From 33225d7b0ac9903c5701bbede7dfdaeba74ad6c3 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 13 Feb 2020 10:51:33 +0100 Subject: printk: Correctly set CON_CONSDEV even when preferred console was not registered CON_CONSDEV flag was historically used to put/keep the preferred console first in console_drivers list. Where the preferred console is the last on the command line. The ordering is important only when opening /dev/console: + tty_kopen() + tty_lookup_driver() + console_device() The flag was originally an implementation detail. But it was later made accessible from userspace via /proc/consoles. It was used, for example, by the tool "showconsole" to show the real tty accessible via /dev/console, see https://github.com/bitstreamout/showconsole Now, the current code sets CON_CONSDEV only for the preferred console or when a fallback console is added. The flag is not set when the preferred console is defined on the command line but it is not registered from some reasons. Simple solution is to set CON_CONSDEV flag for the first registered console. It will work most of the time because: + Most real consoles have console->device defined. + Boot consoles are removed in printk_late_init(). + unregister_console() moves CON_CONSDEV flag to the next console. Clean solution would require checking con->device when the preferred console is registered and in unregister_console(). Conclusion: Use the simple solution for now. It is better than the current state and good enough. The clean solution is not worth it. It would complicate the already complicated code without too much gain. Instead the code would deserve a complete rewrite. Link: https://lore.kernel.org/r/20200213095133.23176-4-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt [pmladek@suse.com: Correct reasoning in the commit message, comment update.] Reviewed-by: Petr Mladek Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/console.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index d09951d5a94e..72141f71c014 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -135,7 +135,7 @@ static inline int con_debug_leave(void) */ #define CON_PRINTBUFFER (1) -#define CON_CONSDEV (2) /* Last on the command line */ +#define CON_CONSDEV (2) /* Preferred console, /dev/console */ #define CON_ENABLED (4) #define CON_BOOT (8) #define CON_ANYTIME (16) /* Safe to call when cpu is offline */ -- cgit v1.2.3 From db751e309ff05461a0c8e114b1238d7a69cc1f18 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:43 +0000 Subject: ELF: UAPI and Kconfig additions for ELF program properties Pull the basic ELF definitions relating to the NT_GNU_PROPERTY_TYPE_0 note from Yu-Cheng Yu's earlier x86 shstk series. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Signed-off-by: Yu-cheng Yu Reviewed-by: Catalin Marinas Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/elf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index e3649b3e970e..f7b24c5fcfb6 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -2,6 +2,7 @@ #ifndef _LINUX_ELF_H #define _LINUX_ELF_H +#include #include #include @@ -56,4 +57,15 @@ static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { extern int elf_coredump_extra_notes_size(void); extern int elf_coredump_extra_notes_write(struct coredump_params *cprm); #endif + +/* + * NT_GNU_PROPERTY_TYPE_0 header: + * Keep this internal until/unless there is an agreed UAPI definition. + * pr_type values (GNU_PROPERTY_*) are public and defined in the UAPI header. + */ +struct gnu_property { + u32 pr_type; + u32 pr_datasz; +}; + #endif /* _LINUX_ELF_H */ -- cgit v1.2.3 From 00e19ceec80b03a43f626f891fcc53e57919f1b3 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:44 +0000 Subject: ELF: Add ELF program property parsing support ELF program properties will be needed for detecting whether to enable optional architecture or ABI features for a new ELF process. For now, there are no generic properties that we care about, so do nothing unless CONFIG_ARCH_USE_GNU_PROPERTY=y. Otherwise, the presence of properties using the PT_PROGRAM_PROPERTY phdrs entry (if any), and notify each property to the arch code. For now, the added code is not used. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/elf.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index f7b24c5fcfb6..db5113479f5e 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -22,6 +22,9 @@ SET_PERSONALITY(ex) #endif +#define ELF32_GNU_PROPERTY_ALIGN 4 +#define ELF64_GNU_PROPERTY_ALIGN 8 + #if ELF_CLASS == ELFCLASS32 extern Elf32_Dyn _DYNAMIC []; @@ -32,6 +35,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elf_addr_t Elf32_Off #define Elf_Half Elf32_Half #define Elf_Word Elf32_Word +#define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN #else @@ -43,6 +47,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elf_addr_t Elf64_Off #define Elf_Half Elf64_Half #define Elf_Word Elf64_Word +#define ELF_GNU_PROPERTY_ALIGN ELF64_GNU_PROPERTY_ALIGN #endif @@ -68,4 +73,18 @@ struct gnu_property { u32 pr_datasz; }; +struct arch_elf_state; + +#ifndef CONFIG_ARCH_USE_GNU_PROPERTY +static inline int arch_parse_elf_property(u32 type, const void *data, + size_t datasz, bool compat, + struct arch_elf_state *arch) +{ + return 0; +} +#else +extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz, + bool compat, struct arch_elf_state *arch); +#endif + #endif /* _LINUX_ELF_H */ -- cgit v1.2.3 From 8ef8f360cf30be12382f89ff48a57fbbd9b31c14 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:45 +0000 Subject: arm64: Basic Branch Target Identification support This patch adds the bare minimum required to expose the ARMv8.5 Branch Target Identification feature to userspace. By itself, this does _not_ automatically enable BTI for any initial executable pages mapped by execve(). This will come later, but for now it should be possible to enable BTI manually on those pages by using mprotect() from within the target process. Other arches already using the generic mman.h are already using 0x10 for arch-specific prot flags, so we use that for PROT_BTI here. For consistency, signal handler entry points in BTI guarded pages are required to be annotated as such, just like any other function. This blocks a relatively minor attack vector, but comforming userspace will have the annotations anyway, so we may as well enforce them. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Signed-off-by: Catalin Marinas --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 52269e56c514..9e5fce1b2099 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -324,6 +324,9 @@ extern unsigned int kobjsize(const void *objp); #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI +#elif defined(CONFIG_ARM64) +# define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ +# define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -- cgit v1.2.3 From fe0f67660ee9c99408be5261ae045f8b41953b05 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:46 +0000 Subject: elf: Allow arch to tweak initial mmap prot flags An arch may want to tweak the mmap prot flags for an ELFexecutable's initial mappings. For example, arm64 is going to need to add PROT_BTI for executable pages in an ELF process whose executable is marked as using Branch Target Identification (an ARMv8.5-A control flow integrity feature). So that this can be done in a generic way, add a hook arch_elf_adjust_prot() to modify the prot flags as desired: arches can select CONFIG_HAVE_ELF_PROT and implement their own backend where necessary. By default, leave the prot flags unchanged. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/elf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index db5113479f5e..5d5b0321da0b 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -87,4 +87,16 @@ extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz, bool compat, struct arch_elf_state *arch); #endif +#ifdef CONFIG_ARCH_HAVE_ELF_PROT +int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state, + bool has_interp, bool is_interp); +#else +static inline int arch_elf_adjust_prot(int prot, + const struct arch_elf_state *state, + bool has_interp, bool is_interp) +{ + return prot; +} +#endif + #endif /* _LINUX_ELF_H */ -- cgit v1.2.3 From 143324fd89eff7423c01eba79fc7044003a257e9 Mon Sep 17 00:00:00 2001 From: Rohit Sarkar Date: Wed, 18 Mar 2020 21:41:51 +0530 Subject: iio: core: Make mlock internal to the iio core "mlock" should ideally only be used by the iio core. The mlock implementation may change in the future which means that no driver should be explicitly using mlock. Signed-off-by: Rohit Sarkar Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index eed58ed2f368..e975020abaa6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -492,7 +492,7 @@ struct iio_buffer_setup_ops { * @buffer: [DRIVER] any buffer present * @buffer_list: [INTERN] list of all buffers currently attached * @scan_bytes: [INTERN] num bytes captured to be fed to buffer demux - * @mlock: [DRIVER] lock used to prevent simultaneous device state + * @mlock: [INTERN] lock used to prevent simultaneous device state * changes * @available_scan_masks: [DRIVER] optional array of allowed bitmasks * @masklength: [INTERN] the length of the mask established from -- cgit v1.2.3 From 09606b5446c25b2c3b16c5bd2977eca730e3a570 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 22 Mar 2018 17:09:42 +0100 Subject: dma-buf: add peer2peer flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a peer2peer flag noting that the importer can deal with device resources which are not backed by pages. Signed-off-by: Christian König Acked-by: Daniel Vetter Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/359286/ --- include/linux/dma-buf.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 1ade486fc2bb..82e0a4a64601 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -334,6 +334,14 @@ struct dma_buf { * Attachment operations implemented by the importer. */ struct dma_buf_attach_ops { + /** + * @allow_peer2peer: + * + * If this is set to true the importer must be able to handle peer + * resources without struct pages. + */ + bool allow_peer2peer; + /** * @move_notify * @@ -362,6 +370,7 @@ struct dma_buf_attach_ops { * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf. * @sgt: cached mapping. * @dir: direction of cached mapping. + * @peer2peer: true if the importer can handle peer resources without pages. * @priv: exporter specific attachment data. * @importer_ops: importer operations for this attachment, if provided * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held. @@ -382,6 +391,7 @@ struct dma_buf_attachment { struct list_head node; struct sg_table *sgt; enum dma_data_direction dir; + bool peer2peer; const struct dma_buf_attach_ops *importer_ops; void *importer_priv; void *priv; -- cgit v1.2.3 From 2c758e301ed95aefde68f98584204811d55c9bb8 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 25 Mar 2020 18:31:22 +0100 Subject: soc / drm: mediatek: Move routing control to mmsys device Provide a mtk_mmsys_ddp_connect() and mtk_mmsys_disconnect() functions to replace mtk_ddp_add_comp_to_path() and mtk_ddp_remove_comp_from_path(). Those functions will allow DRM driver and others to control the data path routing. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Matthias Brugger Reviewed-by: CK Hu Acked-by: CK Hu Tested-by: Anders Roxell Reviewed-by: Chun-Kuang Hu Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/soc/mediatek/mtk-mmsys.h (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h new file mode 100644 index 000000000000..7bab5d9a3d31 --- /dev/null +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015 MediaTek Inc. + */ + +#ifndef __MTK_MMSYS_H +#define __MTK_MMSYS_H + +enum mtk_ddp_comp_id; +struct device; + +void mtk_mmsys_ddp_connect(struct device *dev, + enum mtk_ddp_comp_id cur, + enum mtk_ddp_comp_id next); + +void mtk_mmsys_ddp_disconnect(struct device *dev, + enum mtk_ddp_comp_id cur, + enum mtk_ddp_comp_id next); + +#endif /* __MTK_MMSYS_H */ -- cgit v1.2.3 From f454f4d1915b44cc3857148aac7a297a31591501 Mon Sep 17 00:00:00 2001 From: Maciej Grochowski Date: Thu, 9 Apr 2020 01:03:37 -0400 Subject: include/ntb: Fix typo in ntb_unregister_device description Signed-off-by: Maciej Grochowski Signed-off-by: Jon Mason --- include/linux/ntb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 8c13538aeffe..a07252f78770 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -478,7 +478,7 @@ void ntb_unregister_client(struct ntb_client *client); int ntb_register_device(struct ntb_dev *ntb); /** - * ntb_register_device() - unregister a ntb device + * ntb_unregister_device() - unregister a ntb device * @ntb: NTB device context. * * The device will be removed from the list of ntb devices. If the ntb device -- cgit v1.2.3 From eec8fd0277e37cf447b88c6be181e81df867bcf1 Mon Sep 17 00:00:00 2001 From: Odin Ugedal Date: Fri, 3 Apr 2020 19:55:28 +0200 Subject: device_cgroup: Cleanup cgroup eBPF device filter code Original cgroup v2 eBPF code for filtering device access made it possible to compile with CONFIG_CGROUP_DEVICE=n and still use the eBPF filtering. Change commit 4b7d4d453fc4 ("device_cgroup: Export devcgroup_check_permission") reverted this, making it required to set it to y. Since the device filtering (and all the docs) for cgroup v2 is no longer a "device controller" like it was in v1, someone might compile their kernel with CONFIG_CGROUP_DEVICE=n. Then (for linux 5.5+) the eBPF filter will not be invoked, and all processes will be allowed access to all devices, no matter what the eBPF filter says. Signed-off-by: Odin Ugedal Acked-by: Roman Gushchin Signed-off-by: Tejun Heo --- include/linux/device_cgroup.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index fa35b52e0002..9a72214496e5 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include -#include #define DEVCG_ACC_MKNOD 1 #define DEVCG_ACC_READ 2 @@ -11,16 +10,10 @@ #define DEVCG_DEV_CHAR 2 #define DEVCG_DEV_ALL 4 /* this represents all devices */ -#ifdef CONFIG_CGROUP_DEVICE -int devcgroup_check_permission(short type, u32 major, u32 minor, - short access); -#else -static inline int devcgroup_check_permission(short type, u32 major, u32 minor, - short access) -{ return 0; } -#endif #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) +int devcgroup_check_permission(short type, u32 major, u32 minor, + short access); static inline int devcgroup_inode_permission(struct inode *inode, int mask) { short type, access = 0; @@ -61,6 +54,9 @@ static inline int devcgroup_inode_mknod(int mode, dev_t dev) } #else +static inline int devcgroup_check_permission(short type, u32 major, u32 minor, + short access) +{ return 0; } static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } static inline int devcgroup_inode_mknod(int mode, dev_t dev) -- cgit v1.2.3 From 07d8350ede4c4c29634b26c163a1eecdf39dfcfb Mon Sep 17 00:00:00 2001 From: afzal mohammed Date: Fri, 27 Mar 2020 21:41:16 +0530 Subject: genirq: Remove setup_irq() and remove_irq() Now that all the users of setup_irq() & remove_irq() have been replaced by request_irq() & free_irq() respectively, delete them. Signed-off-by: afzal mohammed Signed-off-by: Thomas Gleixner Reviewed-by: Linus Walleij Link: https://lkml.kernel.org/r/0aa8771ada1ac8e1312f6882980c9c08bd023148.1585320721.git.afzal.mohd.ma@gmail.com --- include/linux/irq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 9315fbb87db3..c63c2aa915ff 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -573,8 +573,6 @@ enum { #define IRQ_DEFAULT_INIT_FLAGS ARCH_IRQ_INIT_FLAGS struct irqaction; -extern int setup_irq(unsigned int irq, struct irqaction *new); -extern void remove_irq(unsigned int irq, struct irqaction *act); extern int setup_percpu_irq(unsigned int irq, struct irqaction *new); extern void remove_percpu_irq(unsigned int irq, struct irqaction *act); -- cgit v1.2.3 From 70771c69ab9be6e37618b1ec6c105f370e510f94 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 3 Apr 2020 18:10:17 +0100 Subject: firmware: arm_scmi: Add include guard to linux/scmi_protocol.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If this header is include twice, it will generate loads of compile time error with the following below error pattern. It was reported by 0day kbuild robot on a branch pushed with double inclusion by accident. error: conflicting types for ‘...’ note: previous declaration of ‘...’ was here error: redefinition of ‘...’ Add a header include guard just in case. Link: https://lore.kernel.org/r/20200403171018.1230-1-sudeep.holla@arm.com Reported-by: kbuild test robot Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 5c873a59b387..ce2f5c28b2df 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -4,6 +4,10 @@ * * Copyright (C) 2018 ARM Ltd. */ + +#ifndef _LINUX_SCMI_PROTOCOL_H +#define _LINUX_SCMI_PROTOCOL_H + #include #include @@ -319,3 +323,5 @@ static inline void scmi_driver_unregister(struct scmi_driver *driver) {} typedef int (*scmi_prot_init_fn_t)(struct scmi_handle *); int scmi_protocol_register(int protocol_id, scmi_prot_init_fn_t fn); void scmi_protocol_unregister(int protocol_id); + +#endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From 23818b3d8590a79d56af9659cf709ebfae30f832 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 3 Apr 2020 18:10:18 +0100 Subject: firmware: arm_scpi: Add include guard to linux/scpi_protocol.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If this header is include twice, it will generate loads of compile time error with the following below error pattern. It was reported by 0day kbuild robot on a branch pushed with double inclusion by accident. This is based on the similar change in linux/scmi_protocol.h error: conflicting types for ‘...’ note: previous declaration of ‘...’ was here error: redefinition of ‘...’ Add a header include guard just in case. Link: https://lore.kernel.org/r/20200403171018.1230-2-sudeep.holla@arm.com Reported-by: kbuild test robot Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index ecb004711acf..afbf8037d8db 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -4,6 +4,10 @@ * * Copyright (C) 2014 ARM Ltd. */ + +#ifndef _LINUX_SCPI_PROTOCOL_H +#define _LINUX_SCPI_PROTOCOL_H + #include struct scpi_opp { @@ -71,3 +75,5 @@ struct scpi_ops *get_scpi_ops(void); #else static inline struct scpi_ops *get_scpi_ops(void) { return NULL; } #endif + +#endif /* _LINUX_SCPI_PROTOCOL_H */ -- cgit v1.2.3 From b6467ab142b708dd076f6186ca274f14af379c72 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 7 Apr 2020 23:40:58 -0700 Subject: KVM: Check validity of resolved slot when searching memslots Check that the resolved slot (somewhat confusingly named 'start') is a valid/allocated slot before doing the final comparison to see if the specified gfn resides in the associated slot. The resolved slot can be invalid if the binary search loop terminated because the search index was incremented beyond the number of used slots. This bug has existed since the binary search algorithm was introduced, but went unnoticed because KVM statically allocated memory for the max number of slots, i.e. the access would only be truly out-of-bounds if all possible slots were allocated and the specified gfn was less than the base of the lowest memslot. Commit 36947254e5f98 ("KVM: Dynamically size memslot array based on number of used slots") eliminated the "all possible slots allocated" condition and made the bug embarrasingly easy to hit. Fixes: 9c1a5d38780e6 ("kvm: optimize GFN to memslot lookup with large slots amount") Reported-by: syzbot+d889b59b2bb87d4047a2@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20200408064059.8957-2-sean.j.christopherson@intel.com> 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 6d58beb65454..01276e3d01b9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1048,7 +1048,7 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn) start = slot + 1; } - if (gfn >= memslots[start].base_gfn && + if (start < slots->used_slots && gfn >= memslots[start].base_gfn && gfn < memslots[start].base_gfn + memslots[start].npages) { atomic_set(&slots->lru_slot, start); return &memslots[start]; -- cgit v1.2.3 From 12479382877dcf6623af4676caa8d3c647469a1b Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Thu, 2 Apr 2020 22:36:44 +0200 Subject: regmap-irq: make it possible to add irq_chip do a specific device node Add a new function regmap_add_irq_chip_np() with its corresponding devm_regmap_add_irq_chip_np() variant. Sometimes one want to register the IRQ domain on a different device node that the one of the regmap node. For example when using a MFD where there are different interrupt controllers and particularly for the generic regmap gpio_chip/irq_chip driver. In this case it is not desireable to have the IRQ domain on the parent node. Signed-off-by: Michael Walle Link: https://lore.kernel.org/r/20200402203656.27047-5-michael@walle.cc Signed-off-by: Mark Brown --- include/linux/regmap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..ae5034b2d7c3 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -21,6 +21,7 @@ struct module; struct clk; struct device; +struct device_node; struct i2c_client; struct i3c_device; struct irq_domain; @@ -1310,12 +1311,21 @@ struct regmap_irq_chip_data; int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); +int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq, + int irq_flags, int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data); int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); +int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np, + struct regmap *map, int irq, int irq_flags, + int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); void devm_regmap_del_irq_chip(struct device *dev, int irq, struct regmap_irq_chip_data *data); -- cgit v1.2.3 From bd3ddb495762575ab14e7bd2e4017dc1f9a80b2f Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Thu, 2 Apr 2020 10:41:11 +0200 Subject: regmap: add reg_sequence helpers Add helper to make it easier to define a reg_sequence array. Signed-off-by: Marco Felsch Link: https://lore.kernel.org/r/20200402084111.30123-1-m.felsch@pengutronix.de Signed-off-by: Mark Brown --- include/linux/regmap.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..0b5582a78df8 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -71,6 +71,13 @@ struct reg_sequence { unsigned int delay_us; }; +#define REG_SEQ(_reg, _def, _delay_us) { \ + .reg = _reg, \ + .def = _def, \ + .delay_us = _delay_us, \ + } +#define REG_SEQ0(_reg, _def) REG_SEQ(_reg, _def, 0) + #define regmap_update_bits(map, reg, mask, val) \ regmap_update_bits_base(map, reg, mask, val, NULL, false, false) #define regmap_update_bits_async(map, reg, mask, val)\ -- cgit v1.2.3 From 4c5b566c2193e2af82c891daa5303c8899e61044 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 31 Mar 2020 02:15:44 +0800 Subject: crash_dump: Remove no longer used saved_max_pfn saved_max_pfn was originally introduced in commit 92aa63a5a1bf ("[PATCH] kdump: Retrieve saved max pfn") It used to make sure that the user does not try to read the physical memory beyond saved_max_pfn. But since commit 921d58c0e699 ("vmcore: remove saved_max_pfn check") it's no longer used for the check. This variable doesn't have any users anymore so just remove it. [ bp: Drop the Calgary IOMMU reference from the commit message. ] Signed-off-by: Kairui Song Signed-off-by: Borislav Petkov Acked-by: "Eric W. Biederman" Link: https://lkml.kernel.org/r/20200330181544.1595733-1-kasong@redhat.com --- include/linux/crash_dump.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 4664fc1871de..bc156285d097 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -97,8 +97,6 @@ extern void unregister_oldmem_pfn_is_ram(void); static inline bool is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ -extern unsigned long saved_max_pfn; - /* Device Dump information to be filled by drivers */ struct vmcoredd_data { char dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */ -- cgit v1.2.3 From 3c1d1613be80c2e17f1ddf672df1d8a8caebfd0d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 6 Apr 2020 14:25:31 +0200 Subject: i2c: remove i2c_new_probed_device API All in-tree users have been converted to the new i2c_new_scanned_device function, so remove this deprecated one. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 456fc17ecb1c..45d36ba4826b 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -461,12 +461,6 @@ i2c_new_scanned_device(struct i2c_adapter *adap, unsigned short const *addr_list, int (*probe)(struct i2c_adapter *adap, unsigned short addr)); -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 */ int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); -- cgit v1.2.3 From 20d60f6364474a978ab2a2146fb4c2bd9b6bbe3f Mon Sep 17 00:00:00 2001 From: Maciej Grochowski Date: Tue, 14 Apr 2020 00:17:03 -0400 Subject: include/linux/dmaengine: Typos fixes in API documentation Signed-off-by: Maciej Grochowski Link: https://lore.kernel.org/r/20200414041703.6661-1-maciek.grochowski@gmail.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 21065c04c4ac..31e58ec9f741 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -83,9 +83,9 @@ enum dma_transfer_direction { /** * Interleaved Transfer Request * ---------------------------- - * A chunk is collection of contiguous bytes to be transfered. + * A chunk is collection of contiguous bytes to be transferred. * The gap(in bytes) between two chunks is called inter-chunk-gap(ICG). - * ICGs may or maynot change between chunks. + * ICGs may or may not change between chunks. * A FRAME is the smallest series of contiguous {chunk,icg} pairs, * that when repeated an integral number of times, specifies the transfer. * A transfer template is specification of a Frame, the number of times @@ -1069,7 +1069,7 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan) * dmaengine_synchronize() needs to be called before it is safe to free * any memory that is accessed by previously submitted descriptors or before * freeing any resources accessed from within the completion callback of any - * perviously submitted descriptors. + * previously submitted descriptors. * * This function can be called from atomic context as well as from within a * complete callback of a descriptor submitted on the same channel. @@ -1091,7 +1091,7 @@ static inline int dmaengine_terminate_async(struct dma_chan *chan) * * Synchronizes to the DMA channel termination to the current context. When this * function returns it is guaranteed that all transfers for previously issued - * descriptors have stopped and and it is safe to free the memory assoicated + * descriptors have stopped and it is safe to free the memory associated * with them. Furthermore it is guaranteed that all complete callback functions * for a previously submitted descriptor have finished running and it is safe to * free resources accessed from within the complete callbacks. -- cgit v1.2.3 From 5429ef62bcf360aae06740cbe065be01e5cfb6fc Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 22 Jan 2020 19:38:21 +0000 Subject: compiler/gcc: Raise minimum GCC version for kernel builds to 4.8 It is very rare to see versions of GCC prior to 4.8 being used to build the mainline kernel. These old compilers are also know to have codegen issues which can lead to silent miscompilation: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 Raise the minimum GCC version for kernel build to 4.8 and remove some tautological Kconfig dependencies as a consequence. Cc: Masahiro Yamada Acked-by: Arnd Bergmann Reviewed-by: Nick Desaulniers Signed-off-by: Will Deacon --- include/linux/compiler-gcc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d7ee4c6bad48..e2f725273261 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -10,7 +10,8 @@ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) -#if GCC_VERSION < 40600 +/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ +#if GCC_VERSION < 40800 # error Sorry, your compiler is too old - please upgrade it. #endif @@ -126,9 +127,7 @@ #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ -#if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ -#endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 70000 -- cgit v1.2.3 From d87f639258a6a5980183f11876c884931ad93da2 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Feb 2020 16:14:11 -0800 Subject: ext4: use non-movable memory for superblock readahead Since commit a8ac900b8163 ("ext4: use non-movable memory for the superblock") buffers for ext4 superblock were allocated using the sb_bread_unmovable() helper which allocated buffer heads out of non-movable memory blocks. It was necessarily to not block page migrations and do not cause cma allocation failures. However commit 85c8f176a611 ("ext4: preload block group descriptors") broke this by introducing pre-reading of the ext4 superblock. The problem is that __breadahead() is using __getblk() underneath, which allocates buffer heads out of movable memory. It resulted in page migration failures I've seen on a machine with an ext4 partition and a preallocated cma area. Fix this by introducing sb_breadahead_unmovable() and __breadahead_gfp() helpers which use non-movable memory for buffer head allocations and use them for the ext4 superblock readahead. Reviewed-by: Andreas Dilger Fixes: 85c8f176a611 ("ext4: preload block group descriptors") Signed-off-by: Roman Gushchin Link: https://lore.kernel.org/r/20200229001411.128010-1-guro@fb.com Signed-off-by: Theodore Ts'o --- include/linux/buffer_head.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index e0b020eaf32e..15b765a181b8 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -189,6 +189,8 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); +void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, + gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); @@ -319,6 +321,12 @@ sb_breadahead(struct super_block *sb, sector_t block) __breadahead(sb->s_bdev, block, sb->s_blocksize); } +static inline void +sb_breadahead_unmovable(struct super_block *sb, sector_t block) +{ + __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); +} + static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { -- cgit v1.2.3 From 96806229ca033f85310bc5c203410189f8a1d2ee Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 10 Apr 2020 11:13:26 +0100 Subject: irqchip/gic-v4.1: Add support for VPENDBASER's Dirty+Valid signaling When a vPE is made resident, the GIC starts parsing the virtual pending table to deliver pending interrupts. This takes place asynchronously, and can at times take a long while. Long enough that the vcpu enters the guest and hits WFI before any interrupt has been signaled yet. The vcpu then exits, blocks, and now gets a doorbell. Rince, repeat. In order to avoid the above, a (optional on GICv4, mandatory on v4.1) feature allows the GIC to feedback to the hypervisor whether it is done parsing the VPT by clearing the GICR_VPENDBASER.Dirty bit. The hypervisor can then wait until the GIC is ready before actually running the vPE. Plug the detection code as well as polling on vPE schedule. While at it, tidy-up the kernel message that displays the GICv4 optional features. Reviewed-by: Zenghui Yu Signed-off-by: Marc Zyngier --- 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 765d9b769b69..6c36b6cc3edf 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -243,6 +243,7 @@ #define GICR_TYPER_PLPIS (1U << 0) #define GICR_TYPER_VLPIS (1U << 1) +#define GICR_TYPER_DIRTY (1U << 2) #define GICR_TYPER_DirectLPIS (1U << 3) #define GICR_TYPER_LAST (1U << 4) #define GICR_TYPER_RVPEID (1U << 7) @@ -686,6 +687,7 @@ struct rdists { bool has_vlpis; bool has_rvpeid; bool has_direct_lpi; + bool has_vpend_valid_dirty; }; struct irq_domain; -- cgit v1.2.3 From a5460b5e5fb82656807840d40d3deaecad094044 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 16 Dec 2019 16:51:45 +0000 Subject: READ_ONCE: Simplify implementations of {READ,WRITE}_ONCE() The implementations of {READ,WRITE}_ONCE() suffer from a significant amount of indirection and complexity due to a historic GCC bug: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 which was originally worked around by 230fa253df63 ("kernel: Provide READ_ONCE and ASSIGN_ONCE"). Since GCC 4.8 is fairly vintage at this point and we emit a warning if we detect it during the build, return {READ,WRITE}_ONCE() to their former glory with an implementation that is easier to understand and, crucially, more amenable to optimisation. A side effect of this simplification is that WRITE_ONCE() no longer returns a value, but nobody seems to be relying on that and the new behaviour is aligned with smp_store_release(). Suggested-by: Linus Torvalds Cc: Peter Zijlstra Cc: Michael Ellerman Cc: Arnd Bergmann Cc: Christian Borntraeger Signed-off-by: Will Deacon --- include/linux/compiler.h | 118 ++++++++++++++++------------------------------- 1 file changed, 39 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 034b0a644efc..338111a448d0 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -177,60 +177,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) #endif -#include - -#define __READ_ONCE_SIZE \ -({ \ - switch (size) { \ - case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ - case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ - case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ - case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ - default: \ - barrier(); \ - __builtin_memcpy((void *)res, (const void *)p, size); \ - barrier(); \ - } \ -}) - -static __always_inline -void __read_once_size(const volatile void *p, void *res, int size) -{ - __READ_ONCE_SIZE; -} - -#ifdef CONFIG_KASAN -/* - * We can't declare function 'inline' because __no_sanitize_address confilcts - * with inlining. Attempt to inline it may cause a build failure. - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * '__maybe_unused' allows us to avoid defined-but-not-used warnings. - */ -# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused -#else -# define __no_kasan_or_inline __always_inline -#endif - -static __no_kasan_or_inline -void __read_once_size_nocheck(const volatile void *p, void *res, int size) -{ - __READ_ONCE_SIZE; -} - -static __always_inline void __write_once_size(volatile void *p, void *res, int size) -{ - switch (size) { - case 1: *(volatile __u8 *)p = *(__u8 *)res; break; - case 2: *(volatile __u16 *)p = *(__u16 *)res; break; - case 4: *(volatile __u32 *)p = *(__u32 *)res; break; - case 8: *(volatile __u64 *)p = *(__u64 *)res; break; - default: - barrier(); - __builtin_memcpy((void *)p, (const void *)res, size); - barrier(); - } -} - /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of @@ -240,11 +186,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * statements. * * These two macros will also work on aggregate data types like structs or - * unions. If the size of the accessed data type exceeds the word size of - * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will - * fall back to memcpy(). There's at least two memcpy()s: one for the - * __builtin_memcpy() and then one for the macro doing the copy of variable - * - '__u' allocated on the stack. + * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, @@ -256,23 +198,49 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #include #include -#define __READ_ONCE(x, check) \ +#define __READ_ONCE(x) (*(volatile typeof(x) *)&(x)) + +#define READ_ONCE(x) \ ({ \ - union { typeof(x) __val; char __c[1]; } __u; \ - if (check) \ - __read_once_size(&(x), __u.__c, sizeof(x)); \ - else \ - __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ - smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ - __u.__val; \ + typeof(x) __x = __READ_ONCE(x); \ + smp_read_barrier_depends(); \ + __x; \ }) -#define READ_ONCE(x) __READ_ONCE(x, 1) + +#define WRITE_ONCE(x, val) \ +do { \ + *(volatile typeof(x) *)&(x) = (val); \ +} while (0) + +#ifdef CONFIG_KASAN +/* + * We can't declare function 'inline' because __no_sanitize_address conflicts + * with inlining. Attempt to inline it may cause a build failure. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * '__maybe_unused' allows us to avoid defined-but-not-used warnings. + */ +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused +#else +# define __no_kasan_or_inline __always_inline +#endif + +static __no_kasan_or_inline +unsigned long __read_once_word_nocheck(const void *addr) +{ + return __READ_ONCE(*(unsigned long *)addr); +} /* - * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need - * to hide memory access from KASAN. + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a + * word from memory atomically but without telling KASAN. This is usually + * used by unwinding code when walking the stack of a running process. */ -#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) +#define READ_ONCE_NOCHECK(x) \ +({ \ + unsigned long __x = __read_once_word_nocheck(&(x)); \ + smp_read_barrier_depends(); \ + __x; \ +}) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) @@ -281,14 +249,6 @@ unsigned long read_word_at_a_time(const void *addr) return *(unsigned long *)addr; } -#define WRITE_ONCE(x, val) \ -({ \ - union { typeof(x) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(x)) (val) }; \ - __write_once_size(&(x), __u.__c, sizeof(x)); \ - __u.__val; \ -}) - #endif /* __KERNEL__ */ /* -- cgit v1.2.3 From 9e343b467c70379e66b8b771d96f03ae23eba351 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 13 Dec 2019 14:47:02 +0000 Subject: READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses {READ,WRITE}_ONCE() cannot guarantee atomicity for arbitrary data sizes. This can be surprising to callers that might incorrectly be expecting atomicity for accesses to aggregate structures, although there are other callers where tearing is actually permissable (e.g. if they are using something akin to sequence locking to protect the access). Linus sayeth: | We could also look at being stricter for the normal READ/WRITE_ONCE(), | and require that they are | | (a) regular integer types | | (b) fit in an atomic word | | We actually did (b) for a while, until we noticed that we do it on | loff_t's etc and relaxed the rules. But maybe we could have a | "non-atomic" version of READ/WRITE_ONCE() that is used for the | questionable cases? The slight snag is that we also have to support 64-bit accesses on 32-bit architectures, as these appear to be widespread and tend to work out ok if either the architecture supports atomic 64-bit accesses (x86, armv7) or if the variable being accesses represents a virtual address and therefore only requires 32-bit atomicity in practice. Take a step in that direction by introducing a variant of 'compiletime_assert_atomic_type()' and use it to check the pointer argument to {READ,WRITE}_ONCE(). Expose __{READ,WRITE}_ONCE() variants which are allowed to tear and convert the one broken caller over to the new macros. Suggested-by: Linus Torvalds Cc: Peter Zijlstra Cc: Michael Ellerman Cc: Arnd Bergmann Signed-off-by: Will Deacon --- include/linux/compiler.h | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 338111a448d0..50bb2461648f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -198,20 +198,37 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #include #include -#define __READ_ONCE(x) (*(volatile typeof(x) *)&(x)) +/* + * Use __READ_ONCE() instead of READ_ONCE() if you do not require any + * atomicity or dependency ordering guarantees. Note that this may result + * in tears! + */ +#define __READ_ONCE(x) (*(const volatile typeof(x) *)&(x)) -#define READ_ONCE(x) \ +#define __READ_ONCE_SCALAR(x) \ ({ \ typeof(x) __x = __READ_ONCE(x); \ smp_read_barrier_depends(); \ __x; \ }) -#define WRITE_ONCE(x, val) \ +#define READ_ONCE(x) \ +({ \ + compiletime_assert_rwonce_type(x); \ + __READ_ONCE_SCALAR(x); \ +}) + +#define __WRITE_ONCE(x, val) \ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) +#define WRITE_ONCE(x, val) \ +do { \ + compiletime_assert_rwonce_type(x); \ + __WRITE_ONCE(x, val); \ +} while (0) + #ifdef CONFIG_KASAN /* * We can't declare function 'inline' because __no_sanitize_address conflicts @@ -313,6 +330,16 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +/* + * Yes, this permits 64-bit accesses on 32-bit architectures. These will + * actually be atomic in many cases (namely x86), but for others we rely on + * the access being split into 2x32-bit accesses for a 32-bit quantity (e.g. + * a virtual address) and a strong prevailing wind. + */ +#define compiletime_assert_rwonce_type(t) \ + compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ + "Unsupported access size for {READ,WRITE}_ONCE().") + /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -- cgit v1.2.3 From dee081bf8f824cabeb7c7495367d5dad0a444eb1 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 19 Dec 2019 14:22:31 +0000 Subject: READ_ONCE: Drop pointer qualifiers when reading from scalar types Passing a volatile-qualified pointer to READ_ONCE() is an absolute trainwreck for code generation: the use of 'typeof()' to define a temporary variable inside the macro means that the final evaluation in macro scope ends up forcing a read back from the stack. When stack protector is enabled (the default for arm64, at least), this causes the compiler to vomit up all sorts of junk. Unfortunately, dropping pointer qualifiers inside the macro poses quite a challenge, especially since the pointed-to type is permitted to be an aggregate, and this is relied upon by mm/ code accessing things like 'pmd_t'. Based on numerous hacks and discussions on the mailing list, this is the best I've managed to come up with. Introduce '__unqual_scalar_typeof()' which takes an expression and, if the expression is an optionally qualified 8, 16, 32 or 64-bit scalar type, evaluates to the unqualified type. Other input types, including aggregates, remain unchanged. Hopefully READ_ONCE() on volatile aggregate pointers isn't something we do on a fast-path. Cc: Peter Zijlstra Cc: Arnd Bergmann Suggested-by: Linus Torvalds Reported-by: Michael Ellerman Signed-off-by: Will Deacon --- include/linux/compiler.h | 6 +++--- include/linux/compiler_types.h | 21 +++++++++++++++++++++ 2 files changed, 24 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 50bb2461648f..c363d8debc43 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -203,13 +203,13 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * atomicity or dependency ordering guarantees. Note that this may result * in tears! */ -#define __READ_ONCE(x) (*(const volatile typeof(x) *)&(x)) +#define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) #define __READ_ONCE_SCALAR(x) \ ({ \ - typeof(x) __x = __READ_ONCE(x); \ + __unqual_scalar_typeof(x) __x = __READ_ONCE(x); \ smp_read_barrier_depends(); \ - __x; \ + (typeof(x))__x; \ }) #define READ_ONCE(x) \ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e970f97a7fcb..233066c92f6f 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -210,6 +210,27 @@ struct ftrace_likely_data { /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) +/* + * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving + * non-scalar types unchanged. + * + * We build this out of a couple of helper macros in a vain attempt to + * help you keep your lunch down while reading it. + */ +#define __pick_scalar_type(x, type, otherwise) \ + __builtin_choose_expr(__same_type(x, type), (type)0, otherwise) + +#define __pick_integer_type(x, type, otherwise) \ + __pick_scalar_type(x, unsigned type, \ + __pick_scalar_type(x, signed type, otherwise)) + +#define __unqual_scalar_typeof(x) typeof( \ + __pick_integer_type(x, char, \ + __pick_integer_type(x, short, \ + __pick_integer_type(x, int, \ + __pick_integer_type(x, long, \ + __pick_integer_type(x, long long, x)))))) + /* Is this type a native word size -- useful for atomic operations */ #define __native_word(t) \ (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ -- cgit v1.2.3 From 6aba6ed879b3471903c8ada28ba968a268df6143 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Apr 2020 20:38:41 +0300 Subject: pinctrl: mcp23s08: 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 Link: https://lore.kernel.org/r/20200407173849.43628-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- include/linux/spi/mcp23s08.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/spi/mcp23s08.h (limited to 'include/linux') diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h deleted file mode 100644 index 738a45b435f2..000000000000 --- a/include/linux/spi/mcp23s08.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -struct mcp23s08_platform_data { - /* For mcp23s08, up to 4 slaves (numbered 0..3) can share one SPI - * chipselect, each providing 1 gpio_chip instance with 8 gpios. - * For mpc23s17, up to 8 slaves (numbered 0..7) can share one SPI - * chipselect, each providing 1 gpio_chip (port A + port B) with - * 16 gpios. - */ - u32 spi_present_mask; - - /* "base" is the number of the first GPIO or -1 for dynamic - * assignment. If there are gaps in chip addressing the GPIO - * numbers are sequential .. so for example if only slaves 0 - * and 3 are present, their GPIOs range from base to base+15 - * (or base+31 for s17 variant). - */ - unsigned base; -}; -- cgit v1.2.3 From 980737282232b752bb14dab96d77665c15889c36 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Thu, 2 Apr 2020 11:45:31 +0300 Subject: capabilities: Introduce CAP_PERFMON to kernel and user space Introduce the CAP_PERFMON capability designed to secure system performance monitoring and observability operations so that CAP_PERFMON can assist CAP_SYS_ADMIN capability in its governing role for performance monitoring and observability subsystems. CAP_PERFMON hardens system security and integrity during performance monitoring and observability operations by decreasing attack surface that is available to a CAP_SYS_ADMIN privileged process [2]. Providing the access to system performance monitoring and observability operations under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes the operation more secure. Thus, CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e: 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required) CAP_PERFMON meets the demand to secure system performance monitoring and observability operations for adoption in security sensitive, restricted, multiuser production environments (e.g. HPC clusters, cloud and virtual compute environments), where root or CAP_SYS_ADMIN credentials are not available to mass users of a system, and securely unblocks applicability and scalability of system performance monitoring and observability operations beyond root and CAP_SYS_ADMIN use cases. CAP_PERFMON takes over CAP_SYS_ADMIN credentials related to system performance monitoring and observability operations and balances amount of CAP_SYS_ADMIN credentials following the recommendations in the capabilities man page [1] for CAP_SYS_ADMIN: "Note: this capability is overloaded; see Notes to kernel developers, below." For backward compatibility reasons access to system performance monitoring and observability subsystems of the kernel remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN capability usage for secure system performance monitoring and observability operations is discouraged with respect to the designed CAP_PERFMON capability. Although the software running under CAP_PERFMON can not ensure avoidance of related hardware issues, the software can still mitigate these issues following the official hardware issues mitigation procedure [2]. The bugs in the software itself can be fixed following the standard kernel development process [3] to maintain and harden security of system performance monitoring and observability operations. [1] http://man7.org/linux/man-pages/man7/capabilities.7.html [2] https://www.kernel.org/doc/html/latest/process/embargoed-hardware-issues.html [3] https://www.kernel.org/doc/html/latest/admin-guide/security-bugs.html Signed-off-by: Alexey Budankov Acked-by: James Morris Acked-by: Serge E. Hallyn Acked-by: Song Liu Acked-by: Stephen Smalley Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Igor Lubashev Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: intel-gfx@lists.freedesktop.org Cc: linux-doc@vger.kernel.org Cc: linux-man@vger.kernel.org Cc: linux-security-module@vger.kernel.org Cc: selinux@vger.kernel.org Link: http://lore.kernel.org/lkml/5590d543-82c6-490a-6544-08e6a5517db0@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/capability.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index ecce0f43c73a..027d7e4a853b 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); +static inline bool perfmon_capable(void) +{ + return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); +} /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -- cgit v1.2.3 From 18aa18566218d4a46d940049b835314d2b071cc2 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Thu, 2 Apr 2020 11:46:24 +0300 Subject: perf/core: Open access to the core for CAP_PERFMON privileged process Open access to monitoring of kernel code, CPUs, tracepoints and namespaces data for a CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure. CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required) For backward compatibility reasons the access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability. Signed-off-by: Alexey Budankov Reviewed-by: James Morris Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Igor Lubashev Cc: Jiri Olsa Cc: linux-man@vger.kernel.org Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Serge Hallyn Cc: Song Liu Cc: Stephane Eranian Cc: Thomas Gleixner Cc: intel-gfx@lists.freedesktop.org Cc: linux-doc@vger.kernel.org Cc: linux-security-module@vger.kernel.org Cc: selinux@vger.kernel.org Link: http://lore.kernel.org/lkml/471acaef-bb8a-5ce2-923f-90606b78eef9@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- 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 9c3e7619c929..87e21681759c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1305,7 +1305,7 @@ static inline int perf_is_paranoid(void) static inline int perf_allow_kernel(struct perf_event_attr *attr) { - if (sysctl_perf_event_paranoid > 1 && !capable(CAP_SYS_ADMIN)) + if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); @@ -1313,7 +1313,7 @@ static inline int perf_allow_kernel(struct perf_event_attr *attr) static inline int perf_allow_cpu(struct perf_event_attr *attr) { - if (sysctl_perf_event_paranoid > 0 && !capable(CAP_SYS_ADMIN)) + if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); @@ -1321,7 +1321,7 @@ static inline int perf_allow_cpu(struct perf_event_attr *attr) static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { - if (sysctl_perf_event_paranoid > -1 && !capable(CAP_SYS_ADMIN)) + if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); -- cgit v1.2.3 From 3302363a27fb38a3581921a74aff855f4dcbfe0a Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 1 Apr 2020 12:46:22 -0400 Subject: virtio/test: fix up after IOTLB changes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow building vringh without IOTLB (that's the case for userspace builds, will be useful for CAIF/VOD down the road too). Update for API tweaks. Don't include vringh with userspace builds. Cc: Jason Wang Cc: Eugenio Pérez Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vringh.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h index bd0503ca6f8f..9e2763d7c159 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -14,8 +14,10 @@ #include #include #include +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) #include #include +#endif #include /* virtio_ring with information needed for host access. */ @@ -254,6 +256,8 @@ static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val) return __cpu_to_virtio64(vringh_is_little_endian(vrh), val); } +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) + void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb); int vringh_init_iotlb(struct vringh *vrh, u64 features, @@ -284,4 +288,6 @@ void vringh_notify_disable_iotlb(struct vringh *vrh); int vringh_need_notify_iotlb(struct vringh *vrh); +#endif /* CONFIG_VHOST_IOTLB */ + #endif /* _LINUX_VRINGH_H */ -- cgit v1.2.3 From ab7c1e163b525316a870a494dd4ea196e7a6c455 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 15 Apr 2020 18:45:00 +0200 Subject: firmware: Drop unused pages field from struct firmware The struct firmware contains a page table pointer that was used only internally in the past. Since the actual page tables are referred from struct fw_priv and should be never from struct firmware, we can drop this unused field gracefully. Signed-off-by: Takashi Iwai Acked-by: Luis Chamberlain Link: https://lore.kernel.org/r/20200415164500.28749-1-tiwai@suse.de Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 4bbd0afd91b7..cb3e2c06ed8a 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -12,7 +12,6 @@ struct firmware { size_t size; const u8 *data; - struct page **pages; /* firmware loader private fields */ void *priv; -- cgit v1.2.3 From 425a5070239aac22ed8fa4732eca624293f88546 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 9 Apr 2020 16:26:21 -0400 Subject: vdpa: allow a 32 bit vq alignment get_vq_align returns u16 now, but that's not enough for systems/devices with 64K pages. All callers assign it to a u32 variable anyway, so let's just change the return value type to u32. Reported-by: Arnd Bergmann Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 733acfb7ef84..5453af87a33e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -164,7 +164,7 @@ struct vdpa_config_ops { u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); /* Device ops */ - u16 (*get_vq_align)(struct vdpa_device *vdev); + u32 (*get_vq_align)(struct vdpa_device *vdev); u64 (*get_features)(struct vdpa_device *vdev); int (*set_features)(struct vdpa_device *vdev, u64 features); void (*set_config_cb)(struct vdpa_device *vdev, -- cgit v1.2.3 From 15064e70909cd8cca092ed6dd888bdbd9fefaae3 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 17 Apr 2020 03:17:26 -0400 Subject: virtio: drop vringh.h dependency Most virtio drivers don't depend on vringh, let's not pull that dependency, include it directly as needed. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 15f906e4a748..a493eac08393 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -9,7 +9,6 @@ #include #include #include -#include /** * virtqueue - a queue to register buffers for sending or receiving. -- cgit v1.2.3 From 2b07021a940ce1cdec736ec0cacad6af77717afc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 16 Apr 2020 16:54:48 +0200 Subject: debugfs: remove return value of debugfs_create_u32() No one checks the return value of debugfs_create_u32(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20200416145448.GA1380878@kroah.com Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index a274d95fa66e..63cb3606dea7 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -103,8 +103,8 @@ void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value); void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value); -struct dentry *debugfs_create_u32(const char *name, umode_t mode, - struct dentry *parent, u32 *value); +void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, + u32 *value); void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value); struct dentry *debugfs_create_ulong(const char *name, umode_t mode, @@ -250,12 +250,8 @@ static inline void debugfs_create_u8(const char *name, umode_t mode, static inline void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { } -static inline struct dentry *debugfs_create_u32(const char *name, umode_t mode, - struct dentry *parent, - u32 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_u32(const char *name, umode_t mode, + struct dentry *parent, u32 *value) { } static inline void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { } -- cgit v1.2.3 From 23cf1ee1f1869966b75518c59b5cbda4c6c92450 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 31 Mar 2020 17:02:33 -0400 Subject: svcrdma: Fix leak of svc_rdma_recv_ctxt objects Utilize the xpo_release_rqst transport method to ensure that each rqstp's svc_rdma_recv_ctxt object is released even when the server cannot return a Reply for that rqstp. Without this fix, each RPC whose Reply cannot be sent leaks one svc_rdma_recv_ctxt. This is a 2.5KB structure, a 4KB DMA-mapped Receive buffer, and any pages that might be part of the Reply message. The leak is infrequent unless the network fabric is unreliable or Kerberos is in use, as GSS sequence window overruns, which result in connection loss, are more common on fast transports. Fixes: 3a88092ee319 ("svcrdma: Preserve Receive buffer until svc_rdma_sendto") Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 78fe2ac6dc6c..cbcfbd0521e3 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -170,6 +170,7 @@ extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma); extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); +extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ -- cgit v1.2.3 From 699fed4a2d8e32d77d64928e570d7ffd93a62fdf Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Thu, 16 Apr 2020 01:43:10 -0700 Subject: scsi: qed: Send BW update notifications to the protocol drivers Management firmware (MFW) sends a notification whenever there is a change in the bandwidth values. Add driver support for sending this notification to the upper layer drivers (e.g., qedf). Link: https://lore.kernel.org/r/20200416084314.18851-6-skashyap@marvell.com Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Saurav Kashyap Signed-off-by: Martin K. Petersen --- 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 8f29e0d8a7b3..c4956374a444 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -817,6 +817,7 @@ struct qed_common_cb_ops { void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); + void (*bw_update)(void *dev); }; struct qed_selftest_ops { -- cgit v1.2.3 From c4b4c2a78a9fc0c532c58504e8cb5441224ff1d9 Mon Sep 17 00:00:00 2001 From: Zhiqiang Liu Date: Mon, 13 Apr 2020 13:12:10 +0800 Subject: buffer: remove useless comment and WB_REASON_FREE_MORE_MEM, reason. free_more_memory func has been completely removed in commit bc48f001de12 ("buffer: eliminate the need to call free_more_memory() in __getblk_slow()") So comment and `WB_REASON_FREE_MORE_MEM` reason about free_more_memory are no longer needed. Fixes: bc48f001de12 ("buffer: eliminate the need to call free_more_memory() in __getblk_slow()") Reviewed-by: Jan Kara Signed-off-by: Zhiqiang Liu Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 4fc87dee005a..ee577a83cfe6 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -54,7 +54,6 @@ enum wb_reason { WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, - WB_REASON_FREE_MORE_MEM, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done -- cgit v1.2.3 From 2ce0d7f9766f0e49bb54f149c77bae89464932fb Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 16 Apr 2020 19:24:02 +0100 Subject: x86/asm: Provide a Kconfig symbol for disabling old assembly annotations As x86 was converted to use the modern SYM_ annotations for assembly, ifdefs were added to remove the generic definitions of the old style annotations on x86. Rather than collect a list of architectures in the ifdefs as more architectures are converted over, provide a Kconfig symbol for this and update x86 to use it. Signed-off-by: Mark Brown Signed-off-by: Borislav Petkov Acked-by: Jiri Slaby Link: https://lkml.kernel.org/r/20200416182402.6206-1-broonie@kernel.org --- include/linux/linkage.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 9280209d1f62..d796ec20d114 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -105,7 +105,7 @@ /* === DEPRECATED annotations === */ -#ifndef CONFIG_X86 +#ifndef CONFIG_ARCH_USE_SYM_ANNOTATIONS #ifndef GLOBAL /* deprecated, use SYM_DATA*, SYM_ENTRY, or similar */ #define GLOBAL(name) \ @@ -118,10 +118,10 @@ #define ENTRY(name) \ SYM_FUNC_START(name) #endif -#endif /* CONFIG_X86 */ +#endif /* CONFIG_ARCH_USE_SYM_ANNOTATIONS */ #endif /* LINKER_SCRIPT */ -#ifndef CONFIG_X86 +#ifndef CONFIG_ARCH_USE_SYM_ANNOTATIONS #ifndef WEAK /* deprecated, use SYM_FUNC_START_WEAK* */ #define WEAK(name) \ @@ -143,7 +143,7 @@ #define ENDPROC(name) \ SYM_FUNC_END(name) #endif -#endif /* CONFIG_X86 */ +#endif /* CONFIG_ARCH_USE_SYM_ANNOTATIONS */ /* === generic annotations === */ -- cgit v1.2.3 From 0a368bf00e3a7c57a57efc1bf79b79facb97639c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 16:40:21 -0500 Subject: bio: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index c1c0f9ea4e63..a0ee494a6329 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -319,7 +319,7 @@ struct bio_integrity_payload { struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; - struct bio_vec bip_inline_vecs[0];/* embedded bvec array */ + struct bio_vec bip_inline_vecs[];/* embedded bvec array */ }; #if defined(CONFIG_BLK_DEV_INTEGRITY) -- cgit v1.2.3 From f36aaf8be421099103193c49796a14213d3be315 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 16:43:39 -0500 Subject: blk-mq: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index f389d7c724bd..b45148ba3291 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -173,7 +173,7 @@ struct blk_mq_hw_ctx { * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also * blk_mq_hw_ctx_size(). */ - struct srcu_struct srcu[0]; + struct srcu_struct srcu[]; }; /** -- cgit v1.2.3 From 5a58ec8cfc8621f5bdbd610202f62f817e5da204 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 16:45:36 -0500 Subject: blk_types: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 70254ae11769..31eb92876be7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -198,7 +198,7 @@ struct bio { * double allocations for a small number of bio_vecs. This member * MUST obviously be kept at the very end of the bio. */ - struct bio_vec bi_inline_vecs[0]; + struct bio_vec bi_inline_vecs[]; }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) -- cgit v1.2.3 From e76018cb604ace486de9cf85898c14bb2b47faff Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 16:48:10 -0500 Subject: can: dev: peak_canfd.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/can/dev/peak_canfd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h index 511a37302fea..5fd627e9da19 100644 --- a/include/linux/can/dev/peak_canfd.h +++ b/include/linux/can/dev/peak_canfd.h @@ -189,7 +189,7 @@ struct __packed pucan_rx_msg { u8 client; __le16 flags; __le32 can_id; - u8 d[0]; + u8 d[]; }; /* uCAN error types */ @@ -266,7 +266,7 @@ struct __packed pucan_tx_msg { u8 client; __le16 flags; __le32 can_id; - u8 d[0]; + u8 d[]; }; /* build the cmd opcode_channel field with respect to the correct endianness */ -- cgit v1.2.3 From 1fa0949bede6de2b595da535c3ce69de8e130db2 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 17:03:49 -0500 Subject: digsig.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/digsig.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/digsig.h b/include/linux/digsig.h index 594fc66a395a..2ace69e41088 100644 --- a/include/linux/digsig.h +++ b/include/linux/digsig.h @@ -29,7 +29,7 @@ struct pubkey_hdr { uint32_t timestamp; /* key made, always 0 for now */ uint8_t algo; uint8_t nmpi; - char mpi[0]; + char mpi[]; } __packed; struct signature_hdr { @@ -39,7 +39,7 @@ struct signature_hdr { uint8_t hash; uint8_t keyid[8]; uint8_t nmpi; - char mpi[0]; + char mpi[]; } __packed; #if defined(CONFIG_SIGNATURE) || defined(CONFIG_SIGNATURE_MODULE) -- cgit v1.2.3 From a2008395fe2ebd9cd82f220d034d36cc887f35fe Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 17:17:52 -0500 Subject: dirent.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/dirent.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dirent.h b/include/linux/dirent.h index fc61f3cff72f..99002220cd45 100644 --- a/include/linux/dirent.h +++ b/include/linux/dirent.h @@ -7,7 +7,7 @@ struct linux_dirent64 { s64 d_off; unsigned short d_reclen; unsigned char d_type; - char d_name[0]; + char d_name[]; }; #endif -- cgit v1.2.3 From 192199464d6cccb084356add54b3a48d6dde9f96 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 17:21:19 -0500 Subject: enclosure.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/enclosure.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 564e96f625ff..1c630e2c2756 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -101,7 +101,7 @@ struct enclosure_device { struct device edev; struct enclosure_component_callbacks *cb; int components; - struct enclosure_component component[0]; + struct enclosure_component component[]; }; static inline struct enclosure_device * -- cgit v1.2.3 From beb69f15a095245c5cc62389eea93002b41d2eb9 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 17:23:01 -0500 Subject: energy_model.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/energy_model.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index d249b88a4d5a..ade6486a3382 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -36,7 +36,7 @@ struct em_cap_state { struct em_perf_domain { struct em_cap_state *table; int nr_cap_states; - unsigned long cpus[0]; + unsigned long cpus[]; }; #ifdef CONFIG_ENERGY_MODEL -- cgit v1.2.3 From 5299a11a9378e8c68e3b8e2040f7aa7e401d50b7 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 17:24:53 -0500 Subject: ethtool.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/ethtool.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c1d379bf6ee1..a23b26eab479 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -35,7 +35,7 @@ struct compat_ethtool_rxnfc { compat_u64 data; struct compat_ethtool_rx_flow_spec fs; u32 rule_cnt; - u32 rule_locs[0]; + u32 rule_locs[]; }; #endif /* CONFIG_COMPAT */ @@ -462,7 +462,7 @@ int ethtool_check_ops(const struct ethtool_ops *ops); struct ethtool_rx_flow_rule { struct flow_rule *rule; - unsigned long priv[0]; + unsigned long priv[]; }; struct ethtool_rx_flow_spec_input { -- cgit v1.2.3 From 89f60a5d9bf5a6b9b16dfdd56a91c4a2d7b8830d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 17:43:59 -0500 Subject: genalloc.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/genalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 5b14a0f38124..0bd581003cd5 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -76,7 +76,7 @@ struct gen_pool_chunk { void *owner; /* private data to retrieve at alloc time */ unsigned long start_addr; /* start address of memory chunk */ unsigned long end_addr; /* end address of memory chunk (inclusive) */ - unsigned long bits[0]; /* bitmap for allocating memory chunk */ + unsigned long bits[]; /* bitmap for allocating memory chunk */ }; /* -- cgit v1.2.3 From 0ead33642f1df89699f2e4dda8eea59c326b68f6 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 17:59:00 -0500 Subject: igmp.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 463047d0190b..faa6586a5783 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,7 @@ struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; - __be32 sl_addr[0]; + __be32 sl_addr[]; }; #define IP_SFLSIZE(count) (sizeof(struct ip_sf_socklist) + \ -- cgit v1.2.3 From 1d9e13e8ef05029c61d52ad9a6f48f14771d14b7 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 18:00:04 -0500 Subject: ihex.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/ihex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ihex.h b/include/linux/ihex.h index 98cb5ce0b0a0..b824877e6d1b 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -18,7 +18,7 @@ struct ihex_binrec { __be32 addr; __be16 len; - uint8_t data[0]; + uint8_t data[]; } __attribute__((packed)); static inline uint16_t ihex_binrec_size(const struct ihex_binrec *p) -- cgit v1.2.3 From 7856e9f12f1f59cc6abb25f92b336528d0660ebb Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 18:01:11 -0500 Subject: irq.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/irq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 9315fbb87db3..fa8ad93029ad 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1043,7 +1043,7 @@ struct irq_chip_generic { unsigned long unused; struct irq_domain *domain; struct list_head list; - struct irq_chip_type chip_types[0]; + struct irq_chip_type chip_types[]; }; /** @@ -1079,7 +1079,7 @@ struct irq_domain_chip_generic { unsigned int irq_flags_to_clear; unsigned int irq_flags_to_set; enum irq_gc_flags gc_flags; - struct irq_chip_generic *gc[0]; + struct irq_chip_generic *gc[]; }; /* Generic chip callback functions */ -- cgit v1.2.3 From 312322722872324939f0d0347a6e41807c2d4c56 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 16:58:49 -0500 Subject: lib: cpu_rmap: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/cpu_rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index 02edeafcb2bf..be8aea04d023 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -28,7 +28,7 @@ struct cpu_rmap { struct { u16 index; u16 dist; - } near[0]; + } near[]; }; #define CPU_RMAP_DIST_INF 0xffff -- cgit v1.2.3 From 859b494111b196853fd8c1852c6b57ef33738b50 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 18:32:01 -0500 Subject: list_lru.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/list_lru.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index d5ceb2839a2d..9dcaa3e582c9 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -34,7 +34,7 @@ struct list_lru_one { struct list_lru_memcg { struct rcu_head rcu; /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_one *lru[0]; + struct list_lru_one *lru[]; }; struct list_lru_node { -- cgit v1.2.3 From 307ed94c37f842676d336cf5f2162022f4d7cdc4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 18:36:10 -0500 Subject: memcontrol.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1b4150ff64be..d275c72c4f8e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -106,7 +106,7 @@ struct lruvec_stat { */ struct memcg_shrinker_map { struct rcu_head rcu; - unsigned long map[0]; + unsigned long map[]; }; /* @@ -148,7 +148,7 @@ struct mem_cgroup_threshold_ary { /* Size of entries[] */ unsigned int size; /* Array of thresholds */ - struct mem_cgroup_threshold entries[0]; + struct mem_cgroup_threshold entries[]; }; struct mem_cgroup_thresholds { -- cgit v1.2.3 From 1223f3db71ba7bbcf2e77c7a5d4f440c2a2fa9c3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:07:49 -0500 Subject: platform_data: wilco-ec.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/platform_data/wilco-ec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/wilco-ec.h b/include/linux/platform_data/wilco-ec.h index 25f46a939637..3e268e636b5b 100644 --- a/include/linux/platform_data/wilco-ec.h +++ b/include/linux/platform_data/wilco-ec.h @@ -83,7 +83,7 @@ struct wilco_ec_response { u16 result; u16 data_size; u8 reserved[2]; - u8 data[0]; + u8 data[]; } __packed; /** -- cgit v1.2.3 From 70f1451ec98ee43d2c66d2caa5ae6935ee97f90a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:08:58 -0500 Subject: posix_acl.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/posix_acl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 540595a321a7..90797f1b421d 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -28,7 +28,7 @@ struct posix_acl { refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; - struct posix_acl_entry a_entries[0]; + struct posix_acl_entry a_entries[]; }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ -- cgit v1.2.3 From a1c4b9247ddfb62fe3a23eb53d250382e82fae77 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:12:17 -0500 Subject: rio.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/rio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 317bace5ac64..2cd637268b4f 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -100,7 +100,7 @@ struct rio_switch { u32 port_ok; struct rio_switch_ops *ops; spinlock_t lock; - struct rio_dev *nextdev[0]; + struct rio_dev *nextdev[]; }; /** @@ -201,7 +201,7 @@ struct rio_dev { u8 hopcount; struct rio_dev *prev; atomic_t state; - struct rio_switch rswitch[0]; /* RIO switch info */ + struct rio_switch rswitch[]; /* RIO switch info */ }; #define rio_dev_g(n) list_entry(n, struct rio_dev, global_list) -- cgit v1.2.3 From 9dd8bb5f8c449e87cc0084a118673c6d4182bab2 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:13:20 -0500 Subject: rslib.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/rslib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 5974cedd008c..238bb85243d3 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -54,7 +54,7 @@ struct rs_codec { */ struct rs_control { struct rs_codec *codec; - uint16_t buffers[0]; + uint16_t buffers[]; }; /* General purpose RS codec, 8-bit data width, symbol width 1-15 bit */ -- cgit v1.2.3 From fe946db6ca851a0cd8c2f9c9dd96ef74e051cf2f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:14:37 -0500 Subject: sched: topology.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/sched/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index af9319e4cfb9..95253ad792b0 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -142,7 +142,7 @@ struct sched_domain { * by attaching extra space to the end of the structure, * depending on how many CPUs the kernel has booted up with) */ - unsigned long span[0]; + unsigned long span[]; }; static inline struct cpumask *sched_domain_span(struct sched_domain *sd) -- cgit v1.2.3 From 5c91aa1df00ec4fa283c35e92736392df3137d81 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:22:24 -0500 Subject: skbuff.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3a2ac7072dbb..3000c526f552 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4162,7 +4162,7 @@ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ - char data[0] __aligned(8); + char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(void); -- cgit v1.2.3 From 16c3380f8c2e7ed3d75a30776a89aabf5512027a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:23:10 -0500 Subject: swap.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index b835d8dbea0e..e1bbf7a16b27 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -275,7 +275,7 @@ struct swap_info_struct { */ struct work_struct discard_work; /* discard worker */ struct swap_cluster_list discard_clusters; /* discard clusters list */ - struct plist_node avail_lists[0]; /* + struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the -- cgit v1.2.3 From 4ea19ecf322c2f98ef87fc980b3851625b082ac2 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:25:06 -0500 Subject: ti_wilink_st.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/ti_wilink_st.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index eb6cbdf10e50..44a7f9169ac6 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -295,7 +295,7 @@ struct bts_header { u32 magic; u32 version; u8 future[24]; - u8 actions[0]; + u8 actions[]; } __attribute__ ((packed)); /** @@ -305,7 +305,7 @@ struct bts_header { struct bts_action { u16 type; u16 size; - u8 data[0]; + u8 data[]; } __attribute__ ((packed)); struct bts_action_send { @@ -315,7 +315,7 @@ struct bts_action_send { struct bts_action_wait { u32 msec; u32 size; - u8 data[0]; + u8 data[]; } __attribute__ ((packed)); struct bts_action_delay { -- cgit v1.2.3 From 06ccf63da5d8e90e4dff8b741972a9b279b5bf4c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:38:18 -0500 Subject: tpm_eventlog.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/tpm_eventlog.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 131ea1bad458..c253461b1c4e 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -28,7 +28,7 @@ struct tcpa_event { u32 event_type; u8 pcr_value[20]; /* SHA1 */ u32 event_size; - u8 event_data[0]; + u8 event_data[]; }; enum tcpa_event_types { @@ -55,7 +55,7 @@ enum tcpa_event_types { struct tcpa_pc_event { u32 event_id; u32 event_size; - u8 event_data[0]; + u8 event_data[]; }; enum tcpa_pc_event_ids { @@ -102,7 +102,7 @@ struct tcg_pcr_event { struct tcg_event_field { u32 event_size; - u8 event[0]; + u8 event[]; } __packed; struct tcg_pcr_event2_head { -- cgit v1.2.3 From 43951585e1308b322c8ee31a4aafd08213f5c5d7 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 23 Mar 2020 19:41:14 -0500 Subject: xattr.h: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- include/linux/xattr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 4cf6e11f4a3c..47eaa34f8761 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -73,7 +73,7 @@ struct simple_xattr { struct list_head list; char *name; size_t size; - char value[0]; + char value[]; }; /* -- cgit v1.2.3 From 123aff2a789c3975c2235653939ff00107d6156c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 17 Apr 2020 11:38:02 -0700 Subject: net: phy: broadcom: Add support for BCM53125 internal PHYs BCM53125 has internal Gigabit PHYs which support interrupts as well as statistics, make it possible to configure both of those features with a PHY driver entry. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6462c5447872..7e1d857c8468 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -15,6 +15,7 @@ #define PHY_ID_BCMAC131 0x0143bc70 #define PHY_ID_BCM5481 0x0143bca0 #define PHY_ID_BCM5395 0x0143bcf0 +#define PHY_ID_BCM53125 0x03625f20 #define PHY_ID_BCM54810 0x03625d00 #define PHY_ID_BCM5482 0x0143bcb0 #define PHY_ID_BCM5411 0x00206070 -- cgit v1.2.3 From bb7fc863729b45f0fbcdea991d0465d855ffd831 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 5 Apr 2020 20:57:00 +0300 Subject: net/mlx5: Provide simplified command interfaces Many mlx5_cmd_exec() callers are not interested in the output from that command or have standard in/out structures. Those callers simply allocate those structure on the stack and use sizeof() to provide in/out arguments. In this naive approach provide simplified versions of mlx5_cmd_exec(). Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6f8f79ef829b..1caddfa85c4d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -903,6 +903,19 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); + +#define mlx5_cmd_exec_inout(dev, ifc_cmd, in, out) \ + ({ \ + mlx5_cmd_exec(dev, in, MLX5_ST_SZ_BYTES(ifc_cmd##_in), out, \ + MLX5_ST_SZ_BYTES(ifc_cmd##_out)); \ + }) + +#define mlx5_cmd_exec_in(dev, ifc_cmd, in) \ + ({ \ + u32 _out[MLX5_ST_SZ_DW(ifc_cmd##_out)] = {}; \ + mlx5_cmd_exec_inout(dev, ifc_cmd, in, _out); \ + }) + int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); -- cgit v1.2.3 From 66247fbb280c2a699a8621708c52dae6acd2e4bc Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 3 Apr 2020 11:28:28 +0300 Subject: net/mlx5: Remove Q counter low level helper APIs mlx5 core users are encouraged to use low level API (mlx5_cmd_exec) without the need of helper functions, do this for q counters, remove helper functions and call mlx5_cmd_exec directly from users. This will help reduce the total amount of code and reduction of the mlx5_core symbol table. Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/qp.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index ae63b1ae9004..4d25a3d24182 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -595,10 +595,6 @@ int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, struct mlx5_core_qp *sq); void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev, struct mlx5_core_qp *sq); -int mlx5_core_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id); -int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id); -int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id, - int reset, void *out, int out_size); struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev, int res_num, -- cgit v1.2.3 From 333fbaa0255b8d471fc7ae767ef3a1766c732d6d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sat, 4 Apr 2020 10:40:24 +0300 Subject: net/mlx5: Move QP logic to mlx5_ib The mlx5_core doesn't need any functionality coded in qp.c, so move that file to drivers/infiniband/ be under mlx5_ib responsibility. Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cmd.h | 51 --------------------------------------------- include/linux/mlx5/driver.h | 2 -- include/linux/mlx5/qp.h | 45 --------------------------------------- 3 files changed, 98 deletions(-) delete mode 100644 include/linux/mlx5/cmd.h (limited to 'include/linux') diff --git a/include/linux/mlx5/cmd.h b/include/linux/mlx5/cmd.h deleted file mode 100644 index 68cd08f02c2f..000000000000 --- a/include/linux/mlx5/cmd.h +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#ifndef MLX5_CMD_H -#define MLX5_CMD_H - -#include - -struct manage_pages_layout { - u64 ptr; - u32 reserved; - u16 num_entries; - u16 func_id; -}; - - -struct mlx5_cmd_alloc_uar_imm_out { - u32 rsvd[3]; - u32 uarn; -}; - -#endif /* MLX5_CMD_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1caddfa85c4d..b60e5ab7906b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -541,7 +541,6 @@ struct mlx5_priv { struct mlx5_core_health health; /* start: qp staff */ - struct mlx5_qp_table qp_table; struct dentry *qp_debugfs; struct dentry *eq_debugfs; struct dentry *cq_debugfs; @@ -687,7 +686,6 @@ struct mlx5_core_dev { unsigned long intf_state; struct mlx5_priv priv; struct mlx5_profile *profile; - atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_dm *dm; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 4d25a3d24182..ef127a156a62 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -553,53 +553,8 @@ struct mlx5_qp_context { u8 rsvd1[24]; }; -static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u32 qpn) -{ - return radix_tree_lookup(&dev->priv.qp_table.tree, qpn); -} - -int mlx5_core_create_dct(struct mlx5_core_dev *dev, - struct mlx5_core_dct *qp, - u32 *in, int inlen, - u32 *out, int outlen); -int mlx5_core_create_qp(struct mlx5_core_dev *dev, - struct mlx5_core_qp *qp, - u32 *in, - int inlen); -int mlx5_core_qp_modify(struct mlx5_core_dev *dev, u16 opcode, - u32 opt_param_mask, void *qpc, - struct mlx5_core_qp *qp); -int mlx5_core_destroy_qp(struct mlx5_core_dev *dev, - struct mlx5_core_qp *qp); -int mlx5_core_destroy_dct(struct mlx5_core_dev *dev, - struct mlx5_core_dct *dct); -int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, - u32 *out, int outlen); -int mlx5_core_dct_query(struct mlx5_core_dev *dev, struct mlx5_core_dct *dct, - u32 *out, int outlen); - -int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev, - u32 timeout_usec); - -int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn); -int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn); -void mlx5_init_qp_table(struct mlx5_core_dev *dev); -void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev); int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); -int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, - struct mlx5_core_qp *rq); -void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev, - struct mlx5_core_qp *rq); -int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, - struct mlx5_core_qp *sq); -void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev, - struct mlx5_core_qp *sq); - -struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev, - int res_num, - enum mlx5_res_type res_type); -void mlx5_core_res_put(struct mlx5_core_rsc_common *res); static inline const char *mlx5_qp_type_str(int type) { -- cgit v1.2.3 From 59e9e8e4fe83f68e599b87c06aaf239dcc64887b Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Tue, 14 Jan 2020 05:06:25 +0200 Subject: net/mlx5: Enable SW-defined RoCEv2 UDP source port When this is enabled, UDP source port for RoCEv2 packets are defined by software instead of firmware. Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- 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 69b27c7dfc3e..6fa24918eade 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -74,6 +74,7 @@ enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, + MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, }; enum { @@ -903,7 +904,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { struct mlx5_ifc_roce_cap_bits { u8 roce_apm[0x1]; - u8 reserved_at_1[0x1f]; + u8 reserved_at_1[0x3]; + u8 sw_r_roce_src_udp_port[0x1]; + u8 reserved_at_5[0x1b]; u8 reserved_at_20[0x60]; -- cgit v1.2.3 From 501d3e5dd5bd33a7119f35ee6d365a5787e32a30 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Sat, 21 Mar 2020 11:08:01 +0200 Subject: iio: ad_sigma_delta: remove unused IIO channel macros Now that all channel SigmaDelta IIO channel macros have been localized, remove the generic ones. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 58 ---------------------------------- 1 file changed, 58 deletions(-) (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 5a127c0ed200..a3a838dcf8e4 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -133,62 +133,4 @@ void ad_sd_cleanup_buffer_and_trigger(struct iio_dev *indio_dev); int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); -#define __AD_SD_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift, _extend_name, _type, _mask_all) \ - { \ - .type = (_type), \ - .differential = (_channel2 == -1 ? 0 : 1), \ - .indexed = 1, \ - .channel = (_channel1), \ - .channel2 = (_channel2), \ - .address = (_address), \ - .extend_name = (_extend_name), \ - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ - BIT(IIO_CHAN_INFO_OFFSET), \ - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ - .info_mask_shared_by_all = _mask_all, \ - .scan_index = (_si), \ - .scan_type = { \ - .sign = 'u', \ - .realbits = (_bits), \ - .storagebits = (_storagebits), \ - .shift = (_shift), \ - .endianness = IIO_BE, \ - }, \ - } - -#define AD_SD_DIFF_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_SHORTED_CHANNEL(_si, _channel, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel, _channel, _address, _bits, \ - _storagebits, _shift, "shorted", IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_CHANNEL(_si, _channel, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_CHANNEL_NO_SAMP_FREQ(_si, _channel, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE, 0) - -#define AD_SD_TEMP_CHANNEL(_si, _address, _bits, _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, 0, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_TEMP, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_SUPPLY_CHANNEL(_si, _channel, _address, _bits, _storagebits, \ - _shift) \ - __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, "supply", IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - #endif -- cgit v1.2.3 From 9159c7c06cebfab4bebca0a930b924ad29437638 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Sat, 28 Mar 2020 18:34:21 +0200 Subject: iio: buffer: drop left-over 'stufftoread' field This seems like a left-over from a7348347ba8a4 ("staging:iio: Add polling of events on the ring access chrdev."). Then it was moved into the sca3000 driver around 9dd4694dafbd8 ("iio: staging: sca3000: hide stufftoread logic"), and that one seemed to be the only user of this. Then it eventually was no longer used after 152a6a884ae1 ("staging:iio:accel:sca3000 move to hybrid hard / soft buffer design.") Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer_impl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index a4d2d8061ef6..1e7edf6bed96 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -115,9 +115,6 @@ struct iio_buffer { */ struct attribute_group scan_el_group; - /* @stufftoread: Flag to indicate new data. */ - bool stufftoread; - /* @attrs: Standard attributes of the buffer. */ const struct attribute **attrs; -- cgit v1.2.3 From 641dedd50c488739b56ef0f716988e646295dce4 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 24 Mar 2020 15:46:29 +0200 Subject: include: fpga: adi-axi-common.h: fixup whitespace tab -> space The initial version use a tab between '#define' & 'ADI_AXI_REG_VERSION'. This changes it to space. The change is purely cosmetic. Acked-by: Moritz Fischer Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/fpga/adi-axi-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fpga/adi-axi-common.h b/include/linux/fpga/adi-axi-common.h index 7fc95d5c95bb..ebd4e07ae3d8 100644 --- a/include/linux/fpga/adi-axi-common.h +++ b/include/linux/fpga/adi-axi-common.h @@ -11,7 +11,7 @@ #ifndef ADI_AXI_COMMON_H_ #define ADI_AXI_COMMON_H_ -#define ADI_AXI_REG_VERSION 0x0000 +#define ADI_AXI_REG_VERSION 0x0000 #define ADI_AXI_PCORE_VER(major, minor, patch) \ (((major) << 16) | ((minor) << 8) | (patch)) -- cgit v1.2.3 From 20d5fa48d333670ffbc08d387a80710be91259a0 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 24 Mar 2020 15:46:30 +0200 Subject: include: fpga: adi-axi-common.h: add version helper macros The format for all ADI AXI IP cores is the same. i.e. 'major.minor.patch'. This patch adds the helper macros to be re-used in ADI AXI drivers. Acked-by: Moritz Fischer Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/fpga/adi-axi-common.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/adi-axi-common.h b/include/linux/fpga/adi-axi-common.h index ebd4e07ae3d8..141ac3f251e6 100644 --- a/include/linux/fpga/adi-axi-common.h +++ b/include/linux/fpga/adi-axi-common.h @@ -16,4 +16,8 @@ #define ADI_AXI_PCORE_VER(major, minor, patch) \ (((major) << 16) | ((minor) << 8) | (patch)) +#define ADI_AXI_PCORE_VER_MAJOR(version) (((version) >> 16) & 0xff) +#define ADI_AXI_PCORE_VER_MINOR(version) (((version) >> 8) & 0xff) +#define ADI_AXI_PCORE_VER_PATCH(version) ((version) & 0xff) + #endif /* ADI_AXI_COMMON_H_ */ -- cgit v1.2.3 From e0fcca9fbd99e959855aa1d66c125d696f969e68 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 24 Mar 2020 15:46:32 +0200 Subject: iio: buffer-dmaengine: add dev-managed calls for buffer alloc Currently, when using a 'iio_dmaengine_buffer_alloc()', an matching call to 'iio_dmaengine_buffer_free()' must be made. With this change, this can be avoided by using 'devm_iio_dmaengine_buffer_alloc()'. The buffer will get free'd via the device's devres handling. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dmaengine.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index b3a57444a886..0e503db71289 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -14,4 +14,7 @@ struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, const char *channel); void iio_dmaengine_buffer_free(struct iio_buffer *buffer); +struct iio_buffer *devm_iio_dmaengine_buffer_alloc(struct device *dev, + const char *channel); + #endif -- cgit v1.2.3 From ef04070692a21633ec6a60f80c19b6af44b3cf47 Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Tue, 24 Mar 2020 15:46:33 +0200 Subject: iio: adc: adi-axi-adc: add support for AXI ADC IP core This change adds support for the Analog Devices Generic AXI ADC IP core. The IP core is used for interfacing with analog-to-digital (ADC) converters that require either a high-speed serial interface (JESD204B/C) or a source synchronous parallel interface (LVDS/CMOS). Usually, some other interface type (i.e SPI) is used as a control interface for the actual ADC, while the IP core (controlled via this driver), will interface to the data-lines of the ADC and handle the streaming of data into memory via DMA. Because of this, the AXI ADC driver needs the other SPI-ADC driver to register with it. The SPI-ADC needs to be register via the SPI framework, while the AXI ADC registers as a platform driver. The two cannot be ordered in a hierarchy as both drivers have their own registers, and trying to organize this [in a hierarchy becomes] problematic when trying to map memory/registers. There are some modes where the AXI ADC can operate as standalone ADC, but those will be implemented at a later point in time. DocLink: https://wiki.analog.com/resources/fpga/docs/axi_adc_ip Signed-off-by: Michael Hennerich Signed-off-by: Lars-Peter Clausen Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/adi-axi-adc.h | 64 +++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) create mode 100644 include/linux/iio/adc/adi-axi-adc.h (limited to 'include/linux') diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h new file mode 100644 index 000000000000..c5d48e1c2d36 --- /dev/null +++ b/include/linux/iio/adc/adi-axi-adc.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Analog Devices Generic AXI ADC IP core driver/library + * Link: https://wiki.analog.com/resources/fpga/docs/axi_adc_ip + * + * Copyright 2012-2020 Analog Devices Inc. + */ +#ifndef __ADI_AXI_ADC_H__ +#define __ADI_AXI_ADC_H__ + +struct device; +struct iio_chan_spec; + +/** + * struct adi_axi_adc_chip_info - Chip specific information + * @name Chip name + * @id Chip ID (usually product ID) + * @channels Channel specifications of type @struct axi_adc_chan_spec + * @num_channels Number of @channels + * @scale_table Supported scales by the chip; tuples of 2 ints + * @num_scales Number of scales in the table + * @max_rate Maximum sampling rate supported by the device + */ +struct adi_axi_adc_chip_info { + const char *name; + unsigned int id; + + const struct iio_chan_spec *channels; + unsigned int num_channels; + + const unsigned int (*scale_table)[2]; + int num_scales; + + unsigned long max_rate; +}; + +/** + * struct adi_axi_adc_conv - data of the ADC attached to the AXI ADC + * @chip_info chip info details for the client ADC + * @preenable_setup op to run in the client before enabling the AXI ADC + * @reg_access IIO debugfs_reg_access hook for the client ADC + * @read_raw IIO read_raw hook for the client ADC + * @write_raw IIO write_raw hook for the client ADC + */ +struct adi_axi_adc_conv { + const struct adi_axi_adc_chip_info *chip_info; + + int (*preenable_setup)(struct adi_axi_adc_conv *conv); + int (*reg_access)(struct adi_axi_adc_conv *conv, unsigned int reg, + unsigned int writeval, unsigned int *readval); + int (*read_raw)(struct adi_axi_adc_conv *conv, + struct iio_chan_spec const *chan, + int *val, int *val2, long mask); + int (*write_raw)(struct adi_axi_adc_conv *conv, + struct iio_chan_spec const *chan, + int val, int val2, long mask); +}; + +struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev, + size_t sizeof_priv); + +void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv); + +#endif -- cgit v1.2.3 From c0ae3591d900c0d1a54a86666c2102dd39b3d4f7 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 1 Apr 2020 18:57:06 +0200 Subject: iio: dma-buffer: Cleanup buffer.h/buffer_impl.h includes The IIO DMA buffer is a DMA buffer implementation. As such it should include buffer_impl.h rather than buffer.h. The include to buffer.h in buffer-dma.h should be buffer_impl.h so it has access to the struct iio_buffer definition. The code currently only works because all places that use buffer-dma.h include buffer_impl.h before it. The include to buffer.h in industrialio-buffer-dma.c can be removed since those file does not reference any of buffer consumer functions. Signed-off-by: Lars-Peter Clausen Tested-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 016d8a068353..ff15c61bf319 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -11,7 +11,7 @@ #include #include #include -#include +#include struct iio_dma_buffer_queue; struct iio_dma_buffer_ops; -- cgit v1.2.3 From 2e036804d773e00ea19c6f6b8b7a4b8232c77da1 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 10 Apr 2020 12:36:07 +0300 Subject: iio: buffer: remove 'scan_el_attrs' attribute group from buffer struct This field doesn't seem used. It seems that only 'buffer->attrs' was ever used to extend sysfs attributes for an IIO buffer. Moving forward, it may not make sense to keep it. This patch removes the field and it's initialization code. Since we want to rework IIO buffer, to be able to add more buffers per IIO device, we will merge [somehow] the 'buffer' & 'scan_elements' groups, and we will continue to add the attributes to the 'buffer' group. Removing it here, will also make the rework here a bit smaller, since this code will not be present. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer_impl.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index 1e7edf6bed96..a63dc07b7350 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -94,12 +94,6 @@ struct iio_buffer { unsigned int watermark; /* private: */ - /* - * @scan_el_attrs: Control of scan elements if that scan mode - * control method is used. - */ - struct attribute_group *scan_el_attrs; - /* @scan_timestamp: Does the scan mode include a timestamp. */ bool scan_timestamp; -- cgit v1.2.3 From 83af573e980aafa7edf56a449a6e70f6c8ac9792 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:20 +0200 Subject: iio: core: drop devm_iio_device_unregister() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e975020abaa6..1b2630bc327e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -593,9 +593,6 @@ void iio_device_unregister(struct iio_dev *indio_dev); * calls iio_device_register() internally. Refer to that function for more * information. * - * If an iio_dev registered with this function needs to be unregistered - * separately, devm_iio_device_unregister() must be used. - * * RETURNS: * 0 on success, negative error number on failure. */ @@ -603,7 +600,6 @@ void iio_device_unregister(struct iio_dev *indio_dev); __devm_iio_device_register((dev), (indio_dev), THIS_MODULE); int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev, struct module *this_mod); -void devm_iio_device_unregister(struct device *dev, struct iio_dev *indio_dev); int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp); int iio_device_claim_direct_mode(struct iio_dev *indio_dev); void iio_device_release_direct_mode(struct iio_dev *indio_dev); -- cgit v1.2.3 From 666e4de43d942fbe0d7f1d9dbc993f5b5c81760c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:21 +0200 Subject: iio: core: drop devm_iio_triggered_buffer_cleanup() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/triggered_buffer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/triggered_buffer.h b/include/linux/iio/triggered_buffer.h index 238ad30ce166..e99c91799359 100644 --- a/include/linux/iio/triggered_buffer.h +++ b/include/linux/iio/triggered_buffer.h @@ -18,7 +18,5 @@ int devm_iio_triggered_buffer_setup(struct device *dev, irqreturn_t (*h)(int irq, void *p), irqreturn_t (*thread)(int irq, void *p), const struct iio_buffer_setup_ops *ops); -void devm_iio_triggered_buffer_cleanup(struct device *dev, - struct iio_dev *indio_dev); #endif -- cgit v1.2.3 From 66be392a48f9d5256b4ba582ff06303fe97b5ca2 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:22 +0200 Subject: iio: core: drop devm_iio_device_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. This is the last user of 'devm_iio_device_match()', so it can be removed as well in this patch. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 1b2630bc327e..4c1e320ef7ed 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -688,9 +688,7 @@ static inline struct iio_dev *iio_priv_to_dev(void *priv) } void iio_device_free(struct iio_dev *indio_dev); -int devm_iio_device_match(struct device *dev, void *res, void *data); struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); -void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, const char *fmt, ...); void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); -- cgit v1.2.3 From 83381c9803a00d534f32ab52ed91588601eba43f Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:23 +0200 Subject: iio: core: drop devm_iio_trigger_unregister() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 84995e2967ac..cad8325903f9 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -141,9 +141,6 @@ int __devm_iio_trigger_register(struct device *dev, **/ void iio_trigger_unregister(struct iio_trigger *trig_info); -void devm_iio_trigger_unregister(struct device *dev, - struct iio_trigger *trig_info); - /** * iio_trigger_set_immutable() - set an immutable trigger on destination * -- cgit v1.2.3 From 92b7ed7fe40dd26de62ff8f5aa1605909a14e3ef Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:24 +0200 Subject: iio: core: drop devm_iio_trigger_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 4c1e320ef7ed..d63884a54939 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -691,8 +691,6 @@ void iio_device_free(struct iio_dev *indio_dev); struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, const char *fmt, ...); -void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); - /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3 From fc1f75a0347aecc8b967c8c154564f520d6f4412 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:25 +0200 Subject: iio: inkern: drop devm_iio_channel_release{_all} API calls It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/consumer.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 2bde8c912d4d..c4118dcb8e05 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -63,15 +63,6 @@ void iio_channel_release(struct iio_channel *chan); */ struct iio_channel *devm_iio_channel_get(struct device *dev, const char *consumer_channel); -/** - * devm_iio_channel_release() - Resource managed version of - * iio_channel_release(). - * @dev: Pointer to consumer device for which resource - * is allocared. - * @chan: The channel to be released. - */ -void devm_iio_channel_release(struct device *dev, struct iio_channel *chan); - /** * iio_channel_get_all() - get all channels associated with a client * @dev: Pointer to consumer device. @@ -106,15 +97,6 @@ void iio_channel_release_all(struct iio_channel *chan); */ struct iio_channel *devm_iio_channel_get_all(struct device *dev); -/** - * devm_iio_channel_release_all() - Resource managed version of - * iio_channel_release_all(). - * @dev: Pointer to consumer device for which resource - * is allocared. - * @chan: Array channel to be released. - */ -void devm_iio_channel_release_all(struct device *dev, struct iio_channel *chan); - struct iio_cb_buffer; /** * iio_channel_get_all_cb() - register callback for triggered capture -- cgit v1.2.3 From 05c09e3cee0aa97a51c2eac1a2f453cac0ba5683 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:26 +0200 Subject: iio: buffer: drop devm_iio_hw_consumer_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/hw-consumer.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/hw-consumer.h b/include/linux/iio/hw-consumer.h index 44d48bb1d39f..e8255c2e33bc 100644 --- a/include/linux/iio/hw-consumer.h +++ b/include/linux/iio/hw-consumer.h @@ -14,7 +14,6 @@ struct iio_hw_consumer; struct iio_hw_consumer *iio_hw_consumer_alloc(struct device *dev); void iio_hw_consumer_free(struct iio_hw_consumer *hwc); struct iio_hw_consumer *devm_iio_hw_consumer_alloc(struct device *dev); -void devm_iio_hw_consumer_free(struct device *dev, struct iio_hw_consumer *hwc); int iio_hw_consumer_enable(struct iio_hw_consumer *hwc); void iio_hw_consumer_disable(struct iio_hw_consumer *hwc); -- cgit v1.2.3 From 608d98a2c4a0a72c15fa16ef1542df67afe41fee Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:27 +0200 Subject: iio: buffer: drop devm_iio_kfifo_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/kfifo_buf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index 764659e01b68..1fc1efa7799d 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -9,6 +9,5 @@ struct iio_buffer *iio_kfifo_allocate(void); void iio_kfifo_free(struct iio_buffer *r); struct iio_buffer *devm_iio_kfifo_allocate(struct device *dev); -void devm_iio_kfifo_free(struct device *dev, struct iio_buffer *r); #endif -- cgit v1.2.3 From a07479147be03d2450376ebaff9ea1a0682f25d6 Mon Sep 17 00:00:00 2001 From: Lars Engebretsen Date: Wed, 15 Apr 2020 12:10:43 +0200 Subject: iio: core: remove extra semi-colon from devm_iio_device_register() macro This change removes the semi-colon from the devm_iio_device_register() macro which seems to have been added by accident. Fixes: 63b19547cc3d9 ("iio: Use macro magic to avoid manual assign of driver_module") Signed-off-by: Lars Engebretsen Cc: Reviewed-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index eed58ed2f368..4e7848415c4f 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -600,7 +600,7 @@ void iio_device_unregister(struct iio_dev *indio_dev); * 0 on success, negative error number on failure. */ #define devm_iio_device_register(dev, indio_dev) \ - __devm_iio_device_register((dev), (indio_dev), THIS_MODULE); + __devm_iio_device_register((dev), (indio_dev), THIS_MODULE) int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev, struct module *this_mod); void devm_iio_device_unregister(struct device *dev, struct iio_dev *indio_dev); -- 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 418fd78771220f5e522d02676758ed824c349fd5 Mon Sep 17 00:00:00 2001 From: Clement Leger Date: Fri, 10 Apr 2020 12:24:32 +0200 Subject: remoteproc: add rproc_coredump_set_elf_info This function allows drivers to correctly setup the coredump output elf information. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Clement Leger Link: https://lore.kernel.org/r/20200410102433.2672-2-cleger@kalray.eu Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 9c07d7958c53..0547676479d3 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -518,6 +518,7 @@ struct rproc { struct list_head dump_segments; int nb_vdev; u8 elf_class; + u16 elf_machine; }; /** @@ -622,6 +623,7 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, struct rproc_dump_segment *segment, void *dest), void *priv); +int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine); static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) { -- cgit v1.2.3 From bb15aded5144d36b2a050e1dad415876c0b94234 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 7 Apr 2020 23:56:43 +0300 Subject: mtd: spi-nor: move #define SPINOR_OP_WRDI The write disable (WRDI) opcode is not really specific to the SST flashes (anymore?) -- move the #define to the main opcode group, just before WREN. Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 1e2af0ec1f03..1cc8ed5d59ed 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -20,6 +20,7 @@ */ /* Flash opcodes. */ +#define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_WREN 0x06 /* Write enable */ #define SPINOR_OP_RDSR 0x05 /* Read status register */ #define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */ @@ -80,7 +81,6 @@ /* Used for SST flashes only. */ #define SPINOR_OP_BP 0x02 /* Byte program */ -#define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ /* Used for S3AN flashes only */ -- cgit v1.2.3 From c84dc6e68a1d2464e050d9694be4e4ff49e32bfd Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 14 Apr 2020 17:04:55 -0700 Subject: dma-pool: add additional coherent pools to map to gfp mask The single atomic pool is allocated from the lowest zone possible since it is guaranteed to be applicable for any DMA allocation. Devices may allocate through the DMA API but not have a strict reliance on GFP_DMA memory. Since the atomic pool will be used for all non-blockable allocations, returning all memory from ZONE_DMA may unnecessarily deplete the zone. Provision for multiple atomic pools that will map to the optimal gfp mask of the device. When allocating non-blockable memory, determine the optimal gfp mask of the device and use the appropriate atomic pool. The coherent DMA mask will remain the same between allocation and free and, thus, memory will be freed to the same atomic pool it was allocated from. __dma_atomic_pool_init() will be changed to return struct gen_pool * later once dynamic expansion is added. Signed-off-by: David Rientjes Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 2 ++ include/linux/dma-mapping.h | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 24b8684aa21d..136f984df0d9 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -67,6 +67,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, } u64 dma_direct_get_required_mask(struct device *dev); +gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, + u64 *phys_mask); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 330ad58fbf4d..b43116a6405d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -630,9 +630,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size); -bool dma_in_atomic_pool(void *start, size_t size); -void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags); -bool dma_free_from_pool(void *start, size_t size); +void *dma_alloc_from_pool(struct device *dev, size_t size, + struct page **ret_page, gfp_t flags); +bool dma_free_from_pool(struct device *dev, void *start, size_t size); int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, -- cgit v1.2.3 From e9d7144597b10ff13ff2264c059f7d4a7fbc89ac Mon Sep 17 00:00:00 2001 From: Mark Gross Date: Thu, 16 Apr 2020 17:23:10 +0200 Subject: x86/cpu: Add a steppings field to struct x86_cpu_id Intel uses the same family/model for several CPUs. Sometimes the stepping must be checked to tell them apart. On x86 there can be at most 16 steppings. Add a steppings bitmask to x86_cpu_id and a X86_MATCH_VENDOR_FAMILY_MODEL_STEPPING_FEATURE macro and support for matching against family/model/stepping. [ bp: Massage. ] Signed-off-by: Mark Gross Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Tony Luck Reviewed-by: Josh Poimboeuf --- include/linux/mod_devicetable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4c2ddd0941a7..0754b8d71262 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -663,6 +663,7 @@ struct x86_cpu_id { __u16 vendor; __u16 family; __u16 model; + __u16 steppings; __u16 feature; /* bit index */ kernel_ulong_t driver_data; }; @@ -671,6 +672,7 @@ struct x86_cpu_id { #define X86_VENDOR_ANY 0xffff #define X86_FAMILY_ANY 0 #define X86_MODEL_ANY 0 +#define X86_STEPPING_ANY 0 #define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */ /* -- cgit v1.2.3 From 02094d54870590a667f822e4032bbd1ba6c48d00 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 8 Apr 2020 19:09:02 +0300 Subject: software node: Allow register and unregister software node groups Sometimes it's more convenient to register a set of individual software nodes grouped together. Add couple of functions for that. Signed-off-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Tested-by: Hans de Goede Reviewed-by: Heikki Krogerus --- include/linux/property.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index d86de017c689..c7b5f3db36aa 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -440,6 +440,9 @@ software_node_find_by_name(const struct software_node *parent, int software_node_register_nodes(const struct software_node *nodes); void software_node_unregister_nodes(const struct software_node *nodes); +int software_node_register_node_group(const struct software_node **node_group); +void software_node_unregister_node_group(const struct software_node **node_group); + int software_node_register(const struct software_node *node); int software_node_notify(struct device *dev, unsigned long action); -- cgit v1.2.3 From 2a6ba3f794e892c37d67b8ebb19487ce105eabc2 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Fri, 27 Mar 2020 10:59:47 +0530 Subject: tee: enable support to register kernel memory Enable support to register kernel memory reference with TEE. This change will allow TEE bus drivers to register memory references. Signed-off-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 1412e9cc79ce..e96154d92b1e 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -26,6 +26,7 @@ #define TEE_SHM_REGISTER BIT(3) /* Memory registered in secure world */ #define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ #define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ +#define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ struct device; struct tee_device; -- cgit v1.2.3 From e44ab4e14d6f4c448ae555132090c1a116b19e5c Mon Sep 17 00:00:00 2001 From: Dejin Zheng Date: Mon, 20 Apr 2020 21:46:46 +0800 Subject: regmap: Simplify implementation of the regmap_read_poll_timeout() macro Simplify the implementation of the macro regmap_read_poll_timeout() by using the macro read_poll_timeout(). Signed-off-by: Dejin Zheng Link: https://lore.kernel.org/r/20200420134647.9121-2-zhengdejin5@gmail.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 25 +++++-------------------- 1 file changed, 5 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 91420af1c30d..b50e930a9c18 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -17,6 +17,7 @@ #include #include #include +#include struct module; struct clk; @@ -130,26 +131,10 @@ struct reg_sequence { */ #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ ({ \ - u64 __timeout_us = (timeout_us); \ - unsigned long __sleep_us = (sleep_us); \ - ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ - int __ret; \ - might_sleep_if(__sleep_us); \ - 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 (__sleep_us) \ - usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ - } \ - __ret ?: ((cond) ? 0 : -ETIMEDOUT); \ + int __ret, __tmp; \ + __tmp = read_poll_timeout(regmap_read, __ret, __ret || (cond), \ + sleep_us, timeout_us, false, (map), (addr), &(val)); \ + __ret ?: __tmp; \ }) /** -- cgit v1.2.3 From 148c01d176237115d9c2805f6d29c0b6a72fbd10 Mon Sep 17 00:00:00 2001 From: Dejin Zheng Date: Mon, 20 Apr 2020 21:46:47 +0800 Subject: regmap: Simplify implementation of the regmap_field_read_poll_timeout() macro Simplify the implementation of the macro regmap_field_read_poll_timeout() by using the macro read_poll_timeout(). Signed-off-by: Dejin Zheng Link: https://lore.kernel.org/r/20200420134647.9121-3-zhengdejin5@gmail.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 23 ++++------------------- 1 file changed, 4 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b50e930a9c18..4c4fbe4d41a6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -202,25 +202,10 @@ struct reg_sequence { */ #define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \ ({ \ - u64 __timeout_us = (timeout_us); \ - unsigned long __sleep_us = (sleep_us); \ - ktime_t timeout = ktime_add_us(ktime_get(), __timeout_us); \ - int pollret; \ - might_sleep_if(__sleep_us); \ - for (;;) { \ - pollret = regmap_field_read((field), &(val)); \ - if (pollret) \ - break; \ - if (cond) \ - break; \ - if (__timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ - pollret = regmap_field_read((field), &(val)); \ - break; \ - } \ - if (__sleep_us) \ - usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ - } \ - pollret ?: ((cond) ? 0 : -ETIMEDOUT); \ + int __ret, __tmp; \ + __tmp = read_poll_timeout(regmap_field_read, __ret, __ret || (cond), \ + sleep_us, timeout_us, false, (field), &(val)); \ + __ret ?: __tmp; \ }) #ifdef CONFIG_REGMAP -- cgit v1.2.3 From b9151e7bca82a17ff7aa442a168e0f924a07443c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 20 Apr 2020 09:24:52 -0700 Subject: blk-mq: Add blk_mq_delay_run_hw_queues() API call We have: * blk_mq_run_hw_queue() * blk_mq_delay_run_hw_queue() * blk_mq_run_hw_queues() ...but not blk_mq_delay_run_hw_queues(), presumably because nobody needed it before now. Since we need it for a later patch in this series, add it. Signed-off-by: Douglas Anderson Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b45148ba3291..51fbf6f76593 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -508,6 +508,7 @@ void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); +void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); -- cgit v1.2.3 From d46430bf5a2298f55e20f59a90ebe3545d273b2f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:28:57 +0200 Subject: block: remove the disk argument from blk_drop_partitions The gendisk can be trivially deducted from the block_device. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9b3fffdf4011..058d895544c7 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -339,7 +339,7 @@ extern dev_t blk_lookup_devt(const char *name, int partno); int bdev_disk_changed(struct block_device *bdev, bool invalidate); int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); -int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev); +int blk_drop_partitions(struct block_device *bdev); extern void printk_all_partitions(void); extern struct gendisk *__alloc_disk_node(int minors, int node_id); -- cgit v1.2.3 From 02d33b6771fcc63c98cb48cad0cd8b8fb033837a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:29:01 +0200 Subject: block: mark invalidate_partition static invalidate_partition is only used in genhd.c, so mark it static. Also drop the return value given that is is always ignored. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- 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 4f6f59b4f22a..2b4e9f86b151 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2723,7 +2723,6 @@ extern bool is_bad_inode(struct inode *); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); extern int __invalidate_device(struct block_device *, bool); -extern int invalidate_partition(struct gendisk *, int); #endif unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); -- cgit v1.2.3 From 9bc5c397d8384b50c8202f4400bf2f87fe8291d9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:29:02 +0200 Subject: block: fold bdev_unhash_inode into invalidate_partition invalidate_partition and bdev_unhash_inode are always paired, and invalidate_partition already does an icache lookup for the block device inode. Piggy back on that to remove the inode from the hash. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- 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 2b4e9f86b151..1a95e5158811 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2581,7 +2581,6 @@ extern struct kmem_cache *names_cachep; #ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern void unregister_blkdev(unsigned int, const char *); -extern void bdev_unhash_inode(dev_t dev); extern struct block_device *bdget(dev_t); extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); -- cgit v1.2.3 From eec517cdb4810b3843eb7707971de3164088bff1 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 20 Apr 2020 00:11:50 +0200 Subject: net: Add IF_OPER_TESTING RFC 2863 defines the operational state testing. Add support for this state, both as a IF_LINK_MODE_ and __LINK_STATE_. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 130a668049ab..0750b54b3765 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -288,6 +288,7 @@ enum netdev_state_t { __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, + __LINK_STATE_TESTING, }; @@ -3907,6 +3908,46 @@ static inline bool netif_dormant(const struct net_device *dev) } +/** + * netif_testing_on - mark device as under test. + * @dev: network device + * + * Mark device as under test (as per RFC2863). + * + * The testing state indicates that some test(s) must be performed on + * the interface. After completion, of the test, the interface state + * will change to up, dormant, or down, as appropriate. + */ +static inline void netif_testing_on(struct net_device *dev) +{ + if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing_off - set device as not under test. + * @dev: network device + * + * Device is not in testing state. + */ +static inline void netif_testing_off(struct net_device *dev) +{ + if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing - test if device is under test + * @dev: network device + * + * Check if device is under test + */ +static inline bool netif_testing(const struct net_device *dev) +{ + return test_bit(__LINK_STATE_TESTING, &dev->state); +} + + /** * netif_oper_up - test if device is operational * @dev: network device -- cgit v1.2.3 From 1dbd51d0a71a561056579e2d4f406e5ce5343af0 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Tue, 10 Dec 2019 13:20:55 +0200 Subject: net/mlx5: Refactor mlx5_accel_esp_create_hw_context parameter list Currently the FPGA IPsec is the only hw implementation of the IPsec acceleration api, and so the mlx5_accel_esp_create_hw_context was wrongly made to suit this HW api, among other in its parameter list and some of its parameter endianness. This implementation might not be suitable for different HW. Refactor by group and pass all function arguments of mlx5_accel_esp_create_hw_context in common mlx5_accel_esp_xfrm_attrs struct field of mlx5_accel_esp_xfrm struct and correct the endianness according to the HW being called. Signed-off-by: Raed Salem Reviewed-by: Boris Pismenny Reviewed-by: Huy Nguyen Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 5613e677a5f9..b919d143a9a6 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -92,6 +92,18 @@ struct mlx5_accel_esp_xfrm_attrs { union { struct aes_gcm_keymat aes_gcm; } keymat; + + union { + __be32 a4; + __be32 a6[4]; + } saddr; + + union { + __be32 a4; + __be32 a6[4]; + } daddr; + + u8 is_ipv6; }; struct mlx5_accel_esp_xfrm { -- cgit v1.2.3 From 72ef5e52b3f74c0be47b20f5c434b7ecc830cf40 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:35 +0200 Subject: docs: fix broken references to text files Several references got broken due to txt to ReST conversion. Several of them can be automatically fixed with: scripts/documentation-file-ref-check --fix Reviewed-by: Mathieu Poirier # hwtracing/coresight/Kconfig Reviewed-by: Paul E. McKenney # memory-barrier.txt Acked-by: Alex Shi # translations/zh_CN Acked-by: Federico Vaga # translations/it_IT Acked-by: Marc Zyngier # kvm/arm64 Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/6f919ddb83a33b5f2a63b6b5f0575737bb2b36aa.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..1f2850465f59 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1219,7 +1219,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages); * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS * scheme). * - * For more information, please see Documentation/vm/pin_user_pages.rst. + * For more information, please see Documentation/core-api/pin_user_pages.rst. * * @page: pointer to page to be queried. * @Return: True, if it is likely that the page has been "dma-pinned". @@ -2834,7 +2834,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * - * Please see Documentation/vm/pin_user_pages.rst for more information. + * Please see Documentation/core-api/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 0c1bc6b84525b96aa9fb8f6fbe8c5cb26a5c0ead Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:37 +0200 Subject: docs: filesystems: fix renamed references Some filesystem references got broken by a previous patch series I submitted. Address those. Signed-off-by: Mauro Carvalho Chehab Acked-by: David Sterba # fs/affs/Kconfig Link: https://lore.kernel.org/r/57318c53008dbda7f6f4a5a9e5787f4d37e8565a.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/kobject.h | 2 +- include/linux/kobject_ns.h | 2 +- include/linux/relay.h | 2 +- include/linux/sysfs.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index e2ca0a292e21..fc8d83e91379 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -7,7 +7,7 @@ * Copyright (c) 2006-2008 Greg Kroah-Hartman * Copyright (c) 2006-2008 Novell Inc. * - * Please read Documentation/kobject.txt before using the kobject + * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index 069aa2ebef90..2b5b64256cf4 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -8,7 +8,7 @@ * * Split from kobject.h by David Howells (dhowells@redhat.com) * - * Please read Documentation/kobject.txt before using the kobject + * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ diff --git a/include/linux/relay.h b/include/linux/relay.h index c759f96e39c1..e13a333e7c37 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -141,7 +141,7 @@ struct rchan_callbacks * cause relay_open() to create a single global buffer rather * than the default set of per-cpu buffers. * - * See Documentation/filesystems/relay.txt for more info. + * See Documentation/filesystems/relay.rst for more info. */ struct dentry *(*create_buf_file)(const char *filename, struct dentry *parent, diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 80bb865b3a33..86067dbe7745 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -7,7 +7,7 @@ * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo * - * Please see Documentation/filesystems/sysfs.txt for more information. + * Please see Documentation/filesystems/sysfs.rst for more information. */ #ifndef _SYSFS_H_ -- cgit v1.2.3 From ad89c8852fde7ab0c4007f5b753517cf508d12be Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:44 +0200 Subject: docs: spi: spi.h: fix a doc building warning We need to add a blank line to avoid this warning: ./include/linux/spi/spi.h:401: WARNING: Unexpected indentation. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/1c701b3ac903dc0bc304dca958fbdee53bd38dc3.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 38286de779e3..aac57b5b7c21 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -394,6 +394,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * for example doing DMA mapping. Called from threaded * context. * @transfer_one: transfer a single spi_transfer. + * * - return 0 if the transfer is finished, * - return 1 if the transfer is still in progress. When * the driver is finished with this transfer it must -- cgit v1.2.3 From 4951d27b099bd24f87a093f67d91618742bd3a65 Mon Sep 17 00:00:00 2001 From: Bumsik Kim Date: Fri, 3 Apr 2020 12:15:07 +0900 Subject: watchdog: clarify that stop() is optional The commit d0684c8a9354 ("watchdog: Make stop function optional") made stop function not mandatory, but the comments and the doc weren't reflected. Fix it to clarify. Signed-off-by: Bumsik Kim Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20200403031507.63487-1-k.bumsik@gmail.com Signed-off-by: Jonathan Corbet --- include/linux/watchdog.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 417d9f37077a..1464ce6ffa31 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -37,15 +37,15 @@ struct watchdog_governor; * * The watchdog_ops structure contains a list of low-level operations * that control a watchdog device. It also contains the module that owns - * these operations. The start and stop function are mandatory, all other + * these operations. The start function is mandatory, all other * functions are optional. */ struct watchdog_ops { struct module *owner; /* mandatory operations */ int (*start)(struct watchdog_device *); - int (*stop)(struct watchdog_device *); /* optional operations */ + int (*stop)(struct watchdog_device *); int (*ping)(struct watchdog_device *); unsigned int (*status)(struct watchdog_device *); int (*set_timeout)(struct watchdog_device *, unsigned int); -- cgit v1.2.3 From 90c165f0de3adad4719e65ab0c31d59edf5bd481 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo?= Date: Fri, 3 Apr 2020 11:36:17 +0200 Subject: docs: pr_*() kerneldocs and basic printk docs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add kerneldocs comments to the pr_*() macros in printk.h. Add a new rst node in the core-api manual describing the basic usage of printk and the related macro aliases. Signed-off-by: Ricardo Cañuelo Link: https://lore.kernel.org/r/20200403093617.18003-1-ricardo.canuelo@collabora.com Signed-off-by: Jonathan Corbet --- include/linux/printk.h | 112 +++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 100 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index e061635e0409..ccea5d4a509e 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -279,39 +279,116 @@ static inline void printk_safe_flush_on_panic(void) extern int kptr_restrict; +/** + * pr_fmt - used by the pr_*() macros to generate the printk format string + * @fmt: format string passed from a pr_*() macro + * + * This macro can be used to generate a unified format string for pr_*() + * macros. A common use is to prefix all pr_*() messages in a file with a common + * string. For example, defining this at the top of a source file: + * + * #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + * + * would prefix all pr_info, pr_emerg... messages in the file with the module + * name. + */ #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif -/* - * These can be used to print at the various log levels. - * All of these will print unconditionally, although note that pr_debug() - * and other debug macros are compiled out unless either DEBUG is defined - * or CONFIG_DYNAMIC_DEBUG is set. +/** + * pr_emerg - Print an emergency-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_EMERG loglevel. It uses pr_fmt() to + * generate the format string. */ #define pr_emerg(fmt, ...) \ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_alert - Print an alert-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_ALERT loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_alert(fmt, ...) \ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_crit - Print a critical-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_CRIT loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_crit(fmt, ...) \ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_err - Print an error-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_ERR loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_warn - Print a warning-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_WARNING loglevel. It uses pr_fmt() + * to generate the format string. + */ #define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_notice - Print a notice-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_NOTICE loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_info - Print an info-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_INFO loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_info(fmt, ...) \ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -/* - * Like KERN_CONT, pr_cont() should only be used when continuing - * a line with no newline ('\n') enclosed. Otherwise it defaults - * back to KERN_DEFAULT. + +/** + * pr_cont - Continues a previous log message in the same line. + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_CONT loglevel. It should only be + * used when continuing a log message with no newline ('\n') enclosed. Otherwise + * it defaults back to KERN_DEFAULT loglevel. */ #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) -/* pr_devel() should produce zero code unless DEBUG is defined */ +/** + * pr_devel - Print a debug-level message conditionally + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_DEBUG loglevel if DEBUG is + * defined. Otherwise it does nothing. + * + * It uses pr_fmt() to generate the format string. + */ #ifdef DEBUG #define pr_devel(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) @@ -325,8 +402,19 @@ extern int kptr_restrict; #if defined(CONFIG_DYNAMIC_DEBUG) #include -/* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */ -#define pr_debug(fmt, ...) \ +/** + * pr_debug - Print a debug-level message conditionally + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to dynamic_pr_debug() if CONFIG_DYNAMIC_DEBUG is + * set. Otherwise, if DEBUG is defined, it's equivalent to a printk with + * KERN_DEBUG loglevel. If DEBUG is not defined it does nothing. + * + * It uses pr_fmt() to generate the format string (dynamic_pr_debug() uses + * pr_fmt() internally). + */ +#define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) #elif defined(DEBUG) #define pr_debug(fmt, ...) \ -- cgit v1.2.3 From 1487deda19c82d30d1867277e89bc2d515b9d2d4 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Mon, 20 Apr 2020 17:15:58 -0600 Subject: remoteproc: Use kstrdup_const() rather than kstrdup() For cases where @firmware is declared "const char *", use function kstrdup_const() to avoid needlessly creating another copy on the heap. Suggested-by: Bjorn Andersson Signed-off-by: Mathieu Poirier Reviewed-by: Alex Elder Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200420231601.16781-2-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 0547676479d3..800b4f09dc98 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -489,7 +489,7 @@ struct rproc { struct list_head node; struct iommu_domain *domain; const char *name; - char *firmware; + const char *firmware; void *priv; struct rproc_ops *ops; struct device dev; -- cgit v1.2.3 From 305ac5a766b1d0dd8a4052c8c92e5464888eaa10 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 17 Apr 2020 19:00:37 +0200 Subject: remoteproc: Add device-managed variants of rproc_alloc/rproc_add Add API functions devm_rproc_alloc() and devm_rproc_add(), which behave like rproc_alloc() and rproc_add() respectively, but register their respective cleanup function to be called on driver detach. Reviewed-by: Bjorn Andersson Signed-off-by: Paul Cercueil Link: https://lore.kernel.org/r/20200417170040.174319-2-paul@crapouillou.net Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 800b4f09dc98..ac4082f12e8b 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -600,6 +600,11 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +struct rproc *devm_rproc_alloc(struct device *dev, const char *name, + const struct rproc_ops *ops, + const char *firmware, int len); +int devm_rproc_add(struct device *dev, struct rproc *rproc); + void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); struct rproc_mem_entry * -- cgit v1.2.3 From 812756a82ea51e3c7ff7ba5e6fa3f34345234bc7 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Tue, 14 Apr 2020 17:56:25 +0200 Subject: kvm_host: unify VM_STAT and VCPU_STAT definitions in a single place The macros VM_STAT and VCPU_STAT are redundantly implemented in multiple files, each used by a different architecure to initialize the debugfs entries for statistics. Since they all have the same purpose, they can be unified in a single common definition in include/linux/kvm_host.h Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20200414155625.20559-1-eesposit@redhat.com> Acked-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01276e3d01b9..658215f6102c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1130,6 +1130,11 @@ struct kvm_stats_debugfs_item { #define KVM_DBGFS_GET_MODE(dbgfs_item) \ ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) +#define VM_STAT(n, x, ...) \ + { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } +#define VCPU_STAT(n, x, ...) \ + { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; -- cgit v1.2.3 From c36b71503a2268206ebeda6697094ffb4e7e94c2 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 16 Apr 2020 09:48:07 -0400 Subject: KVM: x86/mmu: Avoid an extra memslot lookup in try_async_pf() for L2 Create a new function kvm_is_visible_memslot() and use it from kvm_is_visible_gfn(); use the new function in try_async_pf() too, to avoid an extra memslot lookup. Opportunistically squish a multi-line comment into a single-line comment. Note, the end result, KVM_PFN_NOSLOT, is unchanged. Cc: Jim Mattson Cc: Rick Edgecombe Suggested-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 658215f6102c..7d4f1eb70274 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1357,6 +1357,12 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ +static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) +{ + return (memslot && memslot->id < KVM_USER_MEM_SLOTS && + !(memslot->flags & KVM_MEMSLOT_INVALID)); +} + struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); -- cgit v1.2.3 From 1b94f6f81007b4afaea3480ec018bc9236148961 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Thu, 16 Apr 2020 13:10:57 +0800 Subject: KVM: Remove redundant argument to kvm_arch_vcpu_ioctl_run In earlier versions of kvm, 'kvm_run' was an independent structure and was not included in the vcpu structure. At present, 'kvm_run' is already included in the vcpu structure, so the parameter 'kvm_run' is redundant. This patch simplifies the function definition, removes the extra 'kvm_run' parameter, and extracts it from the 'kvm_vcpu' structure if necessary. Signed-off-by: Tianjia Zhang Message-Id: <20200416051057.26526-1-tianjia.zhang@linux.alibaba.com> 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 7d4f1eb70274..5285a5568208 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -866,7 +866,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); int kvm_arch_init(void *opaque); void kvm_arch_exit(void); -- cgit v1.2.3 From 14bbe3e33710be52f21d61253a94c5f44a696d02 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 1 Apr 2020 10:33:43 -0700 Subject: docs: Add rbtree documentation to the core-api This file is close enough to being in rst format that I didn't feel the need to alter it in any way. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Michel Lespinasse Link: https://lore.kernel.org/r/20200401173343.17472-1-willy@infradead.org Signed-off-by: Jonathan Corbet --- include/linux/rbtree.h | 2 +- include/linux/rbtree_augmented.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 1fd61a9af45c..d7db17996322 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -11,7 +11,7 @@ I know it's not the cleaner way, but in C (not in C++) to get performances and genericity... - See Documentation/rbtree.txt for documentation and samples. + See Documentation/core-api/rbtree.rst for documentation and samples. */ #ifndef _LINUX_RBTREE_H diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 724b0d036b57..d1c53e9d8c75 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -21,7 +21,7 @@ * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * - * See Documentation/rbtree.txt for documentation and samples. + * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { -- cgit v1.2.3 From bdebd6a2831b6fab69eb85cee74a8ba77f1a1cc2 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 20 Apr 2020 18:14:11 -0700 Subject: vmalloc: fix remap_vmalloc_range() bounds checks remap_vmalloc_range() has had various issues with the bounds checks it promises to perform ("This function checks that addr is a valid vmalloc'ed area, and that it is big enough to cover the vma") over time, e.g.: - not detecting pgoff< Signed-off-by: Andrew Morton Cc: stable@vger.kernel.org Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Martin KaFai Lau Cc: Song Liu Cc: Yonghong Song Cc: Andrii Nakryiko Cc: John Fastabend Cc: KP Singh Link: http://lkml.kernel.org/r/20200415222312.236431-1-jannh@google.com Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0507a162ccd0..a95d3cc74d79 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -137,7 +137,7 @@ extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, - unsigned long size); + unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -- cgit v1.2.3 From 51161bfc66a68d21f13d15a689b3ea7980457790 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 19 Apr 2020 18:55:06 +0300 Subject: kernel/module: Hide vermagic header file from general use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit VERMAGIC* definitions are not supposed to be used by the drivers, see this [1] bug report, so introduce special define to guard inclusion of this header file and define it in kernel/modules.h and in internal script that generates *.mod.c files. In-tree module build: ➜ kernel git:(vermagic) ✗ make clean ➜ kernel git:(vermagic) ✗ make M=drivers/infiniband/hw/mlx5 ➜ kernel git:(vermagic) ✗ modinfo drivers/infiniband/hw/mlx5/mlx5_ib.ko filename: /images/leonro/src/kernel/drivers/infiniband/hw/mlx5/mlx5_ib.ko <...> vermagic: 5.6.0+ SMP mod_unload modversions Out-of-tree module build: ➜ mlx5 make -C /images/leonro/src/kernel clean M=/tmp/mlx5 ➜ mlx5 make -C /images/leonro/src/kernel M=/tmp/mlx5 ➜ mlx5 modinfo /tmp/mlx5/mlx5_ib.ko filename: /tmp/mlx5/mlx5_ib.ko <...> vermagic: 5.6.0+ SMP mod_unload modversions [1] https://lore.kernel.org/lkml/20200411155623.GA22175@zn.tnic Reported-by: Borislav Petkov Acked-by: Borislav Petkov Acked-by: Jessica Yu Co-developed-by: Masahiro Yamada Signed-off-by: Masahiro Yamada Signed-off-by: Leon Romanovsky Signed-off-by: David S. Miller --- include/linux/vermagic.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 9aced11e9000..7768d20ada39 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef INCLUDE_VERMAGIC +#error "This header can be included from kernel/module.c or *.mod.c only" +#endif + #include /* Simply sanity version stamp for modules. */ -- cgit v1.2.3 From b9663b7ca6ff780555108394c9c1b409f63b99a7 Mon Sep 17 00:00:00 2001 From: Voon Weifeng Date: Mon, 20 Apr 2020 23:42:52 +0800 Subject: net: stmmac: Enable SERDES power up/down sequence This patch is to enable Intel SERDES power up/down sequence. The SERDES converts 8/10 bits data to SGMII signal. Below is an example of HW configuration for SGMII mode. The SERDES is located in the PHY IF in the diagram below. <-----------------GBE Controller---------->|<--External PHY chip--> +----------+ +----+ +---+ +----------+ | EQoS | <-GMII->| DW | < ------ > |PHY| <-SGMII-> | External | | MAC | |xPCS| |IF | | PHY | +----------+ +----+ +---+ +----------+ ^ ^ ^ ^ | | | | +---------------------MDIO-------------------------+ PHY IF configuration and status registers are accessible through mdio address 0x15 which is defined as mdio_adhoc_addr. During D0, The driver will need to power up PHY IF by changing the power state to P0. Likewise, for D3, the driver sets PHY IF power state to P3. Signed-off-by: Voon Weifeng Signed-off-by: Ong Boon Leong Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index fbafb353e9be..bd964c31d333 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -177,6 +177,8 @@ struct plat_stmmacenet_data { struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*fix_mac_speed)(void *priv, unsigned int speed); + int (*serdes_powerup)(struct net_device *ndev, void *priv); + void (*serdes_powerdown)(struct net_device *ndev, void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); struct mac_device_info *(*setup)(void *priv); -- cgit v1.2.3 From 01b2bafe57b19d9119413f138765ef57990921ce Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 14 Apr 2020 12:10:50 -0300 Subject: pnp: Use list_for_each_entry() instead of open coding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Aside from good practice, this avoids a warning from gcc 10: ./include/linux/kernel.h:997:3: warning: array subscript -31 is outside array bounds of ‘struct list_head[1]’ [-Warray-bounds] 997 | ((type *)(__mptr - offsetof(type, member))); }) | ~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/list.h:493:2: note: in expansion of macro ‘container_of’ 493 | container_of(ptr, type, member) | ^~~~~~~~~~~~ ./include/linux/pnp.h:275:30: note: in expansion of macro ‘list_entry’ 275 | #define global_to_pnp_dev(n) list_entry(n, struct pnp_dev, global_list) | ^~~~~~~~~~ ./include/linux/pnp.h:281:11: note: in expansion of macro ‘global_to_pnp_dev’ 281 | (dev) != global_to_pnp_dev(&pnp_global); \ | ^~~~~~~~~~~~~~~~~ arch/x86/kernel/rtc.c:189:2: note: in expansion of macro ‘pnp_for_each_dev’ 189 | pnp_for_each_dev(dev) { Because the common code doesn't cast the starting list_head to the containing struct. Signed-off-by: Jason Gunthorpe [ rjw: Whitespace adjustments ] Signed-off-by: Rafael J. Wysocki --- include/linux/pnp.h | 29 +++++++++-------------------- 1 file changed, 9 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pnp.h b/include/linux/pnp.h index b18dca67253d..c2a7cfbca713 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -220,10 +220,8 @@ struct pnp_card { #define global_to_pnp_card(n) list_entry(n, struct pnp_card, global_list) #define protocol_to_pnp_card(n) list_entry(n, struct pnp_card, protocol_list) #define to_pnp_card(n) container_of(n, struct pnp_card, dev) -#define pnp_for_each_card(card) \ - for((card) = global_to_pnp_card(pnp_cards.next); \ - (card) != global_to_pnp_card(&pnp_cards); \ - (card) = global_to_pnp_card((card)->global_list.next)) +#define pnp_for_each_card(card) \ + list_for_each_entry(card, &pnp_cards, global_list) struct pnp_card_link { struct pnp_card *card; @@ -276,14 +274,9 @@ struct pnp_dev { #define card_to_pnp_dev(n) list_entry(n, struct pnp_dev, card_list) #define protocol_to_pnp_dev(n) list_entry(n, struct pnp_dev, protocol_list) #define to_pnp_dev(n) container_of(n, struct pnp_dev, dev) -#define pnp_for_each_dev(dev) \ - for((dev) = global_to_pnp_dev(pnp_global.next); \ - (dev) != global_to_pnp_dev(&pnp_global); \ - (dev) = global_to_pnp_dev((dev)->global_list.next)) -#define card_for_each_dev(card,dev) \ - for((dev) = card_to_pnp_dev((card)->devices.next); \ - (dev) != card_to_pnp_dev(&(card)->devices); \ - (dev) = card_to_pnp_dev((dev)->card_list.next)) +#define pnp_for_each_dev(dev) list_for_each_entry(dev, &pnp_global, global_list) +#define card_for_each_dev(card, dev) \ + list_for_each_entry(dev, &(card)->devices, card_list) #define pnp_dev_name(dev) (dev)->name static inline void *pnp_get_drvdata(struct pnp_dev *pdev) @@ -437,14 +430,10 @@ struct pnp_protocol { }; #define to_pnp_protocol(n) list_entry(n, struct pnp_protocol, protocol_list) -#define protocol_for_each_card(protocol,card) \ - for((card) = protocol_to_pnp_card((protocol)->cards.next); \ - (card) != protocol_to_pnp_card(&(protocol)->cards); \ - (card) = protocol_to_pnp_card((card)->protocol_list.next)) -#define protocol_for_each_dev(protocol,dev) \ - for((dev) = protocol_to_pnp_dev((protocol)->devices.next); \ - (dev) != protocol_to_pnp_dev(&(protocol)->devices); \ - (dev) = protocol_to_pnp_dev((dev)->protocol_list.next)) +#define protocol_for_each_card(protocol, card) \ + list_for_each_entry(card, &(protocol)->cards, protocol_list) +#define protocol_for_each_dev(protocol, dev) \ + list_for_each_entry(dev, &(protocol)->devices, protocol_list) extern struct bus_type pnp_bus_type; -- cgit v1.2.3 From fa10fed30f2550313a8284365b3e2398526eb42c Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:52 +0200 Subject: proc: allow to mount many instances of proc in one pid namespace This patch allows to have multiple procfs instances inside the same pid namespace. The aim here is lightweight sandboxes, and to allow that we have to modernize procfs internals. 1) The main aim of this work is to have on embedded systems one supervisor for apps. Right now we have some lightweight sandbox support, however if we create pid namespacess we have to manages all the processes inside too, where our goal is to be able to run a bunch of apps each one inside its own mount namespace without being able to notice each other. We only want to use mount namespaces, and we want procfs to behave more like a real mount point. 2) Linux Security Modules have multiple ptrace paths inside some subsystems, however inside procfs, the implementation does not guarantee that the ptrace() check which triggers the security_ptrace_check() hook will always run. We have the 'hidepid' mount option that can be used to force the ptrace_may_access() check inside has_pid_permissions() to run. The problem is that 'hidepid' is per pid namespace and not attached to the mount point, any remount or modification of 'hidepid' will propagate to all other procfs mounts. This also does not allow to support Yama LSM easily in desktop and user sessions. Yama ptrace scope which restricts ptrace and some other syscalls to be allowed only on inferiors, can be updated to have a per-task context, where the context will be inherited during fork(), clone() and preserved across execve(). If we support multiple private procfs instances, then we may force the ptrace_may_access() on /proc// to always run inside that new procfs instances. This will allow to specifiy on user sessions if we should populate procfs with pids that the user can ptrace or not. By using Yama ptrace scope, some restricted users will only be able to see inferiors inside /proc, they won't even be able to see their other processes. Some software like Chromium, Firefox's crash handler, Wine and others are already using Yama to restrict which processes can be ptracable. With this change this will give the possibility to restrict /proc// but more importantly this will give desktop users a generic and usuable way to specifiy which users should see all processes and which users can not. Side notes: * This covers the lack of seccomp where it is not able to parse arguments, it is easy to install a seccomp filter on direct syscalls that operate on pids, however /proc// is a Linux ABI using filesystem syscalls. With this change LSMs should be able to analyze open/read/write/close... In the new patch set version I removed the 'newinstance' option as suggested by Eric W. Biederman. Selftest has been added to verify new behavior. Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/pid_namespace.h | 12 ------------ include/linux/proc_fs.h | 22 +++++++++++++++++++++- 2 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 4956e362e55e..5a5cb45ac57e 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -17,12 +17,6 @@ struct fs_pin; -enum { /* definitions for pid_namespace's hide_pid field */ - HIDEPID_OFF = 0, - HIDEPID_NO_ACCESS = 1, - HIDEPID_INVISIBLE = 2, -}; - struct pid_namespace { struct kref kref; struct idr idr; @@ -32,17 +26,11 @@ struct pid_namespace { struct kmem_cache *pid_cachep; unsigned int level; struct pid_namespace *parent; -#ifdef CONFIG_PROC_FS - struct dentry *proc_self; - struct dentry *proc_thread_self; -#endif #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; #endif struct user_namespace *user_ns; struct ucounts *ucounts; - kgid_t pid_gid; - int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; } __randomize_layout; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 45c05fd9c99d..1b98a41fdd8a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -42,6 +42,26 @@ struct proc_ops { unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); } __randomize_layout; +/* definitions for hide_pid field */ +enum { + HIDEPID_OFF = 0, + HIDEPID_NO_ACCESS = 1, + HIDEPID_INVISIBLE = 2, +}; + +struct proc_fs_info { + struct pid_namespace *pid_ns; + struct dentry *proc_self; /* For /proc/self */ + struct dentry *proc_thread_self; /* For /proc/thread-self */ + kgid_t pid_gid; + int hide_pid; +}; + +static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) +{ + return sb->s_fs_info; +} + #ifdef CONFIG_PROC_FS typedef int (*proc_write_t)(struct file *, char *, size_t); @@ -176,7 +196,7 @@ int open_related_ns(struct ns_common *ns, /* get the associated pid namespace for a file in procfs */ static inline struct pid_namespace *proc_pid_ns(const struct inode *inode) { - return inode->i_sb->s_fs_info; + return proc_sb_info(inode->i_sb)->pid_ns; } #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 24a71ce5c47f6b1b3cdacf544cb24220f5c3b7ef Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:53 +0200 Subject: proc: instantiate only pids that we can ptrace on 'hidepid=4' mount option If "hidepid=4" mount option is set then do not instantiate pids that we can not ptrace. "hidepid=4" means that procfs should only contain pids that the caller can ptrace. Signed-off-by: Djalal Harouni Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 1b98a41fdd8a..5bdc117ae947 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -47,6 +47,7 @@ enum { HIDEPID_OFF = 0, HIDEPID_NO_ACCESS = 1, HIDEPID_INVISIBLE = 2, + HIDEPID_NOT_PTRACEABLE = 4, /* Limit pids to only ptraceable pids */ }; struct proc_fs_info { -- cgit v1.2.3 From 6814ef2d992af09451bbeda4770daa204461329e Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:54 +0200 Subject: proc: add option to mount only a pids subset This allows to hide all files and directories in the procfs that are not related to tasks. Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 5bdc117ae947..8bc31ba5cd9c 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -50,12 +50,19 @@ enum { HIDEPID_NOT_PTRACEABLE = 4, /* Limit pids to only ptraceable pids */ }; +/* definitions for proc mount option pidonly */ +enum { + PROC_PIDONLY_OFF = 0, + PROC_PIDONLY_ON = 1, +}; + struct proc_fs_info { struct pid_namespace *pid_ns; struct dentry *proc_self; /* For /proc/self */ struct dentry *proc_thread_self; /* For /proc/thread-self */ kgid_t pid_gid; int hide_pid; + int pidonly; }; static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) -- cgit v1.2.3 From e61bb8b36a287dddc71bdf30be775e7abcaa595c Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:57 +0200 Subject: proc: use named enums for better readability Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8bc31ba5cd9c..2cb424e6f36a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -43,7 +43,7 @@ struct proc_ops { } __randomize_layout; /* definitions for hide_pid field */ -enum { +enum proc_hidepid { HIDEPID_OFF = 0, HIDEPID_NO_ACCESS = 1, HIDEPID_INVISIBLE = 2, @@ -51,7 +51,7 @@ enum { }; /* definitions for proc mount option pidonly */ -enum { +enum proc_pidonly { PROC_PIDONLY_OFF = 0, PROC_PIDONLY_ON = 1, }; @@ -61,8 +61,8 @@ struct proc_fs_info { struct dentry *proc_self; /* For /proc/self */ struct dentry *proc_thread_self; /* For /proc/thread-self */ kgid_t pid_gid; - int hide_pid; - int pidonly; + enum proc_hidepid hide_pid; + enum proc_pidonly pidonly; }; static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) -- cgit v1.2.3 From e64a0e16928415648d53d721b3d6fc3635eddf92 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:21 +0200 Subject: block: remove RQF_COPY_USER The RQF_COPY_USER is set for bio where the passthrough request mapping helpers decided that bounce buffering is required. It is then used to pad scatterlist for drivers that required it. But given that non-passthrough requests are per definition aligned, and directly mapped pass-through request must be aligned it is not actually required at all. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 32868fbedc9e..76da162b6ae9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -82,8 +82,6 @@ typedef __u32 __bitwise req_flags_t; /* set for "ide_preempt" requests and also for requests for which the SCSI "quiesce" state must be ignored. */ #define RQF_PREEMPT ((__force req_flags_t)(1 << 8)) -/* contains copies of user pages */ -#define RQF_COPY_USER ((__force req_flags_t)(1 << 9)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ -- cgit v1.2.3 From 89de1504d53b59b12bfff227328ee3e63dd3a112 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:22 +0200 Subject: block: provide a blk_rq_map_sg variant that returns the last element To be able to move some of the special purpose hacks in blk_rq_map_sg into the callers we need a variant that returns the last mapped S/G list element to the caller. Add that variant as __blk_rq_map_sg and make blk_rq_map_sg a trivial inline wrapper around it. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 76da162b6ae9..496dc9491026 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1136,7 +1136,15 @@ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) return max_t(unsigned short, rq->nr_phys_segments, 1); } -extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); +int __blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist, struct scatterlist **last_sg); +static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist) +{ + struct scatterlist *last_sg = NULL; + + return __blk_rq_map_sg(q, rq, sglist, &last_sg); +} extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); -- cgit v1.2.3 From cc97923a5bccc776851c242b61015faf288d5c22 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:24 +0200 Subject: block: move dma drain handling to scsi Don't burden the common block code with with specifics of the libata DMA draining mechanism. Instead move most of the code to the scsi midlayer. That also means the nr_phys_segments adjustments in the blk-mq fast path can go away entirely, given that SCSI never looks at nr_phys_segments after mapping the request to a scatterlist. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ------- include/linux/libata.h | 2 ++ 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 496dc9491026..8e4726bce498 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -288,7 +288,6 @@ struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); struct bio_vec; -typedef int (dma_drain_needed_fn)(struct request *); enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ @@ -397,7 +396,6 @@ struct request_queue { struct rq_qos *rq_qos; make_request_fn *make_request_fn; - dma_drain_needed_fn *dma_drain_needed; const struct blk_mq_ops *mq_ops; @@ -467,8 +465,6 @@ struct request_queue { */ unsigned long nr_requests; /* Max # of requests */ - unsigned int dma_drain_size; - void *dma_drain_buffer; unsigned int dma_pad_mask; unsigned int dma_alignment; @@ -1097,9 +1093,6 @@ extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); -extern int blk_queue_dma_drain(struct request_queue *q, - dma_drain_needed_fn *dma_drain_needed, - void *buf, unsigned int size); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); diff --git a/include/linux/libata.h b/include/linux/libata.h index cffa4714bfa8..af832852e620 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1092,6 +1092,7 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #define ATA_SCSI_COMPAT_IOCTL /* empty */ #endif extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); +bool ata_scsi_dma_need_drain(struct request *rq); extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, unsigned int cmd, void __user *arg); extern bool ata_link_online(struct ata_link *link); @@ -1387,6 +1388,7 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .ioctl = ata_scsi_ioctl, \ ATA_SCSI_COMPAT_IOCTL \ .queuecommand = ata_scsi_queuecmd, \ + .dma_need_drain = ata_scsi_dma_need_drain, \ .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .this_id = ATA_SHT_THIS_ID, \ -- cgit v1.2.3 From bdf8710d69f82ee6fd41b0166300c3306898b3c1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:25 +0200 Subject: block: move dma_pad handling from blk_rq_map_sg into the callers There are only two callers of blk_rq_map_sg/__blk_rq_map_sg that set the dma_pad value in the queue. Move the handling into those callers instead of burdening the common code, and move the ->extra_len field from struct request to struct scsi_cmnd. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8e4726bce498..f00bd4042295 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -224,8 +224,6 @@ struct request { unsigned short write_hint; unsigned short ioprio; - unsigned int extra_len; /* length of alignment and padding */ - enum mq_rq_state state; refcount_t ref; -- cgit v1.2.3 From 66648766ef38d8d6c48ded2f59cf98420aec2cdb Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Thu, 2 Apr 2020 19:25:07 +0200 Subject: mm: Remove MPX leftovers Remove MPX leftovers in generic code. Fixes: 45fc24e89b7c ("x86/mpx: remove MPX from arch/x86") Signed-off-by: Jimmy Assarsson Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Link: https://lkml.kernel.org/r/20200402172507.2786-1-jimmyassarsson@gmail.com --- include/linux/mm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..e1882eec1752 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -329,13 +329,6 @@ extern unsigned int kobjsize(const void *objp); # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -#if defined(CONFIG_X86_INTEL_MPX) -/* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_HIGH_ARCH_4 -#else -# define VM_MPX VM_NONE -#endif - #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif -- cgit v1.2.3 From 0a32f1ff2a2e41404deaba5fb32f8a0d640c0974 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 20 Apr 2020 20:21:11 +0200 Subject: net: phy: broadcom: add helper to write/read RDB registers RDB (Register Data Base) registers are used on newer Broadcom PHYs. Add helper to read, write and modify these registers. Signed-off-by: Michael Walle Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 7e1d857c8468..897b69309964 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -115,6 +115,9 @@ #define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10) #define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0) +#define MII_BCM54XX_RDB_ADDR 0x1e +#define MII_BCM54XX_RDB_DATA 0x1f + /* * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) */ -- cgit v1.2.3 From 6937602ed3f9ebd46ed6a6b5e609c0ae4ed99008 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 20 Apr 2020 20:21:12 +0200 Subject: net: phy: add Broadcom BCM54140 support The Broadcom BCM54140 is a Quad SGMII/QSGMII Copper/Fiber Gigabit Ethernet transceiver. This also adds support for tunables to set and get downshift and energy detect auto power-down. The PHY has four ports and each port has its own PHY address. There are per-port registers as well as global registers. Unfortunately, the global registers can only be accessed by reading and writing from/to the PHY address of the first port. Further, there is no way to find out what port you actually are by just reading the per-port registers. We therefore, have to scan the bus on the PHY probe to determine the port and thus what address we need to access the global registers. Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 897b69309964..8be150e69c7c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -25,6 +25,7 @@ #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 +#define PHY_ID_BCM54140 0xae025019 #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM89610 0x03625cd0 -- cgit v1.2.3 From 38f961e744840db9044af68f4773ae5feae60a89 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 20 Apr 2020 23:29:05 +0200 Subject: net: phy: add device-managed devm_mdiobus_register If there's no special ordering requirement for mdiobus_unregister(), then driver code can be simplified by using a device-managed version of mdiobus_register(). Prerequisite is that bus allocation has been done device-managed too. Else mdiobus_free() may be called whilst bus is still registered, resulting in a BUG_ON(). Therefore let devm_mdiobus_register() return -EPERM if bus was allocated non-managed. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2432ca463ddc..3941a6bcba10 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -241,6 +241,9 @@ struct mii_bus { int (*reset)(struct mii_bus *bus); struct mdio_bus_stats stats[PHY_MAX_ADDR]; + unsigned int is_managed:1; /* is device-managed */ + unsigned int is_managed_registered:1; + /* * A lock to ensure that only one thing can read/write * the MDIO bus at a time @@ -286,6 +289,20 @@ static inline struct mii_bus *mdiobus_alloc(void) int __mdiobus_register(struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) +static inline int devm_mdiobus_register(struct mii_bus *bus) +{ + int ret; + + if (!bus->is_managed) + return -EPERM; + + ret = mdiobus_register(bus); + if (!ret) + bus->is_managed_registered = 1; + + return ret; +} + void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); -- cgit v1.2.3 From 62d0fd591db1f9dcf68fb963b3a94af085a6b166 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 22 Apr 2020 01:13:55 +0900 Subject: arch: split MODULE_ARCH_VERMAGIC definitions out to As the bug report [1] pointed out, must be included after . I believe we should not impose any include order restriction. We often sort include directives alphabetically, but it is just coding style convention. Technically, we can include header files in any order by making every header self-contained. Currently, arch-specific MODULE_ARCH_VERMAGIC is defined in , which is not included from . Hence, the straight-forward fix-up would be as follows: |--- a/include/linux/vermagic.h |+++ b/include/linux/vermagic.h |@@ -1,5 +1,6 @@ | /* SPDX-License-Identifier: GPL-2.0 */ | #include |+#include | | /* Simply sanity version stamp for modules. */ | #ifdef CONFIG_SMP This works enough, but for further cleanups, I split MODULE_ARCH_VERMAGIC definitions into . With this, and will be orthogonal, and the location of MODULE_ARCH_VERMAGIC definitions will be consistent. For arc and ia64, MODULE_PROC_FAMILY is only used for defining MODULE_ARCH_VERMAGIC. I squashed it. For hexagon, nds32, and xtensa, I removed entirely because they contained nothing but MODULE_ARCH_VERMAGIC definition. Kbuild will automatically generate at build-time, wrapping . [1] https://lore.kernel.org/lkml/20200411155623.GA22175@zn.tnic Reported-by: Borislav Petkov Signed-off-by: Masahiro Yamada Acked-by: Jessica Yu --- include/linux/vermagic.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 9aced11e9000..dc236577b92f 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -1,5 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VERMAGIC_H +#define _LINUX_VERMAGIC_H + #include +#include /* Simply sanity version stamp for modules. */ #ifdef CONFIG_SMP @@ -24,9 +28,6 @@ #else #define MODULE_VERMAGIC_MODVERSIONS "" #endif -#ifndef MODULE_ARCH_VERMAGIC -#define MODULE_ARCH_VERMAGIC "" -#endif #ifdef RANDSTRUCT_PLUGIN #include #define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED @@ -41,3 +42,4 @@ MODULE_ARCH_VERMAGIC \ MODULE_RANDSTRUCT_PLUGIN +#endif /* _LINUX_VERMAGIC_H */ -- cgit v1.2.3 From a2806ef77ff9a965a70d6c194bb3a4801bbdb07d Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 13 Apr 2020 18:32:46 +0300 Subject: tracing: Remove DECLARE_TRACE_NOARGS This macro was intentionally broken so that the kernel code is not poluted with such noargs macro used simply as markers. This use case can be satisfied by using dummy no inline functions. Just remove it. Link: http://lkml.kernel.org/r/20200413153246.8511-1-nborisov@suse.com Signed-off-by: Nikolay Borisov Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 1fb11daa5c53..a1fecf311621 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -156,8 +156,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * Note, the proto and args passed in includes "__data" as the first parameter. * The reason for this is to handle the "void" prototype. If a tracepoint * has a "void" prototype, then it is invalid to declare a function - * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just - * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". + * as "(void *, void)". */ #define __DO_TRACE(tp, proto, args, cond, rcuidle) \ do { \ @@ -373,25 +372,6 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) # define __tracepoint_string #endif -/* - * The need for the DECLARE_TRACE_NOARGS() is to handle the prototype - * (void). "void" is a special value in a function prototype and can - * not be combined with other arguments. Since the DECLARE_TRACE() - * macro adds a data element at the beginning of the prototype, - * we need a way to differentiate "(void *data, proto)" from - * "(void *data, void)". The second prototype is invalid. - * - * DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype - * and "void *__data" as the callback prototype. - * - * DECLARE_TRACE() passes "proto" as the tracepoint protoype and - * "void *__data, proto" as the callback prototype. - */ -#define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , \ - cpu_online(raw_smp_processor_id()), \ - void *__data, __data) - #define DECLARE_TRACE(name, proto, args) \ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ cpu_online(raw_smp_processor_id()), \ -- cgit v1.2.3 From 5972157c2dde11698d7bcfc55621107d97121c87 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 22 Apr 2020 11:24:55 +0200 Subject: net: mdio: of: export part of of_mdiobus_register_phy() This function will be needed in tja11xx driver for secondary PHY support. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 491a2b7e77c1..0f61a4ac6bcf 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -30,7 +30,9 @@ extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); extern int of_phy_register_fixed_link(struct device_node *np); extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); - +extern int of_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct device_node *child, u32 addr); static inline int of_mdio_parse_addr(struct device *dev, const struct device_node *np) @@ -118,6 +120,13 @@ static inline bool of_phy_is_fixed_link(struct device_node *np) { return false; } + +static inline int of_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct device_node *child, u32 addr) +{ + return -ENOSYS; +} #endif -- cgit v1.2.3 From 33467ac3c8dc80575e1b158e78d0c30ab33c1b08 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Thu, 16 Apr 2020 19:20:35 -0500 Subject: remoteproc: Add prepare and unprepare ops On some SoC architecture, it is needed to enable HW like clock, bus, regulator, memory region... before loading co-processor firmware. This patch introduces prepare and unprepare ops to execute platform specific function before firmware loading and after stop execution. Signed-off-by: Loic Pallardy Signed-off-by: Suman Anna Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200417002036.24359-2-s-anna@ti.com Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index ac4082f12e8b..0468be4d02f4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -355,6 +355,8 @@ enum rsc_handling_status { /** * struct rproc_ops - platform-specific device handlers + * @prepare: prepare device for code loading + * @unprepare: unprepare device after stop * @start: power on the device and boot it * @stop: power off the device * @kick: kick a virtqueue (virtqueue id given as a parameter) @@ -373,6 +375,8 @@ enum rsc_handling_status { * panic at least the returned number of milliseconds */ struct rproc_ops { + int (*prepare)(struct rproc *rproc); + int (*unprepare)(struct rproc *rproc); int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); -- cgit v1.2.3 From 5cc415001bca8fe0e3f0ee6d58a953a314dd9751 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 6 Apr 2020 12:41:52 +0200 Subject: Drivers: hv: avoid passing opaque pointer to vmbus_onmessage() vmbus_onmessage() doesn't need the header of the message, it only uses it to get to the payload, we can pass the pointer to the payload directly. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20200406104154.45010-4-vkuznets@redhat.