_level' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'inner_protocol_type' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'remcsum_offload' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'sender_cpu' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'reserved_tailroom' not described in 'sk_buff' ../include/linux/skbuff.h:890: warning: Function parameter or member 'inner_ipproto' not described in 'sk_buff' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/skbuff.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ca8806b69388..5b50278c4bc8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -611,9 +611,15 @@ typedef unsigned char *sk_buff_data_t; * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left + * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point + * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp + * @list: queue head * @sk: Socket we are owned by + * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in + * fragmentation management * @dev: Device we arrived on/are leaving by + * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @sp: the security path, used for xfrm @@ -632,6 +638,9 @@ typedef unsigned char *sk_buff_data_t; * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @inner_protocol_type: whether the inner protocol is + * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO + * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device @@ -650,6 +659,8 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices + * @head_frag: skb was allocated from page fragments, + * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) @@ -660,15 +671,28 @@ typedef unsigned char *sk_buff_data_t; * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS + * @encapsulation: indicates the inner headers in the skbuff are valid + * @encap_hdr_csum: software checksum is needed + * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL + * @csum_complete_sw: checksum was completed by software + * @csum_level: indicates the number of consecutive checksums found in + * the packet minus one that have been verified as + * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from + * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking * @mark: Generic packet mark + * @reserved_tailroom: (aka @mark) number of bytes of free space available + * at the tail of an sk_buff + * @vlan_present: VLAN tag is present * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) + * @inner_ipproto: (aka @inner_protocol) stores ipproto when + * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) @@ -750,7 +774,9 @@ struct sk_buff { #endif #define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) + /* private: */ __u8 __cloned_offset[0]; + /* public: */ __u8 cloned:1, nohdr:1, fclone:2, @@ -775,7 +801,9 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) + /* private: */ __u8 __pkt_type_offset[0]; + /* public: */ __u8 pkt_type:3; __u8 ignore_df:1; __u8 nf_trace:1; @@ -798,7 +826,9 @@ struct sk_buff { #define PKT_VLAN_PRESENT_BIT 0 #endif #define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) + /* private: */ __u8 __pkt_vlan_present_offset[0]; + /* public: */ __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; -- cgit v1.2.3 From 6a757c07e51f80ac34325fcd558490d2d1439e1b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 3 Feb 2020 17:37:07 +0100 Subject: netfilter: conntrack: allow insertion of clashing entries This patch further relaxes the need to drop an skb due to a clash with an existing conntrack entry. Current clash resolution handles the case where the clash occurs between two identical entries (distinct nf_conn objects with same tuples), i.e.: Original Reply existing: 10.2.3.4:42 -> 10.8.8.8:53 10.2.3.4:42 <- 10.0.0.6:5353 clashing: 10.2.3.4:42 -> 10.8.8.8:53 10.2.3.4:42 <- 10.0.0.6:5353 ... existing handling will discard the unconfirmed clashing entry and makes skb->_nfct point to the existing one. The skb can then be processed normally just as if the clash would not have existed in the first place. For other clashes, the skb needs to be dropped. This frequently happens with DNS resolvers that send A and AAAA queries back-to-back when NAT rules are present that cause packets to get different DNAT transformations applied, for example: -m statistics --mode random ... -j DNAT --dnat-to 10.0.0.6:5353 -m statistics --mode random ... -j DNAT --dnat-to 10.0.0.7:5353 In this case the A or AAAA query is dropped which incurs a costly delay during name resolution. This patch also allows this collision type: Original Reply existing: 10.2.3.4:42 -> 10.8.8.8:53 10.2.3.4:42 <- 10.0.0.6:5353 clashing: 10.2.3.4:42 -> 10.8.8.8:53 10.2.3.4:42 <- 10.0.0.7:5353 In this case, clash is in original direction -- the reply direction is still unique. The change makes it so that when the 2nd colliding packet is received, the clashing conntrack is tagged with new IPS_NAT_CLASH_BIT, gets a fixed 1 second timeout and is inserted in the reply direction only. The entry is hidden from 'conntrack -L', it will time out quickly and it can be early dropped because it will never progress to the ASSURED state. To avoid special-casing the delete code path to special case the ORIGINAL hlist_nulls node, a new helper, "hlist_nulls_add_fake", is added so hlist_nulls_del() will work. Example: CPU A: CPU B: 1. 10.2.3.4:42 -> 10.8.8.8:53 (A) 2. 10.2.3.4:42 -> 10.8.8.8:53 (AAAA) 3. Apply DNAT, reply changed to 10.0.0.6 4. 10.2.3.4:42 -> 10.8.8.8:53 (AAAA) 5. Apply DNAT, reply changed to 10.0.0.7 6. confirm/commit to conntrack table, no collisions 7. commit clashing entry Reply comes in: 10.2.3.4:42 <- 10.0.0.6:5353 (A) -> Finds a conntrack, DNAT is reversed & packet forwarded to 10.2.3.4:42 10.2.3.4:42 <- 10.0.0.7:5353 (AAAA) -> Finds a conntrack, DNAT is reversed & packet forwarded to 10.2.3.4:42 The conntrack entry is deleted from table, as it has the NAT_CLASH bit set. In case of a retransmit from ORIGINAL dir, all further packets will get the DNAT transformation to 10.0.0.6. I tried to come up with other solutions but they all have worse problems. Alternatives considered were: 1. Confirm ct entries at allocation time, not in postrouting. a. will cause uneccesarry work when the skb that creates the conntrack is dropped by ruleset. b. in case nat is applied, ct entry would need to be moved in the table, which requires another spinlock pair to be taken. c. breaks the 'unconfirmed entry is private to cpu' assumption: we would need to guard all nfct->ext allocation requests with ct->lock spinlock. 2. Make the unconfirmed list a hash table instead of a pcpu list. Shares drawback c) of the first alternative. 3. Document this is expected and force users to rearrange their ruleset (e.g. by using "-m cluster" instead of "-m statistics"). nft has the 'jhash' expression which can be used instead of 'numgen'. Major drawback: doesn't fix what I consider a bug, not very realistic and I believe its reasonable to have the existing rulesets to 'just work'. 4. Document this is expected and force users to steer problematic packets to the same CPU -- this would serialize the "allocate new conntrack entry/nat table evaluation/perform nat/confirm entry", so no race can occur. Similar drawback to 3. Another advantage of this patch compared to 1) and 2) is that there are no changes to the hot path; things are handled in the udp tracker and the clash resolution path. Cc: rcu@vger.kernel.org Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Jozsef Kadlecsik Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/rculist_nulls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index e5b752027a03..9670b54b484a 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -145,6 +145,13 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, } } +/* after that hlist_nulls_del will work */ +static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) +{ + n->pprev = &n->next; + n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. -- cgit v1.2.3 From d970a325561da5e611596cbb06475db3755ce823 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 13 Feb 2020 18:22:55 +0100 Subject: KVM: x86: fix missing prototypes Reported with "make W=1" due to -Wmissing-prototypes. Reported-by: Qian Cai Reviewed-by: Miaohe Lin Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e89eb67356cb..7944ad6ac10b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -889,6 +889,8 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); +int kvm_arch_post_init_vm(struct kvm *kvm); +void kvm_arch_pre_destroy_vm(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* -- cgit v1.2.3 From 13a7e459a41a56d788ab33d825c6205379bbb711 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Tue, 14 Jan 2020 09:27:27 +0200 Subject: net/mlx5: DR, Handle reformat capability over sw-steering tables On flow table creation, send the relevant flags according to what the FW currently supports. When FW doesn't support reformat option over SW-steering managed table, the driver shouldn't pass this. Fixes: 988fd6b32d07 ("net/mlx5: DR, Pass table flags at creation to lower layer") Signed-off-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ff8c9d527bb4..bfdf41537cf1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -688,7 +688,10 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 nic_rx_multi_path_tirs[0x1]; u8 nic_rx_multi_path_tirs_fts[0x1]; u8 allow_sniffer_and_nic_rx_shared_tir[0x1]; - u8 reserved_at_3[0x1d]; + u8 reserved_at_3[0x4]; + u8 sw_owner_reformat_supported[0x1]; + u8 reserved_at_8[0x18]; + u8 encap_general_header[0x1]; u8 reserved_at_21[0xa]; u8 log_max_packet_reformat_context[0x5]; -- cgit v1.2.3 From 85c46b78da58398be1c5166f55063c0512decd39 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 20 Feb 2020 21:18:42 +0900 Subject: bootconfig: Add bootconfig magic word for indicating bootconfig explicitly Add bootconfig magic word to the end of bootconfig on initrd image for indicating explicitly the bootconfig is there. Also tools/bootconfig treats wrong size or wrong checksum or parse error as an error, because if there is a bootconfig magic word, there must be a bootconfig. The bootconfig magic word is "#BOOTCONFIG\n", 12 bytes word. Thus the block image of the initrd file with bootconfig is as follows. [Initrd][bootconfig][size][csum][#BOOTCONFIG\n] Link: http://lkml.kernel.org/r/158220112263.26565.3944814205960612841.stgit@devnote2 Suggested-by: Steven Rostedt Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 7e18c939663e..d11e183fcb54 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,9 @@ #include #include +#define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" +#define BOOTCONFIG_MAGIC_LEN 12 + /* XBC tree node */ struct xbc_node { u16 next; -- cgit v1.2.3 From 2546287c5fb363a0165933ae2181c92f03e701d0 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Fri, 21 Feb 2020 10:07:25 +0800 Subject: genirq/irqdomain: Make sure all irq domain flags are distinct This was noticed when printing debugfs for MSIs on my ARM64 server. The new dstate IRQD_MSI_NOMASK_QUIRK came out surprisingly while it should only be the x86 stuff for the time being... The new MSI quirk flag uses the same bit as IRQ_DOMAIN_NAME_ALLOCATED which is oddly defined as bit 6 for no good reason. Switch it to the non used bit 1. Fixes: 6f1a4891a592 ("x86/apic/msi: Plug non-maskable MSI affinity race") Signed-off-by: Zenghui Yu Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200221020725.2038-1-yuzenghui@huawei.com --- include/linux/irqdomain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b2d47571ab67..8d062e86d954 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -192,7 +192,7 @@ enum { IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), /* Irq domain name was allocated in __irq_domain_add() */ - IRQ_DOMAIN_NAME_ALLOCATED = (1 << 6), + IRQ_DOMAIN_NAME_ALLOCATED = (1 << 1), /* Irq domain is an IPI domain with virq per cpu */ IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2), -- cgit v1.2.3 From 595abbaff5db121428247a2e6ab368734472e101 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 20 Feb 2020 20:03:50 -0800 Subject: y2038: remove ktime to/from timespec/timeval conversion A couple of helpers are now obsolete and can be removed, so drivers can no longer start using them and instead use y2038-safe interfaces. Link: http://lkml.kernel.org/r/20200110154232.4104492-2-arnd@arndb.de Signed-off-by: Arnd Bergmann Acked-by: Thomas Gleixner Cc: Deepa Dinamani Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ktime.h | 37 ------------------------------------- 1 file changed, 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index b2bb44f87f5a..d1fb05135665 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -66,33 +66,15 @@ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) */ #define ktime_sub_ns(kt, nsval) ((kt) - (nsval)) -/* convert a timespec to ktime_t format: */ -static inline ktime_t timespec_to_ktime(struct timespec ts) -{ - return ktime_set(ts.tv_sec, ts.tv_nsec); -} - /* convert a timespec64 to ktime_t format: */ static inline ktime_t timespec64_to_ktime(struct timespec64 ts) { return ktime_set(ts.tv_sec, ts.tv_nsec); } -/* convert a timeval to ktime_t format: */ -static inline ktime_t timeval_to_ktime(struct timeval tv) -{ - return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); -} - -/* Map the ktime_t to timespec conversion to ns_to_timespec function */ -#define ktime_to_timespec(kt) ns_to_timespec((kt)) - /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec64(kt) ns_to_timespec64((kt)) -/* Map the ktime_t to timeval conversion to ns_to_timeval function */ -#define ktime_to_timeval(kt) ns_to_timeval((kt)) - /* Convert ktime_t to nanoseconds */ static inline s64 ktime_to_ns(const ktime_t kt) { @@ -215,25 +197,6 @@ static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); -/** - * ktime_to_timespec_cond - convert a ktime_t variable to timespec - * format only if the variable contains data - * @kt: the ktime_t variable to convert - * @ts: the timespec variable to store the result in - * - * Return: %true if there was a successful conversion, %false if kt was 0. - */ -static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, - struct timespec *ts) -{ - if (kt) { - *ts = ktime_to_timespec(kt); - return true; - } else { - return false; - } -} - /** * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 * format only if the variable contains data -- cgit v1.2.3 From 412c53a680a97cb1ae2c0ab60230e193bee86387 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 20 Feb 2020 20:03:54 -0800 Subject: y2038: remove unused time32 interfaces No users remain, so kill these off before we grow new ones. Link: http://lkml.kernel.org/r/20200110154232.4104492-3-arnd@arndb.de Signed-off-by: Arnd Bergmann Acked-by: Thomas Gleixner Cc: Deepa Dinamani Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 29 -------- include/linux/time32.h | 154 +----------------------------------------- include/linux/timekeeping32.h | 32 --------- include/linux/types.h | 5 -- 4 files changed, 1 insertion(+), 219 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 11083d84eb23..df2475be134a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -248,15 +248,6 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; -/* - * These functions operate on 32- or 64-bit specs depending on - * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments. - */ -extern int compat_get_timespec(struct timespec *, const void __user *); -extern int compat_put_timespec(const struct timespec *, void __user *); -extern int compat_get_timeval(struct timeval *, const void __user *); -extern int compat_put_timeval(const struct timeval *, void __user *); - struct compat_iovec { compat_uptr_t iov_base; compat_size_t iov_len; @@ -416,26 +407,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginf int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -static inline int old_timeval32_compare(struct old_timeval32 *lhs, - struct old_timeval32 *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_usec - rhs->tv_usec; -} - -static inline int old_timespec32_compare(struct old_timespec32 *lhs, - struct old_timespec32 *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_nsec - rhs->tv_nsec; -} - extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); /* diff --git a/include/linux/time32.h b/include/linux/time32.h index cad4c3186002..cf9320cd2d0b 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -12,8 +12,6 @@ #include #include -#define TIME_T_MAX (__kernel_old_time_t)((1UL << ((sizeof(__kernel_old_time_t) << 3) - 1)) - 1) - typedef s32 old_time32_t; struct old_timespec32 { @@ -73,162 +71,12 @@ struct __kernel_timex; int get_old_timex32(struct __kernel_timex *, const struct old_timex32 __user *); int put_old_timex32(struct old_timex32 __user *, const struct __kernel_timex *); -#if __BITS_PER_LONG == 64 - -/* timespec64 is defined as timespec here */ -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - return *(const struct timespec *)&ts64; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - return *(const struct timespec64 *)&ts; -} - -#else -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - struct timespec ret; - - ret.tv_sec = (time_t)ts64.tv_sec; - ret.tv_nsec = ts64.tv_nsec; - return ret; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - struct timespec64 ret; - - ret.tv_sec = ts.tv_sec; - ret.tv_nsec = ts.tv_nsec; - return ret; -} -#endif - -static inline int timespec_equal(const struct timespec *a, - const struct timespec *b) -{ - return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); -} - -/* - * lhs < rhs: return <0 - * lhs == rhs: return 0 - * lhs > rhs: return >0 - */ -static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_nsec - rhs->tv_nsec; -} - -/* - * Returns true if the timespec is norm, false if denorm: - */ -static inline bool timespec_valid(const struct timespec *ts) -{ - /* Dates before 1970 are bogus */ - if (ts->tv_sec < 0) - return false; - /* Can't have more nanoseconds then a second */ - if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) - return false; - return true; -} - -/** - * timespec_to_ns - Convert timespec to nanoseconds - * @ts: pointer to the timespec variable to be converted - * - * Returns the scalar nanosecond representation of the timespec - * parameter. - */ -static inline s64 timespec_to_ns(const struct timespec *ts) -{ - return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; -} - /** - * ns_to_timespec - Convert nanoseconds to timespec - * @nsec: the nanoseconds value to be converted - * - * Returns the timespec representation of the nsec parameter. - */ -extern struct timespec ns_to_timespec(const s64 nsec); - -/** - * timespec_add_ns - Adds nanoseconds to a timespec - * @a: pointer to timespec to be incremented - * @ns: unsigned nanoseconds value to be added - * - * This must always be inlined because its used from the x86-64 vdso, - * which cannot call other kernel functions. - */ -static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) -{ - a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); - a->tv_nsec = ns; -} - -static inline unsigned long mktime(const unsigned int year, - const unsigned int mon, const unsigned int day, - const unsigned int hour, const unsigned int min, - const unsigned int sec) -{ - return mktime64(year, mon, day, hour, min, sec); -} - -static inline bool timeval_valid(const struct timeval *tv) -{ - /* Dates before 1970 are bogus */ - if (tv->tv_sec < 0) - return false; - - /* Can't have more microseconds then a second */ - if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) - return false; - - return true; -} - -/** - * timeval_to_ns - Convert timeval to nanoseconds - * @ts: pointer to the timeval variable to be converted - * - * Returns the scalar nanosecond representation of the timeval - * parameter. - */ -static inline s64 timeval_to_ns(const struct timeval *tv) -{ - return ((s64) tv->tv_sec * NSEC_PER_SEC) + - tv->tv_usec * NSEC_PER_USEC; -} - -/** - * ns_to_timeval - Convert nanoseconds to timeval + * ns_to_kernel_old_timeval - Convert nanoseconds to timeval * @nsec: the nanoseconds value to be converted * * Returns the timeval representation of the nsec parameter. */ -extern struct timeval ns_to_timeval(const s64 nsec); extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); -/* - * Old names for the 32-bit time_t interfaces, these will be removed - * when everything uses the new names. - */ -#define compat_time_t old_time32_t -#define compat_timeval old_timeval32 -#define compat_timespec old_timespec32 -#define compat_itimerspec old_itimerspec32 -#define ns_to_compat_timeval ns_to_old_timeval32 -#define get_compat_itimerspec64 get_old_itimerspec32 -#define put_compat_itimerspec64 put_old_itimerspec32 -#define compat_get_timespec64 get_old_timespec32 -#define compat_put_timespec64 put_old_timespec32 - #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index cc59cc9e0e84..266017fc9ee9 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -11,36 +11,4 @@ static inline unsigned long get_seconds(void) return ktime_get_real_seconds(); } -static inline void getnstimeofday(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_real_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void ktime_get_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void getrawmonotonic(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_raw_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void getboottime(struct timespec *ts) -{ - struct timespec64 ts64; - - getboottime64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - #endif diff --git a/include/linux/types.h b/include/linux/types.h index eb870ad42919..d3021c879179 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -65,11 +65,6 @@ typedef __kernel_ssize_t ssize_t; typedef __kernel_ptrdiff_t ptrdiff_t; #endif -#ifndef _TIME_T -#define _TIME_T -typedef __kernel_old_time_t time_t; -#endif - #ifndef _CLOCK_T #define _CLOCK_T typedef __kernel_clock_t clock_t; -- cgit v1.2.3 From f66ee0410b1c3481ee75e5db9b34547b4d582465 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 11 Feb 2020 23:20:43 +0100 Subject: netfilter: ipset: Fix "INFO: rcu detected stall in hash_xxx" reports In the case of huge hash:* types of sets, due to the single spinlock of a set the processing of the whole set under spinlock protection could take too long. There were four places where the whole hash table of the set was processed from bucket to bucket under holding the spinlock: - During resizing a set, the original set was locked to exclude kernel side add/del element operations (userspace add/del is excluded by the nfnetlink mutex). The original set is actually just read during the resize, so the spinlocking is replaced with rcu locking of regions. However, thus there can be parallel kernel side add/del of entries. In order not to loose those operations a backlog is added and replayed after the successful resize. - Garbage collection of timed out entries was also protected by the spinlock. In order not to lock too long, region locking is introduced and a single region is processed in one gc go. Also, the simple timer based gc running is replaced with a workqueue based solution. The internal book-keeping (number of elements, size of extensions) is moved to region level due to the region locking. - Adding elements: when the max number of the elements is reached, the gc was called to evict the timed out entries. The new approach is that the gc is called just for the matching region, assuming that if the region (proportionally) seems to be full, then the whole set does. We could scan the other regions to check every entry under rcu locking, but for huge sets it'd mean a slowdown at adding elements. - Listing the set header data: when the set was defined with timeout support, the garbage collector was called to clean up timed out entries to get the correct element numbers and set size values. Now the set is scanned to check non-timed out entries, without actually calling the gc for the whole set. Thanks to Florian Westphal for helping me to solve the SOFTIRQ-safe -> SOFTIRQ-unsafe lock order issues during working on the patch. Reported-by: syzbot+4b0e9d4ff3cf117837e5@syzkaller.appspotmail.com Reported-by: syzbot+c27b8d5010f45c666ed1@syzkaller.appspotmail.com Reported-by: syzbot+68a806795ac89df3aa1c@syzkaller.appspotmail.com Fixes: 23c42a403a9c ("netfilter: ipset: Introduction of new commands and protocol version 7") Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 908d38dbcb91..5448c8b443db 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -121,6 +121,7 @@ struct ip_set_ext { u32 timeout; u8 packets_op; u8 bytes_op; + bool target; }; struct ip_set; @@ -187,6 +188,14 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Region-locking is used */ + bool region_lock; +}; + +struct ip_set_region { + spinlock_t lock; /* Region lock */ + size_t ext_size; /* Size of the dynamic extensions */ + u32 elements; /* Number of elements vs timeout */ }; /* The core set type structure */ @@ -501,7 +510,7 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, } #define IP_SET_INIT_KEXT(skb, opt, set) \ - { .bytes = (skb)->len, .packets = 1, \ + { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } #define IP_SET_INIT_UEXT(set) \ -- cgit v1.2.3 From c780e86dd48ef6467a1146cf7d0fe1e05a635039 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 6 Feb 2020 15:28:12 +0100 Subject: blktrace: Protect q->blk_trace with RCU KASAN is reporting that __blk_add_trace() has a use-after-free issue when accessing q->blk_trace. Indeed the switching of block tracing (and thus eventual freeing of q->blk_trace) is completely unsynchronized with the currently running tracing and thus it can happen that the blk_trace structure is being freed just while __blk_add_trace() works on it. Protect accesses to q->blk_trace by RCU during tracing and make sure we wait for the end of RCU grace period when shutting down tracing. Luckily that is rare enough event that we can afford that. Note that postponing the freeing of blk_trace to an RCU callback should better be avoided as it could have unexpected user visible side-effects as debugfs files would be still existing for a short while block tracing has been shut down. Link: https://bugzilla.kernel.org/show_bug.cgi?id=205711 CC: stable@vger.kernel.org Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ming Lei Tested-by: Ming Lei Reviewed-by: Bart Van Assche Reported-by: Tristan Madani Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- include/linux/blktrace_api.h | 18 +++++++++++++----- 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 053ea4b51988..10455b2bbbb4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -524,7 +524,7 @@ struct request_queue { unsigned int sg_reserved_size; int node; #ifdef CONFIG_BLK_DEV_IO_TRACE - struct blk_trace *blk_trace; + struct blk_trace __rcu *blk_trace; struct mutex blk_trace_mutex; #endif /* diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7bb2d8de9f30..3b6ff5902edc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -51,9 +51,13 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f **/ #define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ - struct blk_trace *bt = (q)->blk_trace; \ + struct blk_trace *bt; \ + \ + rcu_read_lock(); \ + bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) @@ -61,10 +65,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f static inline bool blk_trace_note_message_enabled(struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; - if (likely(!bt)) - return false; - return bt->act_mask & BLK_TC_NOTIFY; + struct blk_trace *bt; + bool ret; + + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + ret = bt && (bt->act_mask & BLK_TC_NOTIFY); + rcu_read_unlock(); + return ret; } extern void blk_add_driver_data(struct request_queue *q, struct request *rq, -- cgit v1.2.3 From a8e41f6033a0c5633d55d6e35993c9e2005d872f Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 25 Feb 2020 18:05:35 +0800 Subject: icmp: allow icmpv6_ndo_send to work with CONFIG_IPV6=n The icmpv6_send function has long had a static inline implementation with an empty body for CONFIG_IPV6=n, so that code calling it doesn't need to be ifdef'd. The new icmpv6_ndo_send function, which is intended for drivers as a drop-in replacement with an identical function signature, should follow the same pattern. Without this patch, drivers that used to work with CONFIG_IPV6=n now result in a linker error. Cc: Chen Zhou Reported-by: Hulk Robot Fixes: 0b41713b6066 ("icmp: introduce helper for nat'd source address in network device context") Signed-off-by: Jason A. Donenfeld Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 93338fd54af8..33d379602314 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -22,19 +22,23 @@ extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); +#if IS_ENABLED(CONFIG_NF_NAT) +void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); +#else +#define icmpv6_ndo_send icmpv6_send +#endif + #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { - } -#endif -#if IS_ENABLED(CONFIG_NF_NAT) -void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); -#else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb, + u8 type, u8 code, __u32 info) +{ +} #endif extern int icmpv6_init(void); -- cgit v1.2.3 From fcd07f9adc7dacc2532695cf9dd2284d49e716ff Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 28 Feb 2020 09:49:41 +0100 Subject: KVM: let declaration of kvm_get_running_vcpus match implementation Sparse notices that declaration and implementation do not match: arch/s390/kvm/../../../virt/kvm/kvm_main.c:4435:17: warning: incorrect type in return expression (different address spaces) arch/s390/kvm/../../../virt/kvm/kvm_main.c:4435:17: expected struct kvm_vcpu [noderef] ** arch/s390/kvm/../../../virt/kvm/kvm_main.c:4435:17: got struct kvm_vcpu *[noderef] * Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7944ad6ac10b..bcb9b2ac0791 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1344,7 +1344,7 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ struct kvm_vcpu *kvm_get_running_vcpu(void); -struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); -- cgit v1.2.3 From 249bc9744e165abe74ae326f43e9d70bad54c3b7 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 1 Mar 2020 21:36:09 +0100 Subject: net: phy: avoid clearing PHY interrupts twice in irq handler On all PHY drivers that implement did_interrupt() reading the interrupt status bits clears them. This means we may loose an interrupt that is triggered between calling did_interrupt() and