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 692c89ccf5df..cbd24f4e68d1 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1017,7 +1017,7 @@ static inline void clear_low_latency_mode(struct vmbus_channel *c) c->low_latency = false; } -void vmbus_onmessage(void *context); +void vmbus_onmessage(struct vmbus_channel_message_header *hdr); int vmbus_request_offers(void); -- cgit v1.2.3 From 8b6a877c060ed6b86878fe66c7c6493a6054cf23 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:06 +0200 Subject: Drivers: hv: vmbus: Replace the per-CPU channel lists with a global array of channels When Hyper-V sends an interrupt to the guest, the guest has to figure out which channel the interrupt is associated with. Hyper-V sets a bit in a memory page that is shared with the guest, indicating a particular "relid" that the interrupt is associated with. The current Linux code then uses a set of per-CPU linked lists to map a given "relid" to a pointer to a channel structure. This design introduces a synchronization problem if the CPU that Hyper-V will interrupt for a certain channel is changed. If the interrupt comes on the "old CPU" and the channel was already moved to the per-CPU list of the "new CPU", then the relid -> channel mapping will fail and the interrupt is dropped. Similarly, if the interrupt comes on the new CPU but the channel was not moved to the per-CPU list of the new CPU, then the mapping will fail and the interrupt is dropped. Relids are integers ranging from 0 to 2047. The mapping from relids to channel structures can be done by setting up an array with 2048 entries, each entry being a pointer to a channel structure (hence total size ~16K bytes, which is not a problem). The array is global, so there are no per-CPU linked lists to update. The array can be searched and updated by loading from/storing to the array at the specified index. With no per-CPU data structures, the above mentioned synchronization problem is avoided and the relid2channel() function gets simpler. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-4-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index cbd24f4e68d1..f5b3f008c55a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -854,11 +854,6 @@ struct vmbus_channel { * Support per-channel state for use by vmbus drivers. */ void *per_channel_state; - /* - * To support per-cpu lookup mapping of relid to channel, - * link up channels based on their CPU affinity. - */ - struct list_head percpu_list; /* * Defer freeing channel until after all cpu's have -- cgit v1.2.3 From 9403b66e6161130ebae7e55a97491c84c1ad6f9f Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:09 +0200 Subject: Drivers: hv: vmbus: Use a spin lock for synchronizing channel scheduling vs. channel removal Since vmbus_chan_sched() dereferences the ring buffer pointer, we have to make sure that the ring buffer data structures don't get freed while such dereferencing is happening. Current code does this by sending an IPI to the CPU that is allowed to access that ring buffer from interrupt level, cf., vmbus_reset_channel_cb(). But with the new functionality to allow changing the CPU that a channel will interrupt, we can't be sure what CPU will be running the vmbus_chan_sched() function for a particular channel, so the current IPI mechanism is infeasible. Instead synchronize vmbus_chan_sched() and vmbus_reset_channel_cb() by using the (newly introduced) per-channel spin lock "sched_lock". Move the test for onchannel_callback being NULL before the "switch" control statement in vmbus_chan_sched(), in order to not access the ring buffer if the vmbus_reset_channel_cb() has been completed on the channel. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-7-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f5b3f008c55a..62b2c11d0875 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -771,6 +771,12 @@ struct vmbus_channel { void (*onchannel_callback)(void *context); void *channel_callback_context; + /* + * Synchronize channel scheduling and channel removal; see the inline + * comments in vmbus_chan_sched() and vmbus_reset_channel_cb(). + */ + spinlock_t sched_lock; + /* * A channel can be marked for one of three modes of reading: * BATCHED - callback called from taslket and should read -- cgit v1.2.3 From 8ef4c4abbbcdcd9d4bc0fd9454df03e6dac24b73 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:11 +0200 Subject: Drivers: hv: vmbus: Remove the unused HV_LOCALIZED channel affinity logic The logic is unused since commit 509879bdb30b8 ("Drivers: hv: Introduce a policy for controlling channel affinity"). This logic assumes that a channel target_cpu doesn't change during the lifetime of a channel, but this assumption is incompatible with the new functionality that allows changing the vCPU a channel will interrupt. Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-9-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 62b2c11d0875..247356dbd742 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -689,11 +689,6 @@ union hv_connection_id { } u; }; -enum hv_numa_policy { - HV_BALANCED = 0, - HV_LOCALIZED, -}; - enum vmbus_device_type { HV_IDE = 0, HV_SCSI, @@ -808,10 +803,6 @@ struct vmbus_channel { u32 target_vp; /* The corresponding CPUID in the guest */ u32 target_cpu; - /* - * State to manage the CPU affiliation of channels. - */ - struct cpumask alloced_cpus_in_node; int numa_node; /* * Support for sub-channels. For high performance devices, @@ -898,18 +889,6 @@ struct vmbus_channel { */ bool low_latency; - /* - * NUMA distribution policy: - * We support two policies: - * 1) Balanced: Here all performance critical channels are - * distributed evenly amongst all the NUMA nodes. - * This policy will be the default policy. - * 2) Localized: All channels of a given instance of a - * performance critical service will be assigned CPUs - * within a selected NUMA node. - */ - enum hv_numa_policy affinity_policy; - bool probe_done; /* @@ -965,12 +944,6 @@ static inline bool is_sub_channel(const struct vmbus_channel *c) return c->offermsg.offer.sub_channel_index != 0; } -static inline void set_channel_affinity_state(struct vmbus_channel *c, - enum hv_numa_policy policy) -{ - c->affinity_policy = policy; -} - static inline void set_channel_read_mode(struct vmbus_channel *c, enum hv_callback_mode mode) { -- cgit v1.2.3 From 7527810573436f00e582d3d5ef2eb3c027c98d7d Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:13 +0200 Subject: Drivers: hv: vmbus: Introduce the CHANNELMSG_MODIFYCHANNEL message type VMBus version 4.1 and later support the CHANNELMSG_MODIFYCHANNEL(22) message type which can be used to request Hyper-V to change the vCPU that a channel will interrupt. Introduce the CHANNELMSG_MODIFYCHANNEL message type, and define the vmbus_send_modifychannel() function to send CHANNELMSG_MODIFYCHANNEL requests to the host via a hypercall. The function is then used to define a sysfs "store" operation, which allows to change the (v)CPU the channel will interrupt by using the sysfs interface. The feature can be used for load balancing or other purposes. One interesting catch here is that Hyper-V can *not* currently ACK CHANNELMSG_MODIFYCHANNEL messages with the promise that (after the ACK is sent) the channel won't send any more interrupts to the "old" CPU. The peculiarity of the CHANNELMSG_MODIFYCHANNEL messages is problematic if the user want to take a CPU offline, since we don't want to take a CPU offline (and, potentially, "lose" channel interrupts on such CPU) if the host is still processing a CHANNELMSG_MODIFYCHANNEL message associated to that CPU. It is worth mentioning, however, that we have been unable to observe the above mentioned "race": in all our tests, CHANNELMSG_MODIFYCHANNEL requests appeared *as if* they were processed synchronously by the host. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-11-parri.andrea@gmail.com Reviewed-by: Michael Kelley [ wei: fix conflict in channel_mgmt.c ] Signed-off-by: Wei Liu --- include/linux/hyperv.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 247356dbd742..b85d7580f2c1 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -425,7 +425,7 @@ enum vmbus_channel_message_type { CHANNELMSG_19 = 19, CHANNELMSG_20 = 20, CHANNELMSG_TL_CONNECT_REQUEST = 21, - CHANNELMSG_22 = 22, + CHANNELMSG_MODIFYCHANNEL = 22, CHANNELMSG_TL_CONNECT_RESULT = 23, CHANNELMSG_COUNT }; @@ -620,6 +620,13 @@ struct vmbus_channel_tl_connect_request { guid_t host_service_id; } __packed; +/* Modify Channel parameters, cf. vmbus_send_modifychannel() */ +struct vmbus_channel_modifychannel { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 target_vp; +} __packed; + struct vmbus_channel_version_response { struct vmbus_channel_message_header header; u8 version_supported; @@ -1505,6 +1512,7 @@ extern __u32 vmbus_proto_version; int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id, const guid_t *shv_host_servie_id); +int vmbus_send_modifychannel(u32 child_relid, u32 target_vp); void vmbus_set_event(struct vmbus_channel *channel); /* Get the start of the ring buffer. */ -- cgit v1.2.3 From 6824f0ce38cb4b903a3cbf00dd528861f6c2ea7c Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Fri, 3 Apr 2020 14:43:23 +0100 Subject: parport: Add comments for parport_register_dev_model() In preparation to remove parport_register_device(), copy the comments to parport_register_dev_model() and modify the parameters according to what parport_register_dev_model() has. Signed-off-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20200403134325.11523-9-sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/parport.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/parport.h b/include/linux/parport.h index 13932ce8b37b..36a0f6270238 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -337,6 +337,10 @@ struct pardevice *parport_register_device(struct parport *port, void (*irq_func)(void *), int flags, void *handle); +/* + * parport_register_dev_model declares that a device is connected to a + * port, and tells the kernel all it needs to know. + */ struct pardevice * parport_register_dev_model(struct parport *port, const char *name, const struct pardev_cb *par_dev_cb, int cnt); -- cgit v1.2.3 From bae9defb06a781083844cafd0a359f423cd98388 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Fri, 3 Apr 2020 14:43:24 +0100 Subject: parport: remove unused parport_register_device() All the drivers that are using parallel port has been converted to use the new device model api, and parport_register_device() is no longer used. Signed-off-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20200403134325.11523-10-sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/parport.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/parport.h b/include/linux/parport.h index 36a0f6270238..1fb508c19e83 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -325,18 +325,6 @@ struct pardev_cb { unsigned int flags; }; -/* parport_register_device declares that a device is connected to a - port, and tells the kernel all it needs to know. - - pf is the preemption function (may be NULL for no callback) - - kf is the wake-up function (may be NULL for no callback) - - irq_func is the interrupt handler (may be NULL for no interrupts) - - handle is a user pointer that gets handed to callback functions. */ -struct pardevice *parport_register_device(struct parport *port, - const char *name, - int (*pf)(void *), void (*kf)(void *), - void (*irq_func)(void *), - int flags, void *handle); - /* * parport_register_dev_model declares that a device is connected to a * port, and tells the kernel all it needs to know. -- cgit v1.2.3 From 5d1c9a114a6efba2c8391e39d4ac3e4e5c7b6d32 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 7 Apr 2020 18:59:51 +0300 Subject: net/mlx5: Update vport.c to new cmd interface Do mass update of vport.c to reuse newly introduced mlx5_cmd_exec_in*() interfaces. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/vport.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 16060fb9b5e5..8170da1e9f70 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -127,8 +127,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport, u8 other_vport, u64 *rx_discard_vport_down, u64 *tx_discard_vport_down); int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, - int vf, u8 port_num, void *out, - size_t out_sz); + int vf, u8 port_num, void *out); int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev, u8 other_vport, u8 port_num, int vf, -- cgit v1.2.3 From d1f620500cde5c72c7b96a19474733c4c6c67f38 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 9 Apr 2020 11:39:14 +0300 Subject: net/mlx5: Update cq.c to new cmd interface Do mass update of cq.c to reuse newly introduced mlx5_cmd_exec_in*() interfaces. Reviewed-by: Moshe Shemesh Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 40748fc1b11b..b5a9399e07ee 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -188,7 +188,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, - u32 *out, int outlen); + u32 *out); int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen); int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev, -- cgit v1.2.3 From e0b4b4722dfac09658d1519b296cf8dc349a2451 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 9 Apr 2020 21:03:33 +0300 Subject: net/mlx5: Update transobj.c new cmd interface Do mass update of transobj.c to reuse newly introduced mlx5_cmd_exec_in*() interfaces. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/transobj.h | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index dc6b1e7cb8c4..028f442530cf 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -39,27 +39,20 @@ int mlx5_core_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn); void mlx5_core_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn); int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqn); -int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen); +int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in); void mlx5_core_destroy_rq(struct mlx5_core_dev *dev, u32 rqn); int mlx5_core_query_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *out); int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *sqn); -int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen); +int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in); void mlx5_core_destroy_sq(struct mlx5_core_dev *dev, u32 sqn); int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out); int mlx5_core_query_sq_state(struct mlx5_core_dev *dev, u32 sqn, u8 *state); -int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen, - u32 *tirn); -int mlx5_core_create_tir_out(struct mlx5_core_dev *dev, - u32 *in, int inlen, - u32 *out, int outlen); -int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in, - int inlen); +int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, u32 *tirn); +int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in); void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn); -int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen, - u32 *tisn); -int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in, - int inlen); +int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, u32 *tisn); +int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in); void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn); int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqtn); -- cgit v1.2.3 From 6f8b12d661d09b488b9ac879b8eafbd2cc4a1450 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Apr 2020 09:13:27 -0700 Subject: net: napi: add hard irqs deferral feature Back in commit 3b47d30396ba ("net: gro: add a per device gro flush timer") we added the ability to arm one high resolution timer, that we used to keep not-complete packets in GRO engine a bit longer, hoping that further frames might be added to them. Since then, we added the napi_complete_done() interface, and commit 364b6055738b ("net: busy-poll: return busypolling status to drivers") allowed drivers to avoid re-arming NIC interrupts if we made a promise that their NAPI poll() handler would be called in the near future. This infrastructure can be leveraged, thanks to a new device parameter, which allows to arm the napi hrtimer, instead of re-arming the device hard IRQ. We have noticed that on some servers with 32 RX queues or more, the chit-chat between the NIC and the host caused by IRQ delivery and re-arming could hurt throughput by ~20% on 100Gbit NIC. In contrast, hrtimers are using local (percpu) resources and might have lower cost. The new tunable, named napi_defer_hard_irqs, is placed in the same hierarchy than gro_flush_timeout (/sys/class/net/ethX/) By default, both gro_flush_timeout and napi_defer_hard_irqs are zero. This patch does not change the prior behavior of gro_flush_timeout if used alone : NIC hard irqs should be rearmed as before. One concrete usage can be : echo 20000 >/sys/class/net/eth1/gro_flush_timeout echo 10 >/sys/class/net/eth1/napi_defer_hard_irqs If at least one packet is retired, then we will reset napi counter to 10 (napi_defer_hard_irqs), ensuring at least 10 periodic scans of the queue. On busy queues, this should avoid NIC hard IRQ, while before this patch IRQ avoidance was only possible if napi->poll() was exhausting its budget and not call napi_complete_done(). This feature also can be used to work around some non-optimal NIC irq coalescing strategies. Having the ability to insert XX usec delays between each napi->poll() can increase cache efficiency, since we increase batch sizes. It also keeps serving cpus not idle too long, reducing tail latencies. Co-developed-by: Luigi Rizzo Signed-off-by: Eric Dumazet 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 0750b54b3765..5a8d40f1ffe2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -329,6 +329,7 @@ struct napi_struct { unsigned long state; int weight; + int defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL @@ -1995,6 +1996,7 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; + int napi_defer_hard_irqs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; -- cgit v1.2.3 From e7d3c33c58e0108e38e969239cd3b3678a5d8ac5 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 16 Apr 2020 11:15:42 +0300 Subject: mfd: intel_soc_pmic: Add SCU IPC member to struct intel_soc_pmic Both PMIC drivers (intel_soc_pmic_mrfld and intel_soc_pmic_bxtwc) will be using this field going forward to access the SCU IPC instance. While there add kernel-doc for the intel_soc_pmic structure. Signed-off-by: Mika Westerberg Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones --- include/linux/mfd/intel_soc_pmic.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index bfecd6bd4990..6a88e34cb955 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -13,6 +13,20 @@ #include +/** + * struct intel_soc_pmic - Intel SoC PMIC data + * @irq: Master interrupt number of the parent PMIC device + * @regmap: Pointer to the parent PMIC device regmap structure + * @irq_chip_data: IRQ chip data for the PMIC itself + * @irq_chip_data_pwrbtn: Chained IRQ chip data for the Power Button + * @irq_chip_data_tmu: Chained IRQ chip data for the Time Management Unit + * @irq_chip_data_bcu: Chained IRQ chip data for the Burst Control Unit + * @irq_chip_data_adc: Chained IRQ chip data for the General Purpose ADC + * @irq_chip_data_chgr: Chained IRQ chip data for the External Charger + * @irq_chip_data_crit: Chained IRQ chip data for the Critical Event Handler + * @dev: Pointer to the parent PMIC device + * @scu: Pointer to the SCU IPC device data structure + */ struct intel_soc_pmic { int irq; struct regmap *regmap; @@ -24,6 +38,7 @@ struct intel_soc_pmic { struct regmap_irq_chip_data *irq_chip_data_chgr; struct regmap_irq_chip_data *irq_chip_data_crit; struct device *dev; + struct intel_scu_ipc_dev *scu; }; int intel_soc_pmic_exec_mipi_pmic_seq_element(u16 i2c_address, u32 reg_address, -- cgit v1.2.3 From 25f1ca31e230598eaf3c38d387a355a64bd772a7 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 16 Apr 2020 11:15:51 +0300 Subject: platform/x86: intel_pmc_ipc: Convert to MFD This driver only creates a bunch of platform devices sharing resources belonging to the PMC device. This is pretty much what MFD subsystem is for so move the driver there, renaming it to intel_pmc_bxt.c which should be more clear what it is. MFD subsystem provides nice helper APIs for subdevice creation so convert the driver to use those. Unfortunately the ACPI device includes separate resources for most of the subdevices so we cannot simply call mfd_add_devices() to create all of them but instead we need to call it separately for each device. The new MFD driver continues to expose two sysfs attributes that allow userspace to send IPC commands to the PMC/SCU to avoid breaking any existing applications that may use these. Generally this is bad idea so document this in the ABI documentation. Signed-off-by: Mika Westerberg Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones --- include/linux/mfd/intel_pmc_bxt.h | 53 ++++++++++++++++++++++++++++++++++ include/linux/platform_data/itco_wdt.h | 11 ++++--- 2 files changed, 60 insertions(+), 4 deletions(-) create mode 100644 include/linux/mfd/intel_pmc_bxt.h (limited to 'include/linux') diff --git a/include/linux/mfd/intel_pmc_bxt.h b/include/linux/mfd/intel_pmc_bxt.h new file mode 100644 index 000000000000..f51a43d25ffd --- /dev/null +++ b/include/linux/mfd/intel_pmc_bxt.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef MFD_INTEL_PMC_BXT_H +#define MFD_INTEL_PMC_BXT_H + +/* GCR reg offsets from GCR base */ +#define PMC_GCR_PMC_CFG_REG 0x08 +#define PMC_GCR_TELEM_DEEP_S0IX_REG 0x78 +#define PMC_GCR_TELEM_SHLW_S0IX_REG 0x80 + +/* PMC_CFG_REG bit masks */ +#define PMC_CFG_NO_REBOOT_EN BIT(4) + +/** + * struct intel_pmc_dev - Intel PMC device structure + * @dev: Pointer to the parent PMC device + * @scu: Pointer to the SCU IPC device data structure + * @gcr_mem_base: Virtual base address of GCR (Global Configuration Registers) + * @gcr_lock: Lock used to serialize access to GCR registers + * @telem_base: Pointer to telemetry SSRAM base resource or %NULL if not + * available + */ +struct intel_pmc_dev { + struct device *dev; + struct intel_scu_ipc_dev *scu; + void __iomem *gcr_mem_base; + spinlock_t gcr_lock; + struct resource *telem_base; +}; + +#if IS_ENABLED(CONFIG_MFD_INTEL_PMC_BXT) +int intel_pmc_gcr_read64(struct intel_pmc_dev *pmc, u32 offset, u64 *data); +int intel_pmc_gcr_update(struct intel_pmc_dev *pmc, u32 offset, u32 mask, u32 val); +int intel_pmc_s0ix_counter_read(struct intel_pmc_dev *pmc, u64 *data); +#else +static inline int intel_pmc_gcr_read64(struct intel_pmc_dev *pmc, u32 offset, + u64 *data) +{ + return -ENOTSUPP; +} + +static inline int intel_pmc_gcr_update(struct intel_pmc_dev *pmc, u32 offset, + u32 mask, u32 val) +{ + return -ENOTSUPP; +} + +static inline int intel_pmc_s0ix_counter_read(struct intel_pmc_dev *pmc, u64 *data) +{ + return -ENOTSUPP; +} +#endif + +#endif /* MFD_INTEL_PMC_BXT_H */ diff --git a/include/linux/platform_data/itco_wdt.h b/include/linux/platform_data/itco_wdt.h index 2ccdce6a4e27..45d860cac2b0 100644 --- a/include/linux/platform_data/itco_wdt.h +++ b/include/linux/platform_data/itco_wdt.h @@ -12,13 +12,16 @@ #define ICH_RES_MEM_OFF 2 #define ICH_RES_MEM_GCS_PMC 0 +/** + * struct itco_wdt_platform_data - iTCO_wdt platform data + * @name: Name of the platform + * @version: iTCO version + * @no_reboot_use_pmc: Use PMC BXT API to set and clear NO_REBOOT bit + */ struct itco_wdt_platform_data { char name[32]; unsigned int version; - /* private data to be passed to update_no_reboot_bit API */ - void *no_reboot_priv; - /* pointer for platform specific no reboot update function */ - int (*update_no_reboot_bit)(void *priv, bool set); + bool no_reboot_use_pmc; }; #endif /* _ITCO_WDT_H_ */ -- cgit v1.2.3 From 9166cc49767a646990a73380480356416b7794eb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 26 Mar 2020 15:09:32 +0200 Subject: mac80211: implement Operating Mode Notification extended NSS support Somehow we missed this for a long time, but similar to the extended NSS support in VHT capabilities, we need to have this in Operating Mode notification. Implement it by * parsing the 160/80+80 bit there and setting the bandwidth appropriately * having callers of ieee80211_get_vht_max_nss() pass in the current max NSS value as received in the operating mode notification in order to modify it appropriately depending on the extended NSS bits. This updates all drivers that use it, i.e. only iwlwifi/mvm. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20200326150855.098483728cfa.I4e8c25d3288441759c2793247197229f0696a37d@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 16268ef1cbcc..c326aec535c6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2019 Intel Corporation + * Copyright (c) 2018 - 2020 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -859,6 +859,7 @@ enum ieee80211_ht_chanwidth_values { * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width + * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask * (the NSS value is the value of this field + 1) * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift @@ -866,11 +867,12 @@ enum ieee80211_ht_chanwidth_values { * using a beamforming steering matrix */ enum ieee80211_vht_opmode_bits { - IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 3, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 0x03, IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ = 0, IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ = 1, IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ = 2, IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ = 3, + IEEE80211_OPMODE_NOTIF_BW_160_80P80 = 0x04, IEEE80211_OPMODE_NOTIF_RX_NSS_MASK = 0x70, IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT = 4, IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, @@ -1731,6 +1733,9 @@ struct ieee80211_mu_edca_param_set { * @ext_nss_bw_capable: indicates whether or not the local transmitter * (rate scaling algorithm) can deal with the new logic * (dot11VHTExtendedNSSBWCapable) + * @max_vht_nss: current maximum NSS as advertised by the STA in + * operating mode notification, can be 0 in which case the + * capability data will be used to derive this (from MCS support) * * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can * vary for a given BW/MCS. This function parses the data. @@ -1739,7 +1744,8 @@ struct ieee80211_mu_edca_param_set { */ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, enum ieee80211_vht_chanwidth bw, - int mcs, bool ext_nss_bw_capable); + int mcs, bool ext_nss_bw_capable, + unsigned int max_vht_nss); /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 -- cgit v1.2.3 From 2a392596d8811c6d58c014ec881b159c75a0cf45 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Thu, 26 Mar 2020 15:09:35 +0200 Subject: cfg80211: Parse HE membership selector This extends the support for drivers that rebuilds IEs in the FW (same as with HT/VHT). Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20200326150855.20feaabfb484.I886252639604c8e3e84b8ef97962f1b0e4beec81@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c326aec535c6..38f513ce7528 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1067,6 +1067,7 @@ struct ieee80211_mgmt { /* Supported rates membership selectors */ #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY 126 +#define BSS_MEMBERSHIP_SELECTOR_HE_PHY 122 /* mgmt header + 1 byte category code */ #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u) -- cgit v1.2.3 From b572510100165ba037ba43dbbb0f05e8da12c741 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Wed, 1 Apr 2020 18:18:02 -0700 Subject: ieee80211: share 802.11 unit conversion helpers MHZ_TO_KHZ, and KHZ_TO_MHZ are useful to drivers and elsewhere so export these in the common ieee80211 header. Move the power helpers also because we might as well. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200402011810.22947-2-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 38f513ce7528..a561db435a4b 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3330,6 +3330,16 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size) #define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) #define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) +/* convert frequencies */ +#define MHZ_TO_KHZ(freq) ((freq) * 1000) +#define KHZ_TO_MHZ(freq) ((freq) / 1000) + +/* convert powers */ +#define DBI_TO_MBI(gain) ((gain) * 100) +#define MBI_TO_DBI(gain) ((gain) / 100) +#define DBM_TO_MBM(gain) ((gain) * 100) +#define MBM_TO_DBM(gain) ((gain) / 100) + /** * ieee80211_action_contains_tpc - checks if the frame contains TPC element * @skb: the skb containing the frame, length will be checked -- cgit v1.2.3 From 4e9a0f73f030e19a9259b69a7079021048e1f904 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 26 Mar 2020 09:24:14 +0100 Subject: efi: Clean up config table description arrays Increase legibility by adding whitespace to the efi_config_table_type_t arrays that describe which EFI config tables we look for when going over the firmware provided list. While at it, replace the 'name' char pointer with a char array, which is more space efficient on relocatable 64-bit kernels, as it avoids a 8 byte pointer and the associated relocation data (24 bytes when using RELA format) Signed-off-by: Ard Biesheuvel --- 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 251f1f783cdf..9b7c7ec319ac 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -379,8 +379,8 @@ typedef union { typedef struct { efi_guid_t guid; - const char *name; unsigned long *ptr; + const char name[16]; } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) -- cgit v1.2.3 From acd05785e48c01edb2c4f4d014d28478b5f19fb5 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Apr 2020 15:14:46 -0700 Subject: kvm: add capability for halt polling KVM_CAP_HALT_POLL is a per-VM capability that lets userspace control the halt-polling time, allowing halt-polling to be tuned or disabled on particular VMs. With dynamic halt-polling, a VM's VCPUs can poll from anywhere from [0, halt_poll_ns] on each halt. KVM_CAP_HALT_POLL sets the upper limit on the poll time. Signed-off-by: David Matlack Signed-off-by: Jon Cargille Reviewed-by: Jim Mattson Message-Id: <20200417221446.108733-1-jcargill@google.com> 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 5285a5568208..3cc6ccbb1183 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -503,6 +503,7 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + unsigned int max_halt_poll_ns; }; #define kvm_err(fmt, ...) \ -- cgit v1.2.3 From 76c70cb58ce30264af4b714109ee756da25d830a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:52:30 +0200 Subject: PM: sleep: core: Rename dev_pm_may_skip_resume() The name of dev_pm_may_skip_resume() may be easily confused with the power.may_skip_resume flag which is not checked by that function, so rename the former as dev_pm_skip_resume(). No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern Acked-by: Bjorn Helgaas --- include/linux/pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index e057d1fa2469..d89b7099f241 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -758,7 +758,7 @@ extern int pm_generic_poweroff_late(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); -extern bool dev_pm_may_skip_resume(struct device *dev); +extern bool dev_pm_skip_resume(struct device *dev); extern bool dev_pm_smart_suspend_and_suspended(struct device *dev); #else /* !CONFIG_PM_SLEEP */ -- cgit v1.2.3 From fa2bfead910322e44e7e0bb74364ac198a2abd32 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:52:48 +0200 Subject: PM: sleep: core: Rename dev_pm_smart_suspend_and_suspended() Because all callers of dev_pm_smart_suspend_and_suspended use it only for checking whether or not to skip driver suspend callbacks for a device, rename it to dev_pm_skip_suspend() in analogy with dev_pm_skip_resume(). No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern Acked-by: Bjorn Helgaas --- include/linux/pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index d89b7099f241..8c59a7f0bcf4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -759,7 +759,7 @@ extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); extern bool dev_pm_skip_resume(struct device *dev); -extern bool dev_pm_smart_suspend_and_suspended(struct device *dev); +extern bool dev_pm_skip_suspend(struct device *dev); #else /* !CONFIG_PM_SLEEP */ -- cgit v1.2.3 From e07515563d010d8b32967634e8dc2fdc732c1aa6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:53:01 +0200 Subject: PM: sleep: core: Rename DPM_FLAG_NEVER_SKIP Rename DPM_FLAG_NEVER_SKIP to DPM_FLAG_NO_DIRECT_COMPLETE which matches its purpose more closely. No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Bjorn Helgaas # for PCI parts Acked-by: Jeff Kirsher Acked-by: Alan Stern Acked-by: Bjorn Helgaas Acked-by: Alex Deucher --- include/linux/pm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 8c59a7f0bcf4..cdb8fbd6ab18 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -544,7 +544,7 @@ struct pm_subsys_data { * These flags can be set by device drivers at the probe time. They need not be * cleared by the drivers as the driver core will take care of that. * - * NEVER_SKIP: Do not skip all system suspend/resume callbacks for the device. + * NO_DIRECT_COMPLETE: Do not apply direct-complete optimization to the device. * SMART_PREPARE: Check the return value of the driver's ->prepare callback. * SMART_SUSPEND: No need to resume the device from runtime suspend. * LEAVE_SUSPENDED: Avoid resuming the device during system resume if possible. @@ -554,7 +554,7 @@ struct pm_subsys_data { * their ->prepare callbacks if the driver's ->prepare callback returns 0 (in * other words, the system suspend/resume callbacks can only be skipped for the * device if its driver doesn't object against that). This flag has no effect - * if NEVER_SKIP is set. + * if NO_DIRECT_COMPLETE is set. * * Setting SMART_SUSPEND instructs bus types and PM domains which may want to * runtime resume the device upfront during system suspend that doing so is not @@ -565,7 +565,7 @@ struct pm_subsys_data { * Setting LEAVE_SUSPENDED informs the PM core and middle-layer code that the * driver prefers the device to be left in suspend after system resume. */ -#define DPM_FLAG_NEVER_SKIP BIT(0) +#define DPM_FLAG_NO_DIRECT_COMPLETE BIT(0) #define DPM_FLAG_SMART_PREPARE BIT(1) #define DPM_FLAG_SMART_SUSPEND BIT(2) #define DPM_FLAG_LEAVE_SUSPENDED BIT(3) -- cgit v1.2.3 From 2a3f34750b8b07df42ab4b30b70e029d46e0d7f3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:53:20 +0200 Subject: PM: sleep: core: Rename DPM_FLAG_LEAVE_SUSPENDED Rename DPM_FLAG_LEAVE_SUSPENDED to DPM_FLAG_MAY_SKIP_RESUME which matches its purpose more closely. No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Wolfram Sang # for I2C Acked-by: Alan Stern Acked-by: Bjorn Helgaas --- include/linux/pm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index cdb8fbd6ab18..35796fc49e7a 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -547,7 +547,7 @@ struct pm_subsys_data { * NO_DIRECT_COMPLETE: Do not apply direct-complete optimization to the device. * SMART_PREPARE: Check the return value of the driver's ->prepare callback. * SMART_SUSPEND: No need to resume the device from runtime suspend. - * LEAVE_SUSPENDED: Avoid resuming the device during system resume if possible. + * MAY_SKIP_RESUME: Avoid resuming the device during system resume if possible. * * Setting SMART_PREPARE instructs bus types and PM domains which may want * system suspend/resume callbacks to be skipped for the device to return 0 from @@ -562,13 +562,13 @@ struct pm_subsys_data { * invocations of the ->suspend_late and ->suspend_noirq callbacks provided by * the driver if they decide to leave the device in runtime suspend. * - * Setting LEAVE_SUSPENDED informs the PM core and middle-layer code that the + * Setting MAY_SKIP_RESUME informs the PM core and middle-layer code that the * driver prefers the device to be left in suspend after system resume. */ #define DPM_FLAG_NO_DIRECT_COMPLETE BIT(0) #define DPM_FLAG_SMART_PREPARE BIT(1) #define DPM_FLAG_SMART_SUSPEND BIT(2) -#define DPM_FLAG_LEAVE_SUSPENDED BIT(3) +#define DPM_FLAG_MAY_SKIP_RESUME BIT(3) struct dev_pm_info { pm_message_t power_state; -- cgit v1.2.3 From 2fff3f73e8c27801b84d2315e1a49bce96b00eff Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:55:32 +0200 Subject: Documentation: PM: sleep: Update driver flags documentation Update the documentation of the driver flags for system-wide power management to reflect the current code flows and be more consistent. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 35796fc49e7a..121c104a4090 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -545,25 +545,11 @@ struct pm_subsys_data { * cleared by the drivers as the driver core will take care of that. * * NO_DIRECT_COMPLETE: Do not apply direct-complete optimization to the device. - * SMART_PREPARE: Check the return value of the driver's ->prepare callback. - * SMART_SUSPEND: No need to resume the device from runtime suspend. - * MAY_SKIP_RESUME: Avoid resuming the device during system resume if possible. - * - * Setting SMART_PREPARE instructs bus types and PM domains which may want - * system suspend/resume callbacks to be skipped for the device to return 0 from - * their ->prepare callbacks if the driver's ->prepare callback returns 0 (in - * other words, the system suspend/resume callbacks can only be skipped for the - * device if its driver doesn't object against that). This flag has no effect - * if NO_DIRECT_COMPLETE is set. - * - * Setting SMART_SUSPEND instructs bus types and PM domains which may want to - * runtime resume the device upfront during system suspend that doing so is not - * necessary from the driver's perspective. It also may cause them to skip - * invocations of the ->suspend_late and ->suspend_noirq callbacks provided by - * the driver if they decide to leave the device in runtime suspend. - * - * Setting MAY_SKIP_RESUME informs the PM core and middle-layer code that the - * driver prefers the device to be left in suspend after system resume. + * SMART_PREPARE: Take the driver ->prepare callback return value into account. + * SMART_SUSPEND: Avoid resuming the device from runtime suspend. + * MAY_SKIP_RESUME: Allow driver "noirq" and "early" callbacks to be skipped. + * + * See Documentation/driver-api/pm/devices.rst for details. */ #define DPM_FLAG_NO_DIRECT_COMPLETE BIT(0) #define DPM_FLAG_SMART_PREPARE BIT(1) -- cgit v1.2.3 From 5c05c1dbb177293636a3f5ea4caa872dfcf50ccd Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 23 Apr 2020 17:02:56 +0100 Subject: net: phylink, dsa: eliminate phylink_fixed_state_cb() Move the callback into the phylink_config structure, rather than providing a callback to set this up. Signed-off-by: Russell King Tested-by: Florian Fainelli Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phylink.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 3f8d37ec5503..cc5b452a184e 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -67,6 +67,9 @@ struct phylink_config { struct device *dev; enum phylink_op_type type; bool pcs_poll; + bool poll_fixed_state; + void (*get_fixed_state)(struct phylink_config *config, + struct phylink_link_state *state); }; /** @@ -366,9 +369,6 @@ void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); void phylink_disconnect_phy(struct phylink *); -int phylink_fixed_state_cb(struct phylink *, - void (*cb)(struct net_device *dev, - struct phylink_link_state *)); void phylink_mac_change(struct phylink *, bool up); -- cgit v1.2.3 From 3194915486b2bc3f77745774f1731b78f32ff688 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 23 Apr 2020 21:35:36 +0200 Subject: net: phy: remove genphy_no_soft_reset Since 6e2d85ec0559 ("net: phy: Stop with excessive soft reset") we don't need genphy_no_soft_reset() any longer. Not setting callback soft_reset results in a no-op now. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3941a6bcba10..e2bfb9240587 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1251,10 +1251,6 @@ static inline int genphy_config_aneg(struct phy_device *phydev) return __genphy_config_aneg(phydev, false); } -static inline int genphy_no_soft_reset(struct phy_device *phydev) -{ - return 0; -} static inline int genphy_no_ack_interrupt(struct phy_device *phydev) { return 0; -- cgit v1.2.3 From fec86c6b8369b5dd8e3a1ad3752578a737163b25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:40 +0200 Subject: iio: imu: adis: Add Managed device functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds support for a managed device version of adis_setup_buffer_and_trigger. It works exactly as the original one but it calls all the devm_iio_* functions to setup an iio buffer and trigger. Hence we do not need to care about cleaning those and we do not need to support a remove() callback for every driver using the adis library. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index dd8219138c2e..e70814d96e1c 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -448,11 +448,15 @@ struct adis_burst { unsigned int extra_len; }; +int +devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, + irq_handler_t trigger_handler); int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *)); void adis_cleanup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev); +int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); void adis_remove_trigger(struct adis *adis); @@ -461,6 +465,13 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, #else /* CONFIG_IIO_BUFFER */ +static inline int +devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, + irq_handler_t trigger_handler) +{ + return 0; +} + static inline int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *)) { @@ -472,6 +483,12 @@ static inline void adis_cleanup_buffer_and_trigger(struct adis *adis, { } +static inline int devm_adis_probe_trigger(struct adis *adis, + struct iio_dev *indio_dev) +{ + return 0; +} + static inline int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) { -- cgit v1.2.3 From 698211065d4aa71ce599b38c23452664a5a8e370 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:41 +0200 Subject: iio: imu: adis: Add irq flag variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are some ADIS devices that can configure the data ready pin polarity. Hence, we cannot hardcode our IRQ mask as IRQF_TRIGGER_RISING since we might want to have it as IRQF_TRIGGER_FALLING. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index e70814d96e1c..70e4d1d262f5 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -87,6 +87,7 @@ struct adis_data { * @msg: SPI message object * @xfer: SPI transfer objects to be used for a @msg * @current_page: Some ADIS devices have registers, this selects current page + * @irq_flag: IRQ handling flags as passed to request_irq() * @buffer: Data buffer for information read from the device * @tx: DMA safe TX buffer for SPI transfers * @rx: DMA safe RX buffer for SPI transfers @@ -113,6 +114,7 @@ struct adis { struct spi_message msg; struct spi_transfer *xfer; unsigned int current_page; + unsigned long irq_flag; void *buffer; uint8_t tx[10] ____cacheline_aligned; -- cgit v1.2.3 From b9c5eec725d67b548e4dfdc406d6ca2c6d30d1c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:42 +0200 Subject: iio: adis: Add adis_update_bits() APIs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a `regmap_update_bits()` like API to the ADIS library. It provides locked and unlocked variant. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 59 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 70e4d1d262f5..247fc4c7185c 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -333,6 +333,65 @@ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, return ret; } +int __adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask, + const u32 val, u8 size); +/** + * adis_update_bits_base() - ADIS Update bits function - Locked version + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @mask: Bitmask to change + * @val: Value to be written + * @size: Size of the register to update + * + * Updates the desired bits of @reg in accordance with @mask and @val. + */ +static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, + const u32 mask, const u32 val, u8 size) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_update_bits_base(adis, reg, mask, val, size); + mutex_unlock(&adis->state_lock); + return ret; +} + +/** + * adis_update_bits() - Wrapper macro for adis_update_bits_base - Locked version + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @mask: Bitmask to change + * @val: Value to be written + * + * This macro evaluates the sizeof of @val at compile time and calls + * adis_update_bits_base() accordingly. Be aware that using MACROS/DEFINES for + * @val can lead to undesired behavior if the register to update is 16bit. + */ +#define adis_update_bits(adis, reg, mask, val) ({ \ + BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ + __builtin_choose_expr(sizeof(val) == 4, \ + adis_update_bits_base(adis, reg, mask, val, 4), \ + adis_update_bits_base(adis, reg, mask, val, 2)); \ +}) + +/** + * adis_update_bits() - Wrapper macro for adis_update_bits_base + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @mask: Bitmask to change + * @val: Value to be written + * + * This macro evaluates the sizeof of @val at compile time and calls + * adis_update_bits_base() accordingly. Be aware that using MACROS/DEFINES for + * @val can lead to undesired behavior if the register to update is 16bit. + */ +#define __adis_update_bits(adis, reg, mask, val) ({ \ + BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ + __builtin_choose_expr(sizeof(val) == 4, \ + __adis_update_bits_base(adis, reg, mask, val, 4), \ + __adis_update_bits_base(adis, reg, mask, val, 2)); \ +}) + int adis_enable_irq(struct adis *adis, bool enable); int __adis_check_status(struct adis *adis); int __adis_initial_startup(struct adis *adis); -- cgit v1.2.3 From 3e04cb60e872b9433e523d62c39addf0bd1a18f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:43 +0200 Subject: iio: adis: Support different burst sizes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add burst_max_len to `adis_burst`. This is useful for devices which support different burst modes with different sizes. The buffer to be used in the spi transfer is allocated with this variable making sure that has space for all burst modes. The spi transfer length should hold the "real" burst length depending on the current burst mode configured in the device. Moreover, `extra_len` in `adis_burst` is made const and it should contain the smallest extra length necessary for a burst transfer. In `struct adis` was added a new `burst_extra_len` that should hold the extra bytes needed depending on the device instance being used. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 247fc4c7185c..2df67448f0d1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -83,6 +83,8 @@ struct adis_data { * @trig: IIO trigger object data * @data: ADIS chip variant specific data * @burst: ADIS burst transfer information + * @burst_extra_len: Burst extra length. Should only be used by devices that can + * dynamically change their burst mode length. * @state_lock: Lock used by the device to protect state * @msg: SPI message object * @xfer: SPI transfer objects to be used for a @msg @@ -98,7 +100,7 @@ struct adis { const struct adis_data *data; struct adis_burst *burst; - + unsigned int burst_extra_len; /** * The state_lock is meant to be used during operations that require * a sequence of SPI R/W in order to protect the SPI transfer @@ -502,11 +504,14 @@ int adis_single_conversion(struct iio_dev *indio_dev, * @en burst mode enabled * @reg_cmd register command that triggers burst * @extra_len extra length to account in the SPI RX buffer + * @burst_max_len holds the maximum burst size when the device supports + * more than one burst mode with different sizes */ struct adis_burst { bool en; unsigned int reg_cmd; - unsigned int extra_len; + const u32 extra_len; + const u32 burst_max_len; }; int -- cgit v1.2.3 From 8cf7961dab42c9177a556b719c15f5b9449c24d1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:53:36 +0200 Subject: block: bypass ->make_request_fn for blk-mq drivers Call blk_mq_make_request when no ->make_request_fn is set. This is safe now that blk_alloc_queue always sets up the pointer for make_request based drivers. This avoids an indirect call in the blk-mq driver I/O fast path, which is rather expensive due to spectre mitigations. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 51fbf6f76593..d7307795439a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -578,4 +578,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } +blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio); + #endif -- cgit v1.2.3 From 0456ea170cd665ddbb9503be92e39f96055dd5fa Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 20 Apr 2020 10:46:10 -0700 Subject: bpf: Enable more helpers for BPF_PROG_TYPE_CGROUP_{DEVICE,SYSCTL,SOCKOPT} Currently the following prog types don't fall back to bpf_base_func_proto() (instead they have cgroup_base_func_proto which has a limited set of helpers from bpf_base_func_proto): * BPF_PROG_TYPE_CGROUP_DEVICE * BPF_PROG_TYPE_CGROUP_SYSCTL * BPF_PROG_TYPE_CGROUP_SOCKOPT I don't see any specific reason why we shouldn't use bpf_base_func_proto(), every other type of program (except bpf-lirc and, understandably, tracing) use it, so let's fall back to bpf_base_func_proto for those prog types as well. This basically boils down to adding access to the following helpers: * BPF_FUNC_get_prandom_u32 * BPF_FUNC_get_smp_processor_id * BPF_FUNC_get_numa_node_id * BPF_FUNC_tail_call * BPF_FUNC_ktime_get_ns * BPF_FUNC_spin_lock (CAP_SYS_ADMIN) * BPF_FUNC_spin_unlock (CAP_SYS_ADMIN) * BPF_FUNC_jiffies64 (CAP_SYS_ADMIN) I've also added bpf_perf_event_output() because it's really handy for logging and debugging. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200420174610.77494-1-sdf@google.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 fd2b2322412d..25da6ff2a880 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1523,6 +1523,7 @@ 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; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; +extern const struct bpf_func_proto bpf_event_output_data_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 6890896bd765b0504761c61901c9804fca23bfb2 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 24 Apr 2020 16:59:41 -0700 Subject: bpf: Fix missing bpf_base_func_proto in cgroup_base_func_proto for CGROUP_NET=n linux-next build bot reported compile issue [1] with one of its configs. It looks like when we have CONFIG_NET=n and CONFIG_BPF{,_SYSCALL}=y, we are missing the bpf_base_func_proto definition (from net/core/filter.c) in cgroup_base_func_proto. I'm reshuffling the code a bit to make it work. The common helpers are moved into kernel/bpf/helpers.c and the bpf_base_func_proto is exported from there. Also, bpf_get_raw_cpu_id goes into kernel/bpf/core.c akin to existing bpf_user_rnd_u32. [1] https://lore.kernel.org/linux-next/CAKH8qBsBvKHswiX1nx40LgO+BGeTmb1NX8tiTttt_0uu6T3dCA@mail.gmail.com/T/#mff8b0c083314c68c2e2ef0211cb11bc20dc13c72 Fixes: 0456ea170cd6 ("bpf: Enable more helpers for BPF_PROG_TYPE_CGROUP_{DEVICE,SYSCTL,SOCKOPT}") Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Cc: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200424235941.58382-1-sdf@google.com --- include/linux/bpf.h | 8 ++++++++ include/linux/filter.h | 2 -- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 25da6ff2a880..5147e11e53ff 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1215,6 +1215,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, struct bpf_prog *bpf_prog_by_id(u32 id); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1365,6 +1366,12 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } + +static inline const struct bpf_func_proto * +bpf_base_func_proto(enum bpf_func_id func_id) +{ + return NULL; +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@ -1531,6 +1538,7 @@ const struct bpf_func_proto *bpf_tracing_func_proto( /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, diff --git a/include/linux/filter.h b/include/linux/filter.h index 9b5aa5c483cc..af37318bb1c5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -863,8 +863,6 @@ 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 71d19214776e61b33da48f7c1b46e522c7f78221 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Sun, 26 Apr 2020 09:15:25 -0700 Subject: bpf: add bpf_ktime_get_boot_ns() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On a device like a cellphone which is constantly suspending and resuming CLOCK_MONOTONIC is not particularly useful for keeping track of or reacting to external network events. Instead you want to use CLOCK_BOOTTIME. Hence add bpf_ktime_get_boot_ns() as a mirror of bpf_ktime_get_ns() based around CLOCK_BOOTTIME instead of CLOCK_MONOTONIC. Signed-off-by: Maciej Żenczykowski Signed-off-by: Alexei Starovoitov --- 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 5147e11e53ff..10960cfabea4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1509,6 +1509,7 @@ extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; +extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; -- cgit v1.2.3 From 26363af5643490a817272e1cc6f1d3f1d550a699 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Apr 2020 08:43:35 +0200 Subject: mm: remove watermark_boost_factor_sysctl_handler watermark_boost_factor_sysctl_handler is just a pointless wrapper for proc_dointvec_minmax, so remove it and use proc_dointvec_minmax directly. Signed-off-by: Christoph Hellwig Acked-by: David Rientjes Signed-off-by: Al Viro --- include/linux/mmzone.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b9de7d220fb..f37bb8f187fc 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -911,8 +911,6 @@ static inline int is_highmem(struct zone *zone) struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int watermark_boost_factor_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; -- cgit v1.2.3 From 2374c09b1c8a883bb9b4b2fc3756703eeb618f4a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Apr 2020 08:43:36 +0200 Subject: sysctl: remove all extern declaration from sysctl.c Extern declarations in .c files are a bad style and can lead to mismatches. Use existing definitions in headers where they exist, and otherwise move the external declarations to suitable header files. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/coredump.h | 4 ++++ include/linux/file.h | 2 ++ include/linux/mm.h | 2 ++ include/linux/mmzone.h | 2 ++ include/linux/pid.h | 3 +++ include/linux/sysctl.h | 8 ++++++++ 6 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index abf4b4e65dbb..7a899e83835d 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -22,4 +22,8 @@ extern void do_coredump(const kernel_siginfo_t *siginfo); static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif +extern int core_uses_pid; +extern char core_pattern[]; +extern unsigned int core_pipe_limit; + #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/file.h b/include/linux/file.h index 142d102f285e..122f80084a3e 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -94,4 +94,6 @@ extern void fd_install(unsigned int fd, struct file *file); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); +extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; + #endif /* __LINUX_FILE_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..9c4e7e76dedd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3140,5 +3140,7 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif +extern int sysctl_nr_trim_pages; + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f37bb8f187fc..b2af594ef0f7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -909,6 +909,7 @@ static inline int is_highmem(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; + int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, @@ -925,6 +926,7 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, extern int numa_zonelist_order_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 diff --git a/include/linux/pid.h b/include/linux/pid.h index cc896f0fc4e3..93543cbc0e6b 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -108,6 +108,9 @@ extern void transfer_pid(struct task_struct *old, struct task_struct *new, struct pid_namespace; extern struct pid_namespace init_pid_ns; +extern int pid_max; +extern int pid_max_min, pid_max_max; + /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 02fa84493f23..36143ca40b56 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -207,7 +207,15 @@ void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); +extern int pwrsw_enabled; +extern int unaligned_enabled; +extern int unaligned_dump_stack; +extern int no_unaligned_warning; + extern struct ctl_table sysctl_mount_point[]; +extern struct ctl_table random_table[]; +extern struct ctl_table firmware_config_table[]; +extern struct ctl_table epoll_table[]; #else /* CONFIG_SYSCTL */ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) -- cgit v1.2.3 From 32927393dc1ccd60fb2bdc05b9e8e88753761469 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Apr 2020 08:43:38 +0200 Subject: sysctl: pass kernel pointers to ->proc_handler Instead of having all the sysctl handlers deal with user pointers, which is rather hairy in terms of the BPF interaction, copy the input to and from userspace in common code. This also means that the strings are always NUL-terminated by the common code, making the API a little bit safer. As most handler just pass through the data to one of the common handlers a lot of the changes are mechnical. Signed-off-by: Christoph Hellwig Acked-by: Andrey Ignatov Signed-off-by: Al Viro --- include/linux/bpf-cgroup.h | 9 ++++---- include/linux/compaction.h | 2 +- include/linux/fs.h | 6 ++--- include/linux/ftrace.h | 3 +-- include/linux/hugetlb.h | 15 ++++++------- include/linux/kprobes.h | 2 +- include/linux/latencytop.h | 4 ++-- include/linux/mm.h | 12 +++++----- include/linux/mmzone.h | 23 +++++++++---------- include/linux/nmi.h | 15 +++++-------- include/linux/perf_event.h | 13 +++++------ include/linux/printk.h | 2 +- include/linux/sched/sysctl.h | 44 +++++++++++++----------------------- include/linux/security.h | 2 +- include/linux/sysctl.h | 53 ++++++++++++++++++-------------------------- include/linux/timer.h | 3 +-- include/linux/vmstat.h | 8 +++---- include/linux/writeback.h | 28 +++++++++-------------- 18 files changed, 101 insertions(+), 143 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index c11b413d5b1a..0b41fd5fc96b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -138,8 +138,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, - void __user *buf, size_t *pcount, - loff_t *ppos, void **new_buf, + void **buf, size_t *pcount, loff_t *ppos, enum bpf_attach_type type); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, @@ -302,12 +301,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf) \ +#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ - buf, count, pos, nbuf, \ + buf, count, pos, \ BPF_CGROUP_SYSCTL); \ __ret; \ }) @@ -429,7 +428,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 4b898cdbdf05..a0eabfbeb0e1 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -86,7 +86,7 @@ static inline unsigned long compact_gap(unsigned int order) #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos); + void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..9b028d260649 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3536,11 +3536,11 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_dentry(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_inodes(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); #define __FMODE_EXEC ((__force int) FMODE_EXEC) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index db95244a62d4..ddfc377de0d2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1005,8 +1005,7 @@ extern void disable_trace_on_warning(void); extern int __disable_trace_on_warning; int tracepoint_printk_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #else /* CONFIG_TRACING */ static inline void disable_trace_on_warning(void) { } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 43a1cef8f0f1..92c21c5ccc58 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -105,14 +105,13 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); - -#ifdef CONFIG_NUMA -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -#endif +int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 04bdaf01112c..594265bfd390 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -312,7 +312,7 @@ DEFINE_INSN_CACHE_OPS(optinsn); #ifdef CONFIG_SYSCTL extern int sysctl_kprobes_optimization; extern int proc_kprobes_optimization_handler(struct ctl_table *table, - int write, void __user *buffer, + int write, void *buffer, size_t *length, loff_t *ppos); #endif extern void wait_for_kprobe_optimizer(void); diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h index 9022f0c2e2e4..abe3d95f795b 100644 --- a/include/linux/latencytop.h +++ b/include/linux/latencytop.h @@ -38,8 +38,8 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter) void clear_tsk_latency_tracing(struct task_struct *p); -extern int sysctl_latencytop(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); +int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #else diff --git a/include/linux/mm.h b/include/linux/mm.h index 9c4e7e76dedd..a7b1ef8ed970 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -201,10 +201,10 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; -extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *, - size_t *, loff_t *); -extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, - size_t *, loff_t *); +int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) @@ -2957,8 +2957,8 @@ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; -int drop_caches_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #endif void drop_slab(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b2af594ef0f7..93cf20f41e26 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -910,22 +910,21 @@ static inline int is_highmem(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; -int min_free_kbytes_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, + size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; -int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, + size_t *, loff_t *); int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); - -extern int numa_zonelist_order_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); +int numa_zonelist_order_handler(struct ctl_table *, int, + void *, size_t *, loff_t *); extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 9003e29cde46..750c7f395ca9 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -202,16 +202,11 @@ static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif struct ctl_table; -extern int proc_watchdog(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_nmi_watchdog(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_soft_watchdog(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_watchdog_thresh(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_watchdog_cpumask(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); +int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); +int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *); +int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *); #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9c3e7619c929..347ea379622a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1280,15 +1280,12 @@ extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); -extern int perf_proc_update_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - +int perf_proc_update_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 diff --git a/include/linux/printk.h b/include/linux/printk.h index e061635e0409..fcde0772ec98 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -189,7 +189,7 @@ extern int printk_delay_msec; extern int dmesg_restrict; extern int -devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void __user *buf, +devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos); extern void wake_up_klogd(void); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index d4f6215ee03f..7b4d3a49b6c5 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -12,9 +12,8 @@ extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_check_interval_secs; extern int sysctl_hung_task_warnings; -extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); +int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); #else /* Avoid need for ifdefs elsewhere in the code */ enum { sysctl_hung_task_timeout_secs = 0 }; @@ -43,8 +42,7 @@ extern __read_mostly unsigned int sysctl_sched_migration_cost; extern __read_mostly unsigned int sysctl_sched_nr_migrate; int sched_proc_update_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, - loff_t *ppos); + void *buffer, size_t *length, loff_t *ppos); #endif /* @@ -72,33 +70,21 @@ extern unsigned int sysctl_sched_autogroup_enabled; extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; -extern int sched_rr_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - -extern int sched_rt_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - -#ifdef CONFIG_UCLAMP_TASK -extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -#endif - -extern int sysctl_numa_balancing(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - -extern int sysctl_schedstats(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int sched_rr_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int sched_rt_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) extern unsigned int sysctl_sched_energy_aware; -extern int sched_energy_aware_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int sched_energy_aware_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); #endif #endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/include/linux/security.h b/include/linux/security.h index a8d9310472df..6aa229b252ce 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -211,7 +211,7 @@ struct request_sock; #ifdef CONFIG_MMU extern int mmap_min_addr_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif /* security_inode_init_security callback function to write xattrs */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 36143ca40b56..f2401e45a3c2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -44,35 +44,26 @@ struct ctl_dir; extern const int sysctl_vals[]; -typedef int proc_handler (struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); - -extern int proc_dostring(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_douintvec(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec_minmax(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_douintvec_minmax(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int proc_dointvec_jiffies(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_doulongvec_minmax(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, - void __user *, size_t *, loff_t *); -extern int proc_do_large_bitmap(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_do_static_key(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, + size_t *lenp, loff_t *ppos); + +int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, + loff_t *); +int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *, + loff_t *); +int proc_doulongvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void *, + size_t *, loff_t *); +int proc_do_large_bitmap(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_do_static_key(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); /* * Register a set of sysctl names by calling register_sysctl_table @@ -246,7 +237,7 @@ static inline void setup_sysctl_set(struct ctl_table_set *p, #endif /* CONFIG_SYSCTL */ -int sysctl_max_threads(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); +int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #endif /* _LINUX_SYSCTL_H */ diff --git a/include/linux/timer.h b/include/linux/timer.h index 0dc19a8c39c9..07910ae5ddd9 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -201,8 +201,7 @@ struct ctl_table; extern unsigned int sysctl_timer_migration; int timer_migration_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif unsigned long __round_jiffies(unsigned long j, int cpu); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 292485f3d24d..cb507151710f 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -16,8 +16,8 @@ extern int sysctl_stat_interval; #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); -extern int sysctl_vm_numa_stat_handler(struct ctl_table *table, - int write, void __user *buffer, size_t *length, loff_t *ppos); +int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { @@ -274,8 +274,8 @@ void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; -int vmstat_refresh(struct ctl_table *, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); +int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, + loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a19d845dd7eb..f8a7e1a850fb 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -362,24 +362,18 @@ extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; -extern int dirty_background_ratio_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int dirty_background_bytes_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int dirty_ratio_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int dirty_bytes_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int dirty_background_ratio_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_background_bytes_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_ratio_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_bytes_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); int dirtytime_interval_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); - -struct ctl_table; -int dirty_writeback_centisecs_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); -- cgit v1.2.3 From 31c9590ae468478fe47dc0f5f0d3562b2f69450e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 18 Apr 2020 21:06:23 -0400 Subject: SUNRPC: Add "@len" parameter to gss_unwrap() Refactor: This is a pre-requisite to fixing the client-side ralign computation in gss_unwrap_resp_priv(). The length value is passed in explicitly rather that as the value of buf->len. This will subsequently allow gss_unwrap_kerberos_v1() to compute a slack and align value, instead of computing it in gss_unwrap_resp_priv(). Fixes: 35e77d21baa0 ("SUNRPC: Add rpc_auth::au_ralign field") Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_api.h | 2 ++ include/linux/sunrpc/gss_krb5.h | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 48c1b1674cbf..e9a79518d652 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -66,6 +66,7 @@ u32 gss_wrap( u32 gss_unwrap( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *inbuf); u32 gss_delete_sec_context( struct gss_ctx **ctx_id); @@ -126,6 +127,7 @@ struct gss_api_ops { u32 (*gss_unwrap)( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf); void (*gss_delete_sec_context)( void *internal_ctx_id); diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index c1d77dd8ed41..e8f8ffe7448b 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -83,7 +83,7 @@ struct gss_krb5_enctype { u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages); /* v2 encryption function */ - u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, + u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *headskip, u32 *tailskip); /* v2 decryption function */ }; @@ -255,7 +255,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset, struct xdr_buf *outbuf, struct page **pages); u32 -gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, +gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len, struct xdr_buf *buf); @@ -312,7 +312,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct page **pages); u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *plainoffset, u32 *plainlen); -- cgit v1.2.3 From a7e429a6fa6d612d1dacde96c885dc1bb4a9f400 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 18 Apr 2020 14:38:19 -0400 Subject: SUNRPC: Fix GSS privacy computation of auth->au_ralign When the au_ralign field was added to gss_unwrap_resp_priv, the wrong calculation was used. Setting au_rslack == au_ralign is probably correct for kerberos_v1 privacy, but kerberos_v2 privacy adds additional GSS data after the clear text RPC message. au_ralign needs to be smaller than au_rslack in that fairly common case. When xdr_buf_trim() is restored to gss_unwrap_kerberos_v2(), it does exactly what I feared it would: it trims off part of the clear text RPC message. However, that's because rpc_prepare_reply_pages() does not set up the rq_rcv_buf's tail correctly because au_ralign is too large. Fixing the au_ralign computation also corrects the alignment of rq_rcv_buf->pages so that the client does not have to shift reply data payloads after they are received. Fixes: 35e77d21baa0 ("SUNRPC: Add rpc_auth::au_ralign field") Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_api.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index e9a79518d652..bc07e51f20d1 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -21,6 +21,7 @@ struct gss_ctx { struct gss_api_mech *mech_type; void *internal_ctx_id; + unsigned int slack, align; }; #define GSS_C_NO_BUFFER ((struct xdr_netobj) 0) -- cgit v1.2.3 From 0a8e7b7d08466b5fc52f8e96070acc116d82a8bb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 15 Apr 2020 17:36:22 -0400 Subject: SUNRPC: Revert 241b1f419f0e ("SUNRPC: Remove xdr_buf_trim()") I've noticed that when krb5i or krb5p security is in use, retransmitted requests are missing the server's duplicate reply cache. The computed checksum on the retransmitted request does not match the cached checksum, resulting in the server performing the retransmitted request again instead of returning the cached reply. The assumptions made when removing xdr_buf_trim() were not correct. In the send paths, the upper layer has already set the segment lengths correctly, and shorting the buffer's content is simply a matter of reducing buf->len. xdr_buf_trim() is the right answer in the receive/unwrap path on both the client and the server. The buffer segment lengths have to be shortened one-by-one. On the server side in particular, head.iov_len needs to be updated correctly to enable nfsd_cache_csum() to work correctly. The simple buf->len computation doesn't do that, and that results in checksumming stale data in the buffer. The problem isn't noticed until there's significant instability of the RPC transport. At that point, the reliability of retransmit detection on the server becomes crucial. Fixes: 241b1f419f0e ("SUNRPC: Remove xdr_buf_trim()") Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 01bb41908c93..22c207b2425f 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -184,6 +184,7 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); +extern void xdr_buf_trim(struct xdr_buf *, unsigned int); extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); -- cgit v1.2.3 From 0821009445a8261ac4d32a6df4b83938e007c765 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Mon, 13 Apr 2020 10:40:12 -0700 Subject: dmaengine: fix channel index enumeration When the channel register code was changed to allow hotplug operations, dynamic indexing wasn't taken into account. When channels are randomly plugged and unplugged out of order, the serial indexing breaks. Convert channel indexing to using IDA tracking in order to allow dynamic assignment. The previous code does not cause any regression bug for existing channel allocation besides idxd driver since the hotplug usage case is only used by idxd at this point. With this change, the chan->idr_ref is also not needed any longer. We can have a device with no channels registered due to hot plug. The channel device release code no longer should attempt to free the dma device id on the last channel release. Fixes: e81274cd6b52 ("dmaengine: add support to dynamic register/unregister of channels") Reported-by: Yixin Zhang Signed-off-by: Dave Jiang Tested-by: Yixin Zhang Link: https://lore.kernel.org/r/158679961260.7674.8485924270472851852.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 31e58ec9f741..e1c03339918f 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -341,13 +341,11 @@ struct dma_chan { * @chan: driver channel device * @device: sysfs device * @dev_id: parent dma_device dev_id - * @idr_ref: reference count to gate release of dma_device dev_id */ struct dma_chan_dev { struct dma_chan *chan; struct device device; int dev_id; - atomic_t *idr_ref; }; /** @@ -835,6 +833,8 @@ struct dma_device { int dev_id; struct device *dev; struct module *owner; + struct ida chan_ida; + struct mutex chan_mutex; /* to protect chan_ida */ u32 src_addr_widths; u32 dst_addr_widths; -- cgit v1.2.3 From a78d163978567adc2733465289293dad479d842a Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 24 Apr 2020 17:08:30 +0200 Subject: vsock/virtio: fix multiple packet delivery to monitoring devices In virtio_transport.c, if the virtqueue is full, the transmitting packet is queued up and it will be sent in the next iteration. This causes the same packet to be delivered multiple times to monitoring devices. We want to continue to deliver packets to monitoring devices before it is put in the virtqueue, to avoid that replies can appear in the packet capture before the transmitted packet. This patch fixes the issue, adding a new flag (tap_delivered) in struct virtio_vsock_pkt, to check if the packet is already delivered to monitoring devices. In vhost/vsock.c, we are splitting packets, so we must set 'tap_delivered' to false when we queue up the same virtio_vsock_pkt to handle the remaining bytes. Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 71c81e0dc8f2..dc636b727179 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,6 +48,7 @@ struct virtio_vsock_pkt { u32 len; u32 off; bool reply; + bool tap_delivered; }; struct virtio_vsock_pkt_info { -- cgit v1.2.3 From ddc465936643108d5ba61f88594a2868d6a156ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Thu, 5 Mar 2020 23:22:55 +0100 Subject: Revert "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 This reverts commit f452ee096d95482892b101bde4fd037fa025d3cc. The workaround became unnecessary with commit 43756e347f21 ("scripts/kernel-doc: Add support for named variable macro arguments"). Signed-off-by: Jonathan Neuschäfer 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 8214cdc715f2..7375bb3da140 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -371,7 +371,7 @@ 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() @@ -646,7 +646,7 @@ 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 6be7436d2245d3dd8b9a8f949367c13841c23308 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 10 Apr 2020 13:47:41 -0700 Subject: rcu: Add rcu_gp_might_be_stalled() This commit adds rcu_gp_might_be_stalled(), which returns true if there is some reason to believe that the RCU grace period is stalled. The use case is where an RCU free-memory path needs to allocate memory in order to free it, a situation that should be avoided where possible. But where it is necessary, there is always the alternative of using synchronize_rcu() to wait for a grace period in order to avoid the allocation. And if the grace period is stalled, allocating memory to asynchronously wait for it is a bad idea of epic proportions: Far better to let others use the memory, because these others might actually be able to free that memory before the grace period ends. Thus, rcu_gp_might_be_stalled() can be used to help decide whether allocating memory on an RCU free path is a semi-reasonable course of action. Cc: Joel Fernandes Cc: Uladzislau Rezki Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 045c28b71f4f..dbf5ac439594 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -87,6 +87,7 @@ static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } static inline void rcu_momentary_dyntick_idle(void) { } static inline void kfree_rcu_scheduler_running(void) { } +static inline bool rcu_gp_might_be_stalled(void) { return false; } /* 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 45f3f66bb04d..fbc26274af4d 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -39,6 +39,7 @@ void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); void rcu_momentary_dyntick_idle(void); void kfree_rcu_scheduler_running(void); +bool rcu_gp_might_be_stalled(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); -- cgit v1.2.3 From f0bdf6d473cf12a488a78422e15aafdfe77cf853 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sat, 15 Feb 2020 14:52:32 -0800 Subject: rcu: Remove unused ->rcu_read_unlock_special.b.deferred_qs field The ->rcu_read_unlock_special.b.deferred_qs field is set to true in rcu_read_unlock_special() but never set to false. This is not particularly useful, so this commit removes this field. The only possible justification for this field is to ease debugging of RCU deferred quiscent states, but the combination of the other ->rcu_read_unlock_special fields plus ->rcu_blocked_node and of course ->rcu_read_lock_nesting should cover debugging needs. And if this last proves incorrect, this patch can always be reverted, along with the required setting of ->rcu_read_unlock_special.b.deferred_qs to false in rcu_preempt_deferred_qs_irqrestore(). Signed-off-by: Lai Jiangshan Signed-off-by: Paul E. McKenney --- 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 4418f5cb8324..a4b727f57095 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -613,7 +613,7 @@ union rcu_special { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ - u8 deferred_qs; + u8 pad; /* No garbage from compiler! */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; -- cgit v1.2.3 From 2beaf3280e57bb891f8012dca49c87ed0f01e2f3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 11 Mar 2020 14:23:21 -0700 Subject: sched/core: Add function to sample state of locked-down task A running task's state can be sampled in a consistent manner (for example, for diagnostic purposes) simply by invoking smp_call_function_single() on its CPU, which may be obtained using task_cpu(), then having the IPI handler verify that the desired task is in fact still running. However, if the task is not running, this sampling can in theory be done immediately and directly. In practice, the task might start running at any time, including during the sampling period. Gaining a consistent sample of a not-running task therefore requires that something be done to lock down the target task's state. This commit therefore adds a try_invoke_on_locked_down_task() function that invokes a specified function if the specified task can be locked down, returning true if successful and if the specified function returns true. Otherwise this function simply returns false. Given that the function passed to try_invoke_on_nonrunning_task() might be invoked with a runqueue lock held, that function had better be quite lightweight. The function is passed the target task's task_struct pointer and the argument passed to try_invoke_on_locked_down_task(), allowing easy access to task state and to a location for further variables to be passed in and out. Note that the specified function will be called even if the specified task is currently running. The function can use ->on_rq and task_curr() to quickly and easily determine the task's state, and can return false if this state is not to the function's liking. The caller of the try_invoke_on_locked_down_task() would then see the false return value, and could take appropriate action, for example, trying again later or sending an IPI if matters are more urgent. It is expected that use cases such as the RCU CPU stall warning code will simply return false if the task is currently running. However, there are use cases involving nohz_full CPUs where the specified function might instead fall back to an alternative sampling scheme that relies on heavier synchronization (such as memory barriers) in the target task. Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Ben Segall Cc: Mel Gorman [ paulmck: Apply feedback from Peter Zijlstra and Steven Rostedt. ] [ paulmck: Invoke if running to handle feedback from Mathieu Desnoyers. ] Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/wait.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index feeb6be5cad6..898c890fc153 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1149,4 +1149,6 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i (wait)->flags = 0; \ } while (0) +bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg); + #endif /* _LINUX_WAIT_H */ -- cgit v1.2.3 From b3d73156b075014ce5b2609f4f47723d6c0c23d6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Mar 2020 13:58:27 -0800 Subject: rcu: Reinstate synchronize_rcu_mult() With the advent and likely usage of synchronize_rcu_rude(), there is again a need to wait on multiple types of RCU grace periods, for example, call_rcu_tasks() and call_rcu_tasks_rude(). This commit therefore reinstates synchronize_rcu_mult() in order to allow these grace periods to be straightforwardly waited on concurrently. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_wait.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index c0578ba23c1a..699b938358bf 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -31,4 +31,23 @@ do { \ #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) +/** + * synchronize_rcu_mult - Wait concurrently for multiple grace periods + * @...: List of call_rcu() functions for different grace periods to wait on + * + * This macro waits concurrently for multiple types of RCU grace periods. + * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait + * on concurrent RCU and RCU-tasks grace periods. Waiting on a given SRCU + * domain requires you to write a wrapper function for that SRCU domain's + * call_srcu() function, with this wrapper supplying the pointer to the + * corresponding srcu_struct. + * + * The first argument tells Tiny RCU's _wait_rcu_gp() not to + * bother waiting for RCU. The reason for this is because anywhere + * synchronize_rcu_mult() can be called is automatically already a full + * grace period. + */ +#define synchronize_rcu_mult(...) \ + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ -- cgit v1.2.3 From 5873b8a94e5dae04b8e11fc798df512614e6d1e7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 3 Mar 2020 11:49:21 -0800 Subject: rcu-tasks: Refactor RCU-tasks to allow variants to be added This commit splits out generic processing from RCU-tasks-specific processing in order to allow additional flavors to be added. It also adds a def_bool TASKS_RCU_GENERIC to enable the common RCU-tasks infrastructure code. This is primarily, but not entirely, a code-movement commit. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2678a37c3169..5523145e0a78 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -129,7 +129,7 @@ static inline void rcu_init_nohz(void) { } * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ -#ifdef CONFIG_TASKS_RCU +#ifdef CONFIG_TASKS_RCU_GENERIC #define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ @@ -140,14 +140,14 @@ void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); -#else /* #ifdef CONFIG_TASKS_RCU */ +#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } -#endif /* #else #ifdef CONFIG_TASKS_RCU */ +#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU -- cgit v1.2.3 From c84aad765406c4c7573ce449e8a9977ebb8f4cb9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 Mar 2020 21:06:43 -0800 Subject: rcu-tasks: Add an RCU-tasks rude variant This commit adds a "rude" variant of RCU-tasks that has as quiescent states schedule(), cond_resched_tasks_rcu_qs(), userspace execution, and (in theory, anyway) cond_resched(). In other words, RCU-tasks rude readers are regions of code with preemption disabled, but excluding code early in the CPU-online sequence and late in the CPU-offline sequence. Updates make use of IPIs and force an IPI and a context switch on each online CPU. This variant is useful in some situations in tracing. Suggested-by: Steven Rostedt [ paulmck: Apply EXPORT_SYMBOL_GPL() feedback from Qiujun Huang. ] Signed-off-by: Paul E. McKenney [ paulmck: Apply review feedback from Steve Rostedt. ] --- include/linux/rcupdate.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5523145e0a78..2be97a83f266 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -37,6 +37,7 @@ /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); +void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU @@ -138,6 +139,8 @@ static inline void rcu_init_nohz(void) { } #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); +void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ -- cgit v1.2.3 From d5f177d35c24429c87db2567d20563fc16f7e8f6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 9 Mar 2020 19:56:53 -0700 Subject: rcu-tasks: Add an RCU Tasks Trace to simplify protection of tracing hooks Because RCU does not watch exception early-entry/late-exit, idle-loop, or CPU-hotplug execution, protection of tracing and BPF operations is needlessly complicated. This commit therefore adds a variant of Tasks RCU that: o Has explicit read-side markers to allow finite grace periods in the face of in-kernel loops for PREEMPT=n builds. These markers are rcu_read_lock_trace() and rcu_read_unlock_trace(). o Protects code in the idle loop, exception entry/exit, and CPU-hotplug code paths. In this respect, RCU-tasks trace is similar to SRCU, but with lighter-weight readers. o Avoids expensive read-side instruction, having overhead similar to that of Preemptible RCU. There are of course downsides: o The grace-period code can send IPIs to CPUs, even when those CPUs are in the idle loop or in nohz_full userspace. This is mitigated by later commits. o It is necessary to scan the full tasklist, much as for Tasks RCU. o There is a single callback queue guarded by a single lock, again, much as for Tasks RCU. However, those early use cases that request multiple grace periods in quick succession are expected to do so from a single task, which makes the single lock almost irrelevant. If needed, multiple callback queues can be provided using any number of schemes. Perhaps most important, this variant of RCU does not affect the vanilla flavors, rcu_preempt and rcu_sched. The fact that RCU Tasks Trace readers can operate from idle, offline, and exception entry/exit in no way enables rcu_preempt and rcu_sched readers to do so. The memory ordering was outlined here: https://lore.kernel.org/lkml/20200319034030.GX3199@paulmck-ThinkPad-P72/ This effort benefited greatly from off-list discussions of BPF requirements with Alexei Starovoitov and Andrii Nakryiko. At least some of the on-list discussions are captured in the Link: tags below. In addition, KCSAN was quite helpful in finding some early bugs. Link: https://lore.kernel.org/lkml/20200219150744.428764577@infradead.org/ Link: https://lore.kernel.org/lkml/87mu8p797b.fsf@nanos.tec.linutronix.de/ Link: https://lore.kernel.org/lkml/20200225221305.605144982@linutronix.de/ Cc: Alexei Starovoitov Cc: Andrii Nakryiko [ paulmck: Apply feedback from Steve Rostedt and Joel Fernandes. ] [ paulmck: Decrement trc_n_readers_need_end upon IPI failure. ] [ paulmck: Fix locking issue reported by rcutorture. ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 84 ++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 8 ++++ 2 files changed, 92 insertions(+) create mode 100644 include/linux/rcupdate_trace.h (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h new file mode 100644 index 000000000000..ed97e10817bd --- /dev/null +++ b/include/linux/rcupdate_trace.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Read-Copy Update mechanism for mutual exclusion, adapted for tracing. + * + * Copyright (C) 2020 Paul E. McKenney. + */ + +#ifndef __LINUX_RCUPDATE_TRACE_H +#define __LINUX_RCUPDATE_TRACE_H + +#include +#include + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +extern struct lockdep_map rcu_trace_lock_map; + +static inline int rcu_read_lock_trace_held(void) +{ + return lock_is_held(&rcu_trace_lock_map); +} + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +static inline int rcu_read_lock_trace_held(void) +{ + return 1; +} + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +#ifdef CONFIG_TASKS_TRACE_RCU + +void rcu_read_unlock_trace_special(struct task_struct *t); + +/** + * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section + * + * When synchronize_rcu_trace() is invoked by one task, then that task + * is guaranteed to block until all other tasks exit their read-side + * critical sections. Similarly, if call_rcu_trace() is invoked on one + * task while other tasks are within RCU read-side critical sections, + * invocation of the corresponding RCU callback is deferred until after + * the all the other tasks exit their critical sections. + * + * For more details, please see the documentation for rcu_read_lock(). + */ +static inline void rcu_read_lock_trace(void) +{ + struct task_struct *t = current; + + WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); + rcu_lock_acquire(&rcu_trace_lock_map); +} + +/** + * rcu_read_unlock_trace - mark end of RCU-trace read-side critical section + * + * Pairs with a preceding call to rcu_read_lock_trace(), and nesting is + * allowed. Invoking a rcu_read_unlock_trace() when there is no matching + * rcu_read_lock_trace() is verboten, and will result in lockdep complaints. + * + * For more details, please see the documentation for rcu_read_unlock(). + */ +static inline void rcu_read_unlock_trace(void) +{ + int nesting; + struct task_struct *t = current; + + rcu_lock_release(&rcu_trace_lock_map); + nesting = READ_ONCE(t->trc_reader_nesting) - 1; + WRITE_ONCE(t->trc_reader_nesting, nesting); + if (likely(!READ_ONCE(t->trc_reader_need_end)) || nesting) + return; // We assume shallow reader nesting. + rcu_read_unlock_trace_special(t); +} + +void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); +void synchronize_rcu_tasks_trace(void); +void rcu_barrier_tasks_trace(void); + +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ + +#endif /* __LINUX_RCUPDATE_TRACE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index a4b727f57095..864f60e51c41 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -724,6 +724,14 @@ struct task_struct { struct list_head rcu_tasks_holdout_list; #endif /* #ifdef CONFIG_TASKS_RCU */ +#ifdef CONFIG_TASKS_TRACE_RCU + int trc_reader_nesting; + int trc_ipi_to_cpu; + bool trc_reader_need_end; + bool trc_reader_checked; + struct list_head trc_holdout_list; +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ + struct sched_info sched_info; struct list_head tasks; -- cgit v1.2.3 From 43766c3eadcf6033c92eb953f88801aebac0f785 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 16 Mar 2020 20:38:29 -0700 Subject: rcu-tasks: Make RCU Tasks Trace make use of RCU scheduler hooks This commit makes the calls to rcu_tasks_qs() detect and report quiescent states for RCU tasks trace. If the task is in a quiescent state and if ->trc_reader_checked is not yet set, the task sets its own ->trc_reader_checked. This will cause the grace-period kthread to remove it from the holdout list if it still remains there. [ paulmck: Fix conditional compilation per kbuild test robot feedback. ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 44 +++++++++++++++++++++++++++++++++++++------- include/linux/rcutiny.h | 2 +- 2 files changed, 38 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2be97a83f266..659cbfa7581a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -131,20 +131,50 @@ static inline void rcu_init_nohz(void) { } * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC -#define rcu_tasks_qs(t) \ - do { \ - if (READ_ONCE((t)->rcu_tasks_holdout)) \ - WRITE_ONCE((t)->rcu_tasks_holdout, false); \ + +# ifdef CONFIG_TASKS_RCU +# define rcu_tasks_classic_qs(t, preempt) \ + do { \ + if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ + WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) -#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +# else +# define rcu_tasks_classic_qs(t, preempt) do { } while (0) +# define call_rcu_tasks call_rcu +# define synchronize_rcu_tasks synchronize_rcu +# endif + +# ifdef CONFIG_TASKS_RCU_TRACE +# define rcu_tasks_trace_qs(t) \ + do { \ + if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ + !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ + smp_store_release(&(t)->trc_reader_checked, true); \ + smp_mb(); /* Readers partitioned by store. */ \ + } \ + } while (0) +# else +# define rcu_tasks_trace_qs(t) do { } while (0) +# endif + +#define rcu_tasks_qs(t, preempt) \ +do { \ + rcu_tasks_classic_qs((t), (preempt)); \ + rcu_tasks_trace_qs((t)); \ +} while (0) + +# ifdef CONFIG_TASKS_RUDE_RCU void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); +# endif + +#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ -#define rcu_tasks_qs(t) do { } while (0) +#define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu @@ -161,7 +191,7 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - rcu_tasks_qs(current); \ + rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 045c28b71f4f..d77e11186afd 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -49,7 +49,7 @@ static inline void rcu_softirq_qs(void) #define rcu_note_context_switch(preempt) \ do { \ rcu_qs(); \ - rcu_tasks_qs(current); \ + rcu_tasks_qs(current, (preempt)); \ } while (0) static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) -- cgit v1.2.3 From 276c410448dbca357a2bc3539acfe04862e5f172 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 17 Mar 2020 16:02:06 -0700 Subject: rcu-tasks: Split ->trc_reader_need_end This commit splits ->trc_reader_need_end by using the rcu_special union. This change permits readers to check to see if a memory barrier is required without any added overhead in the common case where no such barrier is required. This commit also adds the read-side checking. Later commits will add the machinery to properly set the new ->trc_reader_special.b.need_mb field. This commit also makes rcu_read_unlock_trace_special() tolerate nested read-side critical sections within interrupt and NMI handlers. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 11 +++++++---- include/linux/sched.h | 4 ++-- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index ed97e10817bd..c42b365ca176 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -31,7 +31,7 @@ static inline int rcu_read_lock_trace_held(void) #ifdef CONFIG_TASKS_TRACE_RCU -void rcu_read_unlock_trace_special(struct task_struct *t); +void rcu_read_unlock_trace_special(struct task_struct *t, int nesting); /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section @@ -50,6 +50,8 @@ static inline void rcu_read_lock_trace(void) struct task_struct *t = current; WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); + if (t->trc_reader_special.b.need_mb) + smp_mb(); // Pairs with update-side barriers rcu_lock_acquire(&rcu_trace_lock_map); } @@ -69,10 +71,11 @@ static inline void rcu_read_unlock_trace(void) rcu_lock_release(&rcu_trace_lock_map); nesting = READ_ONCE(t->trc_reader_nesting) - 1; - WRITE_ONCE(t->trc_reader_nesting, nesting); - if (likely(!READ_ONCE(t->trc_reader_need_end)) || nesting) + if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) { + WRITE_ONCE(t->trc_reader_nesting, nesting); return; // We assume shallow reader nesting. - rcu_read_unlock_trace_special(t); + } + rcu_read_unlock_trace_special(t, nesting); } void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); diff --git a/include/linux/sched.h b/include/linux/sched.h index 864f60e51c41..9437b53cc603 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -613,7 +613,7 @@ union rcu_special { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ - u8 pad; /* No garbage from compiler! */ + u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; @@ -727,7 +727,7 @@ struct task_struct { #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; - bool trc_reader_need_end; + union rcu_special trc_reader_special; bool trc_reader_checked; struct list_head trc_holdout_list; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ -- cgit v1.2.3 From 9ae58d7bd11f1fc4c96389df11751f8593d8bd33 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 18 Mar 2020 17:16:37 -0700 Subject: rcu-tasks: Add Kconfig option to mediate smp_mb() vs. IPI This commit provides a new TASKS_TRACE_RCU_READ_MB Kconfig option that enables use of read-side memory barriers by both rcu_read_lock_trace() and rcu_read_unlock_trace() when the are executed with the current->trc_reader_special.b.need_mb flag set. This flag is currently never set. Doing that is the subject of a later commit. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index c42b365ca176..4c25a41f8b27 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -50,7 +50,8 @@ static inline void rcu_read_lock_trace(void) struct task_struct *t = current; WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); - if (t->trc_reader_special.b.need_mb) + if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && + t->trc_reader_special.b.need_mb) smp_mb(); // Pairs with update-side barriers rcu_lock_acquire(&rcu_trace_lock_map); } -- cgit v1.2.3 From be44ae62431196ac2a55198c0855028fff3ccfb4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 25 Feb 2020 21:09:19 -0800 Subject: locktorture.c: Fix if-statement empty body warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When using -Wextra, gcc complains about torture_preempt_schedule() when its definition is empty (i.e., when CONFIG_PREEMPTION is not set/enabled). Fix these warnings by adding an empty do-while block for that macro when CONFIG_PREEMPTION is not set. Fixes these build warnings: ../kernel/locking/locktorture.c:119:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:166:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:337:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:490:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:528:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:553:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] I have verified that there is no object code change (with gcc 7.5.0). Signed-off-by: Randy Dunlap Cc: Davidlohr Bueso Cc: Josh Triplett Signed-off-by: "Paul E. McKenney" --- include/linux/torture.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 6241f59e2d6f..629b66e6c161 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -89,7 +89,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #ifdef CONFIG_PREEMPTION #define torture_preempt_schedule() preempt_schedule() #else -#define torture_preempt_schedule() +#define torture_preempt_schedule() do { } while (0) #endif #endif /* __LINUX_TORTURE_H */ -- cgit v1.2.3 From 4b8d7d4c599182393421c190bae3604b4db9629a Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Sun, 26 Apr 2020 15:22:00 +0200 Subject: bridge: mrp: Extend bridge interface To integrate MRP into the bridge, first the bridge needs to be aware of ports that are part of an MRP ring and which rings are on the bridge. Therefore extend bridge interface with the following: - add new flag(BR_MPP_AWARE) to the net bridge ports, this bit will be set when the port is added to an MRP instance. In this way it knows if the frame was received on MRP ring port - add new flag(BR_MRP_LOST_CONT) to the net bridge ports, this bit will be set when the port lost the continuity of MRP Test frames. - add a list of MRP instances Reviewed-by: Nikolay Aleksandrov Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 9e57c4411734..b3a8d3054af0 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -47,6 +47,8 @@ struct br_ip_list { #define BR_BCAST_FLOOD BIT(14) #define BR_NEIGH_SUPPRESS BIT(15) #define BR_ISOLATED BIT(16) +#define BR_MRP_AWARE BIT(17) +#define BR_MRP_LOST_CONT BIT(18) #define BR_DEFAULT_AGEING_TIME (300 * HZ) -- cgit v1.2.3 From e145d9a184f23639edc864e2fa08fcc1853361a4 Mon Sep 17 00:00:00 2001 From: Akash Asthana Date: Wed, 15 Apr 2020 15:53:10 +0530 Subject: interconnect: Add devm_of_icc_get() as exported API for users Users can use devm version of of_icc_get() to benefit from automatic resource release. Signed-off-by: Akash Asthana Reviewed by: Matthias Kaehlcke Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/1586946198-13912-2-git-send-email-akashast@codeaurora.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index d70a914cba11..770692421f4c 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -28,6 +28,7 @@ struct device; struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id); struct icc_path *of_icc_get(struct device *dev, const char *name); +struct icc_path *devm_of_icc_get(struct device *dev, const char *name); void icc_put(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); @@ -46,6 +47,12 @@ static inline struct icc_path *of_icc_get(struct device *dev, return NULL; } +static inline struct icc_path *devm_of_icc_get(struct device *dev, + const char *name) +{ + return NULL; +} + static inline void icc_put(struct icc_path *path) { } -- cgit v1.2.3 From 40a571bc408bf10ac8be0eadf838483b9cf90141 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:41:27 +0300 Subject: mtd: spi-nor: fix kernel-doc for 'struct spi_nor' When introducing 'struct spi_nor', a number of issues was added in its kernel-doc comment: - double article in the heading kernel-doc comment; - "point" instead of "pointer" for the 'mtd' and 'dev' fields; - "a" articles instead of "an" for the 'dev' field; - acronyms in the lower case for the 'dev' field; - missing "pointer to" for the 'priv' field. Fix all of those at once... Fixes: 6e602ef73334 ("mtd: spi-nor: add the basic data structures") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 1cc8ed5d59ed..d3fcf7654040 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -327,10 +327,10 @@ struct spi_nor_manufacturer; struct spi_nor_flash_parameter; /** - * struct spi_nor - Structure for defining a the SPI NOR layer - * @mtd: point to a mtd_info structure + * struct spi_nor - Structure for defining the SPI NOR layer + * @mtd: pointer to an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations - * @dev: point to a spi device, or a spi nor controller device. + * @dev: pointer to an SPI device or an SPI NOR controller device * @spimem: point to the spi mem device * @bouncebuf: bounce buffer used when the buffer passed by the MTD * layer is not DMA-able @@ -354,7 +354,7 @@ struct spi_nor_flash_parameter; * settings that can be overwritten by the spi_nor_fixups * hooks, or dynamically when parsing the SFDP tables. * @dirmap: pointers to struct spi_mem_dirmap_desc for reads/writes. - * @priv: the private data + * @priv: pointer to the private data */ struct spi_nor { struct mtd_info mtd; -- cgit v1.2.3 From ba0aa311b0eb9d0a66a1b6b6fdeaa3b7584b798a Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:44:16 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::mtd When embedding 'struct mtd_info' within 'struct spi_nor', the kernel-doc comment was forgotten. Fix it by dropping the "pointer to" part from the comment. Fixes: 1976367173a4 ("mtd: spi-nor: embed struct mtd_info within struct spi_nor") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index d3fcf7654040..20077881c955 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -328,7 +328,7 @@ struct spi_nor_flash_parameter; /** * struct spi_nor - Structure for defining the SPI NOR layer - * @mtd: pointer to an mtd_info structure + * @mtd: an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations * @dev: pointer to an SPI device or an SPI NOR controller device * @spimem: point to the spi mem device -- cgit v1.2.3 From ba053dd3b4d841e17e910d0b91e22d9ea813fa39 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:45:49 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::reg_proto When adding the '{read|write|reg}_proto' fields to 'struct spi_nor', a colon was missed in the comment for the spi_nor::reg_proto' -- add it. Fixes: cfc5604c488c ("mtd: spi-nor: introduce SPI 1-2-2 and SPI 1-4-4 protocols") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 20077881c955..1b2143d921ac 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -347,7 +347,7 @@ struct spi_nor_flash_parameter; * @flags: flag options for the current SPI-NOR (SNOR_F_*) * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations - * @reg_proto the SPI protocol for read_reg/write_reg/erase operations + * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. * The structure includes legacy flash parameters and -- cgit v1.2.3 From 80cb801144265866ce29fabe5ea7ac8588aa673c Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:49:48 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::info When adding the 'info' field to 'struct spi_nor', some acronyms were in lower case and some in upper case and the JEDEC acronym mistyped -- fix these issues. Fixes: 46dde01f6bab ("mtd: spi-nor: add spi_nor_init() function") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 1b2143d921ac..3333103c519b 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -335,7 +335,7 @@ struct spi_nor_flash_parameter; * @bouncebuf: bounce buffer used when the buffer passed by the MTD * layer is not DMA-able * @bouncebuf_size: size of the bounce buffer - * @info: spi-nor part JDEC MFR id and other info + * @info: SPI NOR part JEDEC MFR ID and other info * @manufacturer: spi-nor manufacturer * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes -- cgit v1.2.3 From 1f241ad2a093b889122bd6bfdce57551d21bba5b Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:50:57 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::spimem When adding the 'spimem' field to 'struct spi_nor', a grammar mistake ("point" instead of "pointer") was made -- fix it and convert the SPI acronym to uppercase and fully spell out "memory", while at it... Fixes: b35b9a10362 ("mtd: spi-nor: Move m25p80 code in spi-nor.c") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 3333103c519b..bebff2729c18 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -331,7 +331,7 @@ struct spi_nor_flash_parameter; * @mtd: an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations * @dev: pointer to an SPI device or an SPI NOR controller device - * @spimem: point to the spi mem device + * @spimem: pointer to the SPI memory device * @bouncebuf: bounce buffer used when the buffer passed by the MTD * layer is not DMA-able * @bouncebuf_size: size of the bounce buffer -- cgit v1.2.3 From 767dea211cd0c68d8116d8c3b5104e82454fb44b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Apr 2020 07:17:03 +0200 Subject: x86/tboot: Mark tboot static This structure is only really used in tboot.c. The only exception is a single tboot_enabled check, but for that we don't need an inline function. Signed-off-by: Christoph Hellwig Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200428051703.1625952-1-hch@lst.de --- include/linux/tboot.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tboot.h b/include/linux/tboot.h index 5424bc6feac8..c7e424766360 100644 --- a/include/linux/tboot.h +++ b/include/linux/tboot.h @@ -121,13 +121,7 @@ struct tboot { #define TBOOT_UUID {0xff, 0x8d, 0x3c, 0x66, 0xb3, 0xe8, 0x82, 0x4b, 0xbf,\ 0xaa, 0x19, 0xea, 0x4d, 0x5, 0x7a, 0x8} -extern struct tboot *tboot; - -static inline int tboot_enabled(void) -{ - return tboot != NULL; -} - +bool tboot_enabled(void); extern void tboot_probe(void); extern void tboot_shutdown(u32 shutdown_type); extern struct acpi_table_header *tboot_get_dmar_table( -- cgit v1.2.3 From 501be6c1c72417eab05e7413671a38ea991a8ebc Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 25 Mar 2020 21:16:03 +0100 Subject: drm/tegra: Fix SMMU support on Tegra124 and Tegra210 When testing whether or not to enable the use of the SMMU, consult the supported DMA mask rather than the actually configured DMA mask, since the latter might already have been restricted. Fixes: 2d9384ff9177 ("drm/tegra: Relax IOMMU usage criteria on old Tegra") Tested-by: Jon Hunter Signed-off-by: Thierry Reding --- include/linux/host1x.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 62d216ff1097..c230b4e70d75 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -17,9 +17,12 @@ enum host1x_class { HOST1X_CLASS_GR3D = 0x60, }; +struct host1x; struct host1x_client; struct iommu_group; +u64 host1x_get_dma_mask(struct host1x *host1x); + /** * struct host1x_client_ops - host1x client operations * @init: host1x client initialization code -- cgit v1.2.3 From 0c6b20a1d720ad1d43a2aca0ffa1af07c201b55d Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 27 Apr 2020 13:28:27 +0530 Subject: bus: mhi: core: Add support for MHI suspend and resume Add support for MHI suspend and resume states. While at it, the mhi_notify() function needs to be exported as well. Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200427075829.9304-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index ad1996001965..a4288f4d656f 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -568,6 +568,13 @@ void mhi_driver_unregister(struct mhi_driver *mhi_drv); void mhi_set_mhi_state(struct mhi_controller *mhi_cntrl, enum mhi_state state); +/** + * mhi_notify - Notify the MHI client driver about client device status + * @mhi_dev: MHI device instance + * @cb_reason: MHI callback reason + */ +void mhi_notify(struct mhi_device *mhi_dev, enum mhi_callback cb_reason); + /** * mhi_prepare_for_power_up - Do pre-initialization before power up. * This is optional, call this before power up if @@ -604,6 +611,18 @@ void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful); */ void mhi_unprepare_after_power_down(struct mhi_controller *mhi_cntrl); +/** + * mhi_pm_suspend - Move MHI into a suspended state + * @mhi_cntrl: MHI controller + */ +int mhi_pm_suspend(struct mhi_controller *mhi_cntrl); + +/** + * mhi_pm_resume - Resume MHI from suspended state + * @mhi_cntrl: MHI controller + */ +int mhi_pm_resume(struct mhi_controller *mhi_cntrl); + /** * mhi_download_rddm_img - Download ramdump image from device for * debugging purpose. -- cgit v1.2.3 From 7536ad8dbfcfd56cd04d005b76cd9ecf2036e220 Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Tue, 14 Apr 2020 15:47:54 -0500 Subject: firmware: fpga: replace the error codes with the standard ones MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Intel service layer driver has defined error codes for the specific services, which started from FPGA configuration then RSU (Remote Status Update). Intel service layer driver should define the standard error codes rather than keep adding more error codes for the new services. The standard error codes will be used by all the clients of Intel service layer driver. Replace FPGA and RSU specific error codes with Intel service layer’s Common error codes. Signed-off-by: Richard Gong Link: https://lore.kernel.org/r/1586897274-307-2-git-send-email-richard.gong@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/intel/stratix10-smc.h | 49 +++++++-------- .../linux/firmware/intel/stratix10-svc-client.h | 71 +++++++++------------- 2 files changed, 51 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index 013ae4819deb..682dbf694007 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -54,32 +54,25 @@ * Secure monitor software doesn't recognize the request. * * INTEL_SIP_SMC_STATUS_OK: - * FPGA configuration completed successfully, - * In case of FPGA configuration write operation, it means secure monitor - * software can accept the next chunk of FPGA configuration data. + * Secure monitor software accepts the service client's request. * - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY: - * In case of FPGA configuration write operation, it means secure monitor - * software is still processing previous data & can't accept the next chunk - * of data. Service driver needs to issue - * INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE call to query the - * completed block(s). + * INTEL_SIP_SMC_STATUS_BUSY: + * Secure monitor software is still processing service client's request. * - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR: - * There is error during the FPGA configuration process. + * INTEL_SIP_SMC_STATUS_REJECTED: + * Secure monitor software reject the service client's request. * - * INTEL_SIP_SMC_REG_ERROR: - * There is error during a read or write operation of the protected registers. + * INTEL_SIP_SMC_STATUS_ERROR: + * There is error during the process of service request. * * INTEL_SIP_SMC_RSU_ERROR: - * There is error during a remote status update. + * There is error during the process of remote status update request. */ #define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF #define INTEL_SIP_SMC_STATUS_OK 0x0 -#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY 0x1 -#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_REJECTED 0x2 -#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR 0x4 -#define INTEL_SIP_SMC_REG_ERROR 0x5 +#define INTEL_SIP_SMC_STATUS_BUSY 0x1 +#define INTEL_SIP_SMC_STATUS_REJECTED 0x2 +#define INTEL_SIP_SMC_STATUS_ERROR 0x4 #define INTEL_SIP_SMC_RSU_ERROR 0x7 /** @@ -95,7 +88,7 @@ * a2-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, or INTEL_SIP_SMC_STATUS_ERROR. * a1-3: not used. */ #define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_START 1 @@ -115,8 +108,8 @@ * a3-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_BUSY or + * INTEL_SIP_SMC_STATUS_ERROR. * a1: 64bit physical address of 1st completed memory block if any completed * block, otherwise zero value. * a2: 64bit physical address of 2nd completed memory block if any completed @@ -133,15 +126,15 @@ * * Sync call used by service driver at EL1 to track the completed write * transactions. This request is called after INTEL_SIP_SMC_FPGA_CONFIG_WRITE - * call returns INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY. + * call returns INTEL_SIP_SMC_STATUS_BUSY. * * Call register usage: * a0: INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE. * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_BUSY or + * INTEL_SIP_SMC_STATUS_ERROR. * a1: 64bit physical address of 1st completed memory block. * a2: 64bit physical address of 2nd completed memory block if * any completed block, otherwise zero value. @@ -164,8 +157,8 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_BUSY or + * INTEL_SIP_SMC_STATUS_ERROR. * a1-3: not used. */ #define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_ISDONE 4 @@ -183,7 +176,7 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_STATUS_ERROR. * a1: start of physical address of reserved memory block. * a2: size of reserved memory block. * a3: not used. @@ -203,7 +196,7 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_STATUS_ERROR. * a1-3: not used. */ #define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_LOOPBACK 6 diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index 59bc6e2af693..64213c3e82f5 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -18,45 +18,37 @@ /** * Status of the sent command, in bit number * - * SVC_COMMAND_STATUS_RECONFIG_REQUEST_OK: - * Secure firmware accepts the request of FPGA reconfiguration. + * SVC_STATUS_OK: + * Secure firmware accepts the request issued by one of service clients. * - * SVC_STATUS_RECONFIG_BUFFER_SUBMITTED: - * Service client successfully submits FPGA configuration - * data buffer to secure firmware. + * SVC_STATUS_BUFFER_SUBMITTED: + * Service client successfully submits data buffer to secure firmware. * - * SVC_COMMAND_STATUS_RECONFIG_BUFFER_DONE: + * SVC_STATUS_BUFFER_DONE: * Secure firmware completes data process, ready to accept the * next WRITE transaction. * - * SVC_COMMAND_STATUS_RECONFIG_COMPLETED: - * Secure firmware completes FPGA configuration successfully, FPGA should - * be in user mode. + * SVC_STATUS_COMPLETED: + * Secure firmware completes service request successfully. In case of + * FPGA configuration, FPGA should be in user mode. * - * SVC_COMMAND_STATUS_RECONFIG_BUSY: - * FPGA configuration is still in process. + * SVC_COMMAND_STATUS_BUSY: + * Service request is still in process. * - * SVC_COMMAND_STATUS_RECONFIG_ERROR: - * Error encountered during FPGA configuration. + * SVC_COMMAND_STATUS_ERROR: + * Error encountered during the process of the service request. * - * SVC_STATUS_RSU_OK: - * Secure firmware accepts the request of remote status update (RSU). - * - * SVC_STATUS_RSU_ERROR: - * Error encountered during remote system update. - * - * SVC_STATUS_RSU_NO_SUPPORT: - * Secure firmware doesn't support RSU retry or notify feature. + * SVC_STATUS_NO_SUPPORT: + * Secure firmware doesn't support requested features such as RSU retry + * or RSU notify. */ -#define SVC_STATUS_RECONFIG_REQUEST_OK 0 -#define SVC_STATUS_RECONFIG_BUFFER_SUBMITTED 1 -#define SVC_STATUS_RECONFIG_BUFFER_DONE 2 -#define SVC_STATUS_RECONFIG_COMPLETED 3 -#define SVC_STATUS_RECONFIG_BUSY 4 -#define SVC_STATUS_RECONFIG_ERROR 5 -#define SVC_STATUS_RSU_OK 6 -#define SVC_STATUS_RSU_ERROR 7 -#define SVC_STATUS_RSU_NO_SUPPORT 8 +#define SVC_STATUS_OK 0 +#define SVC_STATUS_BUFFER_SUBMITTED 1 +#define SVC_STATUS_BUFFER_DONE 2 +#define SVC_STATUS_COMPLETED 3 +#define SVC_STATUS_BUSY 4 +#define SVC_STATUS_ERROR 5 +#define SVC_STATUS_NO_SUPPORT 6 /** * Flag bit for COMMAND_RECONFIG @@ -84,32 +76,29 @@ struct stratix10_svc_chan; * @COMMAND_NOOP: do 'dummy' request for integration/debug/trouble-shooting * * @COMMAND_RECONFIG: ask for FPGA configuration preparation, return status - * is SVC_STATUS_RECONFIG_REQUEST_OK + * is SVC_STATUS_OK * * @COMMAND_RECONFIG_DATA_SUBMIT: submit buffer(s) of bit-stream data for the - * FPGA configuration, return status is SVC_STATUS_RECONFIG_BUFFER_SUBMITTED, - * or SVC_STATUS_RECONFIG_ERROR + * FPGA configuration, return status is SVC_STATUS_SUBMITTED or SVC_STATUS_ERROR * * @COMMAND_RECONFIG_DATA_CLAIM: check the status of the configuration, return - * status is SVC_STATUS_RECONFIG_COMPLETED, or SVC_STATUS_RECONFIG_BUSY, or - * SVC_STATUS_RECONFIG_ERROR + * status is SVC_STATUS_COMPLETED, or SVC_STATUS_BUSY, or SVC_STATUS_ERROR * * @COMMAND_RECONFIG_STATUS: check the status of the configuration, return - * status is SVC_STATUS_RECONFIG_COMPLETED, or SVC_STATUS_RECONFIG_BUSY, or - * SVC_STATUS_RECONFIG_ERROR + * status is SVC_STATUS_COMPLETED, or SVC_STATUS_BUSY, or SVC_STATUS_ERROR * * @COMMAND_RSU_STATUS: request remote system update boot log, return status * is log data or SVC_STATUS_RSU_ERROR * * @COMMAND_RSU_UPDATE: set the offset of the bitstream to boot after reboot, - * return status is SVC_STATUS_RSU_OK or SVC_STATUS_RSU_ERROR + * return status is SVC_STATUS_OK or SVC_STATUS_ERROR * * @COMMAND_RSU_NOTIFY: report the status of hard processor system - * software to firmware, return status is SVC_STATUS_RSU_OK or - * SVC_STATUS_RSU_ERROR + * software to firmware, return status is SVC_STATUS_OK or + * SVC_STATUS_ERROR * * @COMMAND_RSU_RETRY: query firmware for the current image's retry counter, - * return status is SVC_STATUS_RSU_OK or SVC_STATUS_RSU_ERROR + * return status is SVC_STATUS_OK or SVC_STATUS_ERROR */ enum stratix10_svc_command_code { COMMAND_NOOP = 0, -- cgit v1.2.3 From b9b3a8be28b31a3dbcb0ced07aa0d869f45cdb69 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:43 -0700 Subject: firmware: xilinx: Remove eemi ops for get_api_version Use direct function calls instead of using eemi ops. So remove eemi ops for get_api_version and use direct function call. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-2-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 8efa5ac22d7e..a21abcdb1020 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -294,7 +294,6 @@ struct zynqmp_pm_query_data { }; struct zynqmp_eemi_ops { - int (*get_api_version)(u32 *version); int (*get_chipid)(u32 *idcode, u32 *version); int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); @@ -331,11 +330,16 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE) const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); +int zynqmp_pm_get_api_version(u32 *version); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { return ERR_PTR(-ENODEV); } +static inline int zynqmp_pm_get_api_version(u32 *version) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 21cd93bab92b2818c9391465123cd4be6431c69e Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:44 -0700 Subject: firmware: xilinx: Remove eemi ops for get_chipid Use direct function call instead of eemi ops for get_chipid. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-3-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index a21abcdb1020..89f6a5394a65 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -294,7 +294,6 @@ struct zynqmp_pm_query_data { }; struct zynqmp_eemi_ops { - int (*get_chipid)(u32 *idcode, u32 *version); int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); @@ -331,6 +330,7 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE) const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); +int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -340,6 +340,10 @@ static inline int zynqmp_pm_get_api_version(u32 *version) { return -ENODEV; } +static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 6366c1bac3149c63752c03ea1c731d461d5349a7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:45 -0700 Subject: firmware: xilinx: Remove eemi ops for query_data Use direct function call for query_data instead of using eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-4-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 89f6a5394a65..fa1195c72976 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); int (*clock_enable)(u32 clock_id); int (*clock_disable)(u32 clock_id); int (*clock_getstate)(u32 clock_id, u32 *state); @@ -331,6 +330,7 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); +int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -344,6 +344,11 @@ static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version) { return -ENODEV; } +static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, + u32 *out) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 3637e84cd2e910f84835fac9650316dce53218ef Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:46 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_enable Use direct function call for clock_enable instead of eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-5-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index fa1195c72976..77365d1d246c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_enable)(u32 clock_id); int (*clock_disable)(u32 clock_id); int (*clock_getstate)(u32 clock_id, u32 *state); int (*clock_setdivider)(u32 clock_id, u32 divider); @@ -331,6 +330,7 @@ const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); +int zynqmp_pm_clock_enable(u32 clock_id); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -349,6 +349,10 @@ static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, { return -ENODEV; } +static inline int zynqmp_pm_clock_enable(u32 clock_id) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From f5ccd54b67b3f029de9d3818efa70f210d189019 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:47 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_disable Use direct function call for clock_disable instead using of eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-6-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 77365d1d246c..f9a84d974b5c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_disable)(u32 clock_id); int (*clock_getstate)(u32 clock_id, u32 *state); int (*clock_setdivider)(u32 clock_id, u32 divider); int (*clock_getdivider)(u32 clock_id, u32 *divider); @@ -331,6 +330,7 @@ int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); int zynqmp_pm_clock_enable(u32 clock_id); +int zynqmp_pm_clock_disable(u32 clock_id); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -353,6 +353,10 @@ static inline int zynqmp_pm_clock_enable(u32 clock_id) { return -ENODEV; } +static inline int zynqmp_pm_clock_disable(u32 clock_id) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 5e76731dd370ca3217fceaa3e2e84e992e6b7b7f Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:48 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_getstate Use direct function call instead of eemi ops for clock_getstate. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-7-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index f9a84d974b5c..e874f0c5e7ab 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_getstate)(u32 clock_id, u32 *state); int (*clock_setdivider)(u32 clock_id, u32 divider); int (*clock_getdivider)(u32 clock_id, u32 *divider); int (*clock_setrate)(u32 clock_id, u64 rate); @@ -331,6 +330,7 @@ int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); int zynqmp_pm_clock_enable(u32 clock_id); int zynqmp_pm_clock_disable(u32 clock_id); +int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -357,6 +357,10 @@ static inline int zynqmp_pm_clock_disable(u32 clock_id) { return -ENODEV; } +static inline int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From fc9fb8fb985c092f9cf01c7c50269c132efc4d58 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:49 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_setdivider Use direct function call instead of using eemi ops for clock_setdivider. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-8-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index e874f0c5e7ab..023f1f9807ed 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_setdivider)(u32 clock_id, u32 divider); int (*clock_getdivider)(u32 clock_id, u32 *divider); int (*clock_setrate)(u32 clock_id, u64 rate); int (*clock_getrate)(u32 clock_id, u64 *rate); @@ -331,6 +330,7 @@ int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); int zynqmp_pm_clock_enable(u32 clock_id); int zynqmp_pm_clock_disable(u32 clock_id); int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); +int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -361,6 +361,10 @@ static inline int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state) { return -ENODEV; } +static inline int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 0667a8d144bc830d0a752f079c9789735cd4f1f8 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:50 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_getdivider Use direct function call instead of using eemi ops for clock_getdivider. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-9-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 023f1f9807ed..3bda22f5262b 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_getdivider)(u32 clock_id, u32 *divider); int (*clock_setrate)(u32 clock_id, u64 rate); int (*clock_getrate)(u32 clock_id, u64 *rate); int (*clock_setparent)(u32 clock_id, u32 parent_id); @@ -331,6 +330,7 @@ int zynqmp_pm_clock_enable(u32 clock_id); int zynqmp_pm_clock_disable(u32 clock_id); int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); +int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -365,6 +365,10 @@ static inline int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider) { return -ENODEV; } +static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 7a1e10621a215dad4727aaa82396c4c19ce6593f Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:51 -0700 Subject: firmware: xilinx: Remove eemi ops for clock set/get rate Use direct function call instead of eemi ops for clock set/get rate. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-10-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 3bda22f5262b..a71f52c6173e 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,8 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_setrate)(u32 clock_id, u64 rate); - int (*clock_getrate)(u32 clock_id, u64 *rate); int (*clock_setparent)(u32 clock_id, u32 parent_id); int (*clock_getparent)(u32 clock_id, u32 *parent_id); int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); @@ -331,6 +329,8 @@ int zynqmp_pm_clock_disable(u32 clock_id); int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider); +int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate); +int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -369,6 +369,14 @@ static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider) { return -ENODEV; } +static inline int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate) +{ + return -ENODEV; +} +static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 70c0d36462ca5be8fc05176d11bec832dbb355b2 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:52 -0700 Subject: firmware: xilinx: Remove eemi ops for clock set/get parent Use direct function call instead of eemi ops for clock set/get parent. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-11-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index a71f52c6173e..7abb68311f17 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,8 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_setparent)(u32 clock_id, u32 parent_id); - int (*clock_getparent)(u32 clock_id, u32 *parent_id); int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); int (*reset_assert)(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); @@ -331,6 +329,8 @@ int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider); int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate); int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate); +int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id); +int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -377,6 +377,14 @@ static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate) { return -ENODEV; } +static inline int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id) +{ + return -ENODEV; +} +static inline int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 426c8d85df7a7b8337e09eab2806e802311778fd Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:53 -0700 Subject: firmware: xilinx: Use APIs instead of IOCTLs Remove IOCTL API and use individual APIs for better readability. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-12-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 7abb68311f17..5aff8963c11a 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); int (*reset_assert)(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int (*reset_get_status)(const enum zynqmp_pm_reset reset, u32 *status); @@ -331,6 +330,12 @@ int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate); int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate); int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id); int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id); +int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode); +int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode); +int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data); +int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data); +int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); +int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -385,6 +390,30 @@ static inline int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id) { return -ENODEV; } +static inline int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode) +{ + return -ENODEV; +} +static inline int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode) +{ + return -ENODEV; +} +static inline int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data) +{ + return -ENODEV; +} +static inline int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data) +{ + return -ENODEV; +} +static inline int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From cf23ec3531462376ef48237235daea577e1194e7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:54 -0700 Subject: firmware: xilinx: Remove eemi ops for reset_assert Use direct function call instead of using eemi ops for reset_assert. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-13-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 5aff8963c11a..22b2bbe0faea 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,8 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*reset_assert)(const enum zynqmp_pm_reset reset, - const enum zynqmp_pm_reset_action assert_flag); int (*reset_get_status)(const enum zynqmp_pm_reset reset, u32 *status); int (*init_finalize)(void); int (*set_suspend_mode)(u32 mode); @@ -336,6 +334,8 @@ int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data); int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data); int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); +int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, + const enum zynqmp_pm_reset_action assert_flag); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -414,6 +414,11 @@ static inline int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) { return -ENODEV; } +static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, + const enum zynqmp_pm_reset_action assert_flag) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 1b413581fe26404217a2160d444642440bb0e9e7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:55 -0700 Subject: firmware: xilinx: Remove eemi ops for reset_get_status Use direct function call instead of using eemi ops for reset_get_status. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-14-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 22b2bbe0faea..200f9e0dc406 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*reset_get_status)(const enum zynqmp_pm_reset reset, u32 *status); int (*init_finalize)(void); int (*set_suspend_mode)(u32 mode); int (*request_node)(const u32 node, @@ -336,6 +335,7 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); +int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -419,6 +419,11 @@ static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, { return -ENODEV; } +static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, + u32 *status) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 9474da950d1e39f71cbfeaba87367fa146635a88 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:56 -0700 Subject: firmware: xilinx: Remove eemi ops for init_finalize Use direct function call instead of eemi ops for init_finalize. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-15-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 200f9e0dc406..9aa5fe8acbea 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*init_finalize)(void); int (*set_suspend_mode)(u32 mode); int (*request_node)(const u32 node, const u32 capabilities, @@ -336,6 +335,7 @@ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); +int zynqmp_pm_init_finalize(void); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -424,6 +424,10 @@ static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, { return -ENODEV; } +static inline int zynqmp_pm_init_finalize(void) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 951d0a97e41caff96c180ca416093276bfd9a4fd Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:57 -0700 Subject: firmware: xilinx: Remove eemi ops for set_suspend_mode Use direct function call instead of eemi ops for set_suspend_mode. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-16-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 9aa5fe8acbea..761caede5a51 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*set_suspend_mode)(u32 mode); int (*request_node)(const u32 node, const u32 capabilities, const u32 qos, @@ -336,6 +335,7 @@ int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); int zynqmp_pm_init_finalize(void); +int zynqmp_pm_set_suspend_mode(u32 mode); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -428,6 +428,10 @@ static inline int zynqmp_pm_init_finalize(void) { return -ENODEV; } +static inline int zynqmp_pm_set_suspend_mode(u32 mode) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From bf8b27ed2324b5108439593dcfb9ab264a745ee7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:58 -0700 Subject: firmware: xilinx: Remove eemi ops for request_node Use direct function call instead of using eemi ops for request_node. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-17-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 761caede5a51..fb7e5c91c816 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,10 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*request_node)(const u32 node, - const u32 capabilities, - const u32 qos, - const enum zynqmp_pm_request_ack ack); int (*release_node)(const u32 node); int (*set_requirement)(const u32 node, const u32 capabilities, @@ -336,6 +332,8 @@ int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); int zynqmp_pm_init_finalize(void); int zynqmp_pm_set_suspend_mode(u32 mode); +int zynqmp_pm_request_node(const u32 node, const u32 capabilities, + const u32 qos, const enum zynqmp_pm_request_ack ack); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -432,6 +430,12 @@ static inline int zynqmp_pm_set_suspend_mode(u32 mode) { return -ENODEV; } +static inline int zynqmp_pm_request_node(const u32 node, const u32 capabilities, + const u32 qos, + const enum zynqmp_pm_request_ack ack) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 07fb1a4619fcb35f79d0adc13c8678f7726337ef Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:59 -0700 Subject: firmware: xilinx: Remove eemi ops for release_node Use direct function call instead of using eemi ops for release_node. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-18-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index fb7e5c91c816..bfa8cca64455 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*release_node)(const u32 node); int (*set_requirement)(const u32 node, const u32 capabilities, const u32 qos, @@ -334,6 +333,7 @@ int zynqmp_pm_init_finalize(void); int zynqmp_pm_set_suspend_mode(u32 mode); int zynqmp_pm_request_node(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); +int zynqmp_pm_release_node(const u32 node); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -436,6 +436,10 @@ static inline int zynqmp_pm_request_node(const u32 node, const u32 capabilities, { return -ENODEV; } +static inline int zynqmp_pm_release_node(const u32 node) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From cbbbda71fe37fe70e610d5ec3977fc6a096280ed Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:00 -0700 Subject: firmware: xilinx: Remove eemi ops for set_requirement Use direct function call instead of using eemi ops for set_requirement. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-19-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index bfa8cca64455..5927f6f49980 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,10 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*set_requirement)(const u32 node, - const u32 capabilities, - const u32 qos, - const enum zynqmp_pm_request_ack ack); int (*aes)(const u64 address, u32 *out); }; @@ -334,6 +330,9 @@ int zynqmp_pm_set_suspend_mode(u32 mode); int zynqmp_pm_request_node(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_release_node(const u32 node); +int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, + const u32 qos, + const enum zynqmp_pm_request_ack ack); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -440,6 +439,13 @@ static inline int zynqmp_pm_release_node(const u32 node) { return -ENODEV; } +static inline int zynqmp_pm_set_requirement(const u32 node, + const u32 capabilities, + const u32 qos, + const enum zynqmp_pm_request_ack ack) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From bc86f9c546160afce631fae223c3772d9375ee25 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:01 -0700 Subject: firmware: xilinx: Remove eemi ops for aes engine Use direct function call for aes engine instead of using eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-20-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 5927f6f49980..11d7aef2cc3c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*aes)(const u64 address, u32 *out); }; int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, @@ -333,6 +332,7 @@ int zynqmp_pm_release_node(const u32 node); int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); +int zynqmp_pm_aes_engine(const u64 address, u32 *out); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -446,6 +446,10 @@ static inline int zynqmp_pm_set_requirement(const u32 node, { return -ENODEV; } +static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 4db8180ffe7c07bc4a602c82d6d9c1c04751583d Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:02 -0700 Subject: firmware: xilinx: Remove eemi ops for fpga related APIs Use direct function call instead of using eemi ops for fpga related APIs. Also remove eemi ops structure. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-21-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 11d7aef2cc3c..44ffb4f0d8be 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -293,16 +293,11 @@ struct zynqmp_pm_query_data { u32 arg3; }; -struct zynqmp_eemi_ops { - int (*fpga_load)(const u64 address, const u32 size, const u32 flags); - int (*fpga_get_status)(u32 *value); -}; int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 *ret_payload); #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE) -const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); @@ -333,6 +328,8 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_aes_engine(const u64 address, u32 *out); +int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); +int zynqmp_pm_fpga_get_status(u32 *value); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -450,6 +447,15 @@ static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) { return -ENODEV; } +static inline int zynqmp_pm_fpga_load(const u64 address, const u32 size, + const u32 flags) +{ + return -ENODEV; +} +static inline int zynqmp_pm_fpga_get_status(u32 *value) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 4f680b72ea07a3e161ce1167a97ee09b1369f7de Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:03 -0700 Subject: firmware: xilinx: Add APIs to read/write GGS/PGGS registers Add APIs to read/write PGGS and GGS registers. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-22-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 44ffb4f0d8be..e23251d93176 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -107,6 +107,10 @@ enum pm_ioctl_id { IOCTL_GET_PLL_FRAC_MODE, IOCTL_SET_PLL_FRAC_DATA, IOCTL_GET_PLL_FRAC_DATA, + IOCTL_WRITE_GGS = 12, + IOCTL_READ_GGS = 13, + IOCTL_WRITE_PGGS = 14, + IOCTL_READ_PGGS = 15, }; enum pm_query_id { @@ -330,6 +334,10 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, int zynqmp_pm_aes_engine(const u64 address, u32 *out); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); +int zynqmp_pm_write_ggs(u32 index, u32 value); +int zynqmp_pm_read_ggs(u32 index, u32 *value); +int zynqmp_pm_write_pggs(u32 index, u32 value); +int zynqmp_pm_read_pggs(u32 index, u32 *value); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -456,6 +464,22 @@ static inline int zynqmp_pm_fpga_get_status(u32 *value) { return -ENODEV; } +static inline int zynqmp_pm_write_ggs(u32 index, u32 value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_read_ggs(u32 index, u32 *value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_write_pggs(u32 index, u32 value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_read_pggs(u32 index, u32 *value) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From ae5c961da6483b413dcb36d8bf6a881ffd2fb33f Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:04 -0700 Subject: firmware: xilinx: Add sysfs interface Add firmware-ggs sysfs interface which provides read/write interface to global storage registers. Signed-off-by: Rajan Vaja Signed-off-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-23-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index e23251d93176..c1356e93dcb2 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -42,6 +42,8 @@ #define ZYNQMP_PM_MAX_QOS 100U +#define GSS_NUM_REGS (4) + /* Node capabilities */ #define ZYNQMP_PM_CAPABILITY_ACCESS 0x1U #define ZYNQMP_PM_CAPABILITY_CONTEXT 0x2U -- cgit v1.2.3 From fdd2ed88ca971376669bce145f1a1bcf028d775e Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:05 -0700 Subject: firmware: xilinx: Add system shutdown API interface Add system shutdown API interface which asks firmware to perform system shutdown/restart. Signed-off-by: Rajan Vaja Signed-off-by: Michal Simek Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-24-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index c1356e93dcb2..2254c7cc3362 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -64,6 +64,7 @@ enum pm_api_id { PM_GET_API_VERSION = 1, + PM_SYSTEM_SHUTDOWN = 12, PM_REQUEST_NODE = 13, PM_RELEASE_NODE, PM_SET_REQUIREMENT, @@ -340,6 +341,7 @@ int zynqmp_pm_write_ggs(u32 index, u32 value); int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); int zynqmp_pm_read_pggs(u32 index, u32 *value); +int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -482,6 +484,10 @@ static inline int zynqmp_pm_read_pggs(u32 index, u32 *value) { return -ENODEV; } +static inline int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From b3ae24c44848c6403fb2333d7cbe494565058352 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:06 -0700 Subject: firmware: xilinx: Add sysfs to set shutdown scope The Linux shutdown functionality implemented via PSCI system_off does not include an option to set a scope, i.e. which parts of the system to shut down. This patch creates sysfs that allows to set the shutdown scope for the next shutdown request. When the next shutdown is performed, the platform specific portion of PSCI-system_off can use the chosen shutdown scope. Signed-off-by: Rajan Vaja Signed-off-by: Stefan Krsmanovic Signed-off-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-25-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 2254c7cc3362..c297333677d4 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -286,6 +286,18 @@ enum dll_reset_type { PM_DLL_RESET_PULSE, }; +enum zynqmp_pm_shutdown_type { + ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN, + ZYNQMP_PM_SHUTDOWN_TYPE_RESET, + ZYNQMP_PM_SHUTDOWN_TYPE_SETSCOPE_ONLY, +}; + +enum zynqmp_pm_shutdown_subtype { + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SUBSYSTEM, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_PS_ONLY, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SYSTEM, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID -- cgit v1.2.3 From a2cc220a9a9227b2c5c9b39f57340bce64f040fd Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:07 -0700 Subject: firmware: xilinx: Add sysfs and API to set boot health status Add sysfs interface to set boot health status from user space. Add API used by this interface to communicate with firmware. If PMUFW is compiled with CHECK_HEALTHY_BOOT, it will check the healthy bit on FPD WDT expiration. If healthy bit is set by a user application running in Linux, PMUFW will do APU only restart. If healthy bit is not set during FPD WDT expiration, PMUFW will do system restart. Signed-off-by: Rajan Vaja Signed-off-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-26-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- 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 c297333677d4..5968df82b991 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -114,6 +114,8 @@ enum pm_ioctl_id { IOCTL_READ_GGS = 13, IOCTL_WRITE_PGGS = 14, IOCTL_READ_PGGS = 15, + /* Set healthy bit value */ + IOCTL_SET_BOOT_HEALTH_STATUS = 17, }; enum pm_query_id { @@ -354,6 +356,7 @@ int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); int zynqmp_pm_read_pggs(u32 index, u32 *value); int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype); +int zynqmp_pm_set_boot_health_status(u32 value); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -500,6 +503,10 @@ static inline int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype) { return -ENODEV; } +static inline int zynqmp_pm_set_boot_health_status(u32 value) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 9495b7e92f716ab2bd6814fab5e97ab4a39adfdd Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 22 Apr 2020 12:09:54 +0200 Subject: driver core: platform: Initialize dma_parms for platform devices It's currently the platform driver's responsibility to initialize the pointer, dma_parms, for its corresponding struct device. The benefit with this approach allows us to avoid the initialization and to not waste memory for the struct device_dma_parameters, as this can be decided on a case by case basis. However, it has turned out that this approach is not very practical. Not only does it lead to open coding, but also to real errors. In principle callers of dma_set_max_seg_size() doesn't check the error code, but just assumes it succeeds. For these reasons, let's do the initialization from the common platform bus at the device registration point. This also follows the way the PCI devices are being managed, see pci_device_add(). Suggested-by: Christoph Hellwig Cc: Tested-by: Haibo Chen Reviewed-by: Arnd Bergmann Signed-off-by: Ulf Hansson Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20200422100954.31211-1-ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index bdc35753ef7c..77a2aada106d 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -25,6 +25,7 @@ struct platform_device { bool id_auto; struct device dev; u64 platform_dma_mask; + struct device_dma_parameters dma_parms; u32 num_resources; struct resource *resource; -- cgit v1.2.3 From f458488425f1cc9a396aa1d09bb00c48783936da Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 22 Apr 2020 12:10:13 +0200 Subject: amba: Initialize dma_parms for amba devices It's currently the amba driver's responsibility to initialize the pointer, dma_parms, for its corresponding struct device. The benefit with this approach allows us to avoid the initialization and to not waste memory for the struct device_dma_parameters, as this can be decided on a case by case basis. However, it has turned out that this approach is not very practical. Not only does it lead to open coding, but also to real errors. In principle callers of dma_set_max_seg_size() doesn't check the error code, but just assumes it succeeds. For these reasons, let's do the initialization from the common amba bus at the device registration point. This also follows the way the PCI devices are being managed, see pci_device_add(). Suggested-by: Christoph Hellwig Cc: Russell King Cc: Tested-by: Haibo Chen Reviewed-by: Arnd Bergmann Signed-off-by: Ulf Hansson Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20200422101013.31267-1-ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/amba/bus.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 26f0ecf401ea..0bbfd647f5c6 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -65,6 +65,7 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; + struct device_dma_parameters dma_parms; unsigned int periphid; unsigned int cid; struct amba_cs_uci_id uci; -- cgit v1.2.3 From d65dbedfd298344747033f17c1efd2afc8082bc7 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 24 Apr 2020 12:45:02 -0700 Subject: net/mlx5: Add support for COPY steering action Add COPY type to modify_header action. IPsec feature is the first feature that needs COPY steering action. Signed-off-by: Huy Nguyen Signed-off-by: Raed Salem Signed-off-by: Saeed Mahameed Acked-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6fa24918eade..3ad2c51ccde9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5670,9 +5670,9 @@ struct mlx5_ifc_copy_action_in_bits { 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; +union mlx5_ifc_set_add_copy_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]; }; @@ -5746,7 +5746,7 @@ struct mlx5_ifc_alloc_modify_header_context_in_bits { u8 reserved_at_68[0x10]; u8 num_of_actions[0x8]; - union mlx5_ifc_set_action_in_add_action_in_auto_bits actions[0]; + union mlx5_ifc_set_add_copy_action_in_auto_bits actions[0]; }; struct mlx5_ifc_dealloc_modify_header_context_out_bits { -- cgit v1.2.3 From 2b58f6d9df50f534fe465113b69de60a2ef0e74a Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 24 Apr 2020 12:45:03 -0700 Subject: net/mlx5: Introduce IPsec Connect-X offload hardware bits and structures Add IPsec offload related IFC structs, layouts and enumerations. Signed-off-by: Raed Salem Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 4 +++ include/linux/mlx5/mlx5_ifc.h | 78 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 79 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2b90097a6cf9..7b57877e501e 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1107,6 +1107,7 @@ enum mlx5_cap_type { MLX5_CAP_TLS, MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, + MLX5_CAP_IPSEC, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1324,6 +1325,9 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(device_virtio_emulation_cap, \ (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) +#define MLX5_CAP_IPSEC(mdev, cap)\ + MLX5_GET(ipsec_cap, (mdev)->caps.hca_cur[MLX5_CAP_IPSEC], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3ad2c51ccde9..cf971d341189 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -886,7 +886,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 tunnel_stateless_vxlan_gpe[0x1]; u8 tunnel_stateless_ipv4_over_vxlan[0x1]; u8 tunnel_stateless_ip_over_ip[0x1]; - u8 reserved_at_2a[0x6]; + u8 insert_trailer[0x1]; + u8 reserved_at_2b[0x5]; u8 max_vxlan_udp_ports[0x8]; u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; @@ -1100,6 +1101,23 @@ struct mlx5_ifc_tls_cap_bits { u8 reserved_at_20[0x7e0]; }; +struct mlx5_ifc_ipsec_cap_bits { + u8 ipsec_full_offload[0x1]; + u8 ipsec_crypto_offload[0x1]; + u8 ipsec_esn[0x1]; + u8 ipsec_crypto_esp_aes_gcm_256_encrypt[0x1]; + u8 ipsec_crypto_esp_aes_gcm_128_encrypt[0x1]; + u8 ipsec_crypto_esp_aes_gcm_256_decrypt[0x1]; + u8 ipsec_crypto_esp_aes_gcm_128_decrypt[0x1]; + u8 reserved_at_7[0x4]; + u8 log_max_ipsec_offload[0x5]; + u8 reserved_at_10[0x10]; + + u8 min_log_ipsec_full_replay_window[0x8]; + u8 max_log_ipsec_full_replay_window[0x8]; + u8 reserved_at_30[0x7d0]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -1464,7 +1482,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5]; - u8 reserved_at_468[0x3]; + u8 reserved_at_468[0x2]; + u8 ipsec_offload[0x1]; u8 log_max_umem[0x5]; u8 max_num_eqs[0x10]; @@ -4143,7 +4162,8 @@ enum { MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION = 0x0, MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_TAG = 0x1, MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST = 0x2, - MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS = 0x3 + MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS = 0x3, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_IPSEC_OBJ_ID = 0x4 }; struct mlx5_ifc_set_fte_out_bits { @@ -10468,10 +10488,62 @@ struct mlx5_ifc_affiliated_event_header_bits { enum { MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc), + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT(0x13), }; enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, + MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, +}; + +enum { + MLX5_IPSEC_OBJECT_ICV_LEN_16B, + MLX5_IPSEC_OBJECT_ICV_LEN_12B, + MLX5_IPSEC_OBJECT_ICV_LEN_8B, +}; + +struct mlx5_ifc_ipsec_obj_bits { + u8 modify_field_select[0x40]; + u8 full_offload[0x1]; + u8 reserved_at_41[0x1]; + u8 esn_en[0x1]; + u8 esn_overlap[0x1]; + u8 reserved_at_44[0x2]; + u8 icv_length[0x2]; + u8 reserved_at_48[0x4]; + u8 aso_return_reg[0x4]; + u8 reserved_at_50[0x10]; + + u8 esn_msb[0x20]; + + u8 reserved_at_80[0x8]; + u8 dekn[0x18]; + + u8 salt[0x20]; + + u8 implicit_iv[0x40]; + + u8 reserved_at_100[0x700]; +}; + +struct mlx5_ifc_create_ipsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_ipsec_obj_bits ipsec_object; +}; + +enum { + MLX5_MODIFY_IPSEC_BITMASK_ESN_OVERLAP = BIT(0), + MLX5_MODIFY_IPSEC_BITMASK_ESN_MSB = BIT(1), +}; + +struct mlx5_ifc_query_ipsec_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_ipsec_obj_bits ipsec_object; +}; + +struct mlx5_ifc_modify_ipsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_ipsec_obj_bits ipsec_object; }; struct mlx5_ifc_encryption_key_obj_bits { -- cgit v1.2.3 From dff8e2d15283dd92582ddeec25ca86e4cf2618c7 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Fri, 24 Apr 2020 12:45:04 -0700 Subject: net/mlx5: Use aligned variable while allocating ICM memory The alignment value is part of the input structure, so use it and spare extra memory allocation when is not needed. Now, using the new ability when allocating icm for Direct-Rule insertion. Signed-off-by: Ariel Levkovich Signed-off-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b60e5ab7906b..b46537a81703 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1080,7 +1080,8 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, - u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id); + u64 length, u32 log_alignment, u16 uid, + phys_addr_t *addr, u32 *obj_id); int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, u64 length, u16 uid, phys_addr_t addr, u32 obj_id); -- cgit v1.2.3 From 244faedfd4d8e8c8e9f3c628d29bb74196b49743 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 24 Apr 2020 12:45:05 -0700 Subject: net/mlx5: Refactor imm_inval_pkey field in cqe struct The imm_inval_pkey field can hold four different types of data, depends on the usage, the data could be one of the below: - Immediate field of the received message - Invalidate rkey - Pkey of the packet - Flow table metadata Current implementation doesn't reflect the intended usage of the field at usage time. Reflect the different types by replace this field with a union, modify code where this field is used to reflect its intended usage. Signed-off-by: Raed Salem Reviewed-by: Huy Nguyen Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 7b57877e501e..746e17473d72 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -767,7 +767,12 @@ struct mlx5_cqe64 { u8 l4_l3_hdr_type; __be16 vlan_info; __be32 srqn; /* [31:24]: lro_num_seg, [23:0]: srqn */ - __be32 imm_inval_pkey; + union { + __be32 immediate; + __be32 inval_rkey; + __be32 pkey; + __be32 ft_metadata; + }; u8 rsvd40[4]; __be32 byte_cnt; __be32 timestamp_h; -- cgit v1.2.3 From 06939536263d684073a30543930622eede633af1 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 24 Apr 2020 12:45:06 -0700 Subject: net/mlx5: Add structure layout and defines for MFRL register Add needed structure layouts and defines for MFRL (Management Firmware Reset Level) register. This structure will be used for the firmware upgrade and reset flow in the downstream patches. Signed-off-by: Moshe Shemesh Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b46537a81703..d82dbbab8179 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -130,6 +130,7 @@ enum { MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, MLX5_REG_MCIA = 0x9014, + MLX5_REG_MFRL = 0x9028, MLX5_REG_MLCR = 0x902b, MLX5_REG_MTRC_CAP = 0x9040, MLX5_REG_MTRC_CONF = 0x9041, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cf971d341189..9e6a3cec1e32 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9703,6 +9703,29 @@ struct mlx5_ifc_mcda_reg_bits { u8 data[0][0x20]; }; +enum { + MLX5_MFRL_REG_RESET_TYPE_FULL_CHIP = BIT(0), + MLX5_MFRL_REG_RESET_TYPE_NET_PORT_ALIVE = BIT(1), +}; + +enum { + MLX5_MFRL_REG_RESET_LEVEL0 = BIT(0), + MLX5_MFRL_REG_RESET_LEVEL3 = BIT(3), + MLX5_MFRL_REG_RESET_LEVEL6 = BIT(6), +}; + +struct mlx5_ifc_mfrl_reg_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x2]; + u8 pci_sync_for_fw_update_start[0x1]; + u8 pci_sync_for_fw_update_resp[0x2]; + u8 rst_type_sel[0x3]; + u8 reserved_at_28[0x8]; + u8 reset_type[0x8]; + u8 reset_level[0x8]; +}; + struct mlx5_ifc_mirc_reg_bits { u8 reserved_at_0[0x18]; u8 status_code[0x8]; @@ -9766,6 +9789,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mcc_reg_bits mcc_reg; struct mlx5_ifc_mcda_reg_bits mcda_reg; struct mlx5_ifc_mirc_reg_bits mirc_reg; + struct mlx5_ifc_mfrl_reg_bits mfrl_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From 3df0107784ceb388039b1fe510a8c7b8816de8f0 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 24 Apr 2020 12:45:07 -0700 Subject: net/mlx5: Add structure and defines for pci sync for fw update event Add needed structure layouts and defines for pci sync for fw update event. The downstream patches will include event handlers for this event type. Signed-off-by: Moshe Shemesh Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 15 +++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 746e17473d72..de93f0b67973 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -364,6 +364,7 @@ enum { enum { MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5, + MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT = 0x8, }; enum { @@ -689,6 +690,19 @@ struct mlx5_eqe_temp_warning { __be64 sensor_warning_lsb; } __packed; +#define SYNC_RST_STATE_MASK 0xf + +enum sync_rst_state_type { + MLX5_SYNC_RST_STATE_RESET_REQUEST = 0x0, + MLX5_SYNC_RST_STATE_RESET_NOW = 0x1, + MLX5_SYNC_RST_STATE_RESET_ABORT = 0x2, +}; + +struct mlx5_eqe_sync_fw_update { + u8 reserved_at_0[3]; + u8 sync_rst_state; +}; + union ev_data { __be32 raw[7]; struct mlx5_eqe_cmd cmd; @@ -707,6 +721,7 @@ union ev_data { struct mlx5_eqe_dct dct; struct mlx5_eqe_temp_warning temp_warning; struct mlx5_eqe_xrq_err xrq_err; + struct mlx5_eqe_sync_fw_update sync_fw_update; } __packed; struct mlx5_eqe { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9e6a3cec1e32..058ded202b65 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1317,7 +1317,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 wol_p[0x1]; u8 stat_rate_support[0x10]; - u8 reserved_at_1f0[0xc]; + u8 reserved_at_1f0[0x1]; + u8 pci_sync_for_fw_update_event[0x1]; + u8 reserved_at_1f2[0xa]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; -- cgit v1.2.3 From ee5cdf7a5e8945372c7496e98de2b364e095b60b Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Fri, 24 Apr 2020 12:45:08 -0700 Subject: net/mlx5: Introduce TLS RX offload hardware bits Add TLS RX offload related IFC hardware fields and enumerations. Signed-off-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Reviewed-by: Boris Pismenny Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 18 ++++++++++++++++-- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index de93f0b67973..1bc27aca648b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -450,10 +450,12 @@ enum { enum { MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x1, + MLX5_OPC_MOD_TLS_TIR_STATIC_PARAMS = 0x2, }; enum { MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x1, + MLX5_OPC_MOD_TLS_TIR_PROGRESS_PARAMS = 0x2, }; enum { @@ -764,7 +766,7 @@ struct mlx5_err_cqe { }; struct mlx5_cqe64 { - u8 outer_l3_tunneled; + u8 tls_outer_l3_tunneled; u8 rsvd0; __be16 wqe_id; u8 lro_tcppsh_abort_dupack; @@ -854,7 +856,12 @@ static inline u8 get_cqe_l3_hdr_type(struct mlx5_cqe64 *cqe) static inline bool cqe_is_tunneled(struct mlx5_cqe64 *cqe) { - return cqe->outer_l3_tunneled & 0x1; + return cqe->tls_outer_l3_tunneled & 0x1; +} + +static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe) +{ + return (cqe->tls_outer_l3_tunneled >> 3) & 0x3; } static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe) @@ -942,6 +949,13 @@ enum { CQE_L4_OK = 1 << 2, }; +enum { + CQE_TLS_OFFLOAD_NOT_DECRYPTED = 0x0, + CQE_TLS_OFFLOAD_DECRYPTED = 0x1, + CQE_TLS_OFFLOAD_RESYNC = 0x2, + CQE_TLS_OFFLOAD_ERROR = 0x3, +}; + struct mlx5_sig_err_cqe { u8 rsvd0[16]; __be32 expected_trans_sig; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 058ded202b65..6a6bb5dc7916 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1491,7 +1491,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_480[0x1]; u8 tls_tx[0x1]; - u8 reserved_at_482[0x1]; + u8 tls_rx[0x1]; u8 log_max_l2_table[0x5]; u8 reserved_at_488[0x8]; u8 log_uar_page_sz[0x10]; @@ -3136,7 +3136,8 @@ struct mlx5_ifc_tirc_bits { u8 reserved_at_0[0x20]; u8 disp_type[0x4]; - u8 reserved_at_24[0x1c]; + u8 tls_en[0x1]; + u8 reserved_at_25[0x1b]; u8 reserved_at_40[0x40]; -- cgit v1.2.3 From 0e1533bb9cce2c6b2aecdfddfcc0de3beeaddc7b Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Fri, 24 Apr 2020 12:45:09 -0700 Subject: net/mlx5: Add release all pages capability bit Add a bit in HCA capabilities layout to indicate if release all pages is supported. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh 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 6a6bb5dc7916..fb243848132d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1244,7 +1244,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_at_140[0x9]; + u8 reserved_at_140[0x6]; + u8 release_all_pages[0x1]; + u8 reserved_at_147[0x2]; u8 roce_accl[0x1]; u8 log_max_ra_req_qp[0x6]; u8 reserved_at_150[0xa]; -- cgit v1.2.3 From 2dc8b5246d2c94f732c02e7a688d8a9c0c65361f Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 24 Apr 2020 12:45:10 -0700 Subject: net/mlx5: TX WQE Add trailer insertion field Add new TX WQE field for Connect-X6DX trailer insertion support, when set, the HW adds a trailer to the packet, the WQE trailer association flags are used to set to HW the header which the trailer belongs. Signed-off-by: Raed Salem Signed-off-by: Saeed Mahameed --- include/linux/mlx5/qp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index ef127a156a62..f23eb18526fe 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -229,6 +229,11 @@ enum { enum { MLX5_ETH_WQE_SVLAN = 1 << 0, + MLX5_ETH_WQE_TRAILER_HDR_OUTER_IP_ASSOC = 1 << 26, + MLX5_ETH_WQE_TRAILER_HDR_OUTER_L4_ASSOC = 1 << 27, + MLX5_ETH_WQE_TRAILER_HDR_INNER_IP_ASSOC = 3 << 26, + MLX5_ETH_WQE_TRAILER_HDR_INNER_L4_ASSOC = 1 << 28, + MLX5_ETH_WQE_INSERT_TRAILER = 1 << 30, MLX5_ETH_WQE_INSERT_VLAN = 1 << 15, }; @@ -257,6 +262,7 @@ struct mlx5_wqe_eth_seg { __be16 type; __be16 vlan_tci; } insert; + __be32 trailer; }; }; -- cgit v1.2.3 From 7c4310ff56422ea43418305d22bbc5fe19150ec4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 3 Apr 2020 14:33:41 +1100 Subject: SUNRPC: defer slow parts of rpc_free_client() to a workqueue. The rpciod workqueue is on the write-out path for freeing dirty memory, so it is important that it never block waiting for memory to be allocated - this can lead to a deadlock. rpc_execute() - which is often called by an rpciod work item - calls rcp_task_release_client() which can lead to rpc_free_client(). rpc_free_client() makes two calls which could potentially block wating for memory allocation. rpc_clnt_debugfs_unregister() calls into debugfs and will block while any of the debugfs files are being accessed. In particular it can block while any of the 'open' methods are being called and all of these use malloc for one thing or another. So this can deadlock if the memory allocation waits for NFS to complete some writes via rpciod. rpc_clnt_remove_pipedir() can take the inode_lock() and while it isn't obvious that memory allocations can happen while the lock it held, it is safer to assume they might and to not let rpciod call rpc_clnt_remove_pipedir(). So this patch moves these two calls (together with the final kfree() and rpciod_down()) into a work-item to be run from the system work-queue. rpciod can continue its important work, and the final stages of the free can happen whenever they happen. I have seen this deadlock on a 4.12 based kernel where debugfs used synchronize_srcu() when removing objects. synchronize_srcu() requires a workqueue and there were no free workther threads and none could be allocated. While debugsfs no longer uses SRCU, I believe the deadlock is still possible. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index ca7e108248e2..7bd124e06b36 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -71,7 +71,13 @@ struct rpc_clnt { #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *cl_debugfs; /* debugfs directory */ #endif - struct rpc_xprt_iter cl_xpi; + /* cl_work is only needed after cl_xpi is no longer used, + * and that are of similar size + */ + union { + struct rpc_xprt_iter cl_xpi; + struct work_struct cl_work; + }; const struct cred *cl_cred; }; -- cgit v1.2.3 From dff58530c4ca8ce7ee5a74db431c6e35362cf682 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 24 Apr 2020 17:45:50 -0400 Subject: NFSv4.1: fix handling of backchannel binding in BIND_CONN_TO_SESSION Currently, if the client sends BIND_CONN_TO_SESSION with NFS4_CDFC4_FORE_OR_BOTH but only gets NFS4_CDFS4_FORE back it ignores that it wasn't able to enable a backchannel. To make sure, the client sends BIND_CONN_TO_SESSION as the first operation on the connections (ie., no other session compounds haven't been sent before), and if the client's request to bind the backchannel is not satisfied, then reset the connection and retry. Cc: stable@vger.kernel.org Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ include/linux/sunrpc/clnt.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 440230488025..e5f3e7d8d3d5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1317,11 +1317,13 @@ struct nfs41_impl_id { struct nfstime4 date; }; +#define MAX_BIND_CONN_TO_SESSION_RETRIES 3 struct nfs41_bind_conn_to_session_args { struct nfs_client *client; struct nfs4_sessionid sessionid; u32 dir; bool use_conn_in_rdma_mode; + int retries; }; struct nfs41_bind_conn_to_session_res { diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 7bd124e06b36..02e7a5863d28 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -242,4 +242,9 @@ static inline int rpc_reply_expected(struct rpc_task *task) (task->tk_msg.rpc_proc->p_decode != NULL); } +static inline void rpc_task_close_connection(struct rpc_task *task) +{ + if (task->tk_xprt) + xprt_force_disconnect(task->tk_xprt); +} #endif /* _LINUX_SUNRPC_CLNT_H */ -- cgit v1.2.3 From 35fc0e3b0bd5be3b059e53ae90c4536ee4922330 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 24 Apr 2020 11:19:10 -0500 Subject: rculist: Add hlists_swap_heads_rcu Using the struct pid to refer to two tasks in de_thread was a clever idea and ultimately too clever, as it has lead to proc_flush_task being called inconsistently. To support rectifying this add hlists_swap_heads_rcu. An hlist primitive that just swaps the hlist heads of two lists. This is exactly what is needed for exchanging the pids of two tasks. Only consideration of correctness of the code has been given, as the caller is expected to be a slowpath. Link: https://lore.kernel.org/lkml/87mu6vajnq.fsf_-_@x220.int.ebiederm.org/ Acked-by: Linus Torvalds Acked-by: Oleg Nesterov Signed-off-by: "Eric W. Biederman" --- include/linux/rculist.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8214cdc715f2..67867e0d4cec 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -506,6 +506,27 @@ static inline void hlist_replace_rcu(struct hlist_node *old, WRITE_ONCE(old->pprev, LIST_POISON2); } +/** + * hlists_swap_heads_rcu - swap the lists the hlist heads point to + * @left: The hlist head on the left + * @right: The hlist head on the right + * + * The lists start out as [@left ][node1 ... ] and + [@right ][node2 ... ] + * The lists end up as [@left ][node2 ... ] + * [@right ][node1 ... ] + */ +static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) +{ + struct hlist_node *node1 = left->first; + struct hlist_node *node2 = right->first; + + rcu_assign_pointer(left->first, node2); + rcu_assign_pointer(right->first, node1); + WRITE_ONCE(node2->pprev, &left->first); + WRITE_ONCE(node1->pprev, &right->first); +} + /* * return the first or the next element in an RCU protected hlist */ -- cgit v1.2.3 From 6b03d1304a32dc8450c7516000a0fe07bef7c446 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 19 Apr 2020 06:35:02 -0500 Subject: proc: Ensure we see the exit of each process tid exactly once When the thread group leader changes during exec and the old leaders thread is reaped proc_flush_pid will flush the dentries for the entire process because the leader still has it's original pid. Fix this by exchanging the pids in an rcu safe manner, and wrapping the code to do that up in a helper exchange_tids. When I removed switch_exec_pids and introduced this behavior in d73d65293e3e ("[PATCH] pidhash: kill switch_exec_pids") there really was nothing that cared as flushing happened with the cached dentry and de_thread flushed both of them on exec. This lack of fully exchanging pids became a problem a few months later when I introduced 48e6484d4902 ("[PATCH] proc: Rewrite the proc dentry flush on exit optimization"). Which overlooked the de_thread case was no longer swapping pids, and I was looking up proc dentries by task->pid. The current behavior isn't properly a bug as everything in proc will continue to work correctly just a little bit less efficiently. Fix this just so there are no little surprise corner cases waiting to bite people. -- Oleg points out this could be an issue in next_tgid in proc where has_group_leader_pid is called, and reording some of the assignments should fix that. -- Oleg points out this will break the 10 year old hack in __exit_signal.c > /* > * This can only happen if the caller is de_thread(). > * FIXME: this is the temporary hack, we should teach > * posix-cpu-timers to handle this case correctly. > */ > if (unlikely(has_group_leader_pid(tsk))) > posix_cpu_timers_exit_group(tsk); The code in next_tgid has been changed to use PIDTYPE_TGID, and the posix cpu timers code has been fixed so it does not need the 10 year old hack, so this should be safe to merge now. Link: https://lore.kernel.org/lkml/87h7x3ajll.fsf_-_@x220.int.ebiederm.org/ Acked-by: Linus Torvalds Acked-by: Oleg Nesterov Fixes: 48e6484d4902 ("[PATCH] proc: Rewrite the proc dentry flush on exit optimization"). Signed-off-by: Eric W. Biederman --- include/linux/pid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index cc896f0fc4e3..2159ffca63fc 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -102,6 +102,7 @@ extern void attach_pid(struct task_struct *task, enum pid_type); extern void detach_pid(struct task_struct *task, enum pid_type); extern void change_pid(struct task_struct *task, enum pid_type, struct pid *pid); +extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); -- cgit v1.2.3 From c4dad0aab3fca0c1f0baa4cc84b6ec91b7ebf426 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 22 Apr 2020 17:39:28 -0400 Subject: audit: tidy and extend netfilter_cfg x_tables NETFILTER_CFG record generation was inconsistent for x_tables and ebtables configuration changes. The call was needlessly messy and there were supporting records missing at times while they were produced when not requested. Simplify the logging call into a new audit_log_nfcfg call. Honour the audit_enabled setting while more consistently recording information including supporting records by tidying up dummy checks. Add an op= field that indicates the operation being performed (register or replace). Here is the enhanced sample record: type=NETFILTER_CFG msg=audit(1580905834.919:82970): table=filter family=2 entries=83 op=replace Generate audit NETFILTER_CFG records on ebtables table registration. Previously this was being done for x_tables registration and replacement operations and ebtables table replacement only. See: https://github.com/linux-audit/audit-kernel/issues/25 See: https://github.com/linux-audit/audit-kernel/issues/35 See: https://github.com/linux-audit/audit-kernel/issues/43 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index f9ceae57ca8d..5c7f07a9776d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -94,6 +94,11 @@ struct audit_ntp_data { struct audit_ntp_data {}; #endif +enum audit_nfcfgop { + AUDIT_XT_OP_REGISTER, + AUDIT_XT_OP_REPLACE, +}; + extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); @@ -379,6 +384,8 @@ extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); +extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, + enum audit_nfcfgop op); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { @@ -514,6 +521,14 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) __audit_ntp_log(ad); } +static inline void audit_log_nfcfg(const char *name, u8 af, + unsigned int nentries, + enum audit_nfcfgop op) +{ + if (audit_enabled) + __audit_log_nfcfg(name, af, nentries, op); +} + extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ @@ -646,6 +661,12 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) static inline void audit_ptrace(struct task_struct *t) { } + +static inline void audit_log_nfcfg(const char *name, u8 af, + unsigned int nentries, + enum audit_nfcfgop op) +{ } + #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ -- cgit v1.2.3 From bbd40fc4816d5329a89397206ece9f1763787a88 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 26 Apr 2020 07:59:55 -0500 Subject: signal: Remove has_group_leader_pid After the introduction of exchange_tids has_group_leader_pid is equivalent to thread_group_leader. After the last couple of cleanups has_group_leader_pid has no more callers. So remove the now unused and redundant has_group_leader_pid. Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3e5b090c16d4..0ee5e696c5d8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -654,17 +654,6 @@ static inline bool thread_group_leader(struct task_struct *p) return p->exit_signal >= 0; } -/* Do to the insanities of de_thread it is possible for a process - * to have the pid of the thread group leader without actually being - * the thread group leader. For iteration through the pids in proc - * all we care about is that we have a task with the appropriate - * pid, we don't actually care if we have the right task. - */ -static inline bool has_group_leader_pid(struct task_struct *p) -{ - return task_pid(p) == task_tgid(p); -} - static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { -- cgit v1.2.3 From a45d88530b2552ad5ea0da18861600b4ecc9d0c7 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 22 Apr 2020 17:39:29 -0400 Subject: netfilter: add audit table unregister actions Audit the action of unregistering ebtables and x_tables. See: https://github.com/linux-audit/audit-kernel/issues/44 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 5c7f07a9776d..1a2351508211 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -97,6 +97,7 @@ struct audit_ntp_data {}; enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, + AUDIT_XT_OP_UNREGISTER, }; extern int is_audit_feature_set(int which); -- cgit v1.2.3 From f9d041271cf44ca02eed0cc82e1a6d8c814c53ed Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:05 -0700 Subject: bpf: Refactor bpf_link update handling Make bpf_link update support more generic by making it into another bpf_link_ops methods. This allows generic syscall handling code to be agnostic to various conditionally compiled features (e.g., the case of CONFIG_CGROUP_BPF). This also allows to keep link type-specific code to remain static within respective code base. Refactor existing bpf_cgroup_link code and take advantage of this. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-2-andriin@fb.com --- include/linux/bpf-cgroup.h | 12 ------------ include/linux/bpf.h | 3 ++- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 0b41fd5fc96b..a9cb9a5bf8e9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -100,8 +100,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_cgroup_link *link, enum bpf_attach_type type); -int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, - struct bpf_prog *new_prog); int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -112,8 +110,6 @@ int cgroup_bpf_attach(struct cgroup *cgrp, u32 flags); int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type); -int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog, - struct bpf_prog *new_prog); int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -353,7 +349,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, #else struct bpf_prog; -struct bpf_link; struct cgroup_bpf {}; static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} @@ -377,13 +372,6 @@ static inline int cgroup_bpf_link_attach(const union bpf_attr *attr, return -EINVAL; } -static inline int cgroup_bpf_replace(struct bpf_link *link, - struct bpf_prog *old_prog, - struct bpf_prog *new_prog) -{ - return -EINVAL; -} - static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 10960cfabea4..81c8620cb4c4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1093,7 +1093,8 @@ struct bpf_link { struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); - + int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog); }; void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, -- cgit v1.2.3 From a3b80e1078943dc12553166fb08e258463dec013 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:06 -0700 Subject: bpf: Allocate ID for bpf_link Generate ID for each bpf_link using IDR, similarly to bpf_map and bpf_prog. bpf_link creation, initialization, attachment, and exposing to user-space through FD and ID is a complicated multi-step process, abstract it away through bpf_link_primer and bpf_link_prime(), bpf_link_settle(), and bpf_link_cleanup() internal API. They guarantee that until bpf_link is properly attached, user-space won't be able to access partially-initialized bpf_link either from FD or ID. All this allows to simplify bpf_link attachment and error handling code. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-3-andriin@fb.com --- include/linux/bpf.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 81c8620cb4c4..875d1f0af803 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1085,11 +1085,19 @@ int bpf_prog_new_fd(struct bpf_prog *prog); struct bpf_link { atomic64_t refcnt; + u32 id; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; }; +struct bpf_link_primer { + struct bpf_link *link; + struct file *file; + int fd; + u32 id; +}; + struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); @@ -1097,10 +1105,11 @@ struct bpf_link_ops { struct bpf_prog *old_prog); }; -void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, - struct bpf_prog *prog); -void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, - int link_fd); +void bpf_link_init(struct bpf_link *link, + const struct bpf_link_ops *ops, struct bpf_prog *prog); +int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); +int bpf_link_settle(struct bpf_link_primer *primer); +void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); -- cgit v1.2.3 From f2e10bff16a0fdd41ba278c84da9813700e356af Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:08 -0700 Subject: bpf: Add support for BPF_OBJ_GET_INFO_BY_FD for bpf_link Add ability to fetch bpf_link details through BPF_OBJ_GET_INFO_BY_FD command. Also enhance show_fdinfo to potentially include bpf_link type-specific information (similarly to obj_info). Also introduce enum bpf_link_type stored in bpf_link itself and expose it in UAPI. bpf_link_tracing also now will store and return bpf_attach_type. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-5-andriin@fb.com --- include/linux/bpf-cgroup.h | 2 -- include/linux/bpf.h | 8 +++++++- include/linux/bpf_types.h | 6 ++++++ 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a9cb9a5bf8e9..272626cc3fc9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -57,8 +57,6 @@ struct bpf_cgroup_link { enum bpf_attach_type type; }; -extern const struct bpf_link_ops bpf_cgroup_link_lops; - struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 875d1f0af803..c07b1d2f3824 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1026,9 +1026,11 @@ extern const struct file_operations bpf_prog_fops; extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; +#define BPF_LINK_TYPE(_id, _name) #include #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; @@ -1086,6 +1088,7 @@ int bpf_prog_new_fd(struct bpf_prog *prog); struct bpf_link { atomic64_t refcnt; u32 id; + enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; @@ -1103,9 +1106,12 @@ struct bpf_link_ops { void (*dealloc)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); + void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); + int (*fill_link_info)(const struct bpf_link *link, + struct bpf_link_info *info); }; -void bpf_link_init(struct bpf_link *link, +void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index ba0c2d56f8a3..8345cdf553b8 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -118,3 +118,9 @@ 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 + +BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) +BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) +#ifdef CONFIG_CGROUP_BPF +BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) +#endif -- cgit v1.2.3 From 61365ca7b24f1cb106a4c619c94610862bbec778 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 15 Apr 2020 14:14:49 +0200 Subject: backlight: l4f00242t03: Convert to GPIO descriptors This converts the l4f00242t03 backlight driver to use GPIO descriptors and switches the two Freescale i.MX boards over to passing descriptors instead of global GPIO numbers. We use the typical names "enable" and "reset" as found in the device tree bindings for panel GPIOs. This saves a lot of code in the driver and makes it possible to get rid of the platform data header altogether. Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Acked-by: Shawn Guo Signed-off-by: Lee Jones --- include/linux/spi/l4f00242t03.h | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 include/linux/spi/l4f00242t03.h (limited to 'include/linux') diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h deleted file mode 100644 index 831a5de7a0e2..000000000000 --- a/include/linux/spi/l4f00242t03.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * l4f00242t03.h -- Platform glue for Epson L4F00242T03 LCD - * - * Copyright (c) 2009 Alberto Panizzo - * Based on Marek Vasut work in lms283gf05.h -*/ - -#ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_ -#define _INCLUDE_LINUX_SPI_L4F00242T03_H_ - -struct l4f00242t03_pdata { - unsigned int reset_gpio; - unsigned int data_enable_gpio; -}; - -#endif /* _INCLUDE_LINUX_SPI_L4F00242T03_H_ */ -- cgit v1.2.3 From 36b5215436ad115551e12478ceb3be4a2279e415 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 28 Apr 2020 17:23:27 -0700 Subject: gpio: Document proper return value for gpio drivers The legacy defines GPIOF_DIR_XXX are only for consumers. Document the proper ones. Also: don't use "_XXX" since that's harder to find with "git grep". Just list both of the values. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20200428172322.1.I396f351e364f3c09df7c7606e79abefb8682c092@changeid Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b8fc92c177eb..7b5f5681b7e4 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -267,9 +267,9 @@ struct gpio_irq_chip { * @free: optional hook for chip-specific deactivation, such as * disabling module power and clock; may sleep * @get_direction: returns direction for signal "offset", 0=out, 1=in, - * (same as GPIOF_DIR_XXX), or negative error. - * It is recommended to always implement this function, even on - * input-only or output-only gpio chips. + * (same as GPIO_LINE_DIRECTION_OUT / GPIO_LINE_DIRECTION_IN), + * or negative error. It is recommended to always implement this + * function, even on input-only or output-only gpio chips. * @direction_input: configures signal "offset" as input, or returns error * This can be omitted on input-only or output-only gpio chips. * @direction_output: configures signal "offset" as output, or returns error -- cgit v1.2.3 From 8d0910121b070b4edf4239d91cf9a4523b33ca0c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 28 Apr 2020 17:23:28 -0700 Subject: gpio: Make "offset" and "unsigned int", not just "unsigned" When I copied the function prototypes from the GPIO header file into my own driver, checkpatch yelled at me saying that I shouldn't use use "unsigned" but instead should say "unsigned int". Let's make the header file use "unsigned int" so others who copy like I did won't get yelled at. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20200428172322.2.Iacb3c8152c3cf9015a91308678155a578b0cc050@changeid Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 7b5f5681b7e4..8c41ae41b6bb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -349,30 +349,30 @@ struct gpio_chip { struct module *owner; int (*request)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); void (*free)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*get_direction)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*direction_input)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*direction_output)(struct gpio_chip *gc, - unsigned offset, int value); + unsigned int offset, int value); int (*get)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*get_multiple)(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits); void (*set)(struct gpio_chip *gc, - unsigned offset, int value); + unsigned int offset, int value); void (*set_multiple)(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits); int (*set_config)(struct gpio_chip *gc, - unsigned offset, + unsigned int offset, unsigned long config); int (*to_irq)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); void (*dbg_show)(struct seq_file *s, struct gpio_chip *gc); @@ -459,7 +459,7 @@ struct gpio_chip { }; extern const char *gpiochip_is_requested(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); /* add/remove chips */ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, @@ -657,9 +657,9 @@ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gc, } #endif /* CONFIG_LOCKDEP */ -int gpiochip_generic_request(struct gpio_chip *gc, unsigned offset); -void gpiochip_generic_free(struct gpio_chip *gc, unsigned offset); -int gpiochip_generic_config(struct gpio_chip *gc, unsigned offset, +int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset); +void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset); +int gpiochip_generic_config(struct gpio_chip *gc, unsigned int offset, unsigned long config); /** -- cgit v1.2.3 From 0376e9efe18388bd486a65edbc16d34b84bddc8f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Apr 2020 13:27:55 +0200 Subject: block: replace BIO_QUEUE_ENTERED with BIO_CGROUP_ACCT BIO_QUEUE_ENTERED is only used for cgroup accounting now, so rename the flag and move setting it into the cgroup code. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 10 ++++++---- include/linux/blk_types.h | 2 +- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 35f8ffe92b70..4deb8bb7b6af 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -607,12 +607,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, u64_stats_update_begin(&bis->sync); /* - * If the bio is flagged with BIO_QUEUE_ENTERED it means this - * is a split bio and we would have already accounted for the - * size of the bio. + * If the bio is flagged with BIO_CGROUP_ACCT it means this is a + * split bio and we would have already accounted for the size of + * the bio. */ - if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) + if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { + bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; + } bis->cur.ios[rwd]++; u64_stats_update_end(&bis->sync); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 31eb92876be7..90895d594e64 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -220,7 +220,7 @@ enum { * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ - BIO_QUEUE_ENTERED, /* can use blk_queue_enter_live() */ + BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_FLAG_LAST }; -- cgit v1.2.3 From b31d1d2b1c3a8452f425b09ebd374ecd3ddd5179 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Mon, 27 Apr 2020 15:59:02 -0700 Subject: platform/chrome: cros_ec_sensorhub: Allocate sensorhub resource before claiming sensors Allocate callbacks array before enumerating the sensors: The probe routine for these sensors (for instance cros_ec_sensors_probe) can be called within the sensorhub probe routine (cros_ec_sensors_probe()) Fixes: 145d59baff594 ("platform/chrome: cros_ec_sensorhub: Add FIFO support") Signed-off-by: Gwendal Grignou Reported-by: Douglas Anderson Tested-by: Douglas Anderson Signed-off-by: Enric Balletbo i Serra --- include/linux/platform_data/cros_ec_sensorhub.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h index c588be843f61..0ecce6aa69d5 100644 --- a/include/linux/platform_data/cros_ec_sensorhub.h +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -185,6 +185,7 @@ int cros_ec_sensorhub_register_push_data(struct cros_ec_sensorhub *sensorhub, void cros_ec_sensorhub_unregister_push_data(struct cros_ec_sensorhub *sensorhub, u8 sensor_num); +int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub); int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub); void cros_ec_sensorhub_ring_remove(void *arg); int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub, -- cgit v1.2.3 From 3c2214b6027ff37945799de717c417212e1a8c54 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 21 Apr 2020 12:34:55 -0400 Subject: padata: add separate cpuhp node for CPUHP_PADATA_DEAD Removing the pcrypt module triggers this: general protection fault, probably for non-canonical address 0xdead000000000122 CPU: 5 PID: 264 Comm: modprobe Not tainted 5.6.0+ #2 Hardware name: QEMU Standard PC RIP: 0010:__cpuhp_state_remove_instance+0xcc/0x120 Call Trace: padata_sysfs_release+0x74/0xce kobject_put+0x81/0xd0 padata_free+0x12/0x20 pcrypt_exit+0x43/0x8ee [pcrypt] padata instances wrongly use the same hlist node for the online and dead states, so __padata_free()'s second cpuhp remove call chokes on the node that the first poisoned. cpuhp multi-instance callbacks only walk forward in cpuhp_step->list and the same node is linked in both the online and dead lists, so the list corruption that results from padata_alloc() adding the node to a second list without removing it from the first doesn't cause problems as long as no instances are freed. Avoid the issue by giving each state its own node. Fixes: 894c9ef9780c ("padata: validate cpumask without removed CPU during offline") Signed-off-by: Daniel Jordan Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Herbert Xu --- include/linux/padata.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index a0d8b41850b2..693cae9bfe66 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -139,7 +139,8 @@ struct padata_shell { /** * struct padata_instance - The overall control structure. * - * @node: Used by CPU hotplug. + * @cpu_online_node: Linkage for CPU online callback. + * @cpu_dead_node: Linkage for CPU offline callback. * @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. @@ -150,7 +151,8 @@ struct padata_shell { * @flags: padata flags. */ struct padata_instance { - struct hlist_node node; + struct hlist_node cpu_online_node; + struct hlist_node cpu_dead_node; struct workqueue_struct *parallel_wq; struct workqueue_struct *serial_wq; struct list_head pslist; -- cgit v1.2.3 From 97f9ac3db6612f14ac0c509e1a63ce14fd4cc0eb Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Tue, 21 Apr 2020 12:44:49 -0500 Subject: crypto: ccp - Add support for SEV-ES to the PSP driver To provide support for SEV-ES, the hypervisor must provide an area of memory to the PSP. Once this Trusted Memory Region (TMR) is provided to the PSP, the contents of this area of memory are no longer available to the x86. Update the PSP driver to allocate a 1MB region for the TMR that is 1MB aligned and then provide it to the PSP through the SEV INIT command. Signed-off-by: Tom Lendacky Reviewed-by: Brijesh Singh Reviewed-by: Joerg Roedel Signed-off-by: Herbert Xu --- include/linux/psp-sev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 5167bf2bfc75..7fbc8679145c 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -100,6 +100,8 @@ struct sev_data_init { u32 tmr_len; /* In */ } __packed; +#define SEV_INIT_FLAGS_SEV_ES 0x01 + /** * struct sev_data_pek_csr - PEK_CSR command parameters * -- cgit v1.2.3 From 0da0e31600e8a42c6f1dfaa7a06211c8bb243ea7 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 3 Apr 2020 19:44:52 +0200 Subject: of: reserved-memory: Support lookup of regions by name Add support for looking up memory regions by name. This looks up the given name in the newly introduced memory-region-names property and returns the memory region at the corresponding index in the memory- region(s) property. Reviewed-by: Rob Herring Signed-off-by: Thierry Reding --- include/linux/of_reserved_mem.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index 60f541912ccf..a1b427ac291b 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -33,6 +33,9 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem); int of_reserved_mem_device_init_by_idx(struct device *dev, struct device_node *np, int idx); +int of_reserved_mem_device_init_by_name(struct device *dev, + struct device_node *np, + const char *name); void of_reserved_mem_device_release(struct device *dev); void fdt_init_reserved_mem(void); @@ -45,6 +48,14 @@ static inline int of_reserved_mem_device_init_by_idx(struct device *dev, { return -ENOSYS; } + +static inline int of_reserved_mem_device_init_by_name(struct device *dev, + struct device_node *np, + const char *name) +{ + return -ENOSYS; +} + static inline void of_reserved_mem_device_release(struct device *pdev) { } static inline void fdt_init_reserved_mem(void) { } -- cgit v1.2.3 From 6f49c2515e2258f08f2b905c9772dbf729610415 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 7 Apr 2020 21:20:34 -0700 Subject: dma-buf: fix documentation build warnings Fix documentation warnings in dma-buf.[hc]: ../drivers/dma-buf/dma-buf.c:678: warning: Function parameter or member 'importer_ops' not described in 'dma_buf_dynamic_attach' ../drivers/dma-buf/dma-buf.c:678: warning: Function parameter or member 'importer_priv' not described in 'dma_buf_dynamic_attach' ../include/linux/dma-buf.h:339: warning: Incorrect use of kernel-doc format: * @move_notify Signed-off-by: Randy Dunlap Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/7bcbe6fe-0b4b-87da-d003-b68a26eb4cf0@infradead.org --- include/linux/dma-buf.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 1ade486fc2bb..57bcef6f988a 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -329,13 +329,12 @@ struct dma_buf { /** * struct dma_buf_attach_ops - importer operations for an attachment - * @move_notify: [optional] notification that the DMA-buf is moving * * Attachment operations implemented by the importer. */ struct dma_buf_attach_ops { /** - * @move_notify + * @move_notify: [optional] notification that the DMA-buf is moving * * If this callback is provided the framework can avoid pinning the * backing store while mappings exists. -- cgit v1.2.3 From 8aa8eb2a8f5b3305a95f39957dd2b715fa668e21 Mon Sep 17 00:00:00 2001 From: Alexandre Chartre Date: Tue, 14 Apr 2020 12:36:12 +0200 Subject: objtool: Add support for intra-function calls Change objtool to support intra-function calls. On x86, an intra-function call is represented in objtool as a push onto the stack (of the return address), and a jump to the destination address. That way the stack information is correctly updated and the call flow is still accurate. Signed-off-by: Alexandre Chartre Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miroslav Benes Acked-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20200414103618.12657-4-alexandre.chartre@oracle.com --- include/linux/frame.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/frame.h b/include/linux/frame.h index 02d3ca2d9598..303cda600e56 100644 --- a/include/linux/frame.h +++ b/include/linux/frame.h @@ -15,9 +15,20 @@ static void __used __section(.discard.func_stack_frame_non_standard) \ *__func_stack_frame_non_standard_##func = func +/* + * This macro indicates that the following intra-function call is valid. + * Any non-annotated intra-function call will cause objtool to issue a warning. + */ +#define ANNOTATE_INTRA_FUNCTION_CALL \ + 999: \ + .pushsection .discard.intra_function_calls; \ + .long 999b; \ + .popsection; + #else /* !CONFIG_STACK_VALIDATION */ #define STACK_FRAME_NON_STANDARD(func) +#define ANNOTATE_INTRA_FUNCTION_CALL #endif /* CONFIG_STACK_VALIDATION */ -- cgit v1.2.3 From 36c5bdc4387056af3840adb4478c752faeb9d15e Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 15 Apr 2020 22:05:07 +0100 Subject: sched/topology: Kill SD_LOAD_BALANCE That flag is set unconditionally in sd_init(), and no one checks for it anymore. Remove it. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200415210512.805-5-valentin.schneider@arm.com --- include/linux/sched/topology.h | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 95253ad792b0..fb11091129b3 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -11,21 +11,20 @@ */ #ifdef CONFIG_SMP -#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ -#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ -#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ -#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ -#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ -#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ -#define SD_ASYM_CPUCAPACITY 0x0040 /* Domain members have different CPU capacities */ -#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share CPU capacity */ -#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ -#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share CPU pkg resources */ -#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ -#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ -#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ -#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ -#define SD_NUMA 0x4000 /* cross-node balancing */ +#define SD_BALANCE_NEWIDLE 0x0001 /* Balance when about to become idle */ +#define SD_BALANCE_EXEC 0x0002 /* Balance on exec */ +#define SD_BALANCE_FORK 0x0004 /* Balance on fork, clone */ +#define SD_BALANCE_WAKE 0x0008 /* Balance on wakeup */ +#define SD_WAKE_AFFINE 0x0010 /* Wake task to waking CPU */ +#define SD_ASYM_CPUCAPACITY 0x0020 /* Domain members have different CPU capacities */ +#define SD_SHARE_CPUCAPACITY 0x0040 /* Domain members share CPU capacity */ +#define SD_SHARE_POWERDOMAIN 0x0080 /* Domain members share power domain */ +#define SD_SHARE_PKG_RESOURCES 0x0100 /* Domain members share CPU pkg resources */ +#define SD_SERIALIZE 0x0200 /* Only a single load balancing instance */ +#define SD_ASYM_PACKING 0x0400 /* Place busy groups earlier in the domain */ +#define SD_PREFER_SIBLING 0x0800 /* Prefer to place tasks in a sibling domain */ +#define SD_OVERLAP 0x1000 /* sched_domains of this level overlap */ +#define SD_NUMA 0x2000 /* cross-node balancing */ #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) -- cgit v1.2.3 From bf2c59fce4074e55d622089b34be3a6bc95484fb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 1 Apr 2020 17:40:33 -0400 Subject: sched/core: Fix illegal RCU from offline CPUs In the CPU-offline process, it calls mmdrop() after idle entry and the subsequent call to cpuhp_report_idle_dead(). Once execution passes the call to rcu_report_dead(), RCU is ignoring the CPU, which results in lockdep complaining when mmdrop() uses RCU from either memcg or debugobjects below. Fix it by cleaning up the active_mm state from BP instead. Every arch which has CONFIG_HOTPLUG_CPU should have already called idle_task_exit() from AP. The only exception is parisc because it switches them to &init_mm unconditionally (see smp_boot_one_cpu() and smp_cpu_init()), but the patch will still work there because it calls mmgrab(&init_mm) in smp_cpu_init() and then should call mmdrop(&init_mm) in finish_cpu(). WARNING: suspicious RCU usage ----------------------------- kernel/workqueue.c:710 RCU or wq_pool_mutex should be held! other info that might help us debug this: RCU used illegally from offline CPU! Call Trace: dump_stack+0xf4/0x164 (unreliable) lockdep_rcu_suspicious+0x140/0x164 get_work_pool+0x110/0x150 __queue_work+0x1bc/0xca0 queue_work_on+0x114/0x120 css_release+0x9c/0xc0 percpu_ref_put_many+0x204/0x230 free_pcp_prepare+0x264/0x570 free_unref_page+0x38/0xf0 __mmdrop+0x21c/0x2c0 idle_task_exit+0x170/0x1b0 pnv_smp_cpu_kill_self+0x38/0x2e0 cpu_die+0x48/0x64 arch_cpu_idle_dead+0x30/0x50 do_idle+0x2f4/0x470 cpu_startup_entry+0x38/0x40 start_secondary+0x7a8/0xa80 start_secondary_resume+0x10/0x14 Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Qian Cai Signed-off-by: Peter Zijlstra (Intel) Acked-by: Michael Ellerman (powerpc) Link: https://lkml.kernel.org/r/20200401214033.8448-1-cai@lca.pw --- include/linux/sched/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index c49257a3b510..a132d875d351 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,8 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +void mmdrop(struct mm_struct *mm); + /* * This has to be called after a get_task_mm()/mmget_not_zero() * followed by taking the mmap_sem for writing before modifying the -- cgit v1.2.3 From 12ac6782a40ad7636b6ef45680741825b64ab221 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 21 Apr 2020 21:07:39 -0700 Subject: sched/swait: Reword some of the main description With both the increased use of swait and kvm no longer using it, we can reword some of the comments. While removing Linus' valid rant, I've also cared to explicitly mention that swait is very different than regular wait. In addition it is mentioned against using swait in favor of the regular flavor. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200422040739.18601-6-dave@stgolabs.net --- include/linux/swait.h | 23 +++++------------------ 1 file changed, 5 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index 73e06e9986d4..6a8c22b8c2a5 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -9,23 +9,10 @@ #include /* - * BROKEN wait-queues. - * - * These "simple" wait-queues are broken garbage, and should never be - * used. The comments below claim that they are "similar" to regular - * wait-queues, but the semantics are actually completely different, and - * every single user we have ever had has been buggy (or pointless). - * - * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what - * "wake_up()" does, and has led to problems. In other cases, it has - * been fine, because there's only ever one waiter (kvm), but in that - * case gthe whole "simple" wait-queue is just pointless to begin with, - * since there is no "queue". Use "wake_up_process()" with a direct - * pointer instead. - * - * While these are very similar to regular wait queues (wait.h) the most - * important difference is that the simple waitqueue allows for deterministic - * behaviour -- IOW it has strictly bounded IRQ and lock hold times. + * Simple waitqueues are semantically very different to regular wait queues + * (wait.h). The most important difference is that the simple waitqueue allows + * for deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold + * times. * * Mainly, this is accomplished by two things. Firstly not allowing swake_up_all * from IRQ disabled, and dropping the lock upon every wakeup, giving a higher @@ -39,7 +26,7 @@ * sleeper state. * * - the !exclusive mode; because that leads to O(n) wakeups, everything is - * exclusive. + * exclusive. As such swake_up_one will only ever awake _one_ waiter. * * - custom wake callback functions; because you cannot give any guarantees * about random code. This also allows swait to be used in RT, such that -- cgit v1.2.3 From cfde141ea3faa30e362bbdb5c28001bbbdb0b8e0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 30 Apr 2020 15:01:52 +0200 Subject: mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/tcp.h | 51 --------------------------------------------------- 1 file changed, 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 421c99c12291..4f8159e90ce1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -78,47 +78,6 @@ 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; - u64 data_ack; - u64 data_seq; - u32 subflow_seq; - u16 data_len; - u16 mp_capable : 1, - mp_join : 1, - dss : 1, - add_addr : 1, - rm_addr : 1, - family : 4, - echo : 1, - backup : 1; - u32 token; - u32 nonce; - u64 thmac; - u8 hmac[20]; - u8 join_id; - u8 use_map:1, - dsn64:1, - data_fin:1, - use_ack:1, - ack64:1, - mpc_map:1, - __unused:2; - u8 addr_id; - u8 rm_id; - union { - struct in_addr addr; -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - struct in6_addr addr6; -#endif - }; - u64 ahmac; - u16 port; -}; -#endif - struct tcp_options_received { /* PAWS/RTTM data */ int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ @@ -136,9 +95,6 @@ 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) @@ -148,13 +104,6 @@ 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.add_addr = 0; - rx_opt->mptcp.rm_addr = 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 6e3a401fc8af01828bcdc92d713195d318b36e7e Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 30 Apr 2020 18:51:14 +0300 Subject: inet_diag: add cgroup id attribute This patch adds cgroup v2 ID to common inet diag message attributes. Cgroup v2 ID is kernfs ID (ino or ino+gen). This attribute allows filter inet diag output by cgroup ID obtained by name_to_handle_at() syscall. When net_cls or net_prio cgroup is activated this ID is equal to 1 (root cgroup ID) for newly created sockets. Some notes about this ID: 1) gets initialized in socket() syscall 2) incoming socket gets ID from listening socket (not during accept() syscall) 3) not changed when process get moved to another cgroup 4) can point to deleted cgroup (refcounting) v2: - use CONFIG_SOCK_CGROUP_DATA instead if CONFIG_CGROUPS v3: - fix attr size by using nla_total_size_64bit() (Eric Dumazet) - more detailed commit message (Konstantin Khlebnikov) Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Acked-By: Tejun Heo Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index ce9ed1c0602f..0ef2d800fda7 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -71,7 +71,11 @@ static inline size_t inet_diag_msg_attrs_size(void) + nla_total_size(1) /* INET_DIAG_SKV6ONLY */ #endif + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4); /* INET_DIAG_CLASS_ID */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ +#ifdef CONFIG_SOCK_CGROUP_DATA + + nla_total_size_64bit(sizeof(u64)) /* INET_DIAG_CGROUP_ID */ +#endif + ; } int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, -- cgit v1.2.3 From ea5bacaa2cec6967ed337f4d0ad6034123ca737b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 30 Apr 2020 18:04:03 +0200 Subject: docs: networking: convert netdev-features.txt to ReST Not much to be done here: - add SPDX header; - adjust titles and chapters, adding proper markups; - add to networking/index.rst. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 9d53c5ad272c..2cc3cf80b49a 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -89,7 +89,7 @@ enum { * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/core/ethtool.c and maybe * some feature mask #defines below. Please also describe it - * in Documentation/networking/netdev-features.txt. + * in Documentation/networking/netdev-features.rst. */ /**/NETDEV_FEATURE_COUNT -- cgit v1.2.3 From 2b195850128f5bafde177b12489d9fa27962cc1e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 30 Apr 2020 10:35:41 -0700 Subject: tcp: add tp->dup_ack_counter In commit 86de5921a3d5 ("tcp: defer SACK compression after DupThresh") I added a TCP_FASTRETRANS_THRESH bias to tp->compressed_ack in order to enable sack compression only after 3 dupacks. Since we plan to relax this rule for flows that involve stacks not requiring this old rule, this patch adds a distinct tp->dup_ack_counter. This means the TCP_FASTRETRANS_THRESH value is now used in a single location that a future patch can adjust: if (tp->dup_ack_counter < TCP_FASTRETRANS_THRESH) { tp->dup_ack_counter++; goto send_now; } This patch also introduces tcp_sack_compress_send_ack() helper to ease following patch comprehension. This patch refines LINUX_MIB_TCPACKCOMPRESSED to not count the acks that we had to send if the timer expires or tcp_sack_compress_send_ack() is sending an ack. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 421c99c12291..2c6f87e9f0cf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -268,6 +268,7 @@ struct tcp_sock { } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; + u8 dup_ack_counter; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ -- cgit v1.2.3 From 54c52e10dc9b939084a7e6e3d32ce8fd8dee7898 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 13 Apr 2020 12:27:55 -0400 Subject: blk-iocost: switch to fixed non-auto-decaying use_delay The use_delay mechanism was introduced by blk-iolatency to hold memory allocators accountable for the reclaim and other shared IOs they cause. The duration of the delay is dynamically balanced between iolatency increasing the value on each target miss and it auto-decaying as time passes and threads get delayed on it. While this works well for iolatency, iocost's control model isn't compatible with it. There is no repeated "violation" events which can be balanced against auto-decaying. iocost instead knows how much a given cgroup is over budget and wants to prevent that cgroup from issuing IOs while over budget. Until now, iocost has been adding the cost of force-issued IOs. However, this doesn't reflect the amount which is already over budget and is simply not enough to counter the auto-decaying allowing anon-memory leaking low priority cgroup to go over its alloted share of IOs. As auto-decaying doesn't make much sense for iocost, this patch introduces a different mode of operation for use_delay - when blkcg_set_delay() are used insted of blkcg_add/use_delay(), the delay duration is not auto-decayed until it is explicitly cleared with blkcg_clear_delay(). iocost is updated to keep the delay duration synchronized to the budget overage amount. With this change, iocost can effectively police cgroups which generate significant amount of force-issued IOs. Signed-off-by: Tejun Heo Cc: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 43 +++++++++++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 4deb8bb7b6af..a57ebe2f00ab 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -631,6 +631,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, static inline void blkcg_use_delay(struct blkcg_gq *blkg) { + if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) + return; if (atomic_add_return(1, &blkg->use_delay) == 1) atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); } @@ -639,6 +641,8 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); + if (WARN_ON_ONCE(old < 0)) + return 0; if (old == 0) return 0; @@ -663,20 +667,39 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) return 1; } +/** + * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount + * @blkg: target blkg + * @delay: delay duration in nsecs + * + * When enabled with this function, the delay is not decayed and must be + * explicitly cleared with blkcg_clear_delay(). Must not be mixed with + * blkcg_[un]use_delay() and blkcg_add_delay() usages. + */ +static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) +{ + int old = atomic_read(&blkg->use_delay); + + /* We only want 1 person setting the congestion count for this blkg. */ + if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old) + atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); + + atomic64_set(&blkg->delay_nsec, delay); +} + +/** + * blkcg_clear_delay - Disable allocator delay mechanism + * @blkg: target blkg + * + * Disable use_delay mechanism. See blkcg_set_delay(). + */ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); - if (!old) - return; + /* We only want 1 person clearing the congestion count for this blkg. */ - while (old) { - int cur = atomic_cmpxchg(&blkg->use_delay, old, 0); - if (cur == old) { - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); - break; - } - old = cur; - } + if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old) + atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); } void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); -- cgit v1.2.3 From c100beb9ccfb98e2474586a4006483cbf770c823 Mon Sep 17 00:00:00 2001 From: Alexandru Gagniuc Date: Mon, 27 Apr 2020 18:25:13 -0500 Subject: PCI/AER: Use only _OSC to determine AER ownership Per the PCI Firmware spec, r3.2, sec 4.5.1, the OS can request control of AER via bit 3 of the _OSC Control Field. In the returned value of the Control Field: The firmware sets [bit 3] to 1 to grant control over PCI Express Advanced Error Reporting. ... after control is transferred to the operating system, firmware must not modify the Advanced Error Reporting Capability. If control of this feature was requested and denied or was not requested, firmware returns this bit set to 0. Previously the pci_root driver looked at the HEST FIRMWARE_FIRST bit to determine whether to request ownership of the AER Capability. This was based on ACPI spec v6.3, sec 18.3.2.4, and similar sections, which say things like: Bit [0] - FIRMWARE_FIRST: If set, indicates that system firmware will handle errors from this source first. Bit [1] - GLOBAL: If set, indicates that the settings contained in this structure apply globally to all PCI Express Devices. These ACPI references don't say anything about ownership of the AER Capability. Remove use of the FIRMWARE_FIRST bit and rely only on the _OSC bit to determine whether we have control of the AER Capability. Link: https://lore.kernel.org/r/20181115231605.24352-1-mr.nuke.me@gmail.com/ v1 Link: https://lore.kernel.org/r/20190326172343.28946-1-mr.nuke.me@gmail.com/ v2 Link: https://lore.kernel.org/r/67af2931705bed9a588b5a39d369cb70b9942190.1587925636.git.sathyanarayanan.kuppuswamy@linux.intel.com [bhelgaas: commit log, note: Alex posted this identical patch 18 months ago, and I failed to apply it then, so I made him the author, added links to his postings, and added his Signed-off-by] Signed-off-by: Alexandru Gagniuc Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Reviewed-by: Jon Derrick --- include/linux/pci-acpi.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 2d155bfb8fbf..11c98875538a 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -125,10 +125,4 @@ static inline void acpi_pci_add_bus(struct pci_bus *bus) { } static inline void acpi_pci_remove_bus(struct pci_bus *bus) { } #endif /* CONFIG_ACPI */ -#ifdef CONFIG_ACPI_APEI -extern bool aer_acpi_firmware_first(void); -#else -static inline bool aer_acpi_firmware_first(void) { return false; } -#endif - #endif /* _PCI_ACPI_H_ */ -- cgit v1.2.3 From 999a22890cb183b918e4372395d24426a755cef2 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 3 Apr 2020 07:20:50 +0000 Subject: uaccess: Add user_read_access_begin/end and user_write_access_begin/end Some architectures like powerpc64 have the capability to separate read access and write access protection. For get_user() and copy_from_user(), powerpc64 only open read access. For put_user() and copy_to_user(), powerpc64 only open write access. But when using unsafe_get_user() or unsafe_put_user(), user_access_begin open both read and write. Other architectures like powerpc book3s 32 bits only allow write access protection. And on this architecture protection is an heavy operation as it requires locking/unlocking per segment of 256Mbytes. On those architecture it is therefore desirable to do the unlocking only for write access. (Note that book3s/32 ranges from very old powermac from the 90's with powerpc 601 processor, till modern ADSL boxes with PowerQuicc II processors for instance so it is still worth considering.) In order to avoid any risk based of hacking some variable parameters passed to user_access_begin/end that would allow hacking and leaving user access open or opening too much, it is preferable to use dedicated static functions that can't be overridden. Add a user_read_access_begin and user_read_access_end to only open read access. Add a user_write_access_begin and user_write_access_end to only open write access. By default, when undefined, those new access helpers default on the existing user_access_begin and user_access_end. Signed-off-by: Christophe Leroy Reviewed-by: Kees Cook Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/36e43241c7f043a24b5069e78c6a7edd11043be5.1585898438.git.christophe.leroy@c-s.fr --- include/linux/uaccess.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 67f016010aad..9861c89f93be 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -378,6 +378,14 @@ extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif +#ifndef user_write_access_begin +#define user_write_access_begin user_access_begin +#define user_write_access_end user_access_end +#endif +#ifndef user_read_access_begin +#define user_read_access_begin user_access_begin +#define user_read_access_end user_access_end +#endif #ifdef CONFIG_HARDENED_USERCOPY void usercopy_warn(const char *name, const char *detail, bool to_user, -- cgit v1.2.3 From f256356f65e6449a9fcf6089ea25882c91768665 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 27 Apr 2020 11:39:03 +0800 Subject: ptp_qoriq: output PPS signal on FIPER2 in default Output PPS signal on FIPER2 (Fixed Period Interval Pulse) in default which is more desired by user. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 75884563059f..884b8f8ca06d 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -135,7 +135,7 @@ struct ptp_qoriq_registers { #define DEFAULT_CKSEL 1 #define DEFAULT_TMR_PRSC 2 #define DEFAULT_FIPER1_PERIOD 1000000000 -#define DEFAULT_FIPER2_PERIOD 100000 +#define DEFAULT_FIPER2_PERIOD 1000000000 struct ptp_qoriq { void __iomem *base; -- cgit v1.2.3 From 54261af473be4c5481f6196064445d2945f2bdab Mon Sep 17 00:00:00 2001 From: KP Singh Date: Thu, 30 Apr 2020 17:52:40 +0200 Subject: security: Fix the default value of fs_context_parse_param hook security_fs_context_parse_param is called by vfs_parse_fs_param and a succussful return value (i.e 0) implies that a parameter will be consumed by the LSM framework. This stops all further parsing of the parmeter by VFS. Furthermore, if an LSM hook returns a success, the remaining LSM hooks are not invoked for the parameter. The current default behavior of returning success means that all the parameters are expected to be parsed by the LSM hook and none of them end up being populated by vfs in fs_context This was noticed when lsm=bpf is supplied on the command line before any other LSM. As the bpf lsm uses this default value to implement a default hook, this resulted in a failure to parse any fs_context parameters and a failure to mount the root filesystem. Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks") Reported-by: Mikko Ylinen Signed-off-by: KP Singh Signed-off-by: James Morris --- include/linux/lsm_hook_defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..1bdd027766d4 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -55,7 +55,7 @@ LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) -LSM_HOOK(int, 0, fs_context_parse_param, struct fs_context *fc, +LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) -- cgit v1.2.3 From e4e51da66dc812176cca16b0f8a5b87b173deb5d Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 29 Apr 2020 01:06:59 +0200 Subject: net: phy: bcm54140: add second PHY ID This PHY has two PHY IDs depending on its mode. Adjust the mask so that it includes both IDs. Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 8be150e69c7c..58d0150acc3e 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -25,7 +25,7 @@ #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 -#define PHY_ID_BCM54140 0xae025019 +#define PHY_ID_BCM54140 0xae025009 #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM89610 0x03625cd0 -- cgit v1.2.3 From 9ba2353b2cc58ba13f7a7369208107f133f6a27b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Fri, 3 Apr 2020 22:20:32 +0200 Subject: power: supply: core: allow to constify property lists MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since tables pointed to by power_supply_desc->properties and ->usb_types are not expected to change after registration, mark the pointers accordingly Signed-off-by: Michał Mirosław Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index dcd5a71e6c67..6a34df65d4d1 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -223,9 +223,9 @@ struct power_supply_config { struct power_supply_desc { const char *name; enum power_supply_type type; - enum power_supply_usb_type *usb_types; + const enum power_supply_usb_type *usb_types; size_t num_usb_types; - enum power_supply_property *properties; + const enum power_supply_property *properties; size_t num_properties; /* -- cgit v1.2.3 From 0b104773b4f72ccd8af98a2f1efe69b174c344d3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 9 Apr 2020 17:49:21 -0600 Subject: PCI: Constify struct pci_ecam_ops struct pci_ecam_ops is typically DT match table data which is defined to be const. It's also best practice for ops structs to be const. Ideally, we'd make struct pci_ops const as well, but that becomes pretty invasive, so for now we just cast it where needed. Link: https://lore.kernel.org/r/20200409234923.21598-2-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas Acked-by: Catalin Marinas Cc: Catalin Marinas Cc: Will Deacon Cc: Lorenzo Pieralisi Cc: Andrew Murray Cc: Bjorn Helgaas Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Jonathan Chocron Cc: Zhou Wang Cc: Robert Richter Cc: Toan Le Cc: Marc Gonzalez Cc: Mans Rullgard Cc: linux-acpi@vger.kernel.org --- include/linux/pci-acpi.h | 2 +- include/linux/pci-ecam.h | 22 +++++++++++----------- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 2d155bfb8fbf..81f5535ca1b5 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -27,7 +27,7 @@ extern phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle); struct pci_ecam_ops; extern int pci_mcfg_lookup(struct acpi_pci_root *root, struct resource *cfgres, - struct pci_ecam_ops **ecam_ops); + const struct pci_ecam_ops **ecam_ops); static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index a73164c85e78..6c21dd0901ab 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -29,7 +29,7 @@ struct pci_config_window { struct resource res; struct resource busr; void *priv; - struct pci_ecam_ops *ops; + const struct pci_ecam_ops *ops; union { void __iomem *win; /* 64-bit single mapping */ void __iomem **winp; /* 32-bit per-bus mapping */ @@ -40,29 +40,29 @@ struct pci_config_window { /* create and free pci_config_window */ struct pci_config_window *pci_ecam_create(struct device *dev, struct resource *cfgres, struct resource *busr, - struct pci_ecam_ops *ops); + const struct pci_ecam_ops *ops); void pci_ecam_free(struct pci_config_window *cfg); /* map_bus when ->sysdata is an instance of pci_config_window */ void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn, int where); /* default ECAM ops */ -extern struct pci_ecam_ops pci_generic_ecam_ops; +extern const struct pci_ecam_ops pci_generic_ecam_ops; #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) -extern struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ -extern struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ -extern struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */ -extern struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ -extern struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ -extern struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ -extern struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ +extern const struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ +extern const struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ +extern const struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */ +extern const struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ +extern const struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ +extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ +extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ #endif #ifdef CONFIG_PCI_HOST_COMMON /* for DT-based PCI controllers that support ECAM */ int pci_host_common_probe(struct platform_device *pdev, - struct pci_ecam_ops *ops); + const struct pci_ecam_ops *ops); int pci_host_common_remove(struct platform_device *pdev); #endif #endif -- cgit v1.2.3 From 0c59c06a7c90390c3985c9acd58a73320781c15e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 9 Apr 2020 17:49:22 -0600 Subject: PCI: host-generic: Support building as modules Enable building host-generic and its host-common dependency as a module. Link: https://lore.kernel.org/r/20200409234923.21598-3-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Acked-by: Will Deacon Acked-by: Bjorn Helgaas Cc: Lorenzo Pieralisi Cc: Andrew Murray Cc: Bjorn Helgaas Cc: Will Deacon Cc: linux-pci@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org --- include/linux/pci-ecam.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 6c21dd0901ab..fd0edb8b8a00 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -59,7 +59,7 @@ extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ #endif -#ifdef CONFIG_PCI_HOST_COMMON +#if IS_ENABLED(CONFIG_PCI_HOST_COMMON) /* for DT-based PCI controllers that support ECAM */ int pci_host_common_probe(struct platform_device *pdev, const struct pci_ecam_ops *ops); -- cgit v1.2.3 From d46edd671a147032e22cfeb271a5734703093649 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 30 Apr 2020 00:15:04 -0700 Subject: bpf: Sharing bpf runtime stats with BPF_ENABLE_STATS Currently, sysctl kernel.bpf_stats_enabled controls BPF runtime stats. Typical userspace tools use kernel.bpf_stats_enabled as follows: 1. Enable kernel.bpf_stats_enabled; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Disable kernel.bpf_stats_enabled. The problem with this approach is that only one userspace tool can toggle this sysctl. If multiple tools toggle the sysctl at the same time, the measurement may be inaccurate. To fix this problem while keep backward compatibility, introduce a new bpf command BPF_ENABLE_STATS. On success, this command enables stats and returns a valid fd. BPF_ENABLE_STATS takes argument "type". Currently, only one type, BPF_STATS_RUN_TIME, is supported. We can extend the command to support other types of stats in the future. With BPF_ENABLE_STATS, user space tool would have the following flow: 1. Get a fd with BPF_ENABLE_STATS, and make sure it is valid; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Close the fd. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200430071506.1408910-2-songliubraving@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 c07b1d2f3824..1262ec460ab3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -987,6 +987,7 @@ _out: \ #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); +extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, -- cgit v1.2.3 From cff9f12b18915d957a2130885a00f8ab15cff7e4 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 30 Apr 2020 22:21:31 +0300 Subject: net/core: Introduce netdev_get_xmit_slave Add new ndo to get the xmit slave of master device. The reference counters are not incremented so the caller must be careful with locks. User can ask to get the xmit slave assume all the slaves can transmit by set all_slaves arg to true. Signed-off-by: Maor Gottlieb Reviewed-by: Jiri Pirko Reviewed-by: David Ahern Acked-by: David S. Miller Signed-off-by: Saeed Mahameed --- include/linux/netdevice.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 130a668049ab..26bc0f11b7ad 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1146,6 +1146,12 @@ struct netdev_net_notifier { * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * + * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev, + * struct sk_buff *skb, + * bool all_slaves); + * Get the xmit slave of master device. If all_slaves is true, function + * assume all the slaves can transmit. + * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); @@ -1389,6 +1395,9 @@ struct net_device_ops { struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); + struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, @@ -2731,6 +2740,9 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); +struct net_device *netdev_get_xmit_slave(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -- cgit v1.2.3 From c6bc6041b10f70b617f2d13894311fe62027d292 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 30 Apr 2020 22:21:41 +0300 Subject: net/mlx5: Add support to get lag physical port Add function to get the device physical port of the lag slave. Signed-off-by: Maor Gottlieb Reviewed-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d82dbbab8179..267dfcc5493e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1074,6 +1074,8 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); +u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, + struct net_device *slave); int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, -- cgit v1.2.3 From cfc1a89e449c02207952c72a4c0394691fdedf43 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 30 Apr 2020 22:21:46 +0300 Subject: RDMA/mlx5: Set lag tx affinity according to slave The patch sets the lag tx affinity of the data QPs and the GSI QPs according to the LAG xmit slave. For GSI QPs, in case the link layer is Ethenet (RoCE) we create two GSI QPs, one for each physical port. When the driver selects the GSI QP, it will consider the port affinity result. For connected QPs, the driver sets the affinity of the xmit slave. The above, ensures that RC QP and it's corresponding GSI QP will transmit from the same physical port. Link: https://lore.kernel.org/r/20200430192146.12863-17-maorg@mellanox.com Signed-off-by: Maor Gottlieb Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 4 +++- include/linux/mlx5/qp.h | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fb243848132d..c1ba89198335 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1321,7 +1321,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 stat_rate_support[0x10]; u8 reserved_at_1f0[0x1]; u8 pci_sync_for_fw_update_event[0x1]; - u8 reserved_at_1f2[0xa]; + u8 reserved_at_1f2[0x6]; + u8 init2_lag_tx_port_affinity[0x1]; + u8 reserved_at_1fa[0x3]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index f23eb18526fe..b9facdb9b9bd 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -66,6 +66,7 @@ enum mlx5_qp_optpar { MLX5_QP_OPTPAR_RETRY_COUNT = 1 << 12, MLX5_QP_OPTPAR_RNR_RETRY = 1 << 13, MLX5_QP_OPTPAR_ACK_TIMEOUT = 1 << 14, + MLX5_QP_OPTPAR_LAG_TX_AFF = 1 << 15, MLX5_QP_OPTPAR_PRI_PORT = 1 << 16, MLX5_QP_OPTPAR_SRQN = 1 << 18, MLX5_QP_OPTPAR_CQN_RCV = 1 << 19, @@ -321,6 +322,7 @@ struct mlx5_av { struct mlx5_ib_ah { struct ib_ah ibah; struct mlx5_av av; + u8 xmit_port; }; static inline struct mlx5_ib_ah *to_mah(struct ib_ah *ibah) -- cgit v1.2.3 From 184ecc9eb260d5a3bcdddc5bebd18f285ac004e9 Mon Sep 17 00:00:00 2001 From: Vincent Cheng Date: Fri, 1 May 2020 23:35:36 -0400 Subject: ptp: Add adjphase function to support phase offset control. Adds adjust phase function to take advantage of a PHC clock's hardware filtering capability that uses phase offset control word instead of frequency offset control word. Signed-off-by: Vincent Cheng Reviewed-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 121a7eda4593..31144d954d89 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -36,7 +36,7 @@ struct ptp_system_timestamp { }; /** - * struct ptp_clock_info - decribes a PTP hardware clock + * struct ptp_clock_info - describes a PTP hardware clock * * @owner: The clock driver should set to THIS_MODULE. * @name: A short "friendly name" to identify the clock and to @@ -65,6 +65,9 @@ struct ptp_system_timestamp { * parameter delta: Desired frequency offset from nominal frequency * in parts per billion * + * @adjphase: Adjusts the phase offset of the hardware clock. + * parameter delta: Desired change in nanoseconds. + * * @adjtime: Shifts the time of the hardware clock. * parameter delta: Desired change in nanoseconds. * @@ -128,6 +131,7 @@ struct ptp_clock_info { struct ptp_pin_desc *pin_config; int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm); int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); + int (*adjphase)(struct ptp_clock_info *ptp, s32 phase); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); int (*gettimex64)(struct ptp_clock_info *ptp, struct timespec64 *ts, -- cgit v1.2.3 From efbe3c2493d2f7a1e1a753780fe727b34709ebd2 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:33 -0700 Subject: fs: Remove unneeded IS_DAX() check in io_is_direct() Remove the check because DAX now has it's own read/write methods and file systems which support DAX check IS_DAX() prior to IOCB_DIRECT on their own. Therefore, it does not matter if the file state is DAX when the iocb flags are created. Also remove io_is_direct() as it is just a simple flag check. Reviewed-by: Dave Chinner Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..a87cc5845a02 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3394,11 +3394,6 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -static inline bool io_is_direct(struct file *filp) -{ - return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); -} - static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); @@ -3423,7 +3418,7 @@ static inline int iocb_flags(struct file *file) int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; - if (io_is_direct(file)) + if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) res |= IOCB_DSYNC; -- cgit v1.2.3 From a711d91cd97e6c9a554ccd1652527a7f36661857 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:57:00 +0200 Subject: block: add a cdrom_device_info pointer to struct gendisk Add a pointer to the CDROM information structure to struct gendisk. This will allow various removable media file systems to call directly into the CDROM layer instead of abusing ioctls with kernel pointers. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 2 +- include/linux/genhd.h | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 528271c60018..4f74ce050253 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -104,7 +104,7 @@ extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); extern int cdrom_media_changed(struct cdrom_device_info *); -extern int register_cdrom(struct cdrom_device_info *cdi); +extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi); extern void unregister_cdrom(struct cdrom_device_info *cdi); typedef struct { diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 058d895544c7..f9c226f9546a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -217,11 +217,20 @@ struct gendisk { #ifdef CONFIG_BLK_DEV_INTEGRITY struct kobject integrity_kobj; #endif /* CONFIG_BLK_DEV_INTEGRITY */ +#if IS_ENABLED(CONFIG_CDROM) + struct cdrom_device_info *cdi; +#endif int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; }; +#if IS_REACHABLE(CONFIG_CDROM) +#define disk_to_cdi(disk) ((disk)->cdi) +#else +#define disk_to_cdi(disk) NULL +#endif + static inline struct gendisk *part_to_disk(struct hd_struct *part) { if (likely(part)) { -- cgit v1.2.3 From 4c3cfcce45152309c2031b3b87bcf10e4f3899e1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:57:02 +0200 Subject: cdrom: factor out a cdrom_read_tocentry helper Factor out a version of the CDROMREADTOCENTRY ioctl handler that can be called directly from kernel space. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 4f74ce050253..008c4d79fa33 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -94,6 +94,9 @@ struct cdrom_device_ops { struct packet_command *); }; +int cdrom_read_tocentry(struct cdrom_device_info *cdi, + struct cdrom_tocentry *entry); + /* the general block_device operations structure: */ extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t mode); -- cgit v1.2.3 From eaf8e3e4b54a8b778257fc3921ad8f793c941882 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:57:03 +0200 Subject: cdrom: factor out a cdrom_multisession helper Factor out a version of the CDROMMULTISESSION ioctl handler that can be called directly from kernel space. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 008c4d79fa33..8543fa59da72 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -94,6 +94,8 @@ struct cdrom_device_ops { struct packet_command *); }; +int cdrom_multisession(struct cdrom_device_info *cdi, + struct cdrom_multisession *info); int cdrom_read_tocentry(struct cdrom_device_info *cdi, struct cdrom_tocentry *entry); -- cgit v1.2.3 From 9d82973e032e246ff5663c9805fbb5407ae932e3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 4 May 2020 09:16:37 -0700 Subject: gcc-10 warnings: fix low-hanging fruit Due to a bug-report that was compiler-dependent, I updated one of my machines to gcc-10. That shows a lot of new warnings. Happily they seem to be mostly the valid kind, but it's going to cause a round of churn for getting rid of them.. This is the really low-hanging fruit of removing a couple of zero-sized arrays in some core code. We have had a round of these patches before, and we'll have many more coming, and there is nothing special about these except that they were particularly trivial, and triggered more warnings than most. Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- include/linux/tty.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..45cc10cdf6dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -983,7 +983,7 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[0]; + unsigned char f_handle[]; }; static inline struct file *get_file(struct file *f) diff --git a/include/linux/tty.h b/include/linux/tty.h index bd5fe0e907e8..a99e9b8e4e31 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -66,7 +66,7 @@ struct tty_buffer { int read; int flags; /* Data points here */ - unsigned long data[0]; + unsigned long data[]; }; /* Values for .flags field of tty_buffer */ -- cgit v1.2.3 From b86cd700edd3bfe27f631649727b7796067bb3fd Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 4 May 2020 19:27:00 +0200 Subject: net: add helper eth_hw_addr_crc Several drivers use the same code as basis for filter hashes. Therefore let's factor it out to a helper. This way drivers don't have to access struct netdev_hw_addr internals. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 8801f1f986e5..2e5debc0373c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -265,6 +266,17 @@ static inline void eth_hw_addr_random(struct net_device *dev) eth_random_addr(dev->dev_addr); } +/** + * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr + * @ha: pointer to hardware address + * + * Calculate CRC from a hardware address as basis for filter hashes. + */ +static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) +{ + return ether_crc(ETH_ALEN, ha->addr); +} + /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination -- cgit v1.2.3 From 1a33e10e4a95cb109ff1145098175df3113313ef Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 2 May 2020 22:22:19 -0700 Subject: net: partially revert dynamic lockdep key changes This patch reverts the folowing commits: commit 064ff66e2bef84f1153087612032b5b9eab005bd "bonding: add missing netdev_update_lockdep_key()" commit 53d374979ef147ab51f5d632dfe20b14aebeccd0 "net: avoid updating qdisc_xmit_lock_key in netdev_update_lockdep_key()" commit 1f26c0d3d24125992ab0026b0dab16c08df947c7 "net: fix kernel-doc warning in " commit ab92d68fc22f9afab480153bd82a20f6e2533769 "net: core: add generic lockdep keys" but keeps the addr_list_lock_key because we still lock addr_list_lock nestedly on stack devices, unlikely xmit_lock this is safe because we don't take addr_list_lock on any fast path. Reported-and-tested-by: syzbot+aaa6fa4949cc5d9b7b25@syzkaller.appspotmail.com Cc: Dmitry Vyukov Cc: Taehee Yoo Signed-off-by: Cong Wang Acked-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5a8d40f1ffe2..7725efd6e48a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1805,13 +1805,11 @@ enum netdev_priv_flags { * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. - * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock - * spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount - * @qdisc_xmit_lock_key: lockdep class annotating - * netdev_queue->_xmit_lock spinlock + * * @addr_list_lock_key: lockdep class annotating * net_device->addr_list_lock spinlock + * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock + * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -2112,10 +2110,9 @@ struct net_device { #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; - struct lock_class_key qdisc_tx_busylock_key; - struct lock_class_key qdisc_running_key; - struct lock_class_key qdisc_xmit_lock_key; struct lock_class_key addr_list_lock_key; + struct lock_class_key *qdisc_tx_busylock; + struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; @@ -2200,6 +2197,20 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } +#define netdev_lockdep_set_classes(dev) \ +{ \ + static struct lock_class_key qdisc_tx_busylock_key; \ + static struct lock_class_key qdisc_running_key; \ + static struct lock_class_key qdisc_xmit_lock_key; \ + unsigned int i; \ + \ + (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ + (dev)->qdisc_running_key = &qdisc_running_key; \ + for (i = 0; i < (dev)->num_tx_queues; i++) \ + lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ + &qdisc_xmit_lock_key); \ +} + u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, -- cgit v1.2.3 From d26c0cc53950464a24adfa76867f1d71f0cbbea6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 30 Apr 2020 23:30:47 +0200 Subject: bpf: Avoid gcc-10 stringop-overflow warning in struct bpf_prog gcc-10 warns about accesses to zero-length arrays: kernel/bpf/core.c: In function 'bpf_patch_insn_single': cc1: warning: writing 8 bytes into a region of size 0 [-Wstringop-overflow=] In file included from kernel/bpf/core.c:21: include/linux/filter.h:550:20: note: at offset 0 to object 'insnsi' with size 0 declared here 550 | struct bpf_insn insnsi[0]; | ^~~~~~ In this case, we really want to have two flexible-array members, but that is not possible. Removing the union to make insnsi a flexible-array member while leaving insns as a zero-length array fixes the warning, as nothing writes to the other one in that way. This trick only works on linux-3.18 or higher, as older versions had additional members in the union. Fixes: 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") Signed-off-by: Arnd Bergmann Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200430213101.135134-6-arnd@arndb.de --- include/linux/filter.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index af37318bb1c5..73d06a39e2d6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -545,10 +545,8 @@ struct bpf_prog { unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); /* Instructions for interpreter */ - union { - struct sock_filter insns[0]; - struct bpf_insn insnsi[0]; - }; + struct sock_filter insns[0]; + struct bpf_insn insnsi[]; }; struct sk_filter { -- cgit v1.2.3 From d8e81bc3e87c9e7994f5bf24e215a607899ca470 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 15 Apr 2020 16:45:16 +0200 Subject: docs: dt: convert usage-model.txt to ReST - Add a SPDX header; - Adjust document title; - Use footnoote markups; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add it to devicetree/index.rst. Signed-off-by: Mauro Carvalho Chehab Acked-by: Lee Jones Signed-off-by: Rob Herring --- include/linux/mfd/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index d01d1299e49d..21718c8b2b48 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -74,7 +74,7 @@ struct mfd_cell { /* * Device Tree compatible string - * See: Documentation/devicetree/usage-model.txt Chapter 2.2 for details + * See: Documentation/devicetree/usage-model.rst Chapter 2.2 for details */ const char *of_compatible; -- cgit v1.2.3 From 17309a6a43561bd7f4d4b51d7987225eb2b13d05 Mon Sep 17 00:00:00 2001 From: Tao Ren Date: Sun, 15 Mar 2020 12:16:28 -0700 Subject: usb: gadget: add "usb_validate_langid" function The USB LANGID validation code in "check_user_usb_string" function is moved to "usb_validate_langid" function which can be used by other usb gadget drivers. Signed-off-by: Tao Ren Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 9411c08a5c7e..e959c09a97c9 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -773,6 +773,9 @@ struct usb_gadget_string_container { /* put descriptor for string with that id into buf (buflen >= 256) */ int usb_gadget_get_string(const struct usb_gadget_strings *table, int id, u8 *buf); +/* check if the given language identifier is valid */ +bool usb_validate_langid(u16 langid); + /*-------------------------------------------------------------------------*/ /* utility to simplify managing config descriptors */ -- cgit v1.2.3 From 4cbf38511a007867def958872203ae8adb8e2351 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Prakhya Date: Wed, 29 Apr 2020 15:36:40 +0200 Subject: iommu: Add def_domain_type() callback in iommu_ops Some devices are reqired to use a specific type (identity or dma) of default domain when they are used with a vendor iommu. When the system level default domain type is different from it, the vendor iommu driver has to request a new default domain with iommu_request_dma_domain_for_dev() and iommu_request_dm_for_dev() in the add_dev() callback. Unfortunately, these two helpers only work when the group hasn't been assigned to any other devices, hence, some vendor iommu driver has to use a private domain if it fails to request a new default one. This adds def_domain_type() callback in the iommu_ops, so that any special requirement of default domain for a device could be aware by the iommu generic layer. Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Lu Baolu [ jroedel@suse.de: Added iommu_get_def_domain_type() function and use it to allocate the default domain ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-3-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7ef8b0bda695..1f027b07e499 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -248,6 +248,10 @@ struct iommu_iotlb_gather { * @cache_invalidate: invalidate translation caches * @sva_bind_gpasid: bind guest pasid and mm * @sva_unbind_gpasid: unbind guest pasid and mm + * @def_domain_type: device default domain type, return value: + * - IOMMU_DOMAIN_IDENTITY: must use an identity domain + * - IOMMU_DOMAIN_DMA: must use a dma domain + * - 0: use the default setting * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops */ @@ -318,6 +322,8 @@ struct iommu_ops { int (*sva_unbind_gpasid)(struct device *dev, int pasid); + int (*def_domain_type)(struct device *dev); + unsigned long pgsize_bitmap; struct module *owner; }; -- cgit v1.2.3 From a6a4c7e2c5b8b981d1c546a393ff21f2112468c3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:36:45 +0200 Subject: iommu: Add probe_device() and release_device() call-backs Add call-backs to 'struct iommu_ops' as an alternative to the add_device() and remove_device() call-backs, which will be removed when all drivers are converted. The new call-backs will not setup IOMMU groups and domains anymore, so also add a probe_finalize() call-back where the IOMMU driver can do per-device setup work which require the device to be set up with a group and a domain. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-8-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 1f027b07e499..30170d191e5e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -225,6 +225,10 @@ struct iommu_iotlb_gather { * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping + * @probe_device: Add device to iommu driver handling + * @release_device: Remove device from iommu driver handling + * @probe_finalize: Do final setup work after the device is added to an IOMMU + * group and attached to the groups domain * @device_group: find iommu group for a particular device * @domain_get_attr: Query domain attributes * @domain_set_attr: Change domain attributes @@ -275,6 +279,9 @@ struct iommu_ops { phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); void (*remove_device)(struct device *dev); + struct iommu_device *(*probe_device)(struct device *dev); + void (*release_device)(struct device *dev); + void (*probe_finalize)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); int (*domain_get_attr)(struct iommu_domain *domain, enum iommu_attr attr, void *data); @@ -375,6 +382,7 @@ struct iommu_fault_param { * * @fault_param: IOMMU detected device fault reporting data * @fwspec: IOMMU fwspec data + * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data * * TODO: migrate other per device data pointers under iommu_dev_data, e.g. @@ -384,6 +392,7 @@ struct dev_iommu { struct mutex lock; struct iommu_fault_param *fault_param; struct iommu_fwspec *fwspec; + struct iommu_device *iommu_dev; void *priv; }; -- cgit v1.2.3 From 5012c3968537e2ffecbdb2eba3479bf9fb9e5597 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:36:51 +0200 Subject: iommu: Export bus_iommu_probe() and make is safe for re-probing Add a check to the bus_iommu_probe() call-path to make sure it ignores devices which have already been successfully probed. Then export the bus_iommu_probe() function so it can be used by IOMMU drivers. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-14-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 30170d191e5e..fea1622408ad 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -445,6 +445,7 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) #define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); +extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); -- cgit v1.2.3 From 3eeeb45c6d0444b368cdeba9bdafa8bbcf5370d1 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:37:10 +0200 Subject: iommu: Remove add_device()/remove_device() code-paths All drivers are converted to use the probe/release_device() call-backs, so the add_device/remove_device() pointers are unused and the code using them can be removed. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-33-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index fea1622408ad..dd076366383f 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -223,8 +223,6 @@ struct iommu_iotlb_gather { * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue * @iova_to_phys: translate iova to physical address - * @add_device: add device to iommu grouping - * @remove_device: remove device from iommu grouping * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU @@ -277,8 +275,6 @@ struct iommu_ops { void (*iotlb_sync)(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); - int (*add_device)(struct device *dev); - void (*remove_device)(struct device *dev); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); -- cgit v1.2.3 From 1b032ec1ecbce6047af7d11c9db432e237cb17d8 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:37:12 +0200 Subject: iommu: Unexport iommu_group_get_for_dev() The function is now only used in IOMMU core code and shouldn't be used outside of it anyway, so remove the export for it. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-35-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index dd076366383f..7cfd2dddb49d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -527,7 +527,6 @@ extern int iommu_page_response(struct device *dev, struct iommu_page_response *msg); extern int iommu_group_id(struct iommu_group *group); -extern struct iommu_group *iommu_group_get_for_dev(struct device *dev); extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, -- cgit v1.2.3 From 2f5a55c52c00fcded796db5f961057ba3fec8910 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 2 May 2020 14:18:35 +0200 Subject: i2c: use my kernel.org address from now on The old email is still active, but for easier handling, I am going to use my kernel.org address from now on. Also, add a mailmap for the now defunct Pengutronix address. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 45d36ba4826b..49d29054e657 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -2,7 +2,7 @@ /* * i2c.h - definitions for the Linux i2c bus interface * Copyright (C) 1995-2000 Simon G. Vogl - * Copyright (C) 2013-2019 Wolfram Sang + * Copyright (C) 2013-2019 Wolfram Sang * * With some changes from Kyösti Mälkki and * Frodo Looijaard -- cgit v1.2.3 From 115f32512f13c0280161908e9de45a97a87673bb Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 1 May 2020 00:35:50 +0530 Subject: bus: mhi: Fix parsing of mhi_flags With the current parsing of mhi_flags, the following statement always return false: eob = !!(flags & MHI_EOB); This is due to the fact that 'enum mhi_flags' starts with index 0 and we are using direct AND operation to extract each bit. Fix this by using BIT() macros for defining the flags so that the reset of the code need not be touched. Fixes: 189ff97cca53 ("bus: mhi: core: Add support for data transfer") Reported-by: Dan Carpenter Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200430190555.32741-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index ad1996001965..5642806360f3 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -53,9 +53,9 @@ enum mhi_callback { * @MHI_CHAIN: Linked transfer */ enum mhi_flags { - MHI_EOB, - MHI_EOT, - MHI_CHAIN, + MHI_EOB = BIT(0), + MHI_EOT = BIT(1), + MHI_CHAIN = BIT(2), }; /** -- cgit v1.2.3 From 85a087df4a719ebab940efa3c79625e68161f57b Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Fri, 1 May 2020 00:35:52 +0530 Subject: bus: mhi: core: Remove link_status() callback If the MHI core detects invalid data due to a PCI read, it calls into the controller via link_status() to double check that the link is infact down. All in all, this is pretty pointless, and racy. There are no good reasons for this, and only drawbacks. Its pointless because chances are, the controller is going to do the same thing to determine if the link is down - attempt a PCI access and compare the result. This does not make the link status decision any smarter. Its racy because its possible that the link was down at the time of the MHI core access, but then recovered before the controller access. In this case, the controller will indicate the link is not down, and the MHI core will precede to use a bad value as the MHI core does not attempt to retry the access. Retrying the access in the MHI core is a bad idea because again, it is racy - what if the link is down again? Furthermore, there may be some higher level state associated with the link status, that is now invalid because the link went down. The only reason why the MHI core could see "invalid" data when doing a PCI access, that is actually valid, is if the register actually contained the PCI spec defined sentinel for an invalid access. In this case, it is arguable that the MHI implementation broken, and should be fixed, not worked around. Therefore, remove the link_status() callback before anyone attempts to implement it. Signed-off-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Reviewed-by: Hemant Kumar Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200430190555.32741-4-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 5642806360f3..c80ba559face 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -335,7 +335,6 @@ struct mhi_controller_config { * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) - * @link_status: CB function to query link status of the device (required) * @wake_get: CB function to assert device wake (optional) * @wake_put: CB function to de-assert device wake (optional) * @wake_toggle: CB function to assert and de-assert device wake (optional) @@ -417,7 +416,6 @@ struct mhi_controller { void (*status_cb)(struct mhi_controller *mhi_cntrl, enum mhi_callback cb); - int (*link_status)(struct mhi_controller *mhi_cntrl); void (*wake_get)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_put)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_toggle)(struct mhi_controller *mhi_cntrl); -- cgit v1.2.3 From 45723a44845c90c8e859fd0e2b0bb492322b5d0b Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Fri, 1 May 2020 00:35:53 +0530 Subject: bus: mhi: core: Offload register accesses to the controller When reading or writing MHI registers, the core assumes that the physical link is a memory mapped PCI link. This assumption may not hold for all MHI devices. The controller knows what is the physical link (ie PCI, I2C, SPI, etc), and therefore knows the proper methods to access that link. The controller can also handle link specific error scenarios, such as reading -1 when the PCI link went down. Therefore, it is appropriate that the MHI core requests the controller to make register accesses on behalf of the core, which abstracts the core from link specifics, and end up removing an unnecessary assumption. Signed-off-by: Jeffrey Hugo Reviewed-by: Hemant Kumar Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200430190555.32741-5-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index c80ba559face..84a6c9e72f52 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -342,6 +342,8 @@ struct mhi_controller_config { * @runtimet_put: CB function to decrement pm usage (required) * @map_single: CB function to create TRE buffer * @unmap_single: CB function to destroy TRE buffer + * @read_reg: Read a MHI register via the physical link (required) + * @write_reg: Write a MHI register via the physical link (required) * @buffer_len: Bounce buffer length * @bounce_buf: Use of bounce buffer * @fbc_download: MHI host needs to do complete image transfer (optional) @@ -425,6 +427,10 @@ struct mhi_controller { struct mhi_buf_info *buf); void (*unmap_single)(struct mhi_controller *mhi_cntrl, struct mhi_buf_info *buf); + int (*read_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 *out); + void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 val); size_t buffer_len; bool bounce_buf; -- cgit v1.2.3 From af2e58818082ac0db29539444ca17eb1e77f6000 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Fri, 1 May 2020 00:35:54 +0530 Subject: bus: mhi: core: Fix typo in comment There is a typo - "runtimet" should be "runtime". Fix it. Signed-off-by: Jeffrey Hugo Reviewed-by: Hemant Kumar Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200430190555.32741-6-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 84a6c9e72f52..3d7c3c26eeb9 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -339,7 +339,7 @@ struct mhi_controller_config { * @wake_put: CB function to de-assert device wake (optional) * @wake_toggle: CB function to assert and de-assert device wake (optional) * @runtime_get: CB function to controller runtime resume (required) - * @runtimet_put: CB function to decrement pm usage (required) + * @runtime_put: CB function to decrement pm usage (required) * @map_single: CB function to create TRE buffer * @unmap_single: CB function to destroy TRE buffer * @read_reg: Read a MHI register via the physical link (required) -- cgit v1.2.3 From efc930fa1d844869eb65586f8cdd6a7837db3607 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:16:55 +0200 Subject: docs: filesystems: caching/netfs-api.txt: convert it to ReST - Add a SPDX header; - Adjust document and section titles; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add it to filesystems/caching/index.rst. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/cfe4cb1bf8e1f0093d44c30801ec42e74721e543.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/fscache.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index ad044c0cb1f3..a1c928fe98e7 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -6,7 +6,7 @@ * * NOTE!!! See: * - * Documentation/filesystems/caching/netfs-api.txt + * Documentation/filesystems/caching/netfs-api.rst * * for a description of the network filesystem interface declared here. */ @@ -233,7 +233,7 @@ extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_ * * Register a filesystem as desiring caching services if they're available. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -253,7 +253,7 @@ int fscache_register_netfs(struct fscache_netfs *netfs) * Indicate that a filesystem no longer desires caching services for the * moment. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -270,7 +270,7 @@ void fscache_unregister_netfs(struct fscache_netfs *netfs) * Acquire a specific cache referral tag that can be used to select a specific * cache in which to cache an index. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -288,7 +288,7 @@ struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) * * Release a reference to a cache referral tag previously looked up. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -315,7 +315,7 @@ void fscache_release_cache_tag(struct fscache_cache_tag *tag) * that can be used to locate files. This is done by requesting a cookie for * each index in the path to the file. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -351,7 +351,7 @@ struct fscache_cookie *fscache_acquire_cookie( * provided to update the auxiliary data in the cache before the object is * disconnected. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -394,7 +394,7 @@ int fscache_check_consistency(struct fscache_cookie *cookie, * cookie. The auxiliary data on the cookie will be updated first if @aux_data * is set. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -410,7 +410,7 @@ void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) * * Permit data-storage cache objects to be pinned in the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -425,7 +425,7 @@ int fscache_pin_cookie(struct fscache_cookie *cookie) * * Permit data-storage cache objects to be unpinned from the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -441,7 +441,7 @@ void fscache_unpin_cookie(struct fscache_cookie *cookie) * changed. This includes the data size. These attributes will be obtained * through the get_attr() cookie definition op. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -463,7 +463,7 @@ int fscache_attr_changed(struct fscache_cookie *cookie) * * This can be called with spinlocks held. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -479,7 +479,7 @@ void fscache_invalidate(struct fscache_cookie *cookie) * * Wait for the invalidation of an object to complete. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -498,7 +498,7 @@ void fscache_wait_on_invalidate(struct fscache_cookie *cookie) * cookie so that a write to that object within the space can always be * honoured. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -533,7 +533,7 @@ int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) * Else, if the page is unbacked, -ENODATA is returned and a block may have * been allocated in the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -582,7 +582,7 @@ int fscache_read_or_alloc_page(struct fscache_cookie *cookie, * regard to different pages, the return values are prioritised in that order. * Any pages submitted for reading are removed from the pages list. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -617,7 +617,7 @@ int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, * Else, a block will be allocated if one wasn't already, and 0 will be * returned * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -667,7 +667,7 @@ void fscache_readpages_cancel(struct fscache_cookie *cookie, * be cleared at the completion of the write to indicate the success or failure * of the operation. Note that the completion may happen before the return. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -693,7 +693,7 @@ int fscache_write_page(struct fscache_cookie *cookie, * Note that this cannot cancel any outstanding I/O operations between this * page and the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -711,7 +711,7 @@ void fscache_uncache_page(struct fscache_cookie *cookie, * * Ask the cache if a page is being written to the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -731,7 +731,7 @@ bool fscache_check_page_write(struct fscache_cookie *cookie, * Ask the cache to wake us up when a page is no longer being written to the * cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -- cgit v1.2.3 From 0e822145b564204cd5e9dd67a7fd37d4a7b8253b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:16:58 +0200 Subject: docs: filesystems: caching/backend-api.txt: convert it to ReST - Add a SPDX header; - Adjust document and section titles; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add table markups; - Add it to filesystems/caching/index.rst. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/5d0a61abaa87bfe913b9e2f321e74ef7af0f3dfc.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/fscache-cache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index d5ba431b5d63..ce0b5fbf239d 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -6,7 +6,7 @@ * * NOTE!!! See: * - * Documentation/filesystems/caching/backend-api.txt + * Documentation/filesystems/caching/backend-api.rst * * for a description of the cache backend interface declared here. */ @@ -454,7 +454,7 @@ static inline void fscache_object_lookup_error(struct fscache_object *object) * Set the maximum size an object is permitted to reach, implying the highest * byte that may be written. Intended to be called by the attr_changed() op. * - * See Documentation/filesystems/caching/backend-api.txt for a complete + * See Documentation/filesystems/caching/backend-api.rst for a complete * description. */ static inline -- cgit v1.2.3 From 791a17ee19736fc6d4e35c4bf9f8efd1001be77c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:17:09 +0200 Subject: docs: filesystems: convert mount_api.txt to ReST - Add a SPDX header; - Adjust document and section titles; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add table markups; - Add lists markups; - Add it to filesystems/index.rst. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/32332c1659a28c22561cb5e64162c959856066b4.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/fs_context.h | 2 +- include/linux/lsm_hooks.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index e6c3e4c61dad..5f24fcbfbfb4 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -85,7 +85,7 @@ struct p_log { * Superblock creation fills in ->root whereas reconfiguration begins with this * already set. * - * See Documentation/filesystems/mount_api.txt + * See Documentation/filesystems/mount_api.rst */ struct fs_context { const struct fs_context_operations *ops; diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..44d5422c18e4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -77,7 +77,7 @@ * state. This is called immediately after commit_creds(). * * Security hooks for mount using fs_context. - * [See also Documentation/filesystems/mount_api.txt] + * [See also Documentation/filesystems/mount_api.rst] * * @fs_context_dup: * Allocate and attach a security structure to sc->security. This pointer -- cgit v1.2.3 From 982649915d626bba8753c04e994e5a6650523c64 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:17:21 +0200 Subject: docs: filesystems: convert configfs.txt to ReST - Add a SPDX header; - Adjust document and section titles; - Use copyright symbol; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add it to filesystems/index.rst. Also, as this file is alone on its own dir, and it doesn't seem too likely that other documents will follow it, let's move it to the filesystems/ root documentation dir. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/c2424ec2ad4d735751434ff7f52144c44aa02d5a.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/configfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index fa9490a8874c..2e8c69b43c64 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -13,7 +13,7 @@ * * configfs Copyright (C) 2005 Oracle. All rights reserved. * - * Please read Documentation/filesystems/configfs/configfs.txt before using + * Please read Documentation/filesystems/configfs.rst before using * the configfs interface, ESPECIALLY the parts about reference counts and * item destructors. */ -- cgit v1.2.3 From 9b06fc39084e161da84a399b6b5dc524e673f51e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Apr 2020 15:58:10 -0500 Subject: ARM: vexpress: Move vexpress_flags_set() into arch code vexpress_flags_set() is only used by the platform SMP related code and has nothing to do with the vexpress-sysreg MFD driver other than both access the same h/w block. It's also only needed for 32-bit systems and must be built-in for them. Let's move vexpress_flags_set() closer to where it is being used. This will allow for vexpress-sysreg to be built as a module. Cc: Lorenzo Pieralisi Cc: Linus Walleij Reviewed-by: Sudeep Holla Acked-by: Arnd Bergmann Acked-by: Liviu Dudau Acked-by: Lee Jones Signed-off-by: Rob Herring --- include/linux/vexpress.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index 0e130b5077a5..2ec7992b054c 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -40,8 +40,4 @@ struct device *vexpress_config_bridge_register(struct device *parent, struct regmap *devm_regmap_init_vexpress_config(struct device *dev); -/* Platform control */ - -void vexpress_flags_set(u32 data); - #endif -- cgit v1.2.3 From c3b3f52476412a3899f2c65b220075aceb18dd2c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 May 2020 12:12:53 +0200 Subject: signal: refactor copy_siginfo_to_user32 Factor out a copy_siginfo_to_external32 helper from copy_siginfo_to_user32 that fills out the compat_siginfo, but does so on a kernel space data structure. With that we can let architectures override copy_siginfo_to_user32 with their own implementations using copy_siginfo_to_external32. That allows moving the x32 SIGCHLD purely to x86 architecture code. As a nice side effect copy_siginfo_to_external32 also comes in handy for avoiding a set_fs() call in the coredump code later on. Contains improvements from Eric W. Biederman and Arnd Bergmann . Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 0480ba4db592..e90100c0de72 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -402,8 +402,15 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); -int copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo __user *from); -int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); +void copy_siginfo_to_external32(struct compat_siginfo *to, + const struct kernel_siginfo *from); +int copy_siginfo_from_user32(kernel_siginfo_t *to, + const struct compat_siginfo __user *from); +int __copy_siginfo_to_user32(struct compat_siginfo __user *to, + const kernel_siginfo_t *from); +#ifndef copy_siginfo_to_user32 +#define copy_siginfo_to_user32 __copy_siginfo_to_user32 +#endif int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -- cgit v1.2.3 From fa4751f454e6b51ef93babfd8b6c8b43a65c9db2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 5 May 2020 12:12:54 +0200 Subject: binfmt_elf: remove the set_fs in fill_siginfo_note The code in binfmt_elf.c is differnt from the rest of the code that processes siginfo, as it sends siginfo from a kernel buffer to a file rather than from kernel memory to userspace buffers. To remove it's use of set_fs the code needs some different siginfo helpers. Add the helper copy_siginfo_to_external to copy from the kernel's internal siginfo layout to a buffer in the siginfo layout that userspace expects. Modify fill_siginfo_note to use copy_siginfo_to_external instead of set_fs and copy_siginfo_to_user. Update compat_binfmt_elf.c to use the previously added copy_siginfo_to_external32 to handle the compat case. Signed-off-by: "Eric W. Biederman" Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/signal.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 05bacd2ab135..6bb1a3f0258c 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -24,6 +24,14 @@ static inline void clear_siginfo(kernel_siginfo_t *info) #define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) +static inline void copy_siginfo_to_external(siginfo_t *to, + const kernel_siginfo_t *from) +{ + memcpy(to, from, sizeof(*from)); + memset(((char *)to) + sizeof(struct kernel_siginfo), 0, + SI_EXPANSION_SIZE); +} + int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); -- cgit v1.2.3 From 81aabbb9fb7b4b1efd073b62f0505d3adad442f3 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 4 May 2020 10:21:44 -0700 Subject: bpf, sockmap: bpf_tcp_ingress needs to subtract bytes from sg.size In bpf_tcp_ingress we used apply_bytes to subtract bytes from sg.size which is used to track total bytes in a message. But this is not correct because apply_bytes is itself modified in the main loop doing the mem_charge. Then at the end of this we have sg.size incorrectly set and out of sync with actual sk values. Then we can get a splat if we try to cork the data later and again try to redirect the msg to ingress. To fix instead of trying to track msg.size do the easy thing and include it as part of the sk_msg_xfer logic so that when the msg is moved the sg.size is always correct. To reproduce the below users will need ingress + cork and hit an error path that will then try to 'free' the skmsg. [ 173.699981] BUG: KASAN: null-ptr-deref in sk_msg_free_elem+0xdd/0x120 [ 173.699987] Read of size 8 at addr 0000000000000008 by task test_sockmap/5317 [ 173.700000] CPU: 2 PID: 5317 Comm: test_sockmap Tainted: G I 5.7.0-rc1+ #43 [ 173.700005] Hardware name: Dell Inc. Precision 5820 Tower/002KVM, BIOS 1.9.2 01/24/2019 [ 173.700009] Call Trace: [ 173.700021] dump_stack+0x8e/0xcb [ 173.700029] ? sk_msg_free_elem+0xdd/0x120 [ 173.700034] ? sk_msg_free_elem+0xdd/0x120 [ 173.700042] __kasan_report+0x102/0x15f [ 173.700052] ? sk_msg_free_elem+0xdd/0x120 [ 173.700060] kasan_report+0x32/0x50 [ 173.700070] sk_msg_free_elem+0xdd/0x120 [ 173.700080] __sk_msg_free+0x87/0x150 [ 173.700094] tcp_bpf_send_verdict+0x179/0x4f0 [ 173.700109] tcp_bpf_sendpage+0x3ce/0x5d0 Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/158861290407.14306.5327773422227552482.stgit@john-Precision-5820-Tower --- 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 8a709f63c5e5..ad31c9fb7158 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -187,6 +187,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; + src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } -- cgit v1.2.3 From 18f423748b986c00216b6574c931d3d7581b393f Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 5 May 2020 17:11:02 -0700 Subject: Input: lm8333 - update contact email The 'pengutronix' address is defunct for years. Use the proper contact address. Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20200502142639.18925-1-wsa@kernel.org Signed-off-by: Dmitry Torokhov --- include/linux/input/lm8333.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/input/lm8333.h b/include/linux/input/lm8333.h index 79f918c6e8c5..906da5fc06e0 100644 --- a/include/linux/input/lm8333.h +++ b/include/linux/input/lm8333.h @@ -1,6 +1,6 @@ /* * public include for LM8333 keypad driver - same license as driver - * Copyright (C) 2012 Wolfram Sang, Pengutronix + * Copyright (C) 2012 Wolfram Sang, Pengutronix */ #ifndef _LM8333_H -- cgit v1.2.3 From d755cdb1b9d7e1b645e176b97eb137194bbe8cf9 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Thu, 23 Jan 2020 14:00:26 +0800 Subject: usb: chipidea: introduce CI_HDRC_CONTROLLER_VBUS_EVENT glue layer use Some vendors glue layer need to handle some events for vbus, eg, some i.mx platforms (imx7d, imx8mm, imx8mn, etc) needs vbus event to handle charger detection, its charger detection is finished at glue layer code, but not at USB PHY driver. Signed-off-by: Peter Chen --- include/linux/usb/chipidea.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index edd89b7c8f18..54167a2d28ea 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -67,6 +67,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 #define CI_HDRC_IMX_HSIC_ACTIVE_EVENT 2 #define CI_HDRC_IMX_HSIC_SUSPEND_EVENT 3 +#define CI_HDRC_CONTROLLER_VBUS_EVENT 4 int (*notify_event) (struct ci_hdrc *ci, unsigned event); struct regulator *reg_vbus; struct usb_otg_caps ci_otg_caps; -- cgit v1.2.3 From 57a29df341466b5cca43ba3d2d7064426727d7c3 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Sat, 25 Apr 2020 02:49:14 +0800 Subject: iopoll: Introduce read_poll_timeout_atomic macro Like read_poll_timeout, an atomic variant for multiple parameter read function can be useful. Will be used by a later patch. Signed-off-by: Kai-Heng Feng Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20200424184918.30360-1-kai.heng.feng@canonical.com --- include/linux/iopoll.h | 62 ++++++++++++++++++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index cb20c733b15a..bc89ac625f26 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -57,6 +57,48 @@ (cond) ? 0 : -ETIMEDOUT; \ }) +/** + * read_poll_timeout_atomic - Periodically poll an address until a condition is + * met or a timeout occurs + * @op: accessor function (takes @addr as its only argument) + * @addr: Address to poll + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @delay_us: Time to udelay between reads in us (0 tight-loops). Should + * be less than ~10us since udelay is used (see + * Documentation/timers/timers-howto.rst). + * @timeout_us: Timeout in us, 0 means never timeout + * @delay_before_read: if it is true, delay @delay_us before read. + * + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + */ +#define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ + delay_before_read, args...) \ +({ \ + u64 __timeout_us = (timeout_us); \ + unsigned long __delay_us = (delay_us); \ + ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ + if (delay_before_read && __delay_us) \ + udelay(__delay_us); \ + for (;;) { \ + (val) = op(args); \ + if (cond) \ + break; \ + if (__timeout_us && \ + ktime_compare(ktime_get(), __timeout) > 0) { \ + (val) = op(args); \ + break; \ + } \ + if (__delay_us) \ + udelay(__delay_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + /** * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs * @op: accessor function (takes @addr as its only argument) @@ -96,25 +138,7 @@ * macros defined below rather than this macro directly. */ #define readx_poll_timeout_atomic(op, 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); \ - for (;;) { \ - (val) = op(addr); \ - if (cond) \ - break; \ - if (__timeout_us && \ - ktime_compare(ktime_get(), __timeout) > 0) { \ - (val) = op(addr); \ - break; \ - } \ - if (__delay_us) \ - udelay(__delay_us); \ - } \ - (cond) ? 0 : -ETIMEDOUT; \ -}) - + read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, false, addr) #define readb_poll_timeout(addr, val, cond, delay_us, timeout_us) \ readx_poll_timeout(readb, addr, val, cond, delay_us, timeout_us) -- cgit v1.2.3 From b720aaa347f227c416e8aed2f12ca62ea4f1cd4e Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 25 Mar 2020 01:43:34 +0300 Subject: firmware: tf: Different way of L2 cache enabling after LP2 suspend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ASUS TF300T device may not work properly if firmware is asked to fully re-initialize L2 cache after resume from LP2 suspend. The downstream kernel of TF300T uses different opcode to enable cache after resuming from LP2, this opcode also works fine on Nexus 7 and Ouya devices. Supposedly, this may be needed by an older firmware versions. Reported-by: Michał Mirosław Tested-by: Michał Mirosław Tested-by: Jasper Korten Tested-by: David Heidelberg Tested-by: Peter Geis Signed-off-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/firmware/trusted_foundations.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/trusted_foundations.h b/include/linux/firmware/trusted_foundations.h index 2549a2db56aa..be5984bda592 100644 --- a/include/linux/firmware/trusted_foundations.h +++ b/include/linux/firmware/trusted_foundations.h @@ -32,6 +32,7 @@ #define TF_PM_MODE_LP1_NO_MC_CLK 2 #define TF_PM_MODE_LP2 3 #define TF_PM_MODE_LP2_NOFLUSH_L2 4 +#define TF_PM_MODE_NONE 5 struct trusted_foundations_platform_data { unsigned int version_major; -- cgit v1.2.3 From 6349084746ff4f5f7ebc748e4b2a890f8c57b129 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 6 May 2020 16:53:13 +0200 Subject: net: phy: add concept of shared storage for PHYs There are packages which contain multiple PHY devices, eg. a quad PHY transceiver. Provide functions to allocate and free shared storage. Usually, a quad PHY contains global registers, which don't belong to any PHY. Provide convenience functions to access these registers. Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 89 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e2bfb9240587..1d36ac608159 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -227,6 +228,28 @@ struct mdio_bus_stats { struct u64_stats_sync syncp; }; +/* Represents a shared structure between different phydev's in the same + * package, for example a quad PHY. See phy_package_join() and + * phy_package_leave(). + */ +struct phy_package_shared { + int addr; + refcount_t refcnt; + unsigned long flags; + size_t priv_size; + + /* private data pointer */ + /* note that this pointer is shared between different phydevs and + * the user has to take care of appropriate locking. It is allocated + * and freed automatically by phy_package_join() and + * phy_package_leave(). + */ + void *priv; +}; + +/* used as bit number in atomic bitops */ +#define PHY_SHARED_F_INIT_DONE 0 + /* * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure @@ -278,6 +301,12 @@ struct mii_bus { int reset_delay_us; /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; + + /* protect access to the shared element */ + struct mutex shared_lock; + + /* shared state across different PHYs */ + struct phy_package_shared *shared[PHY_MAX_ADDR]; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) @@ -478,6 +507,10 @@ struct phy_device { /* For use by PHYs to maintain extra state */ void *priv; + /* shared data pointer */ + /* For use by PHYs inside the same package that need a shared state. */ + struct phy_package_shared *shared; + /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; @@ -1354,6 +1387,10 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev, int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); +int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size); +void phy_package_leave(struct phy_device *phydev); +int devm_phy_package_join(struct device *dev, struct phy_device *phydev, + int addr, size_t priv_size); #if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); @@ -1406,6 +1443,58 @@ static inline int phy_ethtool_get_stats(struct phy_device *phydev, return 0; } +static inline int phy_package_read(struct phy_device *phydev, u32 regnum) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return mdiobus_read(phydev->mdio.bus, shared->addr, regnum); +} + +static inline int __phy_package_read(struct phy_device *phydev, u32 regnum) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum); +} + +static inline int phy_package_write(struct phy_device *phydev, + u32 regnum, u16 val) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); +} + +static inline int __phy_package_write(struct phy_device *phydev, + u32 regnum, u16 val) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); +} + +static inline bool phy_package_init_once(struct phy_device *phydev) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return false; + + return !test_and_set_bit(PHY_SHARED_F_INIT_DONE, &shared->flags); +} + extern struct bus_type mdio_bus_type; struct mdio_board_info { -- cgit v1.2.3 From c6af13d334759c33c14b6fad4c676c6d1dbf9564 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 1 May 2020 23:27:21 +0200 Subject: timer: add fsleep for flexible sleeping Sleeping for a certain amount of time requires use of different functions, depending on the time period. Documentation/timers/timers-howto.rst explains when to use which function, and also checkpatch checks for some potentially problematic cases. So let's create a helper that automatically chooses the appropriate sleep function -> fsleep(), for flexible sleeping If the delay is a constant, then the compiler should be able to ensure that the new helper doesn't create overhead. If the delay is not constant, then the new helper can save some code. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/delay.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delay.h b/include/linux/delay.h index 8e6828094c1e..5e016a4029d9 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -65,4 +65,15 @@ static inline void ssleep(unsigned int seconds) msleep(seconds * 1000); } +/* see Documentation/timers/timers-howto.rst for the thresholds */ +static inline void fsleep(unsigned long usecs) +{ + if (usecs <= 10) + udelay(usecs); + else if (usecs <= 20000) + usleep_range(usecs, 2 * usecs); + else + msleep(DIV_ROUND_UP(usecs, 1000)); +} + #endif /* defined(_LINUX_DELAY_H) */ -- cgit v1.2.3 From 9274124f023b5c56dc4326637d4f787968b03607 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 4 May 2020 12:48:54 -0400 Subject: net: stricter validation of untrusted gso packets Syzkaller again found a path to a kernel crash through bad gso input: a packet with transport header extending beyond skb_headlen(skb). Tighten validation at kernel entry: - Verify that the transport header lies within the linear section. To avoid pulling linux/tcp.h, verify just sizeof tcphdr. tcp_gso_segment will call pskb_may_pull (th->doff * 4) before use. - Match the gso_type against the ip_proto found by the flow dissector. Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.") Reported-by: syzbot Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 0d1fe9297ac6..6f6ade63b04c 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,6 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include +#include +#include #include static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, @@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, bool little_endian) { unsigned int gso_type = 0; + unsigned int thlen = 0; + unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; + ip_proto = IPPROTO_UDP; + thlen = sizeof(struct udphdr); break; default: return -EINVAL; @@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + + if (skb_transport_offset(skb) + thlen > skb_headlen(skb)) + return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { + struct flow_keys_basic keys; + if (!skb->protocol) virtio_net_hdr_set_proto(skb, hdr); retry: - skb_probe_transport_header(skb); - if (!skb_transport_header_was_set(skb)) { + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, + 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { @@ -75,6 +91,12 @@ retry: } return -EINVAL; } + + if (keys.control.thoff + thlen > skb_headlen(skb) || + keys.basic.ip_proto != ip_proto) + return -EINVAL; + + skb_set_transport_header(skb, keys.control.thoff); } } -- cgit v1.2.3 From bdbdac7649fac05f88c9f7ab18121a17fb591687 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 5 May 2020 08:35:05 +0200 Subject: ethtool: provide UAPI for PHY master/slave configuration. This UAPI is needed for BroadR-Reach 100BASE-T1 devices. Due to lack of auto-negotiation support, we needed to be able to configure the MASTER-SLAVE role of the port manually or from an application in user space. The same UAPI can be used for 1000BASE-T or MultiGBASE-T devices to force MASTER or SLAVE role. See IEEE 802.3-2018: 22.2.4.3.7 MASTER-SLAVE control register (Register 9) 22.2.4.3.8 MASTER-SLAVE status register (Register 10) 40.5.2 MASTER-SLAVE configuration resolution 45.2.1.185.1 MASTER-SLAVE config value (1.2100.14) 45.2.7.10 MultiGBASE-T AN control 1 register (Register 7.32) The MASTER-SLAVE role affects the clock configuration: ------------------------------------------------------------------------------- When the PHY is configured as MASTER, the PMA Transmit function shall source TX_TCLK from a local clock source. When configured as SLAVE, the PMA Transmit function shall source TX_TCLK from the clock recovered from data stream provided by MASTER. iMX6Q KSZ9031 XXX ------\ /-----------\ /------------\ | | | | | MAC |<----RGMII----->| PHY Slave |<------>| PHY Master | |<--- 125 MHz ---+-<------/ | | \ | ------/ \-----------/ \------------/ ^ \-TX_TCLK ------------------------------------------------------------------------------- Since some clock or link related issues are only reproducible in a specific MASTER-SLAVE-role, MAC and PHY configuration, it is beneficial to provide generic (not 100BASE-T1 specific) interface to the user space for configuration flexibility and trouble shooting. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1d36ac608159..a2b91b5f9d0a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -477,6 +477,9 @@ struct phy_device { int duplex; int pause; int asym_pause; + u8 master_slave_get; + u8 master_slave_set; + u8 master_slave_state; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ -- cgit v1.2.3 From b2f75a41eaa6bfc4aa6f6a1faefbf21c2c8d1588 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 9 Apr 2020 17:49:23 -0600 Subject: PCI: host-generic: Eliminate pci_host_common_probe wrappers Most ECAM host drivers are just different pci_ecam_ops which can be DT match table data. That's already the case in some cases, but let's do that for all the ECAM drivers. Then we can use of_device_get_match_data() in pci_host_common_probe() and eliminate the probe wrapper functions and use pci_host_common_probe() directly for probe. Link: https://lore.kernel.org/r/20200409234923.21598-4-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas Cc: Zhou Wang Cc: Lorenzo Pieralisi Cc: Andrew Murray Cc: Bjorn Helgaas Cc: Will Deacon Cc: Robert Richter Cc: Marc Gonzalez Cc: Mans Rullgard Cc: linux-pci@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org --- include/linux/pci-ecam.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index fd0edb8b8a00..1af5cb02ef7f 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -61,8 +61,7 @@ extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ #if IS_ENABLED(CONFIG_PCI_HOST_COMMON) /* for DT-based PCI controllers that support ECAM */ -int pci_host_common_probe(struct platform_device *pdev, - const struct pci_ecam_ops *ops); +int pci_host_common_probe(struct platform_device *pdev); int pci_host_common_remove(struct platform_device *pdev); #endif #endif -- cgit v1.2.3 From 565558558985b1d7cd43b21f18c1ad6b232788d0 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Thu, 30 Apr 2020 12:40:03 +0100 Subject: cpu/hotplug: Remove disable_nonboot_cpus() The single user could have called freeze_secondary_cpus() directly. Since this function was a source of confusion, remove it as it's just a pointless wrapper. While at it, rename enable_nonboot_cpus() to thaw_secondary_cpus() to preserve the naming symmetry. Done automatically via: git grep -l enable_nonboot_cpus | xargs sed -i 's/enable_nonboot_cpus/thaw_secondary_cpus/g' Signed-off-by: Qais Yousef Signed-off-by: Thomas Gleixner Cc: "Rafael J. Wysocki" Link: https://lkml.kernel.org/r/20200430114004.17477-1-qais.yousef@arm.com --- include/linux/cpu.h | 12 +++--------- include/linux/smp.h | 4 ++-- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index beaed2dc269e..9d34dc3b859f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -150,12 +150,7 @@ static inline int freeze_secondary_cpus(int primary) return __freeze_secondary_cpus(primary, true); } -static inline int disable_nonboot_cpus(void) -{ - return __freeze_secondary_cpus(0, false); -} - -void enable_nonboot_cpus(void); +extern void thaw_secondary_cpus(void); static inline int suspend_disable_secondary_cpus(void) { @@ -168,12 +163,11 @@ static inline int suspend_disable_secondary_cpus(void) } static inline void suspend_enable_secondary_cpus(void) { - return enable_nonboot_cpus(); + return thaw_secondary_cpus(); } #else /* !CONFIG_PM_SLEEP_SMP */ -static inline int disable_nonboot_cpus(void) { return 0; } -static inline void enable_nonboot_cpus(void) {} +static inline void thaw_secondary_cpus(void) {} static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ diff --git a/include/linux/smp.h b/include/linux/smp.h index cbc9162689d0..04019872c7bc 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -227,8 +227,8 @@ static inline int get_boot_cpu_id(void) */ extern void arch_disable_smp_support(void); -extern void arch_enable_nonboot_cpus_begin(void); -extern void arch_enable_nonboot_cpus_end(void); +extern void arch_thaw_secondary_cpus_begin(void); +extern void arch_thaw_secondary_cpus_end(void); void smp_setup_processor_id(void); -- cgit v1.2.3 From fb7fb84a0c4e8021ddecb157802d58241a3f1a40 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Thu, 30 Apr 2020 12:40:04 +0100 Subject: cpu/hotplug: Remove __freeze_secondary_cpus() The refactored function is no longer required as the codepaths that call freeze_secondary_cpus() are all suspend/resume related now. Signed-off-by: Qais Yousef Signed-off-by: Thomas Gleixner Cc: "Rafael J. Wysocki" Link: https://lkml.kernel.org/r/20200430114004.17477-2-qais.yousef@arm.com --- include/linux/cpu.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9d34dc3b859f..52692587f7fe 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -144,12 +144,7 @@ static inline void get_online_cpus(void) { cpus_read_lock(); } static inline void put_online_cpus(void) { cpus_read_unlock(); } #ifdef CONFIG_PM_SLEEP_SMP -int __freeze_secondary_cpus(int primary, bool suspend); -static inline int freeze_secondary_cpus(int primary) -{ - return __freeze_secondary_cpus(primary, true); -} - +extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); static inline int suspend_disable_secondary_cpus(void) -- cgit v1.2.3 From 3fec4aecb311995189217e64d725cfe84a568de3 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Wed, 6 May 2020 17:42:23 +0100 Subject: kgdb: Fix spurious true from in_dbg_master() Currently there is a small window where a badly timed migration could cause in_dbg_master() to spuriously return true. Specifically if we migrate to a new core after reading the processor id and the previous core takes a breakpoint then we will evaluate true if we read kgdb_active before we get the IPI to bring us to halt. Fix this by checking irqs_disabled() first. Interrupts are always disabled when we are executing the kgdb trap so this is an acceptable prerequisite. This also allows us to replace raw_smp_processor_id() with smp_processor_id() since the short circuit logic will prevent warnings from PREEMPT_DEBUG. Fixes: dcc7871128e9 ("kgdb: core changes to support kdb") Suggested-by: Will Deacon Link: https://lore.kernel.org/r/20200506164223.2875760-1-daniel.thompson@linaro.org Reviewed-by: Douglas Anderson Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index b072aeb1fd78..4d6fe87fd38f 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -323,7 +323,7 @@ extern void gdbstub_exit(int status); extern int kgdb_single_step; extern atomic_t kgdb_active; #define in_dbg_master() \ - (raw_smp_processor_id() == atomic_read(&kgdb_active)) + (irqs_disabled() && (smp_processor_id() == atomic_read(&kgdb_active))) extern bool dbg_is_early; extern void __init dbg_late_init(void); extern void kgdb_panic(const char *msg); -- cgit v1.2.3 From 1137a96f9b5a8615296bd319151896c859ead292 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 7 May 2020 19:06:49 +0800 Subject: kgdb: Return true in kgdb_nmi_poll_knock() Fix the following coccicheck warning: include/linux/kgdb.h:301:54-55: WARNING: return of 0/1 in function 'kgdb_nmi_poll_knock' with return type bool Signed-off-by: Jason Yan Link: https://lore.kernel.org/r/20200507110649.37426-1-yanaijie@huawei.com Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 4d6fe87fd38f..c2caee08e418 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -298,7 +298,7 @@ extern bool kgdb_nmi_poll_knock(void); #else static inline int kgdb_register_nmi_console(void) { return 0; } static inline int kgdb_unregister_nmi_console(void) { return 0; } -static inline bool kgdb_nmi_poll_knock(void) { return 1; } +static inline bool kgdb_nmi_poll_knock(void) { return true; } #endif extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); -- cgit v1.2.3 From eb7ae5e06bb6e6ac6bb86872d27c43ebab92f6b2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:47:54 +0200 Subject: bdi: move bdi_dev_name out of line bdi_dev_name is not a fast path function, move it out of line. This prepares for using it from modular callers without having to export an implementation detail like bdi_unknown_name. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Greg Kroah-Hartman Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f88197c1ffc2..c9ad5c3b7b4b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -505,13 +505,6 @@ 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); -} +const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ -- cgit v1.2.3 From 5d1f2e3c8090c0769ee4a1b920e82277613327fc Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 22 Apr 2020 17:37:34 -0700 Subject: soc: qcom: glink_ssr: Internalize ssr_notifiers Rather than carrying a special purpose blocking notifier for glink_ssr in remoteproc's qcom_common.c, move it into glink_ssr so allow wider reuse of the common one. The rpmsg glink header file is used in preparation for the next patch. Acked-by: Chris Lew Acked-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/20200423003736.2027371-3-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index 96e26d94719f..09daa0acde2c 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -26,4 +26,10 @@ static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} #endif +#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SSR) +void qcom_glink_ssr_notify(const char *ssr_name); +#else +static inline void qcom_glink_ssr_notify(const char *ssr_name) {} +#endif + #endif -- cgit v1.2.3 From 93bc3feee8bd5fbe29ad27779c5e7b369fd7c80b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 22 Apr 2020 17:37:35 -0700 Subject: rpmsg: glink: Integrate glink_ssr in qcom_glink In all but the very special case of a system with _only_ glink_rpm, GLINK is dependent on glink_ssr, so move it to rpmsg and combine it with qcom_glink_native in the new qcom_glink kernel module. Acked-by: Chris Lew Acked-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/20200423003736.2027371-4-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index 09daa0acde2c..daded9fddf36 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -12,6 +12,7 @@ struct qcom_glink; struct qcom_glink *qcom_glink_smem_register(struct device *parent, struct device_node *node); void qcom_glink_smem_unregister(struct qcom_glink *glink); +void qcom_glink_ssr_notify(const char *ssr_name); #else @@ -23,12 +24,6 @@ qcom_glink_smem_register(struct device *parent, } static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} - -#endif - -#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SSR) -void qcom_glink_ssr_notify(const char *ssr_name); -#else static inline void qcom_glink_ssr_notify(const char *ssr_name) {} #endif -- cgit v1.2.3 From 89826cce37542f7950e8f4b9258284805e98430c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Apr 2020 18:04:54 -0500 Subject: exec: Make unlocking exec_update_mutex explict With install_exec_creds updated to follow immediately after setup_new_exec, the failure of unshare_sighand is the only code path where exec_update_mutex is held but not explicitly unlocked. Update that code path to explicitly unlock exec_update_mutex. Remove the unlocking of exec_update_mutex from free_bprm. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index a345d9fed3d8..6f564b9ad882 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -47,8 +47,7 @@ struct linux_binprm { secureexec:1, /* * Set by flush_old_exec, when exec_mmap has been called. - * This is past the point of no return, when the - * exec_update_mutex has been taken. + * This is past the point of no return. */ called_exec_mmap:1; #ifdef __alpha__ -- cgit v1.2.3 From 1507b7a30ad284a2a136ee79c214c0e86c62da64 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Apr 2020 18:17:50 -0500 Subject: exec: Rename the flag called_exec_mmap point_of_no_return Update the comments and make the code easier to understand by renaming this flag. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 6f564b9ad882..8f479dad7931 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -46,10 +46,10 @@ struct linux_binprm { */ secureexec:1, /* - * Set by flush_old_exec, when exec_mmap has been called. - * This is past the point of no return. + * Set when errors can no longer be returned to the + * original userspace. */ - called_exec_mmap:1; + point_of_no_return:1; #ifdef __alpha__ unsigned int taso:1; #endif -- cgit v1.2.3 From 96ecee29b0b560662ec082ee9b6f2049f2a79090 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 3 May 2020 06:48:17 -0500 Subject: exec: Merge install_exec_creds into setup_new_exec The two functions are now always called one right after the other so merge them together to make future maintenance easier. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8f479dad7931..2a8fddf3574a 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -145,7 +145,6 @@ extern int transfer_args_to_stack(struct linux_binprm *bprm, extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); -extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); -- cgit v1.2.3 From 2388777a0a5957a10b3d78677216530a9b3bd09f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 3 May 2020 07:54:10 -0500 Subject: exec: Rename flush_old_exec begin_new_exec There is and has been for a very long time been a lot more going on in flush_old_exec than just flushing the old state. After the movement of code from setup_new_exec there is a whole lot more going on than just flushing the old executables state. Rename flush_old_exec to begin_new_exec to more accurately reflect what this function does. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 2a8fddf3574a..1b48e2154766 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -125,7 +125,7 @@ extern void unregister_binfmt(struct linux_binfmt *); extern int prepare_binprm(struct linux_binprm *); extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *); -extern int flush_old_exec(struct linux_binprm * bprm); +extern int begin_new_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); extern void finalize_exec(struct linux_binprm *bprm); extern void would_dump(struct linux_binprm *, struct file *); -- cgit v1.2.3 From 7c8e2bdd5f0d990e2398ee3deafc626dd469fc2d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 29 Apr 2020 10:24:44 -0500 Subject: livepatch: Apply vmlinux-specific KLP relocations early KLP relocations are livepatch-specific relocations which are applied to a KLP module's text or data. They exist for two reasons: 1) Unexported symbols: replacement functions often need to access unexported symbols (e.g. static functions), which "normal" relocations don't allow. 2) Late module patching: this is the ability for a KLP module to bypass normal module dependencies, such that the KLP module can be loaded *before* a to-be-patched module. This means that relocations which need to access symbols in the to-be-patched module might need to be applied to the KLP module well after it has been loaded. Non-late-patched KLP relocations are applied from the KLP module's init function. That usually works fine, unless the patched code wants to use alternatives, paravirt patching, jump tables, or some other special section which needs relocations. Then we run into ordering issues and crashes. In order for those special sections to work properly, the KLP relocations should be applied *before* the special section init code runs, such as apply_paravirt(), apply_alternatives(), or jump_label_apply_nops(). You might think the obvious solution would be to move the KLP relocation initialization earlier, but it's not necessarily that simple. The problem is the above-mentioned late module patching, for which KLP relocations can get applied well after the KLP module is loaded. To "fix" this issue in the past, we created .klp.arch sections: .klp.arch.{module}..altinstructions .klp.arch.{module}..parainstructions Those sections allow KLP late module patching code to call apply_paravirt() and apply_alternatives() after the module-specific KLP relocations (.klp.rela.{module}.{section}) have been applied. But that has a lot of drawbacks, including code complexity, the need for arch-specific code, and the (per-arch) danger that we missed some special section -- for example the __jump_table section which is used for jump labels. It turns out there's a simpler and more functional approach. There are two kinds of KLP relocation sections: 1) vmlinux-specific KLP relocation sections .klp.rela.vmlinux.{sec} These are relocations (applied to the KLP module) which reference unexported vmlinux symbols. 2) module-specific KLP relocation sections .klp.rela.{module}.{sec}: These are relocations (applied to the KLP module) which reference unexported or exported module symbols. Up until now, these have been treated the same. However, they're inherently different. Because of late module patching, module-specific KLP relocations can be applied very late, thus they can create the ordering headaches described above. But vmlinux-specific KLP relocations don't have that problem. There's nothing to prevent them from being applied earlier. So apply them at the same time as normal relocations, when the KLP module is being loaded. This means that for vmlinux-specific KLP relocations, we no longer have any ordering issues. vmlinux-referencing jump labels, alternatives, and paravirt patching will work automatically, without the need for the .klp.arch hacks. All that said, for module-specific KLP relocations, the ordering problems still exist and we *do* still need .klp.arch. Or do we? Stay tuned. Suggested-by: Peter Zijlstra Signed-off-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Acked-by: Joe Lawrence Acked-by: Miroslav Benes Acked-by: Jessica Yu Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index e894e74905f3..c4302e9a5905 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -234,6 +234,11 @@ void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor); struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id); struct klp_state *klp_get_prev_state(unsigned long id); +int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symindex, unsigned int secindex, + const char *objname); + #else /* !CONFIG_LIVEPATCH */ static inline int klp_module_coming(struct module *mod) { return 0; } @@ -242,6 +247,15 @@ static inline bool klp_patch_pending(struct task_struct *task) { return false; } static inline void klp_update_patch_state(struct task_struct *task) {} static inline void klp_copy_process(struct task_struct *child) {} +static inline +int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symindex, unsigned int secindex, + const char *objname) +{ + return 0; +} + #endif /* CONFIG_LIVEPATCH */ #endif /* _LINUX_LIVEPATCH_H_ */ -- cgit v1.2.3 From 1d05334d2899bd3ecdf01beb53f0a70884a7f471 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Apr 2020 10:24:45 -0500 Subject: livepatch: Remove .klp.arch After the previous patch, vmlinux-specific KLP relocations are now applied early during KLP module load. This means that .klp.arch sections are no longer needed for *vmlinux-specific* KLP relocations. One might think they're still needed for *module-specific* KLP relocations. If a to-be-patched module is loaded *after* its corresponding KLP module is loaded, any corresponding KLP relocations will be delayed until the to-be-patched module is loaded. If any special sections (.parainstructions, for example) rely on those relocations, their initializations (apply_paravirt) need to be done afterwards. Thus the apparent need for arch_klp_init_object_loaded() and its corresponding .klp.arch sections -- it allows some of the special section initializations to be done at a later time. But... if you look closer, that dependency between the special sections and the module-specific KLP relocations doesn't actually exist in reality. Looking at the contents of the .altinstructions and .parainstructions sections, there's not a realistic scenario in which a KLP module's .altinstructions or .parainstructions section needs to access a symbol in a to-be-patched module. It might need to access a local symbol or even a vmlinux symbol; but not another module's symbol. When a special section needs to reference a local or vmlinux symbol, a normal rela can be used instead of a KLP rela. Since the special section initializations don't actually have any real dependency on module-specific KLP relocations, .klp.arch and arch_klp_init_object_loaded() no longer have a reason to exist. So remove them. As Peter said much more succinctly: So the reason for .klp.arch was that .klp.rela.* stuff would overwrite paravirt instructions. If that happens you're doing it wrong. Those RELAs are core kernel, not module, and thus should've happened in .rela.* sections at patch-module loading time. Reverting this removes the two apply_{paravirt,alternatives}() calls from the late patching path, and means we don't have to worry about them when removing module_disable_ro(). [ jpoimboe: Rewrote patch description. Tweaked klp_init_object_loaded() error path. ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Acked-by: Joe Lawrence Acked-by: Miroslav Benes Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index c4302e9a5905..2614247a9781 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -195,9 +195,6 @@ struct klp_patch { int klp_enable_patch(struct klp_patch *); -void arch_klp_init_object_loaded(struct klp_patch *patch, - struct klp_object *obj); - /* Called from the module loader during module coming/going states */ int klp_module_coming(struct module *mod); void klp_module_going(struct module *mod); -- cgit v1.2.3 From 0d9fbf78fefb421a3af97394ce80bba0db4f046a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 29 Apr 2020 10:24:51 -0500 Subject: module: Remove module_disable_ro() module_disable_ro() has no more users. Remove it. Signed-off-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Acked-by: Joe Lawrence Acked-by: Miroslav Benes Acked-by: Jessica Yu Signed-off-by: Jiri Kosina --- include/linux/module.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1ad393e62bef..e4ef7b36feda 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -860,10 +860,8 @@ extern int module_sysfs_initialized; #ifdef CONFIG_STRICT_MODULE_RWX 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 module_enable_ro(const struct module *mod, bool after_init) { } -static inline void module_disable_ro(const struct module *mod) { } #endif #ifdef CONFIG_GENERIC_BUG -- cgit v1.2.3 From e6eff4376e2897c2e14b70d87bf7284cdb093830 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 29 Apr 2020 10:24:53 -0500 Subject: module: Make module_enable_ro() static again Now that module_enable_ro() has no more external users, make it static again. Suggested-by: Jessica Yu Signed-off-by: Josh Poimboeuf Acked-by: Jessica Yu Signed-off-by: Jiri Kosina --- include/linux/module.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index e4ef7b36feda..2c2e988bcf10 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -858,12 +858,6 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) -#ifdef CONFIG_STRICT_MODULE_RWX -extern void module_enable_ro(const struct module *mod, bool after_init); -#else -static inline void module_enable_ro(const struct module *mod, bool after_init) { } -#endif - #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); -- cgit v1.2.3 From 307f660d056b5eb8f5bb2328fac3915ab75b5007 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:18 -0700 Subject: netpoll: remove dev argument from netpoll_send_skb_on_dev() netpoll_send_skb_on_dev() can get the device pointer directly from np->dev Rename it to __netpoll_send_skb() Following patch will move netpoll_send_skb() out-of-line. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netpoll.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 676f1ff161a9..00e0bae3d402 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,13 +63,12 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, - struct net_device *dev); +void __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { unsigned long flags; local_irq_save(flags); - netpoll_send_skb_on_dev(np, skb, np->dev); + __netpoll_send_skb(np, skb); local_irq_restore(flags); } -- cgit v1.2.3 From fb1eee476b0d3be3e58dac1a3a96f726c6278bed Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:19 -0700 Subject: netpoll: move netpoll_send_skb() out of line There is no need to inline this helper, as we intend to add more code in this function. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netpoll.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 00e0bae3d402..e466ddffef61 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,14 +63,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -void __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); -static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) -{ - unsigned long flags; - local_irq_save(flags); - __netpoll_send_skb(np, skb); - local_irq_restore(flags); -} +void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL static inline void *netpoll_poll_lock(struct napi_struct *napi) -- cgit v1.2.3 From 1ddabdfaf70c202b88925edd74c66f4707dbd92e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:20 -0700 Subject: netpoll: netpoll_send_skb() returns transmit status Some callers want to know if the packet has been sent or dropped, to inform upper stacks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index e466ddffef61..f47af135bd56 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,7 +63,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); +netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL static inline void *netpoll_poll_lock(struct napi_struct *napi) -- cgit v1.2.3 From f78ed2204db9fc35b545d693865bddbe0149aa1f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:21 -0700 Subject: netpoll: accept NULL np argument in netpoll_send_skb() netpoll_send_skb() callers seem to leak skb if the np pointer is NULL. While this should not happen, we can make the code more robust. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/if_team.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index ec7e4bd07f82..537dc2b8c879 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -102,10 +102,7 @@ static inline bool team_port_dev_txable(const struct net_device *port_dev) static inline void team_netpoll_send_skb(struct team_port *port, struct sk_buff *skb) { - struct netpoll *np = port->np; - - if (np) - netpoll_send_skb(np, skb); + netpoll_send_skb(port->np, skb); } #else static inline void team_netpoll_send_skb(struct team_port *port, -- cgit v1.2.3 From 0090c1edebf464f34629e14ae03d764cca7e0a3b Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:50:41 -0500 Subject: audit: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 1a2351508211..3fcd9ee49734 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -19,7 +19,7 @@ struct audit_sig_info { uid_t uid; pid_t pid; - char ctx[0]; + char ctx[]; }; struct audit_buffer; -- cgit v1.2.3 From 6b0b0fa2bce61db790efc8070ae6e5696435b0a8 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 2 May 2020 11:24:25 -0700 Subject: crypto: lib/sha1 - rename "sha" to "sha1" The library implementation of the SHA-1 compression function is confusingly called just "sha_transform()". Alongside it are some "SHA_" constants and "sha_init()". Presumably these are left over from a time when SHA just meant SHA-1. But now there are also SHA-2 and SHA-3, and moreover SHA-1 is now considered insecure and thus shouldn't be used. Therefore, rename these functions and constants to make it very clear that they are for SHA-1. Also add a comment to make it clear that these shouldn't be used. For the extra-misleadingly named "SHA_MESSAGE_BYTES", rename it to SHA1_BLOCK_SIZE and define it to just '64' rather than '(512/8)' so that it matches the same definition in . This prepares for merging into . Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/cryptohash.h | 16 ++++++++++------ include/linux/filter.h | 2 +- 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index f6ba4c3e60d7..c324ffca96e0 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -4,11 +4,15 @@ #include -#define SHA_DIGEST_WORDS 5 -#define SHA_MESSAGE_BYTES (512 /*bits*/ / 8) -#define SHA_WORKSPACE_WORDS 16 - -void sha_init(__u32 *buf); -void sha_transform(__u32 *digest, const char *data, __u32 *W); +/* + * An implementation of SHA-1's compression function. Don't use in new code! + * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't + * the correct way to hash something with SHA-1 (use crypto_shash instead). + */ +#define SHA1_DIGEST_WORDS 5 +#define SHA1_BLOCK_SIZE 64 +#define SHA1_WORKSPACE_WORDS 16 +void sha1_init(__u32 *buf); +void sha1_transform(__u32 *digest, const char *data, __u32 *W); #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 9b5aa5c483cc..f42662adffe4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -746,7 +746,7 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + - sizeof(__be64) + 1, SHA_MESSAGE_BYTES); + sizeof(__be64) + 1, SHA1_BLOCK_SIZE); } static inline unsigned int bpf_prog_size(unsigned int proglen) -- cgit v1.2.3 From 228c4f265c6eb60eaa4ed0edb3bf7c113173576c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 2 May 2020 11:24:27 -0700 Subject: crypto: lib/sha1 - fold linux/cryptohash.h into crypto/sha.h sounds very generic and important, like it's the header to include if you're doing cryptographic hashing in the kernel. But actually it only includes the library implementation of the SHA-1 compression function (not even the full SHA-1). This should basically never be used anymore; SHA-1 is no longer considered secure, and there are much better ways to do cryptographic hashing in the kernel. Remove this header and fold it into which already contains constants and functions for SHA-1 (along with SHA-2). Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/cryptohash.h | 18 ------------------ include/linux/filter.h | 2 +- 2 files changed, 1 insertion(+), 19 deletions(-) delete mode 100644 include/linux/cryptohash.h (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h deleted file mode 100644 index c324ffca96e0..000000000000 --- a/include/linux/cryptohash.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __CRYPTOHASH_H -#define __CRYPTOHASH_H - -#include - -/* - * An implementation of SHA-1's compression function. Don't use in new code! - * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't - * the correct way to hash something with SHA-1 (use crypto_shash instead). - */ -#define SHA1_DIGEST_WORDS 5 -#define SHA1_BLOCK_SIZE 64 -#define SHA1_WORKSPACE_WORDS 16 -void sha1_init(__u32 *buf); -void sha1_transform(__u32 *digest, const char *data, __u32 *W); - -#endif diff --git a/include/linux/filter.h b/include/linux/filter.h index f42662adffe4..ec45fd7992c9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -16,11 +16,11 @@ #include #include #include -#include #include #include #include #include +#include #include -- cgit v1.2.3 From 54163a346d4a0a1b93f2ff6dc1f488419a605fa9 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Wed, 6 May 2020 08:17:53 -0500 Subject: KVM: Introduce kvm_make_all_cpus_request_except() This allows making request to all other vcpus except the one specified in the parameter. Signed-off-by: Suravee Suthikulpanit Message-Id: <1588771076-73790-2-git-send-email-suravee.suthikulpanit@amd.com> 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 01276e3d01b9..131cc1527d68 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -813,8 +813,11 @@ void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); +bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except); bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); -- cgit v1.2.3 From d2218d4e4a65f25bd2d38489567012c7db50233c Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 8 May 2020 18:39:35 +0300 Subject: lib: add linear ranges helpers Many devices have control registers which control some measurable property. Often a register contains control field so that change in this field causes linear change in the controlled property. It is not a rare case that user wants to give 'meaningful' control values and driver needs to convert them to register field values. Even more often user wants to 'see' the currently set value - again in meaningful units - and driver needs to convert the values it reads from register to these meaningful units. Examples of this include: - regulators, voltage/current configurations - power, voltage/current configurations - clk(?) NCOs and maybe others I can't think of right now. Provide a linear_range helper which can do conversion from user value to register value 'selector'. The idea here is stolen from regulator framework and patches refactoring the regulator helpers to use this are following. Current implementation does not support inversely proportional ranges but it might be useful if we could support also inversely proportional ranges? Signed-off-by: Matti Vaittinen Reviewed-by: Mark Brown Reviewed-by: Linus Walleij Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/59259bc475e0c800eb4bb163f02528c7c01f7b3a.1588944082.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/linear_range.h | 48 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/linux/linear_range.h (limited to 'include/linux') diff --git a/include/linux/linear_range.h b/include/linux/linear_range.h new file mode 100644 index 000000000000..17b5943727d5 --- /dev/null +++ b/include/linux/linear_range.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2020 ROHM Semiconductors */ + +#ifndef LINEAR_RANGE_H +#define LINEAR_RANGE_H + +#include + +/** + * struct linear_range - table of selector - value pairs + * + * Define a lookup-table for range of values. Intended to help when looking + * for a register value matching certaing physical measure (like voltage). + * Usable when increment of one in register always results a constant increment + * of the physical measure (like voltage). + * + * @min: Lowest value in range + * @min_sel: Lowest selector for range + * @max_sel: Highest selector for range + * @step: Value step size + */ +struct linear_range { + unsigned int min; + unsigned int min_sel; + unsigned int max_sel; + unsigned int step; +}; + +unsigned int linear_range_values_in_range(const struct linear_range *r); +unsigned int linear_range_values_in_range_array(const struct linear_range *r, + int ranges); +unsigned int linear_range_get_max_value(const struct linear_range *r); + +int linear_range_get_value(const struct linear_range *r, unsigned int selector, + unsigned int *val); +int linear_range_get_value_array(const struct linear_range *r, int ranges, + unsigned int selector, unsigned int *val); +int linear_range_get_selector_low(const struct linear_range *r, + unsigned int val, unsigned int *selector, + bool *found); +int linear_range_get_selector_high(const struct linear_range *r, + unsigned int val, unsigned int *selector, + bool *found); +int linear_range_get_selector_low_array(const struct linear_range *r, + int ranges, unsigned int val, + unsigned int *selector, bool *found); + +#endif -- cgit v1.2.3 From 60ab7f4153b6af461c90d572c31104086b44639f Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 8 May 2020 18:43:36 +0300 Subject: regulator: use linear_ranges helper Change the regulator helpers to use common linear_ranges code. Signed-off-by: Matti Vaittinen Reviewed-by: Mark Brown Acked-by: Charles Keepax Acked-by: Adam Thomson Link: https://lore.kernel.org/r/64f01d5e381b8631a271616b7790f9d5640974fb.1588944082.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 27 +++++---------------------- 1 file changed, 5 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 29d920516e0b..7eb9fea8e482 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -13,6 +13,7 @@ #define __LINUX_REGULATOR_DRIVER_H_ #include +#include #include #include #include @@ -39,31 +40,13 @@ enum regulator_status { REGULATOR_STATUS_UNDEFINED, }; -/** - * struct regulator_linear_range - specify linear voltage ranges - * - * Specify a range of voltages for regulator_map_linear_range() and - * regulator_list_linear_range(). - * - * @min_uV: Lowest voltage in range - * @min_sel: Lowest selector for range - * @max_sel: Highest selector for range - * @uV_step: Step size - */ -struct regulator_linear_range { - unsigned int min_uV; - unsigned int min_sel; - unsigned int max_sel; - unsigned int uV_step; -}; - -/* Initialize struct regulator_linear_range */ +/* Initialize struct linear_range for regulators */ #define REGULATOR_LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV) \ { \ - .min_uV = _min_uV, \ + .min = _min_uV, \ .min_sel = _min_sel, \ .max_sel = _max_sel, \ - .uV_step = _step_uV, \ + .step = _step_uV, \ } /** @@ -348,7 +331,7 @@ struct regulator_desc { unsigned int ramp_delay; int min_dropout_uV; - const struct regulator_linear_range *linear_ranges; + const struct linear_range *linear_ranges; const unsigned int *linear_range_selectors; int n_linear_ranges; -- cgit v1.2.3 From 62a7f3009a460001eb46984395280dd900bc4ef4 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 8 May 2020 14:53:40 +0800 Subject: serial: 8250_pci: Move Pericom IDs to pci_ids.h Move the IDs to pci_ids.h so it can be used by next patch. Link: https://lore.kernel.org/r/20200508065343.32751-1-kai.heng.feng@canonical.com Signed-off-by: Kai-Heng Feng Signed-off-by: Bjorn Helgaas Acked-by: Greg Kroah-Hartman Cc: stable@vger.kernel.org --- include/linux/pci_ids.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1dfc4e1dcb94..9a57e6717e5c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1832,6 +1832,12 @@ #define PCI_VENDOR_ID_NVIDIA_SGS 0x12d2 #define PCI_DEVICE_ID_NVIDIA_SGS_RIVA128 0x0018 +#define PCI_VENDOR_ID_PERICOM 0x12D8 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7951 0x7951 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7952 0x7952 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7954 0x7954 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7958 0x7958 + #define PCI_SUBVENDOR_ID_CHASE_PCIFAST 0x12E0 #define PCI_SUBDEVICE_ID_CHASE_PCIFAST4 0x0031 #define PCI_SUBDEVICE_ID_CHASE_PCIFAST8 0x0021 -- cgit v1.2.3 From f2a8d52e0a4db968c346c4332630a71cba377567 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 5 May 2020 16:04:30 +0200 Subject: nsproxy: add struct nsset Add a simple struct nsset. It holds all necessary pieces to switch to a new set of namespaces without leaving a task in a half-switched state which we will make use of in the next patch. This patch switches the existing setns logic over without causing a change in setns() behavior. This brings setns() closer to how unshare() works(). The prepare_ns() function is responsible to prepare all necessary information. This has two reasons. First it minimizes dependencies between individual namespaces, i.e. all install handler can expect that all fields are properly initialized independent in what order they are called in. Second, this makes the code easier to maintain and easier to follow if it needs to be changed. The prepare_ns() helper will only be switched over to use a flags argument in the next patch. Here it will still use nstype as a simple integer argument which was argued would be clearer. I'm not particularly opinionated about this if it really helps or not. The struct nsset itself already contains the flags field since its name already indicates that it can contain information required by different namespaces. None of this should have functional consequences. Signed-off-by: Christian Brauner Reviewed-by: Serge Hallyn Cc: Eric W. Biederman Cc: Serge Hallyn Cc: Jann Horn Cc: Michael Kerrisk Cc: Aleksa Sarai Link: https://lore.kernel.org/r/20200505140432.181565-2-christian.brauner@ubuntu.com --- include/linux/mnt_namespace.h | 1 + include/linux/nsproxy.h | 24 ++++++++++++++++++++++++ include/linux/proc_ns.h | 4 ++-- 3 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 35942084cd40..007cfa52efb2 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -6,6 +6,7 @@ struct mnt_namespace; struct fs_struct; struct user_namespace; +struct ns_common; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 074f395b9ad2..cdb171efc7cb 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -41,6 +41,30 @@ struct nsproxy { }; extern struct nsproxy init_nsproxy; +/* + * A structure to encompass all bits needed to install + * a partial or complete new set of namespaces. + * + * If a new user namespace is requested cred will + * point to a modifiable set of credentials. If a pointer + * to a modifiable set is needed nsset_cred() must be + * used and tested. + */ +struct nsset { + unsigned flags; + struct nsproxy *nsproxy; + struct fs_struct *fs; + const struct cred *cred; +}; + +static inline struct cred *nsset_cred(struct nsset *set) +{ + if (set->flags & CLONE_NEWUSER) + return (struct cred *)set->cred; + + return NULL; +} + /* * the namespaces access rules are: * diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 6abe85c34681..75807ecef880 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -8,7 +8,7 @@ #include struct pid_namespace; -struct nsproxy; +struct nsset; struct path; struct task_struct; struct inode; @@ -19,7 +19,7 @@ struct proc_ns_operations { int type; struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); - int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); + int (*install)(struct nsset *nsset, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); } __randomize_layout; -- cgit v1.2.3 From 6bd87eec23cbc9ed222bed0f5b5b02bf300e9a8d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:47:56 +0200 Subject: bdi: add a ->dev_name field to struct backing_dev_info Cache a copy of the name for the life time of the backing_dev_info structure so that we can reference it even after unregistering. Fixes: 68f23b89067f ("memcg: fix a crash in wb_workfn when a device disappears") Reported-by: Yufen Yu Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ee577a83cfe6..7367150f962a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -219,6 +219,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; -- cgit v1.2.3 From 4c74746625dedb62ce00ac86ac4faedb640536d0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:47:57 +0200 Subject: driver core: remove device_create_vargs All external users of device_create_vargs are gone, so remove it and open code it in the only caller. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- 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 ac8e37cd716a..15460a5ac024 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -884,10 +884,6 @@ extern bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ -extern __printf(5, 0) -struct device *device_create_vargs(struct class *cls, struct device *parent, - dev_t devt, void *drvdata, - const char *fmt, va_list vargs); extern __printf(5, 6) struct device *device_create(struct class *cls, struct device *parent, dev_t devt, void *drvdata, -- cgit v1.2.3 From 3c5d202b55d3fa9106607f99cdd5044b02b5929b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:47:59 +0200 Subject: bdi: remove bdi_register_owner Split out a new bdi_set_owner helper to set the owner, and move the policy for creating the bdi name back into genhd.c, where it belongs. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Greg Kroah-Hartman Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c9ad5c3b7b4b..4098ed6ba6b4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -33,7 +33,7 @@ int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); -int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); +void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id); -- cgit v1.2.3 From aef33c2ff8aa5e24f3f7d93806aa84ca1c2b6832 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:48:00 +0200 Subject: bdi: simplify bdi_alloc Merge the _node vs normal version and drop the superflous gfp_t argument. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Greg Kroah-Hartman Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 4098ed6ba6b4..6b3504bf7a42 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -36,11 +36,7 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); -struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id); -static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask) -{ - return bdi_alloc_node(gfp_mask, NUMA_NO_NODE); -} +struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); -- cgit v1.2.3 From 1cd925d583857ee3ead6cfbf1e4b1cd067d28591 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:48:01 +0200 Subject: bdi: remove the name field in struct backing_dev_info The name is only printed for a not registered bdi in writeback. Use the device name there as is more useful anyway for the unlike case that the warning triggers. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Greg Kroah-Hartman Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 7367150f962a..90a7e844a098 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -193,8 +193,6 @@ struct backing_dev_info { congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ - const char *name; - struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; -- cgit v1.2.3 From 615399896ca3787728c56c499c99be79e40ac125 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 31 Mar 2020 09:49:46 -0700 Subject: nvme-fc: Sync header to FC-NVME-2 rev 1.08 A couple of minor changes occurred between 1.06 and 1.08: - Addition of NVME_SR_RSP opcode - change of SR_RSP status code 1 to Reserved Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index e8c30b39bb27..51fe44e0328b 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -4,8 +4,8 @@ */ /* - * This file contains definitions relative to FC-NVME-2 r1.06 - * (T11-2019-00210-v001). + * This file contains definitions relative to FC-NVME-2 r1.08 + * (T11-2019-00210-v004). */ #ifndef _NVME_FC_H @@ -81,7 +81,8 @@ struct nvme_fc_ersp_iu { }; -#define FCNVME_NVME_SR_OPCODE 0x01 +#define FCNVME_NVME_SR_OPCODE 0x01 +#define FCNVME_NVME_SR_RSP_OPCODE 0x02 struct nvme_fc_nvme_sr_iu { __u8 fc_id; @@ -94,7 +95,7 @@ struct nvme_fc_nvme_sr_iu { enum { FCNVME_SRSTAT_ACC = 0x0, - FCNVME_SRSTAT_INV_FCID = 0x1, + /* reserved 0x1 */ /* reserved 0x2 */ FCNVME_SRSTAT_LOGICAL_ERR = 0x3, FCNVME_SRSTAT_INV_QUALIF = 0x4, @@ -397,7 +398,7 @@ struct fcnvme_ls_disconnect_conn_rqst { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_assoc_id associd; - struct fcnvme_lsdesc_disconn_cmd connectid; + struct fcnvme_lsdesc_conn_id connectid; }; struct fcnvme_ls_disconnect_conn_acc { -- cgit v1.2.3 From 72e6329f86c714785ac195d293cb19dd24507880 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 31 Mar 2020 09:49:47 -0700 Subject: nvme-fc and nvmet-fc: revise LLDD api for LS reception and LS request The current LLDD api has: nvme-fc: contains api for transport to do LS requests (and aborts of them). However, there is no interface for reception of LS's and sending responses for them. nvmet-fc: contains api for transport to do reception of LS's and sending of responses for them. However, there is no interface for doing LS requests. Revise the api's so that both nvme-fc and nvmet-fc can send LS's, as well as receiving LS's and sending their responses. Change name of the rcv_ls_req struct to better reflect generic use as a context to used to send an ls rsp. Specifically: nvmefc_tgt_ls_req -> nvmefc_ls_rsp nvmefc_tgt_ls_req.nvmet_fc_private -> nvmefc_ls_rsp.nvme_fc_private Change nvmet_fc_rcv_ls_req() calling sequence to provide handle that can be used by transport in later LS request sequences for an association. nvme-fc nvmet_fc nvme_fcloop: Revise to adapt to changed names in api header. Change calling sequence to nvmet_fc_rcv_ls_req() for hosthandle. Add stubs for new interfaces: host/fc.c: nvme_fc_rcv_ls_req() target/fc.c: nvmet_fc_invalidate_host() lpfc: Revise to adapt code to changed names in api header. Change calling sequence to nvmet_fc_rcv_ls_req() for hosthandle. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Reviewed-by: Himanshu Madhani Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc-driver.h | 368 ++++++++++++++++++++++++++++++----------- 1 file changed, 270 insertions(+), 98 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 10f81629b9ce..41e7795a3ee4 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -10,47 +10,26 @@ /* - * ********************** LLDD FC-NVME Host API ******************** + * ********************** FC-NVME LS API ******************** * - * For FC LLDD's that are the NVME Host role. + * Data structures used by both FC-NVME hosts and FC-NVME + * targets to perform FC-NVME LS requests or transmit + * responses. * - * ****************************************************************** + * *********************************************************** */ - - /** - * struct nvme_fc_port_info - port-specific ids and FC connection-specific - * data element used during NVME Host role - * registrations - * - * Static fields describing the port being registered: - * @node_name: FC WWNN for the port - * @port_name: FC WWPN for the port - * @port_role: What NVME roles are supported (see FC_PORT_ROLE_xxx) - * @dev_loss_tmo: maximum delay for reconnects to an association on - * this device. Used only on a remoteport. + * struct nvmefc_ls_req - Request structure passed from the transport + * to the LLDD to perform a NVME-FC LS request and obtain + * a response. + * Used by nvme-fc transport (host) to send LS's such as + * Create Association, Create Connection and Disconnect + * Association. + * Used by the nvmet-fc transport (controller) to send + * LS's such as Disconnect Association. * - * Initialization values for dynamic port fields: - * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must - * be set to 0. - */ -struct nvme_fc_port_info { - u64 node_name; - u64 port_name; - u32 port_role; - u32 port_id; - u32 dev_loss_tmo; -}; - - -/** - * struct nvmefc_ls_req - Request structure passed from NVME-FC transport - * to LLDD in order to perform a NVME FC-4 LS - * request and obtain a response. - * - * Values set by the NVME-FC layer prior to calling the LLDD ls_req - * entrypoint. + * Values set by the requestor prior to calling the LLDD ls_req entrypoint: * @rqstaddr: pointer to request buffer * @rqstdma: PCI DMA address of request buffer * @rqstlen: Length, in bytes, of request buffer @@ -63,8 +42,8 @@ struct nvme_fc_port_info { * @private: pointer to memory allocated alongside the ls request structure * that is specifically for the LLDD to use while processing the * request. The length of the buffer corresponds to the - * lsrqst_priv_sz value specified in the nvme_fc_port_template - * supplied by the LLDD. + * lsrqst_priv_sz value specified in the xxx_template supplied + * by the LLDD. * @done: The callback routine the LLDD is to invoke upon completion of * the LS request. req argument is the pointer to the original LS * request structure. Status argument must be 0 upon success, a @@ -86,6 +65,101 @@ struct nvmefc_ls_req { } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ +/** + * struct nvmefc_ls_rsp - Structure passed from the transport to the LLDD + * to request the transmit the NVME-FC LS response to a + * NVME-FC LS request. The structure originates in the LLDD + * and is given to the transport via the xxx_rcv_ls_req() + * transport routine. As such, the structure represents the + * FC exchange context for the NVME-FC LS request that was + * received and which the response is to be sent for. + * Used by the LLDD to pass the nvmet-fc transport (controller) + * received LS's such as Create Association, Create Connection + * and Disconnect Association. + * Used by the LLDD to pass the nvme-fc transport (host) + * received LS's such as Disconnect Association or Disconnect + * Connection. + * + * The structure is allocated by the LLDD whenever a LS Request is received + * from the FC link. The address of the structure is passed to the nvmet-fc + * or nvme-fc layer via the xxx_rcv_ls_req() transport routines. + * + * The address of the structure is to be passed back to the LLDD + * when the response is to be transmit. The LLDD will use the address to + * map back to the LLDD exchange structure which maintains information such + * the remote N_Port that sent the LS as well as any FC exchange context. + * Upon completion of the LS response transmit, the LLDD will pass the + * address of the structure back to the transport LS rsp done() routine, + * allowing the transport release dma resources. Upon completion of + * the done() routine, no further access to the structure will be made by + * the transport and the LLDD can de-allocate the structure. + * + * Field initialization: + * At the time of the xxx_rcv_ls_req() call, there is no content that + * is valid in the structure. + * + * When the structure is used for the LLDD->xmt_ls_rsp() call, the + * transport layer will fully set the fields in order to specify the + * response payload buffer and its length as well as the done routine + * to be called upon completion of the transmit. The transport layer + * will also set a private pointer for its own use in the done routine. + * + * Values set by the transport layer prior to calling the LLDD xmt_ls_rsp + * entrypoint: + * @rspbuf: pointer to the LS response buffer + * @rspdma: PCI DMA address of the LS response buffer + * @rsplen: Length, in bytes, of the LS response buffer + * @done: The callback routine the LLDD is to invoke upon completion of + * transmitting the LS response. req argument is the pointer to + * the original ls request. + * @nvme_fc_private: pointer to an internal transport-specific structure + * used as part of the transport done() processing. The LLDD is + * not to access this pointer. + */ +struct nvmefc_ls_rsp { + void *rspbuf; + dma_addr_t rspdma; + u16 rsplen; + + void (*done)(struct nvmefc_ls_rsp *rsp); + void *nvme_fc_private; /* LLDD is not to access !! */ +}; + + + +/* + * ********************** LLDD FC-NVME Host API ******************** + * + * For FC LLDD's that are the NVME Host role. + * + * ****************************************************************** + */ + + +/** + * struct nvme_fc_port_info - port-specific ids and FC connection-specific + * data element used during NVME Host role + * registrations + * + * Static fields describing the port being registered: + * @node_name: FC WWNN for the port + * @port_name: FC WWPN for the port + * @port_role: What NVME roles are supported (see FC_PORT_ROLE_xxx) + * @dev_loss_tmo: maximum delay for reconnects to an association on + * this device. Used only on a remoteport. + * + * Initialization values for dynamic port fields: + * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must + * be set to 0. + */ +struct nvme_fc_port_info { + u64 node_name; + u64 port_name; + u32 port_role; + u32 port_id; + u32 dev_loss_tmo; +}; + enum nvmefc_fcp_datadir { NVMEFC_FCP_NODATA, /* payload_length and sg_cnt will be zero */ NVMEFC_FCP_WRITE, @@ -337,6 +411,21 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * + * @xmt_ls_rsp: Called to transmit the response to a FC-NVME FC-4 LS service. + * The nvmefc_ls_rsp structure is the same LLDD-supplied exchange + * structure specified in the nvme_fc_rcv_ls_req() call made when + * the LS request was received. The structure will fully describe + * the buffers for the response payload and the dma address of the + * payload. The LLDD is to transmit the response (or return a + * non-zero errno status), and upon completion of the transmit, call + * the "done" routine specified in the nvmefc_ls_rsp structure + * (argument to done is the address of the nvmefc_ls_rsp structure + * itself). Upon the completion of the done routine, the LLDD shall + * consider the LS handling complete and the nvmefc_ls_rsp structure + * may be freed/released. + * Entrypoint is mandatory if the LLDD calls the nvme_fc_rcv_ls_req() + * entrypoint. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -371,7 +460,7 @@ struct nvme_fc_remote_port { * @lsrqst_priv_sz: The LLDD sets this field to the amount of additional * memory that it would like fc nvme layer to allocate on the LLDD's * behalf whenever a ls request structure is allocated. The additional - * memory area solely for the of the LLDD and its location is + * memory area is solely for use by the LLDD and its location is * specified by the ls_request->private pointer. * Value is Mandatory. Allowed to be zero. * @@ -405,6 +494,9 @@ struct nvme_fc_port_template { struct nvme_fc_remote_port *, void *hw_queue_handle, struct nvmefc_fcp_req *); + int (*xmt_ls_rsp)(struct nvme_fc_local_port *localport, + struct nvme_fc_remote_port *rport, + struct nvmefc_ls_rsp *ls_rsp); u32 max_hw_queues; u16 max_sgl_segments; @@ -441,6 +533,34 @@ void nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport); int nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *remoteport, u32 dev_loss_tmo); +/* + * Routine called to pass a NVME-FC LS request, received by the lldd, + * to the nvme-fc transport. + * + * If the return value is zero: the LS was successfully accepted by the + * transport. + * If the return value is non-zero: the transport has not accepted the + * LS. The lldd should ABTS-LS the LS. + * + * Note: if the LLDD receives and ABTS for the LS prior to the transport + * calling the ops->xmt_ls_rsp() routine to transmit a response, the LLDD + * shall mark the LS as aborted, and when the xmt_ls_rsp() is called: the + * response shall not be transmit and the struct nvmefc_ls_rsp() done + * routine shall be called. The LLDD may transmit the ABTS response as + * soon as the LS was marked or can delay until the xmt_ls_rsp() call is + * made. + * Note: if an RCV LS was successfully posted to the transport and the + * remoteport is then unregistered before xmt_ls_rsp() was called for + * the lsrsp structure, the transport will still call xmt_ls_rsp() + * afterward to cleanup the outstanding lsrsp structure. The LLDD should + * noop the transmission of the rsp and call the lsrsp->done() routine + * to allow the lsrsp structure to be released. + */ +int nvme_fc_rcv_ls_req(struct nvme_fc_remote_port *remoteport, + struct nvmefc_ls_rsp *lsrsp, + void *lsreqbuf, u32 lsreqbuf_len); + + /* * *************** LLDD FC-NVME Target/Subsystem API *************** @@ -470,55 +590,6 @@ struct nvmet_fc_port_info { }; -/** - * struct nvmefc_tgt_ls_req - Structure used between LLDD and NVMET-FC - * layer to represent the exchange context for - * a FC-NVME Link Service (LS). - * - * The structure is allocated by the LLDD whenever a LS Request is received - * from the FC link. The address of the structure is passed to the nvmet-fc - * layer via the nvmet_fc_rcv_ls_req() call. The address of the structure - * will be passed back to the LLDD when the response is to be transmit. - * The LLDD is to use the address to map back to the LLDD exchange structure - * which maintains information such as the targetport the LS was received - * on, the remote FC NVME initiator that sent the LS, and any FC exchange - * context. Upon completion of the LS response transmit, the address of the - * structure will be passed back to the LS rsp done() routine, allowing the - * nvmet-fc layer to release dma resources. Upon completion of the done() - * routine, no further access will be made by the nvmet-fc layer and the - * LLDD can de-allocate the structure. - * - * Field initialization: - * At the time of the nvmet_fc_rcv_ls_req() call, there is no content that - * is valid in the structure. - * - * When the structure is used for the LLDD->xmt_ls_rsp() call, the nvmet-fc - * layer will fully set the fields in order to specify the response - * payload buffer and its length as well as the done routine to be called - * upon compeletion of the transmit. The nvmet-fc layer will also set a - * private pointer for its own use in the done routine. - * - * Values set by the NVMET-FC layer prior to calling the LLDD xmt_ls_rsp - * entrypoint. - * @rspbuf: pointer to the LS response buffer - * @rspdma: PCI DMA address of the LS response buffer - * @rsplen: Length, in bytes, of the LS response buffer - * @done: The callback routine the LLDD is to invoke upon completion of - * transmitting the LS response. req argument is the pointer to - * the original ls request. - * @nvmet_fc_private: pointer to an internal NVMET-FC layer structure used - * as part of the NVMET-FC processing. The LLDD is not to access - * this pointer. - */ -struct nvmefc_tgt_ls_req { - void *rspbuf; - dma_addr_t rspdma; - u16 rsplen; - - void (*done)(struct nvmefc_tgt_ls_req *req); - void *nvmet_fc_private; /* LLDD is not to access !! */ -}; - /* Operations that NVME-FC layer may request the LLDD to perform for FCP */ enum { NVMET_FCOP_READDATA = 1, /* xmt data to initiator */ @@ -693,17 +764,19 @@ struct nvmet_fc_target_port { * Entrypoint is Mandatory. * * @xmt_ls_rsp: Called to transmit the response to a FC-NVME FC-4 LS service. - * The nvmefc_tgt_ls_req structure is the same LLDD-supplied exchange + * The nvmefc_ls_rsp structure is the same LLDD-supplied exchange * structure specified in the nvmet_fc_rcv_ls_req() call made when - * the LS request was received. The structure will fully describe + * the LS request was received. The structure will fully describe * the buffers for the response payload and the dma address of the - * payload. The LLDD is to transmit the response (or return a non-zero - * errno status), and upon completion of the transmit, call the - * "done" routine specified in the nvmefc_tgt_ls_req structure - * (argument to done is the ls reqwuest structure itself). - * After calling the done routine, the LLDD shall consider the - * LS handling complete and the nvmefc_tgt_ls_req structure may - * be freed/released. + * payload. The LLDD is to transmit the response (or return a + * non-zero errno status), and upon completion of the transmit, call + * the "done" routine specified in the nvmefc_ls_rsp structure + * (argument to done is the address of the nvmefc_ls_rsp structure + * itself). Upon the completion of the done() routine, the LLDD shall + * consider the LS handling complete and the nvmefc_ls_rsp structure + * may be freed/released. + * The transport will always call the xmt_ls_rsp() routine for any + * LS received. * Entrypoint is Mandatory. * * @fcp_op: Called to perform a data transfer or transmit a response. @@ -798,6 +871,39 @@ struct nvmet_fc_target_port { * should cause the initiator to rescan the discovery controller * on the targetport. * + * @ls_req: Called to issue a FC-NVME FC-4 LS service request. + * The nvme_fc_ls_req structure will fully describe the buffers for + * the request payload and where to place the response payload. + * The targetport that is to issue the LS request is identified by + * the targetport argument. The remote port that is to receive the + * LS request is identified by the hosthandle argument. The nvmet-fc + * transport is only allowed to issue FC-NVME LS's on behalf of an + * association that was created prior by a Create Association LS. + * The hosthandle will originate from the LLDD in the struct + * nvmefc_ls_rsp structure for the Create Association LS that + * was delivered to the transport. The transport will save the + * hosthandle as an attribute of the association. If the LLDD + * loses connectivity with the remote port, it must call the + * nvmet_fc_invalidate_host() routine to remove any references to + * the remote port in the transport. + * The LLDD is to allocate an exchange, issue the LS request, obtain + * the LS response, and call the "done" routine specified in the + * request structure (argument to done is the ls request structure + * itself). + * Entrypoint is Optional - but highly recommended. + * + * @ls_abort: called to request the LLDD to abort the indicated ls request. + * The call may return before the abort has completed. After aborting + * the request, the LLDD must still call the ls request done routine + * indicating an FC transport Aborted status. + * Entrypoint is Mandatory if the ls_req entry point is specified. + * + * @host_release: called to inform the LLDD that the request to invalidate + * the host port indicated by the hosthandle has been fully completed. + * No associations exist with the host port and there will be no + * further references to hosthandle. + * Entrypoint is Mandatory if the lldd calls nvmet_fc_invalidate_host(). + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -826,11 +932,19 @@ struct nvmet_fc_target_port { * area solely for the of the LLDD and its location is specified by * the targetport->private pointer. * Value is Mandatory. Allowed to be zero. + * + * @lsrqst_priv_sz: The LLDD sets this field to the amount of additional + * memory that it would like nvmet-fc layer to allocate on the LLDD's + * behalf whenever a ls request structure is allocated. The additional + * memory area is solely for use by the LLDD and its location is + * specified by the ls_request->private pointer. + * Value is Mandatory. Allowed to be zero. + * */ struct nvmet_fc_target_template { void (*targetport_delete)(struct nvmet_fc_target_port *tgtport); int (*xmt_ls_rsp)(struct nvmet_fc_target_port *tgtport, - struct nvmefc_tgt_ls_req *tls_req); + struct nvmefc_ls_rsp *ls_rsp); int (*fcp_op)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); void (*fcp_abort)(struct nvmet_fc_target_port *tgtport, @@ -840,6 +954,11 @@ struct nvmet_fc_target_template { void (*defer_rcv)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); void (*discovery_event)(struct nvmet_fc_target_port *tgtport); + int (*ls_req)(struct nvmet_fc_target_port *targetport, + void *hosthandle, struct nvmefc_ls_req *lsreq); + void (*ls_abort)(struct nvmet_fc_target_port *targetport, + void *hosthandle, struct nvmefc_ls_req *lsreq); + void (*host_release)(void *hosthandle); u32 max_hw_queues; u16 max_sgl_segments; @@ -848,7 +967,9 @@ struct nvmet_fc_target_template { u32 target_features; + /* sizes of additional private data for data structures */ u32 target_priv_sz; + u32 lsrqst_priv_sz; }; @@ -859,10 +980,61 @@ int nvmet_fc_register_targetport(struct nvmet_fc_port_info *portinfo, int nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *tgtport); +/* + * Routine called to pass a NVME-FC LS request, received by the lldd, + * to the nvmet-fc transport. + * + * If the return value is zero: the LS was successfully accepted by the + * transport. + * If the return value is non-zero: the transport has not accepted the + * LS. The lldd should ABTS-LS the LS. + * + * Note: if the LLDD receives and ABTS for the LS prior to the transport + * calling the ops->xmt_ls_rsp() routine to transmit a response, the LLDD + * shall mark the LS as aborted, and when the xmt_ls_rsp() is called: the + * response shall not be transmit and the struct nvmefc_ls_rsp() done + * routine shall be called. The LLDD may transmit the ABTS response as + * soon as the LS was marked or can delay until the xmt_ls_rsp() call is + * made. + * Note: if an RCV LS was successfully posted to the transport and the + * targetport is then unregistered before xmt_ls_rsp() was called for + * the lsrsp structure, the transport will still call xmt_ls_rsp() + * afterward to cleanup the outstanding lsrsp structure. The LLDD should + * noop the transmission of the rsp and call the lsrsp->done() routine + * to allow the lsrsp structure to be released. + */ int nvmet_fc_rcv_ls_req(struct nvmet_fc_target_port *tgtport, - struct nvmefc_tgt_ls_req *lsreq, + void *hosthandle, + struct nvmefc_ls_rsp *rsp, void *lsreqbuf, u32 lsreqbuf_len); +/* + * Routine called by the LLDD whenever it has a logout or loss of + * connectivity to a NVME-FC host port which there had been active + * NVMe controllers for. The host port is indicated by the + * hosthandle. The hosthandle is given to the nvmet-fc transport + * when a NVME LS was received, typically to create a new association. + * The nvmet-fc transport will cache the hostport value with the + * association for use in LS requests for the association. + * When the LLDD calls this routine, the nvmet-fc transport will + * immediately terminate all associations that were created with + * the hosthandle host port. + * The LLDD, after calling this routine and having control returned, + * must assume the transport may subsequently utilize hosthandle as + * part of sending LS's to terminate the association. The LLDD + * should reject the LS's if they are attempted. + * Once the last association has terminated for the hosthandle host + * port, the nvmet-fc transport will call the ops->host_release() + * callback. As of the callback, the nvmet-fc transport will no + * longer reference hosthandle. + */ +void nvmet_fc_invalidate_host(struct nvmet_fc_target_port *tgtport, + void *hosthandle); + +/* + * If nvmet_fc_rcv_fcp_req returns non-zero, the transport has not accepted + * the FCP cmd. The lldd should ABTS-LS the cmd. + */ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq, void *cmdiubuf, u32 cmdiubuf_len); -- cgit v1.2.3 From d02abd198633a4c40411b9a5994111452720470d Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Mon, 4 May 2020 01:56:48 -0700 Subject: nvmet: align addrfam list to spec With reference to the NVMeOF Specification (page 44, Figure 38) discovery log page entry provides address family field. We do set the transport type field but the adrfam field is not set when using loop transport and also it doesn't have support in the nvme-cli. So when reading discovery log page with a loop transport it leads to confusing output. As per the spec for adrfam value 254 is reserved for Intra Host Transport i.e. loopback), we add a required macro in the protocol header file, set default port disc addr entry's adrfam to NVMF_ADDR_FAMILY_MAX, and update nvmet_addr_family configfs array for show/store attribute. Without this patch, setting adrfam to (ipv4/ipv6/ib/fc/loop/" ") we get following output for nvme discover command from nvme-cli which is confusing. trtype: loop adrfam: ipv4 trtype: loop adrfam: ipv6 trtype: loop adrfam: infiniband trtype: loop adrfam: fibre-channel trtype: loop # ${CFGFS_HOME}/nvmet/ports/1/addr_adrfam = loop adrfam: pci # <----- pci for loop trtype: loop # ${CFGFS_HOME}/nvmet/ports/1/addr_adrfam = " " adrfam: pci # <----- pci for unrecognized This patch fixes above output :- trtype: loop adrfam: ipv4 trtype: loop adrfam: ipv6 trtype: loop adrfam: infiniband trtype: loop adrfam: fibre-channel trtype: loop # ${CFGFS_HOME}/nvmet/ports/1/addr_adrfam = loop adrfam: loop # <----- loop for loop trtype: loop # ${CFGFS_HOME}/config/nvmet/ports/adrfam = " " adrfam: unrecognized # <----- unrecognized when invalid value Signed-off-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 3d5189f46cb1..2d978d0cbde6 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -38,6 +38,8 @@ enum { NVMF_ADDR_FAMILY_IP6 = 2, /* IP6 */ NVMF_ADDR_FAMILY_IB = 3, /* InfiniBand */ NVMF_ADDR_FAMILY_FC = 4, /* Fibre Channel */ + NVMF_ADDR_FAMILY_LOOP = 254, /* Reserved for host usage */ + NVMF_ADDR_FAMILY_MAX, }; /* Transport Type codes for Discovery Log Page entry TRTYPE field */ -- cgit v1.2.3 From 92decf118f1da4c866515f80387f9cf4d48611d6 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 3 Apr 2020 10:53:46 -0700 Subject: nvme: define constants for identification values Improve code readability by defining the specification's constants that the driver is using when decoding identification payloads. Signed-off-by: Keith Busch Reviewed-by: Bart van Assche Reviewed-by: Chaitanya Kulkarni Acked-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 2d978d0cbde6..b235a48eac8c 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -301,6 +301,8 @@ struct nvme_id_ctrl { }; enum { + NVME_CTRL_CMIC_MULTI_CTRL = 1 << 1, + NVME_CTRL_CMIC_ANA = 1 << 3, NVME_CTRL_ONCS_COMPARE = 1 << 0, NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, NVME_CTRL_ONCS_DSM = 1 << 2, @@ -396,8 +398,12 @@ enum { enum { NVME_NS_FEAT_THIN = 1 << 0, + NVME_NS_FEAT_ATOMICS = 1 << 1, + NVME_NS_FEAT_IO_OPT = 1 << 4, + NVME_NS_ATTR_RO = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, NVME_NS_FLBAS_META_EXT = 0x10, + NVME_NS_NMIC_SHARED = 1 << 0, NVME_LBAF_RP_BEST = 0, NVME_LBAF_RP_BETTER = 1, NVME_LBAF_RP_GOOD = 2, -- cgit v1.2.3 From ae24345da54e452880808b011fa2d8a0bbd191ba Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:58:59 -0700 Subject: bpf: Implement an interface to register bpf_iter targets The target can call bpf_iter_reg_target() to register itself. The needed information: target: target name seq_ops: the seq_file operations for the target init_seq_private target callback to initialize seq_priv during file open fini_seq_private target callback to clean up seq_priv during file release seq_priv_size: the private_data size needed by the seq_file operations The target name represents a target which provides a seq_ops for iterating objects. The target can provide two callback functions, init_seq_private and fini_seq_private, called during file open/release time. For example, /proc/net/{tcp6, ipv6_route, netlink, ...}, net name space needs to be setup properly during file open and released properly during file release. Function bpf_iter_unreg_target() is also implemented to unregister a particular target. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175859.2474669-1-yhs@fb.com --- include/linux/bpf.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1262ec460ab3..40c78b86fe38 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -31,6 +31,7 @@ struct seq_file; struct btf; struct btf_type; struct exception_table_entry; +struct seq_operations; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1126,6 +1127,20 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); + +struct bpf_iter_reg { + const char *target; + const struct seq_operations *seq_ops; + bpf_iter_init_seq_priv_t init_seq_private; + bpf_iter_fini_seq_priv_t fini_seq_private; + u32 seq_priv_size; +}; + +int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); +void bpf_iter_unreg_target(const char *target); + int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, -- cgit v1.2.3 From 15d83c4d7cef5c067a8b075ce59e97df4f60706e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:00 -0700 Subject: bpf: Allow loading of a bpf_iter program A bpf_iter program is a tracing program with attach type BPF_TRACE_ITER. The load attribute attach_btf_id is used by the verifier against a particular kernel function, which represents a target, e.g., __bpf_iter__bpf_map for target bpf_map which is implemented later. The program return value must be 0 or 1 for now. 0 : successful, except potential seq_file buffer overflow which is handled by seq_file reader. 1 : request to restart the same object In the future, other return values may be used for filtering or teminating the iterator. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175900.2474947-1-yhs@fb.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 40c78b86fe38..f28bdd714754 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1127,6 +1127,8 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); +#define BPF_ITER_FUNC_PREFIX "__bpf_iter__" + typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); @@ -1140,6 +1142,7 @@ struct bpf_iter_reg { int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); +bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From de4e05cac46d206f9090051ef09930514bff73e4 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:01 -0700 Subject: bpf: Support bpf tracing/iter programs for BPF_LINK_CREATE Given a bpf program, the step to create an anonymous bpf iterator is: - create a bpf_iter_link, which combines bpf program and the target. In the future, there could be more information recorded in the link. A link_fd will be returned to the user space. - create an anonymous bpf iterator with the given link_fd. The bpf_iter_link can be pinned to bpffs mount file system to create a file based bpf iterator as well. The benefit to use of bpf_iter_link: - using bpf link simplifies design and implementation as bpf link is used for other tracing bpf programs. - for file based bpf iterator, bpf_iter_link provides a standard way to replace underlying bpf programs. - for both anonymous and free based iterators, bpf link query capability can be leveraged. The patch added support of tracing/iter programs for BPF_LINK_CREATE. A new link type BPF_LINK_TYPE_ITER is added to facilitate link querying. Currently, only prog_id is needed, so there is no additional in-kernel show_fdinfo() and fill_link_info() hook is needed for BPF_LINK_TYPE_ITER link. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175901.2475084-1-yhs@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f28bdd714754..e93d2d33c82c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1143,6 +1143,7 @@ struct bpf_iter_reg { int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 8345cdf553b8..29d22752fc87 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) #ifdef CONFIG_CGROUP_BPF BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) -- cgit v1.2.3 From ac51d99bf81caac8d8881fe52098948110d0de68 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:05 -0700 Subject: bpf: Create anonymous bpf iterator A new bpf command BPF_ITER_CREATE is added. The anonymous bpf iterator is seq_file based. The seq_file private data are referenced by targets. The bpf_iter infrastructure allocated additional space at seq_file->private before the space used by targets to store some meta data, e.g., prog: prog to run session_id: an unique id for each opened seq_file seq_num: how many times bpf programs are queried in this session done_stop: an internal state to decide whether bpf program should be called in seq_ops->stop() or not The seq_num will start from 0 for valid objects. The bpf program may see the same seq_num more than once if - seq_file buffer overflow happens and the same object is retried by bpf_seq_read(), or - the bpf program explicitly requests a retry of the same object Since module is not supported for bpf_iter, all target registeration happens at __init time, so there is no need to change bpf_iter_unreg_target() as it is used mostly in error path of the init function at which time no bpf iterators have been created yet. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175905.2475770-1-yhs@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 e93d2d33c82c..80b1b9d8a638 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1144,6 +1144,7 @@ int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_new_fd(struct bpf_link *link); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From 367ec3e4834cbd611401c2c40a23c22c825474f1 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:06 -0700 Subject: bpf: Create file bpf iterator To produce a file bpf iterator, the fd must be corresponding to a link_fd assocciated with a trace/iter program. When the pinned file is opened, a seq_file will be generated. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175906.2475893-1-yhs@fb.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80b1b9d8a638..b06653ab3476 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1022,6 +1022,7 @@ static inline void bpf_enable_instrumentation(void) extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; +extern const struct file_operations bpf_iter_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ @@ -1145,6 +1146,7 @@ void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); +bool bpf_link_is_iter(struct bpf_link *link); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From e5158d987b72c3f318b4b52a01ac6f3997bd0c00 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:07 -0700 Subject: bpf: Implement common macros/helpers for target iterators Macro DEFINE_BPF_ITER_FUNC is implemented so target can define an init function to capture the BTF type which represents the target. The bpf_iter_meta is a structure holding meta data, common to all targets in the bpf program. Additional marker functions are called before or after bpf_seq_read() show()/next()/stop() callback functions to help calculate precise seq_num and whether call bpf_prog inside stop(). Two functions, bpf_iter_get_info() and bpf_iter_run_prog(), are implemented so target can get needed information from bpf_iter infrastructure and can run the program. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175907.2475956-1-yhs@fb.com --- include/linux/bpf.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b06653ab3476..ffe0b9b669bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1129,6 +1129,9 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); #define BPF_ITER_FUNC_PREFIX "__bpf_iter__" +#define DEFINE_BPF_ITER_FUNC(target, args...) \ + extern int __bpf_iter__ ## target(args); \ + int __init __bpf_iter__ ## target(args) { return 0; } typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); @@ -1141,12 +1144,20 @@ struct bpf_iter_reg { u32 seq_priv_size; }; +struct bpf_iter_meta { + __bpf_md_ptr(struct seq_file *, seq); + u64 session_id; + u64 seq_num; +}; + int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); +struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); +int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From 6086d29def80edd78f9832ea6eafa74e3818f6a7 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:09 -0700 Subject: bpf: Add bpf_map iterator Implement seq_file operations to traverse all bpf_maps. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175909.2476096-1-yhs@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 ffe0b9b669bf..363ab0751967 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1082,6 +1082,7 @@ int generic_map_update_batch(struct bpf_map *map, int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); +struct bpf_map *bpf_map_get_curr_or_next(u32 *id); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 138d0be35b141e09f6b267c6ae4094318d4e4491 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:10 -0700 Subject: net: bpf: Add netlink and ipv6_route bpf_iter targets This patch added netlink and ipv6_route targets, using the same seq_ops (except show() and minor changes for stop()) for /proc/net/{netlink,ipv6_route}. The net namespace for these targets are the current net namespace at file open stage, similar to /proc/net/{netlink,ipv6_route} reference counting the net namespace at seq_file open stage. Since module is not supported for now, ipv6_route is supported only if the IPV6 is built-in, i.e., not compiled as a module. The restriction can be lifted once module is properly supported for bpf_iter. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175910.2476329-1-yhs@fb.com --- include/linux/proc_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 45c05fd9c99d..03953c59807d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -105,6 +105,9 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data); extern struct pid *tgid_pidfd_to_pid(const struct file *file); +extern int bpf_iter_init_seq_net(void *priv_data); +extern void bpf_iter_fini_seq_net(void *priv_data); + #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must -- cgit v1.2.3 From b121b341e5983bdccf7a5d6cf9236a45c965a31f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:12 -0700 Subject: bpf: Add PTR_TO_BTF_ID_OR_NULL support Add bpf_reg_type PTR_TO_BTF_ID_OR_NULL support. For tracing/iter program, the bpf program context definition, e.g., for previous bpf_map target, looks like struct bpf_iter__bpf_map { struct bpf_iter_meta *meta; struct bpf_map *map; }; The kernel guarantees that meta is not NULL, but map pointer maybe NULL. The NULL map indicates that all objects have been traversed, so bpf program can take proper action, e.g., do final aggregation and/or send final report to user space. Add btf_id_or_null_non0_off to prog->aux structure, to indicate that if the context access offset is not 0, set to PTR_TO_BTF_ID_OR_NULL instead of PTR_TO_BTF_ID. This bit is set for tracing/iter program. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175912.2476576-1-yhs@fb.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 363ab0751967..cf4b6e44f2bc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -320,6 +320,7 @@ enum bpf_reg_type { PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ PTR_TO_BTF_ID, /* reg points to kernel struct */ + PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -658,6 +659,7 @@ struct bpf_prog_aux { bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; + bool btf_id_or_null_non0_off; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; -- cgit v1.2.3 From 5a63b7ba50fd6b7a897bf9353dbf31d579cfe116 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 8 May 2020 18:47:20 +0300 Subject: power: supply: add battery parameters Add parsing of new device-tree battery bindings. - trickle-charge-current-microamp - precharge-upper-limit-microvolt - re-charge-voltage-microvolt - over-voltage-threshold-microvolt Signed-off-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 6a34df65d4d1..1f60731ec7fe 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -346,8 +346,12 @@ struct power_supply_battery_info { int charge_full_design_uah; /* microAmp-hours */ int voltage_min_design_uv; /* microVolts */ int voltage_max_design_uv; /* microVolts */ + int tricklecharge_current_ua; /* microAmps */ int precharge_current_ua; /* microAmps */ + int precharge_voltage_max_uv; /* microVolts */ int charge_term_current_ua; /* microAmps */ + int charge_restart_voltage_uv; /* microVolts */ + int overvoltage_limit_uv; /* microVolts */ int constant_charge_current_max_ua; /* microAmps */ int constant_charge_voltage_max_uv; /* microVolts */ int factory_internal_resistance_uohm; /* microOhms */ -- cgit v1.2.3 From e7bb7ecefa817543e11fa3c1c3e55deb90b02e6c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:59:21 -0500 Subject: IB/mlx4: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Jakub Kicinski --- include/linux/mlx4/qp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 8e2828d48d7f..9db93e487496 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -362,7 +362,7 @@ struct mlx4_wqe_datagram_seg { struct mlx4_wqe_lso_seg { __be32 mss_hdr_size; - __be32 header[0]; + __be32 header[]; }; enum mlx4_wqe_bind_seg_flags2 { -- cgit v1.2.3 From 7d374b20908338c9fbb03ea8022a11f3b3e0e55f Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Sun, 10 May 2020 18:30:37 +0300 Subject: interconnect: Add helpers for enabling/disabling a path There is a repeated pattern in multiple drivers where they want to switch the bandwidth between zero and some other value. This is happening often in the suspend/resume callbacks. Let's add helper functions to enable and disable the path, so that callers don't have to take care of remembering the bandwidth values and handle this in the framework instead. With this patch the users can call icc_disable() and icc_enable() to lower their bandwidth request to zero and then restore it back to it's previous value. Suggested-by: Evan Green Suggested-by: Bjorn Andersson Signed-off-by: Georgi Djakov Reviewed-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20200507120846.8354-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index 770692421f4c..e56a95e3cf25 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -30,6 +30,8 @@ struct icc_path *icc_get(struct device *dev, const int src_id, struct icc_path *of_icc_get(struct device *dev, const char *name); struct icc_path *devm_of_icc_get(struct device *dev, const char *name); void icc_put(struct icc_path *path); +int icc_enable(struct icc_path *path); +int icc_disable(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); @@ -57,6 +59,16 @@ static inline void icc_put(struct icc_path *path) { } +static inline int icc_enable(struct icc_path *path) +{ + return 0; +} + +static inline int icc_disable(struct icc_path *path) +{ + return 0; +} + static inline int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) { return 0; -- cgit v1.2.3 From a68a813836e12b15715d9101309899123c250302 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:30 +0200 Subject: net: phy: Add cable test support to state machine Running a cable test is desruptive to normal operation of the PHY and can take a 5 to 10 seconds to complete. The RTNL lock cannot be held for this amount of time, and add a new state to the state machine for running a cable test. The driver is expected to implement two functions. The first is used to start a cable test. Once the test has started, it should return. The second function is called once per second, or on interrupt to check if the cable test is complete, and to allow the PHY to report the status. v2: Rename phy_cable_test_abort to phy_abort_cable_test Return different extack when already running test Use phy_init_hw() to reset the PHY Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index a2b91b5f9d0a..632403fc34f4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -372,6 +373,12 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * - irq or timer will set NOLINK if link goes down * - phy_stop moves to HALTED * + * CABLETEST: PHY is performing a cable test. Packet reception/sending + * is not expected to work, carrier will be indicated as down. PHY will be + * poll once per second, or on interrupt for it current state. + * Once complete, move to UP to restart the PHY. + * - phy_stop aborts the running test and moves to HALTED + * * HALTED: PHY is up, but no polling or interrupts are done. Or * PHY is in an error state. * - phy_start moves to UP @@ -383,6 +390,7 @@ enum phy_state { PHY_UP, PHY_RUNNING, PHY_NOLINK, + PHY_CABLETEST, }; /** @@ -689,6 +697,13 @@ struct phy_driver { int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); + /* Start a cable test */ + int (*cable_test_start)(struct phy_device *dev); + /* Once per second, or on interrupt, request the status of the + * test. + */ + int (*cable_test_get_status)(struct phy_device *dev, bool *finished); + /* Get statistics from the phy using ethtool */ int (*get_sset_count)(struct phy_device *dev); void (*get_strings)(struct phy_device *dev, u8 *data); @@ -1227,6 +1242,19 @@ int phy_speed_up(struct phy_device *phydev); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); +#if IS_ENABLED(CONFIG_PHYLIB) +int phy_start_cable_test(struct phy_device *phydev, + struct netlink_ext_ack *extack); +#else +static inline +int phy_start_cable_test(struct phy_device *phydev, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); + return -EOPNOTSUPP; +} +#endif + static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); -- cgit v1.2.3 From 97c22438963a7484c05c59ab6654e30f0a3e9288 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:32 +0200 Subject: net: phy: Add support for polling cable test Some PHYs are not capable of generating interrupts when a cable test finished. They do however support interrupts for normal operations, like link up/down. As such, the PHY state machine would normally not poll the PHY. Add support for indicating the PHY state machine must poll the PHY when performing a cable test. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 632403fc34f4..f58eee735a45 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -79,6 +79,7 @@ extern const int phy_10gbit_features_array[1]; #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 +#define PHY_POLL_CABLE_TEST 0x00000004 #define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ @@ -1061,6 +1062,10 @@ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) */ static inline bool phy_polling_mode(struct phy_device *phydev) { + if (phydev->state == PHY_CABLETEST) + if (phydev->drv->flags & PHY_POLL_CABLE_TEST) + return true; + return phydev->irq == PHY_POLL; } -- cgit v1.2.3 From 1dd3f212af30b42c90ba252c165f2f6d2ddf5230 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:36 +0200 Subject: net: ethtool: Add infrastructure for reporting cable test results Provide infrastructure for PHY drivers to report the cable test results. A netlink skb is associated to the phydev. Helpers will be added which can add results to this skb. Once the test has finished the results are sent to user space. When netlink ethtool is not part of the kernel configuration stubs are provided. It is also impossible to trigger a cable test, so the error code returned by the alloc function is of no consequence. v2: Include the status complete in the netlink notification message v4: Replace -EINVAL with -EMSGSIZE Signed-off-by: Andrew Lunn Reviewed-by: Michal Kubecek Signed-off-by: Jakub Kicinski --- include/linux/ethtool_netlink.h | 20 ++++++++++++++++++++ include/linux/phy.h | 5 +++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index d01b77887f82..7d763ba22f6f 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -14,4 +14,24 @@ enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; +struct phy_device; + +#if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) +int ethnl_cable_test_alloc(struct phy_device *phydev); +void ethnl_cable_test_free(struct phy_device *phydev); +void ethnl_cable_test_finished(struct phy_device *phydev); +#else +static inline int ethnl_cable_test_alloc(struct phy_device *phydev) +{ + return -ENOTSUPP; +} + +static inline void ethnl_cable_test_free(struct phy_device *phydev) +{ +} + +static inline void ethnl_cable_test_finished(struct phy_device *phydev) +{ +} +#endif /* IS_ENABLED(ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index f58eee735a45..169fae4249a9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -523,6 +523,11 @@ struct phy_device { /* For use by PHYs inside the same package that need a shared state. */ struct phy_package_shared *shared; + /* Reporting cable test results */ + struct sk_buff *skb; + void *ehdr; + struct nlattr *nest; + /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; -- cgit v1.2.3 From 1e2dc14509fd072739e4bab98ac42317267dbad6 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:37 +0200 Subject: net: ethtool: Add helpers for reporting test results The PHY drivers can use these helpers for reporting the results. The results get translated into netlink attributes which are added to the pre-allocated skbuf. v3: Poison phydev->skb Return -EMSGSIZE when ethnl_bcastmsg_put() fails Return valid error code when nla_nest_start() fails Use u8 for results Actually put u32 length into message v4: s/ENOTSUPP/EOPNOTSUPP/g Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Michal Kubecek Signed-off-by: Jakub Kicinski --- include/linux/ethtool_netlink.h | 15 ++++++++++++++- include/linux/phy.h | 4 ++++ 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 7d763ba22f6f..e317fc99565e 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -20,10 +20,12 @@ struct phy_device; int ethnl_cable_test_alloc(struct phy_device *phydev); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); +int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); +int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); #else static inline int ethnl_cable_test_alloc(struct phy_device *phydev) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void ethnl_cable_test_free(struct phy_device *phydev) @@ -33,5 +35,16 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev) static inline void ethnl_cable_test_finished(struct phy_device *phydev) { } +static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, + u8 result) +{ + return -EOPNOTSUPP; +} + +static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, + u8 pair, u32 cm) +{ + return -EOPNOTSUPP; +} #endif /* IS_ENABLED(ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 169fae4249a9..5d8ff5428010 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1265,6 +1265,10 @@ int phy_start_cable_test(struct phy_device *phydev, } #endif +int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result); +int phy_cable_test_fault_length(struct phy_device *phydev, u8 pair, + u16 cm); + static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); -- cgit v1.2.3 From b6ca09cb156d349e6fdde8a8466ec15b902d1419 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:59:35 -0500 Subject: net/mlx5: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- include/linux/mlx5/mlx5_ifc.h | 66 +++++++++++++++++++++---------------------- include/linux/mlx5/qp.h | 2 +- 3 files changed, 35 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 267dfcc5493e..24e04901f92e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -201,7 +201,7 @@ struct mlx5_rsc_debug { void *object; enum dbg_rsc_type type; struct dentry *root; - struct mlx5_field_desc fields[0]; + struct mlx5_field_desc fields[]; }; enum mlx5_dev_event { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fb243848132d..c9dd6e99ad56 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1703,7 +1703,7 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_140[0x4c0]; - struct mlx5_ifc_cmd_pas_bits pas[0]; + struct mlx5_ifc_cmd_pas_bits pas[]; }; struct mlx5_ifc_rq_num_bits { @@ -1921,7 +1921,7 @@ struct mlx5_ifc_resource_dump_menu_segment_bits { 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_menu_record_bits record[]; }; struct mlx5_ifc_resource_dump_resource_segment_bits { @@ -1933,7 +1933,7 @@ struct mlx5_ifc_resource_dump_resource_segment_bits { u8 index2[0x20]; - u8 payload[0][0x20]; + u8 payload[][0x20]; }; struct mlx5_ifc_resource_dump_terminate_segment_bits { @@ -3010,7 +3010,7 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_1200[0x600]; - union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[0]; + union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; }; enum { @@ -3303,7 +3303,7 @@ struct mlx5_ifc_rqtc_bits { u8 reserved_at_e0[0x6a0]; - struct mlx5_ifc_rq_num_bits rq_num[0]; + struct mlx5_ifc_rq_num_bits rq_num[]; }; enum { @@ -3415,7 +3415,7 @@ struct mlx5_ifc_nic_vport_context_bits { u8 reserved_at_7e0[0x20]; - u8 current_uc_mac_address[0][0x40]; + u8 current_uc_mac_address[][0x40]; }; enum { @@ -4338,7 +4338,7 @@ struct mlx5_ifc_query_xrc_srq_out_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_xrc_srq_in_bits { @@ -4616,7 +4616,7 @@ struct mlx5_ifc_query_srq_out_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_srq_in_bits { @@ -4827,7 +4827,7 @@ struct mlx5_ifc_query_qp_out_bits { u8 reserved_at_800[0x80]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_qp_in_bits { @@ -5160,7 +5160,7 @@ struct mlx5_ifc_query_hca_vport_pkey_out_bits { u8 reserved_at_40[0x40]; - struct mlx5_ifc_pkey_bits pkey[0]; + struct mlx5_ifc_pkey_bits pkey[]; }; struct mlx5_ifc_query_hca_vport_pkey_in_bits { @@ -5196,7 +5196,7 @@ struct mlx5_ifc_query_hca_vport_gid_out_bits { u8 gids_num[0x10]; u8 reserved_at_70[0x10]; - struct mlx5_ifc_array128_auto_bits gid[0]; + struct mlx5_ifc_array128_auto_bits gid[]; }; struct mlx5_ifc_query_hca_vport_gid_in_bits { @@ -5464,7 +5464,7 @@ struct mlx5_ifc_query_flow_counter_out_bits { u8 reserved_at_40[0x40]; - struct mlx5_ifc_traffic_counter_bits flow_statistics[0]; + struct mlx5_ifc_traffic_counter_bits flow_statistics[]; }; struct mlx5_ifc_query_flow_counter_in_bits { @@ -5558,7 +5558,7 @@ struct mlx5_ifc_query_eq_out_bits { u8 reserved_at_300[0x580]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_eq_in_bits { @@ -5583,7 +5583,7 @@ struct mlx5_ifc_packet_reformat_context_in_bits { u8 reserved_at_20[0x10]; u8 reformat_data[2][0x8]; - u8 more_reformat_data[0][0x8]; + u8 more_reformat_data[][0x8]; }; struct mlx5_ifc_query_packet_reformat_context_out_bits { @@ -5594,7 +5594,7 @@ struct mlx5_ifc_query_packet_reformat_context_out_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context[0]; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context[]; }; struct mlx5_ifc_query_packet_reformat_context_in_bits { @@ -5833,7 +5833,7 @@ struct mlx5_ifc_query_cq_out_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_cq_in_bits { @@ -6440,7 +6440,7 @@ struct mlx5_ifc_modify_cq_in_bits { u8 reserved_at_300[0x580]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_modify_cong_status_out_bits { @@ -6504,7 +6504,7 @@ struct mlx5_ifc_manage_pages_out_bits { u8 reserved_at_60[0x20]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; enum { @@ -6526,7 +6526,7 @@ struct mlx5_ifc_manage_pages_in_bits { u8 input_num_entries[0x20]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_mad_ifc_out_bits { @@ -7481,7 +7481,7 @@ struct mlx5_ifc_create_xrc_srq_in_bits { u8 reserved_at_300[0x580]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_tis_out_bits { @@ -7557,7 +7557,7 @@ struct mlx5_ifc_create_srq_in_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_sq_out_bits { @@ -7718,7 +7718,7 @@ struct mlx5_ifc_create_qp_in_bits { u8 wq_umem_valid[0x1]; u8 reserved_at_861[0x1f]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_psv_out_bits { @@ -7789,7 +7789,7 @@ struct mlx5_ifc_create_mkey_in_bits { u8 reserved_at_320[0x560]; - u8 klm_pas_mtt[0][0x20]; + u8 klm_pas_mtt[][0x20]; }; enum { @@ -7922,7 +7922,7 @@ struct mlx5_ifc_create_eq_in_bits { u8 reserved_at_3c0[0x4c0]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_dct_out_bits { @@ -7979,7 +7979,7 @@ struct mlx5_ifc_create_cq_in_bits { u8 cq_umem_valid[0x1]; u8 reserved_at_2e1[0x59f]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_config_int_moderation_out_bits { @@ -8335,7 +8335,7 @@ struct mlx5_ifc_access_register_out_bits { u8 reserved_at_40[0x40]; - u8 register_data[0][0x20]; + u8 register_data[][0x20]; }; enum { @@ -8355,7 +8355,7 @@ struct mlx5_ifc_access_register_in_bits { u8 argument[0x20]; - u8 register_data[0][0x20]; + u8 register_data[][0x20]; }; struct mlx5_ifc_sltp_reg_bits { @@ -9372,7 +9372,7 @@ struct mlx5_ifc_cmd_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 command[0][0x20]; + u8 command[][0x20]; }; struct mlx5_ifc_cmd_if_box_bits { @@ -9666,7 +9666,7 @@ struct mlx5_ifc_mcqi_reg_bits { u8 reserved_at_a0[0x10]; u8 data_size[0x10]; - union mlx5_ifc_mcqi_reg_data_bits data[0]; + union mlx5_ifc_mcqi_reg_data_bits data[]; }; struct mlx5_ifc_mcc_reg_bits { @@ -10252,7 +10252,7 @@ struct mlx5_ifc_umem_bits { u8 num_of_mtt[0x40]; - struct mlx5_ifc_mtt_bits mtt[0]; + struct mlx5_ifc_mtt_bits mtt[]; }; struct mlx5_ifc_uctx_bits { @@ -10377,7 +10377,7 @@ struct mlx5_ifc_mtrc_stdb_bits { u8 reserved_at_4[0x4]; u8 read_size[0x18]; u8 start_offset[0x20]; - u8 string_db_data[0]; + u8 string_db_data[]; }; struct mlx5_ifc_mtrc_ctrl_bits { @@ -10431,7 +10431,7 @@ struct mlx5_ifc_query_esw_functions_out_bits { struct mlx5_ifc_host_params_context_bits host_params_context; u8 reserved_at_280[0x180]; - u8 host_sf_enable[0][0x40]; + u8 host_sf_enable[][0x40]; }; struct mlx5_ifc_sf_partition_bits { @@ -10451,7 +10451,7 @@ struct mlx5_ifc_query_sf_partitions_out_bits { u8 reserved_at_60[0x20]; - struct mlx5_ifc_sf_partition_bits sf_partition[0]; + struct mlx5_ifc_sf_partition_bits sf_partition[]; }; struct mlx5_ifc_query_sf_partitions_in_bits { diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index f23eb18526fe..1af5e460b5f6 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -408,7 +408,7 @@ struct mlx5_wqe_signature_seg { struct mlx5_wqe_inline_seg { __be32 byte_count; - __be32 data[0]; + __be32 data[]; }; enum mlx5_sig_type { -- cgit v1.2.3 From ac02a451a6148bb9c395b39783ce7299eddf4f31 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 10 May 2020 19:37:43 +0300 Subject: net: dsa: sja1105: implement cross-chip bridging operations sja1105 uses dsa_8021q for DSA tagging, a format which is VLAN at heart and which is compatible with cascading. A complete description of this tagging format is in net/dsa/tag_8021q.c, but a quick summary is that each external-facing port tags incoming frames with a unique pvid, and this special VLAN is transmitted as tagged towards the inside of the system, and as untagged towards the exterior. The tag encodes the switch id and the source port index. This means that cross-chip bridging for dsa_8021q only entails adding the dsa_8021q pvids of one switch to the RX filter of the other switches. Everything else falls naturally into place, as long as the bottom-end of ports (the leaves in the tree) is comprised exclusively of dsa_8021q-compatible (i.e. sja1105 switches). Otherwise, there would be a chance that a front-panel switch transmits a packet tagged with a dsa_8021q header, header which it wouldn't be able to remove, and which would hence "leak" out. The only use case I tested (due to lack of board availability) was when the sja1105 switches are part of disjoint trees (however, this doesn't change the fact that multiple sja1105 switches still need unique switch identifiers in such a system). But in principle, even "true" single-tree setups (with DSA links) should work just as fine, except for a small change which I can't test: dsa_towards_port should be used instead of dsa_upstream_port (I made the assumption that the routing port that any sja1105 should use towards its neighbours is the CPU port. That might not hold true in other setups). Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/dsa/8021q.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index c620d9139c28..b8daaec0896e 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -12,11 +12,33 @@ struct sk_buff; struct net_device; struct packet_type; +struct dsa_8021q_crosschip_link { + struct list_head list; + int port; + struct dsa_switch *other_ds; + int other_port; + refcount_t refcount; +}; + #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, bool enabled); +int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, bool enabled); + +int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links); + +int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links); + struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); @@ -36,6 +58,29 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, return 0; } +int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, bool enabled) +{ + return 0; +} + +int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links) +{ + return 0; +} + +int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links) +{ + return 0; +} + struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci) { -- cgit v1.2.3 From 479da1f538a2f3547e15f9d5922c611b69ec2fbc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Noralf=20Tr=C3=B8nnes?= Date: Sat, 9 May 2020 16:16:10 +0200 Subject: backlight: Add backlight_device_get_by_name() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a way to lookup a backlight device based on its name. Will be used by a USB display gadget getting the name from configfs. Signed-off-by: Noralf Trønnes Reviewed-by: Sam Ravnborg Reviewed-by: Daniel Thompson Acked-by: Jingoo Han Signed-off-by: Lee Jones --- include/linux/backlight.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index c7d6b2e8c3b5..56e4580d4f55 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -190,6 +190,7 @@ extern void backlight_force_update(struct backlight_device *bd, extern int backlight_register_notifier(struct notifier_block *nb); extern int backlight_unregister_notifier(struct notifier_block *nb); extern struct backlight_device *backlight_device_get_by_type(enum backlight_type type); +struct backlight_device *backlight_device_get_by_name(const char *name); extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned long brightness); #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev) -- cgit v1.2.3 From 83c411c29b90b7de505a2fe1d655293c95f8ba90 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 28 Apr 2020 11:42:54 +0200 Subject: mtd: rawnand: timings: Add mode information to the timings structure Convert the timings union into a structure containing the mode and the actual values. The values are still a union in prevision of the addition of the NVDDR modes. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200428094302.14624-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 1e76196f9829..21873168ba4d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -491,13 +491,17 @@ enum nand_data_interface_type { /** * struct nand_data_interface - NAND interface timing * @type: type of the timing - * @timings: The timing, type according to @type + * @timings: The timing information + * @timings.mode: Timing mode as defined in the specification * @timings.sdr: Use it when @type is %NAND_SDR_IFACE. */ struct nand_data_interface { enum nand_data_interface_type type; - union { - struct nand_sdr_timings sdr; + struct nand_timings { + unsigned int mode; + union { + struct nand_sdr_timings sdr; + }; } timings; }; -- cgit v1.2.3 From 9e3307a169537a6adc30b13bf9063e94990a5493 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 3 May 2020 17:53:37 +0200 Subject: mtd: Add support for emulated SLC mode on MLC NANDs MLC NANDs can be made a bit more reliable if we only program the lower page of each pair. At least, this solves the paired-pages corruption issue. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200503155341.16712-5-miquel.raynal@bootlin.com --- include/linux/mtd/mtd.h | 7 ++++++- include/linux/mtd/partitions.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 2d1f4a61f4ac..157357ec1441 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -200,6 +200,8 @@ struct mtd_debug_info { * * @node: list node used to add an MTD partition to the parent partition list * @offset: offset of the partition relatively to the parent offset + * @size: partition size. Should be equal to mtd->size unless + * MTD_SLC_ON_MLC_EMULATION is set * @flags: original flags (before the mtdpart logic decided to tweak them based * on flash constraints, like eraseblock/pagesize alignment) * @@ -209,6 +211,7 @@ struct mtd_debug_info { struct mtd_part { struct list_head node; u64 offset; + u64 size; u32 flags; }; @@ -622,7 +625,9 @@ static inline uint32_t mtd_mod_by_ws(uint64_t sz, struct mtd_info *mtd) static inline int mtd_wunit_per_eb(struct mtd_info *mtd) { - return mtd->erasesize / mtd->writesize; + struct mtd_info *master = mtd_get_master(mtd); + + return master->erasesize / mtd->writesize; } static inline int mtd_offset_to_wunit(struct mtd_info *mtd, loff_t offs) diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index e545c050d3e8..b74a539ec581 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -37,6 +37,7 @@ * master MTD flag set for the corresponding MTD partition. * For example, to force a read-only partition, simply adding * MTD_WRITEABLE to the mask_flags will do the trick. + * add_flags: contains flags to add to the parent flags * * Note: writeable partitions require their size and offset be * erasesize aligned (e.g. use MTDPART_OFS_NEXTBLK). @@ -48,6 +49,7 @@ struct mtd_partition { uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ + uint32_t add_flags; /* flags to add to the partition */ struct device_node *of_node; }; -- cgit v1.2.3 From dd6ed5c9890b759ba1b56697b9f3f50e71909e43 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:29 +0200 Subject: mtd: rawnand: Translate obscure bitfields into readable macros Use the BIT() macro instead of defining a 8-digit value. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 21873168ba4d..4b58de842340 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -129,36 +129,36 @@ enum nand_ecc_algo { * features. */ /* Buswidth is 16 bit */ -#define NAND_BUSWIDTH_16 0x00000002 +#define NAND_BUSWIDTH_16 BIT(1) /* Chip has cache program function */ -#define NAND_CACHEPRG 0x00000008 +#define NAND_CACHEPRG BIT(3) /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support * autoincrement. */ -#define NAND_NEED_READRDY 0x00000100 +#define NAND_NEED_READRDY BIT(8) /* Chip does not allow subpage writes */ -#define NAND_NO_SUBPAGE_WRITE 0x00000200 +#define NAND_NO_SUBPAGE_WRITE BIT(9) /* Device is one of 'new' xD cards that expose fake nand command set */ -#define NAND_BROKEN_XD 0x00000400 +#define NAND_BROKEN_XD BIT(10) /* Device behaves just like nand, but is readonly */ -#define NAND_ROM 0x00000800 +#define NAND_ROM BIT(11) /* Device supports subpage reads */ -#define NAND_SUBPAGE_READ 0x00001000 +#define NAND_SUBPAGE_READ BIT(12) /* * Some MLC NANDs need data scrambling to limit bitflips caused by repeated * patterns. */ -#define NAND_NEED_SCRAMBLING 0x00002000 +#define NAND_NEED_SCRAMBLING BIT(13) /* Device needs 3rd row address cycle */ -#define NAND_ROW_ADDR_3 0x00004000 +#define NAND_ROW_ADDR_3 BIT(14) /* Options valid for Samsung large page devices */ #define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG @@ -173,9 +173,9 @@ enum nand_ecc_algo { * Position within the block: Each of these pages needs to be checked for a * bad block marking pattern. */ -#define NAND_BBM_FIRSTPAGE 0x01000000 -#define NAND_BBM_SECONDPAGE 0x02000000 -#define NAND_BBM_LASTPAGE 0x04000000 +#define NAND_BBM_FIRSTPAGE BIT(24) +#define NAND_BBM_SECONDPAGE BIT(25) +#define NAND_BBM_LASTPAGE BIT(26) /* Position within the OOB data of the page */ #define NAND_BBM_POS_SMALL 5 @@ -183,21 +183,21 @@ enum nand_ecc_algo { /* Non chip related options */ /* This option skips the bbt scan during initialization. */ -#define NAND_SKIP_BBTSCAN 0x00010000 +#define NAND_SKIP_BBTSCAN BIT(16) /* Chip may not exist, so silence any errors in scan */ -#define NAND_SCAN_SILENT_NODEV 0x00040000 +#define NAND_SCAN_SILENT_NODEV BIT(18) /* * Autodetect nand buswidth with readid/onfi. * This suppose the driver will configure the hardware in 8 bits mode * when calling nand_scan_ident, and update its configuration * before calling nand_scan_tail. */ -#define NAND_BUSWIDTH_AUTO 0x00080000 +#define NAND_BUSWIDTH_AUTO BIT(19) /* * This option could be defined by controller drivers to protect against * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers */ -#define NAND_USE_BOUNCE_BUFFER 0x00100000 +#define NAND_USE_BOUNCE_BUFFER BIT(20) /* * In case your controller is implementing ->legacy.cmd_ctrl() and is relying @@ -207,20 +207,20 @@ enum nand_ecc_algo { * If your controller already takes care of this delay, you don't need to set * this flag. */ -#define NAND_WAIT_TCCS 0x00200000 +#define NAND_WAIT_TCCS BIT(21) /* * Whether the NAND chip is a boot medium. Drivers might use this information * to select ECC algorithms supported by the boot ROM or similar restrictions. */ -#define NAND_IS_BOOT_MEDIUM 0x00400000 +#define NAND_IS_BOOT_MEDIUM BIT(22) /* * Do not try to tweak the timings at runtime. This is needed when the * controller initializes the timings on itself or when it relies on * configuration done by the bootloader. */ -#define NAND_KEEP_TIMINGS 0x00800000 +#define NAND_KEEP_TIMINGS BIT(23) /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 -- cgit v1.2.3 From 96d627bdf112d116a79c86435550cd18b9a9d82b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:30 +0200 Subject: mtd: rawnand: Reorder the nand_chip->options flags These flags are in a strange order, reorder the list, add spaces when it is relevant, pack definitions that are related. There is no functional change. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-3-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 57 ++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 4b58de842340..e70fea67030b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -118,20 +118,25 @@ enum nand_ecc_algo { #define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) #define NAND_ECC_MAXIMIZE BIT(1) -/* - * When using software implementation of Hamming, we can specify which byte - * ordering should be used. - */ -#define NAND_ECC_SOFT_HAMMING_SM_ORDER BIT(2) - /* * Option constants for bizarre disfunctionality and real * features. */ + /* Buswidth is 16 bit */ #define NAND_BUSWIDTH_16 BIT(1) + +/* + * When using software implementation of Hamming, we can specify which byte + * ordering should be used. + */ +#define NAND_ECC_SOFT_HAMMING_SM_ORDER BIT(2) + /* Chip has cache program function */ #define NAND_CACHEPRG BIT(3) +/* Options valid for Samsung large page devices */ +#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG + /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support @@ -150,6 +155,8 @@ enum nand_ecc_algo { /* Device supports subpage reads */ #define NAND_SUBPAGE_READ BIT(12) +/* Macros to identify the above */ +#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) /* * Some MLC NANDs need data scrambling to limit bitflips caused by repeated @@ -160,32 +167,12 @@ enum nand_ecc_algo { /* Device needs 3rd row address cycle */ #define NAND_ROW_ADDR_3 BIT(14) -/* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG - -/* Macros to identify the above */ -#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) - -/* - * There are different places where the manufacturer stores the factory bad - * block markers. - * - * Position within the block: Each of these pages needs to be checked for a - * bad block marking pattern. - */ -#define NAND_BBM_FIRSTPAGE BIT(24) -#define NAND_BBM_SECONDPAGE BIT(25) -#define NAND_BBM_LASTPAGE BIT(26) - -/* Position within the OOB data of the page */ -#define NAND_BBM_POS_SMALL 5 -#define NAND_BBM_POS_LARGE 0 - /* Non chip related options */ /* This option skips the bbt scan during initialization. */ #define NAND_SKIP_BBTSCAN BIT(16) /* Chip may not exist, so silence any errors in scan */ #define NAND_SCAN_SILENT_NODEV BIT(18) + /* * Autodetect nand buswidth with readid/onfi. * This suppose the driver will configure the hardware in 8 bits mode @@ -193,6 +180,7 @@ enum nand_ecc_algo { * before calling nand_scan_tail. */ #define NAND_BUSWIDTH_AUTO BIT(19) + /* * This option could be defined by controller drivers to protect against * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers @@ -222,11 +210,26 @@ enum nand_ecc_algo { */ #define NAND_KEEP_TIMINGS BIT(23) +/* + * There are different places where the manufacturer stores the factory bad + * block markers. + * + * Position within the block: Each of these pages needs to be checked for a + * bad block marking pattern. + */ +#define NAND_BBM_FIRSTPAGE BIT(24) +#define NAND_BBM_SECONDPAGE BIT(25) +#define NAND_BBM_LASTPAGE BIT(26) + /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 +/* Position within the OOB data of the page */ +#define NAND_BBM_POS_SMALL 5 +#define NAND_BBM_POS_LARGE 0 + /** * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name -- cgit v1.2.3 From ce8148d7b8f204a18188e3cd7386c8dddbb461a1 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:31 +0200 Subject: mtd: rawnand: Rename a NAND chip option NAND controller drivers can set the NAND_USE_BOUNCE_BUFFER flag to a chip 'option' field. With this flag, the core is responsible of providing DMA-able buffers. The current behavior is to not force the use of a bounce buffer when the core thinks this is not needed. So in the end the name is a bit misleading, because in theory we will always have a DMA buffer but in practice it will not always be a bounce buffer. Rename this flag NAND_USES_DMA to be more accurate. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-4-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e70fea67030b..d1f5c5258e35 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -185,7 +185,7 @@ enum nand_ecc_algo { * This option could be defined by controller drivers to protect against * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers */ -#define NAND_USE_BOUNCE_BUFFER BIT(20) +#define NAND_USES_DMA BIT(20) /* * In case your controller is implementing ->legacy.cmd_ctrl() and is relying -- cgit v1.2.3 From b451f5beece3f5556920992e7498d23f6da6ef6e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:36 +0200 Subject: mtd: rawnand: Give the possibility to verify a read operation is supported This can be used to discriminate between two path in the parameter page detection: use data_in cycles (like before) if supported, use the CHANGE READ COLUMN command otherwise. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-9-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index d1f5c5258e35..70380c91731c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1363,7 +1363,7 @@ int nand_change_write_column_op(struct nand_chip *chip, unsigned int offset_in_page, const void *buf, unsigned int len, bool force_8bit); int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, - bool force_8bit); + bool force_8bit, bool check_only); int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); -- cgit v1.2.3 From 658beb6639606268bd48eb7de7cf308d6b10600f Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:39 +0200 Subject: mtd: rawnand: Expose monolithic read/write_page_raw() helpers The current nand_read/write_page_raw() helpers are already widely used but do not fit the purpose of "constrained" controllers which cannot, for instance, separate command/address cycles with data cycles. Workaround this issue by proposing alternative helpers that can be used by these controller drivers instead. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-12-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 70380c91731c..406e9ff0f45c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1328,13 +1328,17 @@ int nand_read_oob_std(struct nand_chip *chip, int page); int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, u8 *subfeature_param); -/* Default read_page_raw implementation */ +/* read_page_raw implementations */ int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); +int nand_monolithic_read_page_raw(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); -/* Default write_page_raw implementation */ +/* write_page_raw implementations */ int nand_write_page_raw(struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); +int nand_monolithic_write_page_raw(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); -- cgit v1.2.3 From ec7cfc3d763c761ff1ad5a4e66c4f94098d7e161 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 11 May 2020 08:49:15 +0200 Subject: mtd: rawnand: Add a NAND_NO_BBM_QUIRK flag Some controllers with embedded ECC engines override the BBM marker with data or ECC bytes, thus making bad block detection through bad block marker impossible. Let's flag those chips so the core knows it shouldn't check the BBM and consider all blocks good. This should allow us to get rid of two implementers of the legacy.block_bad() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200511064917.6255-1-boris.brezillon@collabora.com --- include/linux/mtd/rawnand.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 406e9ff0f45c..0f45b6984ad1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -221,6 +221,14 @@ enum nand_ecc_algo { #define NAND_BBM_SECONDPAGE BIT(25) #define NAND_BBM_LASTPAGE BIT(26) +/* + * Some controllers with pipelined ECC engines override the BBM marker with + * data or ECC bytes, thus making bad block detection through bad block marker + * impossible. Let's flag those chips so the core knows it shouldn't check the + * BBM and consider all blocks good. + */ +#define NAND_NO_BBM_QUIRK BIT(27) + /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C -- cgit v1.2.3 From 913b99f70feb1cd9fb4bbcb302a029b4b9bee454 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:25:24 -0500 Subject: thunderbolt: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Mika Westerberg --- include/linux/thunderbolt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index ece782ef5466..ff397c0d5c07 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -80,7 +80,7 @@ struct tb { int index; enum tb_security_level security_level; size_t nboot_acl; - unsigned long privdata[0]; + unsigned long privdata[]; }; extern struct bus_type tb_bus_type; -- cgit v1.2.3 From 975cf23e3aa89588cbfc9ad6f2b23bd32af4edc7 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Thu, 7 May 2020 13:33:15 +0100 Subject: PCI: endpoint: Pass page size as argument to pci_epc_mem_init() pci_epc_mem_init() internally used page size equal to *PAGE_SIZE* to manage the address space so instead just pass the page size as a argument to pci_epc_mem_init(). Also make pci_epc_mem_init() as a C function instead of a macro function in preparation for adding support for pci-epc-mem core to handle multiple windows. Link: https://lore.kernel.org/r/1588854799-13710-5-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Lad Prabhakar Signed-off-by: Lorenzo Pieralisi Reviewed-by: Yoshihiro Shimoda Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index e0ed9d01f6e5..5bc1de65849e 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -137,9 +137,6 @@ struct pci_epc_features { #define devm_pci_epc_create(dev, ops) \ __devm_pci_epc_create((dev), (ops), THIS_MODULE) -#define pci_epc_mem_init(epc, phys_addr, size) \ - __pci_epc_mem_init((epc), (phys_addr), (size), PAGE_SIZE) - static inline void epc_set_drvdata(struct pci_epc *epc, void *data) { dev_set_drvdata(&epc->dev, data); @@ -195,6 +192,8 @@ unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); +int pci_epc_mem_init(struct pci_epc *epc, phys_addr_t base, + size_t size, size_t page_size); int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size, size_t page_size); void pci_epc_mem_exit(struct pci_epc *epc); -- cgit v1.2.3 From e33bcbab16d1c0dd85d72bec275308369ad901f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vesa=20J=C3=A4=C3=A4skel=C3=A4inen?= Date: Thu, 30 Apr 2020 15:37:09 +0300 Subject: tee: add support for session's client UUID generation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TEE Client API defines that from user space only information needed for specified login operations is group identifier for group based logins. REE kernel is expected to formulate trustworthy client UUID and pass that to TEE environment. REE kernel is required to verify that provided group identifier for group based logins matches calling processes group memberships. TEE specification only defines that the information passed from REE environment to TEE environment is encoded into on UUID. In order to guarantee trustworthiness of client UUID user space is not allowed to freely pass client UUID. UUIDv5 form is used encode variable amount of information needed for different login types. Signed-off-by: Vesa Jääskeläinen [jw: remove unused variable application_id] Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 1412e9cc79ce..8471b790e858 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -165,6 +165,22 @@ int tee_device_register(struct tee_device *teedev); */ void tee_device_unregister(struct tee_device *teedev); +/** + * tee_session_calc_client_uuid() - Calculates client UUID for session + * @uuid: Resulting UUID + * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) + * @connectuon_data: Connection data for opening session + * + * Based on connection method calculates UUIDv5 based client UUID. + * + * For group based logins verifies that calling process has specified + * credentials. + * + * @return < 0 on failure + */ +int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, + const u8 connection_data[TEE_IOCTL_UUID_LEN]); + /** * struct tee_shm - shared memory object * @ctx: context using the object -- cgit v1.2.3 From be957c886d92aa9caf0f63aee2c77d1497217d93 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 1 May 2020 15:20:45 -0300 Subject: mm/hmm: make hmm_range_fault return 0 or -1 hmm_vma_walk->last is supposed to be updated after every write to the pfns, so that it can be returned by hmm_range_fault(). However, this is not done consistently. Fortunately nothing checks the return code of hmm_range_fault() for anything other than error. More importantly last must be set before returning -EBUSY as it is used to prevent reading an output pfn as an input flags when the loop restarts. For clarity and simplicity make hmm_range_fault() return 0 or -ERRNO. Only set last when returning -EBUSY. Link: https://lore.kernel.org/r/2-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com Acked-by: Felix Kuehling Tested-by: Ralph Campbell Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 7475051100c7..0df27dd03d53 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -120,7 +120,7 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -long hmm_range_fault(struct hmm_range *range); +int hmm_range_fault(struct hmm_range *range); /* * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range -- cgit v1.2.3 From 5c8f3c4cf18ad007242bc370da54d45d4d4293dc Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 1 May 2020 15:20:47 -0300 Subject: mm/hmm: remove HMM_PFN_SPECIAL This is just an alias for HMM_PFN_ERROR, nothing cares that the error was because of a special page vs any other error case. Link: https://lore.kernel.org/r/4-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com Acked-by: Felix Kuehling Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 0df27dd03d53..81c302c884c0 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -44,10 +44,6 @@ enum hmm_pfn_flag_e { * Flags: * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() - * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the - * result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not - * be mirrored by a device, because the entry will never have HMM_PFN_VALID - * set and the pfn value is undefined. * * Driver provides values for none entry, error entry, and special entry. * Driver can alias (i.e., use same value) error and special, but @@ -56,12 +52,10 @@ enum hmm_pfn_flag_e { * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be: * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous, * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry, - * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one */ enum hmm_pfn_value_e { HMM_PFN_ERROR, HMM_PFN_NONE, - HMM_PFN_SPECIAL, HMM_PFN_VALUE_MAX }; @@ -110,8 +104,6 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang return NULL; if (entry == range->values[HMM_PFN_ERROR]) return NULL; - if (entry == range->values[HMM_PFN_SPECIAL]) - return NULL; if (!(entry & range->flags[HMM_PFN_VALID])) return NULL; return pfn_to_page(entry >> range->pfn_shift); -- cgit v1.2.3 From 2733ea144dcce789de20988c1056e228a07b1bff Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 1 May 2020 15:20:48 -0300 Subject: mm/hmm: remove the customizable pfn format from hmm_range_fault Presumably the intent here was that hmm_range_fault() could put the data into some HW specific format and thus avoid some work. However, nothing actually does that, and it isn't clear how anything actually could do that as hmm_range_fault() provides CPU addresses which must be DMA mapped. Perhaps there is some special HW that does not need DMA mapping, but we don't have any examples of this, and the theoretical performance win of avoiding an extra scan over the pfns array doesn't seem worth the complexity. Plus pfns needs to be scanned anyhow to sort out any DEVICE_PRIVATE pages. This version replaces the uint64_t with an usigned long containing a pfn and fixed flags. On input flags is filled with the HMM_PFN_REQ_* values, on successful output it is filled with HMM_PFN_* values, describing the state of the pages. amdgpu is simple to convert, it doesn't use snapshot and doesn't use per-page flags. nouveau uses only 16 hmm_pte entries at most (ie fits in a few cache lines), and it sweeps over its pfns array a couple of times anyhow. It also has a nasty call chain before it reaches the dma map and hardware suggesting performance isn't important: nouveau_svm_fault(): args.i.m.method = NVIF_VMM_V0_PFNMAP nouveau_range_fault() nvif_object_ioctl() client->driver->ioctl() struct nvif_driver nvif_driver_nvkm: .ioctl = nvkm_client_ioctl nvkm_ioctl() nvkm_ioctl_path() nvkm_ioctl_v0[type].func(..) nvkm_ioctl_mthd() nvkm_object_mthd() struct nvkm_object_func nvkm_uvmm: .mthd = nvkm_uvmm_mthd nvkm_uvmm_mthd() nvkm_uvmm_mthd_pfnmap() nvkm_vmm_pfn_map() nvkm_vmm_ptes_get_map() func == gp100_vmm_pgt_pfn struct nvkm_vmm_desc_func gp100_vmm_desc_spt: .pfn = gp100_vmm_pgt_pfn nvkm_vmm_iter() REF_PTES == func == gp100_vmm_pgt_pfn() dma_map_page() Link: https://lore.kernel.org/r/5-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com Acked-by: Felix Kuehling Tested-by: Ralph Campbell Signed-off-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 101 ++++++++++++++++++++-------------------------------- 1 file changed, 38 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 81c302c884c0..e912b9dc4633 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -19,45 +19,47 @@ #include /* - * hmm_pfn_flag_e - HMM flag enums + * On output: + * 0 - The page is faultable and a future call with + * HMM_PFN_REQ_FAULT could succeed. + * HMM_PFN_VALID - the pfn field points to a valid PFN. This PFN is at + * least readable. If dev_private_owner is !NULL then this could + * point at a DEVICE_PRIVATE page. + * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID) + * HMM_PFN_ERROR - accessing the pfn is impossible and the device should + * fail. ie poisoned memory, special pages, no vma, etc * - * Flags: - * HMM_PFN_VALID: pfn is valid. It has, at least, read permission. - * HMM_PFN_WRITE: CPU page table has write permission set - * - * The driver provides a flags array for mapping page protections to device - * PTE bits. If the driver valid bit for an entry is bit 3, - * i.e., (entry & (1 << 3)), then the driver must provide - * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3. - * Same logic apply to all flags. This is the same idea as vm_page_prot in vma - * except that this is per device driver rather than per architecture. + * On input: + * 0 - Return the current state of the page, do not fault it. + * HMM_PFN_REQ_FAULT - The output must have HMM_PFN_VALID or hmm_range_fault() + * will fail + * HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault() + * will fail. Must be combined with HMM_PFN_REQ_FAULT. */ -enum hmm_pfn_flag_e { - HMM_PFN_VALID = 0, - HMM_PFN_WRITE, - HMM_PFN_FLAG_MAX +enum hmm_pfn_flags { + /* Output flags */ + HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), + HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), + HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + + /* Input flags */ + HMM_PFN_REQ_FAULT = HMM_PFN_VALID, + HMM_PFN_REQ_WRITE = HMM_PFN_WRITE, + + HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR, }; /* - * hmm_pfn_value_e - HMM pfn special value - * - * Flags: - * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory - * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() + * hmm_pfn_to_page() - return struct page pointed to by a device entry * - * Driver provides values for none entry, error entry, and special entry. - * Driver can alias (i.e., use same value) error and special, but - * it should not alias none with error or special. - * - * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be: - * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous, - * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry, + * This must be called under the caller 'user_lock' after a successful + * mmu_interval_read_begin(). The caller must have tested for HMM_PFN_VALID + * already. */ -enum hmm_pfn_value_e { - HMM_PFN_ERROR, - HMM_PFN_NONE, - HMM_PFN_VALUE_MAX -}; +static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn) +{ + return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS); +} /* * struct hmm_range - track invalidation lock on virtual address range @@ -66,12 +68,9 @@ enum hmm_pfn_value_e { * @notifier_seq: result of mmu_interval_read_begin() * @start: range virtual start address (inclusive) * @end: range virtual end address (exclusive) - * @pfns: array of pfns (big enough for the range) - * @flags: pfn flags to match device driver page table - * @values: pfn value for some special case (none, special, error, ...) + * @hmm_pfns: array of pfns (big enough for the range) * @default_flags: default flags for the range (write, read, ... see hmm doc) * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter - * @pfn_shift: pfn shift value (should be <= PAGE_SHIFT) * @dev_private_owner: owner of device private pages */ struct hmm_range { @@ -79,36 +78,12 @@ struct hmm_range { unsigned long notifier_seq; unsigned long start; unsigned long end; - uint64_t *pfns; - const uint64_t *flags; - const uint64_t *values; - uint64_t default_flags; - uint64_t pfn_flags_mask; - uint8_t pfn_shift; + unsigned long *hmm_pfns; + unsigned long default_flags; + unsigned long pfn_flags_mask; void *dev_private_owner; }; -/* - * hmm_device_entry_to_page() - return struct page pointed to by a device entry - * @range: range use to decode device entry value - * @entry: device entry value to get corresponding struct page from - * Return: struct page pointer if entry is a valid, NULL otherwise - * - * If the device entry is valid (ie valid flag set) then return the struct page - * matching the entry value. Otherwise return NULL. - */ -static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range, - uint64_t entry) -{ - if (entry == range->values[HMM_PFN_NONE]) - return NULL; - if (entry == range->values[HMM_PFN_ERROR]) - return NULL; - if (!(entry & range->flags[HMM_PFN_VALID])) - return NULL; - return pfn_to_page(entry >> range->pfn_shift); -} - /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -- cgit v1.2.3 From 9c8255c888bac9221739c822132b405d4196bdd8 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:25:07 -0500 Subject: team: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- include/linux/if_team.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 537dc2b8c879..add607943c95 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -67,7 +67,7 @@ struct team_port { u16 queue_id; struct list_head qom_list; /* node in queue override mapping list */ struct rcu_head rcu; - long mode_priv[0]; + long mode_priv[]; }; static inline struct team_port *team_port_get_rcu(const struct net_device *dev) -- cgit v1.2.3 From 0462b6bdb6445b887b8896f28be92e0d94c92e7b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 May 2020 13:59:11 +0200 Subject: net: add a CMSG_USER_DATA macro Add a variant of CMSG_DATA that operates on user pointer to avoid sparse warnings about casting to/from user pointers. Also fix up CMSG_DATA to rely on the gcc extension that allows void pointer arithmetics to cut down on the amount of casts. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/socket.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 54338fac45cb..4cc64d611cf4 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -94,7 +94,10 @@ struct cmsghdr { #define CMSG_ALIGN(len) ( ((len)+sizeof(long)-1) & ~(sizeof(long)-1) ) -#define CMSG_DATA(cmsg) ((void *)((char *)(cmsg) + sizeof(struct cmsghdr))) +#define CMSG_DATA(cmsg) \ + ((void *)(cmsg) + sizeof(struct cmsghdr)) +#define CMSG_USER_DATA(cmsg) \ + ((void __user *)(cmsg) + sizeof(struct cmsghdr)) #define CMSG_SPACE(len) (sizeof(struct cmsghdr) + CMSG_ALIGN(len)) #define CMSG_LEN(len) (sizeof(struct cmsghdr) + (len)) -- cgit v1.2.3 From 1f466e1f15cf1dac7c86798d694649fc42cd868a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 May 2020 13:59:13 +0200 Subject: net: cleanly handle kernel vs user buffers for ->msg_control The msg_control field in struct msghdr can either contain a user pointer when used with the recvmsg system call, or a kernel pointer when used with sendmsg. To complicate things further kernel_recvmsg can stuff a kernel pointer in and then use set_fs to make the uaccess helpers accept it. Replace it with a union of a kernel pointer msg_control field, and a user pointer msg_control_user one, and allow kernel_recvmsg operate on a proper kernel pointer using a bitfield to override the normal choice of a user pointer for recvmsg. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/socket.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 4cc64d611cf4..04d2bc97f497 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,7 +50,17 @@ struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ struct iov_iter msg_iter; /* data */ - void *msg_control; /* ancillary data */ + + /* + * Ancillary data. msg_control_user is the user buffer used for the + * recv* side when msg_control_is_user is set, msg_control is the kernel + * buffer used for all other cases. + */ + union { + void *msg_control; + void __user *msg_control_user; + }; + bool msg_control_is_user : 1; __kernel_size_t msg_controllen; /* ancillary data buffer length */ unsigned int msg_flags; /* flags on received message */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ -- cgit v1.2.3 From 8b59cd81dc5e724eaea283fa6006985891c7bff4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 23 Apr 2020 23:23:52 +0900 Subject: kbuild: ensure full rebuild when the compiler is updated Commit 21c54b774744 ("kconfig: show compiler version text in the top comment") added the environment variable, CC_VERSION_TEXT in the comment of the top Kconfig file. It can detect the compiler update, and invoke the syncconfig because all environment variables referenced in Kconfig files are recorded in include/config/auto.conf.cmd This commit makes it a CONFIG option in order to ensure the full rebuild when the compiler is updated. This works like follows: include/config/kconfig.h contains "CONFIG_CC_VERSION_TEXT" in the comment block. The top Makefile specifies "-include $(srctree)/include/linux/kconfig.h" to guarantee it is included from all kernel source files. fixdep parses every source file and all headers included from it, searching for words prefixed with "CONFIG_". Then, fixdep finds CONFIG_CC_VERSION_TEXT in include/config/kconfig.h and adds include/config/cc/version/text.h into every .*.cmd file. When the compiler is updated, syncconfig is invoked because init/Kconfig contains the reference to the environment variable CC_VERTION_TEXT. CONFIG_CC_VERSION_TEXT is updated to the new version string, and include/config/cc/version/text.h is touched. In the next rebuild, Make will rebuild every files since the timestamp of include/config/cc/version/text.h is newer than that of target. Signed-off-by: Masahiro Yamada --- include/linux/kconfig.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index cc8fa109cfa3..9d12c970f18f 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -2,6 +2,8 @@ #ifndef __LINUX_KCONFIG_H #define __LINUX_KCONFIG_H +/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */ + #include #ifdef CONFIG_CPU_BIG_ENDIAN -- cgit v1.2.3 From 914a1951d88968371c7d43400c9d936382cd7d69 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:05:44 -0500 Subject: PCI: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these as a flexible array member [1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that dynamic memory allocations won't be affected by this change: Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero. [1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type [1]. There are some instances of code in which the sizeof() operator is being incorrectly/erroneously applied to zero-length arrays, and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Link: https://lore.kernel.org/r/20200507190544.GA15633@embeddedor Signed-off-by: Gustavo A. R. Silva Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..0453ee458ab1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -279,7 +279,7 @@ struct pci_cap_saved_data { u16 cap_nr; bool cap_extended; unsigned int size; - u32 data[0]; + u32 data[]; }; struct pci_cap_saved_state { @@ -532,7 +532,7 @@ struct pci_host_bridge { resource_size_t start, resource_size_t size, resource_size_t align); - unsigned long private[0] ____cacheline_aligned; + unsigned long private[] ____cacheline_aligned; }; #define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev) -- cgit v1.2.3 From b0dbd97de1f1fd6b3c9a7bb8f7c795bba7e169d8 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 10 May 2020 14:24:31 +0200 Subject: platform/x86: asus-wmi: Add support for SW_TABLET_MODE On Asus 2-in-1s with a detachable keyboard the Asus WMI interface reports if the tablet is attached to the keyboard or not. Report if the 2-in-1 is in tablet or clamshell mode to userspace by reporting SW_TABLET_MODE events to userspace. This has been tested on a T100TA, T100CHI, T100HA and T200TA. Signed-off-by: Hans de Goede Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 3 +++ 1 file changed, 3 insertions(+) (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 d39fc658c320..897b8332a39f 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -85,6 +85,9 @@ /* Maximum charging percentage */ #define ASUS_WMI_DEVID_RSOC 0x00120057 +/* Keyboard dock */ +#define ASUS_WMI_DEVID_KBD_DOCK 0x00120063 + /* DSTS masks */ #define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 #define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 -- cgit v1.2.3 From 2a0a24ebb499c9d499eea948d3fc108f936e36d4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 27 Mar 2020 12:42:00 +0100 Subject: sched: Make scheduler_ipi inline Now that the scheduler IPI is trivial and simple again there is no point to have the little function out of line. This simplifies the effort of constraining the instrumentation nicely. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134058.453581595@linutronix.de --- include/linux/sched.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..d4ea4407cd6d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1715,7 +1715,15 @@ extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk); }) #ifdef CONFIG_SMP -void scheduler_ipi(void); +static __always_inline void scheduler_ipi(void) +{ + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); +} extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else static inline void scheduler_ipi(void) { } -- cgit v1.2.3 From 1e6769b0aece51ea7a3dc3117c37d4a5669e4a21 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 26 Mar 2020 23:49:48 +0900 Subject: kprobes: Support __kprobes blacklist in modules Support __kprobes attribute for blacklist functions in modules. The __kprobes attribute functions are stored in .kprobes.text section. Signed-off-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134059.678201813@linutronix.de --- include/linux/module.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1ad393e62bef..369c354f9207 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -489,6 +489,10 @@ struct module { unsigned int num_ftrace_callsites; unsigned long *ftrace_callsites; #endif +#ifdef CONFIG_KPROBES + void *kprobes_text_start; + unsigned int kprobes_text_size; +#endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ -- cgit v1.2.3 From 16db6264c93d2d7df9eb8be5d9eb717ab30105fe Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 26 Mar 2020 23:50:00 +0900 Subject: kprobes: Support NOKPROBE_SYMBOL() in modules Support NOKPROBE_SYMBOL() in modules. NOKPROBE_SYMBOL() records only symbol address in "_kprobe_blacklist" section in the module. Signed-off-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134059.771170126@linutronix.de --- include/linux/module.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 369c354f9207..1192097c9a69 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -492,6 +492,8 @@ struct module { #ifdef CONFIG_KPROBES void *kprobes_text_start; unsigned int kprobes_text_size; + unsigned long *kprobe_blacklist; + unsigned int num_kprobe_blacklist; #endif #ifdef CONFIG_LIVEPATCH -- cgit v1.2.3 From 2c864c78c2386ada7433268cdfa8cb77cfe31bf3 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 11 May 2020 14:02:15 -0700 Subject: ptp: fix struct member comment for do_aux_work The do_aux_work callback had documentation in the structure comment which referred to it as "do_work". Signed-off-by: Jacob Keller Cc: Richard Cochran Acked-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 121a7eda4593..c602670bbffb 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -105,10 +105,10 @@ struct ptp_system_timestamp { * parameter func: the desired function to use. * parameter chan: the function channel index to use. * - * @do_work: Request driver to perform auxiliary (periodic) operations - * Driver should return delay of the next auxiliary work scheduling - * time (>=0) or negative value in case further scheduling - * is not required. + * @do_aux_work: Request driver to perform auxiliary (periodic) operations + * Driver should return delay of the next auxiliary work + * scheduling time (>=0) or negative value in case further + * scheduling is not required. * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). -- cgit v1.2.3 From 1f66b0f0aec671f8fbc86d75b2efdf7c7e0f7880 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:26 +0300 Subject: net: dsa: tag_8021q: introduce a vid_is_dsa_8021q helper This function returns a boolean denoting whether the VLAN passed as argument is part of the 1024-3071 range that the dsa_8021q tagging scheme uses. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b8daaec0896e..ebc245ff838a 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -50,6 +50,8 @@ int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); +bool vid_is_dsa_8021q(u16 vid); + #else int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, @@ -107,6 +109,11 @@ int dsa_8021q_rx_source_port(u16 vid) return 0; } +bool vid_is_dsa_8021q(u16 vid) +{ + return false; +} + #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ #endif /* _NET_DSA_8021Q_H */ -- cgit v1.2.3 From ec5ae61076d07be986df19773662506220757c9f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:29 +0300 Subject: net: dsa: sja1105: save/restore VLANs using a delta commit method Managing the VLAN table that is present in hardware will become very difficult once we add a third operating state (best_effort_vlan_filtering). That is because correct cleanup (not too little, not too much) becomes virtually impossible, when VLANs can be added from the bridge layer, from dsa_8021q for basic tagging, for cross-chip bridging, as well as retagging rules for sub-VLANs and cross-chip sub-VLANs. So we need to rethink VLAN interaction with the switch in a more scalable way. In preparation for that, use the priv->expect_dsa_8021q boolean to classify any VLAN request received through .port_vlan_add or .port_vlan_del towards either one of 2 internal lists: bridge VLANs and dsa_8021q VLANs. Then, implement a central sja1105_build_vlan_table method that creates a VLAN configuration from scratch based on the 2 lists of VLANs kept by the driver, and based on the VLAN awareness state. Currently, if we are VLAN-unaware, install the dsa_8021q VLANs, otherwise the bridge VLANs. Then, implement a delta commit procedure that identifies which VLANs from this new configuration are actually different from the config previously committed to hardware. We apply the delta through the dynamic configuration interface (we don't reset the switch). The result is that the hardware should see the exact sequence of operations as before this patch. This also helps remove the "br" argument passed to dsa_8021q_crosschip_bridge_join, which it was only using to figure out whether it should commit the configuration back to us or not, based on the VLAN awareness state of the bridge. We can simplify that, by always allowing those VLANs inside of our dsa_8021q_vlans list, and committing those to hardware when necessary. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index ebc245ff838a..404bd2cce642 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -25,18 +25,14 @@ struct dsa_8021q_crosschip_link { int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, bool enabled); -int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, bool enabled); - int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links); int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, @@ -60,16 +56,9 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, return 0; } -int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, bool enabled) -{ - return 0; -} - int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links) { return 0; @@ -77,7 +66,7 @@ int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links) { return 0; -- cgit v1.2.3 From 38b5beeae7a4cde87edabb0196fac1f55ae668ee Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:32 +0300 Subject: net: dsa: sja1105: prepare tagger for handling DSA tags and VLAN simultaneously In VLAN-unaware mode, sja1105 uses VLAN tags with a custom TPID of 0xdadb. While in the yet-to-be introduced best_effort_vlan_filtering mode, it needs to work with normal VLAN TPID values. A complication arises when we must transmit a VLAN-tagged packet to the switch when it's in VLAN-aware mode. We need to construct a packet with 2 VLAN tags, and the switch will use the outer header for routing and pop it on egress. But sadly, here the 2 hardware generations don't behave the same: - E/T switches won't pop an ETH_P_8021AD tag on egress, it seems (packets will remain double-tagged). - P/Q/R/S switches will drop a packet with 2 ETH_P_8021Q tags (it looks like it tries to prevent VLAN hopping). But looks like the reverse is also true: - E/T switches have no problem popping the outer tag from packets with 2 ETH_P_8021Q tags. - P/Q/R/S will have no problem popping a single tag even if that is ETH_P_8021AD. So it is clear that if we want the hardware to work with dsa_8021q tagging in VLAN-aware mode, we need to send different TPIDs depending on revision. Keep that information in priv->info->qinq_tpid. The per-port tagger structure will hold an xmit_tpid value that depends not only upon the qinq_tpid, but also upon the VLAN awareness state itself (in case we must transmit using 0xdadb). 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 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index fa5735c353cd..f821d08b1b5f 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -59,6 +59,7 @@ struct sja1105_port { struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; + u16 xmit_tpid; }; #endif /* _NET_DSA_SJA1105_H */ -- cgit v1.2.3 From 3eaae1d05f2b5be1be834bfad64f8fc2ad39a56d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:33 +0300 Subject: net: dsa: tag_8021q: support up to 8 VLANs per port using sub-VLANs For switches that support VLAN retagging, such as sja1105, we extend dsa_8021q by encoding a "sub-VLAN" into the remaining 3 free bits in the dsa_8021q tag. A sub-VLAN is nothing more than a number in the range 0-7, which serves as an index into a per-port driver lookup table. The sub-VLAN value of zero means that traffic is untagged (this is also backwards-compatible with dsa_8021q without retagging). The switch should be configured to retag VLAN-tagged traffic that gets transmitted towards the CPU port (and towards the CPU only). Example: bridge vlan add dev sw1p0 vid 100 The switch retags frames received on port 0, going to the CPU, and having VID 100, to the VID of 1104 (0x0450). In dsa_8021q language: | 11 | 10 | 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 | +-----------+-----+-----------------+-----------+-----------------------+ | DIR | SVL | SWITCH_ID | SUBVLAN | PORT | +-----------+-----+-----------------+-----------+-----------------------+ 0x0450 means: - DIR = 0b01: this is an RX VLAN - SUBVLAN = 0b001: this is subvlan #1 - SWITCH_ID = 0b001: this is switch 1 (see the name "sw1p0") - PORT = 0b0000: this is port 0 (see the name "sw1p0") The driver also remembers the "1 -> 100" mapping. In the hotpath, if the sub-VLAN from the tag encodes a non-untagged frame, this mapping is used to create a VLAN hwaccel tag, with the value of 100. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 404bd2cce642..311aa04e7520 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -20,6 +20,8 @@ struct dsa_8021q_crosschip_link { refcount_t refcount; }; +#define DSA_8021Q_N_SUBVLAN 8 + #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, @@ -42,10 +44,14 @@ u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); +u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan); + int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); +u16 dsa_8021q_rx_subvlan(u16 vid); + bool vid_is_dsa_8021q(u16 vid); #else @@ -88,6 +94,11 @@ u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) return 0; } +u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) +{ + return 0; +} + int dsa_8021q_rx_switch_id(u16 vid) { return 0; @@ -98,6 +109,11 @@ int dsa_8021q_rx_source_port(u16 vid) return 0; } +u16 dsa_8021q_rx_subvlan(u16 vid) +{ + return 0; +} + bool vid_is_dsa_8021q(u16 vid) { return false; -- cgit v1.2.3 From 84eeb5d460e399795e9a92a0cd44999254886150 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:34 +0300 Subject: net: dsa: tag_sja1105: implement sub-VLAN decoding Create a subvlan_map as part of each port's tagger private structure. This keeps reverse mappings of bridge-to-dsa_8021q VLAN retagging rules. Note that as of this patch, this piece of code is never engaged, due to the fact that the driver hasn't installed any retagging rule, so we'll always see packets with a subvlan code of 0 (untagged). Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index f821d08b1b5f..dd93735ae228 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -9,6 +9,7 @@ #include #include +#include #include #define ETH_P_SJA1105 ETH_P_DSA_8021Q @@ -53,6 +54,7 @@ struct sja1105_skb_cb { ((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb)) struct sja1105_port { + u16 subvlan_map[DSA_8021Q_N_SUBVLAN]; struct kthread_worker *xmit_worker; struct kthread_work xmit_work; struct sk_buff_head xmit_queue; -- 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 From 4a470f00e10e3336350ab60ec6c3206177093019 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 6 May 2020 14:32:35 +0200 Subject: of: Make self-contained is not self-contained, as it uses _OF_DECLARE() to define RESERVEDMEM_OF_DECLARE(), but does not include . Fix this by adding the missing include. Signed-off-by: Geert Uytterhoeven Reviewed-by: Thierry Reding Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/linux/of_reserved_mem.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index a1b427ac291b..8216a4156263 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -3,6 +3,7 @@ #define __OF_RESERVED_MEM_H #include +#include struct of_phandle_args; struct reserved_mem_ops; -- cgit v1.2.3 From a3cba697a2a09e6769996d5265991a3228004d92 Mon Sep 17 00:00:00 2001 From: Joseph Lo Date: Wed, 29 May 2019 16:21:34 +0800 Subject: clk: tegra: Export functions for EMC clock scaling Export functions to allow accessing the CAR register required by EMC clock scaling. These functions will be used to access the CAR register as part of the scaling sequence. Signed-off-by: Joseph Lo Signed-off-by: Thierry Reding --- include/linux/clk/tegra.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 2b1b35240074..5b0bdb413460 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -131,6 +131,9 @@ extern void tegra210_set_sata_pll_seq_sw(bool state); extern void tegra210_put_utmipll_in_iddq(void); extern void tegra210_put_utmipll_out_iddq(void); extern int tegra210_clk_handle_mbist_war(unsigned int id); +extern void tegra210_clk_emc_dll_enable(bool flag); +extern void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value); +extern void tegra210_clk_emc_update_setting(u32 emc_src_value); struct clk; -- cgit v1.2.3 From 0ac65fc946d3a15ff30cea28b38a00b9ba98217b Mon Sep 17 00:00:00 2001 From: Joseph Lo Date: Wed, 29 May 2019 16:21:35 +0800 Subject: clk: tegra: Implement Tegra210 EMC clock The EMC clock needs to carefully coordinate with the EMC controller programming to make sure external memory can be properly clocked. Do so by hooking up the EMC clock with an EMC provider that will specify which rates are supported by the EMC and provide a callback to use for setting the clock rate at the EMC. Based on work by Peter De Schrijver . Signed-off-by: Joseph Lo Signed-off-by: Thierry Reding --- include/linux/clk/tegra.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 5b0bdb413460..3f01d43f0598 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -146,4 +146,28 @@ void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, void *cb_arg); int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); +struct tegra210_clk_emc_config { + unsigned long rate; + bool same_freq; + u32 value; + + unsigned long parent_rate; + u8 parent; +}; + +struct tegra210_clk_emc_provider { + struct module *owner; + struct device *dev; + + struct tegra210_clk_emc_config *configs; + unsigned int num_configs; + + int (*set_rate)(struct device *dev, + const struct tegra210_clk_emc_config *config); +}; + +int tegra210_clk_emc_attach(struct clk *clk, + struct tegra210_clk_emc_provider *provider); +void tegra210_clk_emc_detach(struct clk *clk); + #endif /* __LINUX_CLK_TEGRA_H_ */ -- cgit v1.2.3 From 529798bae7c155d38eec211436df736349dca2ee Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:19:43 -0500 Subject: remoteproc: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507191943.GA16033@embeddedor Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 0468be4d02f4..e7b7bab8b235 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -73,7 +73,7 @@ struct resource_table { u32 ver; u32 num; u32 reserved[2]; - u32 offset[0]; + u32 offset[]; } __packed; /** @@ -87,7 +87,7 @@ struct resource_table { */ struct fw_rsc_hdr { u32 type; - u8 data[0]; + u8 data[]; } __packed; /** @@ -306,7 +306,7 @@ struct fw_rsc_vdev { u8 status; u8 num_of_vrings; u8 reserved[2]; - struct fw_rsc_vdev_vring vring[0]; + struct fw_rsc_vdev_vring vring[]; } __packed; struct rproc; -- cgit v1.2.3 From 59566b0b622e3e6ea928c0b8cac8a5601b00b383 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 30 Apr 2020 20:21:47 -0400 Subject: x86/ftrace: Have ftrace trampolines turn read-only at the end of system boot up Booting one of my machines, it triggered the following crash: Kernel/User page tables isolation: enabled ftrace: allocating 36577 entries in 143 pages Starting tracer 'function' BUG: unable to handle page fault for address: ffffffffa000005c #PF: supervisor write access in kernel mode #PF: error_code(0x0003) - permissions violation PGD 2014067 P4D 2014067 PUD 2015063 PMD 7b253067 PTE 7b252061 Oops: 0003 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper Not tainted 5.4.0-test+ #24 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 RIP: 0010:text_poke_early+0x4a/0x58 Code: 34 24 48 89 54 24 08 e8 bf 72 0b 00 48 8b 34 24 48 8b 4c 24 08 84 c0 74 0b 48 89 df f3 a4 48 83 c4 10 5b c3 9c 58 fa 48 89 df a4 50 9d 48 83 c4 10 5b e9 d6 f9 ff ff 0 41 57 49 RSP: 0000:ffffffff82003d38 EFLAGS: 00010046 RAX: 0000000000000046 RBX: ffffffffa000005c RCX: 0000000000000005 RDX: 0000000000000005 RSI: ffffffff825b9a90 RDI: ffffffffa000005c RBP: ffffffffa000005c R08: 0000000000000000 R09: ffffffff8206e6e0 R10: ffff88807b01f4c0 R11: ffffffff8176c106 R12: ffffffff8206e6e0 R13: ffffffff824f2440 R14: 0000000000000000 R15: ffffffff8206eac0 FS: 0000000000000000(0000) GS:ffff88807d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa000005c CR3: 0000000002012000 CR4: 00000000000006b0 Call Trace: text_poke_bp+0x27/0x64 ? mutex_lock+0x36/0x5d arch_ftrace_update_trampoline+0x287/0x2d5 ? ftrace_replace_code+0x14b/0x160 ? ftrace_update_ftrace_func+0x65/0x6c __register_ftrace_function+0x6d/0x81 ftrace_startup+0x23/0xc1 register_ftrace_function+0x20/0x37 func_set_flag+0x59/0x77 __set_tracer_option.isra.19+0x20/0x3e trace_set_options+0xd6/0x13e apply_trace_boot_options+0x44/0x6d register_tracer+0x19e/0x1ac early_trace_init+0x21b/0x2c9 start_kernel+0x241/0x518 ? load_ucode_intel_bsp+0x21/0x52 secondary_startup_64+0xa4/0xb0 I was able to trigger it on other machines, when I added to the kernel command line of both "ftrace=function" and "trace_options=func_stack_trace". The cause is the "ftrace=function" would register the function tracer and create a trampoline, and it will set it as executable and read-only. Then the "trace_options=func_stack_trace" would then update the same trampoline to include the stack tracer version of the function tracer. But since the trampoline already exists, it updates it with text_poke_bp(). The problem is that text_poke_bp() called while system_state == SYSTEM_BOOTING, it will simply do a memcpy() and not the page mapping, as it would think that the text is still read-write. But in this case it is not, and we take a fault and crash. Instead, lets keep the ftrace trampolines read-write during boot up, and then when the kernel executable text is set to read-only, the ftrace trampolines get set to read-only as well. Link: https://lkml.kernel.org/r/20200430202147.4dc6e2de@oasis.local.home Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Josh Poimboeuf Cc: "H. Peter Anvin" Cc: stable@vger.kernel.org Fixes: 768ae4406a5c ("x86/ftrace: Use text_poke()") Acked-by: Peter Zijlstra Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index db95244a62d4..ab4bd15cbcdb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -210,6 +210,29 @@ struct ftrace_ops { #endif }; +extern struct ftrace_ops __rcu *ftrace_ops_list; +extern struct ftrace_ops ftrace_list_end; + +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw_check() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw_check() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw_check(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + /* * Type of the current tracing. */ -- cgit v1.2.3 From d2fe97545a1e2d01c0ca0105bdc59002a0d0b130 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:56 -0700 Subject: fscrypt: fix all kerneldoc warnings Fix all kerneldoc warnings in fs/crypto/ and include/linux/fscrypt.h. Most of these were due to missing documentation for function parameters. Detected with: scripts/kernel-doc -v -none fs/crypto/*.{c,h} include/linux/fscrypt.h This cleanup makes it possible to check new patches for kerneldoc warnings without having to filter out all the existing ones. For consistency, also adjust some function "brief descriptions" to include the parentheses and to wrap at 80 characters. (The latter matches the checkpatch expectation.) Link: https://lore.kernel.org/r/20200511191358.53096-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e3c2d2a15525..cb2c41f8dfde 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -75,6 +75,7 @@ static inline bool fscrypt_has_encryption_key(const struct inode *inode) /** * fscrypt_needs_contents_encryption() - check whether an inode needs * contents encryption + * @inode: the inode to check * * Return: %true iff the inode is an encrypted regular file and the kernel was * built with fscrypt support. @@ -504,7 +505,7 @@ static inline void fscrypt_set_ops(struct super_block *sb, #endif /* !CONFIG_FS_ENCRYPTION */ /** - * fscrypt_require_key - require an inode's encryption key + * fscrypt_require_key() - require an inode's encryption key * @inode: the inode we need the key for * * If the inode is encrypted, set up its encryption key if not already done. @@ -530,7 +531,8 @@ static inline int fscrypt_require_key(struct inode *inode) } /** - * fscrypt_prepare_link - prepare to link an inode into a possibly-encrypted directory + * fscrypt_prepare_link() - prepare to link an inode into a possibly-encrypted + * directory * @old_dentry: an existing dentry for the inode being linked * @dir: the target directory * @dentry: negative dentry for the target filename @@ -557,7 +559,8 @@ static inline int fscrypt_prepare_link(struct dentry *old_dentry, } /** - * fscrypt_prepare_rename - prepare for a rename between possibly-encrypted directories + * fscrypt_prepare_rename() - prepare for a rename between possibly-encrypted + * directories * @old_dir: source directory * @old_dentry: dentry for source file * @new_dir: target directory @@ -590,7 +593,8 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir, } /** - * fscrypt_prepare_lookup - prepare to lookup a name in a possibly-encrypted directory + * fscrypt_prepare_lookup() - prepare to lookup a name in a possibly-encrypted + * directory * @dir: directory being searched * @dentry: filename being looked up * @fname: (output) the name to use to search the on-disk directory @@ -623,7 +627,8 @@ static inline int fscrypt_prepare_lookup(struct inode *dir, } /** - * fscrypt_prepare_setattr - prepare to change a possibly-encrypted inode's attributes + * fscrypt_prepare_setattr() - prepare to change a possibly-encrypted inode's + * attributes * @dentry: dentry through which the inode is being changed * @attr: attributes to change * @@ -648,7 +653,7 @@ static inline int fscrypt_prepare_setattr(struct dentry *dentry, } /** - * fscrypt_prepare_symlink - prepare to create a possibly-encrypted symlink + * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink * @dir: directory in which the symlink is being created * @target: plaintext symlink target * @len: length of @target excluding null terminator @@ -687,7 +692,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir, } /** - * fscrypt_encrypt_symlink - encrypt the symlink target if needed + * fscrypt_encrypt_symlink() - encrypt the symlink target if needed * @inode: symlink inode * @target: plaintext symlink target * @len: length of @target excluding null terminator -- cgit v1.2.3 From fe015a78e5d0139cb126e8dbfc46a80be2bd27ad Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:57 -0700 Subject: fscrypt: name all function parameters Name all the function parameters. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fscrypt patches. This also matches the checkpatch expectation. Link: https://lore.kernel.org/r/20200511191358.53096-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 46 +++++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index cb2c41f8dfde..210a05dd9ecd 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -56,10 +56,11 @@ struct fscrypt_name { struct fscrypt_operations { unsigned int flags; const char *key_prefix; - int (*get_context)(struct inode *, void *, size_t); - int (*set_context)(struct inode *, const void *, size_t, void *); - bool (*dummy_context)(struct inode *); - bool (*empty_dir)(struct inode *); + int (*get_context)(struct inode *inode, void *ctx, size_t len); + int (*set_context)(struct inode *inode, const void *ctx, size_t len, + void *fs_data); + bool (*dummy_context)(struct inode *inode); + bool (*empty_dir)(struct inode *inode); unsigned int max_namelen; bool (*has_stable_inodes)(struct super_block *sb); void (*get_ino_and_lblk_bits)(struct super_block *sb, @@ -137,13 +138,15 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) extern void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); -extern int fscrypt_ioctl_get_policy(struct file *, void __user *); -extern int fscrypt_ioctl_get_policy_ex(struct file *, void __user *); +extern int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); +extern int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); +extern int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); extern int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); -extern int fscrypt_has_permitted_context(struct inode *, struct inode *); -extern int fscrypt_inherit_context(struct inode *, struct inode *, - void *, bool); +extern int fscrypt_has_permitted_context(struct inode *parent, + struct inode *child); +extern int fscrypt_inherit_context(struct inode *parent, struct inode *child, + void *fs_data, bool preload); + /* keyring.c */ extern void fscrypt_sb_free(struct super_block *sb); extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); @@ -153,23 +156,24 @@ extern int fscrypt_ioctl_remove_key_all_users(struct file *filp, extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ -extern int fscrypt_get_encryption_info(struct inode *); -extern void fscrypt_put_encryption_info(struct inode *); -extern void fscrypt_free_inode(struct inode *); +extern int fscrypt_get_encryption_info(struct inode *inode); +extern void fscrypt_put_encryption_info(struct inode *inode); +extern void fscrypt_free_inode(struct inode *inode); extern int fscrypt_drop_inode(struct inode *inode); /* fname.c */ -extern int fscrypt_setup_filename(struct inode *, const struct qstr *, - int lookup, struct fscrypt_name *); +extern int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, + int lookup, struct fscrypt_name *fname); static inline void fscrypt_free_filename(struct fscrypt_name *fname) { kfree(fname->crypto_buf.name); } -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_alloc_buffer(const struct inode *inode, + u32 max_encrypted_len, + struct fscrypt_str *crypto_str); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); extern int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, @@ -180,9 +184,9 @@ 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, - unsigned int); +extern void fscrypt_decrypt_bio(struct bio *bio); +extern int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len); /* hooks.c */ extern int fscrypt_file_open(struct inode *inode, struct file *filp); -- cgit v1.2.3 From 607009020a5e7fd9353fb2dd4cdcc73e26f3350f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:58 -0700 Subject: fscrypt: remove unnecessary extern keywords Remove the unnecessary 'extern' keywords from function declarations. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fscrypt patches. This also makes the code shorter and matches the 'checkpatch --strict' expectation. Link: https://lore.kernel.org/r/20200511191358.53096-4-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 138 +++++++++++++++++++++++------------------------- 1 file changed, 65 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 210a05dd9ecd..0e0c7ad19383 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -108,22 +108,21 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) } /* crypto.c */ -extern void fscrypt_enqueue_decrypt_work(struct work_struct *); - -extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, - unsigned int len, - unsigned int offs, - gfp_t gfp_flags); -extern int fscrypt_encrypt_block_inplace(const struct inode *inode, - struct page *page, unsigned int len, - unsigned int offs, u64 lblk_num, - gfp_t gfp_flags); - -extern int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, - unsigned int offs); -extern int fscrypt_decrypt_block_inplace(const struct inode *inode, - struct page *page, unsigned int len, - unsigned int offs, u64 lblk_num); +void fscrypt_enqueue_decrypt_work(struct work_struct *); + +struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, + unsigned int len, + unsigned int offs, + gfp_t gfp_flags); +int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num, gfp_t gfp_flags); + +int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, + unsigned int offs); +int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num); static inline bool fscrypt_is_bounce_page(struct page *page) { @@ -135,81 +134,74 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return (struct page *)page_private(bounce_page); } -extern void fscrypt_free_bounce_page(struct page *bounce_page); +void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); -extern int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); -extern int fscrypt_has_permitted_context(struct inode *parent, - struct inode *child); -extern int fscrypt_inherit_context(struct inode *parent, struct inode *child, - void *fs_data, bool preload); +int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); +int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); +int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); +int fscrypt_inherit_context(struct inode *parent, struct inode *child, + void *fs_data, bool preload); /* keyring.c */ -extern void fscrypt_sb_free(struct super_block *sb); -extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_remove_key_all_users(struct file *filp, - void __user *arg); -extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); +void fscrypt_sb_free(struct super_block *sb); +int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); +int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); +int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ -extern int fscrypt_get_encryption_info(struct inode *inode); -extern void fscrypt_put_encryption_info(struct inode *inode); -extern void fscrypt_free_inode(struct inode *inode); -extern int fscrypt_drop_inode(struct inode *inode); +int fscrypt_get_encryption_info(struct inode *inode); +void fscrypt_put_encryption_info(struct inode *inode); +void fscrypt_free_inode(struct inode *inode); +int fscrypt_drop_inode(struct inode *inode); /* fname.c */ -extern int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, - int lookup, struct fscrypt_name *fname); +int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, + int lookup, struct fscrypt_name *fname); static inline void fscrypt_free_filename(struct fscrypt_name *fname) { kfree(fname->crypto_buf.name); } -extern int fscrypt_fname_alloc_buffer(const struct inode *inode, - u32 max_encrypted_len, - struct fscrypt_str *crypto_str); -extern void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_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); -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); +int fscrypt_fname_alloc_buffer(const struct inode *inode, u32 max_encrypted_len, + struct fscrypt_str *crypto_str); +void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); +int fscrypt_fname_disk_to_usr(const struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname); +bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len); +u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); /* bio.c */ -extern void fscrypt_decrypt_bio(struct bio *bio); -extern int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, - sector_t pblk, unsigned int len); +void fscrypt_decrypt_bio(struct bio *bio); +int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len); /* hooks.c */ -extern int fscrypt_file_open(struct inode *inode, struct file *filp); -extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, - struct dentry *dentry); -extern int __fscrypt_prepare_rename(struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry, - 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); -extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, - unsigned int len, - struct fscrypt_str *disk_link); -extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, - unsigned int max_size, - struct delayed_call *done); +int fscrypt_file_open(struct inode *inode, struct file *filp); +int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, + struct dentry *dentry); +int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags); +int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *fname); +int fscrypt_prepare_setflags(struct inode *inode, + unsigned int oldflags, unsigned int flags); +int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link); +int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, + unsigned int len, struct fscrypt_str *disk_link); +const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, + unsigned int max_size, + struct delayed_call *done); static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { -- cgit v1.2.3 From 6377a38bd345b7f3b664c43ebb647ae55c1166e4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:21:17 -0700 Subject: fs-verity: fix all kerneldoc warnings Fix all kerneldoc warnings in fs/verity/ and include/linux/fsverity.h. Most of these were due to missing documentation for function parameters. Detected with: scripts/kernel-doc -v -none fs/verity/*.{c,h} include/linux/fsverity.h This cleanup makes it possible to check new patches for kerneldoc warnings without having to filter out all the existing ones. Link: https://lore.kernel.org/r/20200511192118.71427-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index ecc604e61d61..5ac30198e032 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -200,6 +200,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) /** * fsverity_active() - do reads from the inode need to go through fs-verity? + * @inode: inode to check * * This checks whether ->i_verity_info has been set. * @@ -207,6 +208,8 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) + * + * Return: true if reads need to go through fs-verity, otherwise false */ static inline bool fsverity_active(const struct inode *inode) { -- cgit v1.2.3 From 9cd6b593cfc9eaa476c9a3fa768b08bca73213d0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:21:18 -0700 Subject: fs-verity: remove unnecessary extern keywords Remove the unnecessary 'extern' keywords from function declarations. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fs-verity patches. This also makes the code shorter and matches the 'checkpatch --strict' expectation. Link: https://lore.kernel.org/r/20200511192118.71427-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 5ac30198e032..78201a6d35f6 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -121,23 +121,23 @@ static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) /* enable.c */ -extern int fsverity_ioctl_enable(struct file *filp, const void __user *arg); +int fsverity_ioctl_enable(struct file *filp, const void __user *arg); /* measure.c */ -extern int fsverity_ioctl_measure(struct file *filp, void __user *arg); +int fsverity_ioctl_measure(struct file *filp, void __user *arg); /* open.c */ -extern int fsverity_file_open(struct inode *inode, struct file *filp); -extern int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); -extern void fsverity_cleanup_inode(struct inode *inode); +int fsverity_file_open(struct inode *inode, struct file *filp); +int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); +void fsverity_cleanup_inode(struct inode *inode); /* verify.c */ -extern bool fsverity_verify_page(struct page *page); -extern void fsverity_verify_bio(struct bio *bio); -extern void fsverity_enqueue_verify_work(struct work_struct *work); +bool fsverity_verify_page(struct page *page); +void fsverity_verify_bio(struct bio *bio); +void fsverity_enqueue_verify_work(struct work_struct *work); #else /* !CONFIG_FS_VERITY */ -- cgit v1.2.3 From 07c4e1e834f8e7c991aa6dcb5ee0b7f2842e495d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 8 May 2020 16:17:56 +0800 Subject: block: only define 'nr_sects_seq' in hd_part for 32bit SMP The seqcount of 'nr_sects_seq' is only needed in case of 32bit SMP, so define it just for 32bit SMP. Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Cc: Yufen Yu Cc: Christoph Hellwig Cc: Hou Tao Signed-off-by: Jens Axboe --- include/linux/genhd.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f9c226f9546a..b4744035ae58 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -68,7 +68,9 @@ struct hd_struct { * can be non-atomic on 32bit machines with 64bit sector_t. */ sector_t nr_sects; +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) seqcount_t nr_sects_seq; +#endif sector_t alignment_offset; unsigned int discard_alignment; struct device __dev; @@ -274,6 +276,13 @@ static inline void disk_put_part(struct hd_struct *part) put_device(part_to_dev(part)); } +static inline void hd_sects_seq_init(struct hd_struct *p) +{ +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + seqcount_init(&p->nr_sects_seq); +#endif +} + /* * Smarter partition iterator without context limits. */ -- cgit v1.2.3 From 520138c3b9425c615d1417687947d86821003319 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 8 May 2020 16:17:57 +0800 Subject: block: re-organize fields of 'struct hd_part' Put all fields accessed in IO path together at the beginning of the struct, so that all can be fetched in single cacheline. Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Cc: Yufen Yu Cc: Christoph Hellwig Cc: Hou Tao Signed-off-by: Jens Axboe --- include/linux/genhd.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index b4744035ae58..a9384449465a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -71,6 +71,14 @@ struct hd_struct { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) seqcount_t nr_sects_seq; #endif + unsigned long stamp; +#ifdef CONFIG_SMP + struct disk_stats __percpu *dkstats; +#else + struct disk_stats dkstats; +#endif + struct percpu_ref ref; + sector_t alignment_offset; unsigned int discard_alignment; struct device __dev; @@ -80,13 +88,6 @@ struct hd_struct { #ifdef CONFIG_FAIL_MAKE_REQUEST int make_it_fail; #endif - unsigned long stamp; -#ifdef CONFIG_SMP - struct disk_stats __percpu *dkstats; -#else - struct disk_stats dkstats; -#endif - struct percpu_ref ref; struct rcu_work rcu_work; }; -- cgit v1.2.3 From e6249cdd46e43a7d3bdb8cce5fe24565d6c11e94 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 3 May 2020 09:54:22 +0800 Subject: block: add blk_io_schedule() for avoiding task hung in sync dio Sync dio could be big, or may take long time in discard or in case of IO failure. We have prevented task hung in submit_bio_wait() and blk_execute_rq(), so apply the same trick for prevent task hung from happening in sync dio. Add helper of blk_io_schedule() and use io_schedule_timeout() to prevent task hung warning. Signed-off-by: Ming Lei Reviewed-by: Bart Van Assche Cc: Salman Qazi Cc: Jesse Barnes Cc: Christoph Hellwig Cc: Bart Van Assche Cc: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f00bd4042295..222eb5f32279 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,6 +27,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -1827,4 +1828,15 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } +static inline void blk_io_schedule(void) +{ + /* Prevent hang_check timer from firing at us during very long I/O */ + unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; + + if (timeout) + io_schedule_timeout(timeout); + else + io_schedule(); +} + #endif -- cgit v1.2.3 From 02992df822e7e36685593aad10721a5a9f8d3402 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 12 May 2020 17:55:45 +0900 Subject: block: provide fallbacks for blk_queue_zone_is_seq and blk_queue_zone_no blk_queue_zone_is_seq() and blk_queue_zone_no() have not been called with CONFIG_BLK_DEV_ZONED disabled until now. The introduction of REQ_OP_ZONE_APPEND will change this, so we need to provide noop fallbacks for the !CONFIG_BLK_DEV_ZONED case. Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 222eb5f32279..d736acf7f564 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -722,6 +722,16 @@ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return 0; } +static inline bool blk_queue_zone_is_seq(struct request_queue *q, + sector_t sector) +{ + return false; +} +static inline unsigned int blk_queue_zone_no(struct request_queue *q, + sector_t sector) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) -- cgit v1.2.3 From 0512a75b98f847c2e9a4b664013424e603e202f7 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 12 May 2020 17:55:47 +0900 Subject: block: Introduce REQ_OP_ZONE_APPEND Define REQ_OP_ZONE_APPEND to append-write sectors to a zone of a zoned block device. This is a no-merge write operation. A zone append write BIO must: * Target a zoned block device * Have a sector position indicating the start sector of the target zone * The target zone must be a sequential write zone * The BIO must not cross a zone boundary * The BIO size must not be split to ensure that a single range of LBAs is written with a single command. Implement these checks in generic_make_request_checks() using the helper function blk_check_zone_append(). To avoid write append BIO splitting, introduce the new max_zone_append_sectors queue limit attribute and ensure that a BIO size is always lower than this limit. Export this new limit through sysfs and check these limits in bio_full(). Also when a LLDD can't dispatch a request to a specific zone, it will return BLK_STS_ZONE_RESOURCE indicating this request needs to be delayed, e.g. because the zone it will be dispatched to is still write-locked. If this happens set the request aside in a local list to continue trying dispatching requests such as READ requests or a WRITE/ZONE_APPEND requests targetting other zones. This way we can still keep a high queue depth without starving other requests even if one request can't be served due to zone write-locking. Finally, make sure that the bio sector position indicates the actual write position as indicated by the device on completion. Signed-off-by: Keith Busch [ jth: added zone-append specific add_page and merge_page helpers ] Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 14 ++++++++++++++ include/linux/blkdev.h | 11 +++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 90895d594e64..b90dca1fa430 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -63,6 +63,18 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) +/* + * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone + * related resources are unavailable, but the driver can guarantee the queue + * will be rerun in the future once the resources become available again. + * + * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references + * a zone specific resource and IO to a different zone on the same device could + * still be served. Examples of that are zones that are write-locked, but a read + * to the same zone could be served. + */ +#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with @@ -296,6 +308,8 @@ enum req_opf { REQ_OP_ZONE_CLOSE = 11, /* Transition a zone to full */ REQ_OP_ZONE_FINISH = 12, + /* write data at the current zone write pointer */ + REQ_OP_ZONE_APPEND = 13, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d736acf7f564..5647c78bb876 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -332,6 +332,7 @@ struct queue_limits { unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; unsigned int max_write_zeroes_sectors; + unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; @@ -750,6 +751,9 @@ static inline bool rq_mergeable(struct request *rq) if (req_op(rq) == REQ_OP_WRITE_ZEROES) return false; + if (req_op(rq) == REQ_OP_ZONE_APPEND) + return false; + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) @@ -1084,6 +1088,8 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q, 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 int); +extern void blk_queue_max_zone_append_sectors(struct request_queue *q, + unsigned int max_zone_append_sectors); 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); @@ -1301,6 +1307,11 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } +static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) +{ + return q->limits.max_zone_append_sectors; +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; -- cgit v1.2.3 From 1392d37018d4f68c5bb2c98dae9a018b73926865 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 12 May 2020 17:55:48 +0900 Subject: block: introduce blk_req_zone_write_trylock Introduce blk_req_zone_write_trylock(), which either grabs the write-lock for a sequential zone or returns false, if the zone is already locked. Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5647c78bb876..73f4f4f1df92 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1738,6 +1738,7 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *, #ifdef CONFIG_BLK_DEV_ZONED bool blk_req_needs_zone_write_lock(struct request *rq); +bool blk_req_zone_write_trylock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); void __blk_req_zone_write_unlock(struct request *rq); -- cgit v1.2.3 From e732671aa5f67232cf760666a15242dead003362 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 12 May 2020 17:55:49 +0900 Subject: block: Modify revalidate zones Modify the interface of blk_revalidate_disk_zones() to add an optional driver callback function that a driver can use to extend processing done during zone revalidation. The callback, if defined, is executed with the device request queue frozen, after all zones have been inspected. Signed-off-by: Damien Le Moal Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 73f4f4f1df92..5360696d85ff 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -358,7 +358,8 @@ unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); -extern int blk_revalidate_disk_zones(struct gendisk *disk); +int blk_revalidate_disk_zones(struct gendisk *disk, + void (*update_driver_data)(struct gendisk *disk)); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From 755a7397947e21123d8162eaf7477b614732ff22 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 26 Apr 2020 16:11:43 +0800 Subject: dt-bindings: firmware: imx: Move system control into dt-binding headfile i.MX8 SoCs DTS file needs system control macro definitions, so move them into dt-binding headfile, then include/linux/firmware/imx/types.h can be removed and those drivers using it should be changed accordingly. Signed-off-by: Dong Aisheng Signed-off-by: Jacky Bai Signed-off-by: Anson Huang Signed-off-by: Shawn Guo --- include/linux/firmware/imx/sci.h | 1 - include/linux/firmware/imx/types.h | 65 -------------------------------------- 2 files changed, 66 deletions(-) delete mode 100644 include/linux/firmware/imx/types.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index 17ba4e405129..3fa418a4ca67 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -11,7 +11,6 @@ #define _SC_SCI_H #include -#include #include #include diff --git a/include/linux/firmware/imx/types.h b/include/linux/firmware/imx/types.h deleted file mode 100644 index 80821100e85f..000000000000 --- a/include/linux/firmware/imx/types.h +++ /dev/null @@ -1,65 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright (C) 2016 Freescale Semiconductor, Inc. - * Copyright 2017~2018 NXP - * - * Header file containing types used across multiple service APIs. - */ - -#ifndef _SC_TYPES_H -#define _SC_TYPES_H - -/* - * This type is used to indicate a control. - */ -enum imx_sc_ctrl { - IMX_SC_C_TEMP = 0, - IMX_SC_C_TEMP_HI = 1, - IMX_SC_C_TEMP_LOW = 2, - IMX_SC_C_PXL_LINK_MST1_ADDR = 3, - IMX_SC_C_PXL_LINK_MST2_ADDR = 4, - IMX_SC_C_PXL_LINK_MST_ENB = 5, - IMX_SC_C_PXL_LINK_MST1_ENB = 6, - IMX_SC_C_PXL_LINK_MST2_ENB = 7, - IMX_SC_C_PXL_LINK_SLV1_ADDR = 8, - IMX_SC_C_PXL_LINK_SLV2_ADDR = 9, - IMX_SC_C_PXL_LINK_MST_VLD = 10, - IMX_SC_C_PXL_LINK_MST1_VLD = 11, - IMX_SC_C_PXL_LINK_MST2_VLD = 12, - IMX_SC_C_SINGLE_MODE = 13, - IMX_SC_C_ID = 14, - IMX_SC_C_PXL_CLK_POLARITY = 15, - IMX_SC_C_LINESTATE = 16, - IMX_SC_C_PCIE_G_RST = 17, - IMX_SC_C_PCIE_BUTTON_RST = 18, - IMX_SC_C_PCIE_PERST = 19, - IMX_SC_C_PHY_RESET = 20, - IMX_SC_C_PXL_LINK_RATE_CORRECTION = 21, - IMX_SC_C_PANIC = 22, - IMX_SC_C_PRIORITY_GROUP = 23, - IMX_SC_C_TXCLK = 24, - IMX_SC_C_CLKDIV = 25, - IMX_SC_C_DISABLE_50 = 26, - IMX_SC_C_DISABLE_125 = 27, - IMX_SC_C_SEL_125 = 28, - IMX_SC_C_MODE = 29, - IMX_SC_C_SYNC_CTRL0 = 30, - IMX_SC_C_KACHUNK_CNT = 31, - IMX_SC_C_KACHUNK_SEL = 32, - IMX_SC_C_SYNC_CTRL1 = 33, - IMX_SC_C_DPI_RESET = 34, - IMX_SC_C_MIPI_RESET = 35, - IMX_SC_C_DUAL_MODE = 36, - IMX_SC_C_VOLTAGE = 37, - IMX_SC_C_PXL_LINK_SEL = 38, - IMX_SC_C_OFS_SEL = 39, - IMX_SC_C_OFS_AUDIO = 40, - IMX_SC_C_OFS_PERIPH = 41, - IMX_SC_C_OFS_IRQ = 42, - IMX_SC_C_RST0 = 43, - IMX_SC_C_RST1 = 44, - IMX_SC_C_SEL0 = 45, - IMX_SC_C_LAST -}; - -#endif /* _SC_TYPES_H */ -- cgit v1.2.3 From 32b1924b210a70dcacdf65abd687c5ef86a67541 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 9 Apr 2020 11:29:47 +0300 Subject: ovl: skip overlayfs superblocks at global sync Stacked filesystems like overlayfs has no own writeback, but they have to forward syncfs() requests to backend for keeping data integrity. During global sync() each overlayfs instance calls method ->sync_fs() for backend although it itself is in global list of superblocks too. As a result one syscall sync() could write one superblock several times and send multiple disk barriers. This patch adds flag SB_I_SKIP_SYNC into sb->sb_iflags to avoid that. Reported-by: Dmitry Monakhov Signed-off-by: Konstantin Khlebnikov Reviewed-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..f186a966a36c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1409,6 +1409,8 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 +#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ + /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ -- cgit v1.2.3 From 303cc571d107b3641d6487061b748e70ffe15ce4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 5 May 2020 16:04:31 +0200 Subject: nsproxy: attach to namespaces via pidfds For quite a while we have been thinking about using pidfds to attach to namespaces. This patchset has existed for about a year already but we've wanted to wait to see how the general api would be received and adopted. Now that more and more programs in userspace have started using pidfds for process management it's time to send this one out. This patch makes it possible to use pidfds to attach to the namespaces of another process, i.e. they can be passed as the first argument to the setns() syscall. When only a single namespace type is specified the semantics are equivalent to passing an nsfd. That means setns(nsfd, CLONE_NEWNET) equals setns(pidfd, CLONE_NEWNET). However, when a pidfd is passed, multiple namespace flags can be specified in the second setns() argument and setns() will attach the caller to all the specified namespaces all at once or to none of them. Specifying 0 is not valid together with a pidfd. Here are just two obvious examples: setns(pidfd, CLONE_NEWPID | CLONE_NEWNS | CLONE_NEWNET); setns(pidfd, CLONE_NEWUSER); Allowing to also attach subsets of namespaces supports various use-cases where callers setns to a subset of namespaces to retain privilege, perform an action and then re-attach another subset of namespaces. If the need arises, as Eric suggested, we can extend this patchset to assume even more context than just attaching all namespaces. His suggestion specifically was about assuming the process' root directory when setns(pidfd, 0) or setns(pidfd, SETNS_PIDFD) is specified. For now, just keep it flexible in terms of supporting subsets of namespaces but let's wait until we have users asking for even more context to be assumed. At that point we can add an extension. The obvious example where this is useful is a standard container manager interacting with a running container: pushing and pulling files or directories, injecting mounts, attaching/execing any kind of process, managing network devices all these operations require attaching to all or at least multiple namespaces at the same time. Given that nowadays most containers are spawned with all namespaces enabled we're currently looking at at least 14 syscalls, 7 to open the /proc//ns/ nsfds, another 7 to actually perform the namespace switch. With time namespaces we're looking at about 16 syscalls. (We could amortize the first 7 or 8 syscalls for opening the nsfds by stashing them in each container's monitor process but that would mean we need to send around those file descriptors through unix sockets everytime we want to interact with the container or keep on-disk state. Even in scenarios where a caller wants to join a particular namespace in a particular order callers still profit from batching other namespaces. That mostly applies to the user namespace but all container runtimes I found join the user namespace first no matter if it privileges or deprivileges the container similar to how unshare behaves.) With pidfds this becomes a single syscall no matter how many namespaces are supposed to be attached to. A decently designed, large-scale container manager usually isn't the parent of any of the containers it spawns so the containers don't die when it crashes or needs to update or reinitialize. This means that for the manager to interact with containers through pids is inherently racy especially on systems where the maximum pid number is not significicantly bumped. This is even more problematic since we often spawn and manage thousands or ten-thousands of containers. Interacting with a container through a pid thus can become risky quite quickly. Especially since we allow for an administrator to enable advanced features such as syscall interception where we're performing syscalls in lieu of the container. In all of those cases we use pidfds if they are available and we pass them around as stable references. Using them to setns() to the target process' namespaces is as reliable as using nsfds. Either the target process is already dead and we get ESRCH or we manage to attach to its namespaces but we can't accidently attach to another process' namespaces. So pidfds lend themselves to be used with this api. The other main advantage is that with this change the pidfd becomes the only relevant token for most container interactions and it's the only token we need to create and send around. Apart from significiantly reducing the number of syscalls from double digit to single digit which is a decent reason post-spectre/meltdown this also allows to switch to a set of namespaces atomically, i.e. either attaching to all the specified namespaces succeeds or we fail. If we fail we haven't changed a single namespace. There are currently three namespaces that can fail (other than for ENOMEM which really is not very interesting since we then have other problems anyway) for non-trivial reasons, user, mount, and pid namespaces. We can fail to attach to a pid namespace if it is not our current active pid namespace or a descendant of it. We can fail to attach to a user namespace because we are multi-threaded or because our current mount namespace shares filesystem state with other tasks, or because we're trying to setns() to the same user namespace, i.e. the target task has the same user namespace as we do. We can fail to attach to a mount namespace because it shares filesystem state with other tasks or because we fail to lookup the new root for the new mount namespace. In most non-pathological scenarios these issues can be somewhat mitigated. But there are cases where we're half-attached to some namespace and failing to attach to another one. I've talked about some of these problem during the hallway track (something only the pre-COVID-19 generation will remember) of Plumbers in Los Angeles in 2018(?). Even if all these issues could be avoided with super careful userspace coding it would be nicer to have this done in-kernel. Pidfds seem to lend themselves nicely for this. The other neat thing about this is that setns() becomes an actual counterpart to the namespace bits of unshare(). Signed-off-by: Christian Brauner Reviewed-by: Serge Hallyn Cc: Eric W. Biederman Cc: Serge Hallyn Cc: Jann Horn Cc: Michael Kerrisk Cc: Aleksa Sarai Link: https://lore.kernel.org/r/20200505140432.181565-3-christian.brauner@ubuntu.com --- include/linux/mnt_namespace.h | 1 + include/linux/proc_fs.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 007cfa52efb2..8f882f5881e8 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -11,6 +11,7 @@ struct ns_common; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); +extern struct ns_common *from_mnt_ns(struct mnt_namespace *); extern const struct file_operations proc_mounts_operations; extern const struct file_operations proc_mountinfo_operations; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 45c05fd9c99d..0cfc44d7ac74 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -179,4 +179,6 @@ static inline struct pid_namespace *proc_pid_ns(const struct inode *inode) return inode->i_sb->s_fs_info; } +bool proc_ns_file(const struct file *file); + #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 1597d453289b385237628cd96d57d147632ab105 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 12 May 2020 15:53:20 +0300 Subject: interconnect: Add of_icc_get_by_index() helper function This is the same as the traditional of_icc_get() function, but the difference is that it takes index as an argument, instead of name. Reviewed-by: Matthias Kaehlcke Reviewed-by: Sibi Sankar Link: https://lore.kernel.org/r/20200512125327.1868-4-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index d70a914cba11..34e97231a6ab 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -28,6 +28,7 @@ struct device; struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id); struct icc_path *of_icc_get(struct device *dev, const char *name); +struct icc_path *of_icc_get_by_index(struct device *dev, int idx); void icc_put(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); @@ -46,6 +47,11 @@ static inline struct icc_path *of_icc_get(struct device *dev, return NULL; } +static inline struct icc_path *of_icc_get_by_index(struct device *dev, int idx) +{ + return NULL; +} + static inline void icc_put(struct icc_path *path) { } -- cgit v1.2.3 From 84c1e51d7df85332705ffebc40ef135205492036 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:53:18 -0500 Subject: greybus: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507185318.GA14393@embeddedor Signed-off-by: Greg Kroah-Hartman --- include/linux/greybus/greybus_protocols.h | 44 +++++++++++++++---------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/greybus/greybus_protocols.h b/include/linux/greybus/greybus_protocols.h index dfbc6c39a74b..aeb8f9243545 100644 --- a/include/linux/greybus/greybus_protocols.h +++ b/include/linux/greybus/greybus_protocols.h @@ -345,7 +345,7 @@ struct gb_cap_get_ims_certificate_request { struct gb_cap_get_ims_certificate_response { __u8 result_code; - __u8 certificate[0]; + __u8 certificate[]; } __packed; /* CAP authenticate request/response */ @@ -358,7 +358,7 @@ struct gb_cap_authenticate_request { struct gb_cap_authenticate_response { __u8 result_code; __u8 response[64]; - __u8 signature[0]; + __u8 signature[]; } __packed; @@ -642,7 +642,7 @@ struct gb_hid_get_report_request { struct gb_hid_set_report_request { __u8 report_type; __u8 report_id; - __u8 report[0]; + __u8 report[]; } __packed; /* HID input report request, via interrupt pipe */ @@ -680,7 +680,7 @@ struct gb_i2c_transfer_op { struct gb_i2c_transfer_request { __le16 op_count; - struct gb_i2c_transfer_op ops[0]; /* op_count of these */ + struct gb_i2c_transfer_op ops[]; /* op_count of these */ } __packed; struct gb_i2c_transfer_response { __u8 data[0]; /* inbound data */ @@ -908,7 +908,7 @@ struct gb_spi_transfer_request { __u8 chip_select; /* of the spi device */ __u8 mode; /* of the spi device */ __le16 count; - struct gb_spi_transfer transfers[0]; /* count of these */ + struct gb_spi_transfer transfers[]; /* count of these */ } __packed; struct gb_spi_transfer_response { @@ -1188,7 +1188,7 @@ struct gb_svc_pwrmon_rail_count_get_response { struct gb_svc_pwrmon_rail_names_get_response { __u8 status; - __u8 name[0][GB_SVC_PWRMON_RAIL_NAME_BUFSIZE]; + __u8 name[][GB_SVC_PWRMON_RAIL_NAME_BUFSIZE]; } __packed; #define GB_SVC_PWRMON_TYPE_CURR 0x01 @@ -1281,7 +1281,7 @@ struct gb_svc_intf_oops_request { struct gb_raw_send_request { __le32 len; - __u8 data[0]; + __u8 data[]; } __packed; @@ -1300,7 +1300,7 @@ struct gb_raw_send_request { /* Represents data from AP -> Module */ struct gb_uart_send_data_request { __le16 size; - __u8 data[0]; + __u8 data[]; } __packed; /* recv-data-request flags */ @@ -1313,7 +1313,7 @@ struct gb_uart_send_data_request { struct gb_uart_recv_data_request { __le16 size; __u8 flags; - __u8 data[0]; + __u8 data[]; } __packed; struct gb_uart_receive_credits_request { @@ -1382,14 +1382,14 @@ struct gb_loopback_transfer_request { __le32 len; __le32 reserved0; __le32 reserved1; - __u8 data[0]; + __u8 data[]; } __packed; struct gb_loopback_transfer_response { __le32 len; __le32 reserved0; __le32 reserved1; - __u8 data[0]; + __u8 data[]; } __packed; /* SDIO */ @@ -1530,13 +1530,13 @@ struct gb_sdio_transfer_request { __le16 data_blocks; __le16 data_blksz; - __u8 data[0]; + __u8 data[]; } __packed; struct gb_sdio_transfer_response { __le16 data_blocks; __le16 data_blksz; - __u8 data[0]; + __u8 data[]; } __packed; /* event request: generated by module and is defined as unidirectional */ @@ -1572,7 +1572,7 @@ struct gb_camera_configure_streams_request { __u8 flags; #define GB_CAMERA_CONFIGURE_STREAMS_TEST_ONLY 0x01 __le16 padding; - struct gb_camera_stream_config_request config[0]; + struct gb_camera_stream_config_request config[]; } __packed; /* Greybus Camera Configure Streams response payload */ @@ -1593,7 +1593,7 @@ struct gb_camera_configure_streams_response { __u8 flags; __u8 padding[2]; __le32 data_rate; - struct gb_camera_stream_config_response config[0]; + struct gb_camera_stream_config_response config[]; }; /* Greybus Camera Capture request payload - response has no payload */ @@ -1602,7 +1602,7 @@ struct gb_camera_capture_request { __u8 streams; __u8 padding; __le16 num_frames; - __u8 settings[0]; + __u8 settings[]; } __packed; /* Greybus Camera Flush response payload - request has no payload */ @@ -1616,7 +1616,7 @@ struct gb_camera_metadata_request { __le16 frame_number; __u8 stream; __u8 padding; - __u8 metadata[0]; + __u8 metadata[]; } __packed; /* Lights */ @@ -1993,7 +1993,7 @@ struct gb_audio_integer64 { struct gb_audio_enumerated { __le32 items; __le16 names_length; - __u8 names[0]; + __u8 names[]; } __packed; struct gb_audio_ctl_elem_info { /* See snd_ctl_elem_info in Linux source */ @@ -2033,7 +2033,7 @@ struct gb_audio_widget { __u8 type; /* GB_AUDIO_WIDGET_TYPE_* */ __u8 state; /* GB_AUDIO_WIDGET_STATE_* */ __u8 ncontrols; - struct gb_audio_control ctl[0]; /* 'ncontrols' entries */ + struct gb_audio_control ctl[]; /* 'ncontrols' entries */ } __packed; struct gb_audio_route { @@ -2059,7 +2059,7 @@ struct gb_audio_topology { * struct gb_audio_widget widgets[num_widgets]; * struct gb_audio_route routes[num_routes]; */ - __u8 data[0]; + __u8 data[]; } __packed; struct gb_audio_get_topology_size_response { @@ -2157,7 +2157,7 @@ struct gb_audio_streaming_event_request { struct gb_audio_send_data_request { __le64 timestamp; - __u8 data[0]; + __u8 data[]; } __packed; @@ -2171,7 +2171,7 @@ struct gb_audio_send_data_request { struct gb_log_send_log_request { __le16 len; - __u8 msg[0]; + __u8 msg[]; } __packed; #endif /* __GREYBUS_PROTOCOLS_H */ -- cgit v1.2.3 From 8c49c9ee4a91c158d28c583862718b348881cb16 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 7 May 2020 18:08:57 +0300 Subject: usb: typec: Add typec_find_orientation() Function that converts orientation string into orientation value. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200507150900.12102-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index b00a2642a9cd..5daa1c49761c 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -254,6 +254,7 @@ int typec_set_mode(struct typec_port *port, int mode); void *typec_get_drvdata(struct typec_port *port); +int typec_find_orientation(const char *name); int typec_find_port_power_role(const char *name); int typec_find_power_role(const char *name); int typec_find_port_data_role(const char *name); -- cgit v1.2.3 From d9d200bcebc1f6e56f0178cbb8db9953e8cc9a11 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 13 May 2020 15:32:08 +0200 Subject: dma-mapping: add generic helpers for mapping sgtable objects struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry). It turned out that it was a common mistake to misuse nents and orig_nents entries, calling DMA-mapping functions with a wrong number of entries or ignoring the number of mapped entries returned by the dma_map_sg function. To avoid such issues, let's introduce a common wrappers operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries. Signed-off-by: Marek Szyprowski Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 80 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 330ad58fbf4d..936e30b86cd3 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -609,6 +609,86 @@ static inline void dma_sync_single_range_for_device(struct device *dev, return dma_sync_single_for_device(dev, addr + offset, size, dir); } +/** + * dma_map_sgtable - Map the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Maps a buffer described by a scatterlist stored in the given sg_table + * object for the @dir DMA operation by the @dev device. After success the + * ownership for the buffer is transferred to the DMA domain. One has to + * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the + * ownership of the buffer back to the CPU domain before touching the + * buffer by the CPU. + * + * Returns 0 on success or -EINVAL on error during mapping the buffer. + */ +static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + int nents; + + nents = dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); + if (nents <= 0) + return -EINVAL; + sgt->nents = nents; + return 0; +} + +/** + * dma_unmap_sgtable - Unmap the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the unmap operation + * + * Unmaps a buffer described by a scatterlist stored in the given sg_table + * object for the @dir DMA operation by the @dev device. After this function + * the ownership of the buffer is transferred back to the CPU domain. + */ +static inline void dma_unmap_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + dma_unmap_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); +} + +/** + * dma_sync_sgtable_for_cpu - Synchronize the given buffer for CPU access + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * + * Performs the needed cache synchronization and moves the ownership of the + * buffer back to the CPU domain, so it is safe to perform any access to it + * by the CPU. Before doing any further DMA operations, one has to transfer + * the ownership of the buffer back to the DMA domain by calling the + * dma_sync_sgtable_for_device(). + */ +static inline void dma_sync_sgtable_for_cpu(struct device *dev, + struct sg_table *sgt, enum dma_data_direction dir) +{ + dma_sync_sg_for_cpu(dev, sgt->sgl, sgt->orig_nents, dir); +} + +/** + * dma_sync_sgtable_for_device - Synchronize the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * + * Performs the needed cache synchronization and moves the ownership of the + * buffer back to the DMA domain, so it is safe to perform the DMA operation. + * Once finished, one has to call dma_sync_sgtable_for_cpu() or + * dma_unmap_sgtable(). + */ +static inline void dma_sync_sgtable_for_device(struct device *dev, + struct sg_table *sgt, enum dma_data_direction dir) +{ + dma_sync_sg_for_device(dev, sgt->sgl, sgt->orig_nents, dir); +} + #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0) #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0) #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0) -- cgit v1.2.3 From 709d6d73c756107fb8a292a9f957d630097425fa Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 13 May 2020 15:32:09 +0200 Subject: scatterlist: add generic wrappers for iterating over sgtable objects struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry). It turned out that it was a common mistake to misuse nents and orig_nents entries, calling the scatterlist iterating functions with a wrong number of the entries. To avoid such issues, lets introduce a common wrappers operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries. While touching this, lets clarify some ambiguities in the comments for the existing for_each helpers. Signed-off-by: Marek Szyprowski Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/scatterlist.h | 50 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 47 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 6eec50fb36c8..4f922afb607a 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -151,6 +151,20 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, #define for_each_sg(sglist, sg, nr, __i) \ for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg)) +/* + * Loop over each sg element in the given sg_table object. + */ +#define for_each_sgtable_sg(sgt, sg, i) \ + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) + +/* + * Loop over each sg element in the given *DMA mapped* sg_table object. + * Please use sg_dma_address(sg) and sg_dma_len(sg) to extract DMA addresses + * of the each element. + */ +#define for_each_sgtable_dma_sg(sgt, sg, i) \ + for_each_sg(sgt->sgl, sg, sgt->nents, i) + /** * sg_chain - Chain two sglists together * @prv: First scatterlist @@ -401,9 +415,10 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) * @sglist: sglist to iterate over * @piter: page iterator to hold current page, sg, sg_pgoffset * @nents: maximum number of sg entries to iterate over - * @pgoffset: starting page offset + * @pgoffset: starting page offset (in pages) * * Callers may use sg_page_iter_page() to get each page pointer. + * In each loop it operates on PAGE_SIZE unit. */ #define for_each_sg_page(sglist, piter, nents, pgoffset) \ for (__sg_page_iter_start((piter), (sglist), (nents), (pgoffset)); \ @@ -412,18 +427,47 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) /** * for_each_sg_dma_page - iterate over the pages of the given sg list * @sglist: sglist to iterate over - * @dma_iter: page iterator to hold current page + * @dma_iter: DMA page iterator to hold current page * @dma_nents: maximum number of sg entries to iterate over, this is the value * returned from dma_map_sg - * @pgoffset: starting page offset + * @pgoffset: starting page offset (in pages) * * Callers may use sg_page_iter_dma_address() to get each page's DMA address. + * In each loop it operates on PAGE_SIZE unit. */ #define for_each_sg_dma_page(sglist, dma_iter, dma_nents, pgoffset) \ for (__sg_page_iter_start(&(dma_iter)->base, sglist, dma_nents, \ pgoffset); \ __sg_page_iter_dma_next(dma_iter);) +/** + * for_each_sgtable_page - iterate over all pages in the sg_table object + * @sgt: sg_table object to iterate over + * @piter: page iterator to hold current page + * @pgoffset: starting page offset (in pages) + * + * Iterates over the all memory pages in the buffer described by + * a scatterlist stored in the given sg_table object. + * See also for_each_sg_page(). In each loop it operates on PAGE_SIZE unit. + */ +#define for_each_sgtable_page(sgt, piter, pgoffset) \ + for_each_sg_page(sgt->sgl, piter, sgt->orig_nents, pgoffset) + +/** + * for_each_sgtable_dma_page - iterate over the DMA mapped sg_table object + * @sgt: sg_table object to iterate over + * @dma_iter: DMA page iterator to hold current page + * @pgoffset: starting page offset (in pages) + * + * Iterates over the all DMA mapped pages in the buffer described by + * a scatterlist stored in the given sg_table object. + * See also for_each_sg_dma_page(). In each loop it operates on PAGE_SIZE + * unit. + */ +#define for_each_sgtable_dma_page(sgt, dma_iter, pgoffset) \ + for_each_sg_dma_page(sgt->sgl, dma_iter, sgt->nents, pgoffset) + + /* * Mapping sg iterator * -- cgit v1.2.3 From 48530d9fab0d3bf08827f9167be54acf66d4d457 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 13 May 2020 15:32:10 +0200 Subject: iommu: add generic helper for mapping sgtable objects struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry). It turned out that it was a common mistake to misuse nents and orig_nents entries, calling mapping functions with a wrong number of entries. To avoid such issues, lets introduce a common wrapper operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries. Signed-off-by: Marek Szyprowski Acked-by: Joerg Roedel Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/iommu.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7ef8b0bda695..b1bfbe6dff42 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -466,6 +466,22 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); +/** + * iommu_map_sgtable - Map the given buffer to the IOMMU domain + * @domain: The IOMMU domain to perform the mapping + * @iova: The start address to map the buffer + * @sgt: The sg_table object describing the buffer + * @prot: IOMMU protection bits + * + * Creates a mapping at @iova for the buffer described by a scatterlist + * stored in the given sg_table object in the provided IOMMU domain. + */ +static inline size_t iommu_map_sgtable(struct iommu_domain *domain, + unsigned long iova, struct sg_table *sgt, int prot) +{ + return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); +} + 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, -- cgit v1.2.3 From dae2f8ed7992e88c8d62c54e8295ffc8475b4a80 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:37 -0700 Subject: fs: Lift XFS_IDONTCACHE to the VFS layer DAX effective mode (S_DAX) changes requires inode eviction. XFS has an advisory flag (XFS_IDONTCACHE) to prevent caching of the inode if no other additional references are taken. We lift this flag to the VFS layer and change the behavior slightly by allowing the flag to remain even if multiple references are taken. This will expedite the eviction of inodes to change S_DAX. Cc: Al Viro Reviewed-by: Dave Chinner Reviewed-by: Jan Kara Signed-off-by: Ira Weiny Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- 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 a87cc5845a02..44bd45af760f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2156,6 +2156,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_CREATING New object's inode in the middle of setting up. * + * I_DONTCACHE Evict inode as soon as it is not used anymore. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2178,6 +2180,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) +#define I_DONTCACHE (1 << 16) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -3049,7 +3052,8 @@ extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { - return !inode->i_nlink || inode_unhashed(inode); + return !inode->i_nlink || inode_unhashed(inode) || + (inode->i_state & I_DONTCACHE); } extern struct inode *ilookup5_nowait(struct super_block *sb, -- cgit v1.2.3 From 2c567af418e3f9380c2051aada58b4e5a4b5c2ad Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:37 -0700 Subject: fs: Introduce DCACHE_DONTCACHE DCACHE_DONTCACHE indicates a dentry should not be cached on final dput(). Also add a helper function to mark DCACHE_DONTCACHE on all dentries pointing to a specific inode when that inode is being set I_DONTCACHE. This facilitates dropping dentry references to inodes sooner which require eviction to swap S_DAX mode. Cc: Al Viro Signed-off-by: Ira Weiny Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/dcache.h | 2 ++ include/linux/fs.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c1488cc84fd9..a81f0c3cf352 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -177,6 +177,8 @@ struct dentry_operations { #define DCACHE_REFERENCED 0x00000040 /* Recently used, don't discard. */ +#define DCACHE_DONTCACHE 0x00000080 /* Purge from memory on final dput() */ + #define DCACHE_CANT_MOUNT 0x00000100 #define DCACHE_GENOCIDE 0x00000200 #define DCACHE_SHRINK_LIST 0x00000400 diff --git a/include/linux/fs.h b/include/linux/fs.h index 44bd45af760f..7c3e8c0306e0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3055,6 +3055,7 @@ static inline int generic_drop_inode(struct inode *inode) return !inode->i_nlink || inode_unhashed(inode) || (inode->i_state & I_DONTCACHE); } +extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), -- cgit v1.2.3 From 9254f8ed15b6dcc9b04b9ad32863a7518cc5a5b1 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 4 May 2020 08:30:10 +0300 Subject: net/mlx5: Add support in forward to namespace Currently, fs_core supports rule of forward the traffic to continue matching in the next priority, now we add support to forward the traffic matching in the next namespace. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky --- 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 e2d13e074067..6c5aa0a21425 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -42,6 +42,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17, MLX5_FLOW_CONTEXT_ACTION_DECRYPT = 1 << 18, + MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS = 1 << 19, }; enum { -- cgit v1.2.3 From 9d9a6ebfea329cadeda87544dceae01e9c27aaef Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:34 -0700 Subject: rcuwait: Let rcuwait_wake_up() return whether or not a task was awoken Propagating the return value of wake_up_process() back to the caller can come in handy for future users, such as for statistics or accounting purposes. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-3-dave@stgolabs.net> Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 2ffe1ee6d482..6ebb23258a27 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -25,7 +25,7 @@ static inline void rcuwait_init(struct rcuwait *w) w->task = NULL; } -extern void rcuwait_wake_up(struct rcuwait *w); +extern int rcuwait_wake_up(struct rcuwait *w); /* * The caller is responsible for locking around rcuwait_wait_event(), -- cgit v1.2.3 From 5c21f7b322cb9fcb97f2e22f5976a0ae8dd71354 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:35 -0700 Subject: rcuwait: Introduce prepare_to and finish_rcuwait This allows further flexibility for some callers to implement ad-hoc versions of the generic rcuwait_wait_event(). For example, kvm will need this to maintain tracing semantics. The naming is of course similar to what waitqueue apis offer. Also go ahead and make use of rcu_assign_pointer() for both task writes as it will make the __rcu sparse people happy - this will be the special nil case, thus no added serialization. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-4-dave@stgolabs.net> Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 6ebb23258a27..45bc6604e9b1 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -29,12 +29,25 @@ extern int rcuwait_wake_up(struct rcuwait *w); /* * The caller is responsible for locking around rcuwait_wait_event(), - * such that writes to @task are properly serialized. + * and [prepare_to/finish]_rcuwait() such that writes to @task are + * properly serialized. */ + +static inline void prepare_to_rcuwait(struct rcuwait *w) +{ + rcu_assign_pointer(w->task, current); +} + +static inline void finish_rcuwait(struct rcuwait *w) +{ + rcu_assign_pointer(w->task, NULL); + __set_current_state(TASK_RUNNING); +} + #define rcuwait_wait_event(w, condition, state) \ ({ \ int __ret = 0; \ - rcu_assign_pointer((w)->task, current); \ + prepare_to_rcuwait(w); \ for (;;) { \ /* \ * Implicit barrier (A) pairs with (B) in \ @@ -51,9 +64,7 @@ extern int rcuwait_wake_up(struct rcuwait *w); \ schedule(); \ } \ - \ - WRITE_ONCE((w)->task, NULL); \ - __set_current_state(TASK_RUNNING); \ + finish_rcuwait(w); \ __ret; \ }) -- cgit v1.2.3 From 191a43be61d6791fd4a9098a35c1a09e73f55228 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:36 -0700 Subject: rcuwait: Introduce rcuwait_active() This call is lockless and thus should not be trusted blindly. For example, the return value of rcuwait_wakeup() should be used to track whether a process was woken up. Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-5-dave@stgolabs.net> Acked-by: Peter Zijlstra (Intel) Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 45bc6604e9b1..c1414ce44abc 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -25,6 +25,15 @@ static inline void rcuwait_init(struct rcuwait *w) w->task = NULL; } +/* + * Note: this provides no serialization and, just as with waitqueues, + * requires care to estimate as to whether or not the wait is active. + */ +static inline int rcuwait_active(struct rcuwait *w) +{ + return !!rcu_dereference(w->task); +} + extern int rcuwait_wake_up(struct rcuwait *w); /* -- cgit v1.2.3 From da4ad88cab5867ee240dfd0585e9d115a8cc47db Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:37 -0700 Subject: kvm: Replace vcpu->swait with rcuwait The use of any sort of waitqueue (simple or regular) for wait/waking vcpus has always been an overkill and semantically wrong. Because this is per-vcpu (which is blocked) there is only ever a single waiting vcpu, thus no need for any sort of queue. As such, make use of the rcuwait primitive, with the following considerations: - rcuwait already provides the proper barriers that serialize concurrent waiter and waker. - Task wakeup is done in rcu read critical region, with a stable task pointer. - Because there is no concurrency among waiters, we need not worry about rcuwait_wait_event() calls corrupting the wait->task. As a consequence, this saves the locking done in swait when modifying the queue. This also applies to per-vcore wait for powerpc kvm-hv. The x86 tscdeadline_latency test mentioned in 8577370fb0cb ("KVM: Use simple waitqueue for vcpu->wq") shows that, on avg, latency is reduced by around 15-20% with this change. Cc: Paul Mackerras Cc: kvmarm@lists.cs.columbia.edu Cc: linux-mips@vger.kernel.org Reviewed-by: Marc Zyngier Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-6-dave@stgolabs.net> [Avoid extra logic changes. - Paolo] Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index abfa71cb5d2d..161684696610 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -277,7 +277,7 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - struct swait_queue_head wq; + struct rcuwait wait; struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -960,12 +960,12 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) } #endif -static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP - return vcpu->arch.wqp; + return vcpu->arch.waitp; #else - return &vcpu->wq; + return &vcpu->wait; #endif } -- cgit v1.2.3 From d06cfe3f123c50449a0c3ece21bc16668289c50f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Apr 2020 15:58:21 -0500 Subject: bus: vexpress-config: Merge vexpress-syscfg into vexpress-config The only thing that vexpress-syscfg does is provide a regmap to vexpress-config bus child devices. There's little reason to have 2 components for this. The current structure with initcall ordering requirements makes turning these components into modules more difficult. So let's start to simplify things and merge vexpress-syscfg into vexpress-config. There's no functional change in this commit and it's still separate components until subsequent commits. Cc: Lorenzo Pieralisi Cc: Linus Walleij Cc: Arnd Bergmann Reviewed-by: Sudeep Holla Acked-by: Greg Kroah-Hartman Acked-by: Liviu Dudau Signed-off-by: Rob Herring --- include/linux/vexpress.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index 2ec7992b054c..65096c792d57 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -18,23 +18,6 @@ /* Config infrastructure */ void vexpress_config_set_master(u32 site); -u32 vexpress_config_get_master(void); - -void vexpress_config_lock(void *arg); -void vexpress_config_unlock(void *arg); - -int vexpress_config_get_topo(struct device_node *node, u32 *site, - u32 *position, u32 *dcc); - -/* Config bridge API */ - -struct vexpress_config_bridge_ops { - struct regmap * (*regmap_init)(struct device *dev, void *context); - void (*regmap_exit)(struct regmap *regmap, void *context); -}; - -struct device *vexpress_config_bridge_register(struct device *parent, - struct vexpress_config_bridge_ops *ops, void *context); /* Config regmap API */ -- cgit v1.2.3 From 310f80d61717425fbf799ef0ff0926e64cd57d9c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Apr 2020 15:58:23 -0500 Subject: vexpress: Move setting master site to vexpress-config bus There's only a single caller of vexpress_config_set_master() from vexpress-sysreg.c. Let's just make the registers needed available to vexpress-config and move all the code there. The registers needed aren't used anywhere else either. With this, we can get rid of the private API between these 2 drivers. Cc: Lorenzo Pieralisi Cc: Linus Walleij Cc: Greg Kroah-Hartman Acked-by: Liviu Dudau Acked-by: Sudeep Holla Acked-by: Lee Jones Signed-off-by: Rob Herring --- include/linux/vexpress.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index 65096c792d57..2f9dd072f11f 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -10,15 +10,6 @@ #include #include -#define VEXPRESS_SITE_MB 0 -#define VEXPRESS_SITE_DB1 1 -#define VEXPRESS_SITE_DB2 2 -#define VEXPRESS_SITE_MASTER 0xf - -/* Config infrastructure */ - -void vexpress_config_set_master(u32 site); - /* Config regmap API */ struct regmap *devm_regmap_init_vexpress_config(struct device *dev); -- cgit v1.2.3 From 21aef70eade22a656297c28d5da93301915d2ac2 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:16 -0700 Subject: bpf: Change btf_iter func proto prefix to "bpf_iter_" This is to be consistent with tracing and lsm programs which have prefix "bpf_trace_" and "bpf_lsm_" respectively. Suggested-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200513180216.2949387-1-yhs@fb.com --- include/linux/bpf.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cf4b6e44f2bc..ab94dfd8826f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1131,10 +1131,10 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); -#define BPF_ITER_FUNC_PREFIX "__bpf_iter__" +#define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ - extern int __bpf_iter__ ## target(args); \ - int __init __bpf_iter__ ## target(args) { return 0; } + extern int bpf_iter_ ## target(args); \ + int __init bpf_iter_ ## target(args) { return 0; } typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); -- cgit v1.2.3 From 15172a46fa2796c1a1358a36babd31274716ed41 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:19 -0700 Subject: bpf: net: Refactor bpf_iter target registration Currently bpf_iter_reg_target takes parameters from target and allocates memory to save them. This is really not necessary, esp. in the future we may grow information passed from targets to bpf_iter manager. The patch refactors the code so target reg_info becomes static and bpf_iter manager can just take a reference to it. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200513180219.2949605-1-yhs@fb.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 ab94dfd8826f..6fa773e2d1bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1153,7 +1153,7 @@ struct bpf_iter_meta { u64 seq_num; }; -int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); +int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); -- cgit v1.2.3 From ab2ee4fcb9d61fd57db70db694adbcf54662bd80 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:20 -0700 Subject: bpf: Change func bpf_iter_unreg_target() signature Change func bpf_iter_unreg_target() parameter from target name to target reg_info, similar to bpf_iter_reg_target(). Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200513180220.2949737-1-yhs@fb.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 6fa773e2d1bf..534174eca86b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1154,7 +1154,7 @@ struct bpf_iter_meta { }; int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); -void bpf_iter_unreg_target(const char *target); +void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); -- cgit v1.2.3 From 3c32cc1bceba8a1755dc35cd97516f6c67856844 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:21 -0700 Subject: bpf: Enable bpf_iter targets registering ctx argument types Commit b121b341e598 ("bpf: Add PTR_TO_BTF_ID_OR_NULL support") adds a field btf_id_or_null_non0_off to bpf_prog->aux structure to indicate that the first ctx argument is PTR_TO_BTF_ID reg_type and all others are PTR_TO_BTF_ID_OR_NULL. This approach does not really scale if we have other different reg types in the future, e.g., a pointer to a buffer. This patch enables bpf_iter targets registering ctx argument reg types which may be different from the default one. For example, for pointers to structures, the default reg_type is PTR_TO_BTF_ID for tracing program. The target can register a particular pointer type as PTR_TO_BTF_ID_OR_NULL which can be used by the verifier to enforce accesses. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200513180221.2949882-1-yhs@fb.com --- 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 534174eca86b..c45d198ac38c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -643,6 +643,12 @@ struct bpf_jit_poke_descriptor { u16 reason; }; +/* reg_type info for ctx arguments */ +struct bpf_ctx_arg_aux { + u32 offset; + enum bpf_reg_type reg_type; +}; + struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; @@ -654,12 +660,13 @@ struct bpf_prog_aux { u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + u32 ctx_arg_info_size; + const struct bpf_ctx_arg_aux *ctx_arg_info; struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; - bool btf_id_or_null_non0_off; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; @@ -1139,12 +1146,15 @@ int bpf_obj_get_user(const char __user *pathname, int flags); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); +#define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; + u32 ctx_arg_info_size; + struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; }; struct bpf_iter_meta { -- cgit v1.2.3 From 11ecf8c55b91806e4dc6a1b9fe7cbf68cdc9b006 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 13 May 2020 18:35:23 +0200 Subject: net: phy: broadcom: add cable test support Most modern broadcom PHYs support ECD (enhanced cable diagnostics). Add support for it in the bcm-phy-lib so they can easily be used in the PHY driver. There are two access methods for ECD: legacy by expansion registers and via the new RDB registers which are exclusive. Provide functions in two variants where the PHY driver can choose from. To keep things simple for now, we just switch the register access to expansion registers in the RDB variant for now. On the flipside, we have to keep a bus lock to prevent any other non-legacy access on the PHY. The results of the intra-pair tests are inconclusive (at least for the BCM54140). Most of the times half the length is reported but sometimes the length is correct. Signed-off-by: Michael Walle Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 58d0150acc3e..d41624db6de2 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -119,6 +119,11 @@ #define MII_BCM54XX_RDB_ADDR 0x1e #define MII_BCM54XX_RDB_DATA 0x1f +/* legacy access control via rdb/expansion register */ +#define BCM54XX_RDB_REG0087 0x0087 +#define BCM54XX_EXP_REG7E (MII_BCM54XX_EXP_SEL_ER + 0x7E) +#define BCM54XX_ACCESS_MODE_LEGACY_EN BIT(15) + /* * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) */ @@ -294,4 +299,51 @@ #define MII_BRCM_CORE_EXPB0 0xB0 #define MII_BRCM_CORE_EXPB1 0xB1 +/* Enhanced Cable Diagnostics */ +#define BCM54XX_RDB_ECD_CTRL 0x2a0 +#define BCM54XX_EXP_ECD_CTRL (MII_BCM54XX_EXP_SEL_ER + 0xc0) + +#define BCM54XX_ECD_CTRL_CABLE_TYPE_CAT3 1 /* CAT3 or worse */ +#define BCM54XX_ECD_CTRL_CABLE_TYPE_CAT5 0 /* CAT5 or better */ +#define BCM54XX_ECD_CTRL_CABLE_TYPE_MASK BIT(0) /* cable type */ +#define BCM54XX_ECD_CTRL_INVALID BIT(3) /* invalid result */ +#define BCM54XX_ECD_CTRL_UNIT_CM 0 /* centimeters */ +#define BCM54XX_ECD_CTRL_UNIT_M 1 /* meters */ +#define BCM54XX_ECD_CTRL_UNIT_MASK BIT(10) /* cable length unit */ +#define BCM54XX_ECD_CTRL_IN_PROGRESS BIT(11) /* test in progress */ +#define BCM54XX_ECD_CTRL_BREAK_LINK BIT(12) /* unconnect link + * during test + */ +#define BCM54XX_ECD_CTRL_CROSS_SHORT_DIS BIT(13) /* disable inter-pair + * short check + */ +#define BCM54XX_ECD_CTRL_RUN BIT(15) /* run immediate */ + +#define BCM54XX_RDB_ECD_FAULT_TYPE 0x2a1 +#define BCM54XX_EXP_ECD_FAULT_TYPE (MII_BCM54XX_EXP_SEL_ER + 0xc1) +#define BCM54XX_ECD_FAULT_TYPE_INVALID 0x0 +#define BCM54XX_ECD_FAULT_TYPE_OK 0x1 +#define BCM54XX_ECD_FAULT_TYPE_OPEN 0x2 +#define BCM54XX_ECD_FAULT_TYPE_SAME_SHORT 0x3 /* short same pair */ +#define BCM54XX_ECD_FAULT_TYPE_CROSS_SHORT 0x4 /* short different pairs */ +#define BCM54XX_ECD_FAULT_TYPE_BUSY 0x9 +#define BCM54XX_ECD_FAULT_TYPE_PAIR_D_MASK GENMASK(3, 0) +#define BCM54XX_ECD_FAULT_TYPE_PAIR_C_MASK GENMASK(7, 4) +#define BCM54XX_ECD_FAULT_TYPE_PAIR_B_MASK GENMASK(11, 8) +#define BCM54XX_ECD_FAULT_TYPE_PAIR_A_MASK GENMASK(15, 12) +#define BCM54XX_ECD_PAIR_A_LENGTH_RESULTS 0x2a2 +#define BCM54XX_ECD_PAIR_B_LENGTH_RESULTS 0x2a3 +#define BCM54XX_ECD_PAIR_C_LENGTH_RESULTS 0x2a4 +#define BCM54XX_ECD_PAIR_D_LENGTH_RESULTS 0x2a5 + +#define BCM54XX_RDB_ECD_PAIR_A_LENGTH_RESULTS 0x2a2 +#define BCM54XX_EXP_ECD_PAIR_A_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc2) +#define BCM54XX_RDB_ECD_PAIR_B_LENGTH_RESULTS 0x2a3 +#define BCM54XX_EXP_ECD_PAIR_B_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc3) +#define BCM54XX_RDB_ECD_PAIR_C_LENGTH_RESULTS 0x2a4 +#define BCM54XX_EXP_ECD_PAIR_C_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc4) +#define BCM54XX_RDB_ECD_PAIR_D_LENGTH_RESULTS 0x2a5 +#define BCM54XX_EXP_ECD_PAIR_D_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc5) +#define BCM54XX_ECD_LENGTH_RESULTS_INVALID 0xffff + #endif /* _LINUX_BRCMPHY_H */ -- cgit v1.2.3 From 3d8c11efd528d56972d44ed0de51c4e11a9a4fa9 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 12 May 2020 13:55:02 +0900 Subject: efi: cper: Add support for printing Firmware Error Record Reference While debugging a boot failure, the following unknown error record was seen in the boot logs. <...> BERT: Error records from previous boot: [Hardware Error]: event severity: fatal [Hardware Error]: Error 0, type: fatal [Hardware Error]: section type: unknown, 81212a96-09ed-4996-9471-8d729c8e69ed [Hardware Error]: section length: 0x290 [Hardware Error]: 00000000: 00000001 00000000 00000000 00020002 ................ [Hardware Error]: 00000010: 00020002 0000001f 00000320 00000000 ........ ....... [Hardware Error]: 00000020: 00000000 00000000 00000000 00000000 ................ [Hardware Error]: 00000030: 00000000 00000000 00000000 00000000 ................ <...> On further investigation, it was found that the error record with UUID (81212a96-09ed-4996-9471-8d729c8e69ed) has been defined in the UEFI Specification at least since v2.4 and has recently had additional fields defined in v2.7 Section N.2.10 Firmware Error Record Reference. Add support for parsing and printing the defined fields to give users a chance to figure out what went wrong. Signed-off-by: Punit Agrawal Cc: Ard Biesheuvel Cc: "Rafael J. Wysocki" Cc: Borislav Petkov Cc: James Morse Cc: linux-acpi@vger.kernel.org Cc: linux-efi@vger.kernel.org Link: https://lore.kernel.org/r/20200512045502.3810339-1-punit1.agrawal@toshiba.co.jp Signed-off-by: Ard Biesheuvel --- include/linux/cper.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h index 4f005d95ce88..8537e9282a65 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -521,6 +521,15 @@ struct cper_sec_pcie { u8 aer_info[96]; }; +/* Firmware Error Record Reference, UEFI v2.7 sec N.2.10 */ +struct cper_sec_fw_err_rec_ref { + u8 record_type; + u8 revision; + u8 reserved[6]; + u64 record_identifier; + guid_t record_identifier_guid; +}; + /* Reset to default packing */ #pragma pack() -- cgit v1.2.3 From f45ce9336ff0640e491c642a84ea02f21daac3a4 Mon Sep 17 00:00:00 2001 From: Gwan-gyeong Mun Date: Thu, 14 May 2020 09:07:19 +0300 Subject: video/hdmi: Add Unpack only function for DRM infoframe It adds an unpack only function for DRM infoframe for dynamic range and mastering infoframe readout. It unpacks the information data block contained in the binary buffer into a structured frame of the HDMI Dynamic Range and Mastering (DRM) information frame. In contrast to hdmi_drm_infoframe_unpack() function, it does not verify a checksum. It can be used for unpacking a DP HDR Metadata Infoframe SDP case. DP HDR Metadata Infoframe SDP uses the same Dynamic Range and Mastering (DRM) information (CTA-861-G spec.) such as HDMI DRM infoframe. But DP SDP header and payload structure are different from HDMI DRM Infoframe. Therefore unpacking DRM infoframe for DP requires skipping of a verifying checksum. v9: Add clear comments to hdmi_drm_infoframe_unpack_only() and hdmi_drm_infoframe_unpack() (Laurent Pinchart) Signed-off-by: Gwan-gyeong Mun Reviewed-by: Uma Shankar Cc: Laurent Pinchart Cc: Ville Syrjala Acked-by: Daniel Vetter Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20200514060732.3378396-2-gwan-gyeong.mun@intel.com --- include/linux/hdmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 9613d796cfb1..50c31f1a0a2d 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -219,6 +219,8 @@ ssize_t hdmi_drm_infoframe_pack(struct hdmi_drm_infoframe *frame, void *buffer, ssize_t hdmi_drm_infoframe_pack_only(const struct hdmi_drm_infoframe *frame, void *buffer, size_t size); int hdmi_drm_infoframe_check(struct hdmi_drm_infoframe *frame); +int hdmi_drm_infoframe_unpack_only(struct hdmi_drm_infoframe *frame, + const void *buffer, size_t size); enum hdmi_spd_sdi { HDMI_SPD_SDI_UNKNOWN, -- cgit v1.2.3 From 2909438d4d62681f392c57df4cd6b7183d19dde0 Mon Sep 17 00:00:00 2001 From: Wang Wenhu Date: Wed, 13 May 2020 07:18:54 -0700 Subject: cpufreq: fix minor typo in struct cpufreq_driver doc comment Delete the duplicate "to", possibly double-typed. Signed-off-by: Wang Wenhu Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index f7240251a949..67d5950bd878 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -330,7 +330,7 @@ struct cpufreq_driver { * * get_intermediate should return a stable intermediate frequency * platform wants to switch to and target_intermediate() should set CPU - * to to that frequency, before jumping to the frequency corresponding + * to that frequency, before jumping to the frequency corresponding * to 'index'. Core will take care of sending notifications and driver * doesn't have to handle them in target_intermediate() or * target_index(). -- cgit v1.2.3 From 71ac860af824ce9ebbbe8de20044e777c0fc33b9 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 14 May 2020 16:45:09 +0800 Subject: block: move blk_io_schedule() out of header file blk_io_schedule() isn't called from performance sensitive code path, and it is easier to maintain by exporting it as symbol. Also blk_io_schedule() is only called by CONFIG_BLOCK code, so it is safe to do this way. Meantime fixes build failure when CONFIG_BLOCK is off. Cc: Christoph Hellwig Fixes: e6249cdd46e4 ("block: add blk_io_schedule() for avoiding task hung in sync dio") Reported-by: Satya Tangirala Tested-by: Satya Tangirala Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5360696d85ff..f9e4b21b051b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,7 +27,6 @@ #include #include #include -#include struct module; struct scsi_ioctl_command; @@ -1221,6 +1220,8 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } +extern void blk_io_schedule(void); + extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); @@ -1851,15 +1852,4 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -static inline void blk_io_schedule(void) -{ - /* Prevent hang_check timer from firing at us during very long I/O */ - unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; - - if (timeout) - io_schedule_timeout(timeout); - else - io_schedule(); -} - #endif -- cgit v1.2.3 From a3c751a50fe6bbe50eb7622a14b18b361804ee0c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:23 +0200 Subject: vfs: allow unprivileged whiteout creation Whiteouts, unlike real device node should not require privileges to create. The general concern with device nodes is that opening them can have side effects. The kernel already avoids zero major (see Documentation/admin-guide/devices.txt). To be on the safe side the patch explicitly forbids registering a char device with 0/0 number (see cdev_add()). This guarantees that a non-O_PATH open on a whiteout will fail with ENODEV; i.e. it won't have any side effect. Signed-off-by: Miklos Szeredi --- include/linux/device_cgroup.h | 3 +++ include/linux/fs.h | 6 +++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index fa35b52e0002..57e63bd63370 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -51,6 +51,9 @@ static inline int devcgroup_inode_mknod(int mode, dev_t dev) if (!S_ISBLK(mode) && !S_ISCHR(mode)) return 0; + if (S_ISCHR(mode) && dev == WHITEOUT_DEV) + return 0; + if (S_ISBLK(mode)) type = DEVCG_DEV_BLOCK; else diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..15665ef1ef90 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1721,7 +1721,11 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct ino extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); -extern int vfs_whiteout(struct inode *, struct dentry *); + +static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) +{ + return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); +} extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag); -- cgit v1.2.3 From 9f6c61f96f2d97cbb5f7fa85607bc398f843ff0f Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:24 +0200 Subject: proc/mounts: add cursor If mounts are deleted after a read(2) call on /proc/self/mounts (or its kin), the subsequent read(2) could miss a mount that comes after the deleted one in the list. This is because the file position is interpreted as the number mount entries from the start of the list. E.g. first read gets entries #0 to #9; the seq file index will be 10. Then entry #5 is deleted, resulting in #10 becoming #9 and #11 becoming #10, etc... The next read will continue from entry #10, and #9 is missed. Solve this by adding a cursor entry for each open instance. Taking the global namespace_sem for write seems excessive, since we are only dealing with a per-namespace list. Instead add a per-namespace spinlock and use that together with namespace_sem taken for read to protect against concurrent modification of the mount list. This may reduce parallelism of is_local_mountpoint(), but it's hardly a big contention point. We could also use RCU freeing of cursors to make traversal not need additional locks, if that turns out to be neceesary. Only move the cursor once for each read (cursor is not added on open) to minimize cacheline invalidation. When EOF is reached, the cursor is taken off the list, in order to prevent an excessive number of cursors due to inactive open file descriptors. Reported-by: Karel Zak Signed-off-by: Miklos Szeredi --- include/linux/mount.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index bf8cc4108b8f..7edac8c7a9c1 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -50,7 +50,8 @@ struct fs_context; #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \ + MNT_CURSOR) #define MNT_INTERNAL 0x4000 @@ -64,6 +65,7 @@ struct fs_context; #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 +#define MNT_CURSOR 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ -- cgit v1.2.3 From fa2fcf4f1df1559a0a4ee0f46915b496cc2ebf60 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:24 +0200 Subject: statx: add mount ID Systemd is hacking around to get it and it's trivial to add to statx, so... Cc: linux-api@vger.kernel.org Cc: linux-man@vger.kernel.org Signed-off-by: Miklos Szeredi Reviewed-by: Christoph Hellwig --- include/linux/stat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stat.h b/include/linux/stat.h index 528c4baad091..56614af83d4a 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -47,6 +47,7 @@ struct kstat { struct timespec64 ctime; struct timespec64 btime; /* File creation time */ u64 blocks; + u64 mnt_id; }; #endif -- cgit v1.2.3 From c8ffd8bcdd28296a198f237cc595148a8d4adfbe Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:25 +0200 Subject: vfs: add faccessat2 syscall POSIX defines faccessat() as having a fourth "flags" argument, while the linux syscall doesn't have it. Glibc tries to emulate AT_EACCESS and AT_SYMLINK_NOFOLLOW, but AT_EACCESS emulation is broken. Add a new faccessat(2) syscall with the added flags argument and implement both flags. The value of AT_EACCESS is defined in glibc headers to be the same as AT_REMOVEDIR. Use this value for the kernel interface as well, together with the explanatory comment. Also add AT_EMPTY_PATH support, which is not documented by POSIX, but can be useful and is trivial to implement. Signed-off-by: Miklos Szeredi --- include/linux/syscalls.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1815065d52f3..7c354c2955f5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -428,6 +428,8 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); #endif asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); +asmlinkage long sys_faccessat2(int dfd, const char __user *filename, int mode, + int flags); asmlinkage long sys_chdir(const char __user *filename); asmlinkage long sys_fchdir(unsigned int fd); asmlinkage long sys_chroot(const char __user *filename); @@ -1333,11 +1335,11 @@ static inline int ksys_chmod(const char __user *filename, umode_t mode) return do_fchmodat(AT_FDCWD, filename, mode); } -extern long do_faccessat(int dfd, const char __user *filename, int mode); +long do_faccessat(int dfd, const char __user *filename, int mode, int flags); static inline long ksys_access(const char __user *filename, int mode) { - return do_faccessat(AT_FDCWD, filename, mode); + return do_faccessat(AT_FDCWD, filename, mode, 0); } extern int do_fchownat(int dfd, const char __user *filename, uid_t user, -- cgit v1.2.3 From 1b2628397058ebce7277480960b29c788138de90 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:17 +0000 Subject: block: Keyslot Manager for Inline Encryption Inline Encryption hardware allows software to specify an encryption context (an encryption key, crypto algorithm, data unit num, data unit size) along with a data transfer request to a storage device, and the inline encryption hardware will use that context to en/decrypt the data. The inline encryption hardware is part of the storage device, and it conceptually sits on the data path between system memory and the storage device. Inline Encryption hardware implementations often function around the concept of "keyslots". These implementations often have a limited number of "keyslots", each of which can hold a key (we say that a key can be "programmed" into a keyslot). Requests made to the storage device may have a keyslot and a data unit number associated with them, and the inline encryption hardware will en/decrypt the data in the requests using the key programmed into that associated keyslot and the data unit number specified with the request. As keyslots are limited, and programming keys may be expensive in many implementations, and multiple requests may use exactly the same encryption contexts, we introduce a Keyslot Manager to efficiently manage keyslots. We also introduce a blk_crypto_key, which will represent the key that's programmed into keyslots managed by keyslot managers. The keyslot manager also functions as the interface that upper layers will use to program keys into inline encryption hardware. For more information on the Keyslot Manager, refer to documentation found in block/keyslot-manager.c and linux/keyslot-manager.h. Co-developed-by: Eric Biggers Signed-off-by: Eric Biggers Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 52 ++++++++++++++++++++ include/linux/blkdev.h | 6 +++ include/linux/keyslot-manager.h | 106 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 164 insertions(+) create mode 100644 include/linux/blk-crypto.h create mode 100644 include/linux/keyslot-manager.h (limited to 'include/linux') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h new file mode 100644 index 000000000000..4e77938c3d0e --- /dev/null +++ b/include/linux/blk-crypto.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_BLK_CRYPTO_H +#define __LINUX_BLK_CRYPTO_H + +enum blk_crypto_mode_num { + BLK_ENCRYPTION_MODE_INVALID, + BLK_ENCRYPTION_MODE_AES_256_XTS, + BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV, + BLK_ENCRYPTION_MODE_ADIANTUM, + BLK_ENCRYPTION_MODE_MAX, +}; + +#define BLK_CRYPTO_MAX_KEY_SIZE 64 +/** + * struct blk_crypto_config - an inline encryption key's crypto configuration + * @crypto_mode: encryption algorithm this key is for + * @data_unit_size: the data unit size for all encryption/decryptions with this + * key. This is the size in bytes of each individual plaintext and + * ciphertext. This is always a power of 2. It might be e.g. the + * filesystem block size or the disk sector size. + * @dun_bytes: the maximum number of bytes of DUN used when using this key + */ +struct blk_crypto_config { + enum blk_crypto_mode_num crypto_mode; + unsigned int data_unit_size; + unsigned int dun_bytes; +}; + +/** + * struct blk_crypto_key - an inline encryption key + * @crypto_cfg: the crypto configuration (like crypto_mode, key size) for this + * key + * @data_unit_size_bits: log2 of data_unit_size + * @size: size of this key in bytes (determined by @crypto_cfg.crypto_mode) + * @raw: the raw bytes of this key. Only the first @size bytes are used. + * + * A blk_crypto_key is immutable once created, and many bios can reference it at + * the same time. It must not be freed until all bios using it have completed + * and it has been evicted from all devices on which it may have been used. + */ +struct blk_crypto_key { + struct blk_crypto_config crypto_cfg; + unsigned int data_unit_size_bits; + unsigned int size; + u8 raw[BLK_CRYPTO_MAX_KEY_SIZE]; +}; + +#endif /* __LINUX_BLK_CRYPTO_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f9e4b21b051b..354e44eebef9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -43,6 +43,7 @@ struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; +struct blk_keyslot_manager; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -468,6 +469,11 @@ struct request_queue { unsigned int dma_pad_mask; unsigned int dma_alignment; +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + /* Inline crypto capabilities */ + struct blk_keyslot_manager *ksm; +#endif + unsigned int rq_timeout; int poll_nsec; diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h new file mode 100644 index 000000000000..18f3f5346843 --- /dev/null +++ b/include/linux/keyslot-manager.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_KEYSLOT_MANAGER_H +#define __LINUX_KEYSLOT_MANAGER_H + +#include +#include + +struct blk_keyslot_manager; + +/** + * struct blk_ksm_ll_ops - functions to manage keyslots in hardware + * @keyslot_program: Program the specified key into the specified slot in the + * inline encryption hardware. + * @keyslot_evict: Evict key from the specified keyslot in the hardware. + * The key is provided so that e.g. dm layers can evict + * keys from the devices that they map over. + * Returns 0 on success, -errno otherwise. + * + * This structure should be provided by storage device drivers when they set up + * a keyslot manager - this structure holds the function ptrs that the keyslot + * manager will use to manipulate keyslots in the hardware. + */ +struct blk_ksm_ll_ops { + int (*keyslot_program)(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot); + int (*keyslot_evict)(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot); +}; + +struct blk_keyslot_manager { + /* + * The struct blk_ksm_ll_ops that this keyslot manager will use + * to perform operations like programming and evicting keys on the + * device + */ + struct blk_ksm_ll_ops ksm_ll_ops; + + /* + * The maximum number of bytes supported for specifying the data unit + * number. + */ + unsigned int max_dun_bytes_supported; + + /* + * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents + * whether a crypto mode and data unit size are supported. The i'th + * bit of crypto_mode_supported[crypto_mode] is set iff a data unit + * size of (1 << i) is supported. We only support data unit sizes + * that are powers of 2. + */ + unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX]; + + /* Device for runtime power management (NULL if none) */ + struct device *dev; + + /* Here onwards are *private* fields for internal keyslot manager use */ + + unsigned int num_slots; + + /* Protects programming and evicting keys from the device */ + struct rw_semaphore lock; + + /* List of idle slots, with least recently used slot at front */ + wait_queue_head_t idle_slots_wait_queue; + struct list_head idle_slots; + spinlock_t idle_slots_lock; + + /* + * Hash table which maps struct *blk_crypto_key to keyslots, so that we + * can find a key's keyslot in O(1) time rather than O(num_slots). + * Protected by 'lock'. + */ + struct hlist_head *slot_hashtable; + unsigned int log_slot_ht_size; + + /* Per-keyslot data */ + struct blk_ksm_keyslot *slots; +}; + +int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots); + +blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + struct blk_ksm_keyslot **slot_ptr); + +unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot); + +void blk_ksm_put_slot(struct blk_ksm_keyslot *slot); + +bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, + const struct blk_crypto_config *cfg); + +int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key); + +void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); + +void blk_ksm_destroy(struct blk_keyslot_manager *ksm); + +#endif /* __LINUX_KEYSLOT_MANAGER_H */ -- cgit v1.2.3 From a892c8d52c02284076fbbacae6692aa5c5807d11 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:18 +0000 Subject: block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 71 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/blk_types.h | 6 ++++ include/linux/blkdev.h | 5 ++++ 3 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 4e77938c3d0e..76095b07dd90 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -6,6 +6,8 @@ #ifndef __LINUX_BLK_CRYPTO_H #define __LINUX_BLK_CRYPTO_H +#include + enum blk_crypto_mode_num { BLK_ENCRYPTION_MODE_INVALID, BLK_ENCRYPTION_MODE_AES_256_XTS, @@ -49,4 +51,73 @@ struct blk_crypto_key { u8 raw[BLK_CRYPTO_MAX_KEY_SIZE]; }; +#define BLK_CRYPTO_MAX_IV_SIZE 32 +#define BLK_CRYPTO_DUN_ARRAY_SIZE (BLK_CRYPTO_MAX_IV_SIZE / sizeof(u64)) + +/** + * struct bio_crypt_ctx - an inline encryption context + * @bc_key: the key, algorithm, and data unit size to use + * @bc_dun: the data unit number (starting IV) to use + * + * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for + * write requests) or decrypted (for read requests) inline by the storage device + * or controller. + */ +struct bio_crypt_ctx { + const struct blk_crypto_key *bc_key; + u64 bc_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; +}; + +#include +#include + +struct request; +struct request_queue; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +static inline bool bio_has_crypt_ctx(struct bio *bio) +{ + return bio->bi_crypt_context; +} + +void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key, + const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], + gfp_t gfp_mask); + +bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc, + unsigned int bytes, + const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]); + +int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, + enum blk_crypto_mode_num crypto_mode, + unsigned int dun_bytes, + unsigned int data_unit_size); + +int blk_crypto_start_using_key(const struct blk_crypto_key *key, + struct request_queue *q); + +int blk_crypto_evict_key(struct request_queue *q, + const struct blk_crypto_key *key); + +bool blk_crypto_config_supported(struct request_queue *q, + const struct blk_crypto_config *cfg); + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static inline bool bio_has_crypt_ctx(struct bio *bio) +{ + return false; +} + +#endif /* CONFIG_BLK_INLINE_ENCRYPTION */ + +void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); +static inline void bio_crypt_clone(struct bio *dst, struct bio *src, + gfp_t gfp_mask) +{ + if (bio_has_crypt_ctx(src)) + __bio_crypt_clone(dst, src, gfp_mask); +} + #endif /* __LINUX_BLK_CRYPTO_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b90dca1fa430..9322261fb316 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,6 +18,7 @@ struct block_device; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); +struct bio_crypt_ctx; /* * Block error status values. See block/blk-core:blk_errors for the details. @@ -185,6 +186,11 @@ struct bio { u64 bi_iocost_cost; #endif #endif + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *bi_crypt_context; +#endif + union { #if defined(CONFIG_BLK_DEV_INTEGRITY) struct bio_integrity_payload *bi_integrity; /* data integrity */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 354e44eebef9..52a9f456cadf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -222,6 +222,11 @@ struct request { unsigned short nr_integrity_segments; #endif +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *crypt_ctx; + struct blk_ksm_keyslot *crypt_keyslot; +#endif + unsigned short write_hint; unsigned short ioprio; -- cgit v1.2.3 From d145dc23030bbf2de3a8ca5e0c29c2e568f69737 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:19 +0000 Subject: block: Make blk-integrity preclude hardware inline encryption Whenever a device supports blk-integrity, make the kernel pretend that the device doesn't support inline encryption (essentially by setting the keyslot manager in the request queue to NULL). There's no hardware currently that supports both integrity and inline encryption. However, it seems possible that there will be such hardware in the near future (like the NVMe key per I/O support that might support both inline encryption and PI). But properly integrating both features is not trivial, and without real hardware that implements both, it is difficult to tell if it will be done correctly by the majority of hardware that support both. So it seems best not to support both features together right now, and to decide what to do at probe time. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 52a9f456cadf..2b33166b9daf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1583,6 +1583,12 @@ struct blk_integrity *bdev_get_integrity(struct block_device *bdev) return blk_get_integrity(bdev->bd_disk); } +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) +{ + return q->integrity.profile; +} + static inline bool blk_integrity_rq(struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; @@ -1663,6 +1669,11 @@ static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { return NULL; } +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) +{ + return false; +} static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) { return 0; @@ -1714,6 +1725,25 @@ static inline struct bio_vec *rq_integrity_vec(struct request *rq) #endif /* CONFIG_BLK_DEV_INTEGRITY */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q); + +void blk_ksm_unregister(struct request_queue *q); + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm, + struct request_queue *q) +{ + return true; +} + +static inline void blk_ksm_unregister(struct request_queue *q) { } + +#endif /* CONFIG_BLK_INLINE_ENCRYPTION */ + + struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); -- cgit v1.2.3 From 488f6682c832e9549d28b30075f00c76328eb1be Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:20 +0000 Subject: block: blk-crypto-fallback for Inline Encryption Blk-crypto delegates crypto operations to inline encryption hardware when available. The separately configurable blk-crypto-fallback contains a software fallback to the kernel crypto API - when enabled, blk-crypto will use this fallback for en/decryption when inline encryption hardware is not available. This lets upper layers not have to worry about whether or not the underlying device has support for inline encryption before deciding to specify an encryption context for a bio. It also allows for testing without actual inline encryption hardware - in particular, it makes it possible to test the inline encryption code in ext4 and f2fs simply by running xfstests with the inlinecrypt mount option, which in turn allows for things like the regular upstream regression testing of ext4 to cover the inline encryption code paths. For more details, refer to Documentation/block/inline-encryption.rst. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 76095b07dd90..e82342907f2b 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -61,7 +61,7 @@ struct blk_crypto_key { * * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for * write requests) or decrypted (for read requests) inline by the storage device - * or controller. + * or controller, or by the crypto API fallback. */ struct bio_crypt_ctx { const struct blk_crypto_key *bc_key; -- cgit v1.2.3 From 04fd61a4e01028210a91f0efc408c8bc61a3018c Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 13 May 2020 17:50:34 -0700 Subject: mm, memcg: fix inconsistent oom event behavior A recent commit 9852ae3fe529 ("mm, memcg: consider subtrees in memory.events") changed the behavior of memcg events, which will now consider subtrees in memory.events. But oom_kill event is a special one as it is used in both cgroup1 and cgroup2. In cgroup1, it is displayed in memory.oom_control. The file memory.oom_control is in both root memcg and non root memcg, that is different with memory.event as it only in non-root memcg. That commit is okay for cgroup2, but it is not okay for cgroup1 as it will cause inconsistent behavior between root memcg and non-root memcg. Here's an example on why this behavior is inconsistent in cgroup1. root memcg / memcg foo / memcg bar Suppose there's an oom_kill in memcg bar, then the oon_kill will be root memcg : memory.oom_control(oom_kill) 0 / memcg foo : memory.oom_control(oom_kill) 1 / memcg bar : memory.oom_control(oom_kill) 1 For the non-root memcg, its memory.oom_control(oom_kill) includes its descendants' oom_kill, but for root memcg, it doesn't include its descendants' oom_kill. That means, memory.oom_control(oom_kill) has different meanings in different memcgs. That is inconsistent. Then the user has to know whether the memcg is root or not. If we can't fully support it in cgroup1, for example by adding memory.events.local into cgroup1 as well, then let's don't touch its original behavior. Fixes: 9852ae3fe529 ("mm, memcg: consider subtrees in memory.events") Reported-by: Randy Dunlap Signed-off-by: Yafang Shao Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Chris Down Acked-by: Michal Hocko Cc: Link: http://lkml.kernel.org/r/20200502141055.7378-1-laoar.shao@gmail.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d275c72c4f8e..977edd3b7bd8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -783,6 +783,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && -- cgit v1.2.3 From 625236ba3832ae947cb3ebb7acc1f30788b274ef Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Tue, 12 May 2020 19:46:07 +0200 Subject: security: Fix the default value of secid_to_secctx hook security_secid_to_secctx is called by the bpf_lsm hook and a successful return value (i.e 0) implies that the parameter will be consumed by the LSM framework. The current behaviour return success when the pointer isn't initialized when CONFIG_BPF_LSM is enabled, with the default return from kernel/bpf/bpf_lsm.c. This is the internal error: [ 1229.341488][ T2659] usercopy: Kernel memory exposure attempt detected from null address (offset 0, size 280)! [ 1229.374977][ T2659] ------------[ cut here ]------------ [ 1229.376813][ T2659] kernel BUG at mm/usercopy.c:99! [ 1229.378398][ T2659] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP [ 1229.380348][ T2659] Modules linked in: [ 1229.381654][ T2659] CPU: 0 PID: 2659 Comm: systemd-journal Tainted: G B W 5.7.0-rc5-next-20200511-00019-g864e0c6319b8-dirty #13 [ 1229.385429][ T2659] Hardware name: linux,dummy-virt (DT) [ 1229.387143][ T2659] pstate: 80400005 (Nzcv daif +PAN -UAO BTYPE=--) [ 1229.389165][ T2659] pc : usercopy_abort+0xc8/0xcc [ 1229.390705][ T2659] lr : usercopy_abort+0xc8/0xcc [ 1229.392225][ T2659] sp : ffff000064247450 [ 1229.393533][ T2659] x29: ffff000064247460 x28: 0000000000000000 [ 1229.395449][ T2659] x27: 0000000000000118 x26: 0000000000000000 [ 1229.397384][ T2659] x25: ffffa000127049e0 x24: ffffa000127049e0 [ 1229.399306][ T2659] x23: ffffa000127048e0 x22: ffffa000127048a0 [ 1229.401241][ T2659] x21: ffffa00012704b80 x20: ffffa000127049e0 [ 1229.403163][ T2659] x19: ffffa00012704820 x18: 0000000000000000 [ 1229.405094][ T2659] x17: 0000000000000000 x16: 0000000000000000 [ 1229.407008][ T2659] x15: 0000000000000000 x14: 003d090000000000 [ 1229.408942][ T2659] x13: ffff80000d5b25b2 x12: 1fffe0000d5b25b1 [ 1229.410859][ T2659] x11: 1fffe0000d5b25b1 x10: ffff80000d5b25b1 [ 1229.412791][ T2659] x9 : ffffa0001034bee0 x8 : ffff00006ad92d8f [ 1229.414707][ T2659] x7 : 0000000000000000 x6 : ffffa00015eacb20 [ 1229.416642][ T2659] x5 : ffff0000693c8040 x4 : 0000000000000000 [ 1229.418558][ T2659] x3 : ffffa0001034befc x2 : d57a7483a01c6300 [ 1229.420610][ T2659] x1 : 0000000000000000 x0 : 0000000000000059 [ 1229.422526][ T2659] Call trace: [ 1229.423631][ T2659] usercopy_abort+0xc8/0xcc [ 1229.425091][ T2659] __check_object_size+0xdc/0x7d4 [ 1229.426729][ T2659] put_cmsg+0xa30/0xa90 [ 1229.428132][ T2659] unix_dgram_recvmsg+0x80c/0x930 [ 1229.429731][ T2659] sock_recvmsg+0x9c/0xc0 [ 1229.431123][ T2659] ____sys_recvmsg+0x1cc/0x5f8 [ 1229.432663][ T2659] ___sys_recvmsg+0x100/0x160 [ 1229.434151][ T2659] __sys_recvmsg+0x110/0x1a8 [ 1229.435623][ T2659] __arm64_sys_recvmsg+0x58/0x70 [ 1229.437218][ T2659] el0_svc_common.constprop.1+0x29c/0x340 [ 1229.438994][ T2659] do_el0_svc+0xe8/0x108 [ 1229.440587][ T2659] el0_svc+0x74/0x88 [ 1229.441917][ T2659] el0_sync_handler+0xe4/0x8b4 [ 1229.443464][ T2659] el0_sync+0x17c/0x180 [ 1229.444920][ T2659] Code: aa1703e2 aa1603e1 910a8260 97ecc860 (d4210000) [ 1229.447070][ T2659] ---[ end trace 400497d91baeaf51 ]--- [ 1229.448791][ T2659] Kernel panic - not syncing: Fatal exception [ 1229.450692][ T2659] Kernel Offset: disabled [ 1229.452061][ T2659] CPU features: 0x240002,20002004 [ 1229.453647][ T2659] Memory Limit: none [ 1229.455015][ T2659] ---[ end Kernel panic - not syncing: Fatal exception ]--- Rework the so the default return value is -EOPNOTSUPP. There are likely other callbacks such as security_inode_getsecctx() that may have the same problem, and that someone that understand the code better needs to audit them. Thank you Arnd for helping me figure out what went wrong. Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks") Signed-off-by: Anders Roxell Signed-off-by: Alexei Starovoitov Acked-by: James Morris Cc: Arnd Bergmann Link: https://lore.kernel.org/bpf/20200512174607.9630-1-anders.roxell@linaro.org --- include/linux/lsm_hook_defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..21f4fff9e4cd 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -243,7 +243,7 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) -LSM_HOOK(int, 0, secid_to_secctx, u32 secid, char **secdata, +LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, u32 *seclen) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) -- cgit v1.2.3 From d639836ab3363f935a9a4336cb4ea3828d0437dd Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Thu, 14 May 2020 12:57:17 +0300 Subject: net: qed: adding hw_err states and handling Here we introduce qed device error tracking flags and error types. qed_hw_err_notify is an entrace point to report errors. It'll notify higher level drivers (qede/qedr/etc) to handle and recover the error. List of posible errors comes from hardware interfaces, but could be extended in future. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8f29e0d8a7b3..1b7d9548ee43 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -607,6 +607,16 @@ struct qed_sb_info { struct qed_dev *cdev; }; +enum qed_hw_err_type { + QED_HW_ERR_FAN_FAIL, + QED_HW_ERR_MFW_RESP_FAIL, + QED_HW_ERR_HW_ATTN, + QED_HW_ERR_DMAE_FAIL, + QED_HW_ERR_RAMROD_FAIL, + QED_HW_ERR_FW_ASSERT, + QED_HW_ERR_LAST, +}; + enum qed_dev_type { QED_DEV_TYPE_BB, QED_DEV_TYPE_AH, @@ -814,6 +824,8 @@ struct qed_common_cb_ops { void (*link_update)(void *dev, struct qed_link_output *link); void (*schedule_recovery_handler)(void *dev); + void (*schedule_hw_err_handler)(void *dev, + enum qed_hw_err_type err_type); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); -- cgit v1.2.3 From 936c7ba4dd5e94a3fc784f2296de5d577a9b5e43 Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Thu, 14 May 2020 12:57:22 +0300 Subject: net: qed: attention clearing properties On different hardware events we have to respond differently, on some of hardware indications hw attention (error condition) should be cleared by the driver to continue normal functioning. Here we introduce attention clear flags, and put them on some important events (in aeu_descs). Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Igor Russkikh 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 1b7d9548ee43..978e91e9ab65 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1046,6 +1046,15 @@ struct qed_common_ops { */ int (*set_led)(struct qed_dev *cdev, enum qed_led_mode mode); + +/** + * @brief attn_clr_enable - Prevent attentions from being reasserted + * + * @param cdev + * @param clr_enable + */ + void (*attn_clr_enable)(struct qed_dev *cdev, bool clr_enable); + /** * @brief db_recovery_add - add doorbell information to the doorbell * recovery mechanism. -- cgit v1.2.3 From 8f76812e1cc4d561c3efc3b2586c686b5428d31f Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Thu, 14 May 2020 12:57:27 +0300 Subject: net: qed: fix bad formatting On some adjacent code, fix bad code formatting Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 978e91e9ab65..48325d7790f8 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -821,12 +821,11 @@ enum qed_nvm_flash_cmd { struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); - void (*link_update)(void *dev, - struct qed_link_output *link); + void (*link_update)(void *dev, struct qed_link_output *link); void (*schedule_recovery_handler)(void *dev); void (*schedule_hw_err_handler)(void *dev, enum qed_hw_err_type err_type); - void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); + void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); }; -- cgit v1.2.3 From 6ae72bfa656ea04806f98ef85cb44b0789064362 Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Sat, 9 May 2020 18:19:28 +0800 Subject: PCI: Unify pcie_find_root_port() and pci_find_pcie_root_port() Previously we used pcie_find_root_port() to find a Root Port from a PCIe device and pci_find_pcie_root_port() to find a Root Port from a Conventional PCI device. Unify the two functions and use pcie_find_root_port() to find a Root Port from either a Conventional PCI device or a PCIe device. Then there is no need to distinguish the type of the device. Link: https://lore.kernel.org/r/1589019568-5216-1-git-send-email-yangyicong@hisilicon.com Signed-off-by: Yicong Yang Signed-off-by: Bjorn Helgaas Acked-by: Kalle Valo # wireless Acked-by: Mika Westerberg # thunderbolt --- include/linux/pci.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0453ee458ab1..bbd6510065a7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1025,7 +1025,6 @@ void pci_bus_add_device(struct pci_dev *dev); void pci_read_bridge_bases(struct pci_bus *child); struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res); -struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev); u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin); int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp); @@ -2143,17 +2142,23 @@ static inline int pci_pcie_type(const struct pci_dev *dev) return (pcie_caps_reg(dev) & PCI_EXP_FLAGS_TYPE) >> 4; } +/** + * pcie_find_root_port - Get the PCIe root port device + * @dev: PCI device + * + * Traverse up the parent chain and return the PCIe Root Port PCI Device + * for a given PCI/PCIe Device. + */ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) { - while (1) { - if (!pci_is_pcie(dev)) - break; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - return dev; - if (!dev->bus->self) - break; - dev = dev->bus->self; + struct pci_dev *bridge = pci_upstream_bridge(dev); + + while (bridge) { + if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) + return bridge; + bridge = pci_upstream_bridge(bridge); } + return NULL; } -- cgit v1.2.3 From cc8a677a76f419016b5e231207d09b073f9b1d3f Mon Sep 17 00:00:00 2001 From: Kevin Lo Date: Thu, 14 May 2020 08:57:33 +0800 Subject: net: phy: broadcom: fix BCM54XX_SHD_SCR3_TRDDAPD value for BCM54810 Set the correct bit when checking for PHY_BRCM_DIS_TXCRXC_NOENRGY on the BCM54810 PHY. Fixes: 0ececcfc9267 ("net: phy: broadcom: Allow BCM54810 to use bcm54xx_adjust_rxrefclk()") Signed-off-by: Kevin Lo Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6462c5447872..f4b77018c625 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -245,6 +245,7 @@ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +#define BCM54810_SHD_SCR3_TRDDAPD 0x0100 /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) -- cgit v1.2.3 From 8695e0b1b964f6d7caee667f14dceb7e8a4a3b3c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:53:29 -0500 Subject: i2c: mux: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/i2c-mux.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h index c5a977320f82..98ef73b7c8fd 100644 --- a/include/linux/i2c-mux.h +++ b/include/linux/i2c-mux.h @@ -29,7 +29,7 @@ struct i2c_mux_core { int num_adapters; int max_adapters; - struct i2c_adapter *adapter[0]; + struct i2c_adapter *adapter[]; }; struct i2c_mux_core *i2c_mux_alloc(struct i2c_adapter *parent, -- cgit v1.2.3 From a9a3ed1eff3601b63aea4fb462d8b3b92c7c1e7e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 22 Apr 2020 18:11:30 +0200 Subject: x86: Fix early boot crash on gcc-10, third try MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ... or the odyssey of trying to disable the stack protector for the function which generates the stack canary value. The whole story started with Sergei reporting a boot crash with a kernel built with gcc-10: Kernel panic — not syncing: stack-protector: Kernel stack is corrupted in: start_secondary CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.6.0-rc5—00235—gfffb08b37df9 #139 Hardware name: Gigabyte Technology Co., Ltd. To be filled by O.E.M./H77M—D3H, BIOS F12 11/14/2013 Call Trace: dump_stack panic ? start_secondary __stack_chk_fail start_secondary secondary_startup_64 -—-[ end Kernel panic — not syncing: stack—protector: Kernel stack is corrupted in: start_secondary This happens because gcc-10 tail-call optimizes the last function call in start_secondary() - cpu_startup_entry() - and thus emits a stack canary check which fails because the canary value changes after the boot_init_stack_canary() call. To fix that, the initial attempt was to mark the one function which generates the stack canary with: __attribute__((optimize("-fno-stack-protector"))) ... start_secondary(void *unused) however, using the optimize attribute doesn't work cumulatively as the attribute does not add to but rather replaces previously supplied optimization options - roughly all -fxxx options. The key one among them being -fno-omit-frame-pointer and thus leading to not present frame pointer - frame pointer which the kernel needs. The next attempt to prevent compilers from tail-call optimizing the last function call cpu_startup_entry(), shy of carving out start_secondary() into a separate compilation unit and building it with -fno-stack-protector, was to add an empty asm(""). This current solution was short and sweet, and reportedly, is supported by both compilers but we didn't get very far this time: future (LTO?) optimization passes could potentially eliminate this, which leads us to the third attempt: having an actual memory barrier there which the compiler cannot ignore or move around etc. That should hold for a long time, but hey we said that about the other two solutions too so... Reported-by: Sergei Trofimovich Signed-off-by: Borislav Petkov Tested-by: Kalle Valo Cc: Link: https://lkml.kernel.org/r/20200314164451.346497-1-slyfox@gentoo.org --- include/linux/compiler.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 034b0a644efc..448c91bf543b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -356,4 +356,10 @@ static inline void *offset_to_ptr(const int *off) /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +/* + * This is needed in functions which generate the stack canary, see + * arch/x86/kernel/smpboot.c::start_secondary() for an example. + */ +#define prevent_tail_call_optimization() mb() + #endif /* __LINUX_COMPILER_H */ -- cgit v1.2.3 From 69cf449166987d9a041020be6422ee7bf94a7228 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Prakhya Date: Wed, 13 May 2020 15:47:21 -0700 Subject: iommu: Remove functions that support private domain After moving iommu_group setup to iommu core code [1][2] and removing private domain support in vt-d [3], there are no users for functions such as iommu_request_dm_for_dev(), iommu_request_dma_domain_for_dev() and request_default_domain_for_dev(). So, remove these functions. [1] commit dce8d6964ebd ("iommu/amd: Convert to probe/release_device() call-backs") [2] commit e5d1841f18b2 ("iommu/vt-d: Convert to probe/release_device() call-backs") [3] commit 327d5b2fee91 ("iommu/vt-d: Allow 32bit devices to uses DMA domain") Signed-off-by: Sai Praneeth Prakhya Cc: Joerg Roedel Cc: Lu Baolu Link: https://lore.kernel.org/r/20200513224721.20504-1-sai.praneeth.prakhya@intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7cfd2dddb49d..78a26ae5c2b6 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -482,8 +482,6 @@ 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); extern void iommu_set_default_translated(bool cmd_line); extern bool iommu_default_passthrough(void); @@ -804,16 +802,6 @@ static inline int iommu_get_group_resv_regions(struct iommu_group *group, return -ENODEV; } -static inline int iommu_request_dm_for_dev(struct device *dev) -{ - return -ENODEV; -} - -static inline int iommu_request_dma_domain_for_dev(struct device *dev) -{ - return -ENODEV; -} - static inline void iommu_set_default_passthrough(bool cmd_line) { } -- cgit v1.2.3 From c150c0f362c1e51c0e3216c9912b85b71d00e70d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 12 May 2020 14:40:02 +0200 Subject: serial: Allow uart_get_rs485_mode() to return errno We're about to amend uart_get_rs485_mode() to support a GPIO pin for rs485 bus termination. Retrieving the GPIO descriptor may fail, so allow uart_get_rs485_mode() to return an errno and change all callers to check for failure. The GPIO descriptor is going to be stored in struct uart_port. Pass that struct to uart_get_rs485_mode() in lieu of a struct device and struct serial_rs485, both of which are directly accessible from struct uart_port. A few drivers call uart_get_rs485_mode() before setting the struct device pointer in struct uart_port. Shuffle those calls around where necessary. [Heiko Stuebner did the ar933x_uart.c portion, hence his Signed-off-by.] Signed-off-by: Heiko Stuebner Signed-off-by: Lukas Wunner Link: https://lore.kernel.org/r/271e814af4b0db3bffbbb74abf2b46b75add4516.1589285873.git.lukas@wunner.de Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 92f5eba86052..b649a2b894e7 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -472,5 +472,5 @@ extern int uart_handle_break(struct uart_port *port); (cflag) & CRTSCTS || \ !((cflag) & CLOCAL)) -void uart_get_rs485_mode(struct device *dev, struct serial_rs485 *rs485conf); +int uart_get_rs485_mode(struct uart_port *port); #endif /* LINUX_SERIAL_CORE_H */ -- cgit v1.2.3 From 0f1c9688a194d22bb81953bd85bd18b0115fd17f Mon Sep 17 00:00:00 2001 From: Emil Velikov Date: Wed, 13 May 2020 22:43:41 +0100 Subject: tty/sysrq: alpha: export and use __sysrq_get_key_op() Export a pointer to the sysrq_get_key_op(). This way we can cleanly unregister it, instead of the current solutions of modifuing it inplace. Since __sysrq_get_key_op() is no longer used externally, let's make it a static function. This patch will allow us to limit access to each and every sysrq op and constify the sysrq handling. Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: linux-kernel@vger.kernel.org Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: linux-alpha@vger.kernel.org Signed-off-by: Emil Velikov Link: https://lore.kernel.org/r/20200513214351.2138580-1-emil.l.velikov@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysrq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 8e159e16850f..9b51f98e5f60 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -47,7 +47,7 @@ void handle_sysrq(int key); void __handle_sysrq(int key, bool check_mask); int register_sysrq_key(int key, struct sysrq_key_op *op); int unregister_sysrq_key(int key, struct sysrq_key_op *op); -struct sysrq_key_op *__sysrq_get_key_op(int key); +extern struct sysrq_key_op *__sysrq_reboot_op; int sysrq_toggle_support(int enable_mask); int sysrq_mask(void); -- cgit v1.2.3 From 23cbedf812ff7c7751582928e32d953d84c1c821 Mon Sep 17 00:00:00 2001 From: Emil Velikov Date: Wed, 13 May 2020 22:43:42 +0100 Subject: tty/sysrq: constify the sysrq API The user is not supposed to thinker with the underlying sysrq_key_op. Make that explicit by adding a handful of const notations. Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: linux-kernel@vger.kernel.org Signed-off-by: Emil Velikov Link: https://lore.kernel.org/r/20200513214351.2138580-2-emil.l.velikov@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysrq.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 9b51f98e5f60..479028391c08 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -30,10 +30,10 @@ #define SYSRQ_ENABLE_RTNICE 0x0100 struct sysrq_key_op { - void (*handler)(int); - char *help_msg; - char *action_msg; - int enable_mask; + void (* const handler)(int); + const char * const help_msg; + const char * const action_msg; + const int enable_mask; }; #ifdef CONFIG_MAGIC_SYSRQ @@ -45,8 +45,8 @@ struct sysrq_key_op { void handle_sysrq(int key); void __handle_sysrq(int key, bool check_mask); -int register_sysrq_key(int key, struct sysrq_key_op *op); -int unregister_sysrq_key(int key, struct sysrq_key_op *op); +int register_sysrq_key(int key, const struct sysrq_key_op *op); +int unregister_sysrq_key(int key, const struct sysrq_key_op *op); extern struct sysrq_key_op *__sysrq_reboot_op; int sysrq_toggle_support(int enable_mask); @@ -62,12 +62,12 @@ static inline void __handle_sysrq(int key, bool check_mask) { } -static inline int register_sysrq_key(int key, struct sysrq_key_op *op) +static inline int register_sysrq_key(int key, const struct sysrq_key_op *op) { return -EINVAL; } -static inline int unregister_sysrq_key(int key, struct sysrq_key_op *op) +static inline int unregister_sysrq_key(int key, const struct sysrq_key_op *op) { return -EINVAL; } -- cgit v1.2.3 From 7fffe31d3eaa2f08bdfde2403adcaa8029f9bea4 Mon Sep 17 00:00:00 2001 From: Emil Velikov Date: Wed, 13 May 2020 22:43:43 +0100 Subject: tty/sysrq: constify the the sysrq_key_op(s) All the users threat them as immutable - annotate them as such. Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: linux-kernel@vger.kernel.org Signed-off-by: Emil Velikov Link: https://lore.kernel.org/r/20200513214351.2138580-3-emil.l.velikov@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysrq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 479028391c08..3a582ec7a2f1 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -47,7 +47,7 @@ void handle_sysrq(int key); void __handle_sysrq(int key, bool check_mask); int register_sysrq_key(int key, const struct sysrq_key_op *op); int unregister_sysrq_key(int key, const struct sysrq_key_op *op); -extern struct sysrq_key_op *__sysrq_reboot_op; +extern const struct sysrq_key_op *__sysrq_reboot_op; int sysrq_toggle_support(int enable_mask); int sysrq_mask(void); -- cgit v1.2.3 From ff4c65ca48f08f4781accfb1d224acd7c897070e Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 14 May 2020 17:50:36 +0530 Subject: usb: hci: add hc_driver as argument for usb_hcd_pci_probe usb_hcd_pci_probe expects users to call this with driver_data set as hc_driver, that limits the possibility of using the driver_data for driver data. Add hc_driver as argument to usb_hcd_pci_probe and modify the callers ehci/ohci/xhci/uhci to pass hc_driver as argument and freeup the driver_data used Tested xhci driver on Dragon-board RB3, compile tested ehci, ohci and uhci. [For all but the xHCI parts] [For the xhci part] Suggested-by: Mathias Nyman Acked-by: Alan Stern Acked-by: Mathias Nyman Signed-off-by: Vinod Koul Link: https://lore.kernel.org/r/20200514122039.300417-2-vkoul@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index e12105ed3834..3dbb42c637c1 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -479,7 +479,8 @@ extern void usb_hcd_platform_shutdown(struct platform_device *dev); struct pci_dev; struct pci_device_id; extern int usb_hcd_pci_probe(struct pci_dev *dev, - const struct pci_device_id *id); + const struct pci_device_id *id, + const struct hc_driver *driver); extern void usb_hcd_pci_remove(struct pci_dev *dev); extern void usb_hcd_pci_shutdown(struct pci_dev *dev); -- cgit v1.2.3 From 6fbeb0048e6b93f7b7f195864f3ddc876ac4d42e Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 7 Feb 2020 15:59:25 -0500 Subject: dm bufio: implement discard Add functions dm_bufio_issue_discard and dm_bufio_discard_buffers. dm_bufio_issue_discard sends discard request to the underlying device. dm_bufio_discard_buffers frees buffers in the range and then calls dm_bufio_issue_discard. Also, factor out block_to_sector for reuse in dm_bufio_issue_discard. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-bufio.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 3c8b7d274bd9..07e1f163e299 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -118,6 +118,18 @@ int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c); */ int dm_bufio_issue_flush(struct dm_bufio_client *c); +/* + * Send a discard request to the underlying device. + */ +int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count); + +/* + * Free the specified range of buffers. If a buffer is held by other process, it + * is not freed. If a buffer is dirty, it is discarded without writeback. + * Finally, send the discard request to the device. + */ +int dm_bufio_discard_buffers(struct dm_bufio_client *c, sector_t block, sector_t count); + /* * Like dm_bufio_release but also move the buffer to the new * block. dm_bufio_write_dirty_buffers is needed to commit the new block. -- cgit v1.2.3 From 087615bf3acdafd0ba7c7c9ed5286e7b7c80fe1b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 30 Apr 2020 16:48:29 -0400 Subject: dm mpath: pass IO start time to path selector The HST path selector needs this information to perform path prediction. For request-based mpath, struct request's io_start_time_ns is used, while for bio-based, use the start_time stored in dm_io. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index af48d9da3916..934037d938b9 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -332,6 +332,8 @@ void *dm_per_bio_data(struct bio *bio, size_t data_size); struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size); unsigned dm_bio_get_target_bio_nr(const struct bio *bio); +u64 dm_start_time_ns_from_clone(struct bio *bio); + int dm_register_target(struct target_type *t); void dm_unregister_target(struct target_type *t); -- cgit v1.2.3 From 716a7a25969003d82ab738179c3f1068a120ed11 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 14 May 2020 22:34:59 -0700 Subject: driver core: fw_devlink: Add support for batching fwnode parsing The amount of time spent parsing fwnodes of devices can become really high if the devices are added in an non-ideal order. Worst case can be O(N^2) when N devices are added. But this can be optimized to O(N) by adding all the devices and then parsing all their fwnodes in one batch. This commit adds fw_devlink_pause() and fw_devlink_resume() to allow doing this. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200515053500.215929-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index e0abafbb17f8..9506f8ec0974 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -171,5 +171,7 @@ struct fwnode_operations { #define get_dev_from_fwnode(fwnode) get_device((fwnode)->dev) extern u32 fw_devlink_get_flags(void); +void fw_devlink_pause(void); +void fw_devlink_resume(void); #endif -- cgit v1.2.3 From a17b53c4a4b55ec322c132b6670743612229ee9c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 13 May 2020 16:03:53 -0700 Subject: bpf, capability: Introduce CAP_BPF Split BPF operations that are allowed under CAP_SYS_ADMIN into combination of CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN. For backward compatibility include them in CAP_SYS_ADMIN as well. The end result provides simple safety model for applications that use BPF: - to load tracing program types BPF_PROG_TYPE_{KPROBE, TRACEPOINT, PERF_EVENT, RAW_TRACEPOINT, etc} use CAP_BPF and CAP_PERFMON - to load networking program types BPF_PROG_TYPE_{SCHED_CLS, XDP, SK_SKB, etc} use CAP_BPF and CAP_NET_ADMIN There are few exceptions from this rule: - bpf_trace_printk() is allowed in networking programs, but it's using tracing mechanism, hence this helper needs additional CAP_PERFMON if networking program is using this helper. - BPF_F_ZERO_SEED flag for hash/lru map is allowed under CAP_SYS_ADMIN only to discourage production use. - BPF HW offload is allowed under CAP_SYS_ADMIN. - bpf_probe_write_user() is allowed under CAP_SYS_ADMIN only. CAPs are not checked at attach/detach time with two exceptions: - loading BPF_PROG_TYPE_CGROUP_SKB is allowed for unprivileged users, hence CAP_NET_ADMIN is required at attach time. - flow_dissector detach doesn't check prog FD at detach, hence CAP_NET_ADMIN is required at detach time. CAP_SYS_ADMIN is required to iterate BPF objects (progs, maps, links) via get_next_id command and convert them to file descriptor via GET_FD_BY_ID command. This restriction guarantees that mutliple tasks with CAP_BPF are not able to affect each other. That leads to clean isolation of tasks. For example: task A with CAP_BPF and CAP_NET_ADMIN loads and attaches a firewall via bpf_link. task B with the same capabilities cannot detach that firewall unless task A explicitly passed link FD to task B via scm_rights or bpffs. CAP_SYS_ADMIN can still detach/unload everything. Two networking user apps with CAP_SYS_ADMIN and CAP_NET_ADMIN can accidentely mess with each other programs and maps. Two networking user apps with CAP_NET_ADMIN and CAP_BPF cannot affect each other. CAP_NET_ADMIN + CAP_BPF allows networking programs access only packet data. Such networking progs cannot access arbitrary kernel memory or leak pointers. bpftool, bpftrace, bcc tools binaries should NOT be installed with CAP_BPF and CAP_PERFMON, since unpriv users will be able to read kernel secrets. But users with these two permissions will be able to use these tracing tools. CAP_PERFMON is least secure, since it allows kprobes and kernel memory access. CAP_NET_ADMIN can stop network traffic via iproute2. CAP_BPF is the safest from security point of view and harmless on its own. Having CAP_BPF and/or CAP_NET_ADMIN is not enough to write into arbitrary map and if that map is used by firewall-like bpf prog. CAP_BPF allows many bpf prog_load commands in parallel. The verifier may consume large amount of memory and significantly slow down the system. Existing unprivileged BPF operations are not affected. In particular unprivileged users are allowed to load socket_filter and cg_skb program types and to create array, hash, prog_array, map-in-map map types. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200513230355.7858-2-alexei.starovoitov@gmail.com --- include/linux/capability.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 027d7e4a853b..b4345b38a6be 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -256,6 +256,11 @@ static inline bool perfmon_capable(void) return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); } +static inline bool bpf_capable(void) +{ + return capable(CAP_BPF) || capable(CAP_SYS_ADMIN); +} + /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -- cgit v1.2.3 From 2c78ee898d8f10ae6fb2fa23a3fbaec96b1b7366 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 13 May 2020 16:03:54 -0700 Subject: bpf: Implement CAP_BPF Implement permissions as stated in uapi/linux/capability.h In order to do that the verifier allow_ptr_leaks flag is split into four flags and they are set as: env->allow_ptr_leaks = bpf_allow_ptr_leaks(); env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); The first three currently equivalent to perfmon_capable(), since leaking kernel pointers and reading kernel memory via side channel attacks is roughly equivalent to reading kernel memory with cap_perfmon. 'bpf_capable' enables bounded loops, precision tracking, bpf to bpf calls and other verifier features. 'allow_ptr_leaks' enable ptr leaks, ptr conversions, subtraction of pointers. 'bypass_spec_v1' disables speculative analysis in the verifier, run time mitigations in bpf array, and enables indirect variable access in bpf programs. 'bypass_spec_v4' disables emission of sanitation code by the verifier. That means that the networking BPF program loaded with CAP_BPF + CAP_NET_ADMIN will have speculative checks done by the verifier and other spectre mitigation applied. Such networking BPF program will not be able to leak kernel pointers and will not be able to access arbitrary kernel memory. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200513230355.7858-3-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 18 +++++++++++++++++- include/linux/bpf_verifier.h | 3 +++ 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c45d198ac38c..efe8836b5c48 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -19,6 +19,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -119,7 +120,7 @@ struct bpf_map { struct bpf_map_memory memory; char name[BPF_OBJ_NAME_LEN]; u32 btf_vmlinux_value_type_id; - bool unpriv_array; + bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ /* 22 bytes hole */ @@ -1095,6 +1096,21 @@ struct bpf_map *bpf_map_get_curr_or_next(u32 *id); extern int sysctl_unprivileged_bpf_disabled; +static inline bool bpf_allow_ptr_leaks(void) +{ + return perfmon_capable(); +} + +static inline bool bpf_bypass_spec_v1(void) +{ + return perfmon_capable(); +} + +static inline bool bpf_bypass_spec_v4(void) +{ + return perfmon_capable(); +} + int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6abd5a778fcd..ea833087e853 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -375,6 +375,9 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool bpf_capable; + bool bypass_spec_v1; + bool bypass_spec_v4; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; -- cgit v1.2.3 From d08b9f0ca6605e13dcb48f04e55a30545b3c71eb Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 27 Apr 2020 09:00:07 -0700 Subject: scs: Add support for Clang's Shadow Call Stack (SCS) This change adds generic support for Clang's Shadow Call Stack, which uses a shadow stack to protect return addresses from being overwritten by an attacker. Details are available here: https://clang.llvm.org/docs/ShadowCallStack.html Note that security guarantees in the kernel differ from the ones documented for user space. The kernel must store addresses of shadow stacks in memory, which means an attacker capable reading and writing arbitrary memory may be able to locate them and hijack control flow by modifying the stacks. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Reviewed-by: Miguel Ojeda [will: Numerous cosmetic changes] Signed-off-by: Will Deacon --- include/linux/compiler-clang.h | 4 +++ include/linux/compiler_types.h | 4 +++ include/linux/scs.h | 68 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 76 insertions(+) create mode 100644 include/linux/scs.h (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 333a6695a918..790c0c6b8552 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -42,3 +42,7 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") + +#if __has_feature(shadow_call_stack) +# define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) +#endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e970f97a7fcb..97b62f47a80d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -193,6 +193,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef __noscs +# define __noscs +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif diff --git a/include/linux/scs.h b/include/linux/scs.h new file mode 100644 index 000000000000..3f3662621a27 --- /dev/null +++ b/include/linux/scs.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shadow Call Stack support. + * + * Copyright (C) 2019 Google LLC + */ + +#ifndef _LINUX_SCS_H +#define _LINUX_SCS_H + +#include +#include +#include +#include + +#ifdef CONFIG_SHADOW_CALL_STACK + +/* + * In testing, 1 KiB shadow stack size (i.e. 128 stack frames on a 64-bit + * architecture) provided ~40% safety margin on stack usage while keeping + * memory allocation overhead reasonable. + */ +#define SCS_SIZE SZ_1K +#define GFP_SCS (GFP_KERNEL | __GFP_ZERO) + +/* An illegal pointer value to mark the end of the shadow stack. */ +#define SCS_END_MAGIC (0x5f6UL + POISON_POINTER_DELTA) + +#define task_scs(tsk) (task_thread_info(tsk)->scs_base) +#define task_scs_offset(tsk) (task_thread_info(tsk)->scs_offset) + +void scs_init(void); +int scs_prepare(struct task_struct *tsk, int node); +void scs_release(struct task_struct *tsk); + +static inline void scs_task_reset(struct task_struct *tsk) +{ + /* + * Reset the shadow stack to the base address in case the task + * is reused. + */ + task_scs_offset(tsk) = 0; +} + +static inline unsigned long *__scs_magic(void *s) +{ + return (unsigned long *)(s + SCS_SIZE) - 1; +} + +static inline bool scs_corrupted(struct task_struct *tsk) +{ + unsigned long *magic = __scs_magic(task_scs(tsk)); + + return (task_scs_offset(tsk) >= SCS_SIZE - 1 || + READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC); +} + +#else /* CONFIG_SHADOW_CALL_STACK */ + +static inline void scs_init(void) {} +static inline void scs_task_reset(struct task_struct *tsk) {} +static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; } +static inline bool scs_corrupted(struct task_struct *tsk) { return false; } +static inline void scs_release(struct task_struct *tsk) {} + +#endif /* CONFIG_SHADOW_CALL_STACK */ + +#endif /* _LINUX_SCS_H */ -- cgit v1.2.3 From 628d06a48f57c36abdc2a024930212e654a501b7 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 27 Apr 2020 09:00:08 -0700 Subject: scs: Add page accounting for shadow call stack allocations This change adds accounting for the memory allocated for shadow stacks. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Acked-by: Will Deacon Signed-off-by: Will Deacon --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b9de7d220fb..acffc3bc6178 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -156,6 +156,9 @@ enum zone_stat_item { NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_PAGETABLE, /* used for pagetables */ NR_KERNEL_STACK_KB, /* measured in KiB */ +#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) + NR_KERNEL_SCS_KB, /* measured in KiB */ +#endif /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) -- cgit v1.2.3 From b0ed0bbfb3046ed127f6004b5893ccb6cdd9ba90 Mon Sep 17 00:00:00 2001 From: Kevin Lo Date: Sat, 16 May 2020 01:24:47 +0800 Subject: net: phy: broadcom: add support for BCM54811 PHY The BCM54811 PHY shares many similarities with the already supported BCM54810 PHY but additionally requires some semi-unique configuration. Signed-off-by: Kevin Lo Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index d41624db6de2..6ad4c000661a 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -17,6 +17,7 @@ #define PHY_ID_BCM5395 0x0143bcf0 #define PHY_ID_BCM53125 0x03625f20 #define PHY_ID_BCM54810 0x03625d00 +#define PHY_ID_BCM54811 0x03625cc0 #define PHY_ID_BCM5482 0x0143bcb0 #define PHY_ID_BCM5411 0x00206070 #define PHY_ID_BCM5421 0x002060e0 @@ -255,6 +256,7 @@ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +#define BCM54810_SHD_SCR3_TRDDAPD 0x0100 /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) -- cgit v1.2.3 From 90bf45134d55d626ae2713cac50cda10c6c8b0c2 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 15 May 2020 19:22:15 +0200 Subject: mptcp: add new sock flag to deal with join subflows MP_JOIN subflows must not land into the accept queue. Currently tcp_check_req() calls an mptcp specific helper to detect such scenario. Such helper leverages the subflow context to check for MP_JOIN subflows. We need to deal also with MP JOIN failures, even when the subflow context is not available due allocation failure. A possible solution would be changing the syn_recv_sock() signature to allow returning a more descriptive action/ error code and deal with that in tcp_check_req(). Since the above need is MPTCP specific, this patch instead uses a TCP request socket hole to add a MPTCP specific flag. Such flag is used by the MPTCP syn_recv_sock() to tell tcp_check_req() how to deal with the request socket. This change is a no-op for !MPTCP build, and makes the MPTCP code simpler. It allows also the next patch to deal correctly with MP JOIN failure. v1 -> v2: - be more conservative on drop_req initialization (Mat) RFC -> v1: - move the drop_req bit inside tcp_request_sock (Eric) Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Reviewed-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 e60db06ec28d..bf44e85d709d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -120,6 +120,9 @@ struct tcp_request_sock { u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; bool is_mptcp; +#if IS_ENABLED(CONFIG_MPTCP) + bool drop_req; +#endif u32 txhash; u32 rcv_isn; u32 snt_isn; -- cgit v1.2.3 From 8b85996095049a2216c0a6b582330ec75913243c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:48 -0700 Subject: linux/parser.h: add include guards is missing include guards. Add them. This is needed to allow declaring a function in that takes a substring_t parameter. Link: https://lore.kernel.org/r/20200512233251.118314-2-ebiggers@kernel.org Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- include/linux/parser.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/parser.h b/include/linux/parser.h index 12fc3482f5fc..89e2b23fb888 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -7,7 +7,8 @@ * but could potentially be used anywhere else that simple option=arg * parsing is required. */ - +#ifndef _LINUX_PARSER_H +#define _LINUX_PARSER_H /* associates an integer enumerator with a pattern string. */ struct match_token { @@ -34,3 +35,5 @@ int match_hex(substring_t *, int *result); bool match_wildcard(const char *pattern, const char *str); size_t match_strlcpy(char *, const substring_t *, size_t); char *match_strdup(const substring_t *); + +#endif /* _LINUX_PARSER_H */ -- cgit v1.2.3 From e5006671acc714d9dbfc6f8a618124c36f5cc6f8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 28 Apr 2020 15:49:45 -0500 Subject: clk: versatile: Drop the legacy IM-PD1 clock code Now that the non-DT IM-PD1 support code has been removed, drop the clock related code from clk-impd1.c. Link: https://lore.kernel.org/r/20200428204945.21067-1-robh@kernel.org Cc: Linus Walleij Cc: Stephen Boyd Cc: linux-arm-kernel@lists.infradead.org Cc: linux-clk@vger.kernel.org Signed-off-by: Rob Herring Reviewed-by: Linus Walleij Reviewed-by: Stephen Boyd Signed-off-by: Arnd Bergmann --- include/linux/platform_data/clk-integrator.h | 2 -- 1 file changed, 2 deletions(-) delete mode 100644 include/linux/platform_data/clk-integrator.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-integrator.h b/include/linux/platform_data/clk-integrator.h deleted file mode 100644 index addd48cac625..000000000000 --- a/include/linux/platform_data/clk-integrator.h +++ /dev/null @@ -1,2 +0,0 @@ -void integrator_impd1_clk_init(void __iomem *base, unsigned int id); -void integrator_impd1_clk_exit(unsigned int id); -- cgit v1.2.3 From 2771cefeac499d68ca2fca3861ba9e46d15bd4ae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 18:10:05 +0200 Subject: block: remove the REQ_NOWAIT_INLINE flag Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9322261fb316..ccb895f911b1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -343,7 +343,6 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ - __REQ_NOWAIT_INLINE, /* Return would-block error inline */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread @@ -378,7 +377,6 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) -#define REQ_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) -- cgit v1.2.3 From e8da08a088236aff4b51d4ec97c750051f9fe417 Mon Sep 17 00:00:00 2001 From: Benjamin Thiel Date: Sat, 16 May 2020 15:26:47 +0200 Subject: efi: Pull up arch-specific prototype efi_systab_show_arch() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pull up arch-specific prototype efi_systab_show_arch() in order to fix a -Wmissing-prototypes warning: arch/x86/platform/efi/efi.c:957:7: warning: no previous prototype for ‘efi_systab_show_arch’ [-Wmissing-prototypes] char *efi_systab_show_arch(char *str) Signed-off-by: Benjamin Thiel Link: https://lore.kernel.org/r/20200516132647.14568-1-b.thiel@posteo.de Signed-off-by: Ard Biesheuvel --- 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 251f1f783cdf..9430d01c0c3d 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1245,4 +1245,6 @@ struct linux_efi_memreserve { void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size); +char *efi_systab_show_arch(char *str); + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 4930f4831b1547b52c5968e9307fe3d840d7fba0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 16 May 2020 10:46:23 +0200 Subject: net: allow __skb_ext_alloc to sleep mptcp calls this from the transmit side, from process context. Allow a sleeping allocation instead of unconditional GFP_ATOMIC. Acked-by: Paolo Abeni Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3000c526f552..531843952809 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4165,7 +4165,7 @@ struct skb_ext { char data[] __aligned(8); }; -struct skb_ext *__skb_ext_alloc(void); +struct skb_ext *__skb_ext_alloc(gfp_t flags); 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); -- cgit v1.2.3 From 9dafdfc2f0a3ae551711098de3d7b621a469f11a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 17 May 2020 14:18:05 +0300 Subject: splice: export do_tee() export do_tee() for use in io_uring Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/splice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/splice.h b/include/linux/splice.h index ebbbfea48aa0..5c47013f708e 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -82,6 +82,9 @@ extern long do_splice(struct file *in, loff_t __user *off_in, struct file *out, loff_t __user *off_out, size_t len, unsigned int flags); +extern long do_tee(struct file *in, struct file *out, size_t len, + unsigned int flags); + /* * for dynamic pipe sizing */ -- cgit v1.2.3 From 4c033b549912bc301c5e2adfb7b6ca007c11bf31 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 11 May 2020 16:52:54 +0200 Subject: gpiolib: Add support for GPIO lookup by line name Currently a GPIO lookup table can only refer to a specific GPIO by a tuple, consisting of a GPIO controller label and a GPIO offset inside the controller. However, a GPIO may also carry a line name, defined by DT or ACPI. If present, the line name is the most use-centric way to refer to a GPIO. Hence add support for looking up GPIOs by line name. Note that there is no guarantee that GPIO line names are globally unique, so this will use the first match found. Implement this by reusing the existing gpiod_lookup infrastructure. Rename gpiod_lookup.chip_label to gpiod_lookup.key, to make it clear that this field can have two meanings, and update the kerneldoc and GPIO_LOOKUP*() macros. Signed-off-by: Geert Uytterhoeven Tested-by: Eugeniu Rosca Reviewed-by: Ulrich Hecht Reviewed-by: Eugeniu Rosca Link: https://lore.kernel.org/r/20200511145257.22970-4-geert+renesas@glider.be Signed-off-by: Linus Walleij --- include/linux/gpio/machine.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 1ebe5be05d5f..781a053abbb9 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -20,8 +20,11 @@ enum gpio_lookup_flags { /** * struct gpiod_lookup - lookup table - * @chip_label: name of the chip the GPIO belongs to - * @chip_hwnum: hardware number (i.e. relative to the chip) of the GPIO + * @key: either the name of the chip the GPIO belongs to, or the GPIO line name + * Note that GPIO line names are not guaranteed to be globally unique, + * so this will use the first match found! + * @chip_hwnum: hardware number (i.e. relative to the chip) of the GPIO, or + * U16_MAX to indicate that @key is a GPIO line name * @con_id: name of the GPIO from the device's point of view * @idx: index of the GPIO in case several GPIOs share the same name * @flags: bitmask of gpio_lookup_flags GPIO_* values @@ -30,7 +33,7 @@ enum gpio_lookup_flags { * functions using platform data. */ struct gpiod_lookup { - const char *chip_label; + const char *key; u16 chip_hwnum; const char *con_id; unsigned int idx; @@ -63,17 +66,17 @@ struct gpiod_hog { /* * Simple definition of a single GPIO under a con_id */ -#define GPIO_LOOKUP(_chip_label, _chip_hwnum, _con_id, _flags) \ - GPIO_LOOKUP_IDX(_chip_label, _chip_hwnum, _con_id, 0, _flags) +#define GPIO_LOOKUP(_key, _chip_hwnum, _con_id, _flags) \ + GPIO_LOOKUP_IDX(_key, _chip_hwnum, _con_id, 0, _flags) /* * Use this macro if you need to have several GPIOs under the same con_id. * Each GPIO needs to use a different index and can be accessed using * gpiod_get_index() */ -#define GPIO_LOOKUP_IDX(_chip_label, _chip_hwnum, _con_id, _idx, _flags) \ +#define GPIO_LOOKUP_IDX(_key, _chip_hwnum, _con_id, _idx, _flags) \ { \ - .chip_label = _chip_label, \ + .key = _key, \ .chip_hwnum = _chip_hwnum, \ .con_id = _con_id, \ .idx = _idx, \ -- cgit v1.2.3 From 5c8f77a278737a6af44a892f0700d9aadb2b0de0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 14 May 2020 10:39:00 +0200 Subject: irqdomain: Make irq_domain_reset_irq_data() available to non-hierarchical users irq_domain_reset_irq_data() doesn't modify the parent data, so it can be made available even if irq domain hierarchy is not being built. We'll subsequently use it in irq_sim code. Signed-off-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20200514083901.23445-2-brgl@bgdev.pl --- 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 8d062e86d954..b37350c4fe37 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -450,6 +450,7 @@ extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq, struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name); +extern void irq_domain_reset_irq_data(struct irq_data *irq_data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY extern struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, unsigned int flags, unsigned int size, @@ -491,7 +492,6 @@ extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, irq_hw_number_t hwirq, struct irq_chip *chip, void *chip_data); -extern void irq_domain_reset_irq_data(struct irq_data *irq_data); extern void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); -- cgit v1.2.3 From 337cbeb2c13eb4cab84f576fd402d7ae4ed31ae1 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 14 May 2020 10:39:01 +0200 Subject: genirq/irq_sim: Simplify the API The interrupt simulator API exposes a lot of custom data structures and functions and doesn't reuse the interfaces already exposed by the irq subsystem. This patch tries to address it. We hide all the simulator-related data structures from users and instead rely on the well-known irq domain. When creating the interrupt simulator the user receives a pointer to a newly created irq_domain and can use it to create mappings for simulated interrupts. It is also possible to pass a handle to fwnode when creating the simulator domain and retrieve it using irq_find_matching_fwnode(). The irq_sim_fire() function is dropped as well. Instead we implement the irq_get/set_irqchip_state interface. We modify the two modules that use the simulator at the same time as adding these changes in order to reduce the intermediate bloat that would result when trying to migrate the drivers in separate patches. Signed-off-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Reviewed-by: Linus Walleij Acked-by: Jonathan Cameron #for IIO Link: https://lore.kernel.org/r/20200514083901.23445-3-brgl@bgdev.pl --- include/linux/irq_sim.h | 33 +++++++++------------------------ 1 file changed, 9 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h index 4500d453a63e..ab831e5ae748 100644 --- a/include/linux/irq_sim.h +++ b/include/linux/irq_sim.h @@ -1,41 +1,26 @@ /* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (C) 2017-2018 Bartosz Golaszewski + * Copyright (C) 2020 Bartosz Golaszewski */ #ifndef _LINUX_IRQ_SIM_H #define _LINUX_IRQ_SIM_H -#include #include +#include +#include /* * Provides a framework for allocating simulated interrupts which can be * requested like normal irqs and enqueued from process context. */ -struct irq_sim_work_ctx { - struct irq_work work; - unsigned long *pending; -}; - -struct irq_sim_irq_ctx { - int irqnum; - bool enabled; -}; - -struct irq_sim { - struct irq_sim_work_ctx work_ctx; - int irq_base; - unsigned int irq_count; - struct irq_sim_irq_ctx *irqs; -}; - -int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs); -int devm_irq_sim_init(struct device *dev, struct irq_sim *sim, - unsigned int num_irqs); -void irq_sim_fini(struct irq_sim *sim); -void irq_sim_fire(struct irq_sim *sim, unsigned int offset); -int irq_sim_irqnum(struct irq_sim *sim, unsigned int offset); +struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, + unsigned int num_irqs); +struct irq_domain *devm_irq_domain_create_sim(struct device *dev, + struct fwnode_handle *fwnode, + unsigned int num_irqs); +void irq_domain_remove_sim(struct irq_domain *domain); #endif /* _LINUX_IRQ_SIM_H */ -- cgit v1.2.3 From 3db9983e4327f773c490de2a8c66d6000561d88a Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:44 +0800 Subject: iommu/vt-d: Move domain helper to header Move domain helper to header to be used by SVA code. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200516062101.29541-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 980234ae0312..ed7171d2ae1f 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -595,6 +595,12 @@ static inline void __iommu_flush_cache( clflush_cache_range(addr, size); } +/* Convert generic struct iommu_domain to private struct dmar_domain */ +static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct dmar_domain, domain); +} + /* * 0: readable * 1: writable -- cgit v1.2.3 From b0d1f8741b812352fe0e5f3b2381427085f23e19 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:46 +0800 Subject: iommu/vt-d: Add nested translation helper function Nested translation mode is supported in VT-d 3.0 Spec.CH 3.8. With PASID granular translation type set to 0x11b, translation result from the first level(FL) also subject to a second level(SL) page table translation. This mode is used for SVA virtualization, where FL performs guest virtual to guest physical translation and SL performs guest physical to host physical translation. This patch adds a helper function for setting up nested translation where second level comes from a domain and first level comes from a guest PGD. Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200516062101.29541-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ed7171d2ae1f..e0d1fed7cbe4 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -42,6 +42,9 @@ #define DMA_FL_PTE_PRESENT BIT_ULL(0) #define DMA_FL_PTE_XD BIT_ULL(63) +#define ADDR_WIDTH_5LEVEL (57) +#define ADDR_WIDTH_4LEVEL (48) + #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 #define CONTEXT_TT_PASS_THROUGH 2 @@ -480,6 +483,23 @@ struct context_entry { u64 hi; }; +/* si_domain contains mulitple devices */ +#define DOMAIN_FLAG_STATIC_IDENTITY BIT(0) + +/* + * When VT-d works in the scalable mode, it allows DMA translation to + * happen through either first level or second level page table. This + * bit marks that the DMA translation for the domain goes through the + * first level page table, otherwise, it goes through the second level. + */ +#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(1) + +/* + * Domain represents a virtual machine which demands iommu nested + * translation mode support. + */ +#define DOMAIN_FLAG_NESTING_MODE BIT(2) + struct dmar_domain { int nid; /* node id */ -- cgit v1.2.3 From 56722a4398a306585ca3ed39ff54fc907af98618 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:47 +0800 Subject: iommu/vt-d: Add bind guest PASID support When supporting guest SVA with emulated IOMMU, the guest PASID table is shadowed in VMM. Updates to guest vIOMMU PASID table will result in PASID cache flush which will be passed down to the host as bind guest PASID calls. For the SL page tables, it will be harvested from device's default domain (request w/o PASID), or aux domain in case of mediated device. .-------------. .---------------------------. | vIOMMU | | Guest process CR3, FL only| | | '---------------------------' .----------------/ | PASID Entry |--- PASID cache flush - '-------------' | | | V | | CR3 in GPA '-------------' Guest ------| Shadow |--------------------------|-------- v v v Host .-------------. .----------------------. | pIOMMU | | Bind FL for GVA-GPA | | | '----------------------' .----------------/ | | PASID Entry | V (Nested xlate) '----------------\.------------------------------. | | |SL for GPA-HPA, default domain| | | '------------------------------' '-------------' Where: - FL = First level/stage one page tables - SL = Second level/stage two page tables Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 6 +++++- include/linux/intel-svm.h | 12 ++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e0d1fed7cbe4..3dfd426dfb03 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -698,7 +698,9 @@ struct dmar_domain *find_domain(struct device *dev); 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); - +int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, + struct iommu_gpasid_bind_data *data); +int intel_svm_unbind_gpasid(struct device *dev, int pasid); struct svm_dev_ops; struct intel_svm_dev { @@ -715,9 +717,11 @@ struct intel_svm_dev { struct intel_svm { struct mmu_notifier notifier; struct mm_struct *mm; + struct intel_iommu *iommu; int flags; int pasid; + int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; struct list_head list; }; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index d7c403d0dd27..1b47ca46373e 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -44,6 +44,18 @@ struct svm_dev_ops { * do such IOTLB flushes automatically. */ #define SVM_FLAG_SUPERVISOR_MODE (1<<1) +/* + * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest + * processes. Compared to the host bind, the primary differences are: + * 1. mm life cycle management + * 2. fault reporting + */ +#define SVM_FLAG_GUEST_MODE (1<<2) +/* + * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space, + * which requires guest and host PASID translation at both directions. + */ +#define SVM_FLAG_GUEST_PASID (1<<3) #ifdef CONFIG_INTEL_IOMMU_SVM -- cgit v1.2.3 From 61a06a16e36d830f7811fbf931668d87197d95b7 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:48 +0800 Subject: iommu/vt-d: Support flushing more translation cache types When Shared Virtual Memory is exposed to a guest via vIOMMU, scalable IOTLB invalidation may be passed down from outside IOMMU subsystems. This patch adds invalidation functions that can be used for additional translation cache types. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200516062101.29541-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3dfd426dfb03..a9c984b29a72 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -334,7 +334,7 @@ enum { #define QI_IOTLB_GRAN(gran) (((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4)) #define QI_IOTLB_ADDR(addr) (((u64)addr) & VTD_PAGE_MASK) #define QI_IOTLB_IH(ih) (((u64)ih) << 6) -#define QI_IOTLB_AM(am) (((u8)am)) +#define QI_IOTLB_AM(am) (((u8)am) & 0x3f) #define QI_CC_FM(fm) (((u64)fm) << 48) #define QI_CC_SID(sid) (((u64)sid) << 32) @@ -353,16 +353,21 @@ enum { #define QI_PC_DID(did) (((u64)did) << 16) #define QI_PC_GRAN(gran) (((u64)gran) << 4) -#define QI_PC_ALL_PASIDS (QI_PC_TYPE | QI_PC_GRAN(0)) -#define QI_PC_PASID_SEL (QI_PC_TYPE | QI_PC_GRAN(1)) +/* PASID cache invalidation granu */ +#define QI_PC_ALL_PASIDS 0 +#define QI_PC_PASID_SEL 1 #define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) #define QI_EIOTLB_IH(ih) (((u64)ih) << 6) -#define QI_EIOTLB_AM(am) (((u64)am)) +#define QI_EIOTLB_AM(am) (((u64)am) & 0x3f) #define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32) #define QI_EIOTLB_DID(did) (((u64)did) << 16) #define QI_EIOTLB_GRAN(gran) (((u64)gran) << 4) +/* QI Dev-IOTLB inv granu */ +#define QI_DEV_IOTLB_GRAN_ALL 1 +#define QI_DEV_IOTLB_GRAN_PASID_SEL 0 + #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) #define QI_DEV_EIOTLB_GLOB(g) ((u64)g) @@ -679,8 +684,16 @@ 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); + +void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, + u32 pasid, u16 qdep, u64 addr, + unsigned int size_order, u64 granu); +void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, + int pasid); + extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); extern int dmar_ir_support(void); -- cgit v1.2.3 From 24f27d32ab6b71dedcbbeeab8f9bdc143b539ac0 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:50 +0800 Subject: iommu/vt-d: Enlightened PASID allocation Enabling IOMMU in a guest requires communication with the host driver for certain aspects. Use of PASID ID to enable Shared Virtual Addressing (SVA) requires managing PASID's in the host. VT-d 3.0 spec provides a Virtual Command Register (VCMD) to facilitate this. Writes to this register in the guest are trapped by vIOMMU which proxies the call to the host driver. This virtual command interface consists of a capability register, a virtual command register, and a virtual response register. Refer to section 10.4.42, 10.4.43, 10.4.44 for more information. This patch adds the enlightened PASID allocation/free interfaces via the virtual command interface. Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200516062101.29541-8-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index a9c984b29a72..addb310b4ded 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -169,6 +169,7 @@ #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) +#define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) ((e >> 41) & 0x1) #define ecap_pasid(e) ((e >> 40) & 0x1) -- cgit v1.2.3 From 3375303e82877552f3b2b42309e8233fe715fd9f Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:51 +0800 Subject: iommu/vt-d: Add custom allocator for IOASID When VT-d driver runs in the guest, PASID allocation must be performed via virtual command interface. This patch registers a custom IOASID allocator which takes precedence over the default XArray based allocator. The resulting IOASID allocation will always come from the host. This ensures that PASID namespace is system- wide. Virtual command registers are used in the guest only, to prevent vmexit cost, we cache the capability and store it during initialization. Signed-off-by: Liu, Yi L Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200516062101.29541-9-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index addb310b4ded..e14124f74b3a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -195,6 +196,9 @@ #define ecap_max_handle_mask(e) ((e >> 20) & 0xf) #define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */ +/* Virtual command interface capability */ +#define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ + /* IOTLB_REG */ #define DMA_TLB_FLUSH_GRANU_OFFSET 60 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60) @@ -288,6 +292,7 @@ /* PRS_REG */ #define DMA_PRS_PPR ((u32)1) +#define DMA_VCS_PAS ((u64)1) #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ @@ -555,6 +560,7 @@ struct intel_iommu { u64 reg_size; /* size of hw register set */ u64 cap; u64 ecap; + u64 vccap; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ raw_spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ @@ -575,6 +581,7 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU_SVM struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ + struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ -- cgit v1.2.3 From e85bb99b79ca5ad2681612a7bb22f94cc2c71866 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:52 +0800 Subject: iommu/vt-d: Add get_domain_info() helper Add a get_domain_info() helper to retrieve the valid per-device iommu private data. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-10-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e14124f74b3a..caa179e806fc 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -714,6 +714,7 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info, 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); +struct device_domain_info *get_domain_info(struct device *dev); #ifdef CONFIG_INTEL_IOMMU_SVM extern void intel_svm_check(struct intel_iommu *iommu); -- cgit v1.2.3 From 064a57d7ddfc46ada02b477b91c478001b03bfa3 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:54 +0800 Subject: iommu/vt-d: Replace intel SVM APIs with generic SVA APIs This patch is an initial step to replace Intel SVM code with the following IOMMU SVA ops: intel_svm_bind_mm() => iommu_sva_bind_device() intel_svm_unbind_mm() => iommu_sva_unbind_device() intel_svm_is_pasid_valid() => iommu_sva_get_pasid() The features below will continue to work but are not included in this patch in that they are handled mostly within the IOMMU subsystem. - IO page fault - mmu notifier Consolidation of the above will come after merging generic IOMMU sva code[1]. There should not be any changes needed for SVA users such as accelerator device drivers during this time. [1] http://jpbrucker.net/sva/ Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 6 ++++ include/linux/intel-svm.h | 86 --------------------------------------------- 2 files changed, 6 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index caa179e806fc..42245e1e1b48 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -723,6 +723,10 @@ extern int intel_svm_finish_prq(struct intel_iommu *iommu); int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, struct iommu_gpasid_bind_data *data); int intel_svm_unbind_gpasid(struct device *dev, int pasid); +struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, + void *drvdata); +void intel_svm_unbind(struct iommu_sva *handle); +int intel_svm_get_pasid(struct iommu_sva *handle); struct svm_dev_ops; struct intel_svm_dev { @@ -730,6 +734,8 @@ struct intel_svm_dev { struct rcu_head rcu; struct device *dev; struct svm_dev_ops *ops; + struct iommu_sva sva; + int pasid; int users; u16 did; u16 dev_iotlb:1; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 1b47ca46373e..c9e7e601950d 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -21,7 +21,6 @@ struct svm_dev_ops { #define SVM_REQ_EXEC (1<<1) #define SVM_REQ_PRIV (1<<0) - /* * The SVM_FLAG_PRIVATE_PASID flag requests a PASID which is *not* the "main" * PASID for the current process. Even if a PASID already exists, a new one @@ -57,89 +56,4 @@ struct svm_dev_ops { */ #define SVM_FLAG_GUEST_PASID (1<<3) -#ifdef CONFIG_INTEL_IOMMU_SVM - -/** - * intel_svm_bind_mm() - Bind the current process to a PASID - * @dev: Device to be granted access - * @pasid: Address for allocated PASID - * @flags: Flags. Later for requesting supervisor mode, etc. - * @ops: Callbacks to device driver - * - * This function attempts to enable PASID support for the given device. - * If the @pasid argument is non-%NULL, a PASID is allocated for access - * to the MM of the current process. - * - * By using a %NULL value for the @pasid argument, this function can - * be used to simply validate that PASID support is available for the - * given device — i.e. that it is behind an IOMMU which has the - * requisite support, and is enabled. - * - * Page faults are handled transparently by the IOMMU code, and there - * should be no need for the device driver to be involved. If a page - * fault cannot be handled (i.e. is an invalid address rather than - * just needs paging in), then the page request will be completed by - * the core IOMMU code with appropriate status, and the device itself - * can then report the resulting fault to its driver via whatever - * mechanism is appropriate. - * - * Multiple calls from the same process may result in the same PASID - * being re-used. A reference count is kept. - */ -extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, - struct svm_dev_ops *ops); - -/** - * intel_svm_unbind_mm() - Unbind a specified PASID - * @dev: Device for which PASID was allocated - * @pasid: PASID value to be unbound - * - * This function allows a PASID to be retired when the device no - * longer requires access to the address space of a given process. - * - * If the use count for the PASID in question reaches zero, the - * PASID is revoked and may no longer be used by hardware. - * - * Device drivers are required to ensure that no access (including - * page requests) is currently outstanding for the PASID in question, - * before calling this function. - */ -extern int intel_svm_unbind_mm(struct device *dev, int pasid); - -/** - * intel_svm_is_pasid_valid() - check if pasid is valid - * @dev: Device for which PASID was allocated - * @pasid: PASID value to be checked - * - * This function checks if the specified pasid is still valid. A - * valid pasid means the backing mm is still having a valid user. - * For kernel callers init_mm is always valid. for other mm, if mm->mm_users - * is non-zero, it is valid. - * - * returns -EINVAL if invalid pasid, 0 if pasid ref count is invalid - * 1 if pasid is valid. - */ -extern int intel_svm_is_pasid_valid(struct device *dev, int pasid); - -#else /* CONFIG_INTEL_IOMMU_SVM */ - -static inline int intel_svm_bind_mm(struct device *dev, int *pasid, - int flags, struct svm_dev_ops *ops) -{ - return -ENOSYS; -} - -static inline int intel_svm_unbind_mm(struct device *dev, int pasid) -{ - BUG(); -} - -static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid) -{ - return -EINVAL; -} -#endif /* CONFIG_INTEL_IOMMU_SVM */ - -#define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL)) - #endif /* __INTEL_SVM_H__ */ -- cgit v1.2.3 From 8a1d824625402b3ef3c3e5965663354ff0394d86 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:55 +0800 Subject: iommu/vt-d: Multiple descriptors per qi_submit_sync() Current qi_submit_sync() only supports single invalidation descriptor per submission and appends wait descriptor after each submission to poll the hardware completion. This extends the qi_submit_sync() helper to support multiple descriptors, and add an option so that the caller could specify the Page-request Drain (PD) bit in the wait descriptor. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200516062101.29541-13-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 42245e1e1b48..677dee59e3c0 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -333,6 +333,7 @@ enum { #define QI_IWD_STATUS_DATA(d) (((u64)d) << 32) #define QI_IWD_STATUS_WRITE (((u64)1) << 5) +#define QI_IWD_PRQ_DRAIN (((u64)1) << 7) #define QI_IOTLB_DID(did) (((u64)did) << 16) #define QI_IOTLB_DR(dr) (((u64)dr) << 7) @@ -702,7 +703,13 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, int pasid); -extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); +int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, + unsigned int count, unsigned long options); +/* + * Options used in qi_submit_sync: + * QI_OPT_WAIT_DRAIN - Wait for PRQ drain completion, spec 6.5.2.8. + */ +#define QI_OPT_WAIT_DRAIN BIT(0) extern int dmar_ir_support(void); -- cgit v1.2.3 From 66ac4db36f4c12a3b02db864ccb0801cd938b6de Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:58 +0800 Subject: iommu/vt-d: Add page request draining support When a PASID is stopped or terminated, there can be pending PRQs (requests that haven't received responses) in remapping hardware. This adds the interface to drain page requests and call it when a PASID is terminated. Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-16-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 677dee59e3c0..21633cee6331 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -292,6 +292,8 @@ /* PRS_REG */ #define DMA_PRS_PPR ((u32)1) +#define DMA_PRS_PRO ((u32)2) + #define DMA_VCS_PAS ((u64)1) #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ @@ -333,6 +335,7 @@ enum { #define QI_IWD_STATUS_DATA(d) (((u64)d) << 32) #define QI_IWD_STATUS_WRITE (((u64)1) << 5) +#define QI_IWD_FENCE (((u64)1) << 6) #define QI_IWD_PRQ_DRAIN (((u64)1) << 7) #define QI_IOTLB_DID(did) (((u64)did) << 16) @@ -582,6 +585,7 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU_SVM struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ + struct completion prq_complete; struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct q_inval *qi; /* Queued invalidation info */ -- cgit v1.2.3 From 81530a38a36d411e01ea99116503901f75aa758b Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 15 May 2020 11:05:15 +0300 Subject: phy: omap-usb2: Clean up exported header Move private definitions from header to phy-omap-usb2.c file. Get rid of unused data structures usb_dpll_params and omap_usb_phy_type. Signed-off-by: Roger Quadros Link: https://lore.kernel.org/r/20200515080518.26870-2-rogerq@ti.com Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/omap_usb.h | 69 ++------------------------------------------ 1 file changed, 2 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/omap_usb.h b/include/linux/phy/omap_usb.h index 5973a6313529..e23b52df93ec 100644 --- a/include/linux/phy/omap_usb.h +++ b/include/linux/phy/omap_usb.h @@ -2,68 +2,14 @@ /* * omap_usb.h -- omap usb2 phy header file * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2012-2020 Texas Instruments Incorporated - http://www.ti.com * Author: Kishon Vijay Abraham I */ #ifndef __DRIVERS_OMAP_USB2_H #define __DRIVERS_OMAP_USB2_H -#include -#include - -struct usb_dpll_params { - u16 m; - u8 n; - u8 freq:3; - u8 sd; - u32 mf; -}; - -enum omap_usb_phy_type { - TYPE_USB2, /* USB2_PHY, power down in CONTROL_DEV_CONF */ - TYPE_DRA7USB2, /* USB2 PHY, power and power_aux e.g. DRA7 */ - TYPE_AM437USB2, /* USB2 PHY, power e.g. AM437x */ -}; - -struct omap_usb { - struct usb_phy phy; - struct phy_companion *comparator; - void __iomem *pll_ctrl_base; - void __iomem *phy_base; - struct device *dev; - struct device *control_dev; - struct clk *wkupclk; - struct clk *optclk; - u8 flags; - enum omap_usb_phy_type type; - struct regmap *syscon_phy_power; /* ctrl. reg. acces */ - unsigned int power_reg; /* power reg. index within syscon */ - u32 mask; - u32 power_on; - u32 power_off; -}; - -struct usb_phy_data { - const char *label; - u8 flags; - u32 mask; - u32 power_on; - u32 power_off; -}; - -/* Driver Flags */ -#define OMAP_USB2_HAS_START_SRP (1 << 0) -#define OMAP_USB2_HAS_SET_VBUS (1 << 1) -#define OMAP_USB2_CALIBRATE_FALSE_DISCONNECT (1 << 2) - -#define OMAP_DEV_PHY_PD BIT(0) -#define OMAP_USB2_PHY_PD BIT(28) - -#define AM437X_USB2_PHY_PD BIT(0) -#define AM437X_USB2_OTG_PD BIT(1) -#define AM437X_USB2_OTGVDET_EN BIT(19) -#define AM437X_USB2_OTGSESSEND_EN BIT(20) +#include #define phy_to_omapusb(x) container_of((x), struct omap_usb, phy) @@ -76,15 +22,4 @@ static inline int omap_usb2_set_comparator(struct phy_companion *comparator) } #endif -static inline u32 omap_usb_readl(void __iomem *addr, unsigned offset) -{ - return __raw_readl(addr + offset); -} - -static inline void omap_usb_writel(void __iomem *addr, unsigned offset, - u32 data) -{ - __raw_writel(data, addr + offset); -} - #endif /* __DRIVERS_OMAP_USB_H */ -- cgit v1.2.3 From 356d411c26735bcc62718c4c9181014255dc302d Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 15 May 2020 15:16:52 -0700 Subject: net/mlx5: Cleanup mlx5_ifc_fte_match_set_misc2_bits Remove the "metadata_reg_b" field and all uses of this field in code to match the device specification. As this field is not in use in SW steering it is safe to remove it. Signed-off-by: Raed Salem Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c9dd6e99ad56..fd8da4875ea0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -584,9 +584,7 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; - u8 metadata_reg_b[0x20]; - - u8 reserved_at_1c0[0x40]; + u8 reserved_at_1a0[0x60]; }; struct mlx5_ifc_fte_match_set_misc3_bits { -- cgit v1.2.3 From 555af0c3fa0b632be73c241cc932129af4b70d27 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 15 May 2020 15:16:53 -0700 Subject: net/mlx5: Move iseg access helper routines close to mlx5_core driver Only mlx5_core driver handles fw initialization check and command interface revision check. Hence move them inside the mlx5_core driver where it is used. This avoid exposing these helpers to all mlx5 drivers. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 24e04901f92e..a988eb405aa6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -823,11 +823,6 @@ static inline u16 fw_rev_sub(struct mlx5_core_dev *dev) return ioread32be(&dev->iseg->cmdif_rev_fw_sub) & 0xffff; } -static inline u16 cmdif_rev(struct mlx5_core_dev *dev) -{ - return ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; -} - static inline u32 mlx5_base_mkey(const u32 key) { return key & 0xffffff00u; @@ -1012,11 +1007,6 @@ int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, u8 roce_version, u8 roce_l3_type, const u8 *gid, const u8 *mac, bool vlan, u16 vlan_id, u8 port_num); -static inline int fw_initializing(struct mlx5_core_dev *dev) -{ - return ioread32be(&dev->iseg->initializing) >> 31; -} - static inline u32 mlx5_mkey_to_idx(u32 mkey) { return mkey >> 8; -- cgit v1.2.3 From 51189c7a7ed1b4ed4493e27275d466ff60406d3a Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 15 May 2020 14:11:05 +0100 Subject: arm64: scs: Store absolute SCS stack pointer value in thread_info Storing the SCS information in thread_info as a {base,offset} pair introduces an additional load instruction on the ret-to-user path, since the SCS stack pointer in x18 has to be converted back to an offset by subtracting the base. Replace the offset with the absolute SCS stack pointer value instead and avoid the redundant load. Tested-by: Sami Tolvanen Reviewed-by: Mark Rutland Signed-off-by: Will Deacon --- include/linux/scs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scs.h b/include/linux/scs.h index 3f3662621a27..0eb2485ef832 100644 --- a/include/linux/scs.h +++ b/include/linux/scs.h @@ -27,7 +27,7 @@ #define SCS_END_MAGIC (0x5f6UL + POISON_POINTER_DELTA) #define task_scs(tsk) (task_thread_info(tsk)->scs_base) -#define task_scs_offset(tsk) (task_thread_info(tsk)->scs_offset) +#define task_scs_sp(tsk) (task_thread_info(tsk)->scs_sp) void scs_init(void); int scs_prepare(struct task_struct *tsk, int node); @@ -39,7 +39,7 @@ static inline void scs_task_reset(struct task_struct *tsk) * Reset the shadow stack to the base address in case the task * is reused. */ - task_scs_offset(tsk) = 0; + task_scs_sp(tsk) = task_scs(tsk); } static inline unsigned long *__scs_magic(void *s) @@ -50,9 +50,9 @@ static inline unsigned long *__scs_magic(void *s) static inline bool scs_corrupted(struct task_struct *tsk) { unsigned long *magic = __scs_magic(task_scs(tsk)); + unsigned long sz = task_scs_sp(tsk) - task_scs(tsk); - return (task_scs_offset(tsk) >= SCS_SIZE - 1 || - READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC); + return sz >= SCS_SIZE - 1 || READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC; } #else /* CONFIG_SHADOW_CALL_STACK */ -- cgit v1.2.3 From 88485be531f4aee841ddc53b56e2f6e6a338854d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 15 May 2020 14:56:05 +0100 Subject: scs: Move scs_overflow_check() out of architecture code There is nothing architecture-specific about scs_overflow_check() as it's just a trivial wrapper around scs_corrupted(). For parity with task_stack_end_corrupted(), rename scs_corrupted() to task_scs_end_corrupted() and call it from schedule_debug() when CONFIG_SCHED_STACK_END_CHECK_is enabled, which better reflects its purpose as a debug feature to catch inadvertent overflow of the SCS. Finally, remove the unused scs_overflow_check() function entirely. This has absolutely no impact on architectures that do not support SCS (currently arm64 only). Tested-by: Sami Tolvanen Reviewed-by: Mark Rutland Signed-off-by: Will Deacon --- include/linux/scs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scs.h b/include/linux/scs.h index 0eb2485ef832..2fd3df50e93e 100644 --- a/include/linux/scs.h +++ b/include/linux/scs.h @@ -47,7 +47,7 @@ static inline unsigned long *__scs_magic(void *s) return (unsigned long *)(s + SCS_SIZE) - 1; } -static inline bool scs_corrupted(struct task_struct *tsk) +static inline bool task_scs_end_corrupted(struct task_struct *tsk) { unsigned long *magic = __scs_magic(task_scs(tsk)); unsigned long sz = task_scs_sp(tsk) - task_scs(tsk); @@ -60,8 +60,8 @@ static inline bool scs_corrupted(struct task_struct *tsk) static inline void scs_init(void) {} static inline void scs_task_reset(struct task_struct *tsk) {} static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; } -static inline bool scs_corrupted(struct task_struct *tsk) { return false; } static inline void scs_release(struct task_struct *tsk) {} +static inline bool task_scs_end_corrupted(struct task_struct *tsk) { return false; } #endif /* CONFIG_SHADOW_CALL_STACK */ -- cgit v1.2.3 From 871e100e432c651c9c46fb9c3184b4577e0de3ae Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 15 May 2020 16:17:12 +0100 Subject: scs: Move DEFINE_SCS macro into core code Defining static shadow call stacks is not architecture-specific, so move the DEFINE_SCS() macro into the core header file. Tested-by: Sami Tolvanen Reviewed-by: Mark Rutland Signed-off-by: Will Deacon --- include/linux/scs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scs.h b/include/linux/scs.h index 2fd3df50e93e..6dec390cf154 100644 --- a/include/linux/scs.h +++ b/include/linux/scs.h @@ -26,6 +26,10 @@ /* An illegal pointer value to mark the end of the shadow stack. */ #define SCS_END_MAGIC (0x5f6UL + POISON_POINTER_DELTA) +/* Allocate a static per-CPU shadow stack */ +#define DEFINE_SCS(name) \ + DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], name) \ + #define task_scs(tsk) (task_thread_info(tsk)->scs_base) #define task_scs_sp(tsk) (task_thread_info(tsk)->scs_sp) -- cgit v1.2.3 From 220995622da5317714b5fe659165735f7b44b87e Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 7 May 2020 13:08:46 -0700 Subject: kgdboc: Add kgdboc_earlycon to support early kgdb using boot consoles We want to enable kgdb to debug the early parts of the kernel. Unfortunately kgdb normally is a client of the tty API in the kernel and serial drivers don't register to the tty layer until fairly late in the boot process. Serial drivers do, however, commonly register a boot console. Let's enable the kgdboc driver to work with boot consoles to provide early debugging. This change co-opts the existing read() function pointer that's part of "struct console". It's assumed that if a boot console (with the flag CON_BOOT) has implemented read() that both the read() and write() function are polling functions. That means they work without interrupts and read() will return immediately (with 0 bytes read) if there's nothing to read. This should be a safe assumption since it appears that no current boot consoles implement read() right now and there seems no reason to do so unless they wanted to support "kgdboc_earlycon". The normal/expected way to make all this work is to use "kgdboc_earlycon" and "kgdboc" together. You should point them both to the same physical serial connection. At boot time, as the system transitions from the boot console to the normal console (and registers a tty), kgdb will switch over. One awkward part of all this, though, is that there can be a window where the boot console goes away and we can't quite transtion over to the main kgdboc that uses the tty layer. There are two main problems: 1. The act of registering the tty doesn't cause any call into kgdboc so there is a window of time when the tty is there but kgdboc's init code hasn't been called so we can't transition to it. 2. On some serial drivers the normal console inits (and replaces the boot console) quite early in the system. Presumably these drivers were coded up before earlycon worked as well as it does today and probably they don't need to do this anymore, but it causes us problems nontheless. Problem #1 is not too big of a deal somewhat due to the luck of probe ordering. kgdboc is last in the tty/serial/Makefile so its probe gets right after all other tty devices. It's not fun to rely on this, but it does work for the most part. Problem #2 is a big deal, but only for some serial drivers. Other serial drivers end up registering the console (which gets rid of the boot console) and tty at nearly the same time. The way we'll deal with the window when the system has stopped using the boot console and the time when we're setup using the tty is to keep using the boot console. This may sound surprising, but it has been found to work well in practice. If it doesn't work, it shouldn't be too hard for a given serial driver to make it keep working. Specifically, it's expected that the read()/write() function provided in the boot console should be the same (or nearly the same) as the normal kgdb polling functions. That means continuing to use them should work just fine. To make things even more likely to work work we'll also trap the recently added exit() function in the boot console we're using and delay any calls to it until we're all done with the boot console. NOTE: there could be ways to use all this in weird / unexpected ways. If you do something like this, it's a bit of a buyer beware situation. Specifically: - If you specify only "kgdboc_earlycon" but not "kgdboc" then (depending on your serial driver) things will probably work OK, but you'll get a warning printed the first time you use kgdb after the boot console is gone. You'd only be able to do this, of course, if the serial driver you're running atop provided an early boot console. - If your "kgdboc_earlycon" and "kgdboc" devices are not the same device things should work OK, but it'll be your job to switch over which device you're monitoring (including figuring out how to switch over gdb in-flight if you're using it). When trying to enable "kgdboc_earlycon" it should be noted that the names that are registered through the boot console layer and the tty layer are not the same for the same port. For example when debugging on one board I'd need to pass "kgdboc_earlycon=qcom_geni kgdboc=ttyMSM0" to enable things properly. Since digging up the boot console name is a pain and there will rarely be more than one boot console enabled, you can provide the "kgdboc_earlycon" parameter without specifying the name of the boot console. In this case we'll just pick the first boot that implements read() that we find. This new "kgdboc_earlycon" parameter should be contrasted to the existing "ekgdboc" parameter. While both provide a way to debug very early, the usage and mechanisms are quite different. Specifically "kgdboc_earlycon" is meant to be used in tandem with "kgdboc" and there is a transition from one to the other. The "ekgdboc" parameter, on the other hand, replaces the "kgdboc" parameter. It runs the same logic as the "kgdboc" parameter but just relies on your TTY driver being present super early. The only known usage of the old "ekgdboc" parameter is documented as "ekgdboc=kbd earlyprintk=vga". It should be noted that "kbd" has special treatment allowing it to init early as a tty device. Signed-off-by: Douglas Anderson Reviewed-by: Greg Kroah-Hartman Tested-by: Sumit Garg Link: https://lore.kernel.org/r/20200507130644.v4.8.I8fba5961bf452ab92350654aa61957f23ecf0100@changeid Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index c2caee08e418..c62d76478adc 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -269,6 +269,9 @@ struct kgdb_arch { * @write_char: Pointer to a function that will write one char. * @flush: Pointer to a function that will flush any pending writes. * @init: Pointer to a function that will initialize the device. + * @deinit: Pointer to a function that will deinit the device. Implies that + * this I/O driver is temporary and expects to be replaced. Called when + * an I/O driver is replaced or explicitly unregistered. * @pre_exception: Pointer to a function that will do any prep work for * the I/O driver. * @post_exception: Pointer to a function that will do any cleanup work @@ -282,6 +285,7 @@ struct kgdb_io { void (*write_char) (u8); void (*flush) (void); int (*init) (void); + void (*deinit) (void); void (*pre_exception) (void); void (*post_exception) (void); int is_console; -- cgit v1.2.3 From a307593a644443db12888f45eed0dafb5869e2cc Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 18 May 2020 15:23:59 -0700 Subject: net: phy: simplify phy_link_change arguments This function was introduced to allow for different handling of link up and link down events particularly with regard to the netif_carrier. The third argument do_carrier allowed the flag to be left unchanged. Since then the phylink has introduced an implementation that completely ignores the third parameter since it never wants to change the flag and the phylib always sets the third parameter to true so the flag is always changed. Therefore the third argument (i.e. do_carrier) is no longer necessary and can be removed. This also means that the phylib phy_link_down() function no longer needs its second argument. Signed-off-by: Doug Berger 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 5d8ff5428010..467aa8bf9f64 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -543,7 +543,7 @@ struct phy_device { u8 mdix; u8 mdix_ctrl; - void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); #if IS_ENABLED(CONFIG_MACSEC) -- cgit v1.2.3 From ed318a6cc0b620440e65f48eb527dc3df7269ce4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:50 -0700 Subject: fscrypt: support test_dummy_encryption=v2 v1 encryption policies are deprecated in favor of v2, and some new features (e.g. encryption+casefolding) are only being added for v2. Therefore, the "test_dummy_encryption" mount option (which is used for encryption I/O testing with xfstests) needs to support v2 policies. To do this, extend its syntax to be "test_dummy_encryption=v1" or "test_dummy_encryption=v2". The existing "test_dummy_encryption" (no argument) also continues to be accepted, to specify the default setting -- currently v1, but the next patch changes it to v2. To cleanly support both v1 and v2 while also making it easy to support specifying other encryption settings in the future (say, accepting "$contents_mode:$filenames_mode:v2"), make ext4 and f2fs maintain a pointer to the dummy fscrypt_context rather than using mount flags. To avoid concurrency issues, don't allow test_dummy_encryption to be set or changed during a remount. (The former restriction is new, but xfstests doesn't run into it, so no one should notice.) Tested with 'gce-xfstests -c {ext4,f2fs}/encrypt -g auto'. On ext4, there are two regressions, both of which are test bugs: ext4/023 and ext4/028 fail because they set an xattr and expect it to be stored inline, but the increase in size of the fscrypt_context from 24 to 40 bytes causes this xattr to be spilled into an external block. Link: https://lore.kernel.org/r/20200512233251.118314-4-ebiggers@kernel.org Acked-by: Jaegeuk Kim Reviewed-by: Theodore Ts'o Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 51 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 44 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 0e0c7ad19383..2862ca5fea33 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -15,12 +15,15 @@ #include #include +#include #include #include #define FS_CRYPTO_BLOCK_SIZE 16 +union fscrypt_context; struct fscrypt_info; +struct seq_file; struct fscrypt_str { unsigned char *name; @@ -59,7 +62,8 @@ struct fscrypt_operations { int (*get_context)(struct inode *inode, void *ctx, size_t len); int (*set_context)(struct inode *inode, const void *ctx, size_t len, void *fs_data); - bool (*dummy_context)(struct inode *inode); + const union fscrypt_context *(*get_dummy_context)( + struct super_block *sb); bool (*empty_dir)(struct inode *inode); unsigned int max_namelen; bool (*has_stable_inodes)(struct super_block *sb); @@ -89,10 +93,12 @@ 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) +static inline const union fscrypt_context * +fscrypt_get_dummy_context(struct super_block *sb) { - return inode->i_sb->s_cop->dummy_context && - inode->i_sb->s_cop->dummy_context(inode); + if (!sb->s_cop->get_dummy_context) + return NULL; + return sb->s_cop->get_dummy_context(sb); } /* @@ -145,6 +151,22 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); int fscrypt_inherit_context(struct inode *parent, struct inode *child, void *fs_data, bool preload); +struct fscrypt_dummy_context { + const union fscrypt_context *ctx; +}; + +int fscrypt_set_test_dummy_encryption(struct super_block *sb, + const substring_t *arg, + struct fscrypt_dummy_context *dummy_ctx); +void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, + struct super_block *sb); +static inline void +fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +{ + kfree(dummy_ctx->ctx); + dummy_ctx->ctx = NULL; +} + /* keyring.c */ void fscrypt_sb_free(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); @@ -219,9 +241,10 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) return false; } -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +static inline const union fscrypt_context * +fscrypt_get_dummy_context(struct super_block *sb) { - return false; + return NULL; } static inline void fscrypt_handle_d_move(struct dentry *dentry) @@ -316,6 +339,20 @@ static inline int fscrypt_inherit_context(struct inode *parent, return -EOPNOTSUPP; } +struct fscrypt_dummy_context { +}; + +static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, + char sep, + struct super_block *sb) +{ +} + +static inline void +fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +{ +} + /* keyring.c */ static inline void fscrypt_sb_free(struct super_block *sb) { @@ -677,7 +714,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir, unsigned int max_len, struct fscrypt_str *disk_link) { - if (IS_ENCRYPTED(dir) || fscrypt_dummy_context_enabled(dir)) + if (IS_ENCRYPTED(dir) || fscrypt_get_dummy_context(dir->i_sb) != NULL) return __fscrypt_prepare_symlink(dir, len, max_len, disk_link); disk_link->name = (unsigned char *)target; -- cgit v1.2.3 From 5cab3ff2489ede5abffa6ad730708e087dc45a4d Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 01:43:18 +0800 Subject: soundwire: bus: rename sdw_bus_master_add/delete, add arguments In preparation for future extensions, rename functions to use sdw_bus_master prefix and add a parent and fwnode argument to sdw_bus_master_add to help with device registration in follow-up patches. No functionality change, just renames and additional arguments. The Intel code is currently unused, the two additional arguments are only needed for compilation. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 00f5826092e3..2003e8c55538 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -832,8 +832,9 @@ struct sdw_bus { bool multi_link; }; -int sdw_add_bus_master(struct sdw_bus *bus); -void sdw_delete_bus_master(struct sdw_bus *bus); +int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, + struct fwnode_handle *fwnode); +void sdw_bus_master_delete(struct sdw_bus *bus); /** * sdw_port_config: Master or Slave Port configuration -- cgit v1.2.3 From 90acca1d54ad566b4af5f1030b4a4a2420ce2ef0 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 01:43:19 +0800 Subject: soundwire: bus_type: introduce sdw_slave_type and sdw_master_type this is a preparatory patch before the introduction of the sdw_master_type. The SoundWire slave support is slightly modified with the use of a sdw_slave_type, and the uevent handling move to slave.c (since it's not necessary for the master). No functionality change other than moving code around. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_type.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index aaa7f4267c14..52eb66cd11bc 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -5,6 +5,13 @@ #define __SOUNDWIRE_TYPES_H extern struct bus_type sdw_bus_type; +extern struct device_type sdw_slave_type; +extern struct device_type sdw_master_type; + +static inline int is_sdw_slave(const struct device *dev) +{ + return dev->type == &sdw_slave_type; +} #define drv_to_sdw_driver(_drv) container_of(_drv, struct sdw_driver, driver) @@ -14,7 +21,7 @@ extern struct bus_type sdw_bus_type; int __sdw_register_driver(struct sdw_driver *drv, struct module *owner); void sdw_unregister_driver(struct sdw_driver *drv); -int sdw_slave_modalias(const struct sdw_slave *slave, char *buf, size_t size); +int sdw_slave_uevent(struct device *dev, struct kobj_uevent_env *env); /** * module_sdw_driver() - Helper macro for registering a Soundwire driver -- cgit v1.2.3 From dbb50c7a9949506f750d59d9ba4d58f0ce8ccd42 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Tue, 19 May 2020 01:43:20 +0800 Subject: soundwire: bus: add unique bus id Adding an unique id for each bus. Suggested-by: Vinod Koul Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-4-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 2003e8c55538..a32cb26f1815 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -789,6 +789,7 @@ struct sdw_master_ops { * struct sdw_bus - SoundWire bus * @dev: Master linux device * @link_id: Link id number, can be 0 to N, unique for each Master + * @id: bus system-wide unique id * @slaves: list of Slaves on this bus * @assigned: Bitmap for Slave device numbers. * Bit set implies used number, bit clear implies unused number. @@ -813,6 +814,7 @@ struct sdw_master_ops { struct sdw_bus { struct device *dev; unsigned int link_id; + int id; struct list_head slaves; DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); struct mutex bus_lock; -- cgit v1.2.3 From 7ceaa40b930e462ba0477ca6af34ec04d08181dc Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 01:43:21 +0800 Subject: soundwire: bus_type: add sdw_master_device support In the existing SoundWire code, Master Devices are not explicitly represented - only SoundWire Slave Devices are exposed (the use of capital letters follows the SoundWire specification conventions). With the existing code, the bus is handled without using a proper device, and bus->dev typically points to a platform device. The right thing to do as discussed in multiple reviews is use a device for each bus. The sdw_master_device addition is done with minimal internal plumbing and not exposed externally. The existing API based on sdw_bus_master_add() and sdw_bus_master_delete() will deal with the sdw_master_device life cycle, which minimizes changes to existing drivers. Note that the Intel code will be modified in follow-up patches (no impact on any platform since the connection with ASoC is not supported upstream so far). Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index a32cb26f1815..7658d9698dd5 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -632,6 +632,19 @@ struct sdw_slave { #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) +/** + * struct sdw_master_device - SoundWire 'Master Device' representation + * @dev: Linux device for this Master + * @bus: Bus handle shortcut + */ +struct sdw_master_device { + struct device dev; + struct sdw_bus *bus; +}; + +#define dev_to_sdw_master_device(d) \ + container_of(d, struct sdw_master_device, dev) + struct sdw_driver { const char *name; @@ -787,7 +800,8 @@ struct sdw_master_ops { /** * struct sdw_bus - SoundWire bus - * @dev: Master linux device + * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. + * @md: Master device * @link_id: Link id number, can be 0 to N, unique for each Master * @id: bus system-wide unique id * @slaves: list of Slaves on this bus @@ -813,6 +827,7 @@ struct sdw_master_ops { */ struct sdw_bus { struct device *dev; + struct sdw_master_device *md; unsigned int link_id; int id; struct list_head slaves; -- cgit v1.2.3 From 2318976619daf0e868de5b8aff19c1fd8d585867 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Thu, 14 May 2020 11:36:41 +0100 Subject: ARM: 8976/1: module: allow arch overrides for .init section names ARM stores unwind information for .init.text in sections named .ARM.extab.init.text and .ARM.exidx.init.text. Since those aren't currently recognized as init sections, they're allocated along with the core section, and relocation fails if the core and the init section are allocated from different regions and can't reach other. final section addresses: ... 0x7f800000 .init.text .. 0xcbb54078 .ARM.exidx.init.text .. section 16 reloc 0 sym '': relocation 42 out of range (0xcbb54078 -> 0x7f800000) Allow architectures to override the section name so that ARM can fix this. Acked-by: Jessica Yu Signed-off-by: Vincent Whitchurch Signed-off-by: Russell King --- include/linux/moduleloader.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index ca92aea8a6bd..4fa67a8b2265 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -29,6 +29,11 @@ void *module_alloc(unsigned long size); /* Free memory returned from module_alloc. */ void module_memfree(void *module_region); +/* Determines if the section name is an init section (that is only used during + * module loading). + */ +bool module_init_section(const char *name); + /* Determines if the section name is an exit section (that is only used during * module unloading) */ -- cgit v1.2.3 From 9d78edeaec759f997c303f286ecd39daee166f2a Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Mon, 18 May 2020 20:07:38 +0200 Subject: proc: proc_pid_ns takes super_block as an argument syzbot found that touch /proc/testfile causes NULL pointer dereference at tomoyo_get_local_path() because inode of the dentry is NULL. Before c59f415a7cb6, Tomoyo received pid_ns from proc's s_fs_info directly. Since proc_pid_ns() can only work with inode, using it in the tomoyo_get_local_path() was wrong. To avoid creating more functions for getting proc_ns, change the argument type of the proc_pid_ns() function. Then, Tomoyo can use the existing super_block to get pid_ns. Link: https://lkml.kernel.org/r/0000000000002f0c7505a5b0e04c@google.com Link: https://lkml.kernel.org/r/20200518180738.2939611-1-gladkov.alexey@gmail.com Reported-by: syzbot+c1af344512918c61362c@syzkaller.appspotmail.com Fixes: c59f415a7cb6 ("Use proc_pid_ns() to get pid_namespace from the proc superblock") Signed-off-by: Alexey Gladkov Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2cb424e6f36a..6ec524d8842c 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -202,9 +202,9 @@ int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)); /* get the associated pid namespace for a file in procfs */ -static inline struct pid_namespace *proc_pid_ns(const struct inode *inode) +static inline struct pid_namespace *proc_pid_ns(struct super_block *sb) { - return proc_sb_info(inode->i_sb)->pid_ns; + return proc_sb_info(sb)->pid_ns; } #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 6553896666433e7efec589838b400a2a652b3ffa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 Mar 2020 22:47:17 +0100 Subject: vmlinux.lds.h: Create section for protection against instrumentation Some code pathes, especially the low level entry code, must be protected against instrumentation for various reasons: - Low level entry code can be a fragile beast, especially on x86. - With NO_HZ_FULL RCU state needs to be established before using it. Having a dedicated section for such code allows to validate with tooling that no unsafe functions are invoked. Add the .noinstr.text section and the noinstr attribute to mark functions. noinstr implies notrace. Kprobes will gain a section check later. Provide also a set of markers: instrumentation_begin()/end() These are used to mark code inside a noinstr function which calls into regular instrumentable text section as safe. The instrumentation markers are only active when CONFIG_DEBUG_ENTRY is enabled as the end marker emits a NOP to prevent the compiler from merging the annotation points. This means the objtool verification requires a kernel compiled with this option. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134100.075416272@linutronix.de --- include/linux/compiler.h | 53 ++++++++++++++++++++++++++++++++++++++++++ include/linux/compiler_types.h | 4 ++++ 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 034b0a644efc..e9ead0505671 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -120,12 +120,65 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(.rodata..c_jump_table) +#ifdef CONFIG_DEBUG_ENTRY +/* Begin/end of an instrumentation safe region */ +#define instrumentation_begin() ({ \ + asm volatile("%c0:\n\t" \ + ".pushsection .discard.instr_begin\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) + +/* + * Because instrumentation_{begin,end}() can nest, objtool validation considers + * _begin() a +1 and _end() a -1 and computes a sum over the instructions. + * When the value is greater than 0, we consider instrumentation allowed. + * + * There is a problem with code like: + * + * noinstr void foo() + * { + * instrumentation_begin(); + * ... + * if (cond) { + * instrumentation_begin(); + * ... + * instrumentation_end(); + * } + * bar(); + * instrumentation_end(); + * } + * + * If instrumentation_end() would be an empty label, like all the other + * annotations, the inner _end(), which is at the end of a conditional block, + * would land on the instruction after the block. + * + * If we then consider the sum of the !cond path, we'll see that the call to + * bar() is with a 0-value, even though, we meant it to happen with a positive + * value. + * + * To avoid this, have _end() be a NOP instruction, this ensures it will be + * part of the condition block and does not escape. + */ +#define instrumentation_end() ({ \ + asm volatile("%c0: nop\n\t" \ + ".pushsection .discard.instr_end\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) +#endif /* CONFIG_DEBUG_ENTRY */ + #else #define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif +#ifndef instrumentation_begin +#define instrumentation_begin() do { } while(0) +#define instrumentation_end() do { } while(0) +#endif + #ifndef ASM_UNREACHABLE # define ASM_UNREACHABLE #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e970f97a7fcb..5da257cbebf1 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -118,6 +118,10 @@ struct ftrace_likely_data { #define notrace __attribute__((__no_instrument_function__)) #endif +/* Section for code which can't be instrumented at all */ +#define noinstr \ + noinline notrace __attribute((__section__(".noinstr.text"))) + /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without -- cgit v1.2.3 From 0995a5dfbe49badff78e78761fb66f46579f2f9a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Mar 2020 13:09:50 +0100 Subject: tracing: Provide lockdep less trace_hardirqs_on/off() variants trace_hardirqs_on/off() is only partially safe vs. RCU idle. The tracer core itself is safe, but the resulting tracepoints can be utilized by e.g. BPF which is unsafe. Provide variants which do not contain the lockdep invocation so the lockdep and tracer invocations can be split at the call site and placed properly. This is required because lockdep needs to be aware of the state before switching away from RCU idle and after switching to RCU idle because these transitions can take locks. As these code pathes are going to be non-instrumentable the tracer can be invoked after RCU is turned on and before the switch to RCU idle. So for these new variants there is no need to invoke the rcuidle aware tracer functions. Name them so they match the lockdep counterparts. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134100.270771162@linutronix.de --- include/linux/irqflags.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 61a9ced3aa50..f150e69ab81d 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -29,6 +29,8 @@ #endif #ifdef CONFIG_TRACE_IRQFLAGS + extern void trace_hardirqs_on_prepare(void); + extern void trace_hardirqs_off_prepare(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define lockdep_hardirq_context(p) ((p)->hardirq_context) @@ -96,6 +98,8 @@ do { \ } while (0) #else +# define trace_hardirqs_on_prepare() do { } while (0) +# define trace_hardirqs_off_prepare() do { } while (0) # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) # define lockdep_hardirq_context(p) 0 -- cgit v1.2.3 From c86e9b987cea3dd0209203e714553a47f5d7c6dd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Mar 2020 14:22:03 +0100 Subject: lockdep: Prepare for noinstr sections Force inlining and prevent instrumentation of all sorts by marking the functions which are invoked from low level entry code with 'noinstr'. Split the irqflags tracking into two parts. One which does the heavy lifting while RCU is watching and the final one which can be invoked after RCU is turned off. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134100.484532537@linutronix.de --- include/linux/irqflags.h | 2 ++ include/linux/sched.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index f150e69ab81d..d7f7e436c3af 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -19,11 +19,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(unsigned long ip); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..658de6164853 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -983,6 +983,7 @@ struct task_struct { unsigned int hardirq_disable_event; int hardirqs_enabled; int hardirq_context; + u64 hardirq_chain_key; unsigned long softirq_disable_ip; unsigned long softirq_enable_ip; unsigned int softirq_disable_event; -- cgit v1.2.3 From af1e56b78534c38bb0e0c712ca70e59f816b74e9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 19 Mar 2020 14:53:56 +0100 Subject: context_tracking: Make guest_enter/exit() .noinstr ready Force inlining of the helpers and mark the instrumentable parts accordingly. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134341.672545766@linutronix.de --- include/linux/context_tracking.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8150f5ac176c..8cac62ee6add 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -101,12 +101,14 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN /* must be called with irqs disabled */ -static inline void guest_enter_irqoff(void) +static __always_inline void guest_enter_irqoff(void) { + instrumentation_begin(); if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; + instrumentation_end(); if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_GUEST); @@ -118,39 +120,48 @@ static inline void guest_enter_irqoff(void) * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ - if (!context_tracking_enabled_this_cpu()) + if (!context_tracking_enabled_this_cpu()) { + instrumentation_begin(); rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); + } } -static inline void guest_exit_irqoff(void) +static __always_inline void guest_exit_irqoff(void) { if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_GUEST); + instrumentation_begin(); if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; + instrumentation_end(); } #else -static inline void guest_enter_irqoff(void) +static __always_inline void guest_enter_irqoff(void) { /* * This is running in ioctl context so its safe * to assume that it's the stime pending cputime * to flush. */ + instrumentation_begin(); vtime_account_kernel(current); current->flags |= PF_VCPU; rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); } -static inline void guest_exit_irqoff(void) +static __always_inline void guest_exit_irqoff(void) { + instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_kernel(current); current->flags &= ~PF_VCPU; + instrumentation_end(); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -- cgit v1.2.3 From 69ea03b56ed2c7189ccd0b5910ad39f3cad1df21 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Feb 2020 09:46:47 +0100 Subject: hardirq/nmi: Allow nested nmi_enter() Since there are already a number of sites (ARM64, PowerPC) that effectively nest nmi_enter(), make the primitive support this before adding even more. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Marc Zyngier Acked-by: Will Deacon Cc: Michael Ellerman Link: https://lkml.kernel.org/r/20200505134100.864179229@linutronix.de --- include/linux/hardirq.h | 5 ++++- include/linux/preempt.h | 4 ++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 7c8b82f69288..a043ad826c67 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -65,13 +65,16 @@ extern void irq_exit(void); #define arch_nmi_exit() do { } while (0) #endif +/* + * nmi_enter() can nest up to 15 times; see NMI_BITS. + */ #define nmi_enter() \ do { \ arch_nmi_enter(); \ printk_nmi_enter(); \ lockdep_off(); \ ftrace_nmi_enter(); \ - BUG_ON(in_nmi()); \ + BUG_ON(in_nmi() == NMI_MASK); \ preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ rcu_nmi_enter(); \ lockdep_hardirq_enter(); \ diff --git a/include/linux/preempt.h b/include/linux/preempt.h index bc3f1aecaa19..7d9c1c0e149c 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -26,13 +26,13 @@ * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 * HARDIRQ_MASK: 0x000f0000 - * NMI_MASK: 0x00100000 + * NMI_MASK: 0x00f00000 * PREEMPT_NEED_RESCHED: 0x80000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 #define HARDIRQ_BITS 4 -#define NMI_BITS 1 +#define NMI_BITS 4 #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -- cgit v1.2.3 From e616cb8daadf637175af4fe53138a94c190c4816 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 24 Feb 2020 22:14:51 +0100 Subject: lockdep: Always inline lockdep_{off,on}() These functions are called {early,late} in nmi_{enter,exit} and should not be traced or probed. They are also puny, so 'inline' them. Reported-by: Steven Rostedt Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134101.048523500@linutronix.de --- include/linux/lockdep.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 206774ac6946..8fce5c98a4b0 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -308,8 +308,27 @@ extern void lockdep_set_selftest_task(struct task_struct *task); extern void lockdep_init_task(struct task_struct *task); -extern void lockdep_off(void); -extern void lockdep_on(void); +/* + * Split the recrursion counter in two to readily detect 'off' vs recursion. + */ +#define LOCKDEP_RECURSION_BITS 16 +#define LOCKDEP_OFF (1U << LOCKDEP_RECURSION_BITS) +#define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1) + +/* + * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due + * to header dependencies. + */ + +#define lockdep_off() \ +do { \ + current->lockdep_recursion += LOCKDEP_OFF; \ +} while (0) + +#define lockdep_on() \ +do { \ + current->lockdep_recursion -= LOCKDEP_OFF; \ +} while (0) extern void lockdep_register_key(struct lock_class_key *key); extern void lockdep_unregister_key(struct lock_class_key *key); -- cgit v1.2.3 From 178ba00c354eb15cec6806a812771e60a5ae3ea1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 24 Feb 2020 22:26:21 +0100 Subject: sh/ftrace: Move arch_ftrace_nmi_{enter,exit} into nmi exception SuperH is the last remaining user of arch_ftrace_nmi_{enter,exit}(), remove it from the generic code and into the SuperH code. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Steven Rostedt (VMware) Cc: Rich Felker Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200505134101.248881738@linutronix.de --- include/linux/ftrace_irq.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h index ccda97dc7f8b..0abd9a1d2852 100644 --- a/include/linux/ftrace_irq.h +++ b/include/linux/ftrace_irq.h @@ -2,15 +2,6 @@ #ifndef _LINUX_FTRACE_IRQ_H #define _LINUX_FTRACE_IRQ_H - -#ifdef CONFIG_FTRACE_NMI_ENTER -extern void arch_ftrace_nmi_enter(void); -extern void arch_ftrace_nmi_exit(void); -#else -static inline void arch_ftrace_nmi_enter(void) { } -static inline void arch_ftrace_nmi_exit(void) { } -#endif - #ifdef CONFIG_HWLAT_TRACER extern bool trace_hwlat_callback_enabled; extern void trace_hwlat_callback(bool enter); @@ -22,12 +13,10 @@ static inline void ftrace_nmi_enter(void) if (trace_hwlat_callback_enabled) trace_hwlat_callback(true); #endif - arch_ftrace_nmi_enter(); } static inline void ftrace_nmi_exit(void) { - arch_ftrace_nmi_exit(); #ifdef CONFIG_HWLAT_TRACER if (trace_hwlat_callback_enabled) trace_hwlat_callback(false); -- cgit v1.2.3 From f93524eb9c54f49be150167918f6546b0a2e09b1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 12 Feb 2020 21:01:16 +0100 Subject: sched,rcu,tracing: Avoid tracing before in_nmi() is correct If a tracer is invoked before in_nmi() becomes true, the tracer can no longer detect it is called from NMI context and behave correctly. Therefore change nmi_{enter,exit}() to use __preempt_count_{add,sub}() as the normal preempt_count_{add,sub}() have a (desired) function trace entry. This fixes a potential issue with the current code; when the function-tracer has stack-tracing enabled __trace_stack() will malfunction when it hits the preempt_count_add() function entry from NMI context. Suggested-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134101.434193525@linutronix.de --- include/linux/hardirq.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index a043ad826c67..621556efe45f 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -65,6 +65,15 @@ extern void irq_exit(void); #define arch_nmi_exit() do { } while (0) #endif +/* + * NMI vs Tracing + * -------------- + * + * We must not land in a tracer until (or after) we've changed preempt_count + * such that in_nmi() becomes true. To that effect all NMI C entry points must + * be marked 'notrace' and call nmi_enter() as soon as possible. + */ + /* * nmi_enter() can nest up to 15 times; see NMI_BITS. */ @@ -75,7 +84,7 @@ extern void irq_exit(void); lockdep_off(); \ ftrace_nmi_enter(); \ BUG_ON(in_nmi() == NMI_MASK); \ - preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ + __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ rcu_nmi_enter(); \ lockdep_hardirq_enter(); \ } while (0) @@ -85,7 +94,7 @@ extern void irq_exit(void); lockdep_hardirq_exit(); \ rcu_nmi_exit(); \ BUG_ON(!in_nmi()); \ - preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ + __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ ftrace_nmi_exit(); \ lockdep_on(); \ printk_nmi_exit(); \ -- cgit v1.2.3 From 5567d11c21a1d508a91a8cb64a819783a0835d9f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Feb 2020 10:22:06 +0100 Subject: x86/mce: Send #MC singal from task work Convert #MC over to using task_work_add(); it will run the same code slightly later, on the return to user path of the same exception. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134100.957390899@linutronix.de --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9437b53cc603..57d0ed061ae4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1297,6 +1297,12 @@ struct task_struct { unsigned long prev_lowest_stack; #endif +#ifdef CONFIG_X86_MCE + u64 mce_addr; + u64 mce_status; + struct callback_head mce_kill_me; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. -- cgit v1.2.3 From 8ae0ae6737ad449c8ae21e2bb01d9736f360a933 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 3 May 2020 15:08:52 +0200 Subject: rcu: Provide rcu_irq_exit_preempt() Interrupts and exceptions invoke rcu_irq_enter() on entry and need to invoke rcu_irq_exit() before they either return to the interrupted code or invoke the scheduler due to preemption. The general assumption is that RCU idle code has to have preemption disabled so that a return from interrupt cannot schedule. So the return from interrupt code invokes rcu_irq_exit() and preempt_schedule_irq(). If there is any imbalance in the rcu_irq/nmi* invocations or RCU idle code had preemption enabled then this goes unnoticed until the CPU goes idle or some other RCU check is executed. Provide rcu_irq_exit_preempt() which can be invoked from the interrupt/exception return code in case that preemption is enabled. It invokes rcu_irq_exit() and contains a few sanity checks in case that CONFIG_PROVE_RCU is enabled to catch such issues directly. Signed-off-by: Thomas Gleixner Reviewed-by: Paul E. McKenney Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134904.364456424@linutronix.de --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 3465ba704a11..980eb78751d9 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -71,6 +71,7 @@ static inline void rcu_irq_enter(void) { } static inline void rcu_irq_exit_irqson(void) { } static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } +static inline void rcu_irq_exit_preempt(void) { } static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index fbc26274af4d..02016e0aa8eb 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -47,6 +47,7 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +void rcu_irq_exit_preempt(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); -- cgit v1.2.3 From b1fcf9b83c4149c63d1e0c699e85f93cbe28e211 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 May 2020 09:44:43 +0200 Subject: rcu: Provide __rcu_is_watching() Same as rcu_is_watching() but without the preempt_disable/enable() pair inside the function. It is merked noinstr so it ends up in the non-instrumentable text section. This is useful for non-preemptible code especially in the low level entry section. Using rcu_is_watching() there results in a call to the preempt_schedule_notrace() thunk which triggers noinstr section warnings in objtool. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200512213810.518709291@linutronix.de --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 980eb78751d9..c869fb20cc51 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -86,6 +86,7 @@ static inline void rcu_scheduler_starting(void) { } static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } +static inline bool __rcu_is_watching(void) { return true; } static inline void rcu_momentary_dyntick_idle(void) { } static inline void kfree_rcu_scheduler_running(void) { } static inline bool rcu_gp_might_be_stalled(void) { return false; } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 02016e0aa8eb..9366fa4d0717 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -58,6 +58,7 @@ extern int rcu_scheduler_active __read_mostly; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); +bool __rcu_is_watching(void); #ifndef CONFIG_PREEMPTION void rcu_all_qs(void); #endif -- cgit v1.2.3 From 66e9b0717102507e64f638790eaece88765cc9e5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2020 14:04:34 +0100 Subject: kprobes: Prevent probes in .noinstr.text section Instrumentation is forbidden in the .noinstr.text section. Make kprobes respect this. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20200505134100.179862032@linutronix.de --- include/linux/module.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1192097c9a69..d849d06e4d44 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -458,6 +458,8 @@ struct module { void __percpu *percpu; unsigned int percpu_size; #endif + void *noinstr_text_start; + unsigned int noinstr_text_size; #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; -- cgit v1.2.3 From 80961525880e58e0efcf536fd357d642c68f4176 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 18 May 2020 12:02:22 -0600 Subject: coresight: Add generic sysfs link creation functions To allow the connections between coresight components to be represented in sysfs, generic methods for creating sysfs links between two coresight devices are added. Signed-off-by: Mike Leach Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-4-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 193cc9dbf448..a2ec25e02ca9 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -148,6 +148,20 @@ struct coresight_connection { struct coresight_device *child_dev; }; +/** + * struct coresight_sysfs_link - representation of a connection in sysfs. + * @orig: Originating (master) coresight device for the link. + * @orig_name: Name to use for the link orig->target. + * @target: Target (slave) coresight device for the link. + * @target_name: Name to use for the link target->orig. + */ +struct coresight_sysfs_link { + struct coresight_device *orig; + const char *orig_name; + struct coresight_device *target; + const char *target_name; +}; + /** * struct coresight_device - representation of a device as used by the framework * @pdata: Platform data with device connections associated to this device. @@ -165,6 +179,9 @@ struct coresight_connection { * @ea: Device attribute for sink representation under PMU directory. * @ect_dev: Associated cross trigger device. Not part of the trace data * path or connections. + * @nr_links: number of sysfs links created to other components from this + * device. These will appear in the "connections" group. + * @has_conns_grp: Have added a "connections" group for sysfs links. */ struct coresight_device { struct coresight_platform_data *pdata; @@ -180,6 +197,9 @@ struct coresight_device { struct dev_ext_attribute *ea; /* cross trigger handling */ struct coresight_device *ect_dev; + /* sysfs links between components */ + int nr_links; + bool has_conns_grp; }; /* -- cgit v1.2.3 From 8a7365c2d41898f2376efa929aadf2723dc281b0 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 18 May 2020 12:02:23 -0600 Subject: coresight: Expose device connections via sysfs Coresight device connections are a bit complicated and is not exposed currently to the user. One has to look at the platform descriptions (DT bindings or ACPI bindings) to make an understanding. Given the new naming scheme, it will be helpful to have this information to choose the appropriate devices for tracing. This patch exposes the device connections via links in the sysfs directories. e.g, for a connection devA[OutputPort_X] -> devB[InputPort_Y] is represented as two symlinks: /sys/bus/coresight/.../devA/out:X -> /sys/bus/coresight/.../devB /sys/bus/coresight/.../devB/in:Y -> /sys/bus/coresight/.../devA Signed-off-by: Suzuki K Poulose [Revised to use the generic sysfs links functions & link structures. Provides a connections sysfs group in each device to hold the links.] Co-developed-by: Mike Leach Signed-off-by: Mike Leach Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-5-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index a2ec25e02ca9..ccd17304d7bd 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -140,12 +140,14 @@ struct coresight_desc { * @chid_fwnode: remote component's fwnode handle. * @child_dev: a @coresight_device representation of the component connected to @outport. + * @link: Representation of the connection as a sysfs link. */ struct coresight_connection { int outport; int child_port; struct fwnode_handle *child_fwnode; struct coresight_device *child_dev; + struct coresight_sysfs_link *link; }; /** -- cgit v1.2.3 From d375b356e687f2eefb51ddc3f1f2414cfa498f86 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 18 May 2020 12:02:31 -0600 Subject: coresight: Fix support for sparsely populated ports On some systems the firmware may not describe all the ports connected to a component (e.g, for security reasons). This could be especially problematic for "funnels" where we could end up in modifying memory beyond the allocated space for refcounts. e.g, for a funnel with input ports listed 0, 3, 5, nr_inport = 3. However the we could access refcnts[5] while checking for references, like : [ 526.110401] ================================================================== [ 526.117988] BUG: KASAN: slab-out-of-bounds in funnel_enable+0x54/0x1b0 [ 526.124706] Read of size 4 at addr ffffff8135f9549c by task bash/1114 [ 526.131324] [ 526.132886] CPU: 3 PID: 1114 Comm: bash Tainted: G S 5.4.25 #232 [ 526.140397] Hardware name: Qualcomm Technologies, Inc. SC7180 IDP (DT) [ 526.147113] Call trace: [ 526.149653] dump_backtrace+0x0/0x188 [ 526.153431] show_stack+0x20/0x2c [ 526.156852] dump_stack+0xdc/0x144 [ 526.160370] print_address_description+0x3c/0x494 [ 526.165211] __kasan_report+0x144/0x168 [ 526.169170] kasan_report+0x10/0x18 [ 526.172769] check_memory_region+0x1a4/0x1b4 [ 526.177164] __kasan_check_read+0x18/0x24 [ 526.181292] funnel_enable+0x54/0x1b0 [ 526.185072] coresight_enable_path+0x104/0x198 [ 526.189649] coresight_enable+0x118/0x26c ... [ 526.237782] Allocated by task 280: [ 526.241298] __kasan_kmalloc+0xf0/0x1ac [ 526.245249] kasan_kmalloc+0xc/0x14 [ 526.248849] __kmalloc+0x28c/0x3b4 [ 526.252361] coresight_register+0x88/0x250 [ 526.256587] funnel_probe+0x15c/0x228 [ 526.260365] dynamic_funnel_probe+0x20/0x2c [ 526.264679] amba_probe+0xbc/0x158 [ 526.268193] really_probe+0x144/0x408 [ 526.271970] driver_probe_device+0x70/0x140 ... [ 526.316810] [ 526.318364] Freed by task 0: [ 526.321344] (stack is not available) [ 526.325024] [ 526.326580] The buggy address belongs to the object at ffffff8135f95480 [ 526.326580] which belongs to the cache kmalloc-128 of size 128 [ 526.339439] The buggy address is located 28 bytes inside of [ 526.339439] 128-byte region [ffffff8135f95480, ffffff8135f95500) [ 526.351399] The buggy address belongs to the page: [ 526.356342] page:ffffffff04b7e500 refcount:1 mapcount:0 mapping:ffffff814b00c380 index:0x0 compound_mapcount: 0 [ 526.366711] flags: 0x4000000000010200(slab|head) [ 526.371475] raw: 4000000000010200 ffffffff05034008 ffffffff0501eb08 ffffff814b00c380 [ 526.379435] raw: 0000000000000000 0000000000190019 00000001ffffffff 0000000000000000 [ 526.387393] page dumped because: kasan: bad access detected [ 526.393128] [ 526.394681] Memory state around the buggy address: [ 526.399619] ffffff8135f95380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.407046] ffffff8135f95400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.414473] >ffffff8135f95480: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.421900] ^ [ 526.426029] ffffff8135f95500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.433456] ffffff8135f95580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.440883] ================================================================== To keep the code simple, we now track the maximum number of possible input/output connections to/from this component @ nr_inport and nr_outport in platform_data, respectively. Thus the output connections could be sparse and code is adjusted to skip the unspecified connections. Cc: Mathieu Poirier Cc: Mike Leach Reported-by: Sai Prakash Ranjan Tested-by: Sai Prakash Ranjan Tested-by: Stephen Boyd Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-13-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index ccd17304d7bd..e3e9f0e3a878 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -100,10 +100,12 @@ union coresight_dev_subtype { }; /** - * struct coresight_platform_data - data harvested from the DT specification - * @nr_inport: number of input ports for this component. - * @nr_outport: number of output ports for this component. - * @conns: Array of nr_outport connections from this component + * struct coresight_platform_data - data harvested from the firmware + * specification. + * + * @nr_inport: Number of elements for the input connections. + * @nr_outport: Number of elements for the output connections. + * @conns: Sparse array of nr_outport connections from this component. */ struct coresight_platform_data { int nr_inport; -- cgit v1.2.3 From e9b880581d555c8f7b58c7d19cc3f8f9016a1b5f Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 18 May 2020 12:02:41 -0600 Subject: coresight: cti: Add CPU Hotplug handling to CTI driver Adds registration of CPU start and stop functions to CPU hotplug mechanisms - for any CPU bound CTI. Sets CTI powered flag according to state. Will enable CTI on CPU start if there are existing enable requests. Signed-off-by: Mike Leach Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-23-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- 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 77d70b633531..6dc7332307ca 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -142,6 +142,7 @@ enum cpuhp_state { CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, + CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, CPUHP_AP_X86_TBOOT_DYING, -- cgit v1.2.3 From c1527c0e12d461ff4c603996f77983f37b85c286 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 18 May 2020 21:07:35 -0700 Subject: bio.h: Declare the arguments of the bio iteration functions const This change makes it possible to pass 'const struct bio *' arguments to these functions. Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Cc: Ming Lei Cc: Damien Le Moal Cc: Chaitanya Kulkarni Cc: Alexander Potapenko Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a0ee494a6329..950c9dc44c4f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -70,7 +70,7 @@ static inline bool bio_has_data(struct bio *bio) return false; } -static inline bool bio_no_advance_iter(struct bio *bio) +static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || @@ -138,8 +138,8 @@ static inline bool bio_next_segment(const struct bio *bio, #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) -static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, - unsigned bytes) +static inline void bio_advance_iter(const struct bio *bio, + struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; -- cgit v1.2.3 From 854b5f01dc6a7b59f0dddd646a80b1fcd767a8db Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 18 May 2020 21:07:36 -0700 Subject: block: Document the bio_vec properties Since it is nontrivial that nth_page() does not have to be used for a bio_vec, document this. Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig CC: Christoph Hellwig Cc: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bvec.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index a81c13ac1972..ac0c7299d5b8 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -12,8 +12,17 @@ #include #include -/* - * was unsigned short, but we might as well be ready for > 64kB I/O pages +/** + * struct bio_vec - a contiguous range of physical memory addresses + * @bv_page: First page associated with the address range. + * @bv_len: Number of bytes in the address range. + * @bv_offset: Start of the address range relative to the start of @bv_page. + * + * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: + * + * nth_page(@bv_page, n) == @bv_page + n + * + * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; -- cgit v1.2.3 From 062022315e8ad9e0628515dfc756ab54b5fdb26b Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 1 May 2020 17:45:41 +0100 Subject: mm/memory-failure: Add memory_failure_queue_kick() The GHES code calls memory_failure_queue() from IRQ context to schedule work on the current CPU so that memory_failure() can sleep. For synchronous memory errors the arch code needs to know any signals that memory_failure() will trigger are pending before it returns to user-space, possibly when exiting from the IRQ. Add a helper to kick the memory failure queue, to ensure the scheduled work has happened. This has to be called from process context, so may have been migrated from the original cpu. Pass the cpu the work was queued on. Change memory_failure_work_func() to permit being called on the 'wrong' cpu. Signed-off-by: James Morse Tested-by: Tyler Baicar Acked-by: Naoya Horiguchi Signed-off-by: Rafael J. Wysocki --- 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 5a323422d783..c606dbbfa5e1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3012,6 +3012,7 @@ enum mf_flags { }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); +extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int get_hwpoison_page(struct page *page); #define put_hwpoison_page(page) put_page(page) -- cgit v1.2.3 From 1b66d253610c7f8f257103808a9460223a087469 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 May 2020 00:45:45 +0200 Subject: bpf: Add get{peer, sock}name attach types for sock_addr As stated in 983695fa6765 ("bpf: fix unconnected udp hooks"), the objective for the existing cgroup connect/sendmsg/recvmsg/bind BPF hooks is to be transparent to applications. In Cilium we make use of these hooks [0] in order to enable E-W load balancing for existing Kubernetes service types for all Cilium managed nodes in the cluster. Those backends can be local or remote. The main advantage of this approach is that it operates as close as possible to the socket, and therefore allows to avoid packet-based NAT given in connect/sendmsg/recvmsg hooks we only need to xlate sock addresses. This also allows to expose NodePort services on loopback addresses in the host namespace, for example. As another advantage, this also efficiently blocks bind requests for applications in the host namespace for exposed ports. However, one missing item is that we also need to perform reverse xlation for inet{,6}_getname() hooks such that we can return the service IP/port tuple back to the application instead of the remote peer address. The vast majority of applications does not bother about getpeername(), but in a few occasions we've seen breakage when validating the peer's address since it returns unexpectedly the backend tuple instead of the service one. Therefore, this trivial patch allows to customise and adds a getpeername() as well as getsockname() BPF cgroup hook for both IPv4 and IPv6 in order to address this situation. Simple example: # ./cilium/cilium service list ID Frontend Service Type Backend 1 1.2.3.4:80 ClusterIP 1 => 10.0.0.10:80 Before; curl's verbose output example, no getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (10.0.0.10) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] After; with getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (1.2.3.4) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] Originally, I had both under a BPF_CGROUP_INET{4,6}_GETNAME type and exposed peer to the context similar as in inet{,6}_getname() fashion, but API-wise this is suboptimal as it always enforces programs having to test for ctx->peer which can easily be missed, hence BPF_CGROUP_INET{4,6}_GET{PEER,SOCK}NAME split. Similarly, the checked return code is on tnum_range(1, 1), but if a use case comes up in future, it can easily be changed to return an error code instead. Helper and ctx member access is the same as with connect/sendmsg/etc hooks. [0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/61a479d759b2482ae3efb45546490bacd796a220.1589841594.git.daniel@iogearbox.net --- include/linux/bpf-cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 272626cc3fc9..c66c545e161a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -396,6 +396,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, } #define cgroup_bpf_enabled (0) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) -- cgit v1.2.3 From c50c75e9b87946499a62bffc021e95c87a1d57cd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 11 May 2020 15:12:27 -0500 Subject: perf/core: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200511201227.GA14041@embeddedor --- include/linux/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 87e21681759c..d7b610c4eebd 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -61,7 +61,7 @@ struct perf_guest_info_callbacks { struct perf_callchain_entry { __u64 nr; - __u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */ + __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { @@ -113,7 +113,7 @@ struct perf_raw_record { struct perf_branch_stack { __u64 nr; __u64 hw_idx; - struct perf_branch_entry entries[0]; + struct perf_branch_entry entries[]; }; struct task_struct; -- cgit v1.2.3 From 607259a695312cdfac2b52fb9d5b5890c834d573 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 May 2020 15:03:13 +0200 Subject: net: add a new ndo_tunnel_ioctl method This method is used to properly allow kernel callers of the IPv4 route management ioctls. The exsting ip_tunnel_ioctl helper is renamed to ip_tunnel_ctl to better reflect that it doesn't directly implement ioctls touching user memory, and is used for the guts of ndo_tunnel_ctl implementations. A new ip_tunnel_ioctl helper is added that can be wired up directly to the ndo_do_ioctl method and takes care of the copy to and from userspace. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a8f8daef09d..a18f8fdf4260 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -53,6 +53,7 @@ struct netpoll_info; struct device; struct phy_device; struct dsa_port; +struct ip_tunnel_parm; struct macsec_context; struct macsec_ops; @@ -1274,6 +1275,9 @@ struct netdev_net_notifier { * Get devlink port instance associated with a given netdev. * Called with a reference on the netdevice and devlink locks only, * rtnl_lock is not held. + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, + * int cmd); + * Add, change, delete or get information on an IPv4 tunnel. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1479,6 +1483,8 @@ struct net_device_ops { int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); + int (*ndo_tunnel_ctl)(struct net_device *dev, + struct ip_tunnel_parm *p, int cmd); }; /** -- cgit v1.2.3 From febd668d375caf13a7fcd93b3498366854de854a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2020 06:30:09 -0400 Subject: rcuwait: avoid lockdep splats from rcuwait_active() rcuwait_active only returns whether w->task is not NULL. This is exactly one of the usecases that are mentioned in the documentation for rcu_access_pointer() where it is correct to bypass lockdep checks. This avoids a splat from kvm_vcpu_on_spin(). Reported-by: Wanpeng Li Tested-by: Wanpeng Li Acked-by: Davidlohr Bueso Cc: Peter Zijlstra Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index c1414ce44abc..61c56cca95c4 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -31,7 +31,7 @@ static inline void rcuwait_init(struct rcuwait *w) */ static inline int rcuwait_active(struct rcuwait *w) { - return !!rcu_dereference(w->task); + return !!rcu_access_pointer(w->task); } extern int rcuwait_wake_up(struct rcuwait *w); -- cgit v1.2.3 From a1ceea67f2e5b73cebd456e7fb463b3052bc6344 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 27 Apr 2020 16:25:27 +0200 Subject: PCI/IOV: Introduce pci_iov_sysfs_link() function Currently pci_iov_add_virtfn() scans the SR-IOV BARs, adds the VF to the bus and also creates the sysfs links between the newly added VF and its parent PF. With pdev->no_vf_scan fencing off the entire pci_iov_add_virtfn() call s390 as the sole pdev->no_vf_scan user thus ends up missing these sysfs links which are required for example by QEMU/libvirt. Instead of duplicating the code refactor pci_iov_add_virtfn() to make sysfs link creation callable separately. Signed-off-by: Niklas Schnelle Acked-by: Bjorn Helgaas Reviewed-by: Pierre Morel Link: https://lore.kernel.org/r/20200506154139.90609-1-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- include/linux/pci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..93a063a7d7f9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2048,6 +2048,8 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); + +int pci_iov_sysfs_link(struct pci_dev *dev, struct pci_dev *virtfn, int id); int pci_iov_add_virtfn(struct pci_dev *dev, int id); void pci_iov_remove_virtfn(struct pci_dev *dev, int id); int pci_num_vf(struct pci_dev *dev); @@ -2073,6 +2075,12 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) } static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } + +static inline int pci_iov_sysfs_link(struct pci_dev *dev, + struct pci_dev *virtfn, int id) +{ + return -ENODEV; +} static inline int pci_iov_add_virtfn(struct pci_dev *dev, int id) { return -ENOSYS; -- cgit v1.2.3 From 7769e18c201aa88eade5556faf9da7f2bc15bb8a Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:14 +0200 Subject: scsi: storvsc: Re-init stor_chns when a channel interrupt is re-assigned For each storvsc_device, storvsc keeps track of the channel target CPUs associated to the device (alloced_cpus) and it uses this information to fill a "cache" (stor_chns) mapping CPU->channel according to a certain heuristic. Update the alloced_cpus mask and the stor_chns array when a channel of the storvsc device is re-assigned to a different CPU. Signed-off-by: Andrea Parri (Microsoft) Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Link: https://lore.kernel.org/r/20200406001514.19876-12-parri.andrea@gmail.com Reviewed-by; Long Li Reviewed-by: Michael Kelley [ wei: fix a small issue reported by kbuild test robot ] Signed-off-by: Wei Liu --- include/linux/hyperv.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b85d7580f2c1..cd64ab7bb3b7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -773,6 +773,9 @@ struct vmbus_channel { void (*onchannel_callback)(void *context); void *channel_callback_context; + void (*change_target_cpu_callback)(struct vmbus_channel *channel, + u32 old, u32 new); + /* * Synchronize channel scheduling and channel removal; see the inline * comments in vmbus_chan_sched() and vmbus_reset_channel_cb(). -- cgit v1.2.3 From b7d18c57c94a38a81c1dbcfee0d63153ffaf1856 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 23 Apr 2020 16:45:05 +0300 Subject: hyper-v: Switch to use UUID types directly uuid_le is an alias for guid_t and is going to be removed in the future. Replace it with original type. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200423134505.78221-4-andriy.shevchenko@linux.intel.com Signed-off-by: Wei Liu --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4c2ddd0941a7..f36b1cf5ffe3 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -434,7 +434,7 @@ struct virtio_device_id { * For Hyper-V devices we use the device guid as the id. */ struct hv_vmbus_device_id { - uuid_le guid; + guid_t guid; kernel_ulong_t driver_data; /* Data private to the driver */ }; -- cgit v1.2.3 From db5871e85533f06ffe1795c1cb9b9153860d1e4f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:53:23 -0500 Subject: vmbus: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507185323.GA14416@embeddedor Signed-off-by: Wei Liu --- include/linux/hyperv.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index cd64ab7bb3b7..d783847d8cb4 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -117,7 +117,7 @@ struct hv_ring_buffer { * Ring data starts here + RingDataStartOffset * !!! DO NOT place any fields below this !!! */ - u8 buffer[0]; + u8 buffer[]; } __packed; struct hv_ring_buffer_info { @@ -313,7 +313,7 @@ struct vmadd_remove_transfer_page_set { struct gpa_range { u32 byte_count; u32 byte_offset; - u64 pfn_array[0]; + u64 pfn_array[]; }; /* @@ -563,7 +563,7 @@ struct vmbus_channel_gpadl_header { u32 gpadl; u16 range_buflen; u16 rangecount; - struct gpa_range range[0]; + struct gpa_range range[]; } __packed; /* This is the followup packet that contains more PFNs. */ @@ -571,7 +571,7 @@ struct vmbus_channel_gpadl_body { struct vmbus_channel_message_header header; u32 msgnumber; u32 gpadl; - u64 pfn[0]; + u64 pfn[]; } __packed; struct vmbus_channel_gpadl_created { @@ -679,7 +679,7 @@ struct vmbus_channel_msginfo { * The channel message that goes out on the "wire". * It will contain at minimum the VMBUS_CHANNEL_MESSAGE_HEADER header */ - unsigned char msg[0]; + unsigned char msg[]; }; struct vmbus_close_msg { -- cgit v1.2.3 From d85234994b2fb2d88fadd3d9e60385b02b244dac Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Fri, 15 May 2020 10:57:07 -0700 Subject: mfd: Add Gateworks System Controller core driver The Gateworks System Controller (GSC) is an I2C slave controller implemented with an MSP430 micro-controller whose firmware embeds the following features: - I/O expander (16 GPIO's) using PCA955x protocol - Real Time Clock using DS1672 protocol - User EEPROM using AT24 protocol - HWMON using custom protocol - Interrupt controller with tamper detect, user pushbotton - Watchdog controller capable of full board power-cycle - Power Control capable of full board power-cycle see http://trac.gateworks.com/wiki/gsc for more details Signed-off-by: Tim Harvey Signed-off-by: Lee Jones --- include/linux/mfd/gsc.h | 76 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 include/linux/mfd/gsc.h (limited to 'include/linux') diff --git a/include/linux/mfd/gsc.h b/include/linux/mfd/gsc.h new file mode 100644 index 000000000000..6bd639c285b4 --- /dev/null +++ b/include/linux/mfd/gsc.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2020 Gateworks Corporation + */ +#ifndef __LINUX_MFD_GSC_H_ +#define __LINUX_MFD_GSC_H_ + +#include + +/* Device Addresses */ +#define GSC_MISC 0x20 +#define GSC_UPDATE 0x21 +#define GSC_GPIO 0x23 +#define GSC_HWMON 0x29 +#define GSC_EEPROM0 0x50 +#define GSC_EEPROM1 0x51 +#define GSC_EEPROM2 0x52 +#define GSC_EEPROM3 0x53 +#define GSC_RTC 0x68 + +/* Register offsets */ +enum { + GSC_CTRL_0 = 0x00, + GSC_CTRL_1 = 0x01, + GSC_TIME = 0x02, + GSC_TIME_ADD = 0x06, + GSC_IRQ_STATUS = 0x0A, + GSC_IRQ_ENABLE = 0x0B, + GSC_FW_CRC = 0x0C, + GSC_FW_VER = 0x0E, + GSC_WP = 0x0F, +}; + +/* Bit definitions */ +#define GSC_CTRL_0_PB_HARD_RESET 0 +#define GSC_CTRL_0_PB_CLEAR_SECURE_KEY 1 +#define GSC_CTRL_0_PB_SOFT_POWER_DOWN 2 +#define GSC_CTRL_0_PB_BOOT_ALTERNATE 3 +#define GSC_CTRL_0_PERFORM_CRC 4 +#define GSC_CTRL_0_TAMPER_DETECT 5 +#define GSC_CTRL_0_SWITCH_HOLD 6 + +#define GSC_CTRL_1_SLEEP_ENABLE 0 +#define GSC_CTRL_1_SLEEP_ACTIVATE 1 +#define GSC_CTRL_1_SLEEP_ADD 2 +#define GSC_CTRL_1_SLEEP_NOWAKEPB 3 +#define GSC_CTRL_1_WDT_TIME 4 +#define GSC_CTRL_1_WDT_ENABLE 5 +#define GSC_CTRL_1_SWITCH_BOOT_ENABLE 6 +#define GSC_CTRL_1_SWITCH_BOOT_CLEAR 7 + +#define GSC_IRQ_PB 0 +#define GSC_IRQ_KEY_ERASED 1 +#define GSC_IRQ_EEPROM_WP 2 +#define GSC_IRQ_RESV 3 +#define GSC_IRQ_GPIO 4 +#define GSC_IRQ_TAMPER 5 +#define GSC_IRQ_WDT_TIMEOUT 6 +#define GSC_IRQ_SWITCH_HOLD 7 + +int gsc_read(void *context, unsigned int reg, unsigned int *val); +int gsc_write(void *context, unsigned int reg, unsigned int val); + +struct gsc_dev { + struct device *dev; + + struct i2c_client *i2c; /* 0x20: interrupt controller, WDT */ + struct i2c_client *i2c_hwmon; /* 0x29: hwmon, fan controller */ + + struct regmap *regmap; + + unsigned int fwver; + unsigned short fwcrc; +}; + +#endif /* __LINUX_MFD_GSC_H_ */ -- cgit v1.2.3 From 3bce5377ef66a8700dcf7a9cb89b7aeb99326cb7 Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Fri, 15 May 2020 10:57:08 -0700 Subject: hwmon: Add Gateworks System Controller support The Gateworks System Controller has a hwmon sub-component that exposes up to 16 ADC's, some of which are temperature sensors, others which are voltage inputs. The ADC configuration (register mapping and name) is configured via device-tree and varies board to board. Signed-off-by: Tim Harvey Reviewed-by: Guenter Roeck Signed-off-by: Lee Jones --- include/linux/platform_data/gsc_hwmon.h | 44 +++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/platform_data/gsc_hwmon.h (limited to 'include/linux') diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h new file mode 100644 index 000000000000..ec1611aff863 --- /dev/null +++ b/include/linux/platform_data/gsc_hwmon.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _GSC_HWMON_H +#define _GSC_HWMON_H + +enum gsc_hwmon_mode { + mode_temperature, + mode_voltage, + mode_voltage_raw, + mode_max, +}; + +/** + * struct gsc_hwmon_channel - configuration parameters + * @reg: I2C register offset + * @mode: channel mode + * @name: channel name + * @mvoffset: voltage offset + * @vdiv: voltage divider array (2 resistor values in milli-ohms) + */ +struct gsc_hwmon_channel { + unsigned int reg; + unsigned int mode; + const char *name; + unsigned int mvoffset; + unsigned int vdiv[2]; +}; + +/** + * struct gsc_hwmon_platform_data - platform data for gsc_hwmon driver + * @channels: pointer to array of gsc_hwmon_channel structures + * describing channels + * @nchannels: number of elements in @channels array + * @vreference: voltage reference (mV) + * @resolution: ADC bit resolution + * @fan_base: register base for FAN controller + */ +struct gsc_hwmon_platform_data { + const struct gsc_hwmon_channel *channels; + int nchannels; + unsigned int resolution; + unsigned int vreference; + unsigned int fan_base; +}; +#endif -- cgit v1.2.3 From 6bf393c577c4a6e324ab103425fbf71126e5385b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 04:35:49 +0800 Subject: soundwire: disco: s/ch/channels/ Use more meaningful member names in preparation for sysfs support. No functionality change. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200518203551.2053-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 7658d9698dd5..9c27a32df9bb 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -291,8 +291,8 @@ struct sdw_dpn_audio_mode { * implementation-defined interrupts * @max_ch: Maximum channels supported * @min_ch: Minimum channels supported - * @num_ch: Number of discrete channels supported - * @ch: Discrete channels supported + * @num_channels: Number of discrete channels supported + * @channels: Discrete channels supported * @num_ch_combinations: Number of channel combinations supported * @ch_combinations: Channel combinations supported * @modes: SDW mode supported @@ -316,8 +316,8 @@ struct sdw_dpn_prop { u32 imp_def_interrupts; u32 max_ch; u32 min_ch; - u32 num_ch; - u32 *ch; + u32 num_channels; + u32 *channels; u32 num_ch_combinations; u32 *ch_combinations; u32 modes; -- cgit v1.2.3 From f6dd975583bd8ce088400648fd9819e4691c8958 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:12 +0200 Subject: pipe: merge anon_pipe_buf*_ops All the op vectors are exactly the same, they are just used to encode packet or nomerge behavior. There already is a flag for the packet behavior, so just add a new one to allow for merging. Inverting it vs the previous nomerge special casing actually allows for much nicer code. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- 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 ae58fad7f1e0..3f7b07b38824 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -8,6 +8,7 @@ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ +#define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */ /** * struct pipe_buffer - a linux kernel pipe buffer @@ -233,7 +234,6 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); -void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -- cgit v1.2.3 From 76887c256744740d6121af9bc4aa787712a1f694 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:14 +0200 Subject: fs: make the pipe_buf_operations ->steal operation optional Just return 1 for failure if it is not present. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- 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 3f7b07b38824..e022b2459301 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -206,6 +206,8 @@ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, static inline int pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { + if (!buf->ops->steal) + return 1; return buf->ops->steal(pipe, buf); } @@ -232,7 +234,6 @@ void free_pipe_info(struct pipe_inode_info *); bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); -int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -- cgit v1.2.3 From b8d9e7f2411b0744df2ec33e80d7698180fef21a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:15 +0200 Subject: fs: make the pipe_buf_operations ->confirm operation optional Just return 0 for success if it is not present. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index e022b2459301..7c057daa0931 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -82,7 +82,7 @@ struct pipe_buf_operations { * and that the contents are good. If the pages in the pipe belong * to a file system, we may need to wait for IO completion in this * hook. Returns 0 for good, or a negative error value in case of - * error. + * error. If not present all pages are considered good. */ int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *); @@ -195,6 +195,8 @@ static inline void pipe_buf_release(struct pipe_inode_info *pipe, static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { + if (!buf->ops->confirm) + return 0; return buf->ops->confirm(pipe, buf); } @@ -232,7 +234,6 @@ void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); -int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); -- cgit v1.2.3 From c928f642c29a5ffb02e16f2430b42b876dde69de Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:16 +0200 Subject: fs: rename pipe_buf ->steal to ->try_steal And replace the arcane return value convention with a simple bool where true means success and false means failure. [AV: braino fix folded in] Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 7c057daa0931..0c31b9461262 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -70,11 +70,11 @@ struct pipe_inode_info { * Note on the nesting of these functions: * * ->confirm() - * ->steal() + * ->try_steal() * - * That is, ->steal() must be called on a confirmed buffer. - * See below for the meaning of each operation. Also see kerneldoc - * in fs/pipe.c for the pipe and generic variants of these hooks. + * That is, ->try_steal() must be called on a confirmed buffer. See below for + * the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the + * pipe and generic variants of these hooks. */ struct pipe_buf_operations { /* @@ -94,13 +94,13 @@ struct pipe_buf_operations { /* * Attempt to take ownership of the pipe buffer and its contents. - * ->steal() returns 0 for success, in which case the contents - * of the pipe (the buf->page) is locked and now completely owned - * by the caller. The page may then be transferred to a different - * mapping, the most often used case is insertion into different - * file address space cache. + * ->try_steal() returns %true for success, in which case the contents + * of the pipe (the buf->page) is locked and now completely owned by the + * caller. The page may then be transferred to a different mapping, the + * most often used case is insertion into different file address space + * cache. */ - int (*steal)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *); /* * Get a reference to the pipe buffer. @@ -201,16 +201,16 @@ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, } /** - * pipe_buf_steal - attempt to take ownership of a pipe_buffer + * pipe_buf_try_steal - attempt to take ownership of a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal */ -static inline int pipe_buf_steal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { - if (!buf->ops->steal) - return 1; - return buf->ops->steal(pipe, buf); + if (!buf->ops->try_steal) + return false; + return buf->ops->try_steal(pipe, buf); } /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual @@ -234,7 +234,7 @@ void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); -int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -- cgit v1.2.3 From 9b47c5275614a16fd64359fab73fe6c736bf57a0 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Mon, 18 May 2020 15:07:10 -0400 Subject: efi/libstub: Add definitions for console input and events Add the required typedefs etc for using con_in's simple text input protocol, and for using the boottime event services. Also add the prototype for the "stall" boot service. Signed-off-by: Arvind Sankar Link: https://lore.kernel.org/r/20200518190716.751506-19-nivedita@alum.mit.edu Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 9b7c7ec319ac..974648db0c68 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -426,6 +426,7 @@ typedef struct { u32 tables; } efi_system_table_32_t; +typedef union efi_simple_text_input_protocol efi_simple_text_input_protocol_t; typedef union efi_simple_text_output_protocol efi_simple_text_output_protocol_t; typedef union { @@ -434,7 +435,7 @@ typedef union { unsigned long fw_vendor; /* physical addr of CHAR16 vendor string */ u32 fw_revision; unsigned long con_in_handle; - unsigned long con_in; + efi_simple_text_input_protocol_t *con_in; unsigned long con_out_handle; efi_simple_text_output_protocol_t *con_out; unsigned long stderr_handle; -- cgit v1.2.3 From 14c574f35cfbc9272fc67b41f074c847db139652 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Mon, 18 May 2020 15:07:11 -0400 Subject: efi/gop: Add an option to list out the available GOP modes Add video=efifb:list option to list the modes that are available. Signed-off-by: Arvind Sankar Link: https://lore.kernel.org/r/20200518190716.751506-20-nivedita@alum.mit.edu Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 974648db0c68..609201bd4682 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -39,6 +39,7 @@ #define EFI_WRITE_PROTECTED ( 8 | (1UL << (BITS_PER_LONG-1))) #define EFI_OUT_OF_RESOURCES ( 9 | (1UL << (BITS_PER_LONG-1))) #define EFI_NOT_FOUND (14 | (1UL << (BITS_PER_LONG-1))) +#define EFI_TIMEOUT (18 | (1UL << (BITS_PER_LONG-1))) #define EFI_ABORTED (21 | (1UL << (BITS_PER_LONG-1))) #define EFI_SECURITY_VIOLATION (26 | (1UL << (BITS_PER_LONG-1))) -- cgit v1.2.3 From 15c704ab6244ac95be54b2c05411b70501d50e8f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:17 +0100 Subject: firmware: smccc: Update link to latest SMCCC specification The current link gets redirected to the revision B published in November 2016 though it actually points to the original revision A published in June 2013. Let us update the link to point to the latest version, so that it doesn't get stale anytime soon. Currently it points to v1.2 published in March 2020(i.e. DEN0028C). Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-3-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 59494df0f55b..31b15db9685d 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -10,7 +10,9 @@ /* * This file provides common defines for ARM SMC Calling Convention as * specified in - * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html + * https://developer.arm.com/docs/den0028/latest + * + * This code is up-to-date with version DEN 0028 B */ #define ARM_SMCCC_STD_CALL _AC(0,U) -- cgit v1.2.3 From 0441bfe7f00acaae7c4937ba0ca48ee1de9b709f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:18 +0100 Subject: firmware: smccc: Add the definition for SMCCCv1.2 version/error codes Add the definition for SMCCC v1.2 version and new error code added. While at it, also add a note that ARM DEN 0070A is deprecated and is now merged into the main SMCCC specification(ARM DEN 0028C). Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Link: https://lore.kernel.org/r/20200518091222.27467-4-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 31b15db9685d..c3784ba8e2a4 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -12,7 +12,7 @@ * specified in * https://developer.arm.com/docs/den0028/latest * - * This code is up-to-date with version DEN 0028 B + * This code is up-to-date with version DEN 0028 C */ #define ARM_SMCCC_STD_CALL _AC(0,U) @@ -58,6 +58,7 @@ #define ARM_SMCCC_VERSION_1_0 0x10000 #define ARM_SMCCC_VERSION_1_1 0x10001 +#define ARM_SMCCC_VERSION_1_2 0x10002 #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ @@ -316,10 +317,14 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, */ #define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) -/* Return codes defined in ARM DEN 0070A */ +/* + * Return codes defined in ARM DEN 0070A + * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C + */ #define SMCCC_RET_SUCCESS 0 #define SMCCC_RET_NOT_SUPPORTED -1 #define SMCCC_RET_NOT_REQUIRED -2 +#define SMCCC_RET_INVALID_PARAMETER -3 /* * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED. -- cgit v1.2.3 From ad5a57dfe434b02ab28852703d7ad5510998ccef Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:19 +0100 Subject: firmware: smccc: Drop smccc_version enum and use ARM_SMCCC_VERSION_1_x instead Instead of maintaining 2 sets of enums/macros for tracking SMCCC version, let us drop smccc_version enum and use ARM_SMCCC_VERSION_1_x directly instead. This is in preparation to drop smccc_version here and move it separately under drivers/firmware/smccc. Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-5-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/psci.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psci.h b/include/linux/psci.h index a67712b73b6c..29bd0671e5bb 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -21,11 +21,6 @@ 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, - SMCCC_VERSION_1_1, -}; - struct psci_operations { u32 (*get_version)(void); int (*cpu_suspend)(u32 state, unsigned long entry_point); @@ -36,7 +31,7 @@ struct psci_operations { unsigned long lowest_affinity_level); int (*migrate_info_type)(void); enum arm_smccc_conduit conduit; - enum smccc_version smccc_version; + u32 smccc_version; }; extern struct psci_operations psci_ops; -- cgit v1.2.3 From f2ae97062a48b114bcf8fb2e99574d9ed2c2cd1b Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:20 +0100 Subject: firmware: smccc: Refactor SMCCC specific bits into separate file In order to add newer SMCCC v1.1+ functionality and to avoid cluttering PSCI firmware driver with SMCCC bits, let us move the SMCCC specific details under drivers/firmware/smccc/smccc.c We can also drop conduit and smccc_version from psci_operations structure as SMCCC was the sole user and now it maintains those. No functionality change in this patch though. Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-6-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/psci.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psci.h b/include/linux/psci.h index 29bd0671e5bb..14ad9b9ebcd6 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -30,8 +30,6 @@ struct psci_operations { int (*affinity_info)(unsigned long target_affinity, unsigned long lowest_affinity_level); int (*migrate_info_type)(void); - enum arm_smccc_conduit conduit; - u32 smccc_version; }; extern struct psci_operations psci_ops; -- cgit v1.2.3 From a4fb17465182c9fc13104e4df04d050892055205 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:21 +0100 Subject: firmware: smccc: Add function to fetch SMCCC version For backward compatibility reasons, PSCI maintains SMCCC version as SMCCC didn't provide ARM_SMCCC_VERSION_FUNC_ID until v1.1. PSCI initialises both the SMCCC version and conduit. Similar to the conduit, let us provide accessors to fetch the SMCCC version also so that other SMCCC v1.1+ features can use it. Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-7-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index c3784ba8e2a4..c491d210e3c3 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -100,6 +100,17 @@ enum arm_smccc_conduit { */ enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); +/** + * arm_smccc_get_version() + * + * Returns the version to be used for SMCCCv1.1 or later. + * + * When SMCCCv1.1 or above is not present, returns SMCCCv1.0, but this + * does not imply the presence of firmware or a valid conduit. Caller + * handling SMCCCv1.0 must determine the conduit by other means. + */ +u32 arm_smccc_get_version(void); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 -- cgit v1.2.3 From b8bff599261c930630385ee21d3f98e7ce7d4843 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 22 Mar 2020 15:46:24 -0500 Subject: exec: Factor security_bprm_creds_for_exec out of security_bprm_set_creds Today security_bprm_set_creds has several implementations: apparmor_bprm_set_creds, cap_bprm_set_creds, selinux_bprm_set_creds, smack_bprm_set_creds, and tomoyo_bprm_set_creds. Except for cap_bprm_set_creds they all test bprm->called_set_creds and return immediately if it is true. The function cap_bprm_set_creds ignores bprm->calld_sed_creds entirely. Create a new LSM hook security_bprm_creds_for_exec that is called just before prepare_binprm in __do_execve_file, resulting in a LSM hook that is called exactly once for the entire of exec. Modify the bits of security_bprm_set_creds that only want to be called once per exec into security_bprm_creds_for_exec, leaving only cap_bprm_set_creds behind. Remove bprm->called_set_creds all of it's former users have been moved to security_bprm_creds_for_exec. Add or upate comments a appropriate to bring them up to date and to reflect this change. Link: https://lkml.kernel.org/r/87v9kszrzh.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Acked-by: Casey Schaufler # For the LSM and Smack bits Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 18 +++++----------- include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 50 ++++++++++++++++++++++++------------------- include/linux/security.h | 6 ++++++ 4 files changed, 40 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 1b48e2154766..d1217fcdedea 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -27,22 +27,14 @@ struct linux_binprm { unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int /* - * True after the bprm_set_creds hook has been called once - * (multiple calls can be made via prepare_binprm() for - * binfmt_script/misc). - */ - called_set_creds:1, - /* - * True if most recent call to the commoncaps bprm_set_creds - * hook (due to multiple prepare_binprm() calls from the - * binfmt_script/misc handlers) resulted in elevated - * privileges. + * True if most recent call to cap_bprm_set_creds + * resulted in elevated privileges. */ cap_elevated:1, /* - * Set by bprm_set_creds hook to indicate a privilege-gaining - * exec has happened. Used to sanitize execution environment - * and to set AT_SECURE auxv for glibc. + * Set by bprm_creds_for_exec hook to indicate a + * privilege-gaining exec has happened. Used to set + * AT_SECURE auxv for glibc. */ secureexec:1, /* diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..aab0695f41df 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -49,6 +49,7 @@ LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) +LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_set_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..c719af37df20 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -34,40 +34,46 @@ * * Security hooks for program execution operations. * + * @bprm_creds_for_exec: + * If the setup in prepare_exec_creds did not setup @bprm->cred->security + * properly for executing @bprm->file, update the LSM's portion of + * @bprm->cred->security to be what commit_creds needs to install for the + * new program. This hook may also optionally check permissions + * (e.g. for transitions between security domains). + * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to + * request libc enable secure mode. + * @bprm contains the linux_binprm structure. + * Return 0 if the hook is successful and permission is granted. * @bprm_set_creds: - * Save security information in the bprm->security field, typically based - * on information about the bprm->file, for later use by the apply_creds - * hook. This hook may also optionally check permissions (e.g. for + * Assuming that the relevant bits of @bprm->cred->security have been + * previously set, examine @bprm->file and regenerate them. This is + * so that the credentials derived from the interpreter the code is + * actually going to run are used rather than credentials derived + * from a script. This done because the interpreter binary needs to + * reopen script, and may end up opening something completely different. + * This hook may also optionally check permissions (e.g. for * transitions between security domains). - * This hook may be called multiple times during a single execve, e.g. for - * interpreters. The hook can tell whether it has already been called by - * checking to see if @bprm->security is non-NULL. If so, then the hook - * may decide either to retain the security information saved earlier or - * to replace it. The hook must set @bprm->secureexec to 1 if a "secure - * exec" has happened as a result of this hook call. The flag is used to - * indicate the need for a sanitized execution environment, and is also - * passed in the ELF auxiliary table on the initial stack to indicate - * whether libc should enable secure mode. + * The hook must set @bprm->cap_elevated to 1 if AT_SECURE should be set to + * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: * This hook mediates the point when a search for a binary handler will - * begin. It allows a check the @bprm->security value which is set in the - * preceding set_creds call. The primary difference from set_creds is - * that the argv list and envp list are reliably available in @bprm. This - * hook may be called multiple times during a single execve; and in each - * pass set_creds is called first. + * begin. It allows a check against the @bprm->cred->security value + * which was set in the preceding creds_for_exec call. The argv list and + * envp list are reliably available in @bprm. This hook may be called + * multiple times during a single execve. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_committing_creds: * Prepare to install the new security attributes of a process being * transformed by an execve operation, based on the old credentials * pointed to by @current->cred and the information set in @bprm->cred by - * the bprm_set_creds hook. @bprm points to the linux_binprm structure. - * This hook is a good place to perform state changes on the process such - * as closing open file descriptors to which access will no longer be - * granted when the attributes are changed. This is called immediately - * before commit_creds(). + * the bprm_creds_for_exec hook. @bprm points to the linux_binprm + * structure. This hook is a good place to perform state changes on the + * process such as closing open file descriptors to which access will no + * longer be granted when the attributes are changed. This is called + * immediately before commit_creds(). * @bprm_committed_creds: * Tidy up after the installation of the new security attributes of a * process being transformed by an execve operation. The new credentials diff --git a/include/linux/security.h b/include/linux/security.h index a8d9310472df..1bd7a6582775 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -276,6 +276,7 @@ int security_quota_on(struct dentry *dentry); int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); +int security_bprm_creds_for_exec(struct linux_binprm *bprm); int security_bprm_set_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); @@ -569,6 +570,11 @@ static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages)); } +static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) +{ + return 0; +} + static inline int security_bprm_set_creds(struct linux_binprm *bprm) { return cap_bprm_set_creds(bprm); -- cgit v1.2.3 From 74244b59a82358b9f51c80981a99c5951ea3028f Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 14 May 2020 08:09:28 +0200 Subject: dm: use dynamic debug instead of compile-time config option Switch to use dynamic debug to avoid having recompile the kernel just to enable debugging messages. Signed-off-by: Hannes Reinecke Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 934037d938b9..8750f2dc5613 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -559,13 +559,8 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); #define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__) #define DMINFO_LIMIT(fmt, ...) pr_info_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) -#ifdef CONFIG_DM_DEBUG -#define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__) +#define DMDEBUG(fmt, ...) pr_debug(DM_FMT(fmt), ##__VA_ARGS__) #define DMDEBUG_LIMIT(fmt, ...) pr_debug_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) -#else -#define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__) -#define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__) -#endif #define DMEMIT(x...) sz += ((sz >= maxlen) ? \ 0 : scnprintf(result + sz, maxlen - sz, x)) -- cgit v1.2.3 From 931ca7ab7fe804d77bc6952f1512950c0d870f26 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2020 17:18:30 -0400 Subject: ip*_mc_gsfget(): lift copyout of struct group_filter into callers pass the userland pointer to the array in its tail, so that part gets copied out by our functions; copyout of everything else is done in the callers. Rationale: reuse for compat; the array is the same in native and compat, the layout of parts before it is different for compat. Signed-off-by: Al Viro --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index faa6586a5783..64ce8cd1cfaf 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -123,7 +123,7 @@ extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct group_filter __user *optval, int __user *optlen); + struct sockaddr_storage __user *p); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); -- cgit v1.2.3 From 4e2e7cfec13afa41fcbed1d9b93d83432aa0154f Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Tue, 21 Apr 2020 11:00:07 +0800 Subject: mfd: mt6397: Modify suspend/resume behavior Some pmics don't need backup interrupt settings, so we change to use pm notifier for the pmics which are necessary to store settings. Signed-off-by: Hsin-Hsiung Wang Signed-off-by: Lee Jones --- include/linux/mfd/mt6397/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index fc88d315bdde..b81d33325ade 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -8,6 +8,7 @@ #define __MFD_MT6397_CORE_H__ #include +#include enum chip_id { MT6323_CHIP_ID = 0x23, @@ -54,6 +55,7 @@ enum mt6397_irq_numbers { struct mt6397_chip { struct device *dev; struct regmap *regmap; + struct notifier_block pm_nb; int irq; struct irq_domain *irq_domain; struct mutex irqlock; -- cgit v1.2.3 From 2b91c28f2abd9471aac4aa6cd8de7896ef469153 Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Tue, 21 Apr 2020 11:00:10 +0800 Subject: mfd: Add support for the MediaTek MT6358 PMIC This adds support for the MediaTek MT6358 PMIC. This is a multifunction device with the following sub modules: - Regulator - RTC - Codec - Interrupt It is interfaced to the host controller using SPI interface by a proprietary hardware called PMIC wrapper or pwrap. MT6358 MFD is a child device of the pwrap. Signed-off-by: Hsin-Hsiung Wang Signed-off-by: Lee Jones --- include/linux/mfd/mt6358/core.h | 158 ++++++++++++++++++++ include/linux/mfd/mt6358/registers.h | 282 +++++++++++++++++++++++++++++++++++ include/linux/mfd/mt6397/core.h | 3 + 3 files changed, 443 insertions(+) create mode 100644 include/linux/mfd/mt6358/core.h create mode 100644 include/linux/mfd/mt6358/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6358/core.h b/include/linux/mfd/mt6358/core.h new file mode 100644 index 000000000000..c5a11b7458d4 --- /dev/null +++ b/include/linux/mfd/mt6358/core.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + */ + +#ifndef __MFD_MT6358_CORE_H__ +#define __MFD_MT6358_CORE_H__ + +#define MT6358_REG_WIDTH 16 + +struct irq_top_t { + int hwirq_base; + unsigned int num_int_regs; + unsigned int num_int_bits; + unsigned int en_reg; + unsigned int en_reg_shift; + unsigned int sta_reg; + unsigned int sta_reg_shift; + unsigned int top_offset; +}; + +struct pmic_irq_data { + unsigned int num_top; + unsigned int num_pmic_irqs; + unsigned short top_int_status_reg; + bool *enable_hwirq; + bool *cache_hwirq; +}; + +enum mt6358_irq_top_status_shift { + MT6358_BUCK_TOP = 0, + MT6358_LDO_TOP, + MT6358_PSC_TOP, + MT6358_SCK_TOP, + MT6358_BM_TOP, + MT6358_HK_TOP, + MT6358_AUD_TOP, + MT6358_MISC_TOP, +}; + +enum mt6358_irq_numbers { + MT6358_IRQ_VPROC11_OC = 0, + MT6358_IRQ_VPROC12_OC, + MT6358_IRQ_VCORE_OC, + MT6358_IRQ_VGPU_OC, + MT6358_IRQ_VMODEM_OC, + MT6358_IRQ_VDRAM1_OC, + MT6358_IRQ_VS1_OC, + MT6358_IRQ_VS2_OC, + MT6358_IRQ_VPA_OC, + MT6358_IRQ_VCORE_PREOC, + MT6358_IRQ_VFE28_OC = 16, + MT6358_IRQ_VXO22_OC, + MT6358_IRQ_VRF18_OC, + MT6358_IRQ_VRF12_OC, + MT6358_IRQ_VEFUSE_OC, + MT6358_IRQ_VCN33_OC, + MT6358_IRQ_VCN28_OC, + MT6358_IRQ_VCN18_OC, + MT6358_IRQ_VCAMA1_OC, + MT6358_IRQ_VCAMA2_OC, + MT6358_IRQ_VCAMD_OC, + MT6358_IRQ_VCAMIO_OC, + MT6358_IRQ_VLDO28_OC, + MT6358_IRQ_VA12_OC, + MT6358_IRQ_VAUX18_OC, + MT6358_IRQ_VAUD28_OC, + MT6358_IRQ_VIO28_OC, + MT6358_IRQ_VIO18_OC, + MT6358_IRQ_VSRAM_PROC11_OC, + MT6358_IRQ_VSRAM_PROC12_OC, + MT6358_IRQ_VSRAM_OTHERS_OC, + MT6358_IRQ_VSRAM_GPU_OC, + MT6358_IRQ_VDRAM2_OC, + MT6358_IRQ_VMC_OC, + MT6358_IRQ_VMCH_OC, + MT6358_IRQ_VEMC_OC, + MT6358_IRQ_VSIM1_OC, + MT6358_IRQ_VSIM2_OC, + MT6358_IRQ_VIBR_OC, + MT6358_IRQ_VUSB_OC, + MT6358_IRQ_VBIF28_OC, + MT6358_IRQ_PWRKEY = 48, + MT6358_IRQ_HOMEKEY, + MT6358_IRQ_PWRKEY_R, + MT6358_IRQ_HOMEKEY_R, + MT6358_IRQ_NI_LBAT_INT, + MT6358_IRQ_CHRDET, + MT6358_IRQ_CHRDET_EDGE, + MT6358_IRQ_VCDT_HV_DET, + MT6358_IRQ_RTC = 64, + MT6358_IRQ_FG_BAT0_H = 80, + MT6358_IRQ_FG_BAT0_L, + MT6358_IRQ_FG_CUR_H, + MT6358_IRQ_FG_CUR_L, + MT6358_IRQ_FG_ZCV, + MT6358_IRQ_FG_BAT1_H, + MT6358_IRQ_FG_BAT1_L, + MT6358_IRQ_FG_N_CHARGE_L, + MT6358_IRQ_FG_IAVG_H, + MT6358_IRQ_FG_IAVG_L, + MT6358_IRQ_FG_TIME_H, + MT6358_IRQ_FG_DISCHARGE, + MT6358_IRQ_FG_CHARGE, + MT6358_IRQ_BATON_LV = 96, + MT6358_IRQ_BATON_HT, + MT6358_IRQ_BATON_BAT_IN, + MT6358_IRQ_BATON_BAT_OUT, + MT6358_IRQ_BIF, + MT6358_IRQ_BAT_H = 112, + MT6358_IRQ_BAT_L, + MT6358_IRQ_BAT2_H, + MT6358_IRQ_BAT2_L, + MT6358_IRQ_BAT_TEMP_H, + MT6358_IRQ_BAT_TEMP_L, + MT6358_IRQ_AUXADC_IMP, + MT6358_IRQ_NAG_C_DLTV, + MT6358_IRQ_AUDIO = 128, + MT6358_IRQ_ACCDET = 133, + MT6358_IRQ_ACCDET_EINT0, + MT6358_IRQ_ACCDET_EINT1, + MT6358_IRQ_SPI_CMD_ALERT = 144, + MT6358_IRQ_NR, +}; + +#define MT6358_IRQ_BUCK_BASE MT6358_IRQ_VPROC11_OC +#define MT6358_IRQ_LDO_BASE MT6358_IRQ_VFE28_OC +#define MT6358_IRQ_PSC_BASE MT6358_IRQ_PWRKEY +#define MT6358_IRQ_SCK_BASE MT6358_IRQ_RTC +#define MT6358_IRQ_BM_BASE MT6358_IRQ_FG_BAT0_H +#define MT6358_IRQ_HK_BASE MT6358_IRQ_BAT_H +#define MT6358_IRQ_AUD_BASE MT6358_IRQ_AUDIO +#define MT6358_IRQ_MISC_BASE MT6358_IRQ_SPI_CMD_ALERT + +#define MT6358_IRQ_BUCK_BITS (MT6358_IRQ_VCORE_PREOC - MT6358_IRQ_BUCK_BASE + 1) +#define MT6358_IRQ_LDO_BITS (MT6358_IRQ_VBIF28_OC - MT6358_IRQ_LDO_BASE + 1) +#define MT6358_IRQ_PSC_BITS (MT6358_IRQ_VCDT_HV_DET - MT6358_IRQ_PSC_BASE + 1) +#define MT6358_IRQ_SCK_BITS (MT6358_IRQ_RTC - MT6358_IRQ_SCK_BASE + 1) +#define MT6358_IRQ_BM_BITS (MT6358_IRQ_BIF - MT6358_IRQ_BM_BASE + 1) +#define MT6358_IRQ_HK_BITS (MT6358_IRQ_NAG_C_DLTV - MT6358_IRQ_HK_BASE + 1) +#define MT6358_IRQ_AUD_BITS (MT6358_IRQ_ACCDET_EINT1 - MT6358_IRQ_AUD_BASE + 1) +#define MT6358_IRQ_MISC_BITS \ + (MT6358_IRQ_SPI_CMD_ALERT - MT6358_IRQ_MISC_BASE + 1) + +#define MT6358_TOP_GEN(sp) \ +{ \ + .hwirq_base = MT6358_IRQ_##sp##_BASE, \ + .num_int_regs = \ + ((MT6358_IRQ_##sp##_BITS - 1) / MT6358_REG_WIDTH) + 1, \ + .num_int_bits = MT6358_IRQ_##sp##_BITS, \ + .en_reg = MT6358_##sp##_TOP_INT_CON0, \ + .en_reg_shift = 0x6, \ + .sta_reg = MT6358_##sp##_TOP_INT_STATUS0, \ + .sta_reg_shift = 0x2, \ + .top_offset = MT6358_##sp##_TOP, \ +} + +#endif /* __MFD_MT6358_CORE_H__ */ diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h new file mode 100644 index 000000000000..2ad0b312aa28 --- /dev/null +++ b/include/linux/mfd/mt6358/registers.h @@ -0,0 +1,282 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + */ + +#ifndef __MFD_MT6358_REGISTERS_H__ +#define __MFD_MT6358_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6358_SWCID 0xa +#define MT6358_MISC_TOP_INT_CON0 0x188 +#define MT6358_MISC_TOP_INT_STATUS0 0x194 +#define MT6358_TOP_INT_STATUS0 0x19e +#define MT6358_SCK_TOP_INT_CON0 0x52e +#define MT6358_SCK_TOP_INT_STATUS0 0x53a +#define MT6358_EOSC_CALI_CON0 0x540 +#define MT6358_EOSC_CALI_CON1 0x542 +#define MT6358_RTC_MIX_CON0 0x544 +#define MT6358_RTC_MIX_CON1 0x546 +#define MT6358_RTC_MIX_CON2 0x548 +#define MT6358_RTC_DSN_ID 0x580 +#define MT6358_RTC_DSN_REV0 0x582 +#define MT6358_RTC_DBI 0x584 +#define MT6358_RTC_DXI 0x586 +#define MT6358_RTC_BBPU 0x588 +#define MT6358_RTC_IRQ_STA 0x58a +#define MT6358_RTC_IRQ_EN 0x58c +#define MT6358_RTC_CII_EN 0x58e +#define MT6358_RTC_AL_MASK 0x590 +#define MT6358_RTC_TC_SEC 0x592 +#define MT6358_RTC_TC_MIN 0x594 +#define MT6358_RTC_TC_HOU 0x596 +#define MT6358_RTC_TC_DOM 0x598 +#define MT6358_RTC_TC_DOW 0x59a +#define MT6358_RTC_TC_MTH 0x59c +#define MT6358_RTC_TC_YEA 0x59e +#define MT6358_RTC_AL_SEC 0x5a0 +#define MT6358_RTC_AL_MIN 0x5a2 +#define MT6358_RTC_AL_HOU 0x5a4 +#define MT6358_RTC_AL_DOM 0x5a6 +#define MT6358_RTC_AL_DOW 0x5a8 +#define MT6358_RTC_AL_MTH 0x5aa +#define MT6358_RTC_AL_YEA 0x5ac +#define MT6358_RTC_OSC32CON 0x5ae +#define MT6358_RTC_POWERKEY1 0x5b0 +#define MT6358_RTC_POWERKEY2 0x5b2 +#define MT6358_RTC_PDN1 0x5b4 +#define MT6358_RTC_PDN2 0x5b6 +#define MT6358_RTC_SPAR0 0x5b8 +#define MT6358_RTC_SPAR1 0x5ba +#define MT6358_RTC_PROT 0x5bc +#define MT6358_RTC_DIFF 0x5be +#define MT6358_RTC_CALI 0x5c0 +#define MT6358_RTC_WRTGR 0x5c2 +#define MT6358_RTC_CON 0x5c4 +#define MT6358_RTC_SEC_CTRL 0x5c6 +#define MT6358_RTC_INT_CNT 0x5c8 +#define MT6358_RTC_SEC_DAT0 0x5ca +#define MT6358_RTC_SEC_DAT1 0x5cc +#define MT6358_RTC_SEC_DAT2 0x5ce +#define MT6358_RTC_SEC_DSN_ID 0x600 +#define MT6358_RTC_SEC_DSN_REV0 0x602 +#define MT6358_RTC_SEC_DBI 0x604 +#define MT6358_RTC_SEC_DXI 0x606 +#define MT6358_RTC_TC_SEC_SEC 0x608 +#define MT6358_RTC_TC_MIN_SEC 0x60a +#define MT6358_RTC_TC_HOU_SEC 0x60c +#define MT6358_RTC_TC_DOM_SEC 0x60e +#define MT6358_RTC_TC_DOW_SEC 0x610 +#define MT6358_RTC_TC_MTH_SEC 0x612 +#define MT6358_RTC_TC_YEA_SEC 0x614 +#define MT6358_RTC_SEC_CK_PDN 0x616 +#define MT6358_RTC_SEC_WRTGR 0x618 +#define MT6358_PSC_TOP_INT_CON0 0x910 +#define MT6358_PSC_TOP_INT_STATUS0 0x91c +#define MT6358_BM_TOP_INT_CON0 0xc32 +#define MT6358_BM_TOP_INT_CON1 0xc38 +#define MT6358_BM_TOP_INT_STATUS0 0xc4a +#define MT6358_BM_TOP_INT_STATUS1 0xc4c +#define MT6358_HK_TOP_INT_CON0 0xf92 +#define MT6358_HK_TOP_INT_STATUS0 0xf9e +#define MT6358_BUCK_TOP_INT_CON0 0x1318 +#define MT6358_BUCK_TOP_INT_STATUS0 0x1324 +#define MT6358_BUCK_VPROC11_CON0 0x1388 +#define MT6358_BUCK_VPROC11_DBG0 0x139e +#define MT6358_BUCK_VPROC11_DBG1 0x13a0 +#define MT6358_BUCK_VPROC11_ELR0 0x13a6 +#define MT6358_BUCK_VPROC12_CON0 0x1408 +#define MT6358_BUCK_VPROC12_DBG0 0x141e +#define MT6358_BUCK_VPROC12_DBG1 0x1420 +#define MT6358_BUCK_VPROC12_ELR0 0x1426 +#define MT6358_BUCK_VCORE_CON0 0x1488 +#define MT6358_BUCK_VCORE_DBG0 0x149e +#define MT6358_BUCK_VCORE_DBG1 0x14a0 +#define MT6358_BUCK_VCORE_ELR0 0x14aa +#define MT6358_BUCK_VGPU_CON0 0x1508 +#define MT6358_BUCK_VGPU_DBG0 0x151e +#define MT6358_BUCK_VGPU_DBG1 0x1520 +#define MT6358_BUCK_VGPU_ELR0 0x1526 +#define MT6358_BUCK_VMODEM_CON0 0x1588 +#define MT6358_BUCK_VMODEM_DBG0 0x159e +#define MT6358_BUCK_VMODEM_DBG1 0x15a0 +#define MT6358_BUCK_VMODEM_ELR0 0x15a6 +#define MT6358_BUCK_VDRAM1_CON0 0x1608 +#define MT6358_BUCK_VDRAM1_DBG0 0x161e +#define MT6358_BUCK_VDRAM1_DBG1 0x1620 +#define MT6358_BUCK_VDRAM1_ELR0 0x1626 +#define MT6358_BUCK_VS1_CON0 0x1688 +#define MT6358_BUCK_VS1_DBG0 0x169e +#define MT6358_BUCK_VS1_DBG1 0x16a0 +#define MT6358_BUCK_VS1_ELR0 0x16ae +#define MT6358_BUCK_VS2_CON0 0x1708 +#define MT6358_BUCK_VS2_DBG0 0x171e +#define MT6358_BUCK_VS2_DBG1 0x1720 +#define MT6358_BUCK_VS2_ELR0 0x172e +#define MT6358_BUCK_VPA_CON0 0x1788 +#define MT6358_BUCK_VPA_CON1 0x178a +#define MT6358_BUCK_VPA_ELR0 MT6358_BUCK_VPA_CON1 +#define MT6358_BUCK_VPA_DBG0 0x1792 +#define MT6358_BUCK_VPA_DBG1 0x1794 +#define MT6358_VPROC_ANA_CON0 0x180c +#define MT6358_VCORE_VGPU_ANA_CON0 0x1828 +#define MT6358_VMODEM_ANA_CON0 0x1888 +#define MT6358_VDRAM1_ANA_CON0 0x1896 +#define MT6358_VS1_ANA_CON0 0x18a2 +#define MT6358_VS2_ANA_CON0 0x18ae +#define MT6358_VPA_ANA_CON0 0x18ba +#define MT6358_LDO_TOP_INT_CON0 0x1a50 +#define MT6358_LDO_TOP_INT_CON1 0x1a56 +#define MT6358_LDO_TOP_INT_STATUS0 0x1a68 +#define MT6358_LDO_TOP_INT_STATUS1 0x1a6a +#define MT6358_LDO_VXO22_CON0 0x1a88 +#define MT6358_LDO_VXO22_CON1 0x1a96 +#define MT6358_LDO_VA12_CON0 0x1a9c +#define MT6358_LDO_VA12_CON1 0x1aaa +#define MT6358_LDO_VAUX18_CON0 0x1ab0 +#define MT6358_LDO_VAUX18_CON1 0x1abe +#define MT6358_LDO_VAUD28_CON0 0x1ac4 +#define MT6358_LDO_VAUD28_CON1 0x1ad2 +#define MT6358_LDO_VIO28_CON0 0x1ad8 +#define MT6358_LDO_VIO28_CON1 0x1ae6 +#define MT6358_LDO_VIO18_CON0 0x1aec +#define MT6358_LDO_VIO18_CON1 0x1afa +#define MT6358_LDO_VDRAM2_CON0 0x1b08 +#define MT6358_LDO_VDRAM2_CON1 0x1b16 +#define MT6358_LDO_VEMC_CON0 0x1b1c +#define MT6358_LDO_VEMC_CON1 0x1b2a +#define MT6358_LDO_VUSB_CON0_0 0x1b30 +#define MT6358_LDO_VUSB_CON1 0x1b40 +#define MT6358_LDO_VSRAM_PROC11_CON0 0x1b46 +#define MT6358_LDO_VSRAM_PROC11_DBG0 0x1b60 +#define MT6358_LDO_VSRAM_PROC11_DBG1 0x1b62 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON0 0x1b64 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON1 0x1b66 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON2 0x1b68 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON3 0x1b6a +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON0 0x1b6c +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON1 0x1b6e +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON2 0x1b70 +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON3 0x1b72 +#define MT6358_LDO_VSRAM_WAKEUP_CON0 0x1b74 +#define MT6358_LDO_GON1_ELR_NUM 0x1b76 +#define MT6358_LDO_VDRAM2_ELR0 0x1b78 +#define MT6358_LDO_VSRAM_PROC12_CON0 0x1b88 +#define MT6358_LDO_VSRAM_PROC12_DBG0 0x1ba2 +#define MT6358_LDO_VSRAM_PROC12_DBG1 0x1ba4 +#define MT6358_LDO_VSRAM_OTHERS_CON0 0x1ba6 +#define MT6358_LDO_VSRAM_OTHERS_DBG0 0x1bc0 +#define MT6358_LDO_VSRAM_OTHERS_DBG1 0x1bc2 +#define MT6358_LDO_VSRAM_GPU_CON0 0x1bc8 +#define MT6358_LDO_VSRAM_GPU_DBG0 0x1be2 +#define MT6358_LDO_VSRAM_GPU_DBG1 0x1be4 +#define MT6358_LDO_VSRAM_CON0 0x1bee +#define MT6358_LDO_VSRAM_CON1 0x1bf0 +#define MT6358_LDO_VSRAM_CON2 0x1bf2 +#define MT6358_LDO_VSRAM_CON3 0x1bf4 +#define MT6358_LDO_VFE28_CON0 0x1c08 +#define MT6358_LDO_VFE28_CON1 0x1c16 +#define MT6358_LDO_VFE28_CON2 0x1c18 +#define MT6358_LDO_VFE28_CON3 0x1c1a +#define MT6358_LDO_VRF18_CON0 0x1c1c +#define MT6358_LDO_VRF18_CON1 0x1c2a +#define MT6358_LDO_VRF18_CON2 0x1c2c +#define MT6358_LDO_VRF18_CON3 0x1c2e +#define MT6358_LDO_VRF12_CON0 0x1c30 +#define MT6358_LDO_VRF12_CON1 0x1c3e +#define MT6358_LDO_VRF12_CON2 0x1c40 +#define MT6358_LDO_VRF12_CON3 0x1c42 +#define MT6358_LDO_VEFUSE_CON0 0x1c44 +#define MT6358_LDO_VEFUSE_CON1 0x1c52 +#define MT6358_LDO_VEFUSE_CON2 0x1c54 +#define MT6358_LDO_VEFUSE_CON3 0x1c56 +#define MT6358_LDO_VCN18_CON0 0x1c58 +#define MT6358_LDO_VCN18_CON1 0x1c66 +#define MT6358_LDO_VCN18_CON2 0x1c68 +#define MT6358_LDO_VCN18_CON3 0x1c6a +#define MT6358_LDO_VCAMA1_CON0 0x1c6c +#define MT6358_LDO_VCAMA1_CON1 0x1c7a +#define MT6358_LDO_VCAMA1_CON2 0x1c7c +#define MT6358_LDO_VCAMA1_CON3 0x1c7e +#define MT6358_LDO_VCAMA2_CON0 0x1c88 +#define MT6358_LDO_VCAMA2_CON1 0x1c96 +#define MT6358_LDO_VCAMA2_CON2 0x1c98 +#define MT6358_LDO_VCAMA2_CON3 0x1c9a +#define MT6358_LDO_VCAMD_CON0 0x1c9c +#define MT6358_LDO_VCAMD_CON1 0x1caa +#define MT6358_LDO_VCAMD_CON2 0x1cac +#define MT6358_LDO_VCAMD_CON3 0x1cae +#define MT6358_LDO_VCAMIO_CON0 0x1cb0 +#define MT6358_LDO_VCAMIO_CON1 0x1cbe +#define MT6358_LDO_VCAMIO_CON2 0x1cc0 +#define MT6358_LDO_VCAMIO_CON3 0x1cc2 +#define MT6358_LDO_VMC_CON0 0x1cc4 +#define MT6358_LDO_VMC_CON1 0x1cd2 +#define MT6358_LDO_VMC_CON2 0x1cd4 +#define MT6358_LDO_VMC_CON3 0x1cd6 +#define MT6358_LDO_VMCH_CON0 0x1cd8 +#define MT6358_LDO_VMCH_CON1 0x1ce6 +#define MT6358_LDO_VMCH_CON2 0x1ce8 +#define MT6358_LDO_VMCH_CON3 0x1cea +#define MT6358_LDO_VIBR_CON0 0x1d08 +#define MT6358_LDO_VIBR_CON1 0x1d16 +#define MT6358_LDO_VIBR_CON2 0x1d18 +#define MT6358_LDO_VIBR_CON3 0x1d1a +#define MT6358_LDO_VCN33_CON0_0 0x1d1c +#define MT6358_LDO_VCN33_CON0_1 0x1d2a +#define MT6358_LDO_VCN33_CON1 0x1d2c +#define MT6358_LDO_VCN33_BT_CON1 MT6358_LDO_VCN33_CON1 +#define MT6358_LDO_VCN33_WIFI_CON1 MT6358_LDO_VCN33_CON1 +#define MT6358_LDO_VCN33_CON2 0x1d2e +#define MT6358_LDO_VCN33_CON3 0x1d30 +#define MT6358_LDO_VLDO28_CON0_0 0x1d32 +#define MT6358_LDO_VLDO28_CON0_1 0x1d40 +#define MT6358_LDO_VLDO28_CON1 0x1d42 +#define MT6358_LDO_VLDO28_CON2 0x1d44 +#define MT6358_LDO_VLDO28_CON3 0x1d46 +#define MT6358_LDO_VSIM1_CON0 0x1d48 +#define MT6358_LDO_VSIM1_CON1 0x1d56 +#define MT6358_LDO_VSIM1_CON2 0x1d58 +#define MT6358_LDO_VSIM1_CON3 0x1d5a +#define MT6358_LDO_VSIM2_CON0 0x1d5c +#define MT6358_LDO_VSIM2_CON1 0x1d6a +#define MT6358_LDO_VSIM2_CON2 0x1d6c +#define MT6358_LDO_VSIM2_CON3 0x1d6e +#define MT6358_LDO_VCN28_CON0 0x1d88 +#define MT6358_LDO_VCN28_CON1 0x1d96 +#define MT6358_LDO_VCN28_CON2 0x1d98 +#define MT6358_LDO_VCN28_CON3 0x1d9a +#define MT6358_VRTC28_CON0 0x1d9c +#define MT6358_LDO_VBIF28_CON0 0x1d9e +#define MT6358_LDO_VBIF28_CON1 0x1dac +#define MT6358_LDO_VBIF28_CON2 0x1dae +#define MT6358_LDO_VBIF28_CON3 0x1db0 +#define MT6358_VCAMA1_ANA_CON0 0x1e08 +#define MT6358_VCAMA2_ANA_CON0 0x1e0c +#define MT6358_VCN33_ANA_CON0 0x1e28 +#define MT6358_VSIM1_ANA_CON0 0x1e2c +#define MT6358_VSIM2_ANA_CON0 0x1e30 +#define MT6358_VUSB_ANA_CON0 0x1e34 +#define MT6358_VEMC_ANA_CON0 0x1e38 +#define MT6358_VLDO28_ANA_CON0 0x1e3c +#define MT6358_VIO28_ANA_CON0 0x1e40 +#define MT6358_VIBR_ANA_CON0 0x1e44 +#define MT6358_VMCH_ANA_CON0 0x1e48 +#define MT6358_VMC_ANA_CON0 0x1e4c +#define MT6358_VRF18_ANA_CON0 0x1e88 +#define MT6358_VCN18_ANA_CON0 0x1e8c +#define MT6358_VCAMIO_ANA_CON0 0x1e90 +#define MT6358_VIO18_ANA_CON0 0x1e94 +#define MT6358_VEFUSE_ANA_CON0 0x1e98 +#define MT6358_VRF12_ANA_CON0 0x1e9c +#define MT6358_VSRAM_PROC11_ANA_CON0 0x1ea0 +#define MT6358_VSRAM_PROC12_ANA_CON0 0x1ea4 +#define MT6358_VSRAM_OTHERS_ANA_CON0 0x1ea6 +#define MT6358_VSRAM_GPU_ANA_CON0 0x1ea8 +#define MT6358_VDRAM2_ANA_CON0 0x1eaa +#define MT6358_VCAMD_ANA_CON0 0x1eae +#define MT6358_VA12_ANA_CON0 0x1eb2 +#define MT6358_AUD_TOP_INT_CON0 0x2228 +#define MT6358_AUD_TOP_INT_STATUS0 0x2234 + +#endif /* __MFD_MT6358_REGISTERS_H__ */ diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index b81d33325ade..949268581b36 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -12,6 +12,7 @@ enum chip_id { MT6323_CHIP_ID = 0x23, + MT6358_CHIP_ID = 0x58, MT6391_CHIP_ID = 0x91, MT6397_CHIP_ID = 0x97, }; @@ -65,8 +66,10 @@ struct mt6397_chip { u16 int_con[2]; u16 int_status[2]; u16 chip_id; + void *irq_data; }; +int mt6358_irq_init(struct mt6397_chip *chip); int mt6397_irq_init(struct mt6397_chip *chip); #endif /* __MFD_MT6397_CORE_H__ */ -- cgit v1.2.3 From 29ee40091e27615530c0ba7773a2879d8266381e Mon Sep 17 00:00:00 2001 From: Ran Bi Date: Tue, 21 Apr 2020 11:00:11 +0800 Subject: rtc: mt6397: Add support for the MediaTek MT6358 RTC This add support for the MediaTek MT6358 RTC. Driver using compatible data to store different RTC_WRTGR address offset. This replace RTC_WRTGR to RTC_WRTGR_MT6323 in mt6323-poweroff driver which only needed by armv7 CPU without ATF. Signed-off-by: Ran Bi Signed-off-by: Hsin-Hsiung Wang Reviewed-by: Nicolas Boichat Acked-by: Alexandre Belloni Acked-by: Sebastian Reichel Reviewed-by: Yingjoe Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6397/rtc.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index 7dfb63b81373..66989a16221a 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -18,7 +18,9 @@ #define RTC_BBPU_CBUSY BIT(6) #define RTC_BBPU_KEY (0x43 << 8) -#define RTC_WRTGR 0x003c +#define RTC_WRTGR_MT6358 0x003a +#define RTC_WRTGR_MT6397 0x003c +#define RTC_WRTGR_MT6323 RTC_WRTGR_MT6397 #define RTC_IRQ_STA 0x0002 #define RTC_IRQ_STA_AL BIT(0) @@ -65,6 +67,10 @@ #define MTK_RTC_POLL_DELAY_US 10 #define MTK_RTC_POLL_TIMEOUT (jiffies_to_usecs(HZ)) +struct mtk_rtc_data { + u32 wrtgr; +}; + struct mt6397_rtc { struct device *dev; struct rtc_device *rtc_dev; @@ -74,6 +80,7 @@ struct mt6397_rtc { struct regmap *regmap; int irq; u32 addr_base; + const struct mtk_rtc_data *data; }; #endif /* _LINUX_MFD_MT6397_RTC_H_ */ -- cgit v1.2.3 From 269fd61e15d785b9e20786672765400732dde8a0 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 21 May 2020 12:08:36 +0100 Subject: firmware: smccc: Fix missing prototype warning for arm_smccc_version_init Commit f2ae97062a48 ("firmware: smccc: Refactor SMCCC specific bits into separate file") introduced the following build warning: drivers/firmware/smccc/smccc.c:14:13: warning: no previous prototype for function 'arm_smccc_version_init' [-Wmissing-prototypes] void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit) ^~~~~~~~~~~~~~~~~~~~~~ Fix the same by adding the missing prototype in arm-smccc.h Reported-by: kbuild test robot Signed-off-by: Sudeep Holla Link: https://lore.kernel.org/r/20200521110836.57252-1-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index c491d210e3c3..56d6a5c6e353 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -5,6 +5,7 @@ #ifndef __LINUX_ARM_SMCCC_H #define __LINUX_ARM_SMCCC_H +#include #include /* @@ -111,6 +112,8 @@ enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); */ u32 arm_smccc_get_version(void); +void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 -- cgit v1.2.3 From 26d7e28e38206b1b3207af1409eee2269ab36f82 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 19 May 2020 16:22:59 +0200 Subject: s390/dasd: remove ioctl_by_bdev calls The IBM partition parser requires device type specific information only available to the DASD driver to correctly register partitions. The current approach of using ioctl_by_bdev with a fake user space pointer is discouraged. Fix this by replacing IOCTL calls with direct in-kernel function calls. Suggested-by: Christoph Hellwig Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Reviewed-by: Peter Oberparleiter Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/dasd_mod.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/dasd_mod.h (limited to 'include/linux') diff --git a/include/linux/dasd_mod.h b/include/linux/dasd_mod.h new file mode 100644 index 000000000000..d39abad2ff6e --- /dev/null +++ b/include/linux/dasd_mod.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef DASD_MOD_H +#define DASD_MOD_H + +#include + +extern int dasd_biodasdinfo(struct gendisk *disk, dasd_information2_t *info); + +#endif -- cgit v1.2.3 From 3783daeb1d24696ff00125050353cfce4f5b6239 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 May 2020 16:33:21 +0200 Subject: block: remove ioctl_by_bdev No callers left. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- 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 1a95e5158811..861ca61d728b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2636,7 +2636,6 @@ extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; #ifdef CONFIG_BLOCK -extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); -- cgit v1.2.3 From 112b7147592e8f46bd1da4f961773e6d974f38a8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 14 May 2020 12:53:44 -0500 Subject: exec: Convert security_bprm_set_creds into security_bprm_repopulate_creds Rename bprm->cap_elevated to bprm->active_secureexec and initialize it in prepare_binprm instead of in cap_bprm_set_creds. Initializing bprm->active_secureexec in prepare_binprm allows multiple implementations of security_bprm_repopulate_creds to play nicely with each other. Rename security_bprm_set_creds to security_bprm_reopulate_creds to emphasize that this path recomputes part of bprm->cred. This recomputation avoids the time of check vs time of use problems that are inherent in unix #! interpreters. In short two renames and a move in the location of initializing bprm->active_secureexec. Link: https://lkml.kernel.org/r/87o8qkzrxp.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 4 ++-- include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 4 ++-- include/linux/security.h | 8 ++++---- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index d1217fcdedea..8605ab4a0f89 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -27,10 +27,10 @@ struct linux_binprm { unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int /* - * True if most recent call to cap_bprm_set_creds + * True if most recent call to security_bprm_set_creds * resulted in elevated privileges. */ - cap_elevated:1, + active_secureexec:1, /* * Set by bprm_creds_for_exec hook to indicate a * privilege-gaining exec has happened. Used to set diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index aab0695f41df..1e295ba12c0d 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -50,7 +50,7 @@ LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) -LSM_HOOK(int, 0, bprm_set_creds, struct linux_binprm *bprm) +LSM_HOOK(int, 0, bprm_repopulate_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c719af37df20..d618ecc4d660 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -44,7 +44,7 @@ * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. - * @bprm_set_creds: + * @bprm_repopulate_creds: * Assuming that the relevant bits of @bprm->cred->security have been * previously set, examine @bprm->file and regenerate them. This is * so that the credentials derived from the interpreter the code is @@ -53,7 +53,7 @@ * reopen script, and may end up opening something completely different. * This hook may also optionally check permissions (e.g. for * transitions between security domains). - * The hook must set @bprm->cap_elevated to 1 if AT_SECURE should be set to + * The hook must set @bprm->active_secureexec to 1 if AT_SECURE should be set to * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. diff --git a/include/linux/security.h b/include/linux/security.h index 1bd7a6582775..6dcec9375e8f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -140,7 +140,7 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -extern int cap_bprm_set_creds(struct linux_binprm *bprm); +extern int cap_bprm_repopulate_creds(struct linux_binprm *bprm); extern int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, const char *name); @@ -277,7 +277,7 @@ int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); int security_bprm_creds_for_exec(struct linux_binprm *bprm); -int security_bprm_set_creds(struct linux_binprm *bprm); +int security_bprm_repopulate_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); @@ -575,9 +575,9 @@ static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) return 0; } -static inline int security_bprm_set_creds(struct linux_binprm *bprm) +static inline int security_bprm_repopulate_creds(struct linux_binprm *bprm) { - return cap_bprm_set_creds(bprm); + return cap_bprm_repopulate_creds(bprm); } static inline int security_bprm_check(struct linux_binprm *bprm) -- cgit v1.2.3 From a16b3357b2b8e910bb614254d8a7e84d2bd59b4c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 16 May 2020 06:02:54 -0500 Subject: exec: Allow load_misc_binary to call prepare_binprm unconditionally Add a flag preserve_creds that binfmt_misc can set to prevent credentials from being updated. This allows binfmt_misc to always call prepare_binprm. Allowing the credential computation logic to be consolidated. Not replacing the credentials with the interpreters credentials is safe because because an open file descriptor to the executable is passed to the interpreter. As the interpreter does not need to reopen the executable it is guaranteed to see the same file that exec sees. Ref: c407c033de84 ("[PATCH] binfmt_misc: improve calculation of interpreter's credentials") Link: https://lkml.kernel.org/r/87imgszrwo.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8605ab4a0f89..dbb5614d62a2 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -26,6 +26,8 @@ struct linux_binprm { unsigned long p; /* current top of mem */ unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int + /* It is safe to use the creds of a script (see binfmt_misc) */ + preserve_creds:1, /* * True if most recent call to security_bprm_set_creds * resulted in elevated privileges. -- cgit v1.2.3 From 8b72ca9004ed35104deb80b07990da5503bc5252 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 13 May 2020 22:25:20 -0500 Subject: exec: Move the call of prepare_binprm into search_binary_handler The code in prepare_binary_handler needs to be run every time search_binary_handler is called so move the call into search_binary_handler itself to make the code simpler and easier to understand. Link: https://lkml.kernel.org/r/87d070zrvx.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Reviewed-by: James Morris Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index dbb5614d62a2..8c7779d6bf19 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -116,7 +116,6 @@ static inline void insert_binfmt(struct linux_binfmt *fmt) extern void unregister_binfmt(struct linux_binfmt *); -extern int prepare_binprm(struct linux_binprm *); extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *); extern int begin_new_exec(struct linux_binprm * bprm); -- cgit v1.2.3 From b8a61c9e7b4a0fec493d191429e9653d66a79ccc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 14 May 2020 15:17:40 -0500 Subject: exec: Generic execfd support Most of the support for passing the file descriptor of an executable to an interpreter already lives in the generic code and in binfmt_elf. Rework the fields in binfmt_elf that deal with executable file descriptor passing to make executable file descriptor passing a first class concept. Move the fd_install from binfmt_misc into begin_new_exec after the new creds have been installed. This means that accessing the file through /proc//fd/N is able to see the creds for the new executable before allowing access to the new executables files. Performing the install of the executables file descriptor after the point of no return also means that nothing special needs to be done on error. The exiting of the process will close all of it's open files. Move the would_dump from binfmt_misc into begin_new_exec right after would_dump is called on the bprm->file. This makes it obvious this case exists and that no nesting of bprm->file is currently supported. In binfmt_misc the movement of fd_install into generic code means that it's special error exit path is no longer needed. Link: https://lkml.kernel.org/r/87y2poyd91.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8c7779d6bf19..653508b25815 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -26,6 +26,9 @@ struct linux_binprm { unsigned long p; /* current top of mem */ unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int + /* Should an execfd be passed to userspace? */ + have_execfd:1, + /* It is safe to use the creds of a script (see binfmt_misc) */ preserve_creds:1, /* @@ -48,6 +51,7 @@ struct linux_binprm { unsigned int taso:1; #endif unsigned int recursion_depth; /* only for search_binary_handler() */ + struct file * executable; /* Executable to pass to the interpreter */ struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ @@ -58,7 +62,7 @@ struct linux_binprm { of the time same as filename, but could be different for binfmt_{misc,script} */ unsigned interp_flags; - unsigned interp_data; + int execfd; /* File descriptor of the executable */ unsigned long loader, exec; struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */ @@ -69,10 +73,6 @@ struct linux_binprm { #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) -/* fd of the binary should be passed to the interpreter */ -#define BINPRM_FLAGS_EXECFD_BIT 1 -#define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT) - /* filename of the binary will be inaccessible after exec */ #define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2 #define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT) -- cgit v1.2.3 From bc2bf338d54b7aadaed49bb45b9e10d4592b2a46 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 18 May 2020 18:43:20 -0500 Subject: exec: Remove recursion from search_binary_handler Recursion in kernel code is generally a bad idea as it can overflow the kernel stack. Recursion in exec also hides that the code is looping and that the loop changes bprm->file. Instead of recursing in search_binary_handler have the methods that would recurse set bprm->interpreter and return 0. Modify exec_binprm to loop when bprm->interpreter is set. Consolidate all of the reassignments of bprm->file in that loop to make it clear what is going on. The structure of the new loop in exec_binprm is that all errors return immediately, while successful completion (ret == 0 && !bprm->interpreter) just breaks out of the loop and runs what exec_bprm has always run upon successful completion. Fail if the an interpreter is being call after execfd has been set. The code has never properly handled an interpreter being called with execfd being set and with reassignments of bprm->file and the assignment of bprm->executable in generic code it has finally become possible to test and fail when if this problematic condition happens. With the reassignments of bprm->file and the assignment of bprm->executable moved into the generic code add a test to see if bprm->executable is being reassigned. In search_binary_handler remove the test for !bprm->file. With all reassignments of bprm->file moved to exec_binprm bprm->file can never be NULL in search_binary_handler. Link: https://lkml.kernel.org/r/87sgfwyd84.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 653508b25815..7fc05929c967 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -50,8 +50,8 @@ struct linux_binprm { #ifdef __alpha__ unsigned int taso:1; #endif - unsigned int recursion_depth; /* only for search_binary_handler() */ struct file * executable; /* Executable to pass to the interpreter */ + struct file * interpreter; struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ @@ -117,7 +117,6 @@ static inline void insert_binfmt(struct linux_binfmt *fmt) extern void unregister_binfmt(struct linux_binfmt *); extern int __must_check remove_arg_zero(struct linux_binprm *); -extern int search_binary_handler(struct linux_binprm *); extern int begin_new_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); extern void finalize_exec(struct linux_binprm *bprm); -- cgit v1.2.3 From 6e0688dbff625f1e49e3ddb028720ae9fd606f0b Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczynski Date: Wed, 20 May 2020 18:34:10 +0000 Subject: PCI: Use bridge window names (PCI_BRIDGE_IO_WINDOW etc) Use bridge resource definitions instead of using the PCI_BRIDGE_RESOURCES constant with an integer offeset. Link: https://lore.kernel.org/r/20200520183411.1534621-2-kw@linux.com Signed-off-by: Krzysztof Wilczynski Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..cdfb07bfdf7d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -100,9 +100,21 @@ enum { PCI_IOV_RESOURCE_END = PCI_IOV_RESOURCES + PCI_SRIOV_NUM_BARS - 1, #endif - /* Resources assigned to buses behind the bridge */ +/* PCI-to-PCI (P2P) bridge windows */ +#define PCI_BRIDGE_IO_WINDOW (PCI_BRIDGE_RESOURCES + 0) +#define PCI_BRIDGE_MEM_WINDOW (PCI_BRIDGE_RESOURCES + 1) +#define PCI_BRIDGE_PREF_MEM_WINDOW (PCI_BRIDGE_RESOURCES + 2) + +/* CardBus bridge windows */ +#define PCI_CB_BRIDGE_IO_0_WINDOW (PCI_BRIDGE_RESOURCES + 0) +#define PCI_CB_BRIDGE_IO_1_WINDOW (PCI_BRIDGE_RESOURCES + 1) +#define PCI_CB_BRIDGE_MEM_0_WINDOW (PCI_BRIDGE_RESOURCES + 2) +#define PCI_CB_BRIDGE_MEM_1_WINDOW (PCI_BRIDGE_RESOURCES + 3) + +/* Total number of bridge resources for P2P and CardBus */ #define PCI_BRIDGE_RESOURCE_NUM 4 + /* Resources assigned to buses behind the bridge */ PCI_BRIDGE_RESOURCES, PCI_BRIDGE_RESOURCE_END = PCI_BRIDGE_RESOURCES + PCI_BRIDGE_RESOURCE_NUM - 1, -- cgit v1.2.3 From 7bfb399eca460500f048098bf427c45b40e17cae Mon Sep 17 00:00:00 2001 From: Yuval Basson Date: Tue, 19 May 2020 23:51:26 +0300 Subject: qed: Add XRC to RoCE Add support for XRC-SRQ's and XRC-QP's for upper layer driver. We maintain separate bitmaps for resource management for srq and xrc-srq, However, the range in FW is one, The xrc-srq's are first and then the srq's follow. Therefore we maintain a srq-id offset. v2: perform cleanups if XRC bitmpas allocation fail. Signed-off-by: Michal Kalderon Signed-off-by: Yuval Bason Signed-off-by: David S. Miller --- include/linux/qed/qed_rdma_if.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 74efca15fde7..f93edd5750a5 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -53,6 +53,13 @@ enum qed_roce_qp_state { QED_ROCE_QP_STATE_SQE }; +enum qed_rdma_qp_type { + QED_RDMA_QP_TYPE_RC, + QED_RDMA_QP_TYPE_XRC_INI, + QED_RDMA_QP_TYPE_XRC_TGT, + QED_RDMA_QP_TYPE_INVAL = 0xffff, +}; + enum qed_rdma_tid_type { QED_RDMA_TID_REGISTERED_MR, QED_RDMA_TID_FMR, @@ -291,6 +298,12 @@ struct qed_rdma_create_srq_in_params { u16 num_pages; u16 pd_id; u16 page_size; + + /* XRC related only */ + bool reserved_key_en; + bool is_xrc; + u32 cq_cid; + u16 xrcd_id; }; struct qed_rdma_destroy_cq_in_params { @@ -319,7 +332,9 @@ struct qed_rdma_create_qp_in_params { u16 rq_num_pages; u64 rq_pbl_ptr; u16 srq_id; + u16 xrcd_id; u8 stats_queue; + enum qed_rdma_qp_type qp_type; }; struct qed_rdma_create_qp_out_params { @@ -429,11 +444,13 @@ struct qed_rdma_create_srq_out_params { struct qed_rdma_destroy_srq_in_params { u16 srq_id; + bool is_xrc; }; struct qed_rdma_modify_srq_in_params { u32 wqe_limit; u16 srq_id; + bool is_xrc; }; struct qed_rdma_stats_out_params { @@ -611,6 +628,8 @@ struct qed_rdma_ops { int (*rdma_set_rdma_int)(struct qed_dev *cdev, u16 cnt); int (*rdma_alloc_pd)(void *rdma_cxt, u16 *pd); void (*rdma_dealloc_pd)(void *rdma_cxt, u16 pd); + int (*rdma_alloc_xrcd)(void *rdma_cxt, u16 *xrcd); + void (*rdma_dealloc_xrcd)(void *rdma_cxt, u16 xrcd); int (*rdma_create_cq)(void *rdma_cxt, struct qed_rdma_create_cq_in_params *params, u16 *icid); -- cgit v1.2.3 From 8066021915924f58ed338bf38208215f5a7355f6 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 20 May 2020 08:29:14 +0200 Subject: ethtool: provide UAPI for PHY Signal Quality Index (SQI) Signal Quality Index is a mandatory value required by "OPEN Alliance SIG" for the 100Base-T1 PHYs [1]. This indicator can be used for cable integrity diagnostic and investigating other noise sources and implement by at least two vendors: NXP[2] and TI[3]. [1] http://www.opensig.org/download/document/218/Advanced_PHY_features_for_automotive_Ethernet_V1.0.pdf [2] https://www.nxp.com/docs/en/data-sheet/TJA1100.pdf [3] https://www.ti.com/product/DP83TC811R-Q1 Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Reviewed-by: Michal Kubecek 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 467aa8bf9f64..2bcdf19ed3b4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -723,6 +723,8 @@ struct phy_driver { struct ethtool_tunable *tuna, const void *data); int (*set_loopback)(struct phy_device *dev, bool enable); + int (*get_sqi)(struct phy_device *dev); + int (*get_sqi_max)(struct phy_device *dev); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -- cgit v1.2.3 From 560e3a045961ed0c7184ef9f6a93b95bd38c1c48 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Thu, 21 May 2020 22:32:40 +0530 Subject: bus: mhi: core: Handle firmware load using state worker Upon power up, driver queues firmware worker thread if the execution environment is PBL. Firmware worker is blocked with a timeout until state worker gets a chance to run and unblock firmware worker. An endpoint power up failure can be seen if state worker gets a chance to run after firmware worker has timed out. Remove this dependency and handle firmware load directly using state worker thread. Signed-off-by: Bhaumik Bhatt Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200521170249.21795-6-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index b0739ad1bae4..8289202b8cbe 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -331,7 +331,6 @@ struct mhi_controller_config { * @wlock: Lock for protecting device wakeup * @mhi_link_info: Device bandwidth info * @st_worker: State transition worker - * @fw_worker: Firmware download worker * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) @@ -412,7 +411,6 @@ struct mhi_controller { spinlock_t wlock; struct mhi_link_info mhi_link_info; struct work_struct st_worker; - struct work_struct fw_worker; struct work_struct syserr_worker; wait_queue_head_t state_event; -- cgit v1.2.3 From bc7ccce5a5192cf277da0aef05e45cd92c81c79a Mon Sep 17 00:00:00 2001 From: Hemant Kumar Date: Thu, 21 May 2020 22:32:44 +0530 Subject: bus: mhi: core: Remove the system error worker thread Remove the system error worker thread and instead have the execution environment worker handle that transition to serialize processing and avoid any possible race conditions during shutdown. Signed-off-by: Hemant Kumar Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200521170249.21795-10-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 8289202b8cbe..c4a940d98912 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -331,7 +331,6 @@ struct mhi_controller_config { * @wlock: Lock for protecting device wakeup * @mhi_link_info: Device bandwidth info * @st_worker: State transition worker - * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) * @wake_get: CB function to assert device wake (optional) @@ -411,7 +410,6 @@ struct mhi_controller { spinlock_t wlock; struct mhi_link_info mhi_link_info; struct work_struct st_worker; - struct work_struct syserr_worker; wait_queue_head_t state_event; void (*status_cb)(struct mhi_controller *mhi_cntrl, -- cgit v1.2.3 From 8786eda9a97763c768e2e81cfd7b4f420281b6e1 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 21 May 2020 13:05:40 -0500 Subject: misc: rtsx: Remove unused pcr_ops Remove the following unused function pointers from struct pcr_ops: int (*set_ltr_latency)(struct rtsx_pcr *pcr, u32 latency); int (*set_l1off_sub)(struct rtsx_pcr *pcr, u8 val); void (*full_on)(struct rtsx_pcr *pcr); void (*power_saving)(struct rtsx_pcr *pcr); Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200521180545.1159896-2-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 65b8142a7fed..df86afb2b4fe 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1080,11 +1080,7 @@ struct pcr_ops { void (*stop_cmd)(struct rtsx_pcr *pcr); void (*set_aspm)(struct rtsx_pcr *pcr, bool enable); - int (*set_ltr_latency)(struct rtsx_pcr *pcr, u32 latency); - int (*set_l1off_sub)(struct rtsx_pcr *pcr, u8 val); void (*set_l1off_cfg_sub_d0)(struct rtsx_pcr *pcr, int active); - void (*full_on)(struct rtsx_pcr *pcr); - void (*power_saving)(struct rtsx_pcr *pcr); void (*enable_ocp)(struct rtsx_pcr *pcr); void (*disable_ocp)(struct rtsx_pcr *pcr); void (*init_ocp)(struct rtsx_pcr *pcr); -- cgit v1.2.3 From 51876e22bf7f8f5d2b9ca7d2b3dcbfaaac2991a9 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 21 May 2020 13:05:41 -0500 Subject: misc: rtsx: Removed unused dev_aspm_mode The struct rtsx_cr_option.dev_aspm_mode member is never set to anything other than DEV_ASPM_DYNAMIC (0). Remove it and code that tests it. No functional change intended. Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200521180545.1159896-3-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index df86afb2b4fe..a75132a0cf8f 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1104,13 +1104,6 @@ enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; #define L1_SNOOZE_TEST_EN BIT(5) #define LTR_L1SS_PWR_GATE_CHECK_CARD_EN BIT(6) -enum dev_aspm_mode { - DEV_ASPM_DYNAMIC, - DEV_ASPM_BACKDOOR, - DEV_ASPM_STATIC, - DEV_ASPM_DISABLE, -}; - /* * struct rtsx_cr_option - card reader option * @dev_flags: device flags @@ -1121,7 +1114,6 @@ enum dev_aspm_mode { * @ltr_active_latency: ltr mode active latency * @ltr_idle_latency: ltr mode idle latency * @ltr_l1off_latency: ltr mode l1off latency - * @dev_aspm_mode: device aspm mode * @l1_snooze_delay: l1 snooze delay * @ltr_l1off_sspwrgate: ltr l1off sspwrgate * @ltr_l1off_snooze_sspwrgate: ltr l1off snooze sspwrgate @@ -1138,7 +1130,6 @@ struct rtsx_cr_option { u32 ltr_active_latency; u32 ltr_idle_latency; u32 ltr_l1off_latency; - enum dev_aspm_mode dev_aspm_mode; u32 l1_snooze_delay; u8 ltr_l1off_sspwrgate; u8 ltr_l1off_snooze_sspwrgate; -- cgit v1.2.3 From 3d1e7aa80d1c0e7ce8313f21c1e9c14a12d3ba48 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 21 May 2020 13:05:43 -0500 Subject: misc: rtsx: Use pcie_capability_clear_and_set_word() for PCI_EXP_LNKCTL Instead of using the driver-specific rtsx_pci_update_cfg_byte() to update the PCIe Link Control Register, use pcie_capability_clear_and_set_word() like the rest of the kernel does. This makes it easier to maintain ASPM across the PCI core and drivers. Remove the now-unused rtsx_pci_update_cfg_byte() and ASPM_MASK_NEG definitions. No functional change intended. Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200521180545.1159896-5-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index a75132a0cf8f..e8780d4e4636 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1307,18 +1307,6 @@ static inline u8 *rtsx_pci_get_cmd_data(struct rtsx_pcr *pcr) return (u8 *)(pcr->host_cmds_ptr); } -static inline int rtsx_pci_update_cfg_byte(struct rtsx_pcr *pcr, int addr, - u8 mask, u8 append) -{ - int err; - u8 val; - - err = pci_read_config_byte(pcr->pci, addr, &val); - if (err < 0) - return err; - return pci_write_config_byte(pcr->pci, addr, (val & mask) | append); -} - static inline void rtsx_pci_write_be32(struct rtsx_pcr *pcr, u16 reg, u32 val) { rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, reg, 0xFF, val >> 24); -- cgit v1.2.3 From d45e3c1a5979efd40dbbac9a5c3586f4fa41f734 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Thu, 7 May 2020 13:33:16 +0100 Subject: PCI: endpoint: Add support to handle multiple base for mapping outbound memory R-Car PCIe controller has support to map multiple memory regions for mapping the outbound memory in local system also the controller limits single allocation for each region (that is, once a chunk is used from the region it cannot be used to allocate a new one). This features inspires to add support for handling multiple memory bases in endpoint framework. With this patch pci_epc_mem_init() initializes address space for endpoint controller which support single window and pci_epc_multi_mem_init() initializes multiple windows supported by endpoint controller. Link: https://lore.kernel.org/r/1588854799-13710-6-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Lad Prabhakar Signed-off-by: Lorenzo Pieralisi Reviewed-by: Yoshihiro Shimoda Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 5bc1de65849e..cc66bec8be90 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -65,20 +65,28 @@ struct pci_epc_ops { struct module *owner; }; +/** + * struct pci_epc_mem_window - address window of the endpoint controller + * @phys_base: physical base address of the PCI address window + * @size: the size of the PCI address window + * @page_size: size of each page + */ +struct pci_epc_mem_window { + phys_addr_t phys_base; + size_t size; + size_t page_size; +}; + /** * struct pci_epc_mem - address space of the endpoint controller - * @phys_base: physical base address of the PCI address space - * @size: the size of the PCI address space + * @window: address window of the endpoint controller * @bitmap: bitmap to manage the PCI address space * @pages: number of bits representing the address region - * @page_size: size of each page * @lock: mutex to protect bitmap */ struct pci_epc_mem { - phys_addr_t phys_base; - size_t size; + struct pci_epc_mem_window window; unsigned long *bitmap; - size_t page_size; int pages; /* mutex to protect against concurrent access for memory allocation*/ struct mutex lock; @@ -89,7 +97,11 @@ struct pci_epc_mem { * @dev: PCI EPC device * @pci_epf: list of endpoint functions present in this EPC device * @ops: function pointers for performing endpoint operations - * @mem: address space of the endpoint controller + * @windows: array of address space of the endpoint controller + * @mem: first window of the endpoint controller, which corresponds to + * default address space of the endpoint controller supporting + * single window. + * @num_windows: number of windows supported by device * @max_functions: max number of functions that can be configured in this EPC * @group: configfs group representing the PCI EPC device * @lock: mutex to protect pci_epc ops @@ -100,7 +112,9 @@ struct pci_epc { struct device dev; struct list_head pci_epf; const struct pci_epc_ops *ops; + struct pci_epc_mem **windows; struct pci_epc_mem *mem; + unsigned int num_windows; u8 max_functions; struct config_group *group; /* mutex to protect against concurrent access of EP controller */ @@ -194,8 +208,9 @@ void pci_epc_put(struct pci_epc *epc); int pci_epc_mem_init(struct pci_epc *epc, phys_addr_t base, size_t size, size_t page_size); -int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size, - size_t page_size); +int pci_epc_multi_mem_init(struct pci_epc *epc, + struct pci_epc_mem_window *window, + unsigned int num_windows); void pci_epc_mem_exit(struct pci_epc *epc); void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, phys_addr_t *phys_addr, size_t size); -- cgit v1.2.3 From 4ffea5e083f8125fe273cf331ecb10d901eb64a2 Mon Sep 17 00:00:00 2001 From: Jonathan Bakker Date: Sat, 16 May 2020 12:47:59 -0700 Subject: regulator: max8998: Add charger regulator The max8998 has a current regulator for charging control. The charger driver in drivers/power/supply/max8998_charger.c has a comment in it stating that 'charger control is done by a current regulator "CHARGER"', but this regulator was never added until now. The current values have been extracted from a downstream driver for the SGH-T959V. Signed-off-by: Jonathan Bakker Link: https://lore.kernel.org/r/BN6PR04MB0660E1F4A3D5A348BE88311CA3BA0@BN6PR04MB0660.namprd04.prod.outlook.com Signed-off-by: Mark Brown --- include/linux/mfd/max8998.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index 061af220dcd3..79c020bd0c70 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -39,6 +39,7 @@ enum { MAX8998_ENVICHG, MAX8998_ESAFEOUT1, MAX8998_ESAFEOUT2, + MAX8998_CHARGER, }; /** -- cgit v1.2.3 From 9398554fb3979852512ff4f1405e759889b45c16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 May 2020 14:36:00 +0200 Subject: block: remove the error_sector argument to blkdev_issue_flush The argument isn't used by any caller, and drivers don't fill out bi_sector for flush requests either. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2b33166b9daf..7d10f4e63232 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1233,7 +1233,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) extern void blk_io_schedule(void); -extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); +int blkdev_issue_flush(struct block_device *, gfp_t); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); @@ -1872,8 +1872,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) return false; } -static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, - sector_t *error_sector) +static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) { return 0; } -- cgit v1.2.3 From ab91c2a89f86be2898cee208d492816ec238b2cf Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 8 May 2020 11:38:26 -0500 Subject: tpm: eventlog: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. Also, the following issue shows up due to the flexible-array member having incomplete type[4]: drivers/char/tpm/eventlog/tpm2.c: In function ‘tpm2_bios_measurements_start’: drivers/char/tpm/eventlog/tpm2.c:54:46: error: invalid application of ‘sizeof’ to incomplete type ‘u8[]’ {aka ‘unsigned char[]’} 54 | size = sizeof(struct tcg_pcr_event) - sizeof(event_header->event) | ^ drivers/char/tpm/eventlog/tpm2.c: In function ‘tpm2_bios_measurements_next’: drivers/char/tpm/eventlog/tpm2.c:102:10: error: invalid application of ‘sizeof’ to incomplete type ‘u8[]’ {aka ‘unsigned char[]’} 102 | sizeof(event_header->event) + event_header->event_size; | ^ drivers/char/tpm/eventlog/tpm2.c: In function ‘tpm2_binary_bios_measurements_show’: drivers/char/tpm/eventlog/tpm2.c:140:10: error: invalid application of ‘sizeof’ to incomplete type ‘u8[]’ {aka ‘unsigned char[]’} 140 | sizeof(event_header->event) + event_header->event_size; | ^ scripts/Makefile.build:266: recipe for target 'drivers/char/tpm/eventlog/tpm2.o' failed make[3]: *** [drivers/char/tpm/eventlog/tpm2.o] Error 1 As mentioned above: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] As in "sizeof(event_header->event) always evaluated to 0, so removing it has no effect". Lastly, make use of the struct_size() helper to deal with the flexible array member and its host structure. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") [4] https://github.com/KSPP/linux/issues/43 Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm_eventlog.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index c253461b1c4e..4f8c90c93c29 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -97,7 +97,7 @@ struct tcg_pcr_event { u32 event_type; u8 digest[20]; u32 event_size; - u8 event[0]; + u8 event[]; } __packed; struct tcg_event_field { -- cgit v1.2.3 From 8eb613c0b8f19627ba1846dcf78bb2c85edbe8dd Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Sun, 3 May 2020 01:00:02 -0400 Subject: ima: verify mprotect change is consistent with mmap policy Files can be mmap'ed read/write and later changed to execute to circumvent IMA's mmap appraise policy rules. Due to locking issues (mmap semaphore would be taken prior to i_mutex), files can not be measured or appraised at this point. Eliminate this integrity gap, by denying the mprotect PROT_EXECUTE change, if an mmap appraise policy rule exists. On mprotect change success, return 0. On failure, return -EACESS. Reviewed-by: Lakshmi Ramasubramanian Signed-off-by: Mimi Zohar --- include/linux/ima.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index aefe758f4466..9164e1534ec9 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,6 +18,7 @@ extern int ima_file_check(struct file *file, int mask); extern void ima_post_create_tmpfile(struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); +extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); extern int ima_load_data(enum kernel_load_data_id id); extern int ima_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, @@ -70,6 +71,12 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) return 0; } +static inline int ima_file_mprotect(struct vm_area_struct *vma, + unsigned long prot) +{ + return 0; +} + static inline int ima_load_data(enum kernel_load_data_id id) { return 0; -- cgit v1.2.3 From d3e81989c0f028aa80cb97fcba83df40585b640d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:53:01 -0500 Subject: treewide: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Li Yang --- include/linux/fsl/bestcomm/bestcomm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsl/bestcomm/bestcomm.h b/include/linux/fsl/bestcomm/bestcomm.h index a0e2e6b19b57..154e541ce57e 100644 --- a/include/linux/fsl/bestcomm/bestcomm.h +++ b/include/linux/fsl/bestcomm/bestcomm.h @@ -27,7 +27,7 @@ */ struct bcom_bd { u32 status; - u32 data[0]; /* variable payload size */ + u32 data[]; /* variable payload size */ }; /* ======================================================================== */ -- cgit v1.2.3 From 17d00e839d3b592da9659c1977d45f85b77f986a Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 27 Dec 2019 07:01:53 +0200 Subject: net/mlx5: Add command entry handling completion When FW response to commands is very slow and all command entries in use are waiting for completion we can have a race where commands can get timeout before they get out of the queue and handled. Timeout completion on uninitialized command will cause releasing command's buffers before accessing it for initialization and then we will get NULL pointer exception while trying access it. It may also cause releasing buffers of another command since we may have timeout completion before even allocating entry index for this command. Add entry handling completion to avoid this race. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Moshe Shemesh Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6f8f79ef829b..9b1f29f26c27 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -743,6 +743,7 @@ struct mlx5_cmd_work_ent { struct delayed_work cb_timeout_work; void *context; int idx; + struct completion handling; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; -- cgit v1.2.3 From d43b7007dbd1195a5b6b83213e49b1516aaf6f5e Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 18 Mar 2020 21:44:32 +0200 Subject: net/mlx5: Fix a race when moving command interface to events mode After driver creates (via FW command) an EQ for commands, the driver will be informed on new commands completion by EQE. However, due to a race in driver's internal command mode metadata update, some new commands will still be miss-handled by driver as if we are in polling mode. Such commands can get two non forced completion, leading to already freed command entry access. CREATE_EQ command, that maps EQ to the command queue must be posted to the command queue while it is empty and no other command should be posted. Add SW mechanism that once the CREATE_EQ command is about to be executed, all other commands will return error without being sent to the FW. Allow sending other commands only after successfully changing the driver's internal command mode metadata. We can safely return error to all other commands while creating the command EQ, as all other commands might be sent from the user/application during driver load. Application can rerun them later after driver's load was finished. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Eran Ben Elisha Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9b1f29f26c27..c03778c75dfa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -284,6 +284,7 @@ struct mlx5_cmd { struct semaphore sem; struct semaphore pages_sem; int mode; + u16 allowed_opcode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; struct dma_pool *pool; struct mlx5_cmd_debug dbg; @@ -875,10 +876,15 @@ mlx5_frag_buf_get_idx_last_contig_stride(struct mlx5_frag_buf_ctrl *fbc, u32 ix) return min_t(u32, last_frag_stride_idx - fbc->strides_offset, fbc->sz_m1); } +enum { + CMD_ALLOWED_OPCODE_ALL, +}; + int mlx5_cmd_init(struct mlx5_core_dev *dev); void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); +void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode); struct mlx5_async_ctx { struct mlx5_core_dev *dev; -- cgit v1.2.3 From f7936ddd35d8b849daf0372770c7c9dbe7910fca Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 19 Mar 2020 21:43:13 +0200 Subject: net/mlx5: Avoid processing commands before cmdif is ready When driver is reloading during recovery flow, it can't get new commands till command interface is up again. Otherwise we may get to null pointer trying to access non initialized command structures. Add cmdif state to avoid processing commands while cmdif is not ready. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Eran Ben Elisha Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c03778c75dfa..8397b6558dc7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -213,6 +213,12 @@ enum mlx5_port_status { MLX5_PORT_DOWN = 2, }; +enum mlx5_cmdif_state { + MLX5_CMDIF_STATE_UNINITIALIZED, + MLX5_CMDIF_STATE_UP, + MLX5_CMDIF_STATE_DOWN, +}; + struct mlx5_cmd_first { __be32 data[4]; }; @@ -258,6 +264,7 @@ struct mlx5_cmd_stats { struct mlx5_cmd { struct mlx5_nb nb; + enum mlx5_cmdif_state state; void *cmd_alloc_buf; dma_addr_t alloc_dma; int alloc_size; @@ -882,6 +889,8 @@ enum { int mlx5_cmd_init(struct mlx5_core_dev *dev); void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); +void mlx5_cmd_set_state(struct mlx5_core_dev *dev, + enum mlx5_cmdif_state cmdif_state); void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode); -- cgit v1.2.3 From 65ece6de0114fc84fbc0487bf68cae91d535dd78 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 Apr 2020 11:50:49 +0200 Subject: virtchnl: Add missing explicit padding to structures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On e.g. m68k, the alignment of 32-bit values is only 2 bytes, leading to the following: ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:577:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:577:32: error: enumerator value for ‘virtchnl_static_assert_virtchnl_filter’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); ^~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:619:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_pf_event); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:619:31: error: enumerator value for ‘virtchnl_static_assert_virtchnl_pf_event’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_pf_event); ^~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:640:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:640:31: error: enumerator value for ‘virtchnl_static_assert_virtchnl_iwarp_qv_info’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); ^~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:647:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_iwarp_qvlist_info); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:647:31: error: enumerator value for ‘virtchnl_static_assert_virtchnl_iwarp_qvlist_info’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_iwarp_qvlist_info); ^~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ Fix this by adding explicit padding to structures with holes. Reported-by: Signed-off-by: Geert Uytterhoeven Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index ca956b672ac0..40bad71865ea 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -476,6 +476,7 @@ struct virtchnl_rss_key { u16 vsi_id; u16 key_len; u8 key[1]; /* RSS hash key, packed bytes */ + u8 pad[1]; }; VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); @@ -484,6 +485,7 @@ struct virtchnl_rss_lut { u16 vsi_id; u16 lut_entries; u8 lut[1]; /* RSS lookup table */ + u8 pad[1]; }; VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); @@ -572,6 +574,7 @@ struct virtchnl_filter { enum virtchnl_action action; u32 action_meta; u8 field_flags; + u8 pad[3]; }; VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); @@ -610,6 +613,7 @@ struct virtchnl_pf_event { /* link_speed provided in Mbps */ u32 link_speed; u8 link_status; + u8 pad[3]; } link_event_adv; } event_data; @@ -635,6 +639,7 @@ struct virtchnl_iwarp_qv_info { u16 ceq_idx; u16 aeq_idx; u8 itr_idx; + u8 pad[3]; }; VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); -- cgit v1.2.3 From afaa33da08abd10be8978781d7c99a9e67d2bbff Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Fri, 22 May 2020 19:19:01 +0200 Subject: Drivers: hv: vmbus: Resolve more races involving init_vp_index() init_vp_index() uses the (per-node) hv_numa_map[] masks to record the CPUs allocated for channel interrupts at a given time, and distribute the performance-critical channels across the available CPUs: in part., the mask of "candidate" target CPUs in a given NUMA node, for a newly offered channel, is determined by XOR-ing the node's CPU mask and the node's hv_numa_map. This operation/mechanism assumes that no offline CPUs is set in the hv_numa_map mask, an assumption that does not hold since such mask is currently not updated when a channel is removed or assigned to a different CPU. To address the issues described above, this adds hooks in the channel removal path (hv_process_channel_removal()) and in target_cpu_store() in order to clear, resp. to update, the hv_numa_map[] masks as needed. This also adds a (missed) update of the masks in init_vp_index() (cf., e.g., the memory-allocation failure path in this function). Like in the case of init_vp_index(), such hooks require to determine if the given channel is performance critical. init_vp_index() does this by parsing the channel's offer, it can not rely on the device data structure (device_obj) to retrieve such information because the device data structure has not been allocated/linked with the channel by the time that init_vp_index() executes. A similar situation may hold in hv_is_alloced_cpu() (defined below); the adopted approach is to "cache" the device type of the channel, as computed by parsing the channel's offer, in the channel structure itself. Fixes: 7527810573436f ("Drivers: hv: vmbus: Introduce the CHANNELMSG_MODIFYCHANNEL message type") Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20200522171901.204127-3-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index d783847d8cb4..40df3103e890 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -901,6 +901,13 @@ struct vmbus_channel { bool probe_done; + /* + * Cache the device ID here for easy access; this is useful, in + * particular, in situations where the channel's device_obj has + * not been allocated/initialized yet. + */ + u16 device_id; + /* * We must offload the handling of the primary/sub channels * from the single-threaded vmbus_connection.work_queue to -- cgit v1.2.3 From cd16627fc0468564fdd60f20ad52420b87195127 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sat, 23 May 2020 15:27:10 +0200 Subject: net: devres: provide devm_register_netdev() Provide devm_register_netdev() - a device resource managed variant of register_netdev(). This new helper will only work for net_device structs that are also already managed by devres. Signed-off-by: Bartosz Golaszewski 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 a18f8fdf4260..1a96e9c4ec36 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4280,6 +4280,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, int register_netdev(struct net_device *dev); void unregister_netdev(struct net_device *dev); +int devm_register_netdev(struct device *dev, struct net_device *ndev); + /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); -- cgit v1.2.3 From 1f1ec622623fe8e49a1036d4127b895a0f0e2c43 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 5 May 2020 12:13:35 +0200 Subject: mtd: rawnand: Propage CS selection to sub operations Some controller using the instruction parse infrastructure might need to know which CS a specific sub-operation is targeting. Let's propagate this information. Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200505101353.1776394-2-boris.brezillon@collabora.com --- include/linux/mtd/rawnand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 0f45b6984ad1..a3bac8824937 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -709,6 +709,7 @@ struct nand_op_instr { /** * struct nand_subop - a sub operation + * @cs: the CS line to select for this NAND sub-operation * @instrs: array of instructions * @ninstrs: length of the @instrs array * @first_instr_start_off: offset to start from for the first instruction @@ -724,6 +725,7 @@ struct nand_op_instr { * controller driver. */ struct nand_subop { + unsigned int cs; const struct nand_op_instr *instrs; unsigned int ninstrs; unsigned int first_instr_start_off; -- cgit v1.2.3 From c8ae3f744ddca0da164bcacee42d1d4b6fe7027d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 09:45:42 +0200 Subject: lib/bch: Rework a little bit the exported function names There are four exported functions, all suffixed by _bch, which is clearly not the norm. Let's rename them by prefixing them with bch_ instead. This is a mechanical change: init_bch -> bch_init free_bch -> bch_free encode_bch -> bch_encode decode_bch -> bch_decode Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200519074549.23673-2-miquel.raynal@bootlin.com --- include/linux/bch.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bch.h b/include/linux/bch.h index aa765af85c38..9c35e7cd5890 100644 --- a/include/linux/bch.h +++ b/include/linux/bch.h @@ -53,14 +53,14 @@ struct bch_control { struct gf_poly *poly_2t[4]; }; -struct bch_control *init_bch(int m, int t, unsigned int prim_poly); +struct bch_control *bch_init(int m, int t, unsigned int prim_poly); -void free_bch(struct bch_control *bch); +void bch_free(struct bch_control *bch); -void encode_bch(struct bch_control *bch, const uint8_t *data, +void bch_encode(struct bch_control *bch, const uint8_t *data, unsigned int len, uint8_t *ecc); -int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len, +int bch_decode(struct bch_control *bch, const uint8_t *data, unsigned int len, const uint8_t *recv_ecc, const uint8_t *calc_ecc, const unsigned int *syn, unsigned int *errloc); -- cgit v1.2.3 From 1759279ad138cb0a903224a89f4bf40f69c417e8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 09:45:43 +0200 Subject: lib/bch: Allow easy bit swapping It seems that several hardware ECC engine use a swapped representation of bytes compared to software. This might having to do with how the ECC engine is wired to the NAND controller or the order the bits are passed to the hardware BCH logic. This means that when the software BCH engine is working in conjunction with data generated with hardware, sometimes we might need to swap the bits inside bytes, eg: 0x0A = b0000_1010 -> b0101_0000 = 0x50 Make it possible by adding a boolean to the BCH initialization routine. Regarding the implementation itself, this is a rather simple approach that can probably be enhanced in the future by preparing the ->a_{mod,pow}_tab tables with the swapping in mind. Suggested-by: Boris Brezillon Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200519074549.23673-3-miquel.raynal@bootlin.com --- include/linux/bch.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bch.h b/include/linux/bch.h index 9c35e7cd5890..85fdce83d4e2 100644 --- a/include/linux/bch.h +++ b/include/linux/bch.h @@ -33,6 +33,7 @@ * @cache: log-based polynomial representation buffer * @elp: error locator polynomial * @poly_2t: temporary polynomials of degree 2t + * @swap_bits: swap bits within data and syndrome bytes */ struct bch_control { unsigned int m; @@ -51,9 +52,11 @@ struct bch_control { int *cache; struct gf_poly *elp; struct gf_poly *poly_2t[4]; + bool swap_bits; }; -struct bch_control *bch_init(int m, int t, unsigned int prim_poly); +struct bch_control *bch_init(int m, int t, unsigned int prim_poly, + bool swap_bits); void bch_free(struct bch_control *bch); -- cgit v1.2.3 From d7904619ea0636411f40fb1f34057288c0783ecf Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 09:45:45 +0200 Subject: mtd: rawnand: Add nand_extract_bits() There are cases where ECC bytes are not byte-aligned. Indeed, BCH implies using a number of ECC bits, which are not always a multiple of 8. We then need a helper like nand_extract_bits() to extract these syndromes from a buffer. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200519074549.23673-5-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a3bac8824937..2804c13e5662 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1414,6 +1414,10 @@ int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, void nand_select_target(struct nand_chip *chip, unsigned int cs); void nand_deselect_target(struct nand_chip *chip); +/* Bitops */ +void nand_extract_bits(u8 *dst, unsigned int dst_off, const u8 *src, + unsigned int src_off, unsigned int nbits); + /** * nand_get_data_buf() - Get the internal page buffer * @chip: NAND chip object -- cgit v1.2.3 From 5469fd64efcfbc2b9b2edb92c4f906912736d5b0 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Tue, 5 May 2020 19:46:13 -0700 Subject: usb: gadget: Introduce usb_request->is_last To take advantage of DWC3 internal TRB prefetch and cache for performance, inform the controller the last request with stream_id before switching to a different stream transfer. This allows the controller to maintain its transfer burst within the stream ID. Introduce the usb-request is_last field to help inform the DWC3 controller of this. Signed-off-by: Thinh Nguyen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index e959c09a97c9..281eabae7f33 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -42,6 +42,8 @@ struct usb_ep; * @num_mapped_sgs: number of SG entries mapped to DMA (internal) * @length: Length of that data * @stream_id: The stream id, when USB3.0 bulk streams are being used + * @is_last: Indicates if this is the last request of a stream_id before + * switching to a different stream (required for DWC3 controllers). * @no_interrupt: If true, hints that no completion irq is needed. * Helpful sometimes with deep request queues that are handled * directly by DMA controllers. @@ -104,6 +106,7 @@ struct usb_request { unsigned num_mapped_sgs; unsigned stream_id:16; + unsigned is_last:1; unsigned no_interrupt:1; unsigned zero:1; unsigned short_not_ok:1; -- cgit v1.2.3 From 3c73bc52195def14165c3a7d91bdbb33b51725f5 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Sun, 10 May 2020 13:30:41 +0800 Subject: usb: gadget: core: sync interrupt before unbind the udc The threaded interrupt handler may still be called after the usb_gadget_disconnect is called, it causes the structures used at interrupt handler was freed before it uses, eg the usb_request. This issue usually occurs we remove the udc function during the transfer. Below is the example when doing stress test for android switch function, the EP0's request is freed by .unbind (configfs_composite_unbind -> composite_dev_cleanup), but the threaded handler accesses this request during handling setup packet request. In fact, there is no protection between unbind the udc and udc interrupt handling, so we have to avoid the interrupt handler is occurred or scheduled during the .unbind flow. init: Sending signal 9 to service 'adbd' (pid 18077) process group... android_work: did not send uevent (0 0 000000007bec2039) libprocessgroup: Successfully killed process cgroup uid 0 pid 18077 in 6ms init: Service 'adbd' (pid 18077) received signal 9 init: Sending signal 9 to service 'adbd' (pid 18077) process group... libprocessgroup: Successfully killed process cgroup uid 0 pid 18077 in 0ms init: processing action (init.svc.adbd=stopped) from (/init.usb.configfs.rc:14) init: Received control message 'start' for 'adbd' from pid: 399 (/vendor/bin/hw/android.hardware.usb@1. init: starting service 'adbd'... read descriptors read strings Unable to handle kernel read from unreadable memory at virtual address 000000000000002a android_work: sent uevent USB_STATE=CONNECTED Mem abort info: ESR = 0x96000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=00000000e97f1000 using random self ethernet address [000000000000002a] pgd=0000000000000000 Internal error: Oops: 96000004 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 232 Comm: irq/68-5b110000 Not tainted 5.4.24-06075-g94a6b52b5815 #92 Hardware name: Freescale i.MX8QXP MEK (DT) pstate: 00400085 (nzcv daIf +PAN -UAO) using random host ethernet address pc : composite_setup+0x5c/0x1730 lr : android_setup+0xc0/0x148 sp : ffff80001349bba0 x29: ffff80001349bba0 x28: ffff00083a50da00 x27: ffff8000124e6000 x26: ffff800010177950 x25: 0000000000000040 x24: ffff000834e18010 x23: 0000000000000000 x22: 0000000000000000 x21: ffff00083a50da00 x20: ffff00082e75ec40 x19: 0000000000000000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000001 x11: ffff80001180fb58 x10: 0000000000000040 x9 : ffff8000120fc980 x8 : 0000000000000000 x7 : ffff00083f98df50 x6 : 0000000000000100 x5 : 00000307e8978431 x4 : ffff800011386788 x3 : 0000000000000000 x2 : ffff800012342000 x1 : 0000000000000000 x0 : ffff800010c6d3a0 Call trace: composite_setup+0x5c/0x1730 android_setup+0xc0/0x148 cdns3_ep0_delegate_req+0x64/0x90 cdns3_check_ep0_interrupt_proceed+0x384/0x738 cdns3_device_thread_irq_handler+0x124/0x6e0 cdns3_thread_irq+0x94/0xa0 irq_thread_fn+0x30/0xa0 irq_thread+0x150/0x248 kthread+0xfc/0x128 ret_from_fork+0x10/0x18 Code: 910e8000 f9400693 12001ed7 79400f79 (3940aa61) ---[ end trace c685db37f8773fba ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x0002,20002008 Memory Limit: none Rebooting in 5 seconds.. Reviewed-by: Jun Li Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 281eabae7f33..6a178177e4c9 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -376,6 +376,7 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @irq: the interrupt number for device controller. * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -430,6 +431,7 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + int irq; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) -- cgit v1.2.3 From 5d363120aa548ba52d58907a295eee25f8207ed2 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Mon, 18 May 2020 12:08:45 +0200 Subject: usb: gadget: Fix issue with config_ep_by_speed function This patch adds new config_ep_by_speed_and_alt function which extends the config_ep_by_speed about alt parameter. This additional parameter allows to find proper usb_ss_ep_comp_descriptor. Problem has appeared during testing f_tcm (BOT/UAS) driver function. f_tcm function for SS use array of headers for both BOT/UAS alternate setting: static struct usb_descriptor_header *uasp_ss_function_desc[] = { (struct usb_descriptor_header *) &bot_intf_desc, (struct usb_descriptor_header *) &uasp_ss_bi_desc, (struct usb_descriptor_header *) &bot_bi_ep_comp_desc, (struct usb_descriptor_header *) &uasp_ss_bo_desc, (struct usb_descriptor_header *) &bot_bo_ep_comp_desc, (struct usb_descriptor_header *) &uasp_intf_desc, (struct usb_descriptor_header *) &uasp_ss_bi_desc, (struct usb_descriptor_header *) &uasp_bi_ep_comp_desc, (struct usb_descriptor_header *) &uasp_bi_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_bo_desc, (struct usb_descriptor_header *) &uasp_bo_ep_comp_desc, (struct usb_descriptor_header *) &uasp_bo_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_status_desc, (struct usb_descriptor_header *) &uasp_status_in_ep_comp_desc, (struct usb_descriptor_header *) &uasp_status_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_cmd_desc, (struct usb_descriptor_header *) &uasp_cmd_comp_desc, (struct usb_descriptor_header *) &uasp_cmd_pipe_desc, NULL, }; The first 5 descriptors are associated with BOT alternate setting, and others are associated with UAS. During handling UAS alternate setting f_tcm driver invokes config_ep_by_speed and this function sets incorrect companion endpoint descriptor in usb_ep object. Instead setting ep->comp_desc to uasp_bi_ep_comp_desc function in this case set ep->comp_desc to uasp_ss_bi_desc. This is due to the fact that it searches endpoint based on endpoint address: for_each_ep_desc(speed_desc, d_spd) { chosen_desc = (struct usb_endpoint_descriptor *)*d_spd; if (chosen_desc->bEndpoitAddress == _ep->address) goto ep_found; } And in result it uses the descriptor from BOT alternate setting instead UAS. Finally, it causes that controller driver during enabling endpoints detect that just enabled endpoint for bot. Signed-off-by: Jayshri Pawar Signed-off-by: Pawel Laszczak Signed-off-by: Felipe Balbi --- include/linux/usb/composite.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 8675e145ea8b..2040696d75b6 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -249,6 +249,9 @@ int usb_function_activate(struct usb_function *); int usb_interface_id(struct usb_configuration *, struct usb_function *); +int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f, + struct usb_ep *_ep, u8 alt); + int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); -- cgit v1.2.3 From d031781bdabe1027858a3220f868866586bf6e7c Mon Sep 17 00:00:00 2001 From: Pradeep Kumar Chitrapu Date: Wed, 6 May 2020 03:24:30 -0700 Subject: ieee80211: Fix incorrect mask for default PE duration Fixes bitmask for HE opration's default PE duration. Fixes: daa5b83513a7 ("mac80211: update HE operation fields to D3.0") Signed-off-by: Pradeep Kumar Chitrapu Link: https://lore.kernel.org/r/20200506102430.5153-1-pradeepc@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 16268ef1cbcc..5d3e48d02033 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2047,7 +2047,7 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) } /* HE Operation defines */ -#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000003 +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x00003ff0 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 4 -- cgit v1.2.3 From eb012d125a2419786f5bcaaf8a901babc7b6e3d7 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 25 May 2020 00:32:43 +0900 Subject: printk: Remove pr_cont_once() pr_cont_once() does not make sense; at least emitting module name using pr_fmt() into middle of a line (after e.g. pr_info_once()) does not make sense. Let's remove unused pr_cont_once(). Link: https://lore.kernel.org/r/20200524153243.11690-1-penguin-kernel@I-love.SAKURA.ne.jp Cc: Joe Perches Signed-off-by: Tetsuo Handa Acked-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index e061635e0409..07f2d08f79ff 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -384,8 +384,7 @@ extern int kptr_restrict; printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_once(fmt, ...) \ printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -#define pr_cont_once(fmt, ...) \ - printk_once(KERN_CONT pr_fmt(fmt), ##__VA_ARGS__) +/* no pr_cont_once, don't do that... */ #if defined(DEBUG) #define pr_devel_once(fmt, ...) \ -- cgit v1.2.3 From 551cb86cbb7d85a3d16d10f6fb4fb954f13a7556 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 19 May 2020 16:12:33 +0300 Subject: gpio: dwapb: Remove unneeded has_irq member in struct dwapb_port_property has_irq member of struct dwapb_port_property is used only in one place, so, make it local test instead and remove from the structure. This local test is using memchr_inv() which is quite efficient in comparison to the original loop and possible little overhead can be neglected. Signed-off-by: Andy Shevchenko Tested-by: Serge Semin Acked-by: Lee Jones Acked-by: Serge Semin Link: https://lore.kernel.org/r/20200519131233.59032-4-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-dwapb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h index 3c606c450d05..ff1be737bad6 100644 --- a/include/linux/platform_data/gpio-dwapb.h +++ b/include/linux/platform_data/gpio-dwapb.h @@ -12,7 +12,6 @@ struct dwapb_port_property { unsigned int ngpio; unsigned int gpio_base; int irq[32]; - bool has_irq; bool irq_shared; }; -- cgit v1.2.3 From 1072c12d7d58b5512b6c05c2268f57d32f1ab76c Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 16 Apr 2020 14:46:11 -0700 Subject: block: add bio_for_each_bvec_all() An upcoming Btrfs fix needs to know the original size of a non-cloned bios. Rather than accessing the bvec table directly, let's add a bio_for_each_bvec_all() accessor. Reviewed-by: Johannes Thumshirn Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- include/linux/bio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a0ee494a6329..8e23f51ccfa4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -169,6 +169,14 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) +/* + * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the + * same reasons as bio_for_each_segment_all(). + */ +#define bio_for_each_bvec_all(bvl, bio, i) \ + for (i = 0, bvl = bio_first_bvec_all(bio); \ + i < (bio)->bi_vcnt; i++, bvl++) \ + #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) -- cgit v1.2.3 From d85dc2e116fdce776280224ed2bee4c78e5e5af2 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Fri, 30 Aug 2019 12:09:24 -0500 Subject: fs: export generic_file_buffered_read() Export generic_file_buffered_read() to be used to supplement incomplete direct reads. Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..366c533d30cd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3124,6 +3124,8 @@ extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *count, unsigned int flags); +extern ssize_t generic_file_buffered_read(struct kiocb *iocb, + struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From 8cecd0ba854799cda72d03a470e7de9eed3ed6c4 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Tue, 14 May 2019 18:54:27 -0500 Subject: iomap: add a filesystem hook for direct I/O bio submission This helps filesystems to perform tasks on the bio while submitting for I/O. This could be post-write operations such as data CRC or data replication for fs-handled RAID. Reviewed-by: Johannes Thumshirn Reviewed-by: Nikolay Borisov Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Goldwyn Rodrigues Signed-off-by: David Sterba --- include/linux/iomap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..5b4875344874 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -252,6 +252,8 @@ int iomap_writepages(struct address_space *mapping, struct iomap_dio_ops { int (*end_io)(struct kiocb *iocb, ssize_t size, int error, unsigned flags); + blk_qc_t (*submit_io)(struct inode *inode, struct iomap *iomap, + struct bio *bio, loff_t file_offset); }; ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, -- cgit v1.2.3 From 4c559f15efcc43b996f4da528cd7f9483aaca36d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 14 May 2020 14:14:23 +0200 Subject: netfilter: nf_conntrack_pptp: prevent buffer overflows in debug code Dan Carpenter says: "Smatch complains that the value for "cmd" comes from the network and can't be trusted." Add pptp_msg_name() helper function that checks for the array boundary. Fixes: f09943fefe6b ("[NETFILTER]: nf_conntrack/nf_nat: add PPTP helper port") Reported-by: Dan Carpenter Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_pptp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index fcc409de31a4..6a4ff6d5ebc2 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -10,7 +10,7 @@ #include #include -extern const char *const pptp_msg_name[]; +extern const char *const pptp_msg_name(u_int16_t msg); /* state of the control session */ enum pptp_ctrlsess_state { -- cgit v1.2.3 From cea0fad0f8b41481c0052a1f30d296d6d6dd0b2e Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Thu, 30 Apr 2020 15:52:24 +0200 Subject: mailmap: change email for Ricardo Ribalda Modify emails to ribalda@kernel.org and unify my surname in all the files. Signed-off-by: Ricardo Ribalda Link: https://lore.kernel.org/r/20200430135224.362700-1-ricardo@ribalda.com Signed-off-by: Jonathan Corbet --- include/linux/platform_data/ad5761.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ad5761.h b/include/linux/platform_data/ad5761.h index 02bef5177ff5..69e261e2ca14 100644 --- a/include/linux/platform_data/ad5761.h +++ b/include/linux/platform_data/ad5761.h @@ -3,7 +3,7 @@ * AD5721, AD5721R, AD5761, AD5761R, Voltage Output Digital to Analog Converter * * Copyright 2016 Qtechnology A/S - * 2016 Ricardo Ribalda + * 2016 Ricardo Ribalda */ #ifndef __LINUX_PLATFORM_DATA_AD5761_H__ #define __LINUX_PLATFORM_DATA_AD5761_H__ -- cgit v1.2.3 From 11399346ac39a26ade2a90303d38ad318163c665 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:00:33 -0500 Subject: mtd: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Acked-by: Miquel Raynal Signed-off-by: Vignesh Raghavendra Link: https://lore.kernel.org/r/20200507190033.GA15215@embeddedor --- include/linux/mtd/cfi.h | 6 +++--- include/linux/mtd/qinfo.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index c98a21108688..fd1ecb821106 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -138,7 +138,7 @@ struct cfi_ident { uint16_t InterfaceDesc; uint16_t MaxBufWriteSize; uint8_t NumEraseRegions; - uint32_t EraseRegionInfo[0]; /* Not host ordered */ + uint32_t EraseRegionInfo[]; /* Not host ordered */ } __packed; /* Extended Query Structure for both PRI and ALT */ @@ -165,7 +165,7 @@ struct cfi_pri_intelext { uint16_t ProtRegAddr; uint8_t FactProtRegSize; uint8_t UserProtRegSize; - uint8_t extra[0]; + uint8_t extra[]; } __packed; struct cfi_intelext_otpinfo { @@ -286,7 +286,7 @@ struct cfi_private { map_word sector_erase_cmd; unsigned long chipshift; /* Because they're of the same type */ const char *im_name; /* inter_module name for cmdset_setup */ - struct flchip chips[0]; /* per-chip data structure for each chip */ + struct flchip chips[]; /* per-chip data structure for each chip */ }; uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, diff --git a/include/linux/mtd/qinfo.h b/include/linux/mtd/qinfo.h index df5b9fddea16..2e3f43788d48 100644 --- a/include/linux/mtd/qinfo.h +++ b/include/linux/mtd/qinfo.h @@ -24,7 +24,7 @@ struct lpddr_private { struct qinfo_chip *qinfo; int numchips; unsigned long chipshift; - struct flchip chips[0]; + struct flchip chips[]; }; /* qinfo_query_info structure contains request information for -- cgit v1.2.3 From 06081646450e46efcc1ca58c3b227bd60083cd3e Mon Sep 17 00:00:00 2001 From: Saravanan Sekar Date: Tue, 26 May 2020 11:06:42 +0200 Subject: mfd: mp2629: Add support for mps battery charger mp2629 is a highly-integrated switching-mode battery charge management device for single-cell Li-ion or Li-polymer battery. Add MFD core enables chip access for ADC driver for battery readings, and a power supply battery-charger driver Signed-off-by: Saravanan Sekar Reviewed-by: Andy Shevchenko Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/mp2629.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/mfd/mp2629.h (limited to 'include/linux') diff --git a/include/linux/mfd/mp2629.h b/include/linux/mfd/mp2629.h new file mode 100644 index 000000000000..baaeeaf82949 --- /dev/null +++ b/include/linux/mfd/mp2629.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2020 Monolithic Power Systems, Inc + */ + +#ifndef __MP2629_H__ +#define __MP2629_H__ + +#include +#include + +struct mp2629_data { + struct device *dev; + struct regmap *regmap; +}; + +#endif -- cgit v1.2.3 From 7abd9fb6468225f5c7f83149ce279cc1a912a68a Mon Sep 17 00:00:00 2001 From: Saravanan Sekar Date: Tue, 26 May 2020 11:06:43 +0200 Subject: iio: adc: mp2629: Add support for mp2629 ADC driver Add support for 8-bit resolution ADC readings for input power supply and battery charging measurement. Provides voltage, current readings to mp2629 power supply driver. Signed-off-by: Saravanan Sekar Reviewed-by: Andy Shevchenko Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/mp2629.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mp2629.h b/include/linux/mfd/mp2629.h index baaeeaf82949..89b706900b57 100644 --- a/include/linux/mfd/mp2629.h +++ b/include/linux/mfd/mp2629.h @@ -14,4 +14,13 @@ struct mp2629_data { struct regmap *regmap; }; +enum mp2629_adc_chan { + MP2629_BATT_VOLT, + MP2629_SYSTEM_VOLT, + MP2629_INPUT_VOLT, + MP2629_BATT_CURRENT, + MP2629_INPUT_CURRENT, + MP2629_ADC_CHAN_END +}; + #endif -- cgit v1.2.3 From 9aa8759960e36291e7663288d58b47ee4927b6f5 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Sat, 16 May 2020 14:06:08 +0300 Subject: mfd: Constify properties in mfd_cell Constify 'struct property_entry *properties' in mfd_cell. It is always passed around as a pointer const struct. Signed-off-by: Tomas Winkler Signed-off-by: Lee Jones --- include/linux/mfd/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index d01d1299e49d..7e5ac3c00891 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -70,7 +70,7 @@ struct mfd_cell { size_t pdata_size; /* device properties passed to the sub devices drivers */ - struct property_entry *properties; + const struct property_entry *properties; /* * Device Tree compatible string -- cgit v1.2.3 From 97eda5dcc2cde5dcc778bef7a9344db3b6bf8ef5 Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Wed, 22 Apr 2020 11:08:33 +0200 Subject: mfd: stmfx: Disable IRQ in suspend to avoid spurious interrupt When STMFX supply is stopped, spurious interrupt can occur. To avoid that, disable the interrupt in suspend before disabling the regulator and re-enable it at the end of resume. Fixes: 06252ade9156 ("mfd: Add ST Multi-Function eXpander (STMFX) core driver") Signed-off-by: Amelie Delaunay Signed-off-by: Lee Jones --- include/linux/mfd/stmfx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stmfx.h b/include/linux/mfd/stmfx.h index 3c67983678ec..744dce63946e 100644 --- a/include/linux/mfd/stmfx.h +++ b/include/linux/mfd/stmfx.h @@ -109,6 +109,7 @@ struct stmfx { struct device *dev; struct regmap *map; struct regulator *vdd; + int irq; struct irq_domain *irq_domain; struct mutex lock; /* IRQ bus lock */ u8 irq_src; -- cgit v1.2.3 From aaf2bc50df1f4bfc6857fc601fc7b21d5a18c6a1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 21 May 2020 22:05:15 +0200 Subject: rcu: Abstract out rcu_irq_enter_check_tick() from rcu_nmi_enter() There will likely be exception handlers that can sleep, which rules out the usual approach of invoking rcu_nmi_enter() on entry and also rcu_nmi_exit() on all exit paths. However, the alternative approach of just not calling anything can prevent RCU from coaxing quiescent states from nohz_full CPUs that are looping in the kernel: RCU must instead IPI them explicitly. It would be better to enable the scheduler tick on such CPUs to interact with RCU in a lighter-weight manner, and this enabling is one of the things that rcu_nmi_enter() currently does. What is needed is something that helps RCU coax quiescent states while not preventing subsequent sleeps. This commit therefore splits out the nohz_full scheduler-tick enabling from the rest of the rcu_nmi_enter() logic into a new function named rcu_irq_enter_check_tick(). [ tglx: Renamed the function and made it a nop when context tracking is off ] [ mingo: Fixed a CONFIG_NO_HZ_FULL assumption, harmonized and fixed all the comment blocks and cleaned up rcu_nmi_enter()/exit() definitions. ] Suggested-by: Andy Lutomirski Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200521202116.996113173@linutronix.de --- include/linux/hardirq.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 621556efe45f..e07cf853aa16 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -2,31 +2,28 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H +#include #include #include #include #include #include - extern void synchronize_irq(unsigned int irq); extern bool synchronize_hardirq(unsigned int irq); -#if defined(CONFIG_TINY_RCU) - -static inline void rcu_nmi_enter(void) -{ -} +#ifdef CONFIG_NO_HZ_FULL +void __rcu_irq_enter_check_tick(void); +#else +static inline void __rcu_irq_enter_check_tick(void) { } +#endif -static inline void rcu_nmi_exit(void) +static __always_inline void rcu_irq_enter_check_tick(void) { + if (context_tracking_enabled()) + __rcu_irq_enter_check_tick(); } -#else -extern void rcu_nmi_enter(void); -extern void rcu_nmi_exit(void); -#endif - /* * It is safe to do non-atomic ops on ->hardirq_context, * because NMI handlers may not preempt and the ops are @@ -65,6 +62,14 @@ extern void irq_exit(void); #define arch_nmi_exit() do { } while (0) #endif +#ifdef CONFIG_TINY_RCU +static inline void rcu_nmi_enter(void) { } +static inline void rcu_nmi_exit(void) { } +#else +extern void rcu_nmi_enter(void); +extern void rcu_nmi_exit(void); +#endif + /* * NMI vs Tracing * -------------- -- cgit v1.2.3 From 07325d4a90d2d84de45cc07b134fd0f023dbb971 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:16 +0200 Subject: rcu: Provide rcu_irq_exit_check_preempt() Provide a debug check which can be invoked from exception return to kernel mode before an attempt is made to schedule. Warn if RCU is not ready for this. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Cc: Paul E. McKenney Link: https://lore.kernel.org/r/20200521202117.089709607@linutronix.de --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index c869fb20cc51..8512caeb7682 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -72,6 +72,7 @@ static inline void rcu_irq_exit_irqson(void) { } static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } static inline void rcu_irq_exit_preempt(void) { } +static inline void rcu_irq_exit_check_preempt(void) { } static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 9366fa4d0717..d5cc9d675987 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -51,6 +51,12 @@ void rcu_irq_exit_preempt(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); +#ifdef CONFIG_PROVE_RCU +void rcu_irq_exit_check_preempt(void); +#else +static inline void rcu_irq_exit_check_preempt(void) { } +#endif + void exit_rcu(void); void rcu_scheduler_starting(void); -- cgit v1.2.3 From 46d26819a5056f4831649c5887ad5c71a16d86f7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 24 May 2020 17:30:40 +0200 Subject: software node: implement software_node_unregister() Sometimes it is better to unregister individual nodes instead of trying to do them all at once with software_node_unregister_nodes(), so create software_node_unregister() so that you can unregister them one at a time. This is especially important when creating nodes in a hierarchy, with parent -> children representations. Children always need to be removed before a parent is, as the swnode logic assumes this is going to be the case. Fix up the lib/test_printf.c fwnode_pointer() test which to use this new function as it had the problem of tearing things down in the backwards order. Fixes: f1ce39df508d ("lib/test_printf: Add tests for %pfw printk modifier") Cc: stable Cc: Andy Shevchenko Cc: Brendan Higgins Cc: Dmitry Torokhov Cc: Petr Mladek Cc: Rafael J. Wysocki Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Sergey Senozhatsky Cc: Steven Rostedt Reported-by: Naresh Kamboju Reported-by: kernel test robot Reported-by: Randy Dunlap Tested-by: Petr Mladek Tested-by: Randy Dunlap Tested-by: Guenter Roeck Reviewed-by: Heikki Krogerus Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20200524153041.2361-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index d86de017c689..0d4099b4ce1f 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -441,6 +441,7 @@ int software_node_register_nodes(const struct software_node *nodes); void software_node_unregister_nodes(const struct software_node *nodes); int software_node_register(const struct software_node *node); +void software_node_unregister(const struct software_node *node); int software_node_notify(struct device *dev, unsigned long action); -- cgit v1.2.3 From ff937b916eb6316fe4644564a572ed3b5867bc1f Mon Sep 17 00:00:00 2001 From: Yuval Basson Date: Tue, 26 May 2020 09:41:20 +0300 Subject: qed: Add EDPM mode type for user-fw compatibility In older FW versions the completion flag was treated as the ack flag in edpm messages. Expose the FW option of setting which mode the QP is in by adding a flag to the qedr <-> qed API. Flag is added for backward compatibility with libqedr. This flag will be set by qedr after determining whether the libqedr is using the updated version. Fixes: f10939403352 ("qed: Add support for QP verbs") Signed-off-by: Yuval Basson Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_rdma_if.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index f93edd5750a5..584077565f12 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -335,6 +335,9 @@ struct qed_rdma_create_qp_in_params { u16 xrcd_id; u8 stats_queue; enum qed_rdma_qp_type qp_type; + u8 flags; +#define QED_ROCE_EDPM_MODE_MASK 0x1 +#define QED_ROCE_EDPM_MODE_SHIFT 0 }; struct qed_rdma_create_qp_out_params { -- cgit v1.2.3 From 90ce665c6a40dc1be771bf5f86e624c0acf3a76f Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 26 May 2020 16:29:36 +0100 Subject: net: mdiobus: add clause 45 mdiobus accessors There is a recurring pattern throughout some of the PHY code converting a devad and regnum to our packed clause 45 representation. Rather than having this scattered around the code, let's put a common translation function in mdio.h, and provide some register accessors. Convert the phylib core, phylink, bcm87xx and cortina to use these. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 31 +++++++++++++++++++++++++++++++ include/linux/phy.h | 6 ------ 2 files changed, 31 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 917e4bb2ed71..36d2e0673d03 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -9,6 +9,13 @@ #include #include +/* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit + * IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. + */ +#define MII_ADDR_C45 (1<<30) +#define MII_DEVADDR_C45_SHIFT 16 +#define MII_REGADDR_C45_MASK GENMASK(15, 0) + struct gpio_desc; struct mii_bus; @@ -326,6 +333,30 @@ int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); +static inline u32 mdiobus_c45_addr(int devad, u16 regnum) +{ + return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; +} + +static inline int __mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, + u16 regnum) +{ + return __mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); +} + +static inline int __mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, + u16 regnum, u16 val) +{ + return __mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), + val); +} + +static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, + u16 regnum) +{ + return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); diff --git a/include/linux/phy.h b/include/linux/phy.h index 2bcdf19ed3b4..6d256e720a66 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -209,12 +209,6 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_BUS_ID_SIZE 61 -/* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit - IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */ -#define MII_ADDR_C45 (1<<30) -#define MII_DEVADDR_C45_SHIFT 16 -#define MII_REGADDR_C45_MASK GENMASK(15, 0) - struct device; struct phylink; struct sfp_bus; -- cgit v1.2.3 From 6dd912f82680761d8fb6b1bb274a69d4c7010988 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 25 May 2020 15:07:40 -0400 Subject: net: check untrusted gso_size at kernel entry Syzkaller again found a path to a kernel crash through bad gso input: a packet with gso size exceeding len. These packets are dropped in tcp_gso_segment and udp[46]_ufo_fragment. But they may affect gso size calculations earlier in the path. Now that we have thlen as of commit 9274124f023b ("net: stricter validation of untrusted gso packets"), check gso_size at entry too. Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.") Reported-by: syzbot Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 6f6ade63b04c..88997022a4b5 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -31,6 +31,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, { unsigned int gso_type = 0; unsigned int thlen = 0; + unsigned int p_off = 0; unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { @@ -68,7 +69,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; - if (skb_transport_offset(skb) + thlen > skb_headlen(skb)) + p_off = skb_transport_offset(skb) + thlen; + if (p_off > skb_headlen(skb)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. @@ -92,17 +94,25 @@ retry: return -EINVAL; } - if (keys.control.thoff + thlen > skb_headlen(skb) || + p_off = keys.control.thoff + thlen; + if (p_off > skb_headlen(skb) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); + } else if (gso_type) { + p_off = thlen; + if (p_off > skb_headlen(skb)) + return -EINVAL; } } if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + if (skb->len - p_off <= gso_size) + return -EINVAL; + skb_shinfo(skb)->gso_size = gso_size; skb_shinfo(skb)->gso_type = gso_type; -- cgit v1.2.3 From f1e71d75f04792721d411170168e68019ccb7de3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:04:52 -0500 Subject: nvme: replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b235a48eac8c..e2993e6a9d7c 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1185,7 +1185,7 @@ struct nvmf_disc_rsp_page_hdr { __le64 numrec; __le16 recfmt; __u8 resv14[1006]; - struct nvmf_disc_rsp_page_entry entries[0]; + struct nvmf_disc_rsp_page_entry entries[]; }; enum { -- cgit v1.2.3 From c295ee4742fda49de598a304ef9a95cf8da6b1f5 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Tue, 19 May 2020 17:05:48 +0300 Subject: block: always define struct blk_integrity in genhd.h This will reduce the amount of ifdefs inside the source code for various drivers and also will reduce the amount of stub functions that were created for the !CONFIG_BLK_DEV_INTEGRITY case. Suggested-by: Christoph Hellwig Signed-off-by: Max Gurtovoy Reviewed-by: Israel Rukshin Reviewed-by: Martin K. Petersen Signed-off-by: Christoph Hellwig --- include/linux/genhd.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f9c226f9546a..2590bed6e6b3 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -169,8 +169,6 @@ struct disk_part_tbl { struct disk_events; struct badblocks; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - struct blk_integrity { const struct blk_integrity_profile *profile; unsigned char flags; @@ -179,8 +177,6 @@ struct blk_integrity { unsigned char tag_size; }; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - struct gendisk { /* major, first_minor and minors are input parameters only, * don't use directly. Use disk_devt() and disk_max_parts(). -- cgit v1.2.3 From 39481fbd14ee272edd419d73a98bc637e2a3fd35 Mon Sep 17 00:00:00 2001 From: Israel Rukshin Date: Tue, 19 May 2020 17:06:00 +0300 Subject: nvme: add Metadata Capabilities enumerations The enumerations will be used to expose the namespace metadata format by the target. Suggested-by: Christoph Hellwig Signed-off-by: Israel Rukshin Signed-off-by: Max Gurtovoy Reviewed-by: James Smart Reviewed-by: Martin K. Petersen Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index e2993e6a9d7c..5ce51ab4c50e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -420,6 +420,12 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +/* Identify Namespace Metadata Capabilities (MC): */ +enum { + NVME_MC_EXTENDED_LBA = (1 << 0), + NVME_MC_METADATA_PTR = (1 << 1), +}; + struct nvme_ns_id_desc { __u8 nidt; __u8 nidl; -- cgit v1.2.3 From 1a644de29f712771c2ec00e52caa391544eb6141 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:38 +0200 Subject: net: ethtool: Add generic parts of cable test TDR Add the generic parts of the code used to trigger a cable test and return raw TDR data. Any PHY driver which support this must implement the new driver op. Signed-off-by: Andrew Lunn v2 Update nxp-tja11xx for API change. Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 4 ++-- include/linux/phy.h | 13 +++++++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index e317fc99565e..24817ba252a0 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -17,13 +17,13 @@ enum ethtool_multicast_groups { struct phy_device; #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) -int ethnl_cable_test_alloc(struct phy_device *phydev); +int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); #else -static inline int ethnl_cable_test_alloc(struct phy_device *phydev) +static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) { return -EOPNOTSUPP; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 6d256e720a66..d3c384f353ca 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -699,6 +699,10 @@ struct phy_driver { /* Start a cable test */ int (*cable_test_start)(struct phy_device *dev); + + /* Start a raw TDR cable test */ + int (*cable_test_tdr_start)(struct phy_device *dev); + /* Once per second, or on interrupt, request the status of the * test. */ @@ -1251,6 +1255,8 @@ int phy_reset_after_clk_enable(struct phy_device *phydev); #if IS_ENABLED(CONFIG_PHYLIB) int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); +int phy_start_cable_test_tdr(struct phy_device *phydev, + struct netlink_ext_ack *extack); #else static inline int phy_start_cable_test(struct phy_device *phydev, @@ -1259,6 +1265,13 @@ int phy_start_cable_test(struct phy_device *phydev, NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } +static inline +int phy_start_cable_test_tdr(struct phy_device *phydev, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); + return -EOPNOTSUPP; +} #endif int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result); -- cgit v1.2.3 From 6b4a0fc106521e480c00b55a7ef38c89f02dc4e8 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:39 +0200 Subject: net: ethtool: Add helpers for cable test TDR data Add helpers for returning raw TDR helpers in netlink messages. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 24817ba252a0..8fbe4f97ffad 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -22,6 +22,10 @@ void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); +int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV); +int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV); +int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last, + u32 step); #else static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) { @@ -46,5 +50,22 @@ static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, { return -EOPNOTSUPP; } + +static inline int ethnl_cable_test_amplitude(struct phy_device *phydev, + u8 pair, s16 mV) +{ + return -EOPNOTSUPP; +} + +static inline int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV) +{ + return -EOPNOTSUPP; +} + +static inline int ethnl_cable_test_step(struct phy_device *phydev, u32 first, + u32 last, u32 step) +{ + return -EOPNOTSUPP; +} #endif /* IS_ENABLED(ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ -- cgit v1.2.3 From f2bc8ad31a7f814237bc6301d59296d76505a688 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:41 +0200 Subject: net: ethtool: Allow PHY cable test TDR data to configured Allow the user to configure where on the cable the TDR data should be retrieved, in terms of first and last sample, and the step between samples. Also add the ability to ask for TDR data for just one pair. If this configuration is not provided, it defaults to 1-150m at 1m intervals for all pairs. Signed-off-by: Andrew Lunn v3: Move the TDR configuration into a structure Add a range check on step Use NL_SET_ERR_MSG_ATTR() when appropriate Move TDR configuration into a nest Document attributes in the request Signed-off-by: David S. Miller --- include/linux/phy.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index d3c384f353ca..8c05d0fb5c00 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -548,6 +548,18 @@ struct phy_device { #define to_phy_device(d) container_of(to_mdio_device(d), \ struct phy_device, mdio) +/* A structure containing possible configuration parameters + * for a TDR cable test. The driver does not need to implement + * all the parameters, but should report what is actually used. + */ +struct phy_tdr_config { + u32 first; + u32 last; + u32 step; + s8 pair; +}; +#define PHY_PAIR_ALL -1 + /* struct phy_driver: Driver structure for a particular PHY type * * driver_data: static driver data @@ -701,7 +713,8 @@ struct phy_driver { int (*cable_test_start)(struct phy_device *dev); /* Start a raw TDR cable test */ - int (*cable_test_tdr_start)(struct phy_device *dev); + int (*cable_test_tdr_start)(struct phy_device *dev, + const struct phy_tdr_config *config); /* Once per second, or on interrupt, request the status of the * test. @@ -1256,7 +1269,8 @@ int phy_reset_after_clk_enable(struct phy_device *phydev); int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); int phy_start_cable_test_tdr(struct phy_device *phydev, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config); #else static inline int phy_start_cable_test(struct phy_device *phydev, @@ -1267,7 +1281,8 @@ int phy_start_cable_test(struct phy_device *phydev, } static inline int phy_start_cable_test_tdr(struct phy_device *phydev, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; -- cgit v1.2.3 From 7edd363421dab1d4806802ac65613d1c0ec85824 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Thu, 23 Apr 2020 19:24:52 +0800 Subject: mfd: Add support for PMIC MT6360 Add MFD driver for mt6360 pmic chip include Battery Charger/ USB_PD/Flash, LED/RGB and LED/LDO/Buck Signed-off-by: Gene Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6360.h | 240 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 240 insertions(+) create mode 100644 include/linux/mfd/mt6360.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6360.h b/include/linux/mfd/mt6360.h new file mode 100644 index 000000000000..ea1304035d4d --- /dev/null +++ b/include/linux/mfd/mt6360.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + */ + +#ifndef __MT6360_H__ +#define __MT6360_H__ + +#include + +enum { + MT6360_SLAVE_PMU = 0, + MT6360_SLAVE_PMIC, + MT6360_SLAVE_LDO, + MT6360_SLAVE_TCPC, + MT6360_SLAVE_MAX, +}; + +#define MT6360_PMU_SLAVEID (0x34) +#define MT6360_PMIC_SLAVEID (0x1A) +#define MT6360_LDO_SLAVEID (0x64) +#define MT6360_TCPC_SLAVEID (0x4E) + +struct mt6360_pmu_data { + struct i2c_client *i2c[MT6360_SLAVE_MAX]; + struct device *dev; + struct regmap *regmap; + struct regmap_irq_chip_data *irq_data; + unsigned int chip_rev; +}; + +/* PMU register defininition */ +#define MT6360_PMU_DEV_INFO (0x00) +#define MT6360_PMU_CORE_CTRL1 (0x01) +#define MT6360_PMU_RST1 (0x02) +#define MT6360_PMU_CRCEN (0x03) +#define MT6360_PMU_RST_PAS_CODE1 (0x04) +#define MT6360_PMU_RST_PAS_CODE2 (0x05) +#define MT6360_PMU_CORE_CTRL2 (0x06) +#define MT6360_PMU_TM_PAS_CODE1 (0x07) +#define MT6360_PMU_TM_PAS_CODE2 (0x08) +#define MT6360_PMU_TM_PAS_CODE3 (0x09) +#define MT6360_PMU_TM_PAS_CODE4 (0x0A) +#define MT6360_PMU_IRQ_IND (0x0B) +#define MT6360_PMU_IRQ_MASK (0x0C) +#define MT6360_PMU_IRQ_SET (0x0D) +#define MT6360_PMU_SHDN_CTRL (0x0E) +#define MT6360_PMU_TM_INF (0x0F) +#define MT6360_PMU_I2C_CTRL (0x10) +#define MT6360_PMU_CHG_CTRL1 (0x11) +#define MT6360_PMU_CHG_CTRL2 (0x12) +#define MT6360_PMU_CHG_CTRL3 (0x13) +#define MT6360_PMU_CHG_CTRL4 (0x14) +#define MT6360_PMU_CHG_CTRL5 (0x15) +#define MT6360_PMU_CHG_CTRL6 (0x16) +#define MT6360_PMU_CHG_CTRL7 (0x17) +#define MT6360_PMU_CHG_CTRL8 (0x18) +#define MT6360_PMU_CHG_CTRL9 (0x19) +#define MT6360_PMU_CHG_CTRL10 (0x1A) +#define MT6360_PMU_CHG_CTRL11 (0x1B) +#define MT6360_PMU_CHG_CTRL12 (0x1C) +#define MT6360_PMU_CHG_CTRL13 (0x1D) +#define MT6360_PMU_CHG_CTRL14 (0x1E) +#define MT6360_PMU_CHG_CTRL15 (0x1F) +#define MT6360_PMU_CHG_CTRL16 (0x20) +#define MT6360_PMU_CHG_AICC_RESULT (0x21) +#define MT6360_PMU_DEVICE_TYPE (0x22) +#define MT6360_PMU_QC_CONTROL1 (0x23) +#define MT6360_PMU_QC_CONTROL2 (0x24) +#define MT6360_PMU_QC30_CONTROL1 (0x25) +#define MT6360_PMU_QC30_CONTROL2 (0x26) +#define MT6360_PMU_USB_STATUS1 (0x27) +#define MT6360_PMU_QC_STATUS1 (0x28) +#define MT6360_PMU_QC_STATUS2 (0x29) +#define MT6360_PMU_CHG_PUMP (0x2A) +#define MT6360_PMU_CHG_CTRL17 (0x2B) +#define MT6360_PMU_CHG_CTRL18 (0x2C) +#define MT6360_PMU_CHRDET_CTRL1 (0x2D) +#define MT6360_PMU_CHRDET_CTRL2 (0x2E) +#define MT6360_PMU_DPDN_CTRL (0x2F) +#define MT6360_PMU_CHG_HIDDEN_CTRL1 (0x30) +#define MT6360_PMU_CHG_HIDDEN_CTRL2 (0x31) +#define MT6360_PMU_CHG_HIDDEN_CTRL3 (0x32) +#define MT6360_PMU_CHG_HIDDEN_CTRL4 (0x33) +#define MT6360_PMU_CHG_HIDDEN_CTRL5 (0x34) +#define MT6360_PMU_CHG_HIDDEN_CTRL6 (0x35) +#define MT6360_PMU_CHG_HIDDEN_CTRL7 (0x36) +#define MT6360_PMU_CHG_HIDDEN_CTRL8 (0x37) +#define MT6360_PMU_CHG_HIDDEN_CTRL9 (0x38) +#define MT6360_PMU_CHG_HIDDEN_CTRL10 (0x39) +#define MT6360_PMU_CHG_HIDDEN_CTRL11 (0x3A) +#define MT6360_PMU_CHG_HIDDEN_CTRL12 (0x3B) +#define MT6360_PMU_CHG_HIDDEN_CTRL13 (0x3C) +#define MT6360_PMU_CHG_HIDDEN_CTRL14 (0x3D) +#define MT6360_PMU_CHG_HIDDEN_CTRL15 (0x3E) +#define MT6360_PMU_CHG_HIDDEN_CTRL16 (0x3F) +#define MT6360_PMU_CHG_HIDDEN_CTRL17 (0x40) +#define MT6360_PMU_CHG_HIDDEN_CTRL18 (0x41) +#define MT6360_PMU_CHG_HIDDEN_CTRL19 (0x42) +#define MT6360_PMU_CHG_HIDDEN_CTRL20 (0x43) +#define MT6360_PMU_CHG_HIDDEN_CTRL21 (0x44) +#define MT6360_PMU_CHG_HIDDEN_CTRL22 (0x45) +#define MT6360_PMU_CHG_HIDDEN_CTRL23 (0x46) +#define MT6360_PMU_CHG_HIDDEN_CTRL24 (0x47) +#define MT6360_PMU_CHG_HIDDEN_CTRL25 (0x48) +#define MT6360_PMU_BC12_CTRL (0x49) +#define MT6360_PMU_CHG_STAT (0x4A) +#define MT6360_PMU_RESV1 (0x4B) +#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEH (0x4E) +#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEL (0x4F) +#define MT6360_PMU_TYPEC_OTP_HYST_TH (0x50) +#define MT6360_PMU_TYPEC_OTP_CTRL (0x51) +#define MT6360_PMU_ADC_BAT_DATA_H (0x52) +#define MT6360_PMU_ADC_BAT_DATA_L (0x53) +#define MT6360_PMU_IMID_BACKBST_ON (0x54) +#define MT6360_PMU_IMID_BACKBST_OFF (0x55) +#define MT6360_PMU_ADC_CONFIG (0x56) +#define MT6360_PMU_ADC_EN2 (0x57) +#define MT6360_PMU_ADC_IDLE_T (0x58) +#define MT6360_PMU_ADC_RPT_1 (0x5A) +#define MT6360_PMU_ADC_RPT_2 (0x5B) +#define MT6360_PMU_ADC_RPT_3 (0x5C) +#define MT6360_PMU_ADC_RPT_ORG1 (0x5D) +#define MT6360_PMU_ADC_RPT_ORG2 (0x5E) +#define MT6360_PMU_BAT_OVP_TH_SEL_CODEH (0x5F) +#define MT6360_PMU_BAT_OVP_TH_SEL_CODEL (0x60) +#define MT6360_PMU_CHG_CTRL19 (0x61) +#define MT6360_PMU_VDDASUPPLY (0x62) +#define MT6360_PMU_BC12_MANUAL (0x63) +#define MT6360_PMU_CHGDET_FUNC (0x64) +#define MT6360_PMU_FOD_CTRL (0x65) +#define MT6360_PMU_CHG_CTRL20 (0x66) +#define MT6360_PMU_CHG_HIDDEN_CTRL26 (0x67) +#define MT6360_PMU_CHG_HIDDEN_CTRL27 (0x68) +#define MT6360_PMU_RESV2 (0x69) +#define MT6360_PMU_USBID_CTRL1 (0x6D) +#define MT6360_PMU_USBID_CTRL2 (0x6E) +#define MT6360_PMU_USBID_CTRL3 (0x6F) +#define MT6360_PMU_FLED_CFG (0x70) +#define MT6360_PMU_RESV3 (0x71) +#define MT6360_PMU_FLED1_CTRL (0x72) +#define MT6360_PMU_FLED_STRB_CTRL (0x73) +#define MT6360_PMU_FLED1_STRB_CTRL2 (0x74) +#define MT6360_PMU_FLED1_TOR_CTRL (0x75) +#define MT6360_PMU_FLED2_CTRL (0x76) +#define MT6360_PMU_RESV4 (0x77) +#define MT6360_PMU_FLED2_STRB_CTRL2 (0x78) +#define MT6360_PMU_FLED2_TOR_CTRL (0x79) +#define MT6360_PMU_FLED_VMIDTRK_CTRL1 (0x7A) +#define MT6360_PMU_FLED_VMID_RTM (0x7B) +#define MT6360_PMU_FLED_VMIDTRK_CTRL2 (0x7C) +#define MT6360_PMU_FLED_PWSEL (0x7D) +#define MT6360_PMU_FLED_EN (0x7E) +#define MT6360_PMU_FLED_Hidden1 (0x7F) +#define MT6360_PMU_RGB_EN (0x80) +#define MT6360_PMU_RGB1_ISNK (0x81) +#define MT6360_PMU_RGB2_ISNK (0x82) +#define MT6360_PMU_RGB3_ISNK (0x83) +#define MT6360_PMU_RGB_ML_ISNK (0x84) +#define MT6360_PMU_RGB1_DIM (0x85) +#define MT6360_PMU_RGB2_DIM (0x86) +#define MT6360_PMU_RGB3_DIM (0x87) +#define MT6360_PMU_RESV5 (0x88) +#define MT6360_PMU_RGB12_Freq (0x89) +#define MT6360_PMU_RGB34_Freq (0x8A) +#define MT6360_PMU_RGB1_Tr (0x8B) +#define MT6360_PMU_RGB1_Tf (0x8C) +#define MT6360_PMU_RGB1_TON_TOFF (0x8D) +#define MT6360_PMU_RGB2_Tr (0x8E) +#define MT6360_PMU_RGB2_Tf (0x8F) +#define MT6360_PMU_RGB2_TON_TOFF (0x90) +#define MT6360_PMU_RGB3_Tr (0x91) +#define MT6360_PMU_RGB3_Tf (0x92) +#define MT6360_PMU_RGB3_TON_TOFF (0x93) +#define MT6360_PMU_RGB_Hidden_CTRL1 (0x94) +#define MT6360_PMU_RGB_Hidden_CTRL2 (0x95) +#define MT6360_PMU_RESV6 (0x97) +#define MT6360_PMU_SPARE1 (0x9A) +#define MT6360_PMU_SPARE2 (0xA0) +#define MT6360_PMU_SPARE3 (0xB0) +#define MT6360_PMU_SPARE4 (0xC0) +#define MT6360_PMU_CHG_IRQ1 (0xD0) +#define MT6360_PMU_CHG_IRQ2 (0xD1) +#define MT6360_PMU_CHG_IRQ3 (0xD2) +#define MT6360_PMU_CHG_IRQ4 (0xD3) +#define MT6360_PMU_CHG_IRQ5 (0xD4) +#define MT6360_PMU_CHG_IRQ6 (0xD5) +#define MT6360_PMU_QC_IRQ (0xD6) +#define MT6360_PMU_FOD_IRQ (0xD7) +#define MT6360_PMU_BASE_IRQ (0xD8) +#define MT6360_PMU_FLED_IRQ1 (0xD9) +#define MT6360_PMU_FLED_IRQ2 (0xDA) +#define MT6360_PMU_RGB_IRQ (0xDB) +#define MT6360_PMU_BUCK1_IRQ (0xDC) +#define MT6360_PMU_BUCK2_IRQ (0xDD) +#define MT6360_PMU_LDO_IRQ1 (0xDE) +#define MT6360_PMU_LDO_IRQ2 (0xDF) +#define MT6360_PMU_CHG_STAT1 (0xE0) +#define MT6360_PMU_CHG_STAT2 (0xE1) +#define MT6360_PMU_CHG_STAT3 (0xE2) +#define MT6360_PMU_CHG_STAT4 (0xE3) +#define MT6360_PMU_CHG_STAT5 (0xE4) +#define MT6360_PMU_CHG_STAT6 (0xE5) +#define MT6360_PMU_QC_STAT (0xE6) +#define MT6360_PMU_FOD_STAT (0xE7) +#define MT6360_PMU_BASE_STAT (0xE8) +#define MT6360_PMU_FLED_STAT1 (0xE9) +#define MT6360_PMU_FLED_STAT2 (0xEA) +#define MT6360_PMU_RGB_STAT (0xEB) +#define MT6360_PMU_BUCK1_STAT (0xEC) +#define MT6360_PMU_BUCK2_STAT (0xED) +#define MT6360_PMU_LDO_STAT1 (0xEE) +#define MT6360_PMU_LDO_STAT2 (0xEF) +#define MT6360_PMU_CHG_MASK1 (0xF0) +#define MT6360_PMU_CHG_MASK2 (0xF1) +#define MT6360_PMU_CHG_MASK3 (0xF2) +#define MT6360_PMU_CHG_MASK4 (0xF3) +#define MT6360_PMU_CHG_MASK5 (0xF4) +#define MT6360_PMU_CHG_MASK6 (0xF5) +#define MT6360_PMU_QC_MASK (0xF6) +#define MT6360_PMU_FOD_MASK (0xF7) +#define MT6360_PMU_BASE_MASK (0xF8) +#define MT6360_PMU_FLED_MASK1 (0xF9) +#define MT6360_PMU_FLED_MASK2 (0xFA) +#define MT6360_PMU_FAULTB_MASK (0xFB) +#define MT6360_PMU_BUCK1_MASK (0xFC) +#define MT6360_PMU_BUCK2_MASK (0xFD) +#define MT6360_PMU_LDO_MASK1 (0xFE) +#define MT6360_PMU_LDO_MASK2 (0xFF) +#define MT6360_PMU_MAXREG (MT6360_PMU_LDO_MASK2) + +/* MT6360_PMU_IRQ_SET */ +#define MT6360_PMU_IRQ_REGNUM (MT6360_PMU_LDO_IRQ2 - MT6360_PMU_CHG_IRQ1 + 1) +#define MT6360_IRQ_RETRIG BIT(2) + +#define CHIP_VEN_MASK (0xF0) +#define CHIP_VEN_MT6360 (0x50) +#define CHIP_REV_MASK (0x0F) + +#endif /* __MT6360_H__ */ -- cgit v1.2.3 From e76fede8bf7c90d92c799d9ceb092dec48346e2c Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 30 Apr 2020 10:25:50 -0700 Subject: cfg80211: add KHz variants of frame RX API Drivers may wish to report the RX frequency in units of KHz. Provide cfg80211_rx_mgmt_khz() and wrap it with cfg80211_rx_mgmt() so exisiting drivers which can't report KHz anyway don't need to change. Add a similar wrapper for cfg80211_report_obss_beacon() so the frequency units stay somewhat consistent. This doesn't actually change the nl80211 API yet. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200430172554.18383-2-thomas@adapt-ip.com [fix mac80211 calling the non-khz version of obss beacon report, drop trace point name changes] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a561db435a4b..41d5f000c0d9 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3333,6 +3333,8 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size) /* convert frequencies */ #define MHZ_TO_KHZ(freq) ((freq) * 1000) #define KHZ_TO_MHZ(freq) ((freq) / 1000) +#define PR_KHZ(f) KHZ_TO_MHZ(f), f % 1000 +#define KHZ_F "%d.%03d" /* convert powers */ #define DBI_TO_MBI(gain) ((gain) * 100) -- cgit v1.2.3 From d6fb67ff86bb991d5ac18471e5f739bc32e5090e Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 30 Apr 2020 10:25:53 -0700 Subject: ieee80211: S1G defines These are found in IEEE-802.11ah-2016. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200430172554.18383-5-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 221 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 221 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 41d5f000c0d9..f630b8978a43 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -105,6 +105,51 @@ /* extension, added by 802.11ad */ #define IEEE80211_STYPE_DMG_BEACON 0x0000 +#define IEEE80211_STYPE_S1G_BEACON 0x0010 + +/* bits unique to S1G beacon */ +#define IEEE80211_S1G_BCN_NEXT_TBTT 0x100 + +/* see 802.11ah-2016 9.9 NDP CMAC frames */ +#define IEEE80211_S1G_1MHZ_NDP_BITS 25 +#define IEEE80211_S1G_1MHZ_NDP_BYTES 4 +#define IEEE80211_S1G_2MHZ_NDP_BITS 37 +#define IEEE80211_S1G_2MHZ_NDP_BYTES 5 + +#define IEEE80211_NDP_FTYPE_CTS 0 +#define IEEE80211_NDP_FTYPE_CF_END 0 +#define IEEE80211_NDP_FTYPE_PS_POLL 1 +#define IEEE80211_NDP_FTYPE_ACK 2 +#define IEEE80211_NDP_FTYPE_PS_POLL_ACK 3 +#define IEEE80211_NDP_FTYPE_BA 4 +#define IEEE80211_NDP_FTYPE_BF_REPORT_POLL 5 +#define IEEE80211_NDP_FTYPE_PAGING 6 +#define IEEE80211_NDP_FTYPE_PREQ 7 + +#define SM64(f, v) ((((u64)v) << f##_S) & f) + +/* NDP CMAC frame fields */ +#define IEEE80211_NDP_FTYPE 0x0000000000000007 +#define IEEE80211_NDP_FTYPE_S 0x0000000000000000 + +/* 1M Probe Request 11ah 9.9.3.1.1 */ +#define IEEE80211_NDP_1M_PREQ_ANO 0x0000000000000008 +#define IEEE80211_NDP_1M_PREQ_ANO_S 3 +#define IEEE80211_NDP_1M_PREQ_CSSID 0x00000000000FFFF0 +#define IEEE80211_NDP_1M_PREQ_CSSID_S 4 +#define IEEE80211_NDP_1M_PREQ_RTYPE 0x0000000000100000 +#define IEEE80211_NDP_1M_PREQ_RTYPE_S 20 +#define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 +#define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 +/* 2M Probe Request 11ah 9.9.3.1.2 */ +#define IEEE80211_NDP_2M_PREQ_ANO 0x0000000000000008 +#define IEEE80211_NDP_2M_PREQ_ANO_S 3 +#define IEEE80211_NDP_2M_PREQ_CSSID 0x0000000FFFFFFFF0 +#define IEEE80211_NDP_2M_PREQ_CSSID_S 4 +#define IEEE80211_NDP_2M_PREQ_RTYPE 0x0000001000000000 +#define IEEE80211_NDP_2M_PREQ_RTYPE_S 36 + +#define IEEE80211_ANO_NETTYPE_WILD 15 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */ #define IEEE80211_CTL_EXT_POLL 0x2000 @@ -121,6 +166,21 @@ #define IEEE80211_MAX_SN IEEE80211_SN_MASK #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) + +/* PV1 Layout 11ah 9.8.3.1 */ +#define IEEE80211_PV1_FCTL_VERS 0x0003 +#define IEEE80211_PV1_FCTL_FTYPE 0x001c +#define IEEE80211_PV1_FCTL_STYPE 0x00e0 +#define IEEE80211_PV1_FCTL_TODS 0x0100 +#define IEEE80211_PV1_FCTL_MOREFRAGS 0x0200 +#define IEEE80211_PV1_FCTL_PM 0x0400 +#define IEEE80211_PV1_FCTL_MOREDATA 0x0800 +#define IEEE80211_PV1_FCTL_PROTECTED 0x1000 +#define IEEE80211_PV1_FCTL_END_SP 0x2000 +#define IEEE80211_PV1_FCTL_RELAYED 0x4000 +#define IEEE80211_PV1_FCTL_ACK_POLICY 0x8000 +#define IEEE80211_PV1_FCTL_CTL_EXT 0x0f00 + static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) { return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); @@ -148,6 +208,7 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_MAX_FRAG_THRESHOLD 2352 #define IEEE80211_MAX_RTS_THRESHOLD 2353 #define IEEE80211_MAX_AID 2007 +#define IEEE80211_MAX_AID_S1G 8191 #define IEEE80211_MAX_TIM_LEN 251 #define IEEE80211_MAX_MESH_PEERINGS 63 /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section @@ -371,6 +432,17 @@ static inline bool ieee80211_is_data(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_DATA); } +/** + * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_is_ext(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == + cpu_to_le16(IEEE80211_FTYPE_EXT); +} + + /** * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder @@ -469,6 +541,18 @@ static inline bool ieee80211_is_beacon(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); } +/** + * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT && + * IEEE80211_STYPE_S1G_BEACON + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_is_s1g_beacon(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | + IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON); +} + /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder @@ -900,6 +984,59 @@ struct ieee80211_addba_ext_ie { u8 data; } __packed; +/** + * struct ieee80211_s1g_bcn_compat_ie + * + * S1G Beacon Compatibility element + */ +struct ieee80211_s1g_bcn_compat_ie { + __le16 compat_info; + __le16 beacon_int; + __le32 tsf_completion; +} __packed; + +/** + * struct ieee80211_s1g_oper_ie + * + * S1G Operation element + */ +struct ieee80211_s1g_oper_ie { + u8 ch_width; + u8 oper_class; + u8 primary_ch; + u8 oper_ch; + __le16 basic_mcs_nss; +} __packed; + +/** + * struct ieee80211_aid_response_ie + * + * AID Response element + */ +struct ieee80211_aid_response_ie { + __le16 aid; + u8 switch_count; + __le16 response_int; +} __packed; + +struct ieee80211_s1g_cap { + u8 capab_info[10]; + u8 supp_mcs_nss[5]; +} __packed; + +struct ieee80211_ext { + __le16 frame_control; + __le16 duration; + union { + struct { + u8 sa[ETH_ALEN]; + __le32 timestamp; + u8 change_seq; + u8 variable[0]; + } __packed s1g_beacon; + } u; +} __packed __aligned(2); + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -2137,6 +2274,86 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) return spr_len; } +/* S1G Capabilities Information field */ +#define S1G_CAPAB_B0_S1G_LONG BIT(0) +#define S1G_CAPAB_B0_SGI_1MHZ BIT(1) +#define S1G_CAPAB_B0_SGI_2MHZ BIT(2) +#define S1G_CAPAB_B0_SGI_4MHZ BIT(3) +#define S1G_CAPAB_B0_SGI_8MHZ BIT(4) +#define S1G_CAPAB_B0_SGI_16MHZ BIT(5) +#define S1G_CAPAB_B0_SUPP_CH_WIDTH_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B0_SUPP_CH_WIDTH_SHIFT 6 + +#define S1G_CAPAB_B1_RX_LDPC BIT(0) +#define S1G_CAPAB_B1_TX_STBC BIT(1) +#define S1G_CAPAB_B1_RX_STBC BIT(2) +#define S1G_CAPAB_B1_SU_BFER BIT(3) +#define S1G_CAPAB_B1_SU_BFEE BIT(4) +#define S1G_CAPAB_B1_BFEE_STS_MASK (BIT(5) | BIT(6) | BIT(7)) +#define S1G_CAPAB_B1_BFEE_STS_SHIFT 5 + +#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_MASK (BIT(0) | BIT(1) | BIT(2)) +#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_SHIFT 0 +#define S1G_CAPAB_B2_MU_BFER BIT(3) +#define S1G_CAPAB_B2_MU_BFEE BIT(4) +#define S1G_CAPAB_B2_PLUS_HTC_VHT BIT(5) +#define S1G_CAPAB_B2_TRAVELING_PILOT_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B2_TRAVELING_PILOT_SHIFT 6 + +#define S1G_CAPAB_B3_RD_RESPONDER BIT(0) +#define S1G_CAPAB_B3_HT_DELAYED_BA BIT(1) +#define S1G_CAPAB_B3_MAX_MPDU_LEN BIT(2) +#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_MASK (BIT(3) | BIT(4)) +#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_SHIFT 3 +#define S1G_CAPAB_B3_MIN_MPDU_START_MASK (BIT(5) | BIT(6) | BIT(7)) +#define S1G_CAPAB_B3_MIN_MPDU_START_SHIFT 5 + +#define S1G_CAPAB_B4_UPLINK_SYNC BIT(0) +#define S1G_CAPAB_B4_DYNAMIC_AID BIT(1) +#define S1G_CAPAB_B4_BAT BIT(2) +#define S1G_CAPAB_B4_TIME_ADE BIT(3) +#define S1G_CAPAB_B4_NON_TIM BIT(4) +#define S1G_CAPAB_B4_GROUP_AID BIT(5) +#define S1G_CAPAB_B4_STA_TYPE_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B4_STA_TYPE_SHIFT 6 + +#define S1G_CAPAB_B5_CENT_AUTH_CONTROL BIT(0) +#define S1G_CAPAB_B5_DIST_AUTH_CONTROL BIT(1) +#define S1G_CAPAB_B5_AMSDU BIT(2) +#define S1G_CAPAB_B5_AMPDU BIT(3) +#define S1G_CAPAB_B5_ASYMMETRIC_BA BIT(4) +#define S1G_CAPAB_B5_FLOW_CONTROL BIT(5) +#define S1G_CAPAB_B5_SECTORIZED_BEAM_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B5_SECTORIZED_BEAM_SHIFT 6 + +#define S1G_CAPAB_B6_OBSS_MITIGATION BIT(0) +#define S1G_CAPAB_B6_FRAGMENT_BA BIT(1) +#define S1G_CAPAB_B6_NDP_PS_POLL BIT(2) +#define S1G_CAPAB_B6_RAW_OPERATION BIT(3) +#define S1G_CAPAB_B6_PAGE_SLICING BIT(4) +#define S1G_CAPAB_B6_TXOP_SHARING_IMP_ACK BIT(5) +#define S1G_CAPAB_B6_VHT_LINK_ADAPT_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B6_VHT_LINK_ADAPT_SHIFT 6 + +#define S1G_CAPAB_B7_TACK_AS_PS_POLL BIT(0) +#define S1G_CAPAB_B7_DUP_1MHZ BIT(1) +#define S1G_CAPAB_B7_MCS_NEGOTIATION BIT(2) +#define S1G_CAPAB_B7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) +#define S1G_CAPAB_B7_NDP_BFING_REPORT_POLL BIT(4) +#define S1G_CAPAB_B7_UNSOLICITED_DYN_AID BIT(5) +#define S1G_CAPAB_B7_SECTOR_TRAINING_OPERATION BIT(6) +#define S1G_CAPAB_B7_TEMP_PS_MODE_SWITCH BIT(7) + +#define S1G_CAPAB_B8_TWT_GROUPING BIT(0) +#define S1G_CAPAB_B8_BDT BIT(1) +#define S1G_CAPAB_B8_COLOR_MASK (BIT(2) | BIT(3) | BIT(4)) +#define S1G_CAPAB_B8_COLOR_SHIFT 2 +#define S1G_CAPAB_B8_TWT_REQUEST BIT(5) +#define S1G_CAPAB_B8_TWT_RESPOND BIT(6) +#define S1G_CAPAB_B8_PV1_FRAME BIT(7) + +#define S1G_CAPAB_B9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -2532,8 +2749,12 @@ enum ieee80211_eid { WLAN_EID_QUIET_CHANNEL = 198, WLAN_EID_OPMODE_NOTIF = 199, + WLAN_EID_S1G_BCN_COMPAT = 213, + WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, + WLAN_EID_S1G_CAPABILITIES = 217, WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, + WLAN_EID_S1G_OPERATION = 232, WLAN_EID_CAG_NUMBER = 237, WLAN_EID_AP_CSN = 239, WLAN_EID_FILS_INDICATION = 240, -- cgit v1.2.3 From fedd0fe4e89b009f31eb53ec36dbdf1e457616c0 Mon Sep 17 00:00:00 2001 From: Tamizh Chelvam Date: Mon, 4 May 2020 22:34:59 +0530 Subject: mac80211: Add new AMPDU factor macro for HE peer caps Add IEEE80211_HE_VHT_MAX_AMPDU_FACTOR and IEEE80211_HE_HT_MAX_AMPDU_FACTOR as per spec to use for peer max ampdu factor. Signed-off-by: Tamizh Chelvam Link: https://lore.kernel.org/r/1588611900-21185-1-git-send-email-tamizhr@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f630b8978a43..2153d465d752 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1958,6 +1958,8 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 #define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_SHIFT 3 + #define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 #define IEEE80211_HE_MAC_CAP4_QTP 0x02 #define IEEE80211_HE_MAC_CAP4_BQR 0x04 @@ -1979,6 +1981,9 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING 0x40 #define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX 0x80 +#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 +#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 + /* 802.11ax HE PHY capabilities */ #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 -- cgit v1.2.3 From 396fba0a59f3c94d6fd6443fbeabd8bd9e3956eb Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:39:09 -0500 Subject: cfg80211: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507183909.GA12993@embeddedor Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2153d465d752..0320ca4c7d28 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -800,7 +800,7 @@ struct ieee80211_msrment_ie { u8 token; u8 mode; u8 type; - u8 request[0]; + u8 request[]; } __packed; /** @@ -1781,7 +1781,7 @@ struct ieee80211_he_operation { __le32 he_oper_params; __le16 he_mcs_nss_set; /* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */ - u8 optional[0]; + u8 optional[]; } __packed; /** @@ -1793,7 +1793,7 @@ struct ieee80211_he_operation { struct ieee80211_he_spr { u8 he_sr_control; /* Optional 0 to 19 bytes: depends on @he_sr_control */ - u8 optional[0]; + u8 optional[]; } __packed; /** -- cgit v1.2.3 From 3234ac664a870e6ea69ae3a57d824cd7edbeacc5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 21 May 2020 14:06:17 -0700 Subject: /dev/mem: Revoke mappings when a driver claims the region Close the hole of holding a mapping over kernel driver takeover event of a given address range. Commit 90a545e98126 ("restrict /dev/mem to idle io memory ranges") introduced CONFIG_IO_STRICT_DEVMEM with the goal of protecting the kernel against scenarios where a /dev/mem user tramples memory that a kernel driver owns. However, this protection only prevents *new* read(), write() and mmap() requests. Established mappings prior to the driver calling request_mem_region() are left alone. Especially with persistent memory, and the core kernel metadata that is stored there, there are plentiful scenarios for a /dev/mem user to violate the expectations of the driver and cause amplified damage. Teach request_mem_region() to find and shoot down active /dev/mem mappings that it believes it has successfully claimed for the exclusive use of the driver. Effectively a driver call to request_mem_region() becomes a hole-punch on the /dev/mem device. The typical usage of unmap_mapping_range() is part of truncate_pagecache() to punch a hole in a file, but in this case the implementation is only doing the "first half" of a hole punch. Namely it is just evacuating current established mappings of the "hole", and it relies on the fact that /dev/mem establishes mappings in terms of absolute physical address offsets. Once existing mmap users are invalidated they can attempt to re-establish the mapping, or attempt to continue issuing read(2) / write(2) to the invalidated extent, but they will then be subject to the CONFIG_IO_STRICT_DEVMEM checking that can block those subsequent accesses. Cc: Arnd Bergmann Cc: Ingo Molnar Cc: Kees Cook Cc: Matthew Wilcox Cc: Russell King Cc: Andrew Morton Cc: Greg Kroah-Hartman Fixes: 90a545e98126 ("restrict /dev/mem to idle io memory ranges") Signed-off-by: Dan Williams Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/159009507306.847224.8502634072429766747.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/ioport.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index a9b9170b5dd2..6c3eca90cbc4 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -301,5 +301,11 @@ struct resource *devm_request_free_mem_region(struct device *dev, struct resource *request_free_mem_region(struct resource *base, unsigned long size, const char *name); +#ifdef CONFIG_IO_STRICT_DEVMEM +void revoke_devmem(struct resource *res); +#else +static inline void revoke_devmem(struct resource *res) { }; +#endif + #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ -- cgit v1.2.3 From 6b646a7e4af69814dd1a3340fca0f02d4977420d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 9 Mar 2020 16:44:25 +0200 Subject: net/mlx5: Add ability to read and write ECE options The end result of RDMA-CM ECE handshake is ECE options, which is needed to be used while configuring data QPs. Such options can come in any QP state, so add in/out fields to set and query ECE options. OUT fields: * create_qp() - default ECE options for that type of QP. * modify_qp() - enabled ECE options after QP state transition. IN fields: * create_qp() - create QP with this ECE option. * modify_qp() - requested options. For unconnected QPs, the FW will return an error if ECE is already configured with any options that not equal to previously set. Reviewed-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fd8da4875ea0..1a56dc079c32 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1208,7 +1208,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_99[0x2]; u8 log_max_qp[0x5]; - u8 reserved_at_a0[0xb]; + u8 reserved_at_a0[0x3]; + u8 ece_support[0x1]; + u8 reserved_at_a4[0x7]; u8 log_max_srq[0x5]; u8 reserved_at_b0[0x10]; @@ -4216,7 +4218,8 @@ struct mlx5_ifc_rts2rts_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_rts2rts_qp_in_bits { @@ -4233,7 +4236,7 @@ struct mlx5_ifc_rts2rts_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -4246,7 +4249,8 @@ struct mlx5_ifc_rtr2rts_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_rtr2rts_qp_in_bits { @@ -4263,7 +4267,7 @@ struct mlx5_ifc_rtr2rts_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -4815,7 +4819,8 @@ struct mlx5_ifc_query_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; u8 opt_param_mask[0x20]; @@ -6580,7 +6585,8 @@ struct mlx5_ifc_init2rtr_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_init2rtr_qp_in_bits { @@ -6597,7 +6603,7 @@ struct mlx5_ifc_init2rtr_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -7693,7 +7699,7 @@ struct mlx5_ifc_create_qp_out_bits { u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_at_60[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_create_qp_in_bits { @@ -7707,7 +7713,7 @@ struct mlx5_ifc_create_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; -- cgit v1.2.3 From 956d510ee78caebc83c0eaeb892db5b239a36a06 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 07:24:04 +0200 Subject: block: add disk/bio-based accounting helpers Add two new helpers to simplify I/O accounting for bio based drivers. Currently these drivers use the generic_start_io_acct and generic_end_io_acct helpers which have very cumbersome calling conventions, don't actually return the time they started accounting, and try to deal with accounting for partitions, which can't happen for bio based drivers. The new helpers will be used to subsequently replace uses of the old helpers. The main API is the bio based wrappes in blkdev.h, but for zram which wants to account rw_page based I/O lower level routines are provided as well. Signed-off-by: Christoph Hellwig Reviewed-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d10f4e63232..6f7ff0fa8fcf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1892,4 +1892,32 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } +unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, + unsigned int op); +void disk_end_io_acct(struct gendisk *disk, unsigned int op, + unsigned long start_time); + +#ifdef CONFIG_BLOCK +/** + * bio_start_io_acct - start I/O accounting for bio based drivers + * @bio: bio to start account for + * + * Returns the start time that should be passed back to bio_end_io_acct(). + */ +static inline unsigned long bio_start_io_acct(struct bio *bio) +{ + return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio)); +} + +/** + * bio_end_io_acct - end I/O accounting for bio based drivers + * @bio: bio to end account for + * @start: start time returned by bio_start_io_acct() + */ +static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) +{ + return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); +} +#endif /* CONFIG_BLOCK */ + #endif -- cgit v1.2.3 From e722fff238bbfe6308d7778a8c2163c181bf998a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 07:24:12 +0200 Subject: block: remove generic_{start,end}_io_acct Remove these now unused functions. Signed-off-by: Christoph Hellwig Reviewed-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 950c9dc44c4f..941378ec5b39 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -444,12 +444,6 @@ void bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -void generic_start_io_acct(struct request_queue *q, int op, - unsigned long sectors, struct hd_struct *part); -void generic_end_io_acct(struct request_queue *q, int op, - struct hd_struct *part, - unsigned long start_time); - extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); -- cgit v1.2.3 From 58d4f14fc30ac26288cfed74d7e566921c22cf59 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 07:24:14 +0200 Subject: block: always use a percpu variable for disk stats percpu variables have a perfectly fine working stub implementation for UP kernels, so use that. Signed-off-by: Christoph Hellwig Reviewed-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/genhd.h | 13 ----------- include/linux/part_stat.h | 55 ++++++++++------------------------------------- 2 files changed, 11 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a9384449465a..f0d6d77309a5 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -39,15 +39,6 @@ extern struct class block_class; #include #include -struct disk_stats { - u64 nsecs[NR_STAT_GROUPS]; - unsigned long sectors[NR_STAT_GROUPS]; - unsigned long ios[NR_STAT_GROUPS]; - unsigned long merges[NR_STAT_GROUPS]; - unsigned long io_ticks; - local_t in_flight[2]; -}; - #define PARTITION_META_INFO_VOLNAMELTH 64 /* * Enough for the string representation of any kind of UUID plus NULL. @@ -72,11 +63,7 @@ struct hd_struct { seqcount_t nr_sects_seq; #endif unsigned long stamp; -#ifdef CONFIG_SMP struct disk_stats __percpu *dkstats; -#else - struct disk_stats dkstats; -#endif struct percpu_ref ref; sector_t alignment_offset; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index ece607607a86..6644197980b9 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -4,19 +4,23 @@ #include +struct disk_stats { + u64 nsecs[NR_STAT_GROUPS]; + unsigned long sectors[NR_STAT_GROUPS]; + unsigned long ios[NR_STAT_GROUPS]; + unsigned long merges[NR_STAT_GROUPS]; + unsigned long io_ticks; + local_t in_flight[2]; +}; + /* * Macros to operate on percpu disk statistics: * - * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters - * and should be called between disk_stat_lock() and - * disk_stat_unlock(). + * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters and should + * be called between disk_stat_lock() and disk_stat_unlock(). * * part_stat_read() can be called at any time. - * - * part_stat_{add|set_all}() and {init|free}_part_stats are for - * internal use only. */ -#ifdef CONFIG_SMP #define part_stat_lock() ({ rcu_read_lock(); get_cpu(); }) #define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) @@ -44,43 +48,6 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) sizeof(struct disk_stats)); } -static inline int init_part_stats(struct hd_struct *part) -{ - part->dkstats = alloc_percpu(struct disk_stats); - if (!part->dkstats) - return 0; - return 1; -} - -static inline void free_part_stats(struct hd_struct *part) -{ - free_percpu(part->dkstats); -} - -#else /* !CONFIG_SMP */ -#define part_stat_lock() ({ rcu_read_lock(); 0; }) -#define part_stat_unlock() rcu_read_unlock() - -#define part_stat_get(part, field) ((part)->dkstats.field) -#define part_stat_get_cpu(part, field, cpu) part_stat_get(part, field) -#define part_stat_read(part, field) part_stat_get(part, field) - -static inline void part_stat_set_all(struct hd_struct *part, int value) -{ - memset(&part->dkstats, value, sizeof(struct disk_stats)); -} - -static inline int init_part_stats(struct hd_struct *part) -{ - return 1; -} - -static inline void free_part_stats(struct hd_struct *part) -{ -} - -#endif /* CONFIG_SMP */ - #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ part_stat_read(part, field[STAT_WRITE]) + \ -- cgit v1.2.3 From 8ab1d40a646e753adb6814642432a093d93dbf47 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 27 May 2020 07:24:17 +0200 Subject: block: remove rcu_read_lock() from part_stat_lock() The RCU lock is required only in disk_map_sector_rcu() to lookup the partition. After that request holds reference to related hd_struct. Replace get_cpu() with preempt_disable() - returned cpu index is unused. [hch: rebased] Signed-off-by: Konstantin Khlebnikov Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/part_stat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 6644197980b9..a6b0938ce82e 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -21,8 +21,8 @@ struct disk_stats { * * part_stat_read() can be called at any time. */ -#define part_stat_lock() ({ rcu_read_lock(); get_cpu(); }) -#define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) +#define part_stat_lock() preempt_disable() +#define part_stat_unlock() preempt_enable() #define part_stat_get_cpu(part, field, cpu) \ (per_cpu_ptr((part)->dkstats, (cpu))->field) -- cgit v1.2.3 From b2d76adbc0828e0f108567973bcc500ed1abc139 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 27 May 2020 07:24:18 +0200 Subject: block: use __this_cpu_add() instead of access by smp_processor_id() Most architectures have fast path to access percpu for current cpu. The required preempt_disable() is provided by part_stat_lock(). [hch: rebased] Signed-off-by: Konstantin Khlebnikov Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/part_stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index a6b0938ce82e..24125778ef3e 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -54,7 +54,7 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) part_stat_read(part, field[STAT_DISCARD])) #define __part_stat_add(part, field, addnd) \ - (part_stat_get(part, field) += (addnd)) + __this_cpu_add((part)->dkstats->field, addnd) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ -- cgit v1.2.3 From 4946ea5c1237036155c3b3a24f049fd5f849f8f6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 27 May 2020 12:24:10 +0200 Subject: netfilter: nf_conntrack_pptp: fix compilation warning with W=1 build >> include/linux/netfilter/nf_conntrack_pptp.h:13:20: warning: 'const' type qualifier on return type has no effect [-Wignored-qualifiers] extern const char *const pptp_msg_name(u_int16_t msg); ^~~~~~ Reported-by: kbuild test robot Fixes: 4c559f15efcc ("netfilter: nf_conntrack_pptp: prevent buffer overflows in debug code") Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_pptp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index 6a4ff6d5ebc2..a28aa289afdc 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -10,7 +10,7 @@ #include #include -extern const char *const pptp_msg_name(u_int16_t msg); +const char *pptp_msg_name(u_int16_t msg); /* state of the control session */ enum pptp_ctrlsess_state { -- cgit v1.2.3 From 521376741b2c26fe53a1ec24d02da24d477eb739 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 20 May 2020 17:22:00 +0200 Subject: PCI/ATS: Only enable ATS for trusted devices Add pci_ats_supported(), which checks whether a device has an ATS capability, and whether it is trusted. A device is untrusted if it is plugged into an external-facing port such as Thunderbolt and could be spoofing an existing device to exploit weaknesses in the IOMMU configuration. PCIe ATS is one such weaknesses since it allows endpoints to cache IOMMU translations and emit transactions with 'Translated' Address Type (10b) that partially bypass the IOMMU translation. The SMMUv3 and VT-d IOMMU drivers already disallow ATS and transactions with 'Translated' Address Type for untrusted devices. Add the check to pci_enable_ats() to let other drivers (AMD IOMMU for now) benefit from it. By checking ats_cap, the pci_ats_supported() helper also returns whether ATS was globally disabled with pci=noats, and could later include more things, for example whether the whole PCIe hierarchy down to the endpoint supports ATS. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Joerg Roedel Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200520152201.3309416-2-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- 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 d08f0869f121..f75c307f346d 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -6,11 +6,14 @@ #ifdef CONFIG_PCI_ATS /* Address Translation Service */ +bool pci_ats_supported(struct pci_dev *dev); int pci_enable_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); int pci_ats_page_aligned(struct pci_dev *dev); #else /* CONFIG_PCI_ATS */ +static inline bool pci_ats_supported(struct pci_dev *d) +{ return false; } static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } static inline void pci_disable_ats(struct pci_dev *d) { } -- cgit v1.2.3 From ad1e4f74c072eaa2c6d77dd710db31aafecd614f Mon Sep 17 00:00:00 2001 From: Domenico Andreoli Date: Tue, 19 May 2020 20:14:10 +0200 Subject: PM: hibernate: Restrict writes to the resume device Hibernation via snapshot device requires write permission to the swap block device, the one that more often (but not necessarily) is used to store the hibernation image. With this patch, such permissions are granted iff: 1) snapshot device config option is enabled 2) swap partition is used as resume device In other circumstances the swap device is not writable from userspace. In order to achieve this, every write attempt to a swap device is checked against the device configured as part of the uswsusp API [0] using a pointer to the inode struct in memory. If the swap device being written was not configured for resuming, the write request is denied. NOTE: this implementation works only for swap block devices, where the inode configured by swapon (which sets S_SWAPFILE) is the same used by SNAPSHOT_SET_SWAP_AREA. In case of swap file, SNAPSHOT_SET_SWAP_AREA indeed receives the inode of the block device containing the filesystem where the swap file is located (+ offset in it) which is never passed to swapon and then has not set S_SWAPFILE. As result, the swap file itself (as a file) has never an option to be written from userspace. Instead it remains writable if accessed directly from the containing block device, which is always writeable from root. [0] Documentation/power/userland-swsusp.rst v2: - rename is_hibernate_snapshot_dev() to is_hibernate_resume_dev() - fix description so to correctly refer to the resume device Signed-off-by: Domenico Andreoli Acked-by: Darrick J. Wong Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 4fcc6fd0cbd6..b960098acfb0 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -466,6 +466,12 @@ static inline bool system_entering_hibernation(void) { return false; } static inline bool hibernation_available(void) { return false; } #endif /* CONFIG_HIBERNATION */ +#ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV +int is_hibernate_resume_dev(const struct inode *); +#else +static inline int is_hibernate_resume_dev(const struct inode *i) { return 0; } +#endif + /* Hibernation and suspend events */ #define PM_HIBERNATION_PREPARE 0x0001 /* Going to hibernate */ #define PM_POST_HIBERNATION 0x0002 /* Hibernation finished */ -- cgit v1.2.3 From f17936993af054b16725d0c54baa58115f9e052a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 27 May 2020 15:54:55 +0300 Subject: fanotify: turn off support for FAN_DIR_MODIFY FAN_DIR_MODIFY has been enabled by commit 44d705b0370b ("fanotify: report name info for FAN_DIR_MODIFY event") in 5.7-rc1. Now we are planning further extensions to the fanotify API and during that we realized that FAN_DIR_MODIFY may behave slightly differently to be more consistent with extensions we plan. So until we finalize these extensions, let's not bind our hands with exposing FAN_DIR_MODIFY to userland. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 3049a6c06d9e..b79fa9bb7359 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -47,8 +47,7 @@ * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. */ -#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ - FAN_DIR_MODIFY) +#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ -- cgit v1.2.3 From f18e26af6aba778b888044859d9c69bb9bbc7bc1 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 26 May 2020 14:54:38 +0300 Subject: RDMA/mlx5: Convert modify QP to use MLX5_SET macros Instead of hand crafted mlx5_qp_context and mlx5_qp_path use common MLX5_SET() macros. Link: https://lore.kernel.org/r/20200526115440.205922-7-leon@kernel.org Reviewed-by: Maor Gottlieb Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/qp.h | 66 ------------------------------------------------- 1 file changed, 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index def601199a1a..b8992b861ae6 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -495,72 +495,6 @@ struct mlx5_core_dct { struct completion drained; }; -struct mlx5_qp_path { - u8 fl_free_ar; - u8 rsvd3; - __be16 pkey_index; - u8 rsvd0; - u8 grh_mlid; - __be16 rlid; - u8 ackto_lt; - u8 mgid_index; - u8 static_rate; - u8 hop_limit; - __be32 tclass_flowlabel; - union { - u8 rgid[16]; - u8 rip[16]; - }; - u8 f_dscp_ecn_prio; - u8 ecn_dscp; - __be16 udp_sport; - u8 dci_cfi_prio_sl; - u8 port; - u8 rmac[6]; -}; - -/* FIXME: use mlx5_ifc.h qpc */ -struct mlx5_qp_context { - __be32 flags; - __be32 flags_pd; - u8 mtu_msgmax; - u8 rq_size_stride; - __be16 sq_crq_size; - __be32 qp_counter_set_usr_page; - __be32 wire_qpn; - __be32 log_pg_sz_remote_qpn; - struct mlx5_qp_path pri_path; - struct mlx5_qp_path alt_path; - __be32 params1; - u8 reserved2[4]; - __be32 next_send_psn; - __be32 cqn_send; - __be32 deth_sqpn; - u8 reserved3[4]; - __be32 last_acked_psn; - __be32 ssn; - __be32 params2; - __be32 rnr_nextrecvpsn; - __be32 xrcd; - __be32 cqn_recv; - __be64 db_rec_addr; - __be32 qkey; - __be32 rq_type_srqn; - __be32 rmsn; - __be16 hw_sq_wqe_counter; - __be16 sw_sq_wqe_counter; - __be16 hw_rcyclic_byte_counter; - __be16 hw_rq_counter; - __be16 sw_rcyclic_byte_counter; - __be16 sw_rq_counter; - u8 rsvd0[5]; - u8 cgs; - u8 cs_req; - u8 cs_res; - __be64 dc_access_key; - u8 rsvd1[24]; -}; - int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); -- cgit v1.2.3 From 3910ebaca8eae0cb9d41a20efe1bcb375ec64dfb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Tue, 26 May 2020 21:39:05 +0000 Subject: PCI: Rename _DSM constants to align with spec MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename PCI-related _DSM constants to align them with the PCI Firmware Spec, r3.2, sec 4.6. No functional change intended. Link: https://lore.kernel.org/r/20200526213905.2479381-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- include/linux/pci-acpi.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 2d155bfb8fbf..a3bb8e768778 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -107,10 +107,12 @@ static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { } #endif extern const guid_t pci_acpi_dsm_guid; -#define IGNORE_PCI_BOOT_CONFIG_DSM 0x05 -#define DEVICE_LABEL_DSM 0x07 -#define RESET_DELAY_DSM 0x08 -#define FUNCTION_DELAY_DSM 0x09 + +/* _DSM Definitions for PCI */ +#define DSM_PCI_PRESERVE_BOOT_CONFIG 0x05 +#define DSM_PCI_DEVICE_NAME 0x07 +#define DSM_PCI_POWER_ON_RESET_DELAY 0x08 +#define DSM_PCI_DEVICE_READINESS_DURATIONS 0x09 #ifdef CONFIG_PCIE_EDR void pci_acpi_add_edr_notifier(struct pci_dev *pdev); -- cgit v1.2.3 From 7a15b2e013f535a125ad7351ffc808c79bc6de35 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 20:22:29 +0200 Subject: net: remove kernel_getsockopt No users left. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/net.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 6451425e828f..74ef5d7315f7 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -303,8 +303,6 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); -int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, - int *optlen); int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, -- cgit v1.2.3 From 1ac71ec0130cce5bed3ec11ffc88651097a24173 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 28 Apr 2020 08:47:43 +0000 Subject: mtd: spi-nor: Fix SPI NOR acronym The correct terminology is serial NOR flash or SPI NOR. s/SPI-NOR/SPI NOR and s/spi-nor/SPI NOR across the subsystem. Signed-off-by: Tudor Ambarus Reviewed-by: Sergei Shtylyov --- include/linux/mtd/spi-nor.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index bebff2729c18..60bac2c0ec45 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -302,7 +302,7 @@ struct spi_nor; * @read: read data from the SPI NOR. * @write: write data to the SPI NOR. * @erase: erase a sector of the SPI NOR at the offset @offs; if - * not provided by the driver, spi-nor will send the erase + * not provided by the driver, SPI NOR will send the erase * opcode via write_reg(). */ struct spi_nor_controller_ops { @@ -336,7 +336,7 @@ struct spi_nor_flash_parameter; * layer is not DMA-able * @bouncebuf_size: size of the bounce buffer * @info: SPI NOR part JEDEC MFR ID and other info - * @manufacturer: spi-nor manufacturer + * @manufacturer: SPI NOR manufacturer * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes * @erase_opcode: the opcode for erasing a sector @@ -344,12 +344,12 @@ struct spi_nor_flash_parameter; * @read_dummy: the dummy needed by the read operation * @program_opcode: the program opcode * @sst_write_second: used by the SST write operation - * @flags: flag options for the current SPI-NOR (SNOR_F_*) + * @flags: flag options for the current SPI NOR (SNOR_F_*) * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @controller_ops: SPI NOR controller driver specific operations. - * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. + * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and * settings that can be overwritten by the spi_nor_fixups * hooks, or dynamically when parsing the SFDP tables. -- cgit v1.2.3 From 91710728d1725de51d06b40674abf6e860d592c7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 27 May 2020 22:11:13 +0200 Subject: locking: Introduce local_lock() preempt_disable() and local_irq_disable/save() are in principle per CPU big kernel locks. This has several downsides: - The protection scope is unknown - Violation of protection rules is hard to detect by instrumentation - For PREEMPT_RT such sections, unless in low level critical code, can violate the preemptability constraints. To address this PREEMPT_RT introduced the concept of local_locks which are strictly per CPU. The lock operations map to preempt_disable(), local_irq_disable/save() and the enabling counterparts on non RT enabled kernels. If lockdep is enabled local locks gain a lock map which tracks the usage context. This will catch cases where an area is protected by preempt_disable() but the access also happens from interrupt context. local locks have identified quite a few such issues over the years, the most recent example is: b7d5dc21072cd ("random: add a spinlock_t to struct batched_entropy") Aside of the lockdep coverage this also improves code readability as it precisely annotates the protection scope. PREEMPT_RT substitutes these local locks with 'sleeping' spinlocks to protect such sections while maintaining preemtability and CPU locality. local locks can replace: - preempt_enable()/disable() pairs - local_irq_disable/enable() pairs - local_irq_save/restore() pairs They are also used to replace code which implicitly disables preemption like: - get_cpu()/put_cpu() - get_cpu_var()/put_cpu_var() with PREEMPT_RT friendly constructs. Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-2-bigeasy@linutronix.de --- include/linux/local_lock.h | 54 ++++++++++++++++++++++ include/linux/local_lock_internal.h | 90 +++++++++++++++++++++++++++++++++++++ 2 files changed, 144 insertions(+) create mode 100644 include/linux/local_lock.h create mode 100644 include/linux/local_lock_internal.h (limited to 'include/linux') diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h new file mode 100644 index 000000000000..e55010fa7329 --- /dev/null +++ b/include/linux/local_lock.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LOCAL_LOCK_H +#define _LINUX_LOCAL_LOCK_H + +#include + +/** + * local_lock_init - Runtime initialize a lock instance + */ +#define local_lock_init(lock) __local_lock_init(lock) + +/** + * local_lock - Acquire a per CPU local lock + * @lock: The lock variable + */ +#define local_lock(lock) __local_lock(lock) + +/** + * local_lock_irq - Acquire a per CPU local lock and disable interrupts + * @lock: The lock variable + */ +#define local_lock_irq(lock) __local_lock_irq(lock) + +/** + * local_lock_irqsave - Acquire a per CPU local lock, save and disable + * interrupts + * @lock: The lock variable + * @flags: Storage for interrupt flags + */ +#define local_lock_irqsave(lock, flags) \ + __local_lock_irqsave(lock, flags) + +/** + * local_unlock - Release a per CPU local lock + * @lock: The lock variable + */ +#define local_unlock(lock) __local_unlock(lock) + +/** + * local_unlock_irq - Release a per CPU local lock and enable interrupts + * @lock: The lock variable + */ +#define local_unlock_irq(lock) __local_unlock_irq(lock) + +/** + * local_unlock_irqrestore - Release a per CPU local lock and restore + * interrupt flags + * @lock: The lock variable + * @flags: Interrupt flags to restore + */ +#define local_unlock_irqrestore(lock, flags) \ + __local_unlock_irqrestore(lock, flags) + +#endif diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h new file mode 100644 index 000000000000..4a8795b21d77 --- /dev/null +++ b/include/linux/local_lock_internal.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LOCAL_LOCK_H +# error "Do not include directly, include linux/local_lock.h" +#endif + +#include +#include + +typedef struct { +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; + struct task_struct *owner; +#endif +} local_lock_t; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define LL_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_CONFIG, \ + } +#else +# define LL_DEP_MAP_INIT(lockname) +#endif + +#define INIT_LOCAL_LOCK(lockname) { LL_DEP_MAP_INIT(lockname) } + +#define __local_lock_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\ +} while (0) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline void local_lock_acquire(local_lock_t *l) +{ + lock_map_acquire(&l->dep_map); + DEBUG_LOCKS_WARN_ON(l->owner); + l->owner = current; +} + +static inline void local_lock_release(local_lock_t *l) +{ + DEBUG_LOCKS_WARN_ON(l->owner != current); + l->owner = NULL; + lock_map_release(&l->dep_map); +} + +#else /* CONFIG_DEBUG_LOCK_ALLOC */ +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ + +#define __local_lock(lock) \ + do { \ + preempt_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_lock_irq(lock) \ + do { \ + local_irq_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_lock_irqsave(lock, flags) \ + do { \ + local_irq_save(flags); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + preempt_enable(); \ + } while (0) + +#define __local_unlock_irq(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + local_irq_enable(); \ + } while (0) + +#define __local_unlock_irqrestore(lock, flags) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + local_irq_restore(flags); \ + } while (0) -- cgit v1.2.3 From cfa6705d89b6562f79c40c249f8d94073c4276e4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 27 May 2020 22:11:14 +0200 Subject: radix-tree: Use local_lock for protection The radix-tree and idr preload mechanisms use preempt_disable() to protect the complete operation between xxx_preload() and xxx_preload_end(). As the code inside the preempt disabled section acquires regular spinlocks, which are converted to 'sleeping' spinlocks on a PREEMPT_RT kernel and eventually calls into a memory allocator, this conflicts with the RT semantics. Convert it to a local_lock which allows RT kernels to substitute them with a real per CPU lock. On non RT kernels this maps to preempt_disable() as before, but provides also lockdep coverage of the critical region. No functional change. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-3-bigeasy@linutronix.de --- include/linux/idr.h | 2 +- include/linux/radix-tree.h | 11 ++++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index ac6e946b6767..3ade03e5c7af 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -171,7 +171,7 @@ static inline bool idr_is_empty(const struct idr *idr) */ static inline void idr_preload_end(void) { - preempt_enable(); + local_unlock(&radix_tree_preloads.lock); } /** diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 63e62372443a..c2a9f7c90727 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -16,11 +16,20 @@ #include #include #include +#include /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node +struct radix_tree_preload { + local_lock_t lock; + unsigned nr; + /* nodes->parent points to next preallocated node */ + struct radix_tree_node *nodes; +}; +DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); + /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: @@ -245,7 +254,7 @@ int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { - preempt_enable(); + local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, -- cgit v1.2.3 From b01b2141999936ac3e4746b7f76c0f204ae4b445 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 27 May 2020 22:11:15 +0200 Subject: mm/swap: Use local_lock for protection The various struct pagevec per CPU variables are protected by disabling either preemption or interrupts across the critical sections. Inside these sections spinlocks have to be acquired. These spinlocks are regular spinlock_t types which are converted to "sleeping" spinlocks on PREEMPT_RT enabled kernels. Obviously sleeping locks cannot be acquired in preemption or interrupt disabled sections. local locks provide a trivial way to substitute preempt and interrupt disable instances. On a non PREEMPT_RT enabled kernel local_lock() maps to preempt_disable() and local_lock_irq() to local_irq_disable(). Create lru_rotate_pvecs containing the pagevec and the locallock. Create lru_pvecs containing the remaining pagevecs and the locallock. Add lru_add_drain_cpu_zone() which is used from compact_zone() to avoid exporting the pvec structure. Change the relevant call sites to acquire these locks instead of using preempt_disable() / get_cpu() / get_cpu_var() and local_irq_disable() / local_irq_save(). There is neither a functional change nor a change in the generated binary code for non PREEMPT_RT enabled non-debug kernels. When lockdep is enabled local locks have lockdep maps embedded. These allow lockdep to validate the protections, i.e. inappropriate usage of a preemption only protected sections would result in a lockdep warning while the same problem would not be noticed with a plain preempt_disable() based protection. local locks also improve readability as they provide a named scope for the protections while preempt/interrupt disable are opaque scopeless. Finally local locks allow PREEMPT_RT to substitute them with real locking primitives to ensure the correctness of operation in a fully preemptible kernel. [ bigeasy: Adopted to use local_lock ] Signed-off-by: Ingo Molnar Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-4-bigeasy@linutronix.de --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e1bbf7a16b27..25181d2dd0b9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -337,6 +337,7 @@ extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); +extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); -- cgit v1.2.3 From 4b44a21dd640b692d4e9b12d3e37c24825f90baa Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 26 May 2020 18:11:02 +0200 Subject: irq_work, smp: Allow irq_work on call_single_queue Currently irq_work_queue_on() will issue an unconditional arch_send_call_function_single_ipi() and has the handler do irq_work_run(). This is unfortunate in that it makes the IPI handler look at a second cacheline and it misses the opportunity to avoid the IPI. Instead note that struct irq_work and struct __call_single_data are very similar in layout, so use a few bits in the flags word to encode a type and stick the irq_work on the call_single_queue list. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200526161908.011635912@infradead.org --- include/linux/irq_work.h | 7 ++++++- include/linux/smp.h | 23 ++++++++++++++++++++++- 2 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 3b752e80c017..f23a359c8f46 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -13,6 +13,8 @@ * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed */ +/* flags share CSD_FLAG_ space */ + #define IRQ_WORK_PENDING BIT(0) #define IRQ_WORK_BUSY BIT(1) @@ -23,9 +25,12 @@ #define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) +/* + * structure shares layout with single_call_data_t. + */ struct irq_work { - atomic_t flags; struct llist_node llnode; + atomic_t flags; void (*func)(struct irq_work *); }; diff --git a/include/linux/smp.h b/include/linux/smp.h index cbc9162689d0..45ad6e30f398 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -16,17 +16,38 @@ typedef void (*smp_call_func_t)(void *info); typedef bool (*smp_cond_func_t)(int cpu, void *info); + +enum { + CSD_FLAG_LOCK = 0x01, + + /* IRQ_WORK_flags */ + + CSD_TYPE_ASYNC = 0x00, + CSD_TYPE_SYNC = 0x10, + CSD_TYPE_IRQ_WORK = 0x20, + CSD_FLAG_TYPE_MASK = 0xF0, +}; + +/* + * structure shares (partial) layout with struct irq_work + */ struct __call_single_data { struct llist_node llist; + unsigned int flags; smp_call_func_t func; void *info; - unsigned int flags; }; /* Use __aligned() to avoid to use 2 cache lines for 1 csd */ typedef struct __call_single_data call_single_data_t __aligned(sizeof(struct __call_single_data)); +/* + * Enqueue a llist_node on the call_single_queue; be very careful, read + * flush_smp_call_function_queue() in detail. + */ +extern void __smp_call_single_queue(int cpu, struct llist_node *node); + /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; -- cgit v1.2.3 From a148866489fbe243c936fe43e4525d8dbfa0318f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 26 May 2020 18:11:04 +0200 Subject: sched: Replace rq::wake_list The recent commit: 90b5363acd47 ("sched: Clean up scheduler_ipi()") got smp_call_function_single_async() subtly wrong. Even though it will return -EBUSY when trying to re-use a csd, that condition is not atomic and still requires external serialization. The change in ttwu_queue_remote() got this wrong. While on first reading ttwu_queue_remote() has an atomic test-and-set that appears to serialize the use, the matching 'release' is not in the right place to actually guarantee this serialization. The actual race is vs the sched_ttwu_pending() call in the idle loop; that can run the wakeup-list without consuming the CSD. Instead of trying to chain the lists, merge them. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200526161908.129371594@infradead.org --- include/linux/sched.h | 1 + include/linux/smp.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ebc68706152a..e0f5f41cf2ee 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -654,6 +654,7 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; + unsigned int wake_entry_type; int on_cpu; #ifdef CONFIG_THREAD_INFO_IN_TASK /* Current CPU: */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 45ad6e30f398..84f90e24ed6f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -25,6 +25,7 @@ enum { CSD_TYPE_ASYNC = 0x00, CSD_TYPE_SYNC = 0x10, CSD_TYPE_IRQ_WORK = 0x20, + CSD_TYPE_TTWU = 0x30, CSD_FLAG_TYPE_MASK = 0xF0, }; -- cgit v1.2.3 From 6db96e5810e0a6a345b7d78549de7676ae5b2662 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 13 Apr 2020 10:46:03 +0800 Subject: mmc: host: Introduce the request_atomic() for the host The SD host controller can process one request in the atomic context if the card is nonremovable, which means we can submit next request in the irq hard handler when using the MMC host software queue to reduce the latency. Thus this patch adds a new API request_atomic() for the host controller, as well as adding support for host software queue to submit a request by the new request_atomic() API. Moreover there is an unusual case that the card is busy when trying to send a command, and we can not polling the card status in interrupt context by using request_atomic() to dispatch requests. Thus we should queue a work to try again in the non-atomic context in case the host releases the busy signal later. Suggested-by: Adrian Hunter Acked-by: Adrian Hunter Signed-off-by: Baolin Wang Link: https://lore.kernel.org/r/a344e27e506cb2329073cbd5cf65e15cc3cbeba9.1586744073.git.baolin.wang7@gmail.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c318fb5b6a94..d4a50e5dc111 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -92,6 +92,9 @@ struct mmc_host_ops { int err); void (*pre_req)(struct mmc_host *host, struct mmc_request *req); void (*request)(struct mmc_host *host, struct mmc_request *req); + /* Submit one request to host in atomic context. */ + int (*request_atomic)(struct mmc_host *host, + struct mmc_request *req); /* * Avoid calling the next three functions too often or in a "fast -- cgit v1.2.3 From 064f7e58ee42372be05ec87fdf57864c7475ba93 Mon Sep 17 00:00:00 2001 From: Krishna Konda Date: Fri, 1 May 2020 19:23:01 +0530 Subject: mmc: core: expose info about enhanced rpmb support Following eMMC JEDEC JESD84-B51 standard, an enhanced form of rpmb is supported. What this enhanced mode supports is in addition to be able to write one rpmb or two rpmb frames at a time, 32 frames can be written at a time. Expose this information present in ext csd field so that the user space application that wants to make use of this can do so. Signed-off-by: Krishna Konda Signed-off-by: Veerabhadrarao Badiganti Link: https://lore.kernel.org/r/1588341189-4371-1-git-send-email-vbadigan@codeaurora.org Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 1 + include/linux/mmc/mmc.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index cf3780a6ccc4..7d46411ffaa2 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -48,6 +48,7 @@ struct mmc_ext_csd { u8 sec_feature_support; u8 rel_sectors; u8 rel_param; + bool enhanced_rpmb_supported; u8 part_config; u8 cache_ctrl; u8 rst_n_function; diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 4b85ef05a906..d9a65c6a8816 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -325,6 +325,7 @@ static inline bool mmc_ready_for_data(u32 status) */ #define EXT_CSD_WR_REL_PARAM_EN (1<<2) +#define EXT_CSD_WR_REL_PARAM_EN_RPMB_REL_WR (1<<4) #define EXT_CSD_BOOT_WP_B_PWR_WP_DIS (0x40) #define EXT_CSD_BOOT_WP_B_PERM_WP_DIS (0x10) -- cgit v1.2.3 From 30e1028dcef9ac981c20df83983e0e77a4df2dc4 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 2 May 2020 16:28:25 +0200 Subject: mmc: sdhci-esdhc: update contact email The 'pengutronix' address is defunct for years. Use the proper contact address. Signed-off-by: Wolfram Sang Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20200502142840.19418-1-wsa@kernel.org Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-esdhc-imx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index 0434f68eda86..cba1184b364c 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright 2010 Wolfram Sang + * Copyright 2010 Wolfram Sang */ #ifndef __ASM_ARCH_IMX_ESDHC_H -- cgit v1.2.3 From f4f20d6897b1c047c5d38b2cfc50928e83d8fd83 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:22:18 -0500 Subject: memstick: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507192218.GA16315@embeddedor Signed-off-by: Ulf Hansson --- include/linux/memstick.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index 216a713bef7f..da4c65f9435f 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -288,7 +288,7 @@ struct memstick_host { int (*set_param)(struct memstick_host *host, enum memstick_param param, int value); - unsigned long private[0] ____cacheline_aligned; + unsigned long private[] ____cacheline_aligned; }; struct memstick_driver { -- cgit v1.2.3 From 1be64c7963f89afbd6f96f27effea20900650dfe Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 8 May 2020 13:29:02 +0200 Subject: mmc: host: Drop redundant MMC_CAP_ERASE The MMC_CAP_ERASE bit is no longer used by the mmc core as erase, discard and trim operations are now always supported. Therefore, drop the bit and move all mmc hosts away from using it. Signed-off-by: Ulf Hansson Reviewed-by: Rui Miguel Silva Link: https://lore.kernel.org/r/20200508112902.23575-1-ulf.hansson@linaro.org Reviewed-by: Linus Walleij --- include/linux/mmc/host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index d4a50e5dc111..7149bab555d7 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -321,7 +321,6 @@ struct mmc_host { #define MMC_CAP_AGGRESSIVE_PM (1 << 7) /* Suspend (e)MMC/SD at idle */ #define MMC_CAP_NONREMOVABLE (1 << 8) /* Nonremovable e.g. eMMC */ #define MMC_CAP_WAIT_WHILE_BUSY (1 << 9) /* Waits while card is busy */ -#define MMC_CAP_ERASE (1 << 10) /* Allow erase/trim commands */ #define MMC_CAP_3_3V_DDR (1 << 11) /* Host supports eMMC DDR 3.3V */ #define MMC_CAP_1_8V_DDR (1 << 12) /* Host supports eMMC DDR 1.8V */ #define MMC_CAP_1_2V_DDR (1 << 13) /* Host supports eMMC DDR 1.2V */ -- cgit v1.2.3 From 991f5c4dd2422881c933ec3c7c19f3a2a1858cc4 Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Mon, 18 May 2020 21:17:39 +0200 Subject: m68k: mcf5441x: add support for esdhc mmc controller Add support for sdhci-edshc mmc controller. Signed-off-by: Angelo Dureghello Acked-by: Greg Ungerer Link: https://lore.kernel.org/r/20200518191742.1251440-1-angelo.dureghello@timesys.com Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-esdhc-mcf.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/platform_data/mmc-esdhc-mcf.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-esdhc-mcf.h b/include/linux/platform_data/mmc-esdhc-mcf.h new file mode 100644 index 000000000000..85cb786a62fe --- /dev/null +++ b/include/linux/platform_data/mmc-esdhc-mcf.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_PLATFORM_DATA_MCF_ESDHC_H__ +#define __LINUX_PLATFORM_DATA_MCF_ESDHC_H__ + +enum cd_types { + ESDHC_CD_NONE, /* no CD, neither controller nor gpio */ + ESDHC_CD_CONTROLLER, /* mmc controller internal CD */ + ESDHC_CD_PERMANENT, /* no CD, card permanently wired to host */ +}; + +struct mcf_esdhc_platform_data { + int max_bus_width; + int cd_type; +}; + +#endif /* __LINUX_PLATFORM_DATA_MCF_ESDHC_H__ */ -- cgit v1.2.3 From 4bc90f492230af6661bc2021dddd501f7c842334 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:02 +0200 Subject: mmc: sdio: Fix macro name for Marvell device with ID 0x9134 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Marvell SDIO device ID 0x9134 is used in SDIO Common CIS (Card Information Structure) and not in SDIO wlan function (with ID 1). SDIO Common CIS is accessed by function ID 0. So change this misleading macro name to SDIO_DEVICE_ID_MARVELL_8887_F0 as it does not refer to wlan function. It refers to function 0. Wlan module on this SDIO card is available at function ID 1 and is identified by different SDIO device ID 0x9135. Kernel quirks for SDIO devices are matched against device ID from SDIO Common CIS. Therefore device ID used in quirk is correct, just has misleading name. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-2-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 2e9a6e4634eb..96f43e0dc78f 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -59,7 +59,7 @@ #define SDIO_DEVICE_ID_MARVELL_8688WLAN 0x9104 #define SDIO_DEVICE_ID_MARVELL_8688BT 0x9105 #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 -#define SDIO_DEVICE_ID_MARVELL_8887WLAN 0x9134 +#define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 #define SDIO_VENDOR_ID_MEDIATEK 0x037a -- cgit v1.2.3 From b75b7ca7c27dfd61dba368f390b7d4dc20b3a8cb Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Mon, 25 Nov 2019 13:24:03 -0600 Subject: fs: remove dio_end_io() Since we removed the last user of dio_end_io(), remove the helper function dio_end_io(). Reviewed-by: Nikolay Borisov Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 366c533d30cd..e84623d5e173 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3187,8 +3187,6 @@ enum { DIO_SKIP_HOLES = 0x02, }; -void dio_end_io(struct bio *bio); - ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, -- cgit v1.2.3 From dc35ada4251f183137ee3a524543c9329d7a4fa2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 15:41:23 +0200 Subject: block: fix a warning when blkdev.h is included for !CONFIG_BLOCK builds disk_start_io_acct and disk_end_io_acct need at least a struct gendisk forward declaration, but for weird historic reasons much of blkdev.h is stubbed out for CONFIG_BLOCK=n. Fix this by stubbing more out for now, but eventually this header will need a massive cleanup. Fixes: 956d510ee78 ("block: add disk/bio-based accounting helpers") Reported-by: Stephen Rothwell Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6f7ff0fa8fcf..8fd900998b4e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1892,12 +1892,12 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } +#ifdef CONFIG_BLOCK unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); -#ifdef CONFIG_BLOCK /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for -- cgit v1.2.3 From 1597b374af22266266e1e20612208c4b11359ad4 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 28 May 2020 17:28:04 +0300 Subject: hwmon: Add notification support For hwmon drivers using the hwmon_device_register_with_info() API, it is desirable to have a generic notification mechanism available. This mechanism can be used to notify userspace as well as the thermal subsystem if the driver experiences any events, such as warning or critical alarms. Implement hwmon_notify_event() to provide this mechanism. The function generates a sysfs event and a udev event. If the device is registered with the thermal subsystem and the event is associated with a temperature sensor, also notify the thermal subsystem that a thermal event occurred. Signed-off-by: Guenter Roeck Signed-off-by: Serge Semin Cc: Maxim Kaurkin Cc: Alexey Malahov Cc: Thomas Bogendoerfer Cc: Arnd Bergmann Cc: Rob Herring Cc: linux-mips@vger.kernel.org Cc: devicetree@vger.kernel.org Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 5e609f25878c..363d4a814aa1 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -436,6 +436,9 @@ devm_hwmon_device_register_with_info(struct device *dev, void hwmon_device_unregister(struct device *dev); void devm_hwmon_device_unregister(struct device *dev); +int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel); + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered -- cgit v1.2.3 From 655078f5f5286fe0ab38e90c4695001a0e15e9dd Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:55:57 +0200 Subject: kobject: increase allowed number of uevent variables SBS battery driver exposes 32 power supply properties now, which will result in uevent failure on (un)plugging the battery. Other drivers (e.g. bq27xxx) are also coming close to this limit, so increase it. Acked-by: Greg Kroah-Hartman Reviewed-by: Emil Velikov Signed-off-by: Sebastian Reichel --- include/linux/kobject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index e2ca0a292e21..75e822569e39 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -29,7 +29,7 @@ #include #define UEVENT_HELPER_PATH_LEN 256 -#define UEVENT_NUM_ENVP 32 /* number of env pointers */ +#define UEVENT_NUM_ENVP 64 /* number of env pointers */ #define UEVENT_BUFFER_SIZE 2048 /* buffer for the variables */ #ifdef CONFIG_UEVENT_HELPER -- cgit v1.2.3 From bac705abcf345c28e419157cfcd1c44032cc9db2 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:55:58 +0200 Subject: power: supply: core: add capacity error margin property Add a property for reporting the error margin expected by fuel gauge chips. Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 1f60731ec7fe..453a85f25635 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -139,6 +139,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_CAPACITY, /* in percents! */ POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN, /* in percents! */ POWER_SUPPLY_PROP_CAPACITY_ALERT_MAX, /* in percents! */ + POWER_SUPPLY_PROP_CAPACITY_ERROR_MARGIN, /* in percents! */ POWER_SUPPLY_PROP_CAPACITY_LEVEL, POWER_SUPPLY_PROP_TEMP, POWER_SUPPLY_PROP_TEMP_MAX, -- cgit v1.2.3 From feabe49e46bb556b8d43e28d4a0d459940f7a5cb Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:55:59 +0200 Subject: power: supply: core: add manufacture date properties Some smart batteries store their manufacture date, which is useful to identify the battery and/or to know about the cell quality. Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 453a85f25635..63ffe2a0a87b 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -159,6 +159,9 @@ enum power_supply_property { POWER_SUPPLY_PROP_PRECHARGE_CURRENT, POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, POWER_SUPPLY_PROP_CALIBRATE, + POWER_SUPPLY_PROP_MANUFACTURE_YEAR, + POWER_SUPPLY_PROP_MANUFACTURE_MONTH, + POWER_SUPPLY_PROP_MANUFACTURE_DAY, /* Properties of type `const char *' */ POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_MANUFACTURER, -- cgit v1.2.3 From 601c2a543f02da484362b3ff9074b2cfe08750de Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:56:00 +0200 Subject: power: supply: core: add POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED Some battery fuel gauges know when the battery needs to be recalibrated before providing usable values. This should be reported via the health property. Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 63ffe2a0a87b..ac1345a48ad0 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -61,6 +61,7 @@ enum { POWER_SUPPLY_HEALTH_WATCHDOG_TIMER_EXPIRE, POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE, POWER_SUPPLY_HEALTH_OVERCURRENT, + POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED, }; enum { -- cgit v1.2.3 From db10538a4b997a77a1fd561adaaa58afc7dcfa2f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:18 +0200 Subject: tcp: add tcp_sock_set_cork Add a helper to directly set the TCP_CORK sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call. Signed-off-by: Christoph Hellwig 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 bf44e85d709d..889eeb2256c2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -497,4 +497,6 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); +void tcp_sock_set_cork(struct sock *sk, bool on); + #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 12abc5ee7873a085cc280240822b8ac53c86fecd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:19 +0200 Subject: tcp: add tcp_sock_set_nodelay Add a helper to directly set the TCP_NODELAY sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call. Signed-off-by: Christoph Hellwig Acked-by: Sagi Grimberg Acked-by: Jason Gunthorpe Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 889eeb2256c2..9e42c7fe50a8 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -498,5 +498,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); void tcp_sock_set_cork(struct sock *sk, bool on); +void tcp_sock_set_nodelay(struct sock *sk); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From ddd061b8daed3ce0c01109a69c9a2a9f9669f01a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:20 +0200 Subject: tcp: add tcp_sock_set_quickack Add a helper to directly set the TCP_QUICKACK sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9e42c7fe50a8..2eaf8320b9db 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -499,5 +499,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); +void tcp_sock_set_quickack(struct sock *sk, int val); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 557eadfcc5ee8f8fa98a795e05ed21db58a65db5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:21 +0200 Subject: tcp: add tcp_sock_set_syncnt Add a helper to directly set the TCP_SYNCNT sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Acked-by: Sagi Grimberg Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2eaf8320b9db..6aa4ae5ebf3d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -500,5 +500,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); +int tcp_sock_set_syncnt(struct sock *sk, int val); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From c488aeadcbd002a992593e6090d54e8ac27c4310 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:22 +0200 Subject: tcp: add tcp_sock_set_user_timeout Add a helper to directly set the TCP_USER_TIMEOUT sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 6aa4ae5ebf3d..de682143efe4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -501,5 +501,6 @@ void tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); +void tcp_sock_set_user_timeout(struct sock *sk, u32 val); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 71c48eb81c9ecb6fed49dc33e7c9b621fdcb7bf8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:23 +0200 Subject: tcp: add tcp_sock_set_keepidle Add a helper to directly set the TCP_KEEP_IDLE sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index de682143efe4..5724dd84a85e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -498,6 +498,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); void tcp_sock_set_cork(struct sock *sk, bool on); +int tcp_sock_set_keepidle(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); -- cgit v1.2.3 From d41ecaac903c9f4658a71d4e7a708673cfb5abba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:24 +0200 Subject: tcp: add tcp_sock_set_keepintvl Add a helper to directly set the TCP_KEEPINTVL sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 5724dd84a85e..1f9bada00faa 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -499,6 +499,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepidle(struct sock *sk, int val); +int tcp_sock_set_keepintvl(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); -- cgit v1.2.3 From 480aeb9639d6a077c611b303a22f9b1e5937d081 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:25 +0200 Subject: tcp: add tcp_sock_set_keepcnt Add a helper to directly set the TCP_KEEPCNT sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1f9bada00faa..9aac824c523c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -498,6 +498,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); void tcp_sock_set_cork(struct sock *sk, bool on); +int tcp_sock_set_keepcnt(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); -- cgit v1.2.3 From 6988f31d558aa8c744464a7f6d91d34ada48ad12 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 27 May 2020 22:20:47 -0700 Subject: mm: remove VM_BUG_ON(PageSlab()) from page_mapcount() Replace superfluous VM_BUG_ON() with comment about correct usage. Technically reverts commit 1d148e218a0d ("mm: add VM_BUG_ON_PAGE() to page_mapcount()"), but context lines have changed. Function isolate_migratepages_block() runs some checks out of lru_lock when choose pages for migration. After checking PageLRU() it checks extra page references by comparing page_count() and page_mapcount(). Between these two checks page could be removed from lru, freed and taken by slab. As a result this race triggers VM_BUG_ON(PageSlab()) in page_mapcount(). Race window is tiny. For certain workload this happens around once a year. page:ffffea0105ca9380 count:1 mapcount:0 mapping:ffff88ff7712c180 index:0x0 compound_mapcount: 0 flags: 0x500000000008100(slab|head) raw: 0500000000008100 dead000000000100 dead000000000200 ffff88ff7712c180 raw: 0000000000000000 0000000080200020 00000001ffffffff 0000000000000000 page dumped because: VM_BUG_ON_PAGE(PageSlab(page)) ------------[ cut here ]------------ kernel BUG at ./include/linux/mm.h:628! invalid opcode: 0000 [#1] SMP NOPTI CPU: 77 PID: 504 Comm: kcompactd1 Tainted: G W 4.19.109-27 #1 Hardware name: Yandex T175-N41-Y3N/MY81-EX0-Y3N, BIOS R05 06/20/2019 RIP: 0010:isolate_migratepages_block+0x986/0x9b0 The code in isolate_migratepages_block() was added in commit 119d6d59dcc0 ("mm, compaction: avoid isolating pinned pages") before adding VM_BUG_ON into page_mapcount(). This race has been predicted in 2015 by Vlastimil Babka (see link below). [akpm@linux-foundation.org: comment tweaks, per Hugh] Fixes: 1d148e218a0d ("mm: add VM_BUG_ON_PAGE() to page_mapcount()") Signed-off-by: Konstantin Khlebnikov Signed-off-by: Andrew Morton Acked-by: Hugh Dickins Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: David Rientjes Cc: Link: http://lkml.kernel.org/r/159032779896.957378.7852761411265662220.stgit@buzz Link: https://lore.kernel.org/lkml/557710E1.6060103@suse.cz/ Link: https://lore.kernel.org/linux-mm/158937872515.474360.5066096871639561424.stgit@buzz/T/ (v1) Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..f3fe7371855c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -782,6 +782,11 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); +/* + * Mapcount of compound page as a whole, does not include mapped sub-pages. + * + * Must be called only for compound pages or any their tail sub-pages. + */ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); @@ -801,10 +806,16 @@ static inline void page_mapcount_reset(struct page *page) int __page_mapcount(struct page *page); +/* + * Mapcount of 0-order page; when compound sub-page, includes + * compound_mapcount(). + * + * Result is undefined for pages which cannot be mapped into userspace. + * For example SLAB or special types of pages. See function page_has_type(). + * They use this place in struct page differently. + */ static inline int page_mapcount(struct page *page) { - VM_BUG_ON_PAGE(PageSlab(page), page); - if (unlikely(PageCompound(page))) return __page_mapcount(page); return atomic_read(&page->_mapcount) + 1; -- cgit v1.2.3 From a8173820f441ab3e2a45c4bb66b70da9a57a349e Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Sat, 23 May 2020 22:41:10 +0530 Subject: gpio: gpiolib: Allow GPIO IRQs to lazy disable With 'commit 461c1a7d4733 ("gpiolib: override irq_enable/disable")' gpiolib overrides irqchip's irq_enable and irq_disable callbacks. If irq_disable callback is implemented then genirq takes unlazy path to disable irq. Underlying irqchip may not want to implement irq_disable callback to lazy disable irq when client drivers invokes disable_irq(). By overriding irq_disable callback, gpiolib ends up always unlazy disabling IRQ. Allow gpiolib to lazy disable IRQs by overriding irq_disable callback only if irqchip implemented irq_disable. In cases where irq_disable is not implemented irq_mask is overridden. Similarly override irq_enable callback only if irqchip implemented irq_enable otherwise irq_unmask is overridden. Fixes: 461c1a7d4733 ("gpiolib: override irq_enable/disable") Signed-off-by: Maulik Shah Tested-by: Hans Verkuil Link: https://lore.kernel.org/r/1590253873-11556-2-git-send-email-mkshah@codeaurora.org Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 8c41ae41b6bb..c8bcaf315d03 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -253,6 +253,19 @@ struct gpio_irq_chip { * Store old irq_chip irq_disable callback */ void (*irq_disable)(struct irq_data *data); + /** + * @irq_unmask: + * + * Store old irq_chip irq_unmask callback + */ + void (*irq_unmask)(struct irq_data *data); + + /** + * @irq_mask: + * + * Store old irq_chip irq_mask callback + */ + void (*irq_mask)(struct irq_data *data); }; /** -- cgit v1.2.3 From 95fc87b44104d9a524ff3e975bbfbd7c1f1a2dd5 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:54 +0530 Subject: vfio: Selective dirty page tracking if IOMMU backed device pins pages Added a check such that only singleton IOMMU groups can pin pages. >From the point when vendor driver pins any pages, consider IOMMU group dirty page scope to be limited to pinned pages. To optimize to avoid walking list often, added flag pinned_page_dirty_scope to indicate if all of the vfio_groups for each vfio_domain in the domain_list dirty page scope is limited to pinned pages. This flag is updated on first pinned pages request for that IOMMU group and on attaching/detaching group. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 5d92ee15d098..38d3c6a8dc7e 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -76,7 +76,9 @@ struct vfio_iommu_driver_ops { struct iommu_group *group); void (*detach_group)(void *iommu_data, struct iommu_group *group); - int (*pin_pages)(void *iommu_data, unsigned long *user_pfn, + int (*pin_pages)(void *iommu_data, + struct iommu_group *group, + unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn); int (*unpin_pages)(void *iommu_data, -- cgit v1.2.3 From 7c6d2ecbda83150b2036a2b36b21381ad4667762 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 28 May 2020 14:57:47 -0700 Subject: net: be more gentle about silly gso requests coming from user Recent change in virtio_net_hdr_to_skb() broke some packetdrill tests. When --mss=XXX option is set, packetdrill always provide gso_type & gso_size for its inbound packets, regardless of packet size. if (packet->tcp && packet->mss) { if (packet->ipv4) gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; gso.gso_size = packet->mss; } Since many other programs could do the same, relax virtio_net_hdr_to_skb() to no longer return an error, but instead ignore gso settings. This keeps Willem intent to make sure no malicious packet could reach gso stack. Note that TCP stack has a special logic in tcp_set_skb_tso_segs() to clear gso_size for small packets. Fixes: 6dd912f82680 ("net: check untrusted gso_size at kernel entry") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 88997022a4b5..e8a924eeea3d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -109,16 +109,17 @@ retry: if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + struct skb_shared_info *shinfo = skb_shinfo(skb); - if (skb->len - p_off <= gso_size) - return -EINVAL; - - skb_shinfo(skb)->gso_size = gso_size; - skb_shinfo(skb)->gso_type = gso_type; + /* Too small packets are not really GSO ones. */ + if (skb->len - p_off > gso_size) { + shinfo->gso_size = gso_size; + shinfo->gso_type = gso_type; - /* Header must be checked, and gso_segs computed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + /* Header must be checked, and gso_segs computed. */ + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; + } } return 0; -- cgit v1.2.3 From 6d3f922c46f2e91f63c92f8dd28381f097082912 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 12 May 2020 15:53:21 +0300 Subject: opp: Add support for parsing interconnect bandwidth The OPP bindings now support bandwidth values, so add support to parse it from device tree and store it into the new dev_pm_opp_icc_bw struct, which is part of the dev_pm_opp. Signed-off-by: Georgi Djakov Reviewed-by: Matthias Kaehlcke [ Viresh: Create _read_bw() and use it, renamed _of_find_icc_paths() to dev_pm_opp_of_find_icc_paths(), exported it and made opp_table argument optional. Also drop the depends on from Kconfig. ] Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 747861816f4f..d5c4a329321d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -41,6 +41,18 @@ struct dev_pm_opp_supply { unsigned long u_amp; }; +/** + * struct dev_pm_opp_icc_bw - Interconnect bandwidth values + * @avg: Average bandwidth corresponding to this OPP (in icc units) + * @peak: Peak bandwidth corresponding to this OPP (in icc units) + * + * This structure stores the bandwidth values for a single interconnect path. + */ +struct dev_pm_opp_icc_bw { + u32 avg; + u32 peak; +}; + /** * struct dev_pm_opp_info - OPP freq/voltage/current values * @rate: Target clk rate in hz @@ -360,6 +372,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); +int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); void dev_pm_opp_of_register_em(struct cpumask *cpus); #else static inline int dev_pm_opp_of_add_table(struct device *dev) @@ -408,6 +421,11 @@ static inline int of_get_required_opp_performance_state(struct device_node *np, { return -ENOTSUPP; } + +static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table) +{ + return -ENOTSUPP; +} #endif #endif /* __LINUX_OPP_H__ */ -- cgit v1.2.3 From 0430b1d5704b0f0f1d237236dde9c143f8669e49 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 18 May 2020 14:25:32 +0300 Subject: opp: Expose bandwidth information via debugfs Expose the bandwidth information as well via debugfs. Signed-off-by: Viresh Kumar Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index 34e97231a6ab..1ad09efd296e 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -32,6 +32,7 @@ struct icc_path *of_icc_get_by_index(struct device *dev, int idx); void icc_put(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); +const char *icc_get_name(struct icc_path *path); #else @@ -65,6 +66,11 @@ static inline void icc_set_tag(struct icc_path *path, u32 tag) { } +static inline const char *icc_get_name(struct icc_path *path) +{ + return NULL; +} + #endif /* CONFIG_INTERCONNECT */ #endif /* __LINUX_INTERCONNECT_H */ -- cgit v1.2.3 From 2849beec3343343b293f33267affbdd7c3f42814 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:03 +0200 Subject: mmc: sdio: Change macro names for Marvell 8688 modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add underscore as separator in Marvell 8688 macro names for better readability and consistency. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-3-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- include/linux/mmc/sdio_ids.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 96f43e0dc78f..7e992a0e6cc0 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -56,8 +56,8 @@ #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 -#define SDIO_DEVICE_ID_MARVELL_8688WLAN 0x9104 -#define SDIO_DEVICE_ID_MARVELL_8688BT 0x9105 +#define SDIO_DEVICE_ID_MARVELL_8688_WLAN 0x9104 +#define SDIO_DEVICE_ID_MARVELL_8688_BT 0x9105 #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 #define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 -- cgit v1.2.3 From 7d14c687376e6bd33cf42028300838466b95e765 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:04 +0200 Subject: mmc: sdio: Move SDIO IDs from mwifiex driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add _WLAN suffix to macro names for consistency with other Marvell macros. These IDs represents wlan function of combo bt/wlan cards. Other functions of these cards have different IDs. Signed-off-by: Pali Rohár Acked-by: Kalle Valo Link: https://lore.kernel.org/r/20200522144412.19712-4-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- include/linux/mmc/sdio_ids.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 7e992a0e6cc0..90361ea7f5ed 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -58,8 +58,18 @@ #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 #define SDIO_DEVICE_ID_MARVELL_8688_WLAN 0x9104 #define SDIO_DEVICE_ID_MARVELL_8688_BT 0x9105 +#define SDIO_DEVICE_ID_MARVELL_8786_WLAN 0x9116 +#define SDIO_DEVICE_ID_MARVELL_8787_WLAN 0x9119 #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 +#define SDIO_DEVICE_ID_MARVELL_8797_WLAN 0x9129 +#define SDIO_DEVICE_ID_MARVELL_8897_WLAN 0x912d #define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 +#define SDIO_DEVICE_ID_MARVELL_8887_WLAN 0x9135 +#define SDIO_DEVICE_ID_MARVELL_8801_WLAN 0x9139 +#define SDIO_DEVICE_ID_MARVELL_8997_F0 0x9140 +#define SDIO_DEVICE_ID_MARVELL_8997_WLAN 0x9141 +#define SDIO_DEVICE_ID_MARVELL_8977_WLAN 0x9145 +#define SDIO_DEVICE_ID_MARVELL_8987_WLAN 0x9149 #define SDIO_VENDOR_ID_MEDIATEK 0x037a -- cgit v1.2.3 From 649c7d76d87ca2285a82a65d86d99ddb60571e20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:05 +0200 Subject: mmc: sdio: Move SDIO IDs from btmrvl driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other Marvell macros. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-5-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- include/linux/mmc/sdio_ids.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 90361ea7f5ed..1237e1048d06 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -60,16 +60,24 @@ #define SDIO_DEVICE_ID_MARVELL_8688_BT 0x9105 #define SDIO_DEVICE_ID_MARVELL_8786_WLAN 0x9116 #define SDIO_DEVICE_ID_MARVELL_8787_WLAN 0x9119 +#define SDIO_DEVICE_ID_MARVELL_8787_BT 0x911a +#define SDIO_DEVICE_ID_MARVELL_8787_BT_AMP 0x911b #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 #define SDIO_DEVICE_ID_MARVELL_8797_WLAN 0x9129 +#define SDIO_DEVICE_ID_MARVELL_8797_BT 0x912a #define SDIO_DEVICE_ID_MARVELL_8897_WLAN 0x912d +#define SDIO_DEVICE_ID_MARVELL_8897_BT 0x912e #define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 #define SDIO_DEVICE_ID_MARVELL_8887_WLAN 0x9135 +#define SDIO_DEVICE_ID_MARVELL_8887_BT 0x9136 #define SDIO_DEVICE_ID_MARVELL_8801_WLAN 0x9139 #define SDIO_DEVICE_ID_MARVELL_8997_F0 0x9140 #define SDIO_DEVICE_ID_MARVELL_8997_WLAN 0x9141 +#define SDIO_DEVICE_ID_MARVELL_8997_BT 0x9142 #define SDIO_DEVICE_ID_MARVELL_8977_WLAN 0x9145 +#define SDIO_DEVICE_ID_MARVELL_8977_BT 0x9146 #define SDIO_DEVICE_ID_MARVELL_8987_WLAN 0x9149 +#define SDIO_DEVICE_ID_MARVELL_8987_BT 0x914a #define SDIO_VENDOR_ID_MEDIATEK 0x037a -- cgit v1.2.3 From baaa110dcacfd704d182a275c4307baecb81423b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:06 +0200 Subject: mmc: sdio: Move SDIO IDs from btmtksdio driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other macros. Signed-off-by: Pali Rohár Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20200522144412.19712-6-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- 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 1237e1048d06..c9aca57d4dea 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -80,6 +80,8 @@ #define SDIO_DEVICE_ID_MARVELL_8987_BT 0x914a #define SDIO_VENDOR_ID_MEDIATEK 0x037a +#define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 +#define SDIO_DEVICE_ID_MEDIATEK_MT7668 0x7668 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 -- cgit v1.2.3 From b8c26a9663e1d888bbf4e14d3a62d033f286623e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:07 +0200 Subject: mmc: sdio: Move SDIO IDs from smssdio driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other Siano macros. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-7-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index c9aca57d4dea..9ec675a7ac37 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -88,6 +88,11 @@ #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 #define SDIO_DEVICE_ID_SIANO_VEGA_A0 0x0300 #define SDIO_DEVICE_ID_SIANO_VENICE 0x0301 +#define SDIO_DEVICE_ID_SIANO_MING 0x0302 +#define SDIO_DEVICE_ID_SIANO_PELE 0x0500 +#define SDIO_DEVICE_ID_SIANO_RIO 0x0600 +#define SDIO_DEVICE_ID_SIANO_DENVER_2160 0x0700 +#define SDIO_DEVICE_ID_SIANO_DENVER_1530 0x0800 #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 -- cgit v1.2.3 From ecc2f3962587aed327ccd3c32e99ccfc9e744fa0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:08 +0200 Subject: mmc: sdio: Move SDIO IDs from ath6kl driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also replace generic MANUFACTURER macros by proper SDIO IDs macros. Check for "AR6003 or later" is slightly modified to use SDIO device IDs. This allows removal of all custom MANUFACTURER macros from ath6kl. Signed-off-by: Pali Rohár Acked-by: Kalle Valo Link: https://lore.kernel.org/r/20200522144412.19712-8-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 9ec675a7ac37..95b67ab7d06a 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -24,6 +24,16 @@ /* * Vendors and devices. Sort key: vendor first, device next. */ + +#define SDIO_VENDOR_ID_ATHEROS 0x0271 +#define SDIO_DEVICE_ID_ATHEROS_AR6003_00 0x0300 +#define SDIO_DEVICE_ID_ATHEROS_AR6003_01 0x0301 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_00 0x0400 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_01 0x0401 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_02 0x0402 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_18 0x0418 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_19 0x0419 + #define SDIO_VENDOR_ID_BROADCOM 0x02d0 #define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 #define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 -- cgit v1.2.3 From 4dc28c948f480c5004613aab153c7160bd4f29ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:09 +0200 Subject: mmc: sdio: Move SDIO IDs from ath10k driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also replace generic MANUFACTURER macros by proper SDIO IDs macros. Checks for device IDs are slightly modified to use SDIO device IDs. This allows removal of all custom MANUFACTURER macros from ath10k. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-9-pali@kernel.org Signed-off-by: Ulf Hansson --- 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 95b67ab7d06a..2894f7739acc 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -33,6 +33,8 @@ #define SDIO_DEVICE_ID_ATHEROS_AR6004_02 0x0402 #define SDIO_DEVICE_ID_ATHEROS_AR6004_18 0x0418 #define SDIO_DEVICE_ID_ATHEROS_AR6004_19 0x0419 +#define SDIO_DEVICE_ID_ATHEROS_AR6005 0x050A +#define SDIO_DEVICE_ID_ATHEROS_QCA9377 0x0701 #define SDIO_VENDOR_ID_BROADCOM 0x02d0 #define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 -- cgit v1.2.3 From 8baa6d1bce05cf26eec6b43bcd428735f33cb60e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:10 +0200 Subject: mmc: sdio: Move SDIO IDs from b43-sdio driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other macros. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-10-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 2894f7739acc..8e7a0683b927 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -25,6 +25,9 @@ * Vendors and devices. Sort key: vendor first, device next. */ +#define SDIO_VENDOR_ID_CGUYS 0x0092 +#define SDIO_DEVICE_ID_CGUYS_EW_CG1102GC 0x0004 + #define SDIO_VENDOR_ID_ATHEROS 0x0271 #define SDIO_DEVICE_ID_ATHEROS_AR6003_00 0x0300 #define SDIO_DEVICE_ID_ATHEROS_AR6003_01 0x0301 @@ -37,6 +40,7 @@ #define SDIO_DEVICE_ID_ATHEROS_QCA9377 0x0701 #define SDIO_VENDOR_ID_BROADCOM 0x02d0 +#define SDIO_DEVICE_ID_BROADCOM_NINTENDO_WII 0x044b #define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 #define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 #define SDIO_DEVICE_ID_BROADCOM_4329 0x4329 -- cgit v1.2.3 From 1eb911258805695c8f85795d3d4cdbd1e84fc2d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:11 +0200 Subject: mmc: sdio: Fix Cypress SDIO IDs macros in common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All macro names for SDIO device IDs are prefixed by vendor name to which device ID belongs. So for consistency add Broadcom string vendor prefix to all Cypress macro names as they belong to SDIO Broadcom vendor ID. Change also Cypress 43012 value from decimal do hexadecimal notation to be consistent with all other values. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-11-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 8e7a0683b927..b19200aea56a 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -58,9 +58,9 @@ #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_DEVICE_ID_BROADCOM_CYPRESS_4373 0x4373 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43012 0xa804 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359 0x4355 #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 -- cgit v1.2.3 From 798dd3c311f6c862719a3fc71c3c14eba192c64e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:12 +0200 Subject: mmc: sdio: Sort all SDIO IDs in common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix ordering of SDIO IDs to conform to the comment above, which says vendor first, device next. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-12-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index b19200aea56a..15ed8ce9d394 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -25,9 +25,23 @@ * Vendors and devices. Sort key: vendor first, device next. */ +#define SDIO_VENDOR_ID_STE 0x0020 +#define SDIO_DEVICE_ID_STE_CW1200 0x2280 + +#define SDIO_VENDOR_ID_INTEL 0x0089 +#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 +#define SDIO_DEVICE_ID_INTEL_IWMC3200WIFI 0x1403 +#define SDIO_DEVICE_ID_INTEL_IWMC3200TOP 0x1404 +#define SDIO_DEVICE_ID_INTEL_IWMC3200GPS 0x1405 +#define SDIO_DEVICE_ID_INTEL_IWMC3200BT 0x1406 +#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX_2G5 0x1407 + #define SDIO_VENDOR_ID_CGUYS 0x0092 #define SDIO_DEVICE_ID_CGUYS_EW_CG1102GC 0x0004 +#define SDIO_VENDOR_ID_TI 0x0097 +#define SDIO_DEVICE_ID_TI_WL1271 0x4076 + #define SDIO_VENDOR_ID_ATHEROS 0x0271 #define SDIO_DEVICE_ID_ATHEROS_AR6003_00 0x0300 #define SDIO_DEVICE_ID_ATHEROS_AR6003_01 0x0301 @@ -41,34 +55,26 @@ #define SDIO_VENDOR_ID_BROADCOM 0x02d0 #define SDIO_DEVICE_ID_BROADCOM_NINTENDO_WII 0x044b -#define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 #define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 #define SDIO_DEVICE_ID_BROADCOM_4329 0x4329 #define SDIO_DEVICE_ID_BROADCOM_4330 0x4330 #define SDIO_DEVICE_ID_BROADCOM_4334 0x4334 -#define SDIO_DEVICE_ID_BROADCOM_43340 0xa94c -#define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 #define SDIO_DEVICE_ID_BROADCOM_4339 0x4339 -#define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 -#define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 -#define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_4345 0x4345 -#define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359 0x4355 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 #define SDIO_DEVICE_ID_BROADCOM_4359 0x4359 #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373 0x4373 #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43012 0xa804 -#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359 0x4355 - -#define SDIO_VENDOR_ID_INTEL 0x0089 -#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 -#define SDIO_DEVICE_ID_INTEL_IWMC3200WIFI 0x1403 -#define SDIO_DEVICE_ID_INTEL_IWMC3200TOP 0x1404 -#define SDIO_DEVICE_ID_INTEL_IWMC3200GPS 0x1405 -#define SDIO_DEVICE_ID_INTEL_IWMC3200BT 0x1406 -#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX_2G5 0x1407 +#define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 +#define SDIO_DEVICE_ID_BROADCOM_43340 0xa94c +#define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d +#define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 +#define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 +#define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 +#define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 @@ -112,12 +118,7 @@ #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 -#define SDIO_VENDOR_ID_TI 0x0097 -#define SDIO_DEVICE_ID_TI_WL1271 0x4076 #define SDIO_VENDOR_ID_TI_WL1251 0x104c #define SDIO_DEVICE_ID_TI_WL1251 0x9066 -#define SDIO_VENDOR_ID_STE 0x0020 -#define SDIO_DEVICE_ID_STE_CW1200 0x2280 - #endif /* LINUX_MMC_SDIO_IDS_H */ -- cgit v1.2.3 From d58a2df3d8877b91ecbfb936a15da364251a228f Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Mon, 18 May 2020 16:45:02 +0200 Subject: serial: 8250: Support rs485 bus termination GPIO Commit e8759ad17d41 ("serial: uapi: Add support for bus termination") introduced the ability to enable rs485 bus termination from user space. So far the feature is only used by a single driver, 8250_exar.c, using a hardcoded GPIO pin specific to Siemens IOT2040 products. Provide for a more generic solution by allowing specification of an rs485 bus termination GPIO pin in the device tree: Amend the serial core to retrieve the GPIO from the device tree (or ACPI table) and amend the default ->rs485_config() callback for 8250 drivers to change the GPIO on request from user space. Perhaps 8250_exar.c can be converted to the generic approach in a follow-up patch. Signed-off-by: Lukas Wunner Reviewed-by: Andy Shevchenko Cc: Jan Kiszka Link: https://lore.kernel.org/r/94c6c800d1ca9fa04766dd1d43a8272c5ad4bedd.1589811297.git.lukas@wunner.de Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index b649a2b894e7..9fd550e7946a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -251,6 +252,7 @@ struct uart_port { struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; + struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; -- cgit v1.2.3 From 8baebfc2aca26e3fa67ab28343671b82be42b22c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 28 May 2020 02:41:03 +0300 Subject: regmap: add helper for per-port regfield initialization Similar to the standalone regfields, add an initializer for the users who need to set .id_size and .id_offset in order to use the regmap_fields_update_bits_base API. Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20200527234113.2491988-2-olteanv@gmail.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..87703d105191 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1134,6 +1134,14 @@ struct reg_field { .msb = _msb, \ } +#define REG_FIELD_ID(_reg, _lsb, _msb, _size, _offset) { \ + .reg = _reg, \ + .lsb = _lsb, \ + .msb = _msb, \ + .id_size = _size, \ + .id_offset = _offset, \ + } + struct regmap_field *regmap_field_alloc(struct regmap *regmap, struct reg_field reg_field); void regmap_field_free(struct regmap_field *field); -- cgit v1.2.3 From fb01562e5a8a731bb1807eba0a9fadb355ca2277 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 23 Apr 2020 14:53:28 +0200 Subject: uacce: Remove mm_exit() op The mm_exit() op will be removed from the SVA API. When a process dies and its mm goes away, the IOMMU driver won't notify device drivers anymore. Drivers should expect to handle a lot more aborted DMA. On the upside, it does greatly simplify the queue management. The uacce_mm struct, that tracks all queues bound to an mm, was only used by the mm_exit() callback. Remove it. Signed-off-by: Jean-Philippe Brucker Acked-by: Jacob Pan Acked-by: Lu Baolu Acked-by: Zhangfei Gao Link: https://lore.kernel.org/r/20200423125329.782066-2-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/uacce.h | 34 +++++++++------------------------- 1 file changed, 9 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 0e215e6d0534..454c2f6672d7 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -68,19 +68,21 @@ enum uacce_q_state { * @uacce: pointer to uacce * @priv: private pointer * @wait: wait queue head - * @list: index into uacce_mm - * @uacce_mm: the corresponding mm + * @list: index into uacce queues list * @qfrs: pointer of qfr regions * @state: queue state machine + * @pasid: pasid associated to the mm + * @handle: iommu_sva handle returned by iommu_sva_bind_device() */ struct uacce_queue { struct uacce_device *uacce; void *priv; wait_queue_head_t wait; struct list_head list; - struct uacce_mm *uacce_mm; struct uacce_qfile_region *qfrs[UACCE_MAX_REGION]; enum uacce_q_state state; + int pasid; + struct iommu_sva *handle; }; /** @@ -96,8 +98,8 @@ struct uacce_queue { * @cdev: cdev of the uacce * @dev: dev of the uacce * @priv: private pointer of the uacce - * @mm_list: list head of uacce_mm->list - * @mm_lock: lock for mm_list + * @queues: list of queues + * @queues_lock: lock for queues list * @inode: core vfs */ struct uacce_device { @@ -112,27 +114,9 @@ struct uacce_device { struct cdev *cdev; struct device dev; void *priv; - struct list_head mm_list; - struct mutex mm_lock; - struct inode *inode; -}; - -/** - * struct uacce_mm - keep track of queues bound to a process - * @list: index into uacce_device - * @queues: list of queues - * @mm: the mm struct - * @lock: protects the list of queues - * @pasid: pasid of the uacce_mm - * @handle: iommu_sva handle return from iommu_sva_bind_device - */ -struct uacce_mm { - struct list_head list; struct list_head queues; - struct mm_struct *mm; - struct mutex lock; - int pasid; - struct iommu_sva *handle; + struct mutex queues_lock; + struct inode *inode; }; #if IS_ENABLED(CONFIG_UACCE) -- cgit v1.2.3 From edcc40d2ab5f47f205c2dd2a9aeedd8c77de050a Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 23 Apr 2020 14:53:30 +0200 Subject: iommu: Remove iommu_sva_ops::mm_exit() After binding a device to an mm, device drivers currently need to register a mm_exit handler. This function is called when the mm exits, to gracefully stop DMA targeting the address space and flush page faults to the IOMMU. This is deemed too complex for the MMU release() notifier, which may be triggered by any mmput() invocation, from about 120 callsites [1]. The upcoming SVA module has an example of such complexity: the I/O Page Fault handler would need to call mmput_async() instead of mmput() after handling an IOPF, to avoid triggering the release() notifier which would in turn drain the IOPF queue and lock up. Another concern is the DMA stop function taking too long, up to several minutes [2]. For some mmput() callers this may disturb other users. For example, if the OOM killer picks the mm bound to a device as the victim and that mm's memory is locked, if the release() takes too long, it might choose additional innocent victims to kill. To simplify the MMU release notifier, don't forward the notification to device drivers. Since they don't stop DMA on mm exit anymore, the PASID lifetime is extended: (1) The device driver calls bind(). A PASID is allocated. Here any DMA fault is handled by mm, and on error we don't print anything to dmesg. Userspace can easily trigger errors by issuing DMA on unmapped buffers. (2) exit_mmap(), for example the process took a SIGKILL. This step doesn't happen during normal operations. Remove the pgd from the PASID table, since the page tables are about to be freed. Invalidate the IOTLBs. Here the device may still perform DMA on the address space. Incoming transactions are aborted but faults aren't printed out. ATS Translation Requests return Successful Translation Completions with R=W=0. PRI Page Requests return with Invalid Request. (3) The device driver stops DMA, possibly following release of a fd, and calls unbind(). PASID table is cleared, IOTLB invalidated if necessary. The page fault queues are drained, and the PASID is freed. If DMA for that PASID is still running here, something went seriously wrong and errors should be reported. For now remove iommu_sva_ops entirely. We might need to re-introduce them at some point, for example to notify device drivers of unhandled IOPF. [1] https://lore.kernel.org/linux-iommu/20200306174239.GM31668@ziepe.ca/ [2] https://lore.kernel.org/linux-iommu/4d68da96-0ad5-b412-5987-2f7a6aa796c3@amd.com/ Signed-off-by: Jean-Philippe Brucker Acked-by: Jacob Pan Acked-by: Lu Baolu Link: https://lore.kernel.org/r/20200423125329.782066-3-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7cfd2dddb49d..08d3506172a1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -53,8 +53,6 @@ struct iommu_fault_event; typedef int (*iommu_fault_handler_t)(struct iommu_domain *, struct device *, unsigned long, int, void *); -typedef int (*iommu_mm_exit_handler_t)(struct device *dev, struct iommu_sva *, - void *); typedef int (*iommu_dev_fault_handler_t)(struct iommu_fault *, void *); struct iommu_domain_geometry { @@ -171,25 +169,6 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) -/** - * struct iommu_sva_ops - device driver callbacks for an SVA context - * - * @mm_exit: called when the mm is about to be torn down by exit_mmap. After - * @mm_exit returns, the device must not issue any more transaction - * with the PASID given as argument. - * - * The @mm_exit handler is allowed to sleep. Be careful about the - * locks taken in @mm_exit, because they might lead to deadlocks if - * they are also held when dropping references to the mm. Consider the - * following call chain: - * mutex_lock(A); mmput(mm) -> exit_mm() -> @mm_exit() -> mutex_lock(A) - * Using mmput_async() prevents this scenario. - * - */ -struct iommu_sva_ops { - iommu_mm_exit_handler_t mm_exit; -}; - #ifdef CONFIG_IOMMU_API /** @@ -616,7 +595,6 @@ struct iommu_fwspec { */ struct iommu_sva { struct device *dev; - const struct iommu_sva_ops *ops; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, @@ -664,8 +642,6 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata); void iommu_sva_unbind_device(struct iommu_sva *handle); -int iommu_sva_set_ops(struct iommu_sva *handle, - const struct iommu_sva_ops *ops); int iommu_sva_get_pasid(struct iommu_sva *handle); #else /* CONFIG_IOMMU_API */ @@ -1069,12 +1045,6 @@ static inline void iommu_sva_unbind_device(struct iommu_sva *handle) { } -static inline int iommu_sva_set_ops(struct iommu_sva *handle, - const struct iommu_sva_ops *ops) -{ - return -EINVAL; -} - static inline int iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; -- cgit v1.2.3 From aa2ff9dbaeddabb5ad166db5f9f1a0580a8bbba8 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 28 May 2020 17:45:02 +0200 Subject: regmap: provide helpers for simple bit operations In many instances regmap_update_bits() is used for simple bit setting and clearing. In these cases the last argument is redundant and we can hide it with a static inline function. This adds three new helpers for simple bit operations: set_bits, clear_bits and test_bits (the last one defined as a regular function). Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20200528154503.26304-2-brgl@bgdev.pl Signed-off-by: Mark Brown --- include/linux/regmap.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..ddf0baff195d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1111,6 +1111,21 @@ bool regmap_reg_in_ranges(unsigned int reg, const struct regmap_range *ranges, unsigned int nranges); +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, bits, + NULL, false, false); +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, 0, NULL, false, false); +} + +int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits); + /** * struct reg_field - Description of an register field * @@ -1410,6 +1425,27 @@ static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_test_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force) -- cgit v1.2.3 From 4fda230ecddc2573ed88632e98b69b0b9b68c0ad Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Wed, 27 May 2020 10:56:16 -0600 Subject: iommu/vt-d: Allocate domain info for real DMA sub-devices Sub-devices of a real DMA device might exist on a separate segment than the real DMA device and its IOMMU. These devices should still have a valid device_domain_info, but the current dma alias model won't allocate info for the subdevice. This patch adds a segment member to struct device_domain_info and uses the sub-device's BDF so that these sub-devices won't alias to other devices. Fixes: 2b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping") Cc: stable@vger.kernel.org # v5.6+ Signed-off-by: Jon Derrick Acked-by: Lu Baolu Link: https://lore.kernel.org/r/20200527165617.297470-3-jonathan.derrick@intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 21633cee6331..4100bd224f5c 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -609,6 +609,7 @@ struct device_domain_info { struct list_head auxiliary_domains; /* auxiliary domains * attached to this device */ + u32 segment; /* PCI segment number */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ u16 pfsid; /* SRIOV physical function source ID */ -- cgit v1.2.3 From 752db83a5dfd4fd3a0624b9ab440ed947fa003ca Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 29 May 2020 14:49:39 +0200 Subject: regulator: extract voltage balancing code to the separate function Move the coupled regulators voltage balancing code to the separate function and allow to call it from the custom regulator couplers. Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200529124940.10675-2-m.szyprowski@samsung.com Signed-off-by: Mark Brown --- include/linux/regulator/coupler.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/coupler.h b/include/linux/regulator/coupler.h index 0212d6255e4e..5f86824bd117 100644 --- a/include/linux/regulator/coupler.h +++ b/include/linux/regulator/coupler.h @@ -62,6 +62,8 @@ int regulator_get_voltage_rdev(struct regulator_dev *rdev); int regulator_set_voltage_rdev(struct regulator_dev *rdev, int min_uV, int max_uV, suspend_state_t state); +int regulator_do_balance_voltage(struct regulator_dev *rdev, + suspend_state_t state, bool skip_coupled); #else static inline int regulator_coupler_register(struct regulator_coupler *coupler) { @@ -92,6 +94,12 @@ static inline int regulator_set_voltage_rdev(struct regulator_dev *rdev, { return -EINVAL; } +static inline int regulator_do_balance_voltage(struct regulator_dev *rdev, + suspend_state_t state, + bool skip_coupled) +{ + return -EINVAL; +} #endif #endif -- cgit v1.2.3 From 9a7875461fd0427dc86e3a87e93bd5723679b8b1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 28 May 2020 16:45:14 +0200 Subject: PM: runtime: Replace pm_runtime_callbacks_present() The name of pm_runtime_callbacks_present() is confusing, because it suggests that the device has PM-runtime callbacks if 'true' is returned by that function, but in fact that may not be the case, so replace it with pm_runtime_has_no_callbacks() which is not ambiguous. No functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson --- include/linux/pm_runtime.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 3bdcbce8141a..3dbc207bff53 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -102,9 +102,9 @@ static inline bool pm_runtime_enabled(struct device *dev) return !dev->power.disable_depth; } -static inline bool pm_runtime_callbacks_present(struct device *dev) +static inline bool pm_runtime_has_no_callbacks(struct device *dev) { - return !dev->power.no_callbacks; + return dev->power.no_callbacks; } static inline void pm_runtime_mark_last_busy(struct device *dev) -- cgit v1.2.3 From 7b11eab041dacfeaaa6d27d9183b247a995bc16d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 29 May 2020 07:51:59 -0700 Subject: blk-mq: blk-mq: provide forced completion method Drivers may need to bypass error injection for error recovery. Rename __blk_mq_complete_request() to blk_mq_force_complete_rq() and export that function so drivers may skip potential fake timeouts after they've reclaimed lost requests. Signed-off-by: Keith Busch Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d7307795439a..856bb10993cf 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -494,6 +494,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); bool blk_mq_complete_request(struct request *rq); +void blk_mq_force_complete_rq(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); -- cgit v1.2.3 From 5d9c305b8ea3fbc95bedfde01f7dd91e68082098 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 May 2020 15:53:08 +0200 Subject: blk-mq: remove the bio argument to ->prepare_request None of the I/O schedulers actually needs it. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Bart Van Assche Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 901bda352dcb..bacc40a0bdf3 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -39,7 +39,7 @@ struct elevator_mq_ops { void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); - void (*prepare_request)(struct request *, struct bio *bio); + void (*prepare_request)(struct request *); void (*finish_request)(struct request *); void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); -- cgit v1.2.3 From bf0beec0607db3c6f6fb7bd2c6d503792b05cf3f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 29 May 2020 15:53:15 +0200 Subject: blk-mq: drain I/O when all CPUs in a hctx are offline Most of blk-mq drivers depend on managed IRQ's auto-affinity to setup up queue mapping. Thomas mentioned the following point[1]: "That was the constraint of managed interrupts from the very beginning: The driver/subsystem has to quiesce the interrupt line and the associated queue _before_ it gets shutdown in CPU unplug and not fiddle with it until it's restarted by the core when the CPU is plugged in again." However, current blk-mq implementation doesn't quiesce hw queue before the last CPU in the hctx is shutdown. Even worse, CPUHP_BLK_MQ_DEAD is a cpuhp state handled after the CPU is down, so there isn't any chance to quiesce the hctx before shutting down the CPU. Add new CPUHP_AP_BLK_MQ_ONLINE state to stop allocating from blk-mq hctxs where the last CPU goes away, and wait for completion of in-flight requests. This guarantees that there is no inflight I/O before shutting down the managed IRQ. Add a BLK_MQ_F_STACKING and set it for dm-rq and loop, so we don't need to wait for completion of in-flight requests from these drivers to avoid a potential dead-lock. It is safe to do this for stacking drivers as those do not use interrupts at all and their I/O completions are triggered by underlying devices I/O completion. [1] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/ [hch: different retry mechanism, merged two patches, minor cleanups] Signed-off-by: Ming Lei Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 10 ++++++++++ include/linux/cpuhotplug.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 856bb10993cf..d6fcae17da5a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -140,6 +140,8 @@ struct blk_mq_hw_ctx { */ atomic_t nr_active; + /** @cpuhp_online: List to store request if CPU is going to die */ + struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ @@ -391,6 +393,11 @@ struct blk_mq_ops { enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, + /* + * Set when this device requires underlying blk-mq device for + * completing IO: + */ + BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_BLOCKING = 1 << 5, BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, @@ -400,6 +407,9 @@ enum { BLK_MQ_S_TAG_ACTIVE = 1, BLK_MQ_S_SCHED_RESTART = 2, + /* hw queue is inactive after all its CPUs become offline */ + BLK_MQ_S_INACTIVE = 3, + BLK_MQ_MAX_DEPTH = 10240, BLK_MQ_CPU_WORK_BATCH = 8, diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 77d70b633531..24b3a77810b6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -152,6 +152,7 @@ enum cpuhp_state { CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_IRQ_AFFINITY_ONLINE, + CPUHP_AP_BLK_MQ_ONLINE, CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS, CPUHP_AP_X86_INTEL_EPB_ONLINE, CPUHP_AP_PERF_ONLINE, -- cgit v1.2.3 From 5a892ff2facb4548c17c05931ed899038a0da63e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 May 2020 14:09:43 +0200 Subject: net: remove kernel_setsockopt No users left. Signed-off-by: Christoph Hellwig Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/linux/net.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 74ef5d7315f7..e10f378194a5 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -303,8 +303,6 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); -int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, - unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, -- cgit v1.2.3 From a7868323c2638a7c6c5b30b37831b73cbdf0dc15 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 May 2020 08:24:10 -0500 Subject: exec: Add a per bprm->file version of per_clear There is a small bug in the code that recomputes parts of bprm->cred for every bprm->file. The code never recomputes the part of clear_dangerous_personality_flags it is responsible for. Which means that in practice if someone creates a sgid script the interpreter will not be able to use any of: READ_IMPLIES_EXEC ADDR_NO_RANDOMIZE ADDR_COMPAT_LAYOUT MMAP_PAGE_ZERO. This accentially clearing of personality flags probably does not matter in practice because no one has complained but it does make the code more difficult to understand. Further remaining bug compatible prevents the recomputation from being removed and replaced by simply computing bprm->cred once from the final bprm->file. Making this change removes the last behavior difference between computing bprm->creds from the final file and recomputing bprm->cred several times. Which allows this behavior change to be justified for it's own reasons, and for any but hunts looking into why the behavior changed to wind up here instead of in the code that will follow that computes bprm->cred from the final bprm->file. This small logic bug appears to have existed since the code started clearing dangerous personality bits. History Tree: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Fixes: 1bb0fa189c6a ("[PATCH] NX: clean up legacy binary support") Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 5 +++++ include/linux/lsm_hooks.h | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 7fc05929c967..50025ead0b72 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -55,6 +55,11 @@ struct linux_binprm { struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ + /* + * bits to clear in current->personality + * recalculated for each bprm->file. + */ + unsigned int pf_per_clear; unsigned int per_clear; /* bits to clear in current->personality */ int argc, envc; const char * filename; /* Name of binary as seen by procps */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d618ecc4d660..f68076d440f3 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -55,6 +55,8 @@ * transitions between security domains). * The hook must set @bprm->active_secureexec to 1 if AT_SECURE should be set to * request libc enable secure mode. + * The hook must add to @bprm->pf_per_clear any personality flags that + * should be cleared from current->personality. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: -- cgit v1.2.3 From 56305aa9b6fab91a5555a45796b79c1b0a6353d1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 May 2020 22:00:54 -0500 Subject: exec: Compute file based creds only once Move the computation of creds from prepare_binfmt into begin_new_exec so that the creds need only be computed once. This is just code reorganization no semantic changes of any kind are made. Moving the computation is safe. I have looked through the kernel and verified none of the binfmts look at bprm->cred directly, and that there are no helpers that look at bprm->cred indirectly. Which means that it is not a problem to compute the bprm->cred later in the execution flow as it is not used until it becomes current->cred. A new function bprm_creds_from_file is added to contain the work that needs to be done. bprm_creds_from_file first computes which file bprm->executable or most likely bprm->file that the bprm->creds will be computed from. The funciton bprm_fill_uid is updated to receive the file instead of accessing bprm->file. The now unnecessary work needed to reset the bprm->cred->euid, and bprm->cred->egid is removed from brpm_fill_uid. A small comment to document that bprm_fill_uid now only deals with the work to handle suid and sgid files. The default case is already heandled by prepare_exec_creds. The function security_bprm_repopulate_creds is renamed security_bprm_creds_from_file and now is explicitly passed the file from which to compute the creds. The documentation of the bprm_creds_from_file security hook is updated to explain when the hook is called and what it needs to do. The file is passed from cap_bprm_creds_from_file into get_file_caps so that the caps are computed for the appropriate file. The now unnecessary work in cap_bprm_creds_from_file to reset the ambient capabilites has been removed. A small comment to document that the work of cap_bprm_creds_from_file is to read capabilities from the files secureity attribute and derive capabilities from the fact the user had uid 0 has been added. Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 14 ++------------ include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 22 +++++++++++----------- include/linux/security.h | 9 +++++---- 4 files changed, 19 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 50025ead0b72..aece1b340e7d 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -29,13 +29,8 @@ struct linux_binprm { /* Should an execfd be passed to userspace? */ have_execfd:1, - /* It is safe to use the creds of a script (see binfmt_misc) */ - preserve_creds:1, - /* - * True if most recent call to security_bprm_set_creds - * resulted in elevated privileges. - */ - active_secureexec:1, + /* Use the creds of a script (see binfmt_misc) */ + execfd_creds:1, /* * Set by bprm_creds_for_exec hook to indicate a * privilege-gaining exec has happened. Used to set @@ -55,11 +50,6 @@ struct linux_binprm { struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ - /* - * bits to clear in current->personality - * recalculated for each bprm->file. - */ - unsigned int pf_per_clear; unsigned int per_clear; /* bits to clear in current->personality */ int argc, envc; const char * filename; /* Name of binary as seen by procps */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 1e295ba12c0d..adbc6603abba 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -50,7 +50,7 @@ LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) -LSM_HOOK(int, 0, bprm_repopulate_creds, struct linux_binprm *bprm) +LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index f68076d440f3..c523c18efa0e 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -44,18 +44,18 @@ * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. - * @bprm_repopulate_creds: - * Assuming that the relevant bits of @bprm->cred->security have been - * previously set, examine @bprm->file and regenerate them. This is - * so that the credentials derived from the interpreter the code is - * actually going to run are used rather than credentials derived - * from a script. This done because the interpreter binary needs to - * reopen script, and may end up opening something completely different. - * This hook may also optionally check permissions (e.g. for - * transitions between security domains). - * The hook must set @bprm->active_secureexec to 1 if AT_SECURE should be set to + * @bprm_creds_from_file: + * If @file is setpcap, suid, sgid or otherwise marked to change + * privilege upon exec, update @bprm->cred to reflect that change. + * This is called after finding the binary that will be executed. + * without an interpreter. This ensures that the credentials will not + * be derived from a script that the binary will need to reopen, which + * when reopend may end up being a completely different file. This + * hook may also optionally check permissions (e.g. for transitions + * between security domains). + * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to * request libc enable secure mode. - * The hook must add to @bprm->pf_per_clear any personality flags that + * The hook must add to @bprm->per_clear any personality flags that * should be cleared from current->personality. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. diff --git a/include/linux/security.h b/include/linux/security.h index 6dcec9375e8f..8444fae7c5b9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -140,7 +140,7 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -extern int cap_bprm_repopulate_creds(struct linux_binprm *bprm); +extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); extern int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, const char *name); @@ -277,7 +277,7 @@ int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); int security_bprm_creds_for_exec(struct linux_binprm *bprm); -int security_bprm_repopulate_creds(struct linux_binprm *bprm); +int security_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); @@ -575,9 +575,10 @@ static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) return 0; } -static inline int security_bprm_repopulate_creds(struct linux_binprm *bprm) +static inline int security_bprm_creds_from_file(struct linux_binprm *bprm, + struct file *file) { - return cap_bprm_repopulate_creds(bprm); + return cap_bprm_creds_from_file(bprm, file); } static inline int security_bprm_check(struct linux_binprm *bprm) -- cgit v1.2.3 From 2553f421f44f4db7579f202b79b69046b579c7b5 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 27 May 2020 23:16:02 -0700 Subject: net/mlx5: cmd: Fix memset with byte count warning Fix sparse warning: drivers/net/ethernet/mellanox/mlx5/core/cmd.c:1949:15: warning: memset with byte count of 271720 mlx5_cmd_stats array is too big to be held inline in mlx5_cmd. Allocate it separately. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6aa6bbd60559..13c0e4556eda 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -298,7 +298,7 @@ struct mlx5_cmd { struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; - struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX]; + struct mlx5_cmd_stats *stats; }; struct mlx5_port_caps { -- cgit v1.2.3 From 44345c4c130ee3df9b9fbc366d59ab3ac707d7f8 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 29 May 2020 00:47:12 -0700 Subject: net/mlx5: IPSec: Fix incorrect type for spi spi is __be32, fix that. Fixes sparse warning: drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c:74:64 warning: incorrect type Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index b919d143a9a6..96ebaa94a92e 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -76,7 +76,7 @@ struct aes_gcm_keymat { struct mlx5_accel_esp_xfrm_attrs { enum mlx5_accel_esp_action action; u32 esn; - u32 spi; + __be32 spi; u32 seq; u32 tfc_pad; u32 flags; -- cgit v1.2.3 From 563ca40ddf400dbf8c6254077f9b6887101d0f08 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 8 May 2020 09:16:02 -0700 Subject: pstore/platform: Switch pstore_info::name to const In order to more cleanly pass around backend names, make the "name" member const. This means the module param needs to be dynamic (technically, it was before, so this actually cleans up a minor memory leak if a backend was specified and then gets unloaded.) Link: https://lore.kernel.org/lkml/20200510202436.63222-3-keescook@chromium.org/ Signed-off-by: Kees Cook --- include/linux/pstore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index e779441e6d26..f6f22b13e04f 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -170,7 +170,7 @@ struct pstore_record { */ struct pstore_info { struct module *owner; - char *name; + const char *name; struct semaphore buf_lock; char *buf; -- cgit v1.2.3 From 6d3cf962dd1a95df868c547b090bfc4c7977f4be Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 15 May 2020 11:05:43 -0700 Subject: printk: Collapse shutdown types into a single dump reason To turn the KMSG_DUMP_* reasons into a more ordered list, collapse the redundant KMSG_DUMP_(RESTART|HALT|POWEROFF) reasons into KMSG_DUMP_SHUTDOWN. The current users already don't meaningfully distinguish between them, so there's no need to, as discussed here: https://lore.kernel.org/lkml/CA+CK2bAPv5u1ih5y9t5FUnTyximtFCtDYXJCpuyjOyHNOkRdqw@mail.gmail.com/ Link: https://lore.kernel.org/lkml/20200515184434.8470-2-keescook@chromium.org/ Reviewed-by: Pavel Tatashin Reviewed-by: Petr Mladek Acked-by: Michael Ellerman (powerpc) Signed-off-by: Kees Cook --- include/linux/kmsg_dump.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 2e7a1e032c71..3f82b5cb2d82 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -25,9 +25,7 @@ enum kmsg_dump_reason { KMSG_DUMP_PANIC, KMSG_DUMP_OOPS, KMSG_DUMP_EMERG, - KMSG_DUMP_RESTART, - KMSG_DUMP_HALT, - KMSG_DUMP_POWEROFF, + KMSG_DUMP_SHUTDOWN, }; /** -- cgit v1.2.3 From b1f6f161b236d0e5a9222fb8b482e65aaff13689 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 5 May 2020 11:45:06 -0400 Subject: printk: honor the max_reason field in kmsg_dumper kmsg_dump() allows to dump kmesg buffer for various system events: oops, panic, reboot, etc. It provides an interface to register a callback call for clients, and in that callback interface there is a field "max_reason", but it was getting ignored when set to any "reason" higher than KMSG_DUMP_OOPS unless "always_kmsg_dump" was passed as kernel parameter. Allow clients to actually control their "max_reason", and keep the current behavior when "max_reason" is not set. Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/lkml/20200515184434.8470-3-keescook@chromium.org/ Reviewed-by: Petr Mladek Signed-off-by: Kees Cook --- include/linux/kmsg_dump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 3f82b5cb2d82..9826014771ab 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -26,6 +26,7 @@ enum kmsg_dump_reason { KMSG_DUMP_OOPS, KMSG_DUMP_EMERG, KMSG_DUMP_SHUTDOWN, + KMSG_DUMP_MAX }; /** -- cgit v1.2.3 From fb13cb8a0482105a415e24042209d02a684255e2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 7 May 2020 19:36:22 -0700 Subject: printk: Introduce kmsg_dump_reason_str() The pstore subsystem already had a private version of this function. With the coming addition of the pstore/zone driver, this needs to be shared. As it really should live with printk, move it there instead. Link: https://lore.kernel.org/lkml/20200515184434.8470-4-keescook@chromium.org/ Acked-by: Petr Mladek Acked-by: Sergey Senozhatsky Reviewed-by: Pavel Tatashin Signed-off-by: Kees Cook --- include/linux/kmsg_dump.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 9826014771ab..3378bcbe585e 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -70,6 +70,8 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper); int kmsg_dump_register(struct kmsg_dumper *dumper); int kmsg_dump_unregister(struct kmsg_dumper *dumper); + +const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason); #else static inline void kmsg_dump(enum kmsg_dump_reason reason) { @@ -111,6 +113,11 @@ static inline int kmsg_dump_unregister(struct kmsg_dumper *dumper) { return -EINVAL; } + +static inline const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) +{ + return "Disabled"; +} #endif #endif /* _LINUX_KMSG_DUMP_H */ -- cgit v1.2.3 From 3524e688b8ee50b0edc76f0e020727eb6c684dbc Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 5 May 2020 11:45:07 -0400 Subject: pstore/platform: Pass max_reason to kmesg dump Add a new member to struct pstore_info for passing information about kmesg dump maximum reason. This allows a finer control of what kmesg dumps are sent to pstore storage backends. Those backends that do not explicitly set this field (keeping it equal to 0), get the default behavior: store only Oopses and Panics, or everything if the printk.always_kmsg_dump boot param is set. Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/lkml/20200515184434.8470-5-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index f6f22b13e04f..eb93a54cff31 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -96,6 +96,12 @@ struct pstore_record { * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for + * @max_reason: Used when PSTORE_FLAGS_DMESG is set. Contains the + * kmsg_dump_reason enum value. KMSG_DUMP_UNDEF means + * "use existing kmsg_dump() filtering, based on the + * printk.always_kmsg_dump boot param" (which is either + * KMSG_DUMP_OOPS when false, or KMSG_DUMP_MAX when + * true); see printk.always_kmsg_dump for more details. * @data: backend-private pointer passed back during callbacks * * Callbacks: @@ -179,6 +185,7 @@ struct pstore_info { struct mutex read_mutex; int flags; + int max_reason; void *data; int (*open)(struct pstore_info *psi); -- cgit v1.2.3 From 791205e3ec6081a8da6f00621e3453d622dc41e7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 13 May 2020 14:35:03 -0700 Subject: pstore/ram: Introduce max_reason and convert dump_oops Now that pstore_register() can correctly pass max_reason to the kmesg dump facility, introduce a new "max_reason" module parameter and "max-reason" Device Tree field. The "dump_oops" module parameter and "dump-oops" Device Tree field are now considered deprecated, but are now automatically converted to their corresponding max_reason values when present, though the new max_reason setting has precedence. For struct ramoops_platform_data, the "dump_oops" member is entirely replaced by a new "max_reason" member, with the only existing user updated in place. Additionally remove the "reason" filter logic from ramoops_pstore_write(), as that is not specifically needed anymore, though technically this is a change in behavior for any ramoops users also setting the printk.always_kmsg_dump boot param, which will cause ramoops to behave as if max_reason was set to KMSG_DUMP_MAX. Co-developed-by: Pavel Tatashin Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/lkml/20200515184434.8470-6-keescook@chromium.org/ Signed-off-by: Kees Cook --- include/linux/pstore_ram.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9cb9b9067298..9f16afec7290 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -133,7 +133,7 @@ struct ramoops_platform_data { unsigned long console_size; unsigned long ftrace_size; unsigned long pmsg_size; - int dump_oops; + int max_reason; u32 flags; struct persistent_ram_ecc_info ecc_info; }; -- cgit v1.2.3 From d26c3321fe18dc74517dc1f518d584aa33b0a851 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:54:56 +0800 Subject: pstore/zone: Introduce common layer to manage storage zones Implement a common set of APIs needed to support pstore storage zones, based on how ramoops is designed. This will be used by pstore/blk with the intention of migrating pstore/ram in the future. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-2-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/pstore_zone.h (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h new file mode 100644 index 000000000000..eb005d9ae40c --- /dev/null +++ b/include/linux/pstore_zone.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PSTORE_ZONE_H_ +#define __PSTORE_ZONE_H_ + +#include + +typedef ssize_t (*pstore_zone_read_op)(char *, size_t, loff_t); +typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); +/** + * struct pstore_zone_info - pstore/zone back-end driver structure + * + * @owner: Module which is responsible for this back-end driver. + * @name: Name of the back-end driver. + * @total_size: The total size in bytes pstore/zone can use. It must be greater + * than 4096 and be multiple of 4096. + * @kmsg_size: The size of oops/panic zone. Zero means disabled, otherwise, + * it must be multiple of SECTOR_SIZE(512 Bytes). + * @max_reason: Maximum kmsg dump reason to store. + * @read: The general read operation. Both of the function parameters + * @size and @offset are relative value to storage. + * On success, the number of bytes should be returned, others + * means error. + * @write: The same as @read. + * @panic_write:The write operation only used for panic case. It's optional + * if you do not care panic log. The parameters and return value + * are the same as @read. + */ +struct pstore_zone_info { + struct module *owner; + const char *name; + + unsigned long total_size; + unsigned long kmsg_size; + int max_reason; + pstore_zone_read_op read; + pstore_zone_write_op write; + pstore_zone_write_op panic_write; +}; + +extern int register_pstore_zone(struct pstore_zone_info *info); +extern void unregister_pstore_zone(struct pstore_zone_info *info); + +#endif -- cgit v1.2.3 From 17639f67c1d61aba3c05e7703f75cd468f9d484f Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:54:57 +0800 Subject: pstore/blk: Introduce backend for block devices pstore/blk is similar to pstore/ram, but uses a block device as the storage rather than persistent ram. The pstore/blk backend solves two common use-cases that used to preclude using pstore/ram: - not all devices have a battery that could be used to persist regular RAM across power failures. - most embedded intelligent equipment have no persistent ram, which increases costs, instead preferring cheaper solutions, like block devices. pstore/blk provides separate configurations for the end user and for the block drivers. User configuration determines how pstore/blk operates, such as record sizes, max kmsg dump reasons, etc. These can be set by Kconfig and/or module parameters, but module parameter have priority over Kconfig. Driver configuration covers all the details about the target block device, such as total size of the device and how to perform read/write operations. These are provided by block drivers, calling pstore_register_blkdev(), including an optional panic_write callback used to bypass regular IO APIs in an effort to avoid potentially destabilized kernel code during a panic. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-3-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 include/linux/pstore_blk.h (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h new file mode 100644 index 000000000000..4501977b1336 --- /dev/null +++ b/include/linux/pstore_blk.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PSTORE_BLK_H_ +#define __PSTORE_BLK_H_ + +#include +#include +#include + +/** + * typedef pstore_blk_panic_write_op - panic write operation to block device + * + * @buf: the data to write + * @start_sect: start sector to block device + * @sects: sectors count on buf + * + * Return: On success, zero should be returned. Others mean error. + * + * Panic write to block device must be aligned to SECTOR_SIZE. + */ +typedef int (*pstore_blk_panic_write_op)(const char *buf, sector_t start_sect, + sector_t sects); + +/** + * struct pstore_blk_info - pstore/blk registration details + * + * @major: Which major device number to support with pstore/blk + * @flags: The supported PSTORE_FLAGS_* from linux/pstore.h. + * @panic_write:The write operation only used for the panic case. + * This can be NULL, but is recommended to avoid losing + * crash data if the kernel's IO path or work queues are + * broken during a panic. + * @devt: The dev_t that pstore/blk has attached to. + * @nr_sects: Number of sectors on @devt. + * @start_sect: Starting sector on @devt. + */ +struct pstore_blk_info { + unsigned int major; + unsigned int flags; + pstore_blk_panic_write_op panic_write; + + /* Filled in by pstore/blk after registration. */ + dev_t devt; + sector_t nr_sects; + sector_t start_sect; +}; + +int register_pstore_blk(struct pstore_blk_info *info); +void unregister_pstore_blk(unsigned int major); + +#endif -- cgit v1.2.3 From 0dc068265a1c5923ffebf40388fbe93050a77ad1 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:54:59 +0800 Subject: pstore/zone,blk: Add support for pmsg frontend Add pmsg support to pstore/blk (through pstore/zone). To enable, pmsg_size must be greater than 0 and a multiple of 4096. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-4-keescook@chromium.org/ Co-developed-by: Colin Ian King Signed-off-by: Colin Ian King Link: https://lore.kernel.org/lkml/20200512171932.222102-1-colin.king@canonical.com Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index eb005d9ae40c..29c367a3bd80 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -17,6 +17,7 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @kmsg_size: The size of oops/panic zone. Zero means disabled, otherwise, * it must be multiple of SECTOR_SIZE(512 Bytes). * @max_reason: Maximum kmsg dump reason to store. + * @pmsg_size: The size of pmsg zone which is the same as @kmsg_size. * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others @@ -33,6 +34,7 @@ struct pstore_zone_info { unsigned long total_size; unsigned long kmsg_size; int max_reason; + unsigned long pmsg_size; pstore_zone_read_op read; pstore_zone_write_op write; pstore_zone_write_op panic_write; -- cgit v1.2.3 From cc9c4d1b5597167f8e8c92f6b61e1cda6d01884d Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:00 +0800 Subject: pstore/zone,blk: Add console frontend support Support backend for console. To enable console backend, just make console_size be greater than 0 and a multiple of 4096. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-5-keescook@chromium.org/ Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index 29c367a3bd80..904ee67f4ba2 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -18,11 +18,12 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * it must be multiple of SECTOR_SIZE(512 Bytes). * @max_reason: Maximum kmsg dump reason to store. * @pmsg_size: The size of pmsg zone which is the same as @kmsg_size. + * @console_size:The size of console zone which is the same as @kmsg_size. * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others * means error. - * @write: The same as @read. + * @write: The same as @read, but -EBUSY means try to write again later. * @panic_write:The write operation only used for panic case. It's optional * if you do not care panic log. The parameters and return value * are the same as @read. @@ -35,6 +36,7 @@ struct pstore_zone_info { unsigned long kmsg_size; int max_reason; unsigned long pmsg_size; + unsigned long console_size; pstore_zone_read_op read; pstore_zone_write_op write; pstore_zone_write_op panic_write; -- cgit v1.2.3 From 34327e9fd213414b35eb70aa512c4e39b2095907 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:01 +0800 Subject: pstore/zone,blk: Add ftrace frontend support Support backend for ftrace. To enable ftrace backend, just make ftrace_size be greater than 0 and a multiple of 4096. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-6-keescook@chromium.org/ Co-developed-by: Colin Ian King Signed-off-by: Colin Ian King Link: https://lore.kernel.org/lkml/20200512170719.221514-1-colin.king@canonical.com Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index 904ee67f4ba2..6f16b0dd834a 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -19,6 +19,7 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @max_reason: Maximum kmsg dump reason to store. * @pmsg_size: The size of pmsg zone which is the same as @kmsg_size. * @console_size:The size of console zone which is the same as @kmsg_size. + * @ftrace_size:The size of ftrace zone which is the same as @kmsg_size. * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others @@ -37,6 +38,7 @@ struct pstore_zone_info { int max_reason; unsigned long pmsg_size; unsigned long console_size; + unsigned long ftrace_size; pstore_zone_read_op read; pstore_zone_write_op write; pstore_zone_write_op panic_write; -- cgit v1.2.3 From 9630a055256de420d528ecde9f35902a9dcd8750 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:35 +0200 Subject: mtd: rawnand: Stop using nand_release() This helper is not very useful and very often people get confused: they use nand_release() instead of nand_cleanup(). Now that all drivers have been converted to do not use nand_release() anymore, let's remove this helper. Signed-off-by: Miquel Raynal Cc: Jonathan Corbet Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-63-miquel.raynal@bootlin.com --- include/linux/mtd/bbm.h | 2 +- include/linux/mtd/rawnand.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index 886e30441c90..d890805f5494 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -98,7 +98,7 @@ struct nand_bbt_descr { /* * Flag set by nand_create_default_bbt_descr(), marking that the nand_bbt_descr - * was allocated dynamicaly and must be freed in nand_release(). Has no meaning + * was allocated dynamicaly and must be freed in nand_cleanup(). Has no meaning * in nand_chip.bbt_options. */ #define NAND_BBT_DYNAMICSTRUCT 0x80000000 diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2804c13e5662..b0b358908a47 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1398,8 +1398,6 @@ void nand_wait_ready(struct nand_chip *chip); * sucessful nand_scan(). */ void nand_cleanup(struct nand_chip *chip); -/* Unregister the MTD device and calls nand_cleanup() */ -void nand_release(struct nand_chip *chip); /* * External helper for controller drivers that have to implement the WAITRDY -- cgit v1.2.3 From f66a6fd0dc7cc49c891a167937e161114f48a62e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 26 May 2020 21:56:14 +0200 Subject: mtd: rawnand: Avoid a typedef In new code, the use of typedef is discouraged. Turn this one in the raw NAND core into a regular enumeration. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200526195633.11543-3-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 6 +++--- include/linux/platform_data/mtd-davinci.h | 2 +- include/linux/platform_data/mtd-nand-s3c2410.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index b0b358908a47..8f662df02fdd 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -83,14 +83,14 @@ struct nand_chip; /* * Constants for ECC_MODES */ -typedef enum { +enum nand_ecc_mode { NAND_ECC_NONE, NAND_ECC_SOFT, NAND_ECC_HW, NAND_ECC_HW_SYNDROME, NAND_ECC_HW_OOB_FIRST, NAND_ECC_ON_DIE, -} nand_ecc_modes_t; +}; enum nand_ecc_algo { NAND_ECC_UNKNOWN, @@ -362,7 +362,7 @@ static const struct nand_ecc_caps __name = { \ * @write_oob: function to write chip OOB data */ struct nand_ecc_ctrl { - nand_ecc_modes_t mode; + enum nand_ecc_mode mode; enum nand_ecc_algo algo; int steps; int size; diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index 08e639e047e5..03e92c71b3fa 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -68,7 +68,7 @@ struct davinci_nand_pdata { /* platform_data */ * Newer ones also support 4-bit ECC, but are awkward * using it with large page chips. */ - nand_ecc_modes_t ecc_mode; + enum nand_ecc_mode ecc_mode; u8 ecc_bits; /* e.g. NAND_BUSWIDTH_16 */ diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index deb849bcf0ec..08675b16f9e1 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -49,7 +49,7 @@ struct s3c2410_platform_nand { unsigned int ignore_unset_ecc:1; - nand_ecc_modes_t ecc_mode; + enum nand_ecc_mode ecc_mode; int nr_sets; struct s3c2410_nand_set *sets; -- cgit v1.2.3 From 74e24cd2376d9cc4cfc6edad8610780b79fd5def Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 26 May 2020 21:56:15 +0200 Subject: mtd: rawnand: Drop OOB_FIRST placement scheme This scheme has been introduced for the Davinci controller and means that the OOB area must be read *before* the rest of the data. This has nothing to do with the ECC in OOB placement as it could be understood and most importantly, there is no point in having this function out of the Davinci NAND controller driver. A DT property for this scheme has been added but never used, even by the Davinci driver which only uses this scheme to change the default nand_read_page(). Move the main read_page() helper into the Davinci driver and remove the remaining boilerplate. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200526195633.11543-4-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8f662df02fdd..605d64ead3a8 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -88,7 +88,6 @@ enum nand_ecc_mode { NAND_ECC_SOFT, NAND_ECC_HW, NAND_ECC_HW_SYNDROME, - NAND_ECC_HW_OOB_FIRST, NAND_ECC_ON_DIE, }; -- cgit v1.2.3 From 86f2b225adf4ecd2edfdc8541a7342645556ac3b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 26 May 2020 21:56:18 +0200 Subject: mtd: rawnand: Add an invalid ECC mode to discriminate with valid ones NAND ECC modes (or providers) have their own enumeration but, unlike their algorithms counterpart, there is no invalid or uninitialized value to discriminate between an error and having chosen a no-ECC situation. Add an "invalid" entry for this purpose. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200526195633.11543-7-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 605d64ead3a8..65b1c1c18b41 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -84,6 +84,7 @@ struct nand_chip; * Constants for ECC_MODES */ enum nand_ecc_mode { + NAND_ECC_INVALID, NAND_ECC_NONE, NAND_ECC_SOFT, NAND_ECC_HW, -- cgit v1.2.3 From 372b38ea5911fc2500f0291b00140e80a26c0e36 Mon Sep 17 00:00:00 2001 From: Tova Mussai Date: Thu, 28 May 2020 21:34:26 +0200 Subject: ieee80211: definitions for reduced neighbor reports Add the necessary definitions to parse reduced neighbor report elements. Signed-off-by: Tova Mussai [change struct name, remove IEEE80211_MIN_AP_NEIGHBOR_INFO_SIZE] Link: https://lore.kernel.org/r/20200528213443.4f9154461c06.I518d9898ad982f838112ea9ca14a20d6bbb16394@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0320ca4c7d28..c29184bf9416 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2754,6 +2754,8 @@ enum ieee80211_eid { WLAN_EID_QUIET_CHANNEL = 198, WLAN_EID_OPMODE_NOTIF = 199, + WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201, + WLAN_EID_S1G_BCN_COMPAT = 213, WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, WLAN_EID_S1G_CAPABILITIES = 217, @@ -3675,4 +3677,30 @@ static inline bool for_each_element_completed(const struct element *element, #define WLAN_RSNX_CAPA_PROTECTED_TWT BIT(4) #define WLAN_RSNX_CAPA_SAE_H2E BIT(5) +/* + * reduced neighbor report, based on Draft P802.11ax_D5.0, + * section 9.4.2.170 + */ +#define IEEE80211_AP_INFO_TBTT_HDR_TYPE 0x03 +#define IEEE80211_AP_INFO_TBTT_HDR_FILTERED 0x04 +#define IEEE80211_AP_INFO_TBTT_HDR_COLOC 0x08 +#define IEEE80211_AP_INFO_TBTT_HDR_COUNT 0xF0 +#define IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM 8 +#define IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM 12 + +#define IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED 0x01 +#define IEEE80211_RNR_TBTT_PARAMS_SAME_SSID 0x02 +#define IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID 0x04 +#define IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID 0x08 +#define IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS 0x10 +#define IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE 0x20 +#define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP 0x40 + +struct ieee80211_neighbor_ap_info { + u8 tbtt_info_hdr; + u8 tbtt_info_len; + u8 op_class; + u8 channel; +} __packed; + #endif /* LINUX_IEEE80211_H */ -- cgit v1.2.3 From 821273a5a502eebaae005557907d122d1e9b7b98 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 28 May 2020 21:34:27 +0200 Subject: ieee80211: add code to obtain and parse 6 GHz operation field Add some code to obtain and parse the 6 GHz operation field inside the HE operation element. While at it, fix the required length using sizeof() the new struct, which is 5 instead of 4 now. Link: https://lore.kernel.org/r/20200528213443.42ca72c45ca9.Id74bc1b03da9ea6574f9bc70deeb60dfc1634359@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c29184bf9416..2bd9e757167d 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2209,6 +2209,28 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 +/** + * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field + * @primary: primary channel + * @control: control flags + * @ccfs0: channel center frequency segment 0 + * @ccfs1: channel center frequency segment 1 + * @minrate: minimum rate (in 1 Mbps units) + */ +struct ieee80211_he_6ghz_oper { + u8 primary; +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH 0x3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ 0 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ 1 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 + u8 control; + u8 ccfs0; + u8 ccfs1; + u8 minrate; +} __packed; + /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the byte @@ -2235,7 +2257,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) oper_len++; if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) - oper_len += 4; + oper_len += sizeof(struct ieee80211_he_6ghz_oper); /* Add the first byte (extension ID) to the total length */ oper_len++; @@ -2243,6 +2265,34 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) return oper_len; } +/** + * ieee80211_he_6ghz_oper - obtain 6 GHz operation field + * @he_oper: HE operation element (must be pre-validated for size) + * but may be %NULL + * + * Return: a pointer to the 6 GHz operation field, or %NULL + */ +static inline const struct ieee80211_he_6ghz_oper * +ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) +{ + const u8 *ret = (void *)&he_oper->optional; + u32 he_oper_params; + + if (!he_oper) + return NULL; + + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + + if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) + return NULL; + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + ret += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) + ret++; + + return (void *)ret; +} + /* HE Spatial Reuse defines */ #define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT 0x4 #define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT 0x8 -- cgit v1.2.3 From 8b30808d9be4183fab17f0b0e68eea88c94ff15a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 28 May 2020 21:34:28 +0200 Subject: ieee80211: add HE ext EIDs and 6 GHz capability defines Add the HE extended element IDs and the definitions for the HE 6 GHz band capabilities element, from Draft 5.0. Link: https://lore.kernel.org/r/20200528213443.1a6689fe093f.Ifdc5400fb01779351354daf38663ebeea03c9ad9@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2bd9e757167d..9580dfd9e2d1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2839,9 +2839,19 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_UORA = 37, WLAN_EID_EXT_HE_MU_EDCA = 38, WLAN_EID_EXT_HE_SPR = 39, + WLAN_EID_EXT_NDP_FEEDBACK_REPORT_PARAMSET = 41, + WLAN_EID_EXT_BSS_COLOR_CHG_ANN = 42, + WLAN_EID_EXT_QUIET_TIME_PERIOD_SETUP = 43, + WLAN_EID_EXT_ESS_REPORT = 45, + WLAN_EID_EXT_OPS = 46, + WLAN_EID_EXT_HE_BSS_LOAD = 47, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, WLAN_EID_EXT_NON_INHERITANCE = 56, + WLAN_EID_EXT_KNOWN_BSSID = 57, + WLAN_EID_EXT_SHORT_SSID_LIST = 58, + WLAN_EID_EXT_HE_6GHZ_CAPA = 59, + WLAN_EID_EXT_UL_MU_POWER_CAPA = 60, }; /* Action category code */ @@ -3384,6 +3394,24 @@ struct ieee80211_tspec_ie { __le16 medium_time; } __packed; +struct ieee80211_he_6ghz_capa { + /* uses IEEE80211_HE_6GHZ_CAP_* below */ + __le16 capa; +} __packed; + +/* HE 6 GHz band capabilities */ +/* uses enum ieee80211_min_mpdu_spacing values */ +#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START 0x0007 +/* uses enum ieee80211_vht_max_ampdu_length_exp values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP 0x0038 +/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN 0x00c0 +/* WLAN_HT_CAP_SM_PS_* values */ +#define IEEE80211_HE_6GHZ_CAP_SM_PS 0x0600 +#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER 0x0800 +#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS 0x1000 +#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS 0x2000 + /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame -- cgit v1.2.3 From 3b3ec3d52e8f72ec8c40477b96f23440a89000be Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Thu, 28 May 2020 21:34:37 +0200 Subject: mac80211: check the correct bit for EMA AP An AP supporting EMA (Enhanced Multi-BSSID advertisement) should set bit 83 in the extended capabilities IE (9.4.2.26 in the 802.11ax D5 spec). So the *3rd* bit of the 10th byte should be checked. Also, in one place, the wrong byte was checked. (cfg80211_find_ie returns a pointer to the beginning of the IE, so the data really starts at ie[2], so the 10th byte should be ie[12]. To avoid this confusion, use cfg80211_find_elem instead). Signed-off-by: Shaul Triebitz Link: https://lore.kernel.org/r/20200528213443.4316121fa2a3.I9745582f8d41ad8e689dac0fefcd70b276d7c1ea@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9580dfd9e2d1..1ecfd19f836d 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3082,7 +3082,7 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT BIT(7) /* Defines support for enhanced multi-bssid advertisement*/ -#define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(1) +#define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(3) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 -- cgit v1.2.3 From 3f19b2ab97a97b413c24b66c67ae16daa4f56c35 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 1 Dec 2017 11:40:16 +0000 Subject: vfs, afs, ext4: Make the inode hash table RCU searchable Make the inode hash table RCU searchable so that searches that want to access or modify an inode without taking a ref on that inode can do so without taking the inode hash table lock. The main thing this requires is some RCU annotation on the list manipulation operations. Inodes are already freed by RCU in most cases. Users of this interface must take care as the inode may be still under construction or may be being torn down around them. There are at least three instances where this can be of use: (1) Testing whether the inode number iunique() is going to return is currently unique (the iunique_lock is still held). (2) Ext4 date stamp updating. (3) AFS callback breaking. Signed-off-by: David Howells Acked-by: Konstantin Khlebnikov cc: linux-ext4@vger.kernel.org cc: linux-afs@lists.infradead.org --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..5f9b2bb4b44f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3070,6 +3070,9 @@ extern struct inode *find_inode_nowait(struct super_block *, int (*match)(struct inode *, unsigned long, void *), void *data); +extern struct inode *find_inode_rcu(struct super_block *, unsigned long, + int (*)(struct inode *, void *), void *); +extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From 335426c6dcdd338d6b7c939c2da15fc9c5dd4959 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:03 +0800 Subject: pstore/zone: Provide way to skip "broken" zone for MTD devices One requirement to support MTD devices in pstore/zone is having a way to declare certain regions as broken. Add this support to pstore/zone. The MTD driver should return -ENOMSG when encountering a bad region, which tells pstore/zone to skip and try the next one. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-8-keescook@chromium.org/ Co-developed-by: Colin Ian King Signed-off-by: Colin Ian King Link: //lore.kernel.org/lkml/20200512173801.222666-1-colin.king@canonical.com Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 3 ++- include/linux/pstore_zone.h | 12 ++++++++---- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h index 4501977b1336..ccba8c068752 100644 --- a/include/linux/pstore_blk.h +++ b/include/linux/pstore_blk.h @@ -14,7 +14,8 @@ * @start_sect: start sector to block device * @sects: sectors count on buf * - * Return: On success, zero should be returned. Others mean error. + * Return: On success, zero should be returned. Others excluding -ENOMSG + * mean error. -ENOMSG means to try next zone. * * Panic write to block device must be aligned to SECTOR_SIZE. */ diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index 6f16b0dd834a..e79a18e41064 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -23,11 +23,15 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others - * means error. - * @write: The same as @read, but -EBUSY means try to write again later. + * mean error. + * @write: The same as @read, but the following error number: + * -EBUSY means try to write again later. + * -ENOMSG means to try next zone. * @panic_write:The write operation only used for panic case. It's optional - * if you do not care panic log. The parameters and return value - * are the same as @read. + * if you do not care panic log. The parameters are relative + * value to storage. + * On success, the number of bytes should be returned, others + * excluding -ENOMSG mean error. -ENOMSG means to try next zone. */ struct pstore_zone_info { struct module *owner; -- cgit v1.2.3 From 1525fb3bb6d69028b3941d34363397c28345ffab Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:04 +0800 Subject: pstore/blk: Provide way to query pstore configuration In order to configure itself, the MTD backend needs to be able to query the current pstore configuration. Introduce pstore_blk_get_config() for this purpose. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-9-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h index ccba8c068752..0c40774e71e0 100644 --- a/include/linux/pstore_blk.h +++ b/include/linux/pstore_blk.h @@ -49,4 +49,32 @@ struct pstore_blk_info { int register_pstore_blk(struct pstore_blk_info *info); void unregister_pstore_blk(unsigned int major); +/** + * struct pstore_blk_config - the pstore_blk backend configuration + * + * @device: Name of the desired block device + * @max_reason: Maximum kmsg dump reason to store to block device + * @kmsg_size: Total size of for kmsg dumps + * @pmsg_size: Total size of the pmsg storage area + * @console_size: Total size of the console storage area + * @ftrace_size: Total size for ftrace logging data (for all CPUs) + */ +struct pstore_blk_config { + char device[80]; + enum kmsg_dump_reason max_reason; + unsigned long kmsg_size; + unsigned long pmsg_size; + unsigned long console_size; + unsigned long ftrace_size; +}; + +/** + * pstore_blk_get_config - get a copy of the pstore_blk backend configuration + * + * @info: The sturct pstore_blk_config to be filled in + * + * Failure returns negative error code, and success returns 0. + */ +int pstore_blk_get_config(struct pstore_blk_config *info); + #endif -- cgit v1.2.3 From 7dcb7848ba110ff192efc917d1a6de66b4c9ca4f Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:05 +0800 Subject: pstore/blk: Support non-block storage devices Add support for non-block devices (e.g. MTD). A non-block driver calls pstore_blk_register_device() to register iself. In addition, pstore/zone is updated to handle non-block devices, where an erase must be done before a write. Without this, there is no way to remove records stored to an MTD. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-10-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/pstore_zone.h | 6 ++++++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h index 0c40774e71e0..61e914522b01 100644 --- a/include/linux/pstore_blk.h +++ b/include/linux/pstore_blk.h @@ -49,6 +49,44 @@ struct pstore_blk_info { int register_pstore_blk(struct pstore_blk_info *info); void unregister_pstore_blk(unsigned int major); +/** + * struct pstore_device_info - back-end pstore/blk driver structure. + * + * @total_size: The total size in bytes pstore/blk can use. It must be greater + * than 4096 and be multiple of 4096. + * @flags: Refer to macro starting with PSTORE_FLAGS defined in + * linux/pstore.h. It means what front-ends this device support. + * Zero means all backends for compatible. + * @read: The general read operation. Both of the function parameters + * @size and @offset are relative value to bock device (not the + * whole disk). + * On success, the number of bytes should be returned, others + * means error. + * @write: The same as @read, but the following error number: + * -EBUSY means try to write again later. + * -ENOMSG means to try next zone. + * @erase: The general erase operation for device with special removing + * job. Both of the function parameters @size and @offset are + * relative value to storage. + * Return 0 on success and others on failure. + * @panic_write:The write operation only used for panic case. It's optional + * if you do not care panic log. The parameters are relative + * value to storage. + * On success, the number of bytes should be returned, others + * excluding -ENOMSG mean error. -ENOMSG means to try next zone. + */ +struct pstore_device_info { + unsigned long total_size; + unsigned int flags; + pstore_zone_read_op read; + pstore_zone_write_op write; + pstore_zone_erase_op erase; + pstore_zone_write_op panic_write; +}; + +int register_pstore_device(struct pstore_device_info *dev); +void unregister_pstore_device(struct pstore_device_info *dev); + /** * struct pstore_blk_config - the pstore_blk backend configuration * diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index e79a18e41064..1e35eaa33e5e 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -7,6 +7,7 @@ typedef ssize_t (*pstore_zone_read_op)(char *, size_t, loff_t); typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); +typedef ssize_t (*pstore_zone_erase_op)(size_t, loff_t); /** * struct pstore_zone_info - pstore/zone back-end driver structure * @@ -27,6 +28,10 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @write: The same as @read, but the following error number: * -EBUSY means try to write again later. * -ENOMSG means to try next zone. + * @erase: The general erase operation for device with special removing + * job. Both of the function parameters @size and @offset are + * relative value to storage. + * Return 0 on success and others on failure. * @panic_write:The write operation only used for panic case. It's optional * if you do not care panic log. The parameters are relative * value to storage. @@ -45,6 +50,7 @@ struct pstore_zone_info { unsigned long ftrace_size; pstore_zone_read_op read; pstore_zone_write_op write; + pstore_zone_erase_op erase; pstore_zone_write_op panic_write; }; -- cgit v1.2.3 From 0958f0cefede403037653e44de0e3332d10b0e1a Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 25 May 2020 16:41:19 +0200 Subject: KVM: introduce kvm_read_guest_offset_cached() We already have kvm_write_guest_offset_cached(), introduce read analogue. Signed-off-by: Vitaly Kuznetsov Message-Id: <20200525144125.143875-5-vkuznets@redhat.com> 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 161684696610..f43b59b1294c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -734,6 +734,9 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, 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); +int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned int offset, + unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, -- cgit v1.2.3 From 97e27aaa9a2cbd6238c66b3251d397e0eacc9968 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 19 Mar 2020 23:45:01 -0400 Subject: ceph: add read/write latency metric support Calculate the latency for OSD read requests. Add a new r_end_stamp field to struct ceph_osd_request that will hold the time of that the reply was received. Use that to calculate the RTT for each call, and divide the sum of those by number of calls to get averate RTT. Keep a tally of RTT for OSD writes and number of calls to track average latency of OSD writes. URL: https://tracker.ceph.com/issues/43215 Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 9d9f745b98a1..734f7c6a9f56 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -213,6 +214,8 @@ struct ceph_osd_request { /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ unsigned long r_start_stamp; /* jiffies */ + ktime_t r_start_latency; /* ktime_t */ + ktime_t r_end_latency; /* ktime_t */ int r_attempts; u32 r_map_dne_bound; -- cgit v1.2.3 From 53ab8e7cd2d47594e68951994ac083d30f82fce4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:51:38 -0500 Subject: libceph, rbd: replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/mon_client.h | 2 +- include/linux/crush/crush.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index dbb8a6959a73..ce4ffeb384d7 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -19,7 +19,7 @@ struct ceph_monmap { struct ceph_fsid fsid; u32 epoch; u32 num_mon; - struct ceph_entity_inst mon_inst[0]; + struct ceph_entity_inst mon_inst[]; }; struct ceph_mon_client; diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 54741295c70b..38b0e4d50ed9 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -87,7 +87,7 @@ struct crush_rule_mask { struct crush_rule { __u32 len; struct crush_rule_mask mask; - struct crush_rule_step steps[0]; + struct crush_rule_step steps[]; }; #define crush_rule_size(len) (sizeof(struct crush_rule) + \ -- cgit v1.2.3 From 8a4b863c876d9f135fa00cfe65774c3740970303 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 May 2020 16:46:47 +0200 Subject: libceph: add non-asserting rbtree insertion helper Needed for the next commit and useful for ceph_pg_pool_info tree as well. I'm leaving the asserting helper in for now, but we should look at getting rid of it in the future. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 525b7c3f1c81..4b5a47bcaba4 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -188,7 +188,7 @@ static inline int calc_pages_for(u64 off, u64 len) #define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b)) #define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ -static void insert_##name(struct rb_root *root, type *t) \ +static bool __insert_##name(struct rb_root *root, type *t) \ { \ struct rb_node **n = &root->rb_node; \ struct rb_node *parent = NULL; \ @@ -206,11 +206,17 @@ static void insert_##name(struct rb_root *root, type *t) \ else if (cmp > 0) \ n = &(*n)->rb_right; \ else \ - BUG(); \ + return false; \ } \ \ rb_link_node(&t->nodefld, parent, n); \ rb_insert_color(&t->nodefld, root); \ + return true; \ +} \ +static void __maybe_unused insert_##name(struct rb_root *root, type *t) \ +{ \ + if (!__insert_##name(root, t)) \ + BUG(); \ } \ static void erase_##name(struct rb_root *root, type *t) \ { \ -- cgit v1.2.3 From 86403a92c3c5c6c395983fdbfc5e2f29dc39279b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 May 2020 17:09:52 +0200 Subject: libceph: decode CRUSH device/bucket types and names These would be matched with the provided client location to calculate the locality value. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/crush/crush.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 38b0e4d50ed9..33c16f2de7f6 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -301,6 +301,12 @@ struct crush_map { __u32 *choose_tries; #else + /* device/bucket type id -> type name (CrushWrapper::type_map) */ + struct rb_root type_names; + + /* device/bucket id -> name (CrushWrapper::name_map) */ + struct rb_root names; + /* CrushWrapper::choose_args */ struct rb_root choose_args; #endif @@ -342,4 +348,10 @@ struct crush_work { struct crush_work_bucket **work; /* Per-bucket working store */ }; +#ifdef __KERNEL__ +/* osdmap.c */ +void clear_crush_names(struct rb_root *root); +void clear_choose_args(struct crush_map *c); +#endif + #endif -- cgit v1.2.3 From 45e6aa9f5592cd127367074f4822039cd8a825c3 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 22 May 2020 15:24:53 +0200 Subject: libceph: crush_location infrastructure Allow expressing client's location in terms of CRUSH hierarchy as a set of (bucket type name, bucket name) pairs. The userspace syntax "crush_location = key1=value1 key2=value2" is incompatible with mount options and needed adaptation. Key-value pairs are separated by '|' and we use ':' instead of '=' to separate keys from values. So for: crush_location = host=foo rack=bar one would write: crush_location=host:foo|rack:bar As in userspace, "multipath" locations are supported, so indicating locality for parallel hierarchies is possible: crush_location=rack:foo1|rack:foo2|datacenter:bar Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 1 + include/linux/ceph/osdmap.h | 16 +++++++++++++++- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4b5a47bcaba4..4733959f1ec7 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -64,6 +64,7 @@ struct ceph_options { int num_mon; char *name; struct ceph_crypto_key *key; + struct rb_root crush_locs; }; /* diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 5e601975745f..8c9d18cc9f45 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -302,9 +302,23 @@ bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid); +struct crush_loc { + char *cl_type_name; + char *cl_name; +}; + +struct crush_loc_node { + struct rb_node cl_node; + struct crush_loc cl_loc; /* pointers into cl_data */ + char cl_data[]; +}; + +int ceph_parse_crush_location(char *crush_location, struct rb_root *locs); +int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2); +void ceph_clear_crush_locs(struct rb_root *locs); + extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id); - 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); -- cgit v1.2.3 From 117d96a04f007ce8fc2e292369056c3bd09f6f63 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 23 May 2020 11:45:48 +0200 Subject: libceph: support for balanced and localized reads OSD-side issues with reads from replica have been resolved in Octopus. Reading from replica should be safe wrt. unstable or uncommitted state now, so add support for balanced and localized reads. There are two cases when a read from replica can't be served: - OSD may silently drop the request, expecting the client to notice that the acting set has changed and resend via the usual means (handled with t->used_replica) - OSD may return EAGAIN, expecting the client to resend to the primary, ignoring replica read flags (see handle_reply()) Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/osd_client.h | 1 + include/linux/ceph/osdmap.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 734f7c6a9f56..671fb93e8c60 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -165,6 +165,7 @@ struct ceph_osd_request_target { bool recovery_deletes; unsigned int flags; /* CEPH_OSD_FLAG_* */ + bool used_replica; bool paused; u32 epoch; diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 8c9d18cc9f45..3f4498fef6ad 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -317,6 +317,9 @@ int ceph_parse_crush_location(char *crush_location, struct rb_root *locs); int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2); void ceph_clear_crush_locs(struct rb_root *locs); +int ceph_get_crush_locality(struct ceph_osdmap *osdmap, int id, + struct rb_root *locs); + extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id); extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); -- cgit v1.2.3 From 8ad44d5e0d1eda7e4a0ed382174888476dc81789 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 23 May 2020 11:47:33 +0200 Subject: libceph: read_from_replica option Expose replica reads through read_from_replica=balance and read_from_replica=localize. The default is to read from primary (read_from_replica=no). Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4733959f1ec7..2247e71beb83 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -53,6 +53,8 @@ struct ceph_options { unsigned long osd_keepalive_timeout; /* jiffies */ unsigned long osd_request_timeout; /* jiffies */ + u32 osd_req_flags; /* CEPH_OSD_FLAG_*, applied to each OSD request */ + /* * any type that can't be simply compared or doesn't need * to be compared should go beyond this point, -- cgit v1.2.3 From c39ba6b3a8d47be07c180f857564a25a0356d336 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Mon, 1 Jun 2020 08:44:39 +0000 Subject: workqueue: fix a piece of comment about reserved bits for work flags 8a2e8e5dec7e("workqueue: fix cwq->nr_active underflow") allocated one more bit from the work flags, and it updated partial of the comments (128 bytes -> 256 bytes), but it failed to update the info about the number of reserved bits. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 8b505d22fc0e..26de0cae2a0a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -62,7 +62,7 @@ enum { WORK_CPU_UNBOUND = NR_CPUS, /* - * Reserve 7 bits off of pwq pointer w/ debugobjects turned off. + * Reserve 8 bits off of pwq pointer w/ debugobjects turned off. * This makes pwqs aligned to 256 bytes and allows 15 workqueue * flush colors. */ -- cgit v1.2.3 From abb30460bda232f304f642510adc8c6576ea51ea Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 1 Jun 2020 10:02:01 -0600 Subject: block: mark bio_wouldblock_error() bio with BIO_QUIET We really don't care about triggering buffer errors for this condition. This avoids a spew of: Buffer I/O error on dev sdc, logical block 785929, async page read Buffer I/O error on dev sdc, logical block 759095, async page read Buffer I/O error on dev sdc, logical block 766922, async page read Buffer I/O error on dev sdc, logical block 17659, async page read Buffer I/O error on dev sdc, logical block 637571, async page read Buffer I/O error on dev sdc, logical block 39241, async page read Buffer I/O error on dev sdc, logical block 397241, async page read Buffer I/O error on dev sdc, logical block 763992, async page read from -EAGAIN conditions on request allocation for async reads. Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 941378ec5b39..683ff5fd8871 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -417,6 +417,7 @@ static inline void bio_io_error(struct bio *bio) static inline void bio_wouldblock_error(struct bio *bio) { + bio_set_flag(bio, BIO_QUIET); bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } -- cgit v1.2.3 From 708b2000362476c9c7a3571c0cc774dffb91836a Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Tue, 26 May 2020 16:18:29 -0700 Subject: PCI/AER: Remove HEST/FIRMWARE_FIRST parsing for AER ownership Commit c100beb9ccfb ("PCI/AER: Use only _OSC to determine AER ownership") removed the use of HEST in determining AER ownership, but the AER driver still used HEST to verify AER ownership in some of its APIs. Per the ACPI spec v6.3, sec 18.3.2.4, some HEST table entries contain a FIRMWARE_FIRST bit, but that bit does not tell us anything about ownership of the AER capability. Remove parsing of HEST to look for FIRMWARE_FIRST. Add pcie_aer_is_native() for the places that need to know whether the OS owns the AER capability. [bhelgaas: commit log, reorder patch, remove unused __aer_firmware_first] Link: https://lore.kernel.org/r/9a37f53a4e6ff4942ff8e18dbb20b00e16c47341.1590534843.git.sathyanarayanan.kuppuswamy@linux.intel.com Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..43f265830eca 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -420,8 +420,6 @@ struct pci_dev { * mappings to make sure they cannot access arbitrary memory. */ unsigned int untrusted:1; - unsigned int __aer_firmware_first_valid:1; - unsigned int __aer_firmware_first:1; unsigned int broken_intx_masking:1; /* INTx masking can't be used */ unsigned int io_window_1k:1; /* Intel bridge 1K I/O windows */ unsigned int irq_managed:1; -- cgit v1.2.3 From bfad978116c2aa3b693701059923de4561196f9b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 28 May 2020 17:45:02 +0200 Subject: regmap: provide helpers for simple bit operations In many instances regmap_update_bits() is used for simple bit setting and clearing. In these cases the last argument is redundant and we can hide it with a static inline function. This adds three new helpers for simple bit operations: set_bits, clear_bits and test_bits (the last one defined as a regular function). Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/regmap.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..ddf0baff195d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1111,6 +1111,21 @@ bool regmap_reg_in_ranges(unsigned int reg, const struct regmap_range *ranges, unsigned int nranges); +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, bits, + NULL, false, false); +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, 0, NULL, false, false); +} + +int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits); + /** * struct reg_field - Description of an register field * @@ -1410,6 +1425,27 @@ static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_test_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force) -- cgit v1.2.3 From d3798acc094c8ff2406e9acc7a9b2c09da994616 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 29 May 2020 20:31:37 +0200 Subject: libceph: support for alloc hint flags Allow indicating future I/O pattern via flags. This is supported since Kraken (and bluestore persists flags together with expected_object_size and expected_write_size). Signed-off-by: Ilya Dryomov Reviewed-by: Jason Dillaman --- include/linux/ceph/osd_client.h | 4 +++- include/linux/ceph/rados.h | 14 ++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 671fb93e8c60..c60b59e9291b 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,7 @@ struct ceph_osd_req_op { struct { u64 expected_object_size; u64 expected_write_size; + u32 flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ } alloc_hint; struct { u64 snapid; @@ -472,7 +473,8 @@ extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, unsigned int which, u64 expected_object_size, - u64 expected_write_size); + u64 expected_write_size, + u32 flags); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 88ed3c5c04c5..3a518fd0eaad 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -464,6 +464,19 @@ enum { const char *ceph_osd_watch_op_name(int o); +enum { + CEPH_OSD_ALLOC_HINT_FLAG_SEQUENTIAL_WRITE = 1, + CEPH_OSD_ALLOC_HINT_FLAG_RANDOM_WRITE = 2, + CEPH_OSD_ALLOC_HINT_FLAG_SEQUENTIAL_READ = 4, + CEPH_OSD_ALLOC_HINT_FLAG_RANDOM_READ = 8, + CEPH_OSD_ALLOC_HINT_FLAG_APPEND_ONLY = 16, + CEPH_OSD_ALLOC_HINT_FLAG_IMMUTABLE = 32, + CEPH_OSD_ALLOC_HINT_FLAG_SHORTLIVED = 64, + CEPH_OSD_ALLOC_HINT_FLAG_LONGLIVED = 128, + CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE = 256, + CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE = 512, +}; + enum { CEPH_OSD_BACKOFF_OP_BLOCK = 1, CEPH_OSD_BACKOFF_OP_ACK_BLOCK = 2, @@ -517,6 +530,7 @@ struct ceph_osd_op { struct { __le64 expected_object_size; __le64 expected_write_size; + __le32 flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ } __attribute__ ((packed)) alloc_hint; struct { __le64 snapid; -- cgit v1.2.3 From 457f44363a8894135c85b7a9afd2bd8196db24ab Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 29 May 2020 00:54:20 -0700 Subject: bpf: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 13 +++++++++++++ include/linux/bpf_types.h | 1 + include/linux/bpf_verifier.h | 4 ++++ 3 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index efe8836b5c48..e5884f7f801c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -90,6 +90,8 @@ struct bpf_map_ops { int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); + __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts); }; struct bpf_map_memory { @@ -244,6 +246,9 @@ enum bpf_arg_type { ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ + ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ + ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ + ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ }; /* type of values returned from helper functions */ @@ -255,6 +260,7 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ + RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -322,6 +328,8 @@ enum bpf_reg_type { PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ PTR_TO_BTF_ID, /* reg points to kernel struct */ PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ + PTR_TO_MEM, /* reg points to valid memory region */ + PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -1611,6 +1619,11 @@ extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; +extern const struct bpf_func_proto bpf_ringbuf_output_proto; +extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; +extern const struct bpf_func_proto bpf_ringbuf_submit_proto; +extern const struct bpf_func_proto bpf_ringbuf_discard_proto; +extern const struct bpf_func_proto bpf_ringbuf_query_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 29d22752fc87..fa8e1b552acd 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -118,6 +118,7 @@ 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 +BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ea833087e853..ca08db4ffb5f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -54,6 +54,8 @@ struct bpf_reg_state { u32 btf_id; /* for PTR_TO_BTF_ID */ + u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ + /* Max size from any of the above. */ unsigned long raw; }; @@ -63,6 +65,8 @@ struct bpf_reg_state { * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. + * For PTR_TO_MEM_OR_NULL this is used to identify memory allocation + * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. */ -- cgit v1.2.3 From fbee97feed9b3e4acdf9590e1f6b4a2eefecfffe Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 29 May 2020 16:07:13 -0600 Subject: bpf: Add support to attach bpf program to a devmap entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern Signed-off-by: Alexei Starovoitov Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov --- 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 e5884f7f801c..e042311f991f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1250,6 +1250,7 @@ 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, struct bpf_prog *xdp_prog); +bool dev_map_can_have_prog(struct bpf_map *map); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_flush(void); @@ -1363,6 +1364,10 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map { return NULL; } +static inline bool dev_map_can_have_prog(struct bpf_map *map) +{ + return false; +} static inline void __dev_flush(void) { -- cgit v1.2.3 From e91de6afa81c10e9f855c5695eb9a53168d96b73 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 29 May 2020 16:06:59 -0700 Subject: bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ad31c9fb7158..08674cd14d5a 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -437,4 +437,12 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs) psock_set_prog(&progs->skb_verdict, NULL); } +int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); + +static inline bool sk_psock_strp_enabled(struct sk_psock *psock) +{ + if (!psock) + return false; + return psock->parser.enabled; +} #endif /* _LINUX_SKMSG_H */ -- cgit v1.2.3 From 958a3f2d2aff896ae2a622878e456114f4a4cd15 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 31 May 2020 17:42:55 +0200 Subject: bpf: Use tracing helpers for lsm programs Currenty lsm uses bpf_tracing_func_proto helpers which do not include stack trace or perf event output. It's useful to have those for bpftrace lsm support [1]. Using tracing_prog_func_proto helpers for lsm programs. [1] https://github.com/iovisor/bpftrace/pull/1347 Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Cc: KP Singh Link: https://lore.kernel.org/bpf/20200531154255.896551-1-jolsa@kernel.org --- 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 e042311f991f..07052d44bca1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1633,6 +1633,9 @@ extern const struct bpf_func_proto bpf_ringbuf_query_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); +const struct bpf_func_proto *tracing_prog_func_proto( + enum bpf_func_id func_id, const struct bpf_prog *prog); + /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -- cgit v1.2.3 From a3fd7ceee05431d2c51ed86c6cae015d236a51f0 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:36 +0200 Subject: net: Introduce netns_bpf for BPF programs attached to netns In order to: (1) attach more than one BPF program type to netns, or (2) support attaching BPF programs to netns with bpf_link, or (3) support multi-prog attach points for netns we will need to keep more state per netns than a single pointer like we have now for BPF flow dissector program. Prepare for the above by extracting netns_bpf that is part of struct net, for storing all state related to BPF programs attached to netns. Turn flow dissector callbacks for querying/attaching/detaching a program into generic ones that operate on netns_bpf. Next patch will move the generic callbacks into their own module. This is similar to how it is organized for cgroup with cgroup_bpf. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Cc: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20200531082846.2117903-3-jakub@cloudflare.com --- include/linux/bpf-netns.h | 56 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/skbuff.h | 26 ---------------------- 2 files changed, 56 insertions(+), 26 deletions(-) create mode 100644 include/linux/bpf-netns.h (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h new file mode 100644 index 000000000000..f3aec3d79824 --- /dev/null +++ b/include/linux/bpf-netns.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_NETNS_H +#define _BPF_NETNS_H + +#include +#include + +enum netns_bpf_attach_type { + NETNS_BPF_INVALID = -1, + NETNS_BPF_FLOW_DISSECTOR = 0, + MAX_NETNS_BPF_ATTACH_TYPE +}; + +static inline enum netns_bpf_attach_type +to_netns_bpf_attach_type(enum bpf_attach_type attach_type) +{ + switch (attach_type) { + case BPF_FLOW_DISSECTOR: + return NETNS_BPF_FLOW_DISSECTOR; + default: + return NETNS_BPF_INVALID; + } +} + +/* Protects updates to netns_bpf */ +extern struct mutex netns_bpf_mutex; + +union bpf_attr; +struct bpf_prog; + +#ifdef CONFIG_NET +int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); +int netns_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog); +int netns_bpf_prog_detach(const union bpf_attr *attr); +#else +static inline int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + +static inline int netns_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +static inline int netns_bpf_prog_detach(const union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} +#endif + +#endif /* _BPF_NETNS_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 531843952809..a0d5c2760103 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1283,32 +1283,6 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); -#ifdef CONFIG_NET -int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr); -int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog); - -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); -#else -static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) -{ - return -EOPNOTSUPP; -} -#endif - struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); -- cgit v1.2.3 From 7f045a49fee04b5662cbdeaf0838f9322ae8c63a Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:38 +0200 Subject: bpf: Add link-based BPF program attachment to network namespace Extend bpf() syscall subcommands that operate on bpf_link, that is LINK_CREATE, LINK_UPDATE, OBJ_GET_INFO, to accept attach types tied to network namespaces (only flow dissector at the moment). Link-based and prog-based attachment can be used interchangeably, but only one can exist at a time. Attempts to attach a link when a prog is already attached directly, and the other way around, will be met with -EEXIST. Attempts to detach a program when link exists result in -EINVAL. Attachment of multiple links of same attach type to one netns is not supported with the intention to lift the restriction when a use-case presents itself. Because of that link create returns -E2BIG when trying to create another netns link, when one already exists. Link-based attachments to netns don't keep a netns alive by holding a ref to it. Instead links get auto-detached from netns when the latter is being destroyed, using a pernet pre_exit callback. When auto-detached, link lives in defunct state as long there are open FDs for it. -ENOLINK is returned if a user tries to update a defunct link. Because bpf_link to netns doesn't hold a ref to struct net, special care is taken when releasing, updating, or filling link info. The netns might be getting torn down when any of these link operations are in progress. That is why auto-detach and update/release/fill_info are synchronized by the same mutex. Also, link ops have to always check if auto-detach has not happened yet and if netns is still alive (refcnt > 0). Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200531082846.2117903-5-jakub@cloudflare.com --- include/linux/bpf-netns.h | 8 ++++++++ include/linux/bpf_types.h | 3 +++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index f3aec3d79824..4052d649f36d 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -34,6 +34,8 @@ int netns_bpf_prog_query(const union bpf_attr *attr, int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netns_bpf_prog_detach(const union bpf_attr *attr); +int netns_bpf_link_create(const union bpf_attr *attr, + struct bpf_prog *prog); #else static inline int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -51,6 +53,12 @@ static inline int netns_bpf_prog_detach(const union bpf_attr *attr) { return -EOPNOTSUPP; } + +static inline int netns_bpf_link_create(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif #endif /* _BPF_NETNS_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa8e1b552acd..a18ae82a298a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -126,3 +126,6 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) #endif BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) +#ifdef CONFIG_NET +BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +#endif -- cgit v1.2.3 From a865e420b9561235851c3f5d483c82ef389d29bd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 6 Apr 2020 08:42:55 -0400 Subject: virtio: force spec specified alignment on types The ring element addresses are passed between components with different alignments assumptions. Thus, if guest/userspace selects a pointer and host then gets and dereferences it, we might need to decrease the compiler-selected alignment to prevent compiler on the host from assuming pointer is aligned. This actually triggers on ARM with -mabi=apcs-gnu - which is a deprecated configuration, but it seems safer to handle this generally. Note that userspace that allocates the memory is actually OK and does not need to be fixed, but userspace that gets it from guest or another process does need to be fixed. The later doesn't generally talk to the kernel so while it might be buggy it's not talking to the kernel in the buggy way - it's just using the header in the buggy way - so fixing header and asking userspace to recompile is the best we can do. I verified that the produced kernel binary on x86 is exactly identical before and after the change. Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vringh.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 9e2763d7c159..59bd50f99291 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -105,9 +105,9 @@ struct vringh_kiov { /* Helpers for userspace vrings. */ int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used); + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used); static inline void vringh_iov_init(struct vringh_iov *iov, struct iovec *iovec, unsigned num) -- cgit v1.2.3 From 25de110d148666752dc0e0da7a0b69de31cd7098 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 2 Jun 2020 12:08:39 +0200 Subject: irq_work: Define irq_work_single() on !CONFIG_IRQ_WORK too Some SMP platforms don't have CONFIG_IRQ_WORK defined, resulting in a link error at build time. Define a stub and clean up the prototype definitions. Reported-by: kbuild test robot Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/irq_work.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index f23a359c8f46..2735da5f839e 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -58,9 +58,11 @@ void irq_work_sync(struct irq_work *work); void irq_work_run(void); bool irq_work_needs_cpu(void); +void irq_work_single(void *arg); #else static inline bool irq_work_needs_cpu(void) { return false; } static inline void irq_work_run(void) { } +static inline void irq_work_single(void *arg) { } #endif #endif /* _LINUX_IRQ_WORK_H */ -- cgit v1.2.3 From ef3534a94fdbdeab4c89d18d0164be2ad5d6dbb7 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Tue, 2 Jun 2020 09:42:08 +0530 Subject: hw-breakpoints: Fix build warnings with clang kbuild test robot reported some build warnings in the hw_breakpoint code when compiled with clang[1]. Some of them were introduced by the recent powerpc change to add arch_reserve_bp_slot() and arch_release_bp_slot(). Fix them all. kernel/events/hw_breakpoint.c:71:12: warning: no previous prototype for function 'hw_breakpoint_weight' kernel/events/hw_breakpoint.c:216:12: warning: no previous prototype for function 'arch_reserve_bp_slot' kernel/events/hw_breakpoint.c:221:13: warning: no previous prototype for function 'arch_release_bp_slot' kernel/events/hw_breakpoint.c:228:13: warning: no previous prototype for function 'arch_unregister_hw_breakpoint' [1]: https://lore.kernel.org/linuxppc-dev/202005192233.oi9CjRtA%25lkp@intel.com/ Fixes: 29da4f91c0c1 ("powerpc/watchpoint: Don't allow concurrent perf and ptrace events") Reported-by: kbuild test robot Signed-off-by: Ravi Bangoria [mpe: Drop extern, flesh out change log, add Fixes tag] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200602041208.128913-1-ravi.bangoria@linux.ibm.com --- include/linux/hw_breakpoint.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 6058c3844a76..d7d4250cd1e4 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -80,6 +80,10 @@ extern int dbg_reserve_bp_slot(struct perf_event *bp); extern int dbg_release_bp_slot(struct perf_event *bp); extern int reserve_bp_slot(struct perf_event *bp); extern void release_bp_slot(struct perf_event *bp); +int hw_breakpoint_weight(struct perf_event *bp); +int arch_reserve_bp_slot(struct perf_event *bp); +void arch_release_bp_slot(struct perf_event *bp); +void arch_unregister_hw_breakpoint(struct perf_event *bp); extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk); -- cgit v1.2.3 From c893de12e1ef17b581eb2cf8fc9018ec0cbd07df Mon Sep 17 00:00:00 2001 From: Wei Li Date: Thu, 21 May 2020 15:21:25 +0800 Subject: kdb: Remove the misfeature 'KDBFLAGS' Currently, 'KDBFLAGS' is an internal variable of kdb, it is combined by 'KDBDEBUG' and state flags. It will be shown only when 'KDBDEBUG' is set, and the user can define an environment variable named 'KDBFLAGS' too. These are puzzling indeed. After communication with Daniel, it seems that 'KDBFLAGS' is a misfeature. So let's replace 'KDBFLAGS' with 'KDBDEBUG' to just show the value we wrote into. After this modification, we can use `md4c1 kdb_flags` instead, to observe the state flags. Suggested-by: Daniel Thompson Signed-off-by: Wei Li Link: https://lore.kernel.org/r/20200521072125.21103-1-liwei391@huawei.com [daniel.thompson@linaro.org: Make kdb_flags unsigned to avoid arithmetic right shift] Signed-off-by: Daniel Thompson --- include/linux/kdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 24cd447659e0..0125a677b67f 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -125,7 +125,7 @@ extern const char *kdb_diemsg; #define KDB_FLAG_NO_I8042 (1 << 7) /* No i8042 chip is available, do * not use keyboard */ -extern int kdb_flags; /* Global flags, see kdb_state for per cpu state */ +extern unsigned int kdb_flags; /* Global flags, see kdb_state for per cpu state */ extern void kdb_save_flags(void); extern void kdb_restore_flags(void); -- cgit v1.2.3 From 735e4ae5ba28c886d249ad04d3c8cc097dad6336 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 1 Jun 2020 21:45:36 -0700 Subject: vfs: track per-sb writeback errors and report them to syncfs Patch series "vfs: have syncfs() return error when there are writeback errors", v6. Currently, syncfs does not return errors when one of the inodes fails to be written back. It will return errors based on the legacy AS_EIO and AS_ENOSPC flags when syncing out the block device fails, but that's not particularly helpful for filesystems that aren't backed by a blockdev. It's also possible for a stray sync to lose those errors. The basic idea in this set is to track writeback errors at the superblock level, so that we can quickly and easily check whether something bad happened without having to fsync each file individually. syncfs is then changed to reliably report writeback errors after they occur, much in the same fashion as fsync does now. This patch (of 2): Usually we suggest that applications call fsync when they want to ensure that all data written to the file has made it to the backing store, but that can be inefficient when there are a lot of open files. Calling syncfs on the filesystem can be more efficient in some situations, but the error reporting doesn't currently work the way most people expect. If a single inode on a filesystem reports a writeback error, syncfs won't necessarily return an error. syncfs only returns an error if __sync_blockdev fails, and on some filesystems that's a no-op. It would be better if syncfs reported an error if there were any writeback failures. Then applications could call syncfs to see if there are any errors on any open files, and could then call fsync on all of the other descriptors to figure out which one failed. This patch adds a new errseq_t to struct super_block, and has mapping_set_error also record writeback errors there. To report those errors, we also need to keep an errseq_t in struct file to act as a cursor. This patch adds a dedicated field for that purpose, which slots nicely into 4 bytes of padding at the end of struct file on x86_64. An earlier version of this patch used an O_PATH file descriptor to cue the kernel that the open file should track the superblock error and not the inode's writeback error. I think that API is just too weird though. This is simpler and should make syncfs error reporting "just work" even if someone is multiplexing fsync and syncfs on the same fds. Signed-off-by: Jeff Layton Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Cc: Andres Freund Cc: Matthew Wilcox Cc: Al Viro Cc: Christoph Hellwig Cc: Dave Chinner Cc: David Howells Link: http://lkml.kernel.org/r/20200428135155.19223-1-jlayton@kernel.org Link: http://lkml.kernel.org/r/20200428135155.19223-2-jlayton@kernel.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 16 ++++++++++++++++ include/linux/pagemap.h | 5 ++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..f2fb5b7406b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -976,6 +976,7 @@ struct file { #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; + errseq_t f_sb_err; /* for syncfs */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1520,6 +1521,9 @@ struct super_block { /* Being remounted read-only */ int s_readonly_remount; + /* per-sb errseq_t for reporting writeback errors via syncfs */ + errseq_t s_wb_err; + /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; @@ -2827,6 +2831,18 @@ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) return errseq_sample(&mapping->wb_err); } +/** + * file_sample_sb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Grab the most current superblock-level errseq_t value for the given + * struct file. + */ +static inline errseq_t file_sample_sb_err(struct file *file) +{ + return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a8f7bd8ea1c6..d4409b13747e 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -51,7 +51,10 @@ static inline void mapping_set_error(struct address_space *mapping, int error) return; /* Record in wb_err for checkers using errseq_t based tracking */ - filemap_set_wb_err(mapping, error); + __filemap_set_wb_err(mapping, error); + + /* Record it in superblock */ + errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) -- cgit v1.2.3 From cee9a0c4e84db024d692d6b5c18f65465eb06905 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:07 -0700 Subject: mm: move readahead prototypes from mm.h Patch series "Change readahead API", v11. This series adds a readahead address_space operation to replace the readpages operation. The key difference is that pages are added to the page cache as they are allocated (and then looked up by the filesystem) instead of passing them on a list to the readpages operation and having the filesystem add them to the page cache. It's a net reduction in code for each implementation, more efficient than walking a list, and solves the direct-write vs buffered-read problem reported by yu kuai at http://lkml.kernel.org/r/20200116063601.39201-1-yukuai3@huawei.com The only unconverted filesystems are those which use fscache. Their conversion is pending Dave Howells' rewrite which will make the conversion substantially easier. This should be completed by the end of the year. I want to thank the reviewers/testers; Dave Chinner, John Hubbard, Eric Biggers, Johannes Thumshirn, Dave Sterba, Zi Yan, Christoph Hellwig and Miklos Szeredi have done a marvellous job of providing constructive criticism. These patches pass an xfstests run on ext4, xfs & btrfs with no regressions that I can tell (some of the tests seem a little flaky before and remain flaky afterwards). This patch (of 25): The readahead code is part of the page cache so should be found in the pagemap.h file. force_page_cache_readahead is only used within mm, so move it to mm/internal.h instead. Remove the parameter names where they add no value, and rename the ones which were actively misleading. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Reviewed-by: Johannes Thumshirn Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-1-willy@infradead.org Link: http://lkml.kernel.org/r/20200414150233.24495-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 19 ------------------- include/linux/pagemap.h | 8 ++++++++ 2 files changed, 8 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3fe7371855c..92704fde6475 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2612,25 +2612,6 @@ extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); -/* readahead.c */ -#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) - -int force_page_cache_readahead(struct address_space *mapping, struct file *filp, - pgoff_t offset, unsigned long nr_to_read); - -void page_cache_sync_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - pgoff_t offset, - unsigned long size); - -void page_cache_async_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - struct page *pg, - pgoff_t offset, - unsigned long size); - extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d4409b13747e..8c081cda4b35 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -618,6 +618,14 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); +#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) + +void page_cache_sync_readahead(struct address_space *, struct file_ra_state *, + struct file *, pgoff_t index, unsigned long req_count); +void page_cache_async_readahead(struct address_space *, struct file_ra_state *, + struct file *, struct page *, pgoff_t index, + unsigned long req_count); + /* * Like add_to_page_cache_locked, but used to add newly allocated pages: * the page is new, so we can just run __SetPageLocked() against it. -- cgit v1.2.3 From 042124cc64c33555deba0b11c6e0c612ae7a8653 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:21 -0700 Subject: mm: add new readahead_control API Filesystems which implement the upcoming ->readahead method will get their pages by calling readahead_page() or readahead_page_batch(). These functions support large pages, even though none of the filesystems to be converted do yet. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: John Hubbard Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-6-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 140 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 140 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8c081cda4b35..c3bf73263ec9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -642,6 +642,146 @@ static inline int add_to_page_cache(struct page *page, return error; } +/** + * struct readahead_control - Describes a readahead request. + * + * A readahead request is for consecutive pages. Filesystems which + * implement the ->readahead method should call readahead_page() or + * readahead_page_batch() in a loop and attempt to start I/O against + * each page in the request. + * + * Most of the fields in this struct are private and should be accessed + * by the functions below. + * + * @file: The file, used primarily by network filesystems for authentication. + * May be NULL if invoked internally by the filesystem. + * @mapping: Readahead this filesystem object. + */ +struct readahead_control { + struct file *file; + struct address_space *mapping; +/* private: use the readahead_* accessors instead */ + pgoff_t _index; + unsigned int _nr_pages; + unsigned int _batch_count; +}; + +/** + * readahead_page - Get the next page to read. + * @rac: The current readahead request. + * + * Context: The page is locked and has an elevated refcount. The caller + * should decreases the refcount once the page has been submitted for I/O + * and unlock the page once all I/O to that page has completed. + * Return: A pointer to the next page, or %NULL if we are done. + */ +static inline struct page *readahead_page(struct readahead_control *rac) +{ + struct page *page; + + BUG_ON(rac->_batch_count > rac->_nr_pages); + rac->_nr_pages -= rac->_batch_count; + rac->_index += rac->_batch_count; + + if (!rac->_nr_pages) { + rac->_batch_count = 0; + return NULL; + } + + page = xa_load(&rac->mapping->i_pages, rac->_index); + VM_BUG_ON_PAGE(!PageLocked(page), page); + rac->_batch_count = hpage_nr_pages(page); + + return page; +} + +static inline unsigned int __readahead_batch(struct readahead_control *rac, + struct page **array, unsigned int array_sz) +{ + unsigned int i = 0; + XA_STATE(xas, &rac->mapping->i_pages, 0); + struct page *page; + + BUG_ON(rac->_batch_count > rac->_nr_pages); + rac->_nr_pages -= rac->_batch_count; + rac->_index += rac->_batch_count; + rac->_batch_count = 0; + + xas_set(&xas, rac->_index); + rcu_read_lock(); + xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageTail(page), page); + array[i++] = page; + rac->_batch_count += hpage_nr_pages(page); + + /* + * The page cache isn't using multi-index entries yet, + * so the xas cursor needs to be manually moved to the + * next index. This can be removed once the page cache + * is converted. + */ + if (PageHead(page)) + xas_set(&xas, rac->_index + rac->_batch_count); + + if (i == array_sz) + break; + } + rcu_read_unlock(); + + return i; +} + +/** + * readahead_page_batch - Get a batch of pages to read. + * @rac: The current readahead request. + * @array: An array of pointers to struct page. + * + * Context: The pages are locked and have an elevated refcount. The caller + * should decreases the refcount once the page has been submitted for I/O + * and unlock the page once all I/O to that page has completed. + * Return: The number of pages placed in the array. 0 indicates the request + * is complete. + */ +#define readahead_page_batch(rac, array) \ + __readahead_batch(rac, array, ARRAY_SIZE(array)) + +/** + * readahead_pos - The byte offset into the file of this readahead request. + * @rac: The readahead request. + */ +static inline loff_t readahead_pos(struct readahead_control *rac) +{ + return (loff_t)rac->_index * PAGE_SIZE; +} + +/** + * readahead_length - The number of bytes in this readahead request. + * @rac: The readahead request. + */ +static inline loff_t readahead_length(struct readahead_control *rac) +{ + return (loff_t)rac->_nr_pages * PAGE_SIZE; +} + +/** + * readahead_index - The index of the first page in this readahead request. + * @rac: The readahead request. + */ +static inline pgoff_t readahead_index(struct readahead_control *rac) +{ + return rac->_index; +} + +/** + * readahead_count - The number of pages in this readahead request. + * @rac: The readahead request. + */ +static inline unsigned int readahead_count(struct readahead_control *rac) +{ + return rac->_nr_pages; +} + static inline unsigned long dir_pages(struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> -- cgit v1.2.3 From 8151b4c8bee43cea7a28cb0300123df90880e60c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:44 -0700 Subject: mm: add readahead address space operation This replaces ->readpages with a saner interface: - Return void instead of an ignored error code. - Page cache is already populated with locked pages when ->readahead is called. - New arguments can be passed to the implementation without changing all the filesystems that use a common helper function like mpage_readahead(). Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-12-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f2fb5b7406b9..1434ed801b80 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -292,6 +292,7 @@ enum positive_aop_returns { struct page; struct address_space; struct writeback_control; +struct readahead_control; /* * Write life time hint values. @@ -375,6 +376,7 @@ struct address_space_operations { */ int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); + void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, -- cgit v1.2.3 From 2c684234d36f7e8c80414e4a772911d407e821fa Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:51 -0700 Subject: mm: add page_cache_readahead_unbounded ext4 and f2fs have duplicated the guts of the readahead code so they can read past i_size. Instead, separate out the guts of the readahead code so they can call it directly. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Tested-by: Eric Biggers Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Reviewed-by: Eric Biggers Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Gao Xiang Cc: Jaegeuk Kim Cc: John Hubbard Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-14-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c3bf73263ec9..c6348c50136f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -625,6 +625,9 @@ void page_cache_sync_readahead(struct address_space *, struct file_ra_state *, void page_cache_async_readahead(struct address_space *, struct file_ra_state *, struct file *, struct page *, pgoff_t index, unsigned long req_count); +void page_cache_readahead_unbounded(struct address_space *, struct file *, + pgoff_t index, unsigned long nr_to_read, + unsigned long lookahead_count); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: -- cgit v1.2.3 From d4388340ae0bc8397ef5b24342279f7739982918 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:47:02 -0700 Subject: fs: convert mpage_readpages to mpage_readahead Implement the new readahead aop and convert all callers (block_dev, exfat, ext2, fat, gfs2, hpfs, isofs, jfs, nilfs2, ocfs2, omfs, qnx6, reiserfs & udf). The callers are all trivial except for GFS2 & OCFS2. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Junxiao Bi # ocfs2 Reviewed-by: Joseph Qi # ocfs2 Reviewed-by: Dave Chinner Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-17-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mpage.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 001f1fcf9836..f4f5e90a6844 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -13,9 +13,9 @@ #ifdef CONFIG_BLOCK struct writeback_control; +struct readahead_control; -int mpage_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages, get_block_t get_block); +void mpage_readahead(struct readahead_control *, get_block_t get_block); int mpage_readpage(struct page *page, get_block_t get_block); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); -- cgit v1.2.3 From 9d24a13a93d995e4c980fdaa389aa3e2f1ea0b12 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:47:34 -0700 Subject: iomap: convert from readpages to readahead Use the new readahead operation in iomap. Convert XFS and ZoneFS to use it. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: John Hubbard Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-26-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/iomap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..bc20bd04c2a2 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -155,8 +155,7 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); -int iomap_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages, const struct iomap_ops *ops); +void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); int iomap_set_page_dirty(struct page *page); int iomap_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); -- cgit v1.2.3 From b03143accd9274d9e024da42ed5857a71a6b6a27 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 1 Jun 2020 21:47:38 -0700 Subject: include/linux/pagemap.h: introduce attach/detach_page_private MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Introduce attach/detach_page_private to cleanup code". This patch (of 10): The logic in attach_page_buffers and __clear_page_buffers are quite paired, but 1. they are located in different files. 2. attach_page_buffers is implemented in buffer_head.h, so it could be used by other files. But __clear_page_buffers is static function in buffer.c and other potential users can't call the function, md-bitmap even copied the function. So, introduce the new attach/detach_page_private to replace them. With the new pair of function, we will remove the usage of attach_page_buffers and __clear_page_buffers in next patches. Thanks for suggestions about the function name from Alexander Viro, Andreas Grünbacher, Christoph Hellwig and Matthew Wilcox. Suggested-by: Matthew Wilcox Signed-off-by: Guoqing Jiang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: "Darrick J. Wong" Cc: William Kucharski Cc: "Kirill A. Shutemov" Cc: Andreas Gruenbacher Cc: Yang Shi Cc: Yafang Shao Cc: Song Liu Cc: Chris Mason Cc: Josef Bacik Cc: David Sterba Cc: Alexander Viro Cc: Jaegeuk Kim Cc: Chao Yu Cc: Christoph Hellwig Cc: Anton Altaparmakov Cc: Mike Marshall Cc: Martin Brandenburg Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Roman Gushchin Cc: Andreas Dilger Cc: Chao Yu Cc: Dave Chinner Link: http://lkml.kernel.org/r/20200517214718.468-1-guoqing.jiang@cloud.ionos.com Link: http://lkml.kernel.org/r/20200517214718.468-2-guoqing.jiang@cloud.ionos.com Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c6348c50136f..8e085713150c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -208,6 +208,43 @@ static inline int page_cache_add_speculative(struct page *page, int count) return __page_cache_add_speculative(page, count); } +/** + * attach_page_private - Attach private data to a page. + * @page: Page to attach data to. + * @data: Data to attach to page. + * + * Attaching private data to a page increments the page's reference count. + * The data must be detached before the page will be freed. + */ +static inline void attach_page_private(struct page *page, void *data) +{ + get_page(page); + set_page_private(page, (unsigned long)data); + SetPagePrivate(page); +} + +/** + * detach_page_private - Detach private data from a page. + * @page: Page to detach data from. + * + * Removes the data that was previously attached to the page and decrements + * the refcount on the page. + * + * Return: Data that was attached to the page. + */ +static inline void *detach_page_private(struct page *page) +{ + void *data = (void *)page_private(page); + + if (!PagePrivate(page)) + return NULL; + ClearPagePrivate(page); + set_page_private(page, 0); + put_page(page); + + return data; +} + #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else -- cgit v1.2.3 From 7b59435a2afed12dc9b2ec1b930efa2e94f1c397 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 1 Jun 2020 21:48:03 -0700 Subject: buffer_head.h: remove attach_page_buffers All the callers have replaced attach_page_buffers with the new function attach_page_private, so remove it. Signed-off-by: Guoqing Jiang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Roman Gushchin Cc: Andreas Dilger Link: http://lkml.kernel.org/r/20200517214718.468-10-guoqing.jiang@cloud.ionos.com Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 15b765a181b8..22fb11e2d2e0 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -272,14 +272,6 @@ void buffer_init(void); * inline definitions */ -static inline void attach_page_buffers(struct page *page, - struct buffer_head *head) -{ - get_page(page); - SetPagePrivate(page); - set_page_private(page, (unsigned long)head); -} - static inline void get_bh(struct buffer_head *bh) { atomic_inc(&bh->b_count); -- cgit v1.2.3 From 60e65a6f42d0af33fa7361bd8723adc70539121b Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 1 Jun 2020 21:48:09 -0700 Subject: mm_types.h: change set_page_private to inline function Change it to inline function to make callers use the proper argument. And no need for it to be macro per Andrew's comment [1]. [1] https://lore.kernel.org/lkml/20200518221235.1fa32c38e5766113f78e3f0d@linux-foundation.org/ Signed-off-by: Guoqing Jiang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200525203149.18802-1-guoqing.jiang@cloud.ionos.com Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4aba6c0c2ba8..ef6d3aface8a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,7 +240,11 @@ static inline atomic_t *compound_pincount_ptr(struct page *page) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) #define page_private(page) ((page)->private) -#define set_page_private(page, v) ((page)->private = (v)) + +static inline void set_page_private(struct page *page, unsigned long private) +{ + page->private = private; +} struct page_frag_cache { void * va; -- cgit v1.2.3 From a37b0715ddf3007734c4e2424c14bc7efcdd1190 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 1 Jun 2020 21:48:18 -0700 Subject: mm/writeback: replace PF_LESS_THROTTLE with PF_LOCAL_THROTTLE PF_LESS_THROTTLE exists for loop-back nfsd (and a similar need in the loop block driver and callers of prctl(PR_SET_IO_FLUSHER)), where a daemon needs to write to one bdi (the final bdi) in order to free up writes queued to another bdi (the client bdi). The daemon sets PF_LESS_THROTTLE and gets a larger allowance of dirty pages, so that it can still dirty pages after other processses have been throttled. The purpose of this is to avoid deadlock that happen when the PF_LESS_THROTTLE process must write for any dirty pages to be freed, but it is being thottled and cannot write. This approach was designed when all threads were blocked equally, independently on which device they were writing to, or how fast it was. Since that time the writeback algorithm has changed substantially with different threads getting different allowances based on non-trivial heuristics. This means the simple "add 25%" heuristic is no longer reliable. The important issue is not that the daemon needs a *larger* dirty page allowance, but that it needs a *private* dirty page allowance, so that dirty pages for the "client" bdi that it is helping to clear (the bdi for an NFS filesystem or loop block device etc) do not affect the throttling of the daemon writing to the "final" bdi. This patch changes the heuristic so that the task is not throttled when the bdi it is writing to has a dirty page count below below (or equal to) the free-run threshold for that bdi. This ensures it will always be able to have some pages in flight, and so will not deadlock. In a steady-state, it is expected that PF_LOCAL_THROTTLE tasks might still be throttled by global threshold, but that is acceptable as it is only the deadlock state that is interesting for this flag. This approach of "only throttle when target bdi is busy" is consistent with the other use of PF_LESS_THROTTLE in current_may_throttle(), were it causes attention to be focussed only on the target bdi. So this patch - renames PF_LESS_THROTTLE to PF_LOCAL_THROTTLE, - removes the 25% bonus that that flag gives, and - If PF_LOCAL_THROTTLE is set, don't delay at all unless the global and the local free-run thresholds are exceeded. Note that previously realtime threads were treated the same as PF_LESS_THROTTLE threads. This patch does *not* change the behvaiour for real-time threads, so it is now different from the behaviour of nfsd and loop tasks. I don't know what is wanted for realtime. [akpm@linux-foundation.org: coding style fixes] Signed-off-by: NeilBrown Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Acked-by: Chuck Lever [nfsd] Cc: Christoph Hellwig Cc: Michal Hocko Cc: Trond Myklebust Link: http://lkml.kernel.org/r/87ftbf7gs3.fsf@notabene.neil.brown.name Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..12ef0c753284 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1481,7 +1481,8 @@ extern struct pid *cad_pid; #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ -#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ +#define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, + * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -- cgit v1.2.3 From 8d92890bd6b8502d6aee4b37430ae6444ade7a8c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 1 Jun 2020 21:48:21 -0700 Subject: mm/writeback: discard NR_UNSTABLE_NFS, use NR_WRITEBACK instead After an NFS page has been written it is considered "unstable" until a COMMIT request succeeds. If the COMMIT fails, the page will be re-written. These "unstable" pages are currently accounted as "reclaimable", either in WB_RECLAIMABLE, or in NR_UNSTABLE_NFS which is included in a 'reclaimable' count. This might have made sense when sending the COMMIT required a separate action by the VFS/MM (e.g. releasepage() used to send a COMMIT). However now that all writes generated by ->writepages() will automatically be followed by a COMMIT (since commit 919e3bd9a875 ("NFS: Ensure we commit after writeback is complete")) it makes more sense to treat them as writeback pages. So this patch removes NR_UNSTABLE_NFS and accounts unstable pages in NR_WRITEBACK and WB_WRITEBACK. A particular effect of this change is that when wb_check_background_flush() calls wb_over_bg_threshold(), the latter will report 'true' a lot less often as the 'unstable' pages are no longer considered 'dirty' (as there is nothing that writeback can do about them anyway). Currently wb_check_background_flush() will trigger writeback to NFS even when there are relatively few dirty pages (if there are lots of unstable pages), this can result in small writes going to the server (10s of Kilobytes rather than a Megabyte) which hurts throughput. With this patch, there are fewer writes which are each larger on average. Where the NR_UNSTABLE_NFS count was included in statistics virtual-files, the entry is retained, but the value is hard-coded as zero. static trace points and warning printks which mentioned this counter no longer report it. [akpm@linux-foundation.org: re-layout comment] [akpm@linux-foundation.org: fix printk warning] Signed-off-by: NeilBrown Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Acked-by: Trond Myklebust Acked-by: Michal Hocko [mm] Cc: Christoph Hellwig Cc: Chuck Lever Link: http://lkml.kernel.org/r/87d06j7gqa.fsf@notabene.neil.brown.name Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b9de7d220fb..a89f47515eb1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -193,7 +193,6 @@ enum node_stat_item { NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, - NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ -- cgit v1.2.3 From 91429023342789a89f4b6ae95b47a7df71ab6d95 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Mon, 1 Jun 2020 21:48:27 -0700 Subject: mm/gup: introduce pin_user_pages_unlocked Introduce pin_user_pages_unlocked(), which is nearly identical to the get_user_pages_unlocked() that it wraps, except that it sets FOLL_PIN and rejects FOLL_GET. Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Andy Walls Cc: Mauro Carvalho Chehab Link: http://lkml.kernel.org/r/20200518012157.1178336-2-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 92704fde6475..ebbb0acbeee2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1713,6 +1713,8 @@ 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, struct page **pages, unsigned int gup_flags); +long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, + struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); -- cgit v1.2.3 From 4b4bb6bb451c8b0c1cbc38fa20a89a3988aa4e0b Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 1 Jun 2020 21:49:13 -0700 Subject: mm/swapfile.c: classify SWAP_MAP_XXX to make it more readable swap_info_struct->swap_map[] encodes some flag and count. And to do some condition check, it also introduces some special values. Currently those macros are defined with some magic order, which makes audience hard to understand the exact meaning. This patch split those macros into three categories: flag special value for first swap_map special value for continued swap_map May this help audiences a little. [akpm@linux-foundation.org: tweak capitalization in comments] Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200501015259.32237-1-richard.weiyang@gmail.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e1bbf7a16b27..873bf5206afb 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -183,12 +183,17 @@ enum { #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX -#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */ -#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */ +/* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ -#define SWAP_CONT_MAX 0x7f /* Max count, in each swap_map continuation */ -#define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */ -#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */ +#define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ + +/* Special value in first swap_map */ +#define SWAP_MAP_MAX 0x3e /* Max count */ +#define SWAP_MAP_BAD 0x3f /* Note page is bad */ +#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ + +/* Special value in each swap_map continuation */ +#define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk -- cgit v1.2.3 From 490705888107c3edf8c264ec930909107f76a984 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 1 Jun 2020 21:49:22 -0700 Subject: swap: reduce lock contention on swap cache from swap slots allocation In some swap scalability test, it is found that there are heavy lock contention on swap cache even if we have split one swap cache radix tree per swap device to one swap cache radix tree every 64 MB trunk in commit 4b3ef9daa4fc ("mm/swap: split swap cache into 64MB trunks"). The reason is as follow. After the swap device becomes fragmented so that there's no free swap cluster, the swap device will be scanned linearly to find the free swap slots. swap_info_struct->cluster_next is the next scanning base that is shared by all CPUs. So nearby free swap slots will be allocated for different CPUs. The probability for multiple CPUs to operate on the same 64 MB trunk is high. This causes the lock contention on the swap cache. To solve the issue, in this patch, for SSD swap device, a percpu version next scanning base (cluster_next_cpu) is added. Every CPU will use its own per-cpu next scanning base. And after finishing scanning a 64MB trunk, the per-cpu scanning base will be changed to the beginning of another randomly selected 64MB trunk. In this way, the probability for multiple CPUs to operate on the same 64 MB trunk is reduced greatly. Thus the lock contention is reduced too. For HDD, because sequential access is more important for IO performance, the original shared next scanning base is used. To test the patch, we have run 16-process pmbench memory benchmark on a 2-socket server machine with 48 cores. One ram disk is configured as the swap device per socket. The pmbench working-set size is much larger than the available memory so that swapping is triggered. The memory read/write ratio is 80/20 and the accessing pattern is random. In the original implementation, the lock contention on the swap cache is heavy. The perf profiling data of the lock contention code path is as following, _raw_spin_lock_irq.add_to_swap_cache.add_to_swap.shrink_page_list: 7.91 _raw_spin_lock_irqsave.__remove_mapping.shrink_page_list: 7.11 _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 2.51 _raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 1.66 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 1.29 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.03 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 0.93 After applying this patch, it becomes, _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 3.58 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 2.3 _raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 2.26 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 1.8 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.19 The lock contention on the swap cache is almost eliminated. And the pmbench score increases 18.5%. The swapin throughput increases 18.7% from 2.96 GB/s to 3.51 GB/s. While the swapout throughput increases 18.5% from 2.99 GB/s to 3.54 GB/s. We need really fast disk to show the benefit. I have tried this on 2 Intel P3600 NVMe disks. The performance improvement is only about 1%. The improvement should be better on the faster disks, such as Intel Optane disk. [ying.huang@intel.com: fix cluster_next_cpu allocation and freeing, per Daniel] Link: http://lkml.kernel.org/r/20200525002648.336325-1-ying.huang@intel.com [ying.huang@intel.com: v4] Link: http://lkml.kernel.org/r/20200529010840.928819-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Cc: Michal Hocko Cc: Minchan Kim Cc: Tim Chen Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200520031502.175659-1-ying.huang@intel.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 873bf5206afb..6c23a6a14012 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -252,6 +252,7 @@ struct swap_info_struct { unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ + unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ -- cgit v1.2.3 From 251af0cda614e5ad6bfda059bd120aed7432891d Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 1 Jun 2020 21:49:29 -0700 Subject: include/linux/swap.h: delete meaningless __add_to_swap_cache() declaration Since commit 8d93b41c09d1 ("mm: Convert add_to_swap_cache to XArray"), __add_to_swap_cache and add_to_swap_cache are combined into one function. There is no __add_to_swap_cache() anymore. Signed-off-by: Miaohe Lin Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Reviewed-by: "Huang, Ying" Link: http://lkml.kernel.org/r/1590810326-2493-1-git-send-email-linmiaohe@huawei.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6c23a6a14012..68ef7638311f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -414,7 +414,6 @@ extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); -extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); extern void __delete_from_swap_cache(struct page *, swp_entry_t entry); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); -- cgit v1.2.3 From d1663a907bd348f912b7f7088e83ca1b6fd3309f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 1 Jun 2020 21:49:49 -0700 Subject: mm/memcg: move cgroup high memory limit setting into struct page_counter High memory limit is currently recorded directly in struct mem_cgroup. We are about to add a high limit for swap, move the field to struct page_counter and add some helpers. Signed-off-by: Jakub Kicinski Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Chris Down Cc: Hugh Dickins Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200527195846.102707-4-kuba@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 --- include/linux/page_counter.h | 8 ++++++++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 977edd3b7bd8..95a09a7ec412 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -215,9 +215,6 @@ struct mem_cgroup { struct page_counter kmem; struct page_counter tcpmem; - /* Upper bound of normal memory consumption range */ - unsigned long high; - /* Range enforcement for interrupt charges */ struct work_struct high_work; diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index bab7e57f659b..85bd413e784e 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -10,6 +10,7 @@ struct page_counter { atomic_long_t usage; unsigned long min; unsigned long low; + unsigned long high; unsigned long max; struct page_counter *parent; @@ -55,6 +56,13 @@ bool page_counter_try_charge(struct page_counter *counter, void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages); + +static inline void page_counter_set_high(struct page_counter *counter, + unsigned long nr_pages) +{ + WRITE_ONCE(counter->high, nr_pages); +} + int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); -- cgit v1.2.3 From 4b82ab4f28836646eca12cb37f408568d3cdc5c3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 1 Jun 2020 21:49:52 -0700 Subject: mm/memcg: automatically penalize tasks with high swap use Add a memory.swap.high knob, which can be used to protect the system from SWAP exhaustion. The mechanism used for penalizing is similar to memory.high penalty (sleep on return to user space). That is not to say that the knob itself is equivalent to memory.high. The objective is more to protect the system from potentially buggy tasks consuming a lot of swap and impacting other tasks, or even bringing the whole system to stand still with complete SWAP exhaustion. Hopefully without the need to find per-task hard limits. Slowing misbehaving tasks down gradually allows user space oom killers or other protection mechanisms to react. oomd and earlyoom already do killing based on swap exhaustion, and memory.swap.high protection will help implement such userspace oom policies more reliably. We can use one counter for number of pages allocated under pressure to save struct task space and avoid two separate hierarchy walks on the hot path. The exact overage is calculated on return to user space, anyway. Take the new high limit into account when determining if swap is "full". Borrowing the explanation from Johannes: The idea behind "swap full" is that as long as the workload has plenty of swap space available and it's not changing its memory contents, it makes sense to generously hold on to copies of data in the swap device, even after the swapin. A later reclaim cycle can drop the page without any IO. Trading disk space for IO. But the only two ways to reclaim a swap slot is when they're faulted in and the references go away, or by scanning the virtual address space like swapoff does - which is very expensive (one could argue it's too expensive even for swapoff, it's often more practical to just reboot). So at some point in the fill level, we have to start freeing up swap slots on fault/swapin. Otherwise we could eventually run out of swap slots while they're filled with copies of data that is also in RAM. We don't want to OOM a workload because its available swap space is filled with redundant cache. Signed-off-by: Jakub Kicinski Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Cc: Tejun Heo Cc: Chris Down Cc: Shakeel Butt Cc: Michal Hocko Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200527195846.102707-5-kuba@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 95a09a7ec412..bfe9533bb67e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -45,6 +45,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, -- cgit v1.2.3 From 1494e0c38ee903e83aefb58caf54a9217273d49a Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 1 Jun 2020 21:49:58 -0700 Subject: x86: mm: ptdump: calculate effective permissions correctly Patch series "Fix W+X debug feature on x86" Jan alerted me[1] that the W+X detection debug feature was broken in x86 by my change[2] to switch x86 to use the generic ptdump infrastructure. Fundamentally the approach of trying to move the calculation of effective permissions into note_page() was broken because note_page() is only called for 'leaf' entries and the effective permissions are passed down via the internal nodes of the page tree. The solution I've taken here is to create a new (optional) callback which is called for all nodes of the page tree and therefore can calculate the effective permissions. Secondly on some configurations (32 bit with PAE) "unsigned long" is not large enough to store the table entries. The fix here is simple - let's just use a u64. [1] https://lore.kernel.org/lkml/d573dc7e-e742-84de-473d-f971142fa319@suse.com/ [2] 2ae27137b2db ("x86: mm: convert dump_pagetables to use walk_page_range") This patch (of 2): By switching the x86 page table dump code to use the generic code the effective permissions are no longer calculated correctly because the note_page() function is only called for *leaf* entries. To calculate the actual effective permissions it is necessary to observe the full hierarchy of the page tree. Introduce a new callback for ptdump which is called for every entry and can therefore update the prot_levels array correctly. note_page() can then simply access the appropriate element in the array. [steven.price@arm.com: make the assignment conditional on val != 0] Link: http://lkml.kernel.org/r/430c8ab4-e7cd-6933-dde6-087fac6db872@arm.com Fixes: 2ae27137b2db ("x86: mm: convert dump_pagetables to use walk_page_range") Reported-by: Jan Beulich Signed-off-by: Steven Price Signed-off-by: Andrew Morton Cc: Qian Cai Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Link: http://lkml.kernel.org/r/20200521152308.33096-1-steven.price@arm.com Link: http://lkml.kernel.org/r/20200521152308.33096-2-steven.price@arm.com 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 a67065c403c3..ac01502763bf 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -14,6 +14,7 @@ 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); + void (*effective_prot)(struct ptdump_state *st, int level, u64 val); const struct ptdump_range *range; }; -- cgit v1.2.3 From 99395ee3f7b4accc3a16a6aa4c2abb3774fc33ca Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 1 Jun 2020 21:50:01 -0700 Subject: mm: ptdump: expand type of 'val' in note_page() The page table entry is passed in the 'val' argument to note_page(), however this was previously an "unsigned long" which is fine on 64-bit platforms. But for 32 bit x86 it is not always big enough to contain a page table entry which may be 64 bits. Change the type to u64 to ensure that it is always big enough. [akpm@linux-foundation.org: fix riscv] Reported-by: Jan Beulich Signed-off-by: Steven Price Signed-off-by: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Link: http://lkml.kernel.org/r/20200521152308.33096-3-steven.price@arm.com Signed-off-by: Linus Torvalds --- include/linux/ptdump.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h index ac01502763bf..2a3a95586425 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -13,7 +13,7 @@ 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); + int level, u64 val); void (*effective_prot)(struct ptdump_state *st, int level, u64 val); const struct ptdump_range *range; }; -- cgit v1.2.3 From 4926627793c0a7e7db2bc674e1d06777e86d8dab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:50:45 -0700 Subject: mm: remove __get_vm_area Switch the two remaining callers to use __get_vm_area_caller instead. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-9-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a95d3cc74d79..ff69d1e037ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -161,8 +161,6 @@ static inline size_t get_vm_area_size(const struct vm_struct *area) extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller); -extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, - unsigned long start, unsigned long end); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, -- cgit v1.2.3 From 8b136018da7bf49b988a24064fc45c290baffd93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:50:53 -0700 Subject: mm: rename CONFIG_PGTABLE_MAPPING to CONFIG_ZSMALLOC_PGTABLE_MAPPING Rename the Kconfig variable to clarify the scope. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Minchan Kim Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-11-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/zsmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 2219cce81ca4..0fdbf653b173 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -20,7 +20,7 @@ * zsmalloc mapping modes * * NOTE: These only make a difference when a mapped object spans pages. - * They also have no effect when PGTABLE_MAPPING is selected. + * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected. */ enum zs_mapmode { ZS_MM_RW, /* normal read-write mapping */ -- cgit v1.2.3 From ed1f324c5fed06c91f30a36aedb66f34244ab86e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:19 -0700 Subject: mm: remove map_vm_range Switch all callers to map_kernel_range, which symmetric to the unmap side (as well as the _noflush versions). Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-17-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ff69d1e037ca..a1e9bdc3ad9e 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -168,11 +168,11 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size, extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); -extern int map_vm_area(struct vm_struct *area, pgprot_t prot, - struct page **pages); #ifdef CONFIG_MMU extern int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); +int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, + struct page **pages); extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); static inline void set_vm_flush_reset_perms(void *addr) @@ -189,14 +189,12 @@ map_kernel_range_noflush(unsigned long start, unsigned long size, { return size >> PAGE_SHIFT; } +#define map_kernel_range map_kernel_range_noflush static inline void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) { } -static inline void -unmap_kernel_range(unsigned long addr, unsigned long size) -{ -} +#define unmap_kernel_range unmap_kernel_range_noflush static inline void set_vm_flush_reset_perms(void *addr) { } -- cgit v1.2.3 From d4efd79a81abc7096a418ee3103f261cfb6ab634 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:27 -0700 Subject: mm: remove the prot argument from vm_map_ram This is always PAGE_KERNEL - for long term mappings with other properties vmap should be used. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-19-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a1e9bdc3ad9e..5488cea5ef11 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -88,8 +88,7 @@ struct vmap_area { * Highlevel APIs for driver use */ extern void vm_unmap_ram(const void *mem, unsigned int count); -extern void *vm_map_ram(struct page **pages, unsigned int count, - int node, pgprot_t prot); +extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU -- cgit v1.2.3 From 88dca4ca5a93d2c09e5bbc6a62fbfc3af83c4fca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:40 -0700 Subject: mm: remove the pgprot argument to __vmalloc The pgprot argument to __vmalloc is always PAGE_KERNEL now, so remove it. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Michael Kelley [hyperv] Acked-by: Gao Xiang [erofs] Acked-by: Peter Zijlstra (Intel) Acked-by: Wei Liu Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-22-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 5488cea5ef11..1c278e030599 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -110,7 +110,7 @@ extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); +extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, -- cgit v1.2.3 From 4d39d7285f45cc6c72b850f040d3addd626658e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:49 -0700 Subject: mm: remove both instances of __vmalloc_node_flags The real version just had a few callers that can open code it and remove one layer of indirection. The nommu stub was public but only had a single caller, so remove it and avoid a CONFIG_MMU ifdef in vmalloc.h. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-24-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 1c278e030599..91d143783458 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -115,17 +115,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); -#ifndef CONFIG_MMU -extern void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags); -static inline void *__vmalloc_node_flags_caller(unsigned long size, int node, - gfp_t flags, void *caller) -{ - return __vmalloc_node_flags(size, node, flags); -} -#else extern void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags, void *caller); -#endif extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From 2b9059489c839e67ca9254913325e18cea11a980 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:53 -0700 Subject: mm: remove __vmalloc_node_flags_caller Just use __vmalloc_node instead which gets and extra argument. To be able to to use __vmalloc_node in all caller make it available outside of vmalloc and implement it in nommu.c. [akpm@linux-foundation.org: fix nommu build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-25-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 91d143783458..964d58a060ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -115,8 +115,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); -extern void *__vmalloc_node_flags_caller(unsigned long size, - int node, gfp_t flags, void *caller); +void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, + int node, const void *caller); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From 041de93ff86fc500aa73e5360039c95f4d31b95f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:52:02 -0700 Subject: mm: remove vmalloc_user_node_flags Open code it in __bpf_map_area_alloc, which is the only caller. Also clean up __bpf_map_area_alloc to have a single vmalloc call with slightly different flags instead of the current two different calls. For this to compile for the nommu case add a __vmalloc_node_range stub to nommu.c. [akpm@linux-foundation.org: fix nommu.c build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-27-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 964d58a060ca..3332926295d4 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); -- cgit v1.2.3 From d8626138009ba58ae2c22356966c2edaa1f1c3b5 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:18 -0700 Subject: mm: add functions to track page directory modifications Patch series "mm: Get rid of vmalloc_sync_(un)mappings()", v3. After the recent issue with vmalloc and tracing code[1] on x86 and a long history of previous issues related to the vmalloc_sync_mappings() interface, I thought the time has come to remove it. Please see [2], [3], and [4] for some other issues in the past. The patches add tracking of page-table directory changes to the vmalloc and ioremap code. Depending on which page-table levels changes have been made, a new per-arch function is called: arch_sync_kernel_mappings(). On x86-64 with 4-level paging, this function will not be called more than 64 times in a systems runtime (because vmalloc-space takes 64 PGD entries which are only populated, but never cleared). As a side effect this also allows to get rid of vmalloc faults on x86, making it safe to touch vmalloc'ed memory in the page-fault handler. Note that this potentially includes per-cpu memory. This patch (of 7): Add page-table allocation functions which will keep track of changed directory entries. They are needed for new PGD, P4D, PUD, and PMD entries and will be used in vmalloc and ioremap code to decide whether any changes in the kernel mappings need to be synchronized between page-tables in the system. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: "H . Peter Anvin" Cc: Dave Hansen Cc: "Rafael J. Wysocki" Cc: Arnd Bergmann Cc: Steven Rostedt (VMware) Cc: Vlastimil Babka Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20200515140023.25469-1-joro@8bytes.org Link: http://lkml.kernel.org/r/20200515140023.25469-2-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ebbb0acbeee2..fda41eb7f1c8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2091,13 +2091,54 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } + +static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, + unsigned long address, + pgtbl_mod_mask *mod_mask) + +{ + if (unlikely(pgd_none(*pgd))) { + if (__p4d_alloc(mm, pgd, address)) + return NULL; + *mod_mask |= PGTBL_PGD_MODIFIED; + } + + return p4d_offset(pgd, address); +} + #endif /* !__ARCH_HAS_5LEVEL_HACK */ +static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(p4d_none(*p4d))) { + if (__pud_alloc(mm, p4d, address)) + return NULL; + *mod_mask |= PGTBL_P4D_MODIFIED; + } + + return pud_offset(p4d, address); +} + static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } + +static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(pud_none(*pud))) { + if (__pmd_alloc(mm, pud, address)) + return NULL; + *mod_mask |= PGTBL_PUD_MODIFIED; + } + + return pmd_offset(pud, address); +} #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS @@ -2213,6 +2254,11 @@ static inline void pgtable_pte_page_dtor(struct page *page) ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) +#define pte_alloc_kernel_track(pmd, address, mask) \ + ((unlikely(pmd_none(*(pmd))) && \ + (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ + NULL: pte_offset_kernel(pmd, address)) + #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) -- cgit v1.2.3 From 2ba3e6947aed9bb9575eb1603c0ac6e39185d32a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:22 -0700 Subject: mm/vmalloc: track which page-table levels were modified Track at which levels in the page-table entries were modified by vmap/vunmap. After the page-table has been modified, use that information do decide whether the new arch_sync_kernel_mappings() needs to be called. [akpm@linux-foundation.org: map_kernel_range_noflush() needs the arch_sync_kernel_mappings() call] Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-3-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3332926295d4..0efc35dc5b25 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -133,6 +133,22 @@ extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, void vmalloc_sync_mappings(void); void vmalloc_sync_unmappings(void); +/* + * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values + * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() + * needs to be called. + */ +#ifndef ARCH_PAGE_TABLE_SYNC_MASK +#define ARCH_PAGE_TABLE_SYNC_MASK 0 +#endif + +/* + * There is no default implementation for arch_sync_kernel_mappings(). It is + * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK + * is 0. + */ +void arch_sync_kernel_mappings(unsigned long start, unsigned long end); + /* * Lowlevel-APIs (not for driver use!) */ -- cgit v1.2.3 From 73f693c3a705756032c2863bfb37570276902d7d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:36 -0700 Subject: mm: remove vmalloc_sync_(un)mappings() These functions are not needed anymore because the vmalloc and ioremap mappings are now synchronized when they are created or torn down. Remove all callers and function definitions. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Tested-by: Steven Rostedt (VMware) Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-7-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0efc35dc5b25..48bb681e6c2a 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -130,8 +130,6 @@ 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_mappings(void); -void vmalloc_sync_unmappings(void); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values -- cgit v1.2.3 From 836e66c218f355ec01ba57671c85abf32961dcea Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 2 Jun 2020 16:58:32 +0200 Subject: bpf: Fix up bpf_skb_adjust_room helper's skb csum setting Lorenz recently reported: In our TC classifier cls_redirect [0], we use the following sequence of helper calls to decapsulate a GUE (basically IP + UDP + custom header) encapsulated packet: bpf_skb_adjust_room(skb, -encap_len, BPF_ADJ_ROOM_MAC, BPF_F_ADJ_ROOM_FIXED_GSO) bpf_redirect(skb->ifindex, BPF_F_INGRESS) It seems like some checksums of the inner headers are not validated in this case. For example, a TCP SYN packet with invalid TCP checksum is still accepted by the network stack and elicits a SYN ACK. [...] That is, we receive the following packet from the driver: | ETH | IP | UDP | GUE | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY ip_summed is CHECKSUM_UNNECESSARY because our NICs do rx checksum offloading. On this packet we run skb_adjust_room_mac(-encap_len), and get the following: | ETH | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY Note that ip_summed is still CHECKSUM_UNNECESSARY. After bpf_redirect()'ing into the ingress, we end up in tcp_v4_rcv(). There, skb_checksum_init() is turned into a no-op due to CHECKSUM_UNNECESSARY. The bpf_skb_adjust_room() helper is not aware of protocol specifics. Internally, it handles the CHECKSUM_COMPLETE case via skb_postpull_rcsum(), but that does not cover CHECKSUM_UNNECESSARY. In this case skb->csum_level of the original skb prior to bpf_skb_adjust_room() call was 0, that is, covering UDP. Right now there is no way to adjust the skb->csum_level. NICs that have checksum offload disabled (CHECKSUM_NONE) or that support CHECKSUM_COMPLETE are not affected. Use a safe default for CHECKSUM_UNNECESSARY by resetting to CHECKSUM_NONE and add a flag to the helper called BPF_F_ADJ_ROOM_NO_CSUM_RESET that allows users from opting out. Opting out is useful for the case where we don't remove/add full protocol headers, or for the case where a user wants to adjust the csum level manually e.g. through bpf_csum_level() helper that is added in subsequent patch. The bpf_skb_proto_{4_to_6,6_to_4}() for NAT64/46 translation from the BPF bpf_skb_change_proto() helper uses bpf_skb_net_hdr_{push,pop}() pair internally as well but doesn't change layers, only transitions between v4 to v6 and vice versa, therefore no adoption is required there. [0] https://lore.kernel.org/bpf/20200424185556.7358-1-lmb@cloudflare.com/ Fixes: 2be7e212d541 ("bpf: add bpf_skb_adjust_room helper") Reported-by: Lorenz Bauer Reported-by: Alan Maguire Signed-off-by: Daniel Borkmann Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Reviewed-by: Alan Maguire Link: https://lore.kernel.org/bpf/CACAyw9-uU_52esMd1JjuA80fRPHJv5vsSg8GnfW3t_qDU4aVKQ@mail.gmail.com/ Link: https://lore.kernel.org/bpf/11a90472e7cce83e76ddbfce81fdfce7bfc68808.1591108731.git.daniel@iogearbox.net --- include/linux/skbuff.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a0d5c2760103..0c0377fc00c2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3919,6 +3919,14 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) } } +static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) +{ + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + skb->ip_summed = CHECKSUM_NONE; + skb->csum_level = 0; + } +} + /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise -- cgit v1.2.3 From 1f55b7ab907d373581e9abf3fc4b24ed19cf831f Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 May 2020 16:45:50 -0300 Subject: RDMA/mlx4: Remove FMR support for memory registration HCA's that are driven by mlx4 driver support FRWR method to register memory. Remove the ancient and unsafe FMR method. Link: https://lore.kernel.org/r/8-v3-f58e6669d5d3+2cf-fmr_removal_jgg@mellanox.com Reviewed-by: Max Gurtovoy Signed-off-by: Max Gurtovoy Signed-off-by: Jason Gunthorpe --- include/linux/mlx4/device.h | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 20372de0b587..06e066e04a4b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -573,7 +573,6 @@ struct mlx4_caps { int reserved_eqs; int num_comp_vectors; int num_mpts; - int max_fmr_maps; int num_mtts; int fmr_reserved_mtts; int reserved_mtts; @@ -707,17 +706,6 @@ struct mlx4_mw { int enabled; }; -struct mlx4_fmr { - struct mlx4_mr mr; - struct mlx4_mpt_entry *mpt; - __be64 *mtts; - dma_addr_t dma_handle; - int max_pages; - int max_maps; - int maps; - u8 page_shift; -}; - struct mlx4_uar { unsigned long pfn; int index; @@ -1412,14 +1400,6 @@ int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan); -int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list, - int npages, u64 iova, u32 *lkey, u32 *rkey); -int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages, - int max_maps, u8 page_shift, struct mlx4_fmr *fmr); -int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr); -void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, - u32 *lkey, u32 *rkey); -int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupt(struct mlx4_dev *dev, int vector); int mlx4_test_async(struct mlx4_dev *dev); @@ -1522,6 +1502,8 @@ int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port, int enable); + +struct mlx4_mpt_entry; int mlx4_mr_hw_get_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr, struct mlx4_mpt_entry ***mpt_entry); int mlx4_mr_hw_write_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr, -- cgit v1.2.3 From 649392bf75a423287a9c4936b341677f12e8cf0b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 28 May 2020 16:45:54 -0300 Subject: RDMA: Remove 'max_fmr' Now that FMR support is gone, this attribute can be deleted from all places. Link: https://lore.kernel.org/r/12-v3-f58e6669d5d3+2cf-fmr_removal_jgg@mellanox.com Reviewed-by: Max Gurtovoy Reviewed-by: Bernard Metzler Signed-off-by: Jason Gunthorpe --- include/linux/qed/qed_rdma_if.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 74efca15fde7..c90276cda5c1 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -91,7 +91,6 @@ struct qed_rdma_device { u64 max_mr_size; u32 max_cqe; u32 max_mw; - u32 max_fmr; u32 max_mr_mw_fmr_pbl; u64 max_mr_mw_fmr_size; u32 max_pd; -- cgit v1.2.3 From 6a45b0e2589fafd7fc501a5fbd0ab56689a08124 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Thu, 28 May 2020 16:58:43 +0200 Subject: gpiolib: Introduce gpiochip_irqchip_add_domain() The function connects an IRQ domain to a gpiochip and reuses gpiochip_to_irq() which is provided by gpiolib. gpiochip_irqchip_* and regmap_irq partially provide the same functionality. This function will help to connect just the minimal functionality of the gpiochip_irqchip which is needed to work together with regmap-irq. Signed-off-by: Michael Walle Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200528145845.31436-2-michael@walle.cc Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c8bcaf315d03..c4f272af7af5 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -612,6 +612,9 @@ int gpiochip_irqchip_add_key(struct gpio_chip *gc, bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc, unsigned int offset); +int gpiochip_irqchip_add_domain(struct gpio_chip *gc, + struct irq_domain *domain); + #ifdef CONFIG_LOCKDEP /* -- cgit v1.2.3 From ebe363197e525ffbd279c729421f6f6c24d8d681 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Thu, 28 May 2020 16:58:44 +0200 Subject: gpio: add a reusable generic gpio_chip using regmap There are quite a lot simple GPIO controller which are using regmap to access the hardware. This driver tries to be a base to unify existing code into one place. This won't cover everything but it should be a good starting point. It does not implement its own irq_chip because there is already a generic one for regmap based devices. Instead, the irq_chip will be instantiated in the parent driver and its irq domain will be associate to this driver. For now it consists of the usual registers, like set (and an optional clear) data register, an input register and direction registers. Out-of-the-box, it supports consecutive register mappings and mappings where the registers have gaps between them with a linear mapping between GPIO offset and bit position. For weirder mappings the user can register its own .xlate(). Signed-off-by: Michael Walle Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200528145845.31436-3-michael@walle.cc Signed-off-by: Linus Walleij --- include/linux/gpio/regmap.h | 86 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) create mode 100644 include/linux/gpio/regmap.h (limited to 'include/linux') diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h new file mode 100644 index 000000000000..4c1e6b34e824 --- /dev/null +++ b/include/linux/gpio/regmap.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _LINUX_GPIO_REGMAP_H +#define _LINUX_GPIO_REGMAP_H + +struct device; +struct gpio_regmap; +struct irq_domain; +struct regmap; + +#define GPIO_REGMAP_ADDR_ZERO ((unsigned long)(-1)) +#define GPIO_REGMAP_ADDR(addr) ((addr) ? : GPIO_REGMAP_ADDR_ZERO) + +/** + * struct gpio_regmap_config - Description of a generic regmap gpio_chip. + * @parent: The parent device + * @regmap: The regmap used to access the registers + * given, the name of the device is used + * @label: (Optional) Descriptive name for GPIO controller. + * If not given, the name of the device is used. + * @ngpio: Number of GPIOs + * @names: (Optional) Array of names for gpios + * @reg_dat_base: (Optional) (in) register base address + * @reg_set_base: (Optional) set register base address + * @reg_clr_base: (Optional) clear register base address + * @reg_dir_in_base: (Optional) in setting register base address + * @reg_dir_out_base: (Optional) out setting register base address + * @reg_stride: (Optional) May be set if the registers (of the + * same type, dat, set, etc) are not consecutive. + * @ngpio_per_reg: Number of GPIOs per register + * @irq_domain: (Optional) IRQ domain if the controller is + * interrupt-capable + * @reg_mask_xlate: (Optional) Translates base address and GPIO + * offset to a register/bitmask pair. If not + * given the default gpio_regmap_simple_xlate() + * is used. + * + * The ->reg_mask_xlate translates a given base address and GPIO offset to + * register and mask pair. The base address is one of the given register + * base addresses in this structure. + * + * Although all register base addresses are marked as optional, there are + * several rules: + * 1. if you only have @reg_dat_base set, then it is input-only + * 2. if you only have @reg_set_base set, then it is output-only + * 3. if you have either @reg_dir_in_base or @reg_dir_out_base set, then + * you have to set both @reg_dat_base and @reg_set_base + * 4. if you have @reg_set_base set, you may also set @reg_clr_base to have + * two different registers for setting and clearing the output. This is + * also valid for the output-only case. + * 5. @reg_dir_in_base and @reg_dir_out_base are exclusive; is there really + * hardware which has redundant registers? + * + * Note: All base addresses may have the special value %GPIO_REGMAP_ADDR_ZERO + * which forces the address to the value 0. + */ +struct gpio_regmap_config { + struct device *parent; + struct regmap *regmap; + + const char *label; + int ngpio; + const char *const *names; + + unsigned int reg_dat_base; + unsigned int reg_set_base; + unsigned int reg_clr_base; + unsigned int reg_dir_in_base; + unsigned int reg_dir_out_base; + int reg_stride; + int ngpio_per_reg; + struct irq_domain *irq_domain; + + int (*reg_mask_xlate)(struct gpio_regmap *gpio, unsigned int base, + unsigned int offset, unsigned int *reg, + unsigned int *mask); +}; + +struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config); +void gpio_regmap_unregister(struct gpio_regmap *gpio); +struct gpio_regmap *devm_gpio_regmap_register(struct device *dev, + const struct gpio_regmap_config *config); +void gpio_regmap_set_drvdata(struct gpio_regmap *gpio, void *data); +void *gpio_regmap_get_drvdata(struct gpio_regmap *gpio); + +#endif /* _LINUX_GPIO_REGMAP_H */ -- cgit v1.2.3 From a645a89d9a780a8fbb6e283f84fc91ad538c2edc Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 2 Jun 2020 15:55:48 +0300 Subject: RDMA/mlx5: Return ECE DC support The DC QPs are many-to-one QP types that means that first connection will establish ECE options that coming connections should follow. Due to this property, the ECE code was removed between first [1] and second [2] ECE submissions. This patch returns the dropped code, because ECE is a property of a connection and like any other connection users are needed to manage this data. Allow them to set ECE parameter for DC too and avoid need of having compatibility flag for the DC ECE. [1] https://lore.kernel.org/linux-rdma/20200523132243.817936-1-leon@kernel.org/ [2] https://lore.kernel.org/linux-rdma/20200525174401.71152-1-leon@kernel.org/ Link: https://lore.kernel.org/r/20200602125548.172654-4-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4d2e36dd2c6b..116bd9bb347f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3690,7 +3690,8 @@ struct mlx5_ifc_dctc_bits { u8 ecn[0x2]; u8 dscp[0x6]; - u8 reserved_at_1c0[0x40]; + u8 reserved_at_1c0[0x20]; + u8 ece[0x20]; }; enum { @@ -7940,7 +7941,7 @@ struct mlx5_ifc_create_dct_out_bits { u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_at_60[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_create_dct_in_bits { -- cgit v1.2.3 From 5ea75ae6ae60d13dfa35fd5d2e2a81824cba6662 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 18 Feb 2020 17:30:05 -0500 Subject: user_regset_copyout_zero(): use clear_user() that's the only caller of __clear_user() in generic code, and it's not hot enough to bother with skipping access_ok(). Signed-off-by: Al Viro --- include/linux/regset.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index bf0243779738..46d6ae68c455 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -320,7 +320,7 @@ static inline int user_regset_copyout_zero(unsigned int *pos, if (*kbuf) { memset(*kbuf, 0, copy); *kbuf += copy; - } else if (__clear_user(*ubuf, copy)) + } else if (clear_user(*ubuf, copy)) return -EFAULT; else *ubuf += copy; -- cgit v1.2.3 From 376a34efa4eeb699d285c1a741b186d44b44c429 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 3 Jun 2020 15:56:30 -0700 Subject: mm/gup: refactor and de-duplicate gup_fast() code There were two nearly identical sets of code for gup_fast() style of walking the page tables with interrupts disabled. This has lead to the usual maintenance problems that arise from having duplicated code. There is already a core internal routine in gup.c for gup_fast(), so just enhance it very slightly: allow skipping the fall-back to "slow" (regular) get_user_pages(), via the new FOLL_FAST_ONLY flag. Then, just call internal_get_user_pages_fast() from __get_user_pages_fast(), and adjust the API to match pre-existing API behavior. There is a change in behavior from this refactoring: the nested form of interrupt disabling is used in all gup_fast() variants now. That's because there is only one place that interrupt disabling for page walking is done, and so the safer form is required. This should, if anything, eliminate possible (rare) bugs, because the non-nested form of enabling interrupts was fragile at best. [jhubbard@nvidia.com: fixup] Link: http://lkml.kernel.org/r/20200521233841.1279742-1-jhubbard@nvidia.com Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Jani Nikula Cc: "Joonas Lahtinen" Cc: Matthew Auld Cc: Matthew Wilcox Cc: Rodrigo Vivi Cc: Souptick Joarder Cc: Tvrtko Ursulin Link: http://lkml.kernel.org/r/20200519002124.2025955-3-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- 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 7e07f4f490cb..e6b884715da1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2816,6 +2816,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #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 unpin_user_page */ +#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each -- cgit v1.2.3 From 104acc327648b347d1716374586803e82fa1dc95 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 3 Jun 2020 15:56:34 -0700 Subject: mm/gup: introduce pin_user_pages_fast_only() This is the FOLL_PIN equivalent of __get_user_pages_fast(), except with a more descriptive name, and gup_flags instead of a boolean "write" in the argument list. Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Jani Nikula Cc: "Joonas Lahtinen" Cc: Matthew Auld Cc: Matthew Wilcox Cc: Rodrigo Vivi Cc: Souptick Joarder Cc: Tvrtko Ursulin Link: http://lkml.kernel.org/r/20200519002124.2025955-4-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e6b884715da1..6c236c5b0015 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1827,6 +1827,8 @@ extern int mprotect_fixup(struct vm_area_struct *vma, */ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +int pin_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); /* * per-process(per-mm_struct) statistics. */ -- cgit v1.2.3 From 47227d27e2fcb01a9e8f5958d8997cf47a820afc Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Wed, 3 Jun 2020 15:56:46 -0700 Subject: string.h: fix incompatibility between FORTIFY_SOURCE and KASAN The memcmp KASAN self-test fails on a kernel with both KASAN and FORTIFY_SOURCE. When FORTIFY_SOURCE is on, a number of functions are replaced with fortified versions, which attempt to check the sizes of the operands. However, these functions often directly invoke __builtin_foo() once they have performed the fortify check. Using __builtins may bypass KASAN checks if the compiler decides to inline it's own implementation as sequence of instructions, rather than emit a function call that goes out to a KASAN-instrumented implementation. Why is only memcmp affected? ============================ Of the string and string-like functions that kasan_test tests, only memcmp is replaced by an inline sequence of instructions in my testing on x86 with gcc version 9.2.1 20191008 (Ubuntu 9.2.1-9ubuntu2). I believe this is due to compiler heuristics. For example, if I annotate kmalloc calls with the alloc_size annotation (and disable some fortify compile-time checking!), the compiler will replace every memset except the one in kmalloc_uaf_memset with inline instructions. (I have some WIP patches to add this annotation.) Does this affect other functions in string.h? ============================================= Yes. Anything that uses __builtin_* rather than __real_* could be affected. This looks like: - strncpy - strcat - strlen - strlcpy maybe, under some circumstances? - strncat under some circumstances - memset - memcpy - memmove - memcmp (as noted) - memchr - strcpy Whether a function call is emitted always depends on the compiler. Most bugs should get caught by FORTIFY_SOURCE, but the missed memcmp test shows that this is not always the case. Isn't FORTIFY_SOURCE disabled with KASAN? ========================================- The string headers on all arches supporting KASAN disable fortify with kasan, but only when address sanitisation is _also_ disabled. For example from x86: #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) /* * For files that are not instrumented (e.g. mm/slub.c) we * should use not instrumented version of mem* functions. */ #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) #ifndef __NO_FORTIFY #define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ #endif #endif This comes from commit 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions"), and doesn't work when KASAN is enabled and the file is supposed to be sanitised - as with test_kasan.c I'm pretty sure this is not wrong, but not as expansive it should be: * we shouldn't use __builtin_memcpy etc in files where we don't have instrumentation - it could devolve into a function call to memcpy, which will be instrumented. Rather, we should use __memcpy which by convention is not instrumented. * we also shouldn't be using __builtin_memcpy when we have a KASAN instrumented file, because it could be replaced with inline asm that will not be instrumented. What is correct behaviour? ========================== Firstly, there is some overlap between fortification and KASAN: both provide some level of _runtime_ checking. Only fortify provides compile-time checking. KASAN and fortify can pick up different things at runtime: - Some fortify functions, notably the string functions, could easily be modified to consider sub-object sizes (e.g. members within a struct), and I have some WIP patches to do this. KASAN cannot detect these because it cannot insert poision between members of a struct. - KASAN can detect many over-reads/over-writes when the sizes of both operands are unknown, which fortify cannot. So there are a couple of options: 1) Flip the test: disable fortify in santised files and enable it in unsanitised files. This at least stops us missing KASAN checking, but we lose the fortify checking. 2) Make the fortify code always call out to real versions. Do this only for KASAN, for fear of losing the inlining opportunities we get from __builtin_*. (We can't use kasan_check_{read,write}: because the fortify functions are _extern inline_, you can't include _static_ inline functions without a compiler warning. kasan_check_{read,write} are static inline so we can't use them even when they would otherwise be suitable.) Take approach 2 and call out to real versions when KASAN is enabled. Use __underlying_foo to distinguish from __real_foo: __real_foo always refers to the kernel's implementation of foo, __underlying_foo could be either the kernel implementation or the __builtin_foo implementation. This is sometimes enough to make the memcmp test succeed with FORTIFY_SOURCE enabled. It is at least enough to get the function call into the module. One more fix is needed to make it reliable: see the next patch. Fixes: 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions") Signed-off-by: Daniel Axtens Signed-off-by: Andrew Morton Tested-by: David Gow Reviewed-by: Dmitry Vyukov Cc: Daniel Micay Cc: Andrey Ryabinin Cc: Alexander Potapenko Link: http://lkml.kernel.org/r/20200423154503.5103-3-dja@axtens.net Signed-off-by: Linus Torvalds --- include/linux/string.h | 60 ++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 48 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 6dfbb2efa815..9b7a0632e87a 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -272,6 +272,31 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) + +#ifdef CONFIG_KASAN +extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); +extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); +extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); +extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); +extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); +extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); +#else +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp +#define __underlying_memcpy __builtin_memcpy +#define __underlying_memmove __builtin_memmove +#define __underlying_memset __builtin_memset +#define __underlying_strcat __builtin_strcat +#define __underlying_strcpy __builtin_strcpy +#define __underlying_strlen __builtin_strlen +#define __underlying_strncat __builtin_strncat +#define __underlying_strncpy __builtin_strncpy +#endif + __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -279,14 +304,14 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_strncpy(p, q, size); + return __underlying_strncpy(p, q, size); } __FORTIFY_INLINE char *strcat(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); if (p_size == (size_t)-1) - return __builtin_strcat(p, q); + return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); return p; @@ -300,7 +325,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) /* Work around gcc excess stack consumption issue */ if (p_size == (size_t)-1 || (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) - return __builtin_strlen(p); + return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(__func__); @@ -333,7 +358,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) __write_overflow(); if (len >= p_size) fortify_panic(__func__); - __builtin_memcpy(p, q, len); + __underlying_memcpy(p, q, len); p[len] = '\0'; } return ret; @@ -346,12 +371,12 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strncat(p, q, count); + return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); if (p_size < p_len + copy_len + 1) fortify_panic(__func__); - __builtin_memcpy(p + p_len, q, copy_len); + __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } @@ -363,7 +388,7 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memset(p, c, size); + return __underlying_memset(p, c, size); } __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) @@ -378,7 +403,7 @@ __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcpy(p, q, size); + return __underlying_memcpy(p, q, size); } __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) @@ -393,7 +418,7 @@ __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memmove(p, q, size); + return __underlying_memmove(p, q, size); } extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); @@ -419,7 +444,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcmp(p, q, size); + return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) @@ -429,7 +454,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) __read_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memchr(p, c, size); + return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); @@ -460,11 +485,22 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strcpy(p, q); + return __underlying_strcpy(p, q); memcpy(p, q, strlen(q) + 1); return p; } +/* Don't use these outside the FORITFY_SOURCE implementation */ +#undef __underlying_memchr +#undef __underlying_memcmp +#undef __underlying_memcpy +#undef __underlying_memmove +#undef __underlying_memset +#undef __underlying_strcat +#undef __underlying_strcpy +#undef __underlying_strlen +#undef __underlying_strncat +#undef __underlying_strncpy #endif /** -- cgit v1.2.3 From 574c1ae66c12410a08aeef8474936baa50e0371d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 Jun 2020 15:56:49 -0700 Subject: mm: clarify __GFP_MEMALLOC usage It seems that the existing documentation is not explicit about the expected usage and potential risks enough. While it is calls out that users have to free memory when using this flag it is not really apparent that users have to careful to not deplete memory reserves and that they should implement some sort of throttling wrt. freeing process. This is partly based on Neil's explanation [1]. Let's also call out that a pre allocated pool allocator should be considered. [1] http://lkml.kernel.org/r/877dz0yxoa.fsf@notabene.neil.brown.name [akpm@linux-foundation.org: coding style fixes] [mhocko@kernel.org: update] Link: http://lkml.kernel.org/r/20200406070137.GC19426@dhcp22.suse.cz Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Cc: David Rientjes Cc: Joel Fernandes Cc: Neil Brown Cc: Paul E. McKenney Cc: John Hubbard Link: http://lkml.kernel.org/r/20200403083543.11552-2-mhocko@kernel.org Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4aba4c86c626..fab6d486cbb7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -110,6 +110,11 @@ struct vm_area_struct; * the caller guarantees the allocation will allow more memory to be freed * very shortly e.g. process exiting or swapping. Users either should * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). + * Users of this flag have to be extremely careful to not deplete the reserve + * completely and implement a throttling mechanism which controls the + * consumption of the reserve based on the amount of freed memory. + * Usage of a pre-allocated pool (e.g. mempool) should be always considered + * before using this flag. * * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. -- cgit v1.2.3 From 6f24fbd38c4e05f7905814791806c01dc6c4b9de Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:56:57 -0700 Subject: mm: make early_pfn_to_nid() and related defintions close to each other early_pfn_to_nid() and its helper __early_pfn_to_nid() are spread around include/linux/mm.h, include/linux/mmzone.h and mm/page_alloc.c. Drop unused stub for __early_pfn_to_nid() and move its actual generic implementation close to its users. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-3-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- include/linux/mmzone.h | 9 --------- 2 files changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6c236c5b0015..4288e6993dc8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2445,9 +2445,9 @@ extern void sparse_memory_present_with_active_regions(int nid); #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) -static inline int __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state) +static inline int early_pfn_to_nid(unsigned long pfn) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fdd9beb5efed..c3a77eb85b42 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1080,15 +1080,6 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #include #endif -#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ - !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) -static inline unsigned long early_pfn_to_nid(unsigned long pfn) -{ - BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); - return 0; -} -#endif - #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif -- cgit v1.2.3 From 3f08a302f533f74ad2e909e7a61274aa7eebc0ab Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:02 -0700 Subject: mm: remove CONFIG_HAVE_MEMBLOCK_NODE_MAP option CONFIG_HAVE_MEMBLOCK_NODE_MAP is used to differentiate initialization of nodes and zones structures between the systems that have region to node mapping in memblock and those that don't. Currently all the NUMA architectures enable this option and for the non-NUMA systems we can presume that all the memory belongs to node 0 and therefore the compile time configuration option is not required. The remaining few architectures that use DISCONTIGMEM without NUMA are easily updated to use memblock_add_node() instead of memblock_add() and thus have proper correspondence of memblock regions to NUMA nodes. Still, free_area_init_node() must have a backward compatible version because its semantics with and without CONFIG_HAVE_MEMBLOCK_NODE_MAP is different. Once all the architectures will use the new semantics, the entire compatibility layer can be dropped. To avoid addition of extra run time memory to store node id for architectures that keep memblock but have only a single node, the node id field of the memblock_region is guarded by CONFIG_NEED_MULTIPLE_NODES and the corresponding accessors presume that in those cases it is always 0. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Acked-by: Catalin Marinas [arm64] Cc: Baoquan He Cc: Brian Cain Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-4-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 8 +++----- include/linux/mm.h | 12 ++---------- include/linux/mmzone.h | 2 +- 3 files changed, 6 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 6bc37a731d27..45abfc54da37 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -50,7 +50,7 @@ struct memblock_region { phys_addr_t base; phys_addr_t size; enum memblock_flags flags; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES int nid; #endif }; @@ -215,7 +215,6 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, @@ -234,7 +233,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, #define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \ for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \ i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid)) -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, @@ -310,10 +308,10 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid); +#ifdef CONFIG_NEED_MULTIPLE_NODES static inline void memblock_set_region_node(struct memblock_region *r, int nid) { r->nid = nid; @@ -332,7 +330,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) { return 0; } -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +#endif /* CONFIG_NEED_MULTIPLE_NODES */ /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/include/linux/mm.h b/include/linux/mm.h index 4288e6993dc8..5f15d8723167 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2401,9 +2401,8 @@ static inline unsigned long get_num_physpages(void) return phys_pages; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its + * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in a more * architecture independent manner. This is a substitute for creating the * zone_sizes[] and zholes_size[] arrays and passing them to @@ -2424,9 +2423,6 @@ static inline unsigned long get_num_physpages(void) * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. - * - * See mm/page_alloc.c for more information on each function exposed by - * CONFIG_HAVE_MEMBLOCK_NODE_MAP. */ extern void free_area_init_nodes(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); @@ -2441,13 +2437,9 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - -#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ - !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) +#ifndef CONFIG_NEED_MULTIPLE_NODES static inline int early_pfn_to_nid(unsigned long pfn) { - BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c3a77eb85b42..0c575c3d7feb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -876,7 +876,7 @@ extern int movable_zone; #ifdef CONFIG_HIGHMEM static inline int zone_movable_is_highmem(void) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES return movable_zone == ZONE_HIGHMEM; #else return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; -- cgit v1.2.3 From fa3354e4ea39e97af906c05551a36396541d70b4 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:06 -0700 Subject: mm: free_area_init: use maximal zone PFNs rather than zone sizes Currently, architectures that use free_area_init() to initialize memory map and node and zone structures need to calculate zone and hole sizes. We can use free_area_init_nodes() instead and let it detect the zone boundaries while the architectures will only have to supply the possible limits for the zones. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-5-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5f15d8723167..788704977de0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,7 +2329,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void free_area_init(unsigned long * zones_size); +extern void free_area_init(unsigned long * max_zone_pfn); extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); -- cgit v1.2.3 From 9691a071aa26a21fc8dac804a2b98d3c24f76f9a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:10 -0700 Subject: mm: use free_area_init() instead of free_area_init_nodes() free_area_init() has effectively became a wrapper for free_area_init_nodes() and there is no point of keeping it. Still free_area_init() name is shorter and more general as it does not imply necessity to initialize multiple nodes. Rename free_area_init_nodes() to free_area_init(), update the callers and drop old version of free_area_init(). Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Acked-by: Catalin Marinas Cc: Brian Cain Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-6-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 788704977de0..ff2c19e14c1e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,7 +2329,6 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void free_area_init(unsigned long * max_zone_pfn); extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); @@ -2410,21 +2409,21 @@ static inline unsigned long get_num_physpages(void) * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling - * free_area_init_nodes() passing in the PFN each zone ends at. At a basic + * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) - * free_area_init_nodes(max_zone_pfns); + * free_area_init(max_zone_pfns); * * free_bootmem_with_active_regions() calls free_bootmem_node() for each * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. */ -extern void free_area_init_nodes(unsigned long *max_zone_pfn); +void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); -- cgit v1.2.3 From 51930df5801e4da60e962ea52b811634d257a148 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:58:03 -0700 Subject: mm: free_area_init: allow defining max_zone_pfn in descending order Some architectures (e.g. ARC) have the ZONE_HIGHMEM zone below the ZONE_NORMAL. Allowing free_area_init() parse max_zone_pfn array even it is sorted in descending order allows using free_area_init() on such architectures. Add top -> down traversal of max_zone_pfn array in free_area_init() and use the latter in ARC node/zone initialization. [rppt@kernel.org: ARC fix] Link: http://lkml.kernel.org/r/20200504153901.GM14260@kernel.org [rppt@linux.ibm.com: arc: free_area_init(): take into account PAE40 mode] Link: http://lkml.kernel.org/r/20200507205900.GH683243@linux.ibm.com [akpm@linux-foundation.org: declare arch_has_descending_max_zone_pfns()] Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Cc: Guenter Roeck Link: http://lkml.kernel.org/r/20200412194859.12663-18-rppt@kernel.org Signed-off-by: Linus Torvalds --- 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 ff2c19e14c1e..21cf171ae9de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2473,6 +2473,7 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; +extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; -- cgit v1.2.3 From bc9331a19d758706493cbebba67ca70382edddac Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:58:09 -0700 Subject: mm: rename free_area_init_node() to free_area_init_memoryless_node() free_area_init_node() is only used by x86 to initialize a memory-less nodes. Make its name reflect this and drop all the function parameters except node ID as they are anyway zero. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Cc: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-19-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 21cf171ae9de..0d998c84231c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,8 +2329,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void __init free_area_init_node(int nid, unsigned long * zones_size, - unsigned long zone_start_pfn, unsigned long *zholes_size); +extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* @@ -2402,10 +2401,8 @@ static inline unsigned long get_num_physpages(void) /* * Using memblock node mappings, an architecture may initialise its - * zones, allocate the backing mem_map and account for memory holes in a more - * architecture independent manner. This is a substitute for creating the - * zone_sizes[] and zholes_size[] arrays and passing them to - * free_area_init_node() + * zones, allocate the backing mem_map and account for memory holes in an + * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling -- cgit v1.2.3 From 4ca7be24eeb3198dffdae9472d7464c8b8cadadb Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 3 Jun 2020 15:58:45 -0700 Subject: mm/page_alloc.c: remove unused free_bootmem_with_active_regions Since commit 397dc00e249ec64e10 ("mips: sgi-ip27: switch from DISCONTIGMEM to SPARSEMEM"), the last caller of free_bootmem_with_active_regions() was gone. Now no user calls it any more. Let's remove it. Signed-off-by: Baoquan He Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Link: http://lkml.kernel.org/r/20200402143455.5145-1-bhe@redhat.com 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 0d998c84231c..4141ebcb3a65 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2415,8 +2415,6 @@ static inline unsigned long get_num_physpages(void) * memblock_add_node(base, size, nid) * free_area_init(max_zone_pfns); * - * free_bootmem_with_active_regions() calls free_bootmem_node() for each - * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. */ @@ -2429,8 +2427,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern void free_bootmem_with_active_regions(int nid, - unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); #ifndef CONFIG_NEED_MULTIPLE_NODES -- cgit v1.2.3 From 97a225e69a1f880886f33d2e65a7ace13f152caa Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 3 Jun 2020 15:59:01 -0700 Subject: mm/page_alloc: integrate classzone_idx and high_zoneidx classzone_idx is just different name for high_zoneidx now. So, integrate them and add some comment to struct alloc_context in order to reduce future confusion about the meaning of this variable. The accessor, ac_classzone_idx() is also removed since it isn't needed after integration. In addition to integration, this patch also renames high_zoneidx to highest_zoneidx since it represents more precise meaning. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Acked-by: Vlastimil Babka Acked-by: David Rientjes Cc: Johannes Weiner Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Ye Xiaolong Link: http://lkml.kernel.org/r/1587095923-7515-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 9 +++++---- include/linux/mmzone.h | 12 ++++++------ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 4b898cdbdf05..3ed2f22b588a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -97,7 +97,7 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, - unsigned int alloc_flags, int classzone_idx); + unsigned int alloc_flags, int highest_zoneidx); extern void defer_compaction(struct zone *zone, int order); extern bool compaction_deferred(struct zone *zone, int order); @@ -182,7 +182,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, extern int kcompactd_run(int nid); extern void kcompactd_stop(int nid); -extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); +extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); #else static inline void reset_isolation_suitable(pg_data_t *pgdat) @@ -190,7 +190,7 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) } static inline enum compact_result compaction_suitable(struct zone *zone, int order, - int alloc_flags, int classzone_idx) + int alloc_flags, int highest_zoneidx) { return COMPACT_SKIPPED; } @@ -232,7 +232,8 @@ static inline void kcompactd_stop(int nid) { } -static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) +static inline void wakeup_kcompactd(pg_data_t *pgdat, + int order, int highest_zoneidx) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0c575c3d7feb..cd8bd5f90552 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -699,13 +699,13 @@ typedef struct pglist_data { struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; - enum zone_type kswapd_classzone_idx; + enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; - enum zone_type kcompactd_classzone_idx; + enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; #endif @@ -783,15 +783,15 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, - enum zone_type classzone_idx); + enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags, + int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, + unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx); + unsigned long mark, int highest_zoneidx); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, -- cgit v1.2.3 From 01c0bfe061f309b848d51619f20495ee2acd7727 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 3 Jun 2020 15:59:08 -0700 Subject: mm: rename gfpflags_to_migratetype to gfp_migratetype for same convention Pageblock migrate type is encoded in GFP flags, just as zone_type and zonelist. Currently we use gfp_zone() and gfp_zonelist() to extract related information, it would be proper to use the same naming convention for migrate type. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Reviewed-by: Pankaj Gupta Link: http://lkml.kernel.org/r/20200329080823.7735-1-richard.weiyang@gmail.com Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fab6d486cbb7..67a0774e080b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -312,7 +312,7 @@ struct vm_area_struct; #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 -static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) +static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); -- cgit v1.2.3 From ae70eddd5633fc71dccf210f237c5aefc96f4332 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 15:59:17 -0700 Subject: mm/page_alloc: restrict and formalize compound_page_dtors[] Restrict elements in compound_page_dtors[] array per NR_COMPOUND_DTORS and explicitly position them according to enum compound_dtor_id. This improves protection against possible misalignment between compound_page_dtors[] and enum compound_dtor_id later on. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Link: http://lkml.kernel.org/r/1589795958-19317-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4141ebcb3a65..32f3c17715ac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -867,7 +867,7 @@ enum compound_dtor_id { #endif NR_COMPOUND_DTORS, }; -extern compound_page_dtor * const compound_page_dtors[]; +extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) -- cgit v1.2.3 From 3d060856adfc59afb9d029c233141334cfaba418 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Wed, 3 Jun 2020 15:59:24 -0700 Subject: mm: initialize deferred pages with interrupts enabled Initializing struct pages is a long task and keeping interrupts disabled for the duration of this operation introduces a number of problems. 1. jiffies are not updated for long period of time, and thus incorrect time is reported. See proposed solution and discussion here: lkml/20200311123848.118638-1-shile.zhang@linux.alibaba.com 2. It prevents farther improving deferred page initialization by allowing intra-node multi-threading. We are keeping interrupts disabled to solve a rather theoretical problem that was never observed in real world (See 3a2d7fa8a3d5). Let's keep interrupts enabled. In case we ever encounter a scenario where an interrupt thread wants to allocate large amount of memory this early in boot we can deal with that by growing zone (see deferred_grow_zone()) by the needed amount before starting deferred_init_memmap() threads. Before: [ 1.232459] node 0 initialised, 12058412 pages in 1ms After: [ 1.632580] node 0 initialised, 12051227 pages in 436ms Fixes: 3a2d7fa8a3d5 ("mm: disable interrupts while initializing deferred pages") Reported-by: Shile Zhang Signed-off-by: Pavel Tatashin Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Dan Williams Cc: James Morris Cc: Kirill Tkhai Cc: Sasha Levin Cc: Yiqian Wei Cc: [4.17+] Link: http://lkml.kernel.org/r/20200403140952.17177-3-pasha.tatashin@soleen.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cd8bd5f90552..2f79ff4477ba 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -680,6 +680,8 @@ typedef struct pglist_data { /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. + * Also synchronizes pgdat->first_deferred_pfn during deferred page + * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG -- cgit v1.2.3 From f1b192b117cd418bacf42a9583d7a01855a18fe5 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:35 -0700 Subject: padata: initialize earlier padata will soon initialize the system's struct pages in parallel, so it needs to be ready by page_alloc_init_late(). The error return from padata_driver_init() triggers an initcall warning, so add a warning to padata_init() to avoid silent failure. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-3-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 693cae9bfe66..d50bd1a7756f 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -166,6 +166,12 @@ struct padata_instance { #define PADATA_INVALID 4 }; +#ifdef CONFIG_PADATA +extern void __init padata_init(void); +#else +static inline void __init padata_init(void) {} +#endif + extern struct padata_instance *padata_alloc_possible(const char *name); extern void padata_free(struct padata_instance *pinst); extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); -- cgit v1.2.3 From 4611ce22468895acd61fee9ac1da810d60617d9a Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:39 -0700 Subject: padata: allocate work structures for parallel jobs from a pool padata allocates per-CPU, per-instance work structs for parallel jobs. A do_parallel call assigns a job to a sequence number and hashes the number to a CPU, where the job will eventually run using the corresponding work. This approach fit with how padata used to bind a job to each CPU round-robin, makes less sense after commit bfde23ce200e6 ("padata: unbind parallel jobs from specific CPUs") because a work isn't bound to a particular CPU anymore, and isn't needed at all for multithreaded jobs because they don't have sequence numbers. Replace the per-CPU works with a preallocated pool, which allows sharing them between existing padata users and the upcoming multithreaded user. The pool will also facilitate setting NUMA-aware concurrency limits with later users. The pool is sized according to the number of possible CPUs. With this limit, MAX_OBJ_NUM no longer makes sense, so remove it. If the global pool is exhausted, a parallel job is run in the current task instead to throttle a system trying to do too much in parallel. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-4-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index d50bd1a7756f..b4da88f8588c 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -24,7 +24,6 @@ * @list: List entry, to attach to the padata lists. * @pd: Pointer to the internal control structure. * @cb_cpu: Callback cpu for serializatioon. - * @cpu: Cpu for parallelization. * @seq_nr: Sequence number of the parallelized data object. * @info: Used to pass information from the parallel to the serial function. * @parallel: Parallel execution function. @@ -34,7 +33,6 @@ struct padata_priv { struct list_head list; struct parallel_data *pd; int cb_cpu; - int cpu; unsigned int seq_nr; int info; void (*parallel)(struct padata_priv *padata); @@ -68,15 +66,11 @@ struct padata_serial_queue { /** * struct padata_parallel_queue - The percpu padata parallel queue * - * @parallel: List to wait for parallelization. * @reorder: List to wait for reordering after parallel processing. - * @work: work struct for parallelization. * @num_obj: Number of objects that are processed by this cpu. */ struct padata_parallel_queue { - struct padata_list parallel; struct padata_list reorder; - struct work_struct work; atomic_t num_obj; }; @@ -111,7 +105,7 @@ struct parallel_data { struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; atomic_t refcnt; - atomic_t seq_nr; + unsigned int seq_nr; unsigned int processed; int cpu; struct padata_cpumask cpumask; -- cgit v1.2.3 From 004ed42638f4428e70ead59d170f3d17ff761a0f Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:43 -0700 Subject: padata: add basic support for multithreaded jobs Sometimes the kernel doesn't take full advantage of system memory bandwidth, leading to a single CPU spending excessive time in initialization paths where the data scales with memory size. Multithreading naturally addresses this problem. Extend padata, a framework that handles many parallel yet singlethreaded jobs, to also handle multithreaded jobs by adding support for splitting up the work evenly, specifying a minimum amount of work that's appropriate for one helper thread to do, load balancing between helpers, and coordinating them. This is inspired by work from Pavel Tatashin and Steve Sistare. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-5-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index b4da88f8588c..7302efff5e65 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -4,6 +4,9 @@ * * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert + * + * Copyright (c) 2020 Oracle and/or its affiliates. + * Author: Daniel Jordan */ #ifndef PADATA_H @@ -130,6 +133,31 @@ struct padata_shell { struct list_head list; }; +/** + * struct padata_mt_job - represents one multithreaded job + * + * @thread_fn: Called for each chunk of work that a padata thread does. + * @fn_arg: The thread function argument. + * @start: The start of the job (units are job-specific). + * @size: size of this node's work (units are job-specific). + * @align: Ranges passed to the thread function fall on this boundary, with the + * possible exceptions of the beginning and end of the job. + * @min_chunk: The minimum chunk size in job-specific units. This allows + * the client to communicate the minimum amount of work that's + * appropriate for one worker thread to do at once. + * @max_threads: Max threads to use for the job, actual number may be less + * depending on task size and minimum chunk size. + */ +struct padata_mt_job { + void (*thread_fn)(unsigned long start, unsigned long end, void *arg); + void *fn_arg; + unsigned long start; + unsigned long size; + unsigned long align; + unsigned long min_chunk; + int max_threads; +}; + /** * struct padata_instance - The overall control structure. * @@ -173,6 +201,7 @@ 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 void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); extern int padata_start(struct padata_instance *pinst); -- cgit v1.2.3 From ecd096506922332fdb36ff1211e03601befe6e18 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:55 -0700 Subject: mm: make deferred init's max threads arch-specific Using padata during deferred init has only been tested on x86, so for now limit it to this architecture. If another arch wants this, it can find the max thread limit that's best for it and override deferred_page_init_max_threads(). Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-8-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 45abfc54da37..807ab9daf0cd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -273,6 +273,9 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, #define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \ for (; i != U64_MAX; \ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) + +int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); + #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** -- cgit v1.2.3 From ae94da898133947c2d1f005da10838478e4548db Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 3 Jun 2020 16:00:34 -0700 Subject: hugetlbfs: add arch_hugetlb_valid_size Patch series "Clean up hugetlb boot command line processing", v4. Longpeng(Mike) reported a weird message from hugetlb command line processing and proposed a solution [1]. While the proposed patch does address the specific issue, there are other related issues in command line processing. As hugetlbfs evolved, updates to command line processing have been made to meet immediate needs and not necessarily in a coordinated manner. The result is that some processing is done in arch specific code, some is done in arch independent code and coordination is problematic. Semantics can vary between architectures. The patch series does the following: - Define arch specific arch_hugetlb_valid_size routine used to validate passed huge page sizes. - Move hugepagesz= command line parsing out of arch specific code and into an arch independent routine. - Clean up command line processing to follow desired semantics and document those semantics. [1] https://lore.kernel.org/linux-mm/20200305033014.1152-1-longpeng2@huawei.com This patch (of 3): The architecture independent routine hugetlb_default_setup sets up the default huge pages size. It has no way to verify if the passed value is valid, so it accepts it and attempts to validate at a later time. This requires undocumented cooperation between the arch specific and arch independent code. For architectures that support more than one huge page size, provide a routine arch_hugetlb_valid_size to validate a huge page size. hugetlb_default_setup can use this to validate passed values. arch_hugetlb_valid_size will also be used in a subsequent patch to move processing of the "hugepagesz=" in arch specific code to a common routine in arch independent code. Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Acked-by: Gerald Schaefer [s390] Acked-by: Will Deacon Cc: Catalin Marinas Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Dave Hansen Cc: Jonathan Corbet Cc: Longpeng Cc: Christophe Leroy Cc: Randy Dunlap Cc: Mina Almasry Cc: Peter Xu Cc: Nitesh Narayan Lal Cc: Anders Roxell Cc: "Aneesh Kumar K.V" Cc: Qian Cai Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200428205614.246260-1-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200428205614.246260-2-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200417185049.275845-1-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200417185049.275845-2-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 43a1cef8f0f1..2eb15f5ab01e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -521,6 +521,7 @@ int __init alloc_bootmem_huge_page(struct hstate *h); void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); +bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE -- cgit v1.2.3 From 359f25443a8dada0fb709dd044a422017031790f Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 3 Jun 2020 16:00:38 -0700 Subject: hugetlbfs: move hugepagesz= parsing to arch independent code Now that architectures provide arch_hugetlb_valid_size(), parsing of "hugepagesz=" can be done in architecture independent code. Create a single routine to handle hugepagesz= parsing and remove all arch specific routines. We can also remove the interface hugetlb_bad_size() as this is no longer used outside arch independent code. This also provides consistent behavior of hugetlbfs command line options. The hugepagesz= option should only be specified once for a specific size, but some architectures allow multiple instances. This appears to be more of an oversight when code was added by some architectures to set up ALL huge pages sizes. Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Tested-by: Sandipan Das Reviewed-by: Peter Xu Acked-by: Mina Almasry Acked-by: Gerald Schaefer [s390] Acked-by: Will Deacon Cc: Albert Ou Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Longpeng Cc: Nitesh Narayan Lal Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Anders Roxell Cc: "Aneesh Kumar K.V" Cc: Qian Cai Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200417185049.275845-3-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200428205614.246260-3-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2eb15f5ab01e..0c13706054ef 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -519,7 +519,6 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, int __init __alloc_bootmem_huge_page(struct hstate *h); int __init alloc_bootmem_huge_page(struct hstate *h); -void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); -- cgit v1.2.3 From b0eae98c66fe4ccac3a5a79a1479c057f2c7cdd7 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 16:01:01 -0700 Subject: mm/hugetlb: define a generic fallback for is_hugepage_only_range() There are multiple similar definitions for is_hugepage_only_range() on various platforms. Lets just add it's generic fallback definition for platforms that do not override. This help reduce code duplication. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1588907271-11920-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c13706054ef..bf97b17ab206 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -591,6 +591,15 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) #include +#ifndef is_hugepage_only_range +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} +#define is_hugepage_only_range is_hugepage_only_range +#endif + #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) -- cgit v1.2.3 From 5be993432821750f382809df5e20bf4c129b24f7 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 16:01:05 -0700 Subject: mm/hugetlb: define a generic fallback for arch_clear_hugepage_flags() There are multiple similar definitions for arch_clear_hugepage_flags() on various platforms. Lets just add it's generic fallback definition for platforms that do not override. This help reduce code duplication. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1588907271-11920-4-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bf97b17ab206..2e66b71c1236 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -600,6 +600,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, #define is_hugepage_only_range is_hugepage_only_range #endif +#ifndef arch_clear_hugepage_flags +static inline void arch_clear_hugepage_flags(struct page *page) { } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#endif + #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) -- cgit v1.2.3 From ff45fc3ca0f3c38e752d75f71b8d8efcf409e42d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 3 Jun 2020 16:01:09 -0700 Subject: mm: simplify calling a compound page destructor None of the three callers of get_compound_page_dtor() want to know the value; they just want to call the function. Replace it with destroy_compound_page() which calls the dtor for them. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Anshuman Khandual Reviewed-by: David Hildenbrand Acked-by: Kirill A. Shutemov Link: http://lkml.kernel.org/r/20200517105051.9352-1-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32f3c17715ac..ff73187c3fd4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -876,10 +876,10 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } -static inline compound_page_dtor *get_compound_page_dtor(struct page *page) +static inline void destroy_compound_page(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); - return compound_page_dtors[page[1].compound_dtor]; + compound_page_dtors[page[1].compound_dtor](page); } static inline unsigned int compound_order(struct page *page) -- cgit v1.2.3 From 1f318a9b0dc3990490e98eef48f21e6f15185781 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Wed, 3 Jun 2020 16:01:15 -0700 Subject: mm/vmscan: count layzfree pages and fix nr_isolated_* mismatch Fix an nr_isolate_* mismatch problem between cma and dirty lazyfree pages. If try_to_unmap_one is used for reclaim and it detects a dirty lazyfree page, then the lazyfree page is changed to a normal anon page having SwapBacked by commit 802a3a92ad7a ("mm: reclaim MADV_FREE pages"). Even with the change, reclaim context correctly counts isolated files because it uses is_file_lru to distinguish file. And the change to anon is not happened if try_to_unmap_one is used for migration. So migration context like compaction also correctly counts isolated files even though it uses page_is_file_lru insted of is_file_lru. Recently page_is_file_cache was renamed to page_is_file_lru by commit 9de4f22a60f7 ("mm: code cleanup for MADV_FREE"). But the nr_isolate_* mismatch problem happens on cma alloc. There is reclaim_clean_pages_from_list which is being used only by cma. It was introduced by commit 02c6de8d757c ("mm: cma: discard clean pages during contiguous allocation instead of migration") to reclaim clean file pages without migration. The cma alloc uses both reclaim_clean_pages_from_list and migrate_pages, and it uses page_is_file_lru to count isolated files. If there are dirty lazyfree pages allocated from cma memory region, the pages are counted as isolated file at the beginging but are counted as isolated anon after finished. Mem-Info: Node 0 active_anon:3045904kB inactive_anon:611448kB active_file:14892kB inactive_file:205636kB unevictable:10416kB isolated(anon):0kB isolated(file):37664kB mapped:630216kB dirty:384kB writeback:0kB shmem:42576kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no Like log above, there were too much isolated files, 37664kB, which triggers too_many_isolated in reclaim even when there is no actually isolated file in system wide. It could be reproducible by running two programs, writing on MADV_FREE page and doing cma alloc, respectively. Although isolated anon is 0, I found that the internal value of isolated anon was the negative value of isolated file. Fix this by compensating the isolated count for both LRU lists. Count non-discarded lazyfree pages in shrink_page_list, then compensate the counted number in reclaim_clean_pages_from_list. Reported-by: Yong-Taek Lee Suggested-by: Minchan Kim Signed-off-by: Jaewon Kim Signed-off-by: Andrew Morton Acked-by: Minchan Kim Cc: Mel Gorman Cc: Johannes Weiner Cc: Marek Szyprowski Cc: Michal Nazarewicz Cc: Shaohua Li Link: http://lkml.kernel.org/r/20200426011718.30246-1-jaewon31.kim@samsung.com Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 292485f3d24d..10cc932e209a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -29,6 +29,7 @@ struct reclaim_stat { unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; + unsigned nr_lazyfree_fail; }; enum writeback_stat_item { -- cgit v1.2.3 From 3fba69a56e16e8dcf182fe6ca77735dd65a898aa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:31 -0700 Subject: mm: memcontrol: drop @compound parameter from memcg charging API The memcg charging API carries a boolean @compound parameter that tells whether the page we're dealing with is a hugepage. mem_cgroup_commit_charge() has another boolean @lrucare that indicates whether the page needs LRU locking or not while charging. The majority of callsites know those parameters at compile time, which results in a lot of naked "false, false" argument lists. This makes for cryptic code and is a breeding ground for subtle mistakes. Thankfully, the huge page state can be inferred from the page itself and doesn't need to be passed along. This is safe because charging completes before the page is published and somebody may split it. Simplify the callsites by removing @compound, and let memcg infer the state by using hpage_nr_pages() unconditionally. That function does PageTransHuge() to identify huge pages, which also helpfully asserts that nobody passes in tail pages by accident. The following patches will introduce a new charging API, best not to carry over unnecessary weight. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe9533bb67e..fc400002c7be 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -359,15 +359,12 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound); + bool lrucare); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -849,8 +846,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -859,8 +855,7 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -868,13 +863,12 @@ static inline int mem_cgroup_try_charge_delay(struct page *page, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg, - bool compound) + struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 6caa6a0703e03236f46461342e31ca53d0e3c091 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:38 -0700 Subject: mm: memcontrol: move out cgroup swaprate throttling The cgroup swaprate throttling is about matching new anon allocations to the rate of available IO when that is being throttled. It's the io controller hooking into the VM, rather than a memory controller thing. Rename mem_cgroup_throttle_swaprate() to cgroup_throttle_swaprate(), and drop the @memcg argument which is only used to check whether the preceding page charge has succeeded and the fault is proceeding. We could decouple the call from mem_cgroup_try_charge() here as well, but that would cause unnecessary churn: the following patches convert all callsites to a new charge API and we'll decouple as we go along. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e92176fc8824..6cea1eb97d45 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -651,11 +651,9 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, - gfp_t gfp_mask); +extern void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); #else -static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, - int node, gfp_t gfp_mask) +static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif -- cgit v1.2.3 From 3fea5a499d57dec46043fcdb08e38eac1767bb0d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:41 -0700 Subject: mm: memcontrol: convert page cache to a new mem_cgroup_charge() API The try/commit/cancel protocol that memcg uses dates back to when pages used to be uncharged upon removal from the page cache, and thus couldn't be committed before the insertion had succeeded. Nowadays, pages are uncharged when they are physically freed; it doesn't matter whether the insertion was successful or not. For the page cache, the transaction dance has become unnecessary. Introduce a mem_cgroup_charge() function that simply charges a newly allocated page to a cgroup and sets up page->mem_cgroup in one single step. If the insertion fails, the caller doesn't have to do anything but free/put the page. Then switch the page cache over to this new API. Subsequent patches will also convert anon pages, but it needs a bit more prep work. Right now, memcg depends on page->mapping being already set up at the time of charging, so that it can maintain its own MEMCG_CACHE and MEMCG_RSS counters. For anon, page->mapping is set under the same pte lock under which the page is publishd, so a single charge point that can block doesn't work there just yet. The following prep patches will replace the private memcg counters with the generic vmstat counters, thus removing the page->mapping dependency, then complete the transition to the new single-point charge API and delete the old transactional scheme. v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo) v3: rebase on preceeding shmem simplification patch Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fc400002c7be..898925bdd676 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -365,6 +365,10 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); + +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare); + void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -872,6 +876,12 @@ static inline void mem_cgroup_cancel_charge(struct page *page, { } +static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, bool lrucare) +{ + return 0; +} + static inline void mem_cgroup_uncharge(struct page *page) { } -- cgit v1.2.3 From 9da7b5216869f80e91f78403a57c72b42357758c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:51 -0700 Subject: mm: memcontrol: prepare cgroup vmstat infrastructure for native anon counters Anonymous compound pages can be mapped by ptes, which means that if we want to track NR_MAPPED_ANON, NR_ANON_THPS on a per-cgroup basis, we have to be prepared to see tail pages in our accounting functions. Make mod_lruvec_page_state() and lock_page_memcg() deal with tail pages correctly, namely by redirecting to the head page which has the page->mem_cgroup set up. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 898925bdd676..8f00dd755818 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -709,16 +709,17 @@ static inline void mod_lruvec_state(struct lruvec *lruvec, static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { + struct page *head = compound_head(page); /* rmap on tail pages */ pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!page->mem_cgroup) { + if (!head->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } - lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat); + lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } -- cgit v1.2.3 From 0d1c20722ab333ac0ac03ae2188922c1021d3abc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:54 -0700 Subject: mm: memcontrol: switch to native NR_FILE_PAGES and NR_SHMEM counters Memcg maintains private MEMCG_CACHE and NR_SHMEM counters. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counters of NR_FILE_PAGES and NR_SHMEM. The page is already locked in these places, so page->mem_cgroup is stable; we only need minimal tweaks of two mem_cgroup_migrate() calls to ensure it's set up in time. Then replace MEMCG_CACHE