phy_clear_interrupt(). As part of the fix make it a requirement that did_interrupt() clears the interrupt. The Fixes tag refers to the first commit where the patch applies cleanly. Fixes: 49644e68f472 ("net: phy: add callback for custom interrupt handler to struct phy_driver") Reported-by: Michael Walle Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index c570e162e05e..22f5e763e894 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -557,6 +557,7 @@ struct phy_driver { /* * 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); -- cgit v1.2.3 From e959e5405f34aa92d71d0dd162b969c21742061d Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Mon, 2 Mar 2020 14:24:08 +0100 Subject: block: Remove used kblockd_schedule_work_on() Commit ee63cfa7fc19 ("block: add kblockd_schedule_work_on()") introduced the helper in 2016. Remove it because since then no caller was added. Cc: Jens Axboe Signed-off-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 10455b2bbbb4..f629d40c645c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1494,7 +1494,6 @@ static inline void put_dev_sector(Sector p) } int kblockd_schedule_work(struct work_struct *work); -int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ -- cgit v1.2.3 From 02d715b4a8182f4887d82df82a7b83aced647760 Mon Sep 17 00:00:00 2001 From: Amol Grover Date: Sun, 23 Feb 2020 22:25:39 +0530 Subject: iommu/vt-d: Fix RCU list debugging warnings dmar_drhd_units is traversed using list_for_each_entry_rcu() outside of an RCU read side critical section but under the protection of dmar_global_lock. Hence add corresponding lockdep expression to silence the following false-positive warnings: [ 1.603975] ============================= [ 1.603976] WARNING: suspicious RCU usage [ 1.603977] 5.5.4-stable #17 Not tainted [ 1.603978] ----------------------------- [ 1.603980] drivers/iommu/intel-iommu.c:4769 RCU-list traversed in non-reader section!! [ 1.603869] ============================= [ 1.603870] WARNING: suspicious RCU usage [ 1.603872] 5.5.4-stable #17 Not tainted [ 1.603874] ----------------------------- [ 1.603875] drivers/iommu/dmar.c:293 RCU-list traversed in non-reader section!! Tested-by: Madhuparna Bhowmik Signed-off-by: Amol Grover Cc: stable@vger.kernel.org Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index f64ca27dc210..712be8bc6a7c 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -69,8 +69,9 @@ struct dmar_pci_notify_info { extern struct rw_semaphore dmar_global_lock; extern struct list_head dmar_drhd_units; -#define for_each_drhd_unit(drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) +#define for_each_drhd_unit(drhd) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) #define for_each_active_drhd_unit(drhd) \ list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ @@ -81,7 +82,8 @@ extern struct list_head dmar_drhd_units; if (i=drhd->iommu, drhd->ignored) {} else #define for_each_iommu(i, drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (i=drhd->iommu, 0) {} else static inline bool dmar_rcu_check(void) -- cgit v1.2.3 From ac338acf514e7b578fa9e3742ec2c292323b4c1a Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 21 Feb 2020 00:05:09 -0800 Subject: driver core: Add dev_has_sync_state() Add an API to check if a device has sync_state support in its driver or bus. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200221080510.197337-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 0cd7c647c16c..fa04dfd22bbc 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -798,6 +798,17 @@ static inline struct device_node *dev_of_node(struct device *dev) return dev->of_node; } +static inline bool dev_has_sync_state(struct device *dev) +{ + if (!dev) + return false; + if (dev->driver && dev->driver->sync_state) + return true; + if (dev->bus && dev->bus->sync_state) + return true; + return false; +} + /* * High level routines for use by the bus drivers */ -- cgit v1.2.3 From 8019ad13ef7f64be44d4f892af9c840179009254 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 4 Mar 2020 11:28:31 +0100 Subject: futex: Fix inode life-time issue As reported by Jann, ihold() does not in fact guarantee inode persistence. And instead of making it so, replace the usage of inode pointers with a per boot, machine wide, unique inode identifier. This sequence number is global, but shared (file backed) futexes are rare enough that this should not become a performance issue. Reported-by: Jann Horn Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) --- include/linux/fs.h | 1 + include/linux/futex.h | 17 ++++++++++------- 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3cd4fe6b845e..abedbffe2c9e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -698,6 +698,7 @@ struct inode { struct rcu_head i_rcu; }; atomic64_t i_version; + atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; diff --git a/include/linux/futex.h b/include/linux/futex.h index 5cc3fed27d4c..b70df27d7e85 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -31,23 +31,26 @@ struct task_struct; union futex_key { struct { + u64 i_seq; unsigned long pgoff; - struct inode *inode; - int offset; + unsigned int offset; } shared; struct { + union { + struct mm_struct *mm; + u64 __tmp; + }; unsigned long address; - struct mm_struct *mm; - int offset; + unsigned int offset; } private; struct { + u64 ptr; unsigned long word; - void *ptr; - int offset; + unsigned int offset; } both; }; -#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } +#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } } #ifdef CONFIG_FUTEX enum { -- cgit v1.2.3 From c87cbc1f007c4b46165f05ceca04e1973cda0b9c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 5 Mar 2020 22:28:42 -0800 Subject: mm, hotplug: fix page online with DEBUG_PAGEALLOC compiled but not enabled Commit cd02cf1aceea ("mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC") fixed memory hotplug with debug_pagealloc enabled, where onlining a page goes through page freeing, which removes the direct mapping. Some arches don't like when the page is not mapped in the first place, so generic_online_page() maps it first. This is somewhat wasteful, but better than special casing page freeing fast paths. The commit however missed that DEBUG_PAGEALLOC configured doesn't mean it's actually enabled. One has to test debug_pagealloc_enabled() since 031bc5743f15 ("mm/debug-pagealloc: make debug-pagealloc boottime configurable"), or alternatively debug_pagealloc_enabled_static() since 8e57f8acbbd1 ("mm, debug_pagealloc: don't rely on static keys too early"), but this is not done. As a result, a s390 kernel with DEBUG_PAGEALLOC configured but not enabled will crash: Unable to handle kernel pointer dereference in virtual kernel address space Failing address: 0000000000000000 TEID: 0000000000000483 Fault in home space mode while using kernel ASCE. AS:0000001ece13400b R2:000003fff7fd000b R3:000003fff7fcc007 S:000003fff7fd7000 P:000000000000013d Oops: 0004 ilc:2 [#1] SMP CPU: 1 PID: 26015 Comm: chmem Kdump: loaded Tainted: GX 5.3.18-5-default #1 SLE15-SP2 (unreleased) Krnl PSW : 0704e00180000000 0000001ecd281b9e (__kernel_map_pages+0x166/0x188) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3 Krnl GPRS: 0000000000000000 0000000000000800 0000400b00000000 0000000000000100 0000000000000001 0000000000000000 0000000000000002 0000000000000100 0000001ece139230 0000001ecdd98d40 0000400b00000100 0000000000000000 000003ffa17e4000 001fffe0114f7d08 0000001ecd4d93ea 001fffe0114f7b20 Krnl Code: 0000001ecd281b8e: ec17ffff00d8 ahik %r1,%r7,-1 0000001ecd281b94: ec111dbc0355 risbg %r1,%r1,29,188,3 >0000001ecd281b9e: 94fb5006 ni 6(%r5),251 0000001ecd281ba2: 41505008 la %r5,8(%r5) 0000001ecd281ba6: ec51fffc6064 cgrj %r5,%r1,6,1ecd281b9e 0000001ecd281bac: 1a07 ar %r0,%r7 0000001ecd281bae: ec03ff584076 crj %r0,%r3,4,1ecd281a5e Call Trace: [<0000001ecd281b9e>] __kernel_map_pages+0x166/0x188 [<0000001ecd4d9516>] online_pages_range+0xf6/0x128 [<0000001ecd2a8186>] walk_system_ram_range+0x7e/0xd8 [<0000001ecda28aae>] online_pages+0x2fe/0x3f0 [<0000001ecd7d02a6>] memory_subsys_online+0x8e/0xc0 [<0000001ecd7add42>] device_online+0x5a/0xc8 [<0000001ecd7d0430>] state_store+0x88/0x118 [<0000001ecd5b9f62>] kernfs_fop_write+0xc2/0x200 [<0000001ecd5064b6>] vfs_write+0x176/0x1e0 [<0000001ecd50676a>] ksys_write+0xa2/0x100 [<0000001ecda315d4>] system_call+0xd8/0x2c8 Fix this by checking debug_pagealloc_enabled_static() before calling kernel_map_pages(). Backports for kernel before 5.5 should use debug_pagealloc_enabled() instead. Also add comments. Fixes: cd02cf1aceea ("mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC") Reported-by: Gerald Schaefer Signed-off-by: Andrew Morton Signed-off-by: Vlastimil Babka Reviewed-by: David Hildenbrand Cc: Cc: Joonsoo Kim Cc: Qian Cai Link: http://lkml.kernel.org/r/20200224094651.18257-1-vbabka@suse.cz Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 52269e56c514..c54fb96cb1e6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2715,6 +2715,10 @@ static inline bool debug_pagealloc_enabled_static(void) #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) extern void __kernel_map_pages(struct page *page, int numpages, int enable); +/* + * When called in DEBUG_PAGEALLOC context, the call should most likely be + * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static() + */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) { -- cgit v1.2.3 From aeaa925bff844d225f259215a250d2811e436499 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Thu, 5 Mar 2020 17:05:16 +0100 Subject: rhashtable: Document the right function parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rhashtable_lookup_get_insert_key doesn't have a parameter `data`. It does have a parameter `key`, however. Signed-off-by: Jonathan Neuschäfer Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index beb9a9da1699..70ebef866cc8 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -972,9 +972,9 @@ static inline int rhashtable_lookup_insert_key( /** * rhashtable_lookup_get_insert_key - lookup and insert object into hash table * @ht: hash table + * @key: key * @obj: pointer to hash head inside object * @params: hash table parameters - * @data: pointer to element data already in hashes * * Just like rhashtable_lookup_insert_key(), but this function returns the * object if it exists, NULL if it does not and the insertion was successful, -- cgit v1.2.3 From 83f73c5bb7b9a9135173f0ba2b1aa00c06664ff9 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 5 Mar 2020 15:33:12 +0300 Subject: inet_diag: return classid for all socket types In commit 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") croup classid reporting was fixed. But this works only for TCP sockets because for other socket types icsk parameter can be NULL and classid code path is skipped. This change moves classid handling to inet_diag_msg_attrs_fill() function. Also inet_diag_msg_attrs_size() helper was added and addends in nlmsg_new() were reordered to save order from inet_sk_diag_fill(). Fixes: 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 39faaaf843e1..c91cf2dee12a 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -2,15 +2,10 @@ #ifndef _INET_DIAG_H_ #define _INET_DIAG_H_ 1 +#include #include -struct net; -struct sock; struct inet_hashinfo; -struct nlattr; -struct nlmsghdr; -struct sk_buff; -struct netlink_callback; struct inet_diag_handler { void (*dump)(struct sk_buff *skb, @@ -62,6 +57,17 @@ int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk); +static inline size_t inet_diag_msg_attrs_size(void) +{ + return nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ +#if IS_ENABLED(CONFIG_IPV6) + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(1) /* INET_DIAG_SKV6ONLY */ +#endif + + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4); /* INET_DIAG_CLASS_ID */ +} int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, struct user_namespace *user_ns, bool net_admin); -- cgit v1.2.3 From f5152416528c2295f35dd9c9bd4fb27c4032413d Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 5 Mar 2020 15:15:02 -0500 Subject: iommu/vt-d: Silence RCU-list debugging warnings Similar to the commit 02d715b4a818 ("iommu/vt-d: Fix RCU list debugging warnings"), there are several other places that call list_for_each_entry_rcu() outside of an RCU read side critical section but with dmar_global_lock held. Silence those false positives as well. drivers/iommu/intel-iommu.c:4288 RCU-list traversed in non-reader section!! 1 lock held by swapper/0/1: #0: ffffffff935892c8 (dmar_global_lock){+.+.}, at: intel_iommu_init+0x1ad/0xb97 drivers/iommu/dmar.c:366 RCU-list traversed in non-reader section!! 1 lock held by swapper/0/1: #0: ffffffff935892c8 (dmar_global_lock){+.+.}, at: intel_iommu_init+0x125/0xb97 drivers/iommu/intel-iommu.c:5057 RCU-list traversed in non-reader section!! 1 lock held by swapper/0/1: #0: ffffffffa71892c8 (dmar_global_lock){++++}, at: intel_iommu_init+0x61a/0xb13 Signed-off-by: Qian Cai Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 712be8bc6a7c..d7bf029df737 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -74,11 +74,13 @@ extern struct list_head dmar_drhd_units; dmar_rcu_check()) #define for_each_active_drhd_unit(drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (drhd->ignored) {} else #define for_each_active_iommu(i, drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (i=drhd->iommu, drhd->ignored) {} else #define for_each_iommu(i, drhd) \ -- cgit v1.2.3 From 1292e3efb149ee21d8d33d725eeed4e6b1ade963 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 10 Mar 2020 12:49:43 +0100 Subject: mmc: core: Allow host controllers to require R1B for CMD6 It has turned out that some host controllers can't use R1B for CMD6 and other commands that have R1B associated with them. Therefore invent a new host cap, MMC_CAP_NEED_RSP_BUSY to let them specify this. In __mmc_switch(), let's check the flag and use it to prevent R1B responses from being converted into R1. Note that, this also means that the host are on its own, when it comes to manage the busy timeout. Suggested-by: Sowjanya Komatineni Cc: Tested-by: Anders Roxell Tested-by: Sowjanya Komatineni Tested-by: Faiz Abbas Tested-By: Peter Geis Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index ba703384bea0..4c5eb3aa8e72 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -333,6 +333,7 @@ struct mmc_host { MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \ MMC_CAP_UHS_DDR50) #define MMC_CAP_SYNC_RUNTIME_PM (1 << 21) /* Synced runtime PM suspends. */ +#define MMC_CAP_NEED_RSP_BUSY (1 << 22) /* Commands with R1B can't use R1. */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ -- cgit v1.2.3 From e3a36eb6dfaeea8175c05d5915dcf0b939be6dab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Mar 2020 17:07:10 +0100 Subject: driver code: clarify and fix platform device DMA mask allocation This does three inter-related things to clarify the usage of the platform device dma_mask field. In the process, fix the bug introduced by cdfee5623290 ("driver core: initialize a default DMA mask for platform device") that caused Artem Tashkinov's laptop to not boot with newer Fedora kernels. This does: - First off, rename the field to "platform_dma_mask" to make it greppable. We have way too many different random fields called "dma_mask" in various data structures, where some of them are actual masks, and some of them are just pointers to the mask. And the structures all have pointers to each other, or embed each other inside themselves, and "pdev" sometimes means "platform device" and sometimes it means "PCI device". So to make it clear in the code when you actually use this new field, give it a unique name (it really should be something even more unique like "platform_device_dma_mask", since it's per platform device, not per platform, but that gets old really fast, and this is unique enough in context). To further clarify when the field gets used, initialize it when we actually start using it with the default value. - Then, use this field instead of the random one-off allocation in platform_device_register_full() that is now unnecessary since we now already have a perfectly fine allocation for it in the platform device structure. - The above then allows us to fix the actual bug, where the error path of platform_device_register_full() would unconditionally free the platform device DMA allocation with 'kfree()'. That kfree() was dont regardless of whether the allocation had been done earlier with the (now removed) kmalloc, or whether setup_pdev_dma_masks() had already been used and the dma_mask pointer pointed to the mask that was part of the platform device. It seems most people never triggered the error path, or only triggered it from a call chain that set an explicit pdevinfo->dma_mask value (and thus caused the unnecessary allocation that was "cleaned up" in the error path) before calling platform_device_register_full(). Robin Murphy points out that in Artem's case the wdat_wdt driver failed in platform_device_add(), and that was the one that had called platform_device_register_full() with pdevinfo.dma_mask = 0, and would have caused that kfree() of pdev.dma_mask corrupting the heap. A later unrelated kmalloc() then oopsed due to the heap corruption. Fixes: cdfee5623290 ("driver core: initialize a default DMA mask for platform device") Reported-bisected-and-tested-by: Artem S. Tashkinov Reviewed-by: Robin Murphy Cc: Greg Kroah-Hartman Signed-off-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/platform_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 276a03c24691..041bfa412aa0 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -24,7 +24,7 @@ struct platform_device { int id; bool id_auto; struct device dev; - u64 dma_mask; + u64 platform_dma_mask; u32 num_resources; struct resource *resource; -- cgit v1.2.3 From b53df2e7442c73a932fb74228147fb946e531585 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Fri, 21 Feb 2020 10:37:08 +0900 Subject: block: Fix partition support for host aware zoned block devices Commit b72053072c0b ("block: allow partitions on host aware zone devices") introduced the helper function disk_has_partitions() to check if a given disk has valid partitions. However, since this function result directly depends on the disk partition table length rather than the actual existence of valid partitions in the table, it returns true even after all partitions are removed from the disk. For host aware zoned block devices, this results in zone management support to be kept disabled even after removing all partitions. Fix this by changing disk_has_partitions() to walk through the partition table entries and return true if and only if a valid non-zero size partition is found. Fixes: b72053072c0b ("block: allow partitions on host aware zone devices") Cc: stable@vger.kernel.org # 5.5 Reviewed-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Shin'ichiro Kawasaki Signed-off-by: Jens Axboe --- include/linux/genhd.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fbe58538ad6..07dc91835b98 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -245,18 +245,6 @@ static inline bool disk_part_scan_enabled(struct gendisk *disk) !(disk->flags & GENHD_FL_NO_PART_SCAN); } -static inline bool disk_has_partitions(struct gendisk *disk) -{ - bool ret = false; - - rcu_read_lock(); - if (rcu_dereference(disk->part_tbl)->len > 1) - ret = true; - rcu_read_unlock(); - - return ret; -} - static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); @@ -298,6 +286,7 @@ extern void disk_part_iter_exit(struct disk_part_iter *piter); extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); +bool disk_has_partitions(struct gendisk *disk); /* * Macros to operate on percpu disk statistics: -- cgit v1.2.3 From 611d779af7cad2b87487ff58e4931a90c20b113c Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 12 Mar 2020 22:25:20 +0100 Subject: net: phy: fix MDIO bus PM PHY resuming So far we have the unfortunate situation that mdio_bus_phy_may_suspend() is called in suspend AND resume path, assuming that function result is the same. After the original change this is no longer the case, resulting in broken resume as reported by Geert. To fix this call mdio_bus_phy_may_suspend() in the suspend path only, and let the phy_device store the info whether it was suspended by MDIO bus PM. Fixes: 503ba7c69610 ("net: phy: Avoid multiple suspends") Reported-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 22f5e763e894..452e8ba8665f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -357,6 +357,7 @@ struct macsec_ops; * 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. * state: state of the PHY for management purposes @@ -396,6 +397,7 @@ struct phy_device { unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; + unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; -- cgit v1.2.3 From ba3b01d7a6f4ab9f8a0557044c9a7678f64ae070 Mon Sep 17 00:00:00 2001 From: Megha Dey Date: Mon, 9 Mar 2020 13:09:46 -0700 Subject: iommu/vt-d: Fix debugfs register reads Commit 6825d3ea6cde ("iommu/vt-d: Add debugfs support to show register contents") dumps the register contents for all IOMMU devices. Currently, a 64 bit read(dmar_readq) is done for all the IOMMU registers, even though some of the registers are 32 bits, which is incorrect. Use the correct read function variant (dmar_readl/dmar_readq) while reading the contents of 32/64 bit registers respectively. Signed-off-by: Megha Dey Link: https://lore.kernel.org/r/1583784587-26126-2-git-send-email-megha.dey@linux.intel.com Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4a16b39ae353..980234ae0312 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -123,6 +123,8 @@ #define dmar_readq(a) readq(a) #define dmar_writeq(a,v) writeq(v,a) +#define dmar_readl(a) readl(a) +#define dmar_writel(a, v) writel(v, a) #define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4) #define DMAR_VER_MINOR(v) ((v) & 0x0f) -- cgit v1.2.3 From f1388ec4a144f40348321a0915c5535d623e165c Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Sun, 15 Mar 2020 18:17:48 +0100 Subject: netlink: add nl_set_extack_cookie_u32() Similar to existing nl_set_extack_cookie_u64(), add new helper nl_set_extack_cookie_u32() which sets extack cookie to a u32 value. Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- include/linux/netlink.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 205fa7b1f07a..4090524c3462 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -119,6 +119,15 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, extack->cookie_len = sizeof(__cookie); } +static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, + u32 cookie) +{ + u32 __cookie = cookie; + + memcpy(extack->cookie, &__cookie, sizeof(__cookie)); + extack->cookie_len = sizeof(__cookie); +} + void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); -- cgit v1.2.3 From 8e7ae2518f5265f0ef09d561748098fde5a87ccd Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 13 Mar 2020 18:02:09 -0700 Subject: bpf: Sanitize the bpf_struct_ops tcp-cc name The bpf_struct_ops tcp-cc name should be sanitized in order to avoid problematic chars (e.g. whitespaces). This patch reuses the bpf_obj_name_cpy() for accepting the same set of characters in order to keep a consistent bpf programming experience. A "size" param is added. Also, the strlen is returned on success so that the caller (like the bpf_tcp_ca here) can error out on empty name. The existing callers of the bpf_obj_name_cpy() only need to change the testing statement to "if (err < 0)". For all these existing callers, the err will be overwritten later, so no extra change is needed for the new strlen return value. v3: - reverse xmas tree style v2: - Save the orig_src to avoid "end - size" (Andrii) Fixes: 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf") Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200314010209.1131542-1-kafai@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 49b1a70e12c8..212991f6f2a5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -160,6 +160,7 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); +int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; struct bpf_offloaded_map; -- cgit v1.2.3 From 4022e7af86be2dd62975dedb6b7ea551d108695e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 19 Mar 2020 19:23:18 -0600 Subject: io_uring: make sure openat/openat2 honor rlimit nofile Dmitry reports that a test case shows that io_uring isn't honoring a modified rlimit nofile setting. get_unused_fd_flags() checks the task signal->rlimi[] for the limits. As this isn't easily inheritable, provide a __get_unused_fd_flags() that takes the value instead. Then we can grab it when the request is prepared (from the original task), and pass that in when we do the async part part of the open. Reported-by: Dmitry Kadashev Tested-by: Dmitry Kadashev Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/linux/file.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index c6c7b24ea9f7..142d102f285e 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -85,6 +85,7 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); +extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); -- cgit v1.2.3 From 09952e3e7826119ddd4357c453d54bcc7ef25156 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 19 Mar 2020 20:16:56 -0600 Subject: io_uring: make sure accept honor rlimit nofile Just like commit 4022e7af86be, this fixes the fact that IORING_OP_ACCEPT ends up using get_unused_fd_flags(), which checks current->signal->rlim[] for limits. Add an extra argument to __sys_accept4_file() that allows us to pass in the proper nofile limit, and grab it at request prep time. Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/linux/socket.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 2d2313403101..15f3412d481e 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -401,7 +401,8 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len, int addr_len); extern int __sys_accept4_file(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags); + int __user *upeer_addrlen, int flags, + unsigned long nofile); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); -- cgit v1.2.3 From d72520ad004a8ce18a6ba6cde317f0081b27365a Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sat, 21 Mar 2020 18:22:17 -0700 Subject: page-flags: fix a crash at SetPageError(THP_SWAP) Commit bd4c82c22c36 ("mm, THP, swap: delay splitting THP after swapped out") supported writing THP to a swap device but forgot to upgrade an older commit df8c94d13c7e ("page-flags: define behavior of FS/IO-related flags on compound pages") which could trigger a crash during THP swapping out with DEBUG_VM_PGFLAGS=y, kernel BUG at include/linux/page-flags.h:317! page dumped because: VM_BUG_ON_PAGE(1 && PageCompound(page)) page:fffff3b2ec3a8000 refcount:512 mapcount:0 mapping:000000009eb0338c index:0x7f6e58200 head:fffff3b2ec3a8000 order:9 compound_mapcount:0 compound_pincount:0 anon flags: 0x45fffe0000d8454(uptodate|lru|workingset|owner_priv_1|writeback|head|reclaim|swapbacked) end_swap_bio_write() SetPageError(page) VM_BUG_ON_PAGE(1 && PageCompound(page)) bio_endio+0x297/0x560 dec_pending+0x218/0x430 [dm_mod] clone_endio+0xe4/0x2c0 [dm_mod] bio_endio+0x297/0x560 blk_update_request+0x201/0x920 scsi_end_request+0x6b/0x4b0 scsi_io_completion+0x509/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 __blk_mqnterrupt+0xf/0x20 Fix by checking PF_NO_TAIL in those places instead. Fixes: bd4c82c22c36 ("mm, THP, swap: delay splitting THP after swapped out") Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Acked-by: "Huang, Ying" Acked-by: Rafael Aquini Cc: Link: http://lkml.kernel.org/r/20200310235846.1319-1-cai@lca.pw Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1bf83c8fcaa7..77de28bfefb0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -311,7 +311,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) -PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND) +PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) __SETPAGEFLAG(Referenced, referenced, PF_HEAD) -- cgit v1.2.3 From 763802b53a427ed3cbd419dbba255c414fdd9e7c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Sat, 21 Mar 2020 18:22:41 -0700 Subject: x86/mm: split vmalloc_sync_all() Commit 3f8fd02b1bf1 ("mm/vmalloc: Sync unmappings in __purge_vmap_area_lazy()") introduced a call to vmalloc_sync_all() in the vunmap() code-path. While this change was necessary to maintain correctness on x86-32-pae kernels, it also adds additional cycles for architectures that don't need it. Specifically on x86-64 with CONFIG_VMAP_STACK=y some people reported severe performance regressions in micro-benchmarks because it now also calls the x86-64 implementation of vmalloc_sync_all() on vunmap(). But the vmalloc_sync_all() implementation on x86-64 is only needed for newly created mappings. To avoid the unnecessary work on x86-64 and to gain the performance back, split up vmalloc_sync_all() into two functions: * vmalloc_sync_mappings(), and * vmalloc_sync_unmappings() Most call-sites to vmalloc_sync_all() only care about new mappings being synchronized. The only exception is the new call-site added in the above mentioned commit. Shile Zhang directed us to a report of an 80% regression in reaim throughput. Fixes: 3f8fd02b1bf1 ("mm/vmalloc: Sync unmappings in __purge_vmap_area_lazy()") Reported-by: kernel test robot Reported-by: Shile Zhang Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Tested-by: Borislav Petkov Acked-by: Rafael J. Wysocki [GHES] Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Link: http://lkml.kernel.org/r/20191009124418.8286-1-joro@8bytes.org Link: https://lists.01.org/hyperkitty/list/lkp@lists.01.org/thread/4D3JPPHBNOSPFK2KEPC6KGKS6J25AIDB/ Link: http://lkml.kernel.org/r/20191113095530.228959-1-shile.zhang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ec3813236699..0507a162ccd0 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -141,8 +141,9 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -void vmalloc_sync_all(void); - +void vmalloc_sync_mappings(void); +void vmalloc_sync_unmappings(void); + /* * Lowlevel-APIs (not for driver use!) */ -- cgit v1.2.3 From 692b65c84f0bb0ca70c11e62c865cbaf7e8e3afd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 17 Mar 2020 15:54:22 +0100 Subject: i2c: fix a doc warning Don't let non-letters inside a literal block without escaping it, as the toolchain would mis-interpret it: ./include/linux/i2c.h:518: WARNING: Inline strong start-string without end-string. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index f834687989f7..f6b942150631 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -506,7 +506,7 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, * @smbus_xfer_atomic: same as @smbus_xfer. Yet, only using atomic context * so e.g. PMICs can be accessed very late before shutdown. Optional. * @functionality: Return the flags that this algorithm/adapter pair supports - * from the I2C_FUNC_* flags. + * from the ``I2C_FUNC_*`` flags. * @reg_slave: Register given client to I2C slave mode of this adapter * @unreg_slave: Unregister given client from I2C slave mode of this adapter * @@ -515,7 +515,7 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, * be addressed using the same bus algorithms - i.e. bit-banging or the PCF8584 * to name two of the most common. * - * The return codes from the @master_xfer{_atomic} fields should indicate the + * The return codes from the ``master_xfer{_atomic}`` fields should indicate the * type of error code that occurred during the transfer, as documented in the * Kernel Documentation file Documentation/i2c/fault-codes.rst. */ -- cgit v1.2.3 From 7614209736fbc4927584d4387faade4f31444fce Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 9 Mar 2020 12:03:14 +0100 Subject: ceph: check POOL_FLAG_FULL/NEARFULL in addition to OSDMAP_FULL/NEARFULL CEPH_OSDMAP_FULL/NEARFULL aren't set since mimic, so we need to consult per-pool flags as well. Unfortunately the backwards compatibility here is lacking: - the change that deprecated OSDMAP_FULL/NEARFULL went into mimic, but was guarded by require_osd_release >= RELEASE_LUMINOUS - it was subsequently backported to luminous in v12.2.2, but that makes no difference to clients that only check OSDMAP_FULL/NEARFULL because require_osd_release is not client-facing -- it is for OSDs Since all kernels are affected, the best we can do here is just start checking both map flags and pool flags and send that to stable. These checks are best effort, so take osdc->lock and look up pool flags just once. Remove the FIXME, since filesystem quotas are checked above and RADOS quotas are reflected in POOL_FLAG_FULL: when the pool reaches its quota, both POOL_FLAG_FULL and POOL_FLAG_FULL_QUOTA are set. Cc: stable@vger.kernel.org Reported-by: Yanhu Cao Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton Acked-by: Sage Weil --- include/linux/ceph/osdmap.h | 4 ++++ include/linux/ceph/rados.h | 6 ++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index e081b56f1c1d..5e601975745f 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -37,6 +37,9 @@ int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs); #define CEPH_POOL_FLAG_HASHPSPOOL (1ULL << 0) /* hash pg seed and pool id together */ #define CEPH_POOL_FLAG_FULL (1ULL << 1) /* pool is full */ +#define CEPH_POOL_FLAG_FULL_QUOTA (1ULL << 10) /* pool ran out of quota, + will set FULL too */ +#define CEPH_POOL_FLAG_NEARFULL (1ULL << 11) /* pool is nearfull */ struct ceph_pg_pool_info { struct rb_node node; @@ -304,5 +307,6 @@ extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); +u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id); #endif diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 59bdfd470100..88ed3c5c04c5 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -143,8 +143,10 @@ extern const char *ceph_osd_state_name(int s); /* * osd map flag bits */ -#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC) */ -#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC) */ +#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC), + not set since ~luminous */ +#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC), + not set since ~luminous */ #define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */ #define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */ #define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */ -- cgit v1.2.3 From e886274031200bb60965c1b9c49b7acda56a93bd Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 10 Mar 2020 16:19:01 +0100 Subject: libceph: fix alloc_msg_with_page_vector() memory leaks Make it so that CEPH_MSG_DATA_PAGES data item can own pages, fixing a bunch of memory leaks for a page vector allocated in alloc_msg_with_page_vector(). Currently, only watch-notify messages trigger this allocation, and normally the page vector is freed either in handle_watch_notify() or by the caller of ceph_osdc_notify(). But if the message is freed before that (e.g. if the session faults while reading in the message or if the notify is stale), we leak the page vector. This was supposed to be fixed by switching to a message-owned pagelist, but that never happened. Fixes: 1907920324f1 ("libceph: support for sending notifies") Reported-by: Roman Penyaev Signed-off-by: Ilya Dryomov Reviewed-by: Roman Penyaev --- include/linux/ceph/messenger.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c4458dc6a757..76371aaae2d1 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -175,9 +175,10 @@ struct ceph_msg_data { #endif /* CONFIG_BLOCK */ struct ceph_bvec_iter bvec_pos; struct { - struct page **pages; /* NOT OWNER. */ + struct page **pages; size_t length; /* total # bytes */ unsigned int alignment; /* first page */ + bool own_pages; }; struct ceph_pagelist *pagelist; }; @@ -356,8 +357,8 @@ extern void ceph_con_keepalive(struct ceph_connection *con); extern bool ceph_con_keepalive_expired(struct ceph_connection *con, unsigned long interval); -extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, - size_t length, size_t alignment); +void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, + size_t length, size_t alignment, bool own_pages); extern void ceph_msg_data_add_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK -- cgit v1.2.3 From 55b474c41e586a5c21c7ab81ff474eb6bacb4322 Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Sat, 21 Mar 2020 00:46:50 +0100 Subject: netlink: check for null extack in cookie helpers Unlike NL_SET_ERR_* macros, nl_set_extack_cookie_u64() and nl_set_extack_cookie_u32() helpers do not check extack argument for null and neither do their callers, as syzbot recently discovered for ethnl_parse_header(). Instead of fixing the callers and leaving the trap in place, add check of null extack to both helpers to make them consistent with NL_SET_ERR_* macros. v2: drop incorrect second Fixes tag Fixes: 2363d73a2f3e ("ethtool: reject unrecognized request flags") Reported-by: syzbot+258a9089477493cea67b@syzkaller.appspotmail.com Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- include/linux/netlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 4090524c3462..60739d0cbf93 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -115,6 +115,8 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, { u64 __cookie = cookie; + if (!extack) + return; memcpy(extack->cookie, &__cookie, sizeof(__cookie)); extack->cookie_len = sizeof(__cookie); } @@ -124,6 +126,8 @@ static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, { u32 __cookie = cookie; + if (!extack) + return; memcpy(extack->cookie, &__cookie, sizeof(__cookie)); extack->cookie_len = sizeof(__cookie); } -- cgit v1.2.3 From e80f40cbe4dd51371818e967d40da8fe305db5e4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 24 Mar 2020 11:45:34 +0200 Subject: net: dsa: tag_8021q: replace dsa_8021q_remove_header with __skb_vlan_pop Not only did this wheel did not need reinventing, but there is also an issue with it: It doesn't remove the VLAN header in a way that preserves the L2 payload checksum when that is being provided by the DSA master hw. It should recalculate checksum both for the push, before removing the header, and for the pull afterwards. But the current implementation is quite dizzying, with pulls followed immediately afterwards by pushes, the memmove is done before the push, etc. This makes a DSA master with RX checksumming offload to print stack traces with the infamous 'hw csum failure' message. So remove the dsa_8021q_remove_header function and replace it with something that actually works with inet checksumming. Fixes: d461933638ae ("net: dsa: tag_8021q: Create helper function for removing VLAN header") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 0aa803c451a3..c620d9139c28 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -28,8 +28,6 @@ int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); -struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb); - #else int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, @@ -64,11 +62,6 @@ int dsa_8021q_rx_source_port(u16 vid) return 0; } -struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb) -{ - return NULL; -} - #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ #endif /* _NET_DSA_8021Q_H */ -- cgit v1.2.3 From 575a97acc3b7446094b0dcaf6285c7c6934c2477 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 25 Mar 2020 09:09:19 +0100 Subject: ieee80211: fix HE SPR size calculation The he_sr_control field is just a u8, so le32_to_cpu() shouldn't be applied to it; this was evidently copied from ieee80211_he_oper_size(). Fix it, and also adjust the type of the local variable. Fixes: ef11a931bd1c ("mac80211: HE: add Spatial Reuse element parsing support") Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20200325090918.dfe483b49e06.Ia53622f23b2610a2ae6ea39a199866196fe946c1@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7d3f2ced92d1..73c66a3a33ae 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2102,14 +2102,14 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) { struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; u8 spr_len = sizeof(struct ieee80211_he_spr); - u32 he_spr_params; + u8 he_spr_params; /* Make sure the input is not NULL */ if (!he_spr_ie) return 0; /* Calc required length */ - he_spr_params = le32_to_cpu(he_spr->he_sr_control); + he_spr_params = he_spr->he_sr_control; if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) spr_len++; if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) -- cgit v1.2.3 From 2c64605b590edadb3fb46d1ec6badb49e940b479 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 25 Mar 2020 13:47:18 +0100 Subject: net: Fix CONFIG_NET_CLS_ACT=n and CONFIG_NFT_FWD_NETDEV={y, m} build MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit net/netfilter/nft_fwd_netdev.c: In function ‘nft_fwd_netdev_eval’: net/netfilter/nft_fwd_netdev.c:32:10: error: ‘struct sk_buff’ has no member named ‘tc_redirected’ pkt->skb->tc_redirected = 1; ^~ net/netfilter/nft_fwd_netdev.c:33:10: error: ‘struct sk_buff’ has no member named ‘tc_from_ingress’ pkt->skb->tc_from_ingress = 1; ^~ To avoid a direct dependency with tc actions from netfilter, wrap the redirect bits around CONFIG_NET_REDIRECT and move helpers to include/linux/skbuff.h. Turn on this toggle from the ifb driver, the only existing client of these bits in the tree. This patch adds skb_set_redirected() that sets on the redirected bit on the skbuff, it specifies if the packet was redirect from ingress and resets the timestamp (timestamp reset was originally missing in the netfilter bugfix). Fixes: bcfabee1afd99484 ("netfilter: nft_fwd_netdev: allow to redirect to ifb via ingress") Reported-by: noreply@ellerman.id.au Reported-by: Geert Uytterhoeven Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/skbuff.h | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5b50278c4bc8..e59620234415 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -645,8 +645,8 @@ typedef unsigned char *sk_buff_data_t; * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress - * @tc_redirected: packet was redirected by a tc action - * @tc_from_ingress: if tc_redirected, tc_at_ingress at time of redirect + * @redirected: packet was redirected by packet classifier + * @from_ingress: packet was redirected from the ingress path * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -848,8 +848,10 @@ struct sk_buff { #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; - __u8 tc_redirected:1; - __u8 tc_from_ingress:1; +#endif +#ifdef CONFIG_NET_REDIRECT + __u8 redirected:1; + __u8 from_ingress:1; #endif #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; @@ -4579,5 +4581,31 @@ static inline __wsum lco_csum(struct sk_buff *skb) return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } +static inline bool skb_is_redirected(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_REDIRECT + return skb->redirected; +#else + return false; +#endif +} + +static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) +{ +#ifdef CONFIG_NET_REDIRECT + skb->redirected = 1; + skb->from_ingress = from_ingress; + if (skb->from_ingress) + skb->tstamp = 0; +#endif +} + +static inline void skb_reset_redirect(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_REDIRECT + skb->redirected = 0; +#endif +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.3 From 4e934301203648b1705360c1c52d4ce2e2acec5e Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 24 Mar 2020 19:22:57 -0700 Subject: clk: Pass correct arguments to __clk_hw_register_gate() I copy/pasted these macros and forgot to update the argument names and where they're passed to. Fix it so that these macros make sense. Reported-by: Maxime Ripard Fixes: 194efb6e2667 ("clk: gate: Add support for specifying parents via DT/pointers") Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20200325022257.148244-1-sboyd@kernel.org Tested-by: Maxime Ripard --- include/linux/clk-provider.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 952ac035bab9..bd1ee9039558 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -522,9 +522,9 @@ struct clk *clk_register_gate(struct device *dev, const char *name, * @clk_gate_flags: gate-specific flags for this clock * @lock: shared register lock for this clock */ -#define clk_hw_register_gate_parent_hw(dev, name, parent_name, flags, reg, \ +#define clk_hw_register_gate_parent_hw(dev, name, parent_hw, flags, reg, \ bit_idx, clk_gate_flags, lock) \ - __clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + __clk_hw_register_gate((dev), NULL, (name), NULL, (parent_hw), \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) /** @@ -539,10 +539,10 @@ struct clk *clk_register_gate(struct device *dev, const char *name, * @clk_gate_flags: gate-specific flags for this clock * @lock: shared register lock for this clock */ -#define clk_hw_register_gate_parent_data(dev, name, parent_name, flags, reg, \ +#define clk_hw_register_gate_parent_data(dev, name, parent_data, flags, reg, \ bit_idx, clk_gate_flags, lock) \ - __clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ - NULL, (flags), (reg), (bit_idx), \ + __clk_hw_register_gate((dev), NULL, (name), NULL, NULL, (parent_data), \ + (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); -- cgit v1.2.3 From 8380ce479010f2f779587b462a9b4681934297c3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 28 Mar 2020 19:17:25 -0700 Subject: mm: fork: fix kernel_stack memcg stats for various stack implementations Depending on CONFIG_VMAP_STACK and the THREAD_SIZE / PAGE_SIZE ratio the space for task stacks can be allocated using __vmalloc_node_range(), alloc_pages_node() and kmem_cache_alloc_node(). In the first and the second cases page->mem_cgroup pointer is set, but in the third it's not: memcg membership of a slab page should be determined using the memcg_from_slab_page() function, which looks at page->slab_cache->memcg_params.memcg . In this case, using mod_memcg_page_state() (as in account_kernel_stack()) is incorrect: page->mem_cgroup pointer is NULL even for pages charged to a non-root memory cgroup. It can lead to kernel_stack per-memcg counters permanently showing 0 on some architectures (depending on the configuration). In order to fix it, let's introduce a mod_memcg_obj_state() helper, which takes a pointer to a kernel object as a first argument, uses mem_cgroup_from_obj() to get a RCU-protected memcg pointer and calls mod_memcg_state(). It allows to handle all possible configurations (CONFIG_VMAP_STACK and various THREAD_SIZE/PAGE_SIZE values) without spilling any memcg/kmem specifics into fork.c . Note: This is a special version of the patch created for stable backports. It contains code from the following two patches: - mm: memcg/slab: introduce mem_cgroup_from_obj() - mm: fork: fix kernel_stack memcg stats for various stack implementations [guro@fb.com: introduce mem_cgroup_from_obj()] Link: http://lkml.kernel.org/r/20200324004221.GA36662@carbon.dhcp.thefacebook.com Fixes: 4d96ba353075 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages") Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Bharata B Rao Cc: Shakeel Butt Cc: Link: http://lkml.kernel.org/r/20200303233550.251375-1-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a7a0a1a5c8d5..e9ba01336d4e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -695,6 +695,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); +void mod_memcg_obj_state(void *p, int idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) @@ -1123,6 +1124,10 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, __mod_node_page_state(page_pgdat(page), idx, val); } +static inline void mod_memcg_obj_state(void *p, int idx, int val) +{ +} + static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, @@ -1427,6 +1432,8 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } +struct mem_cgroup *mem_cgroup_from_obj(void *p); + #else static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) @@ -1468,6 +1475,11 @@ static inline void memcg_put_cache_ids(void) { } +static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) +{ + return NULL; +} + #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ -- cgit v1.2.3 From 4ea8391e3556ad08ff0ea8fb282f9a550b8a3333 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 18 Apr 2020 13:40:09 -0700 Subject: Input: delete unused GP2AP002A00F driver There is now an IIO driver for GP2AP002A00F and GP2AP002S00F in drivers/iio/light/gp2ap002.c. Delete this driver, it is unused in the kernel tree and new users can make use of the IIO driver. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20200417203059.8151-1-linus.walleij@linaro.org Signed-off-by: Dmitry Torokhov --- include/linux/input/gp2ap002a00f.h | 23 ----------------------- 1 file changed, 23 deletions(-) delete mode 100644 include/linux/input/gp2ap002a00f.h (limited to 'include/linux') diff --git a/include/linux/input/gp2ap002a00f.h b/include/linux/input/gp2ap002a00f.h deleted file mode 100644 index 3614a13a8297..000000000000 --- a/include/linux/input/gp2ap002a00f.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _GP2AP002A00F_H_ -#define _GP2AP002A00F_H_ - -#include - -#define GP2A_I2C_NAME "gp2ap002a00f" - -/** - * struct gp2a_platform_data - Sharp gp2ap002a00f proximity platform data - * @vout_gpio: The gpio connected to the object detected pin (VOUT) - * @wakeup: Set to true if the proximity can wake the device from suspend - * @hw_setup: Callback for setting up hardware such as gpios and vregs - * @hw_shutdown: Callback for properly shutting down hardware - */ -struct gp2a_platform_data { - int vout_gpio; - bool wakeup; - int (*hw_setup)(struct i2c_client *client); - int (*hw_shutdown)(struct i2c_client *client); -}; - -#endif -- cgit v1.2.3 From 5fc70e350edd30fb22d2f9b4e6d680c5471890ff Mon Sep 17 00:00:00 2001 From: Jiada Wang Date: Mon, 11 May 2020 13:12:13 -0700 Subject: Input: introduce input_mt_report_slot_inactive() input_mt_report_slot_state() ignores "tool" argument when the slot is closed, which has caused a bit of confusion. Let's introduce input_mt_report_slot_inactive() to report inactive slot state. Suggested-by: Dmitry Torokhov Signed-off-by: Jiada Wang Link: https://lore.kernel.org/r/20200508055656.96389-2-jiada_wang@mentor.com Signed-off-by: Dmitry Torokhov --- include/linux/input/mt.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index 9e409bb13642..3b8580bd33c1 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -100,6 +100,11 @@ static inline bool input_is_mt_axis(int axis) bool input_mt_report_slot_state(struct input_dev *dev, unsigned int tool_type, bool active); +static inline void input_mt_report_slot_inactive(struct input_dev *dev) +{ + input_mt_report_slot_state(dev, 0, false); +} + void input_mt_report_finger_count(struct input_dev *dev, int count); void input_mt_report_pointer_emulation(struct input_dev *dev, bool use_count); void input_mt_drop_unused(struct input_dev *dev); -- cgit v1.2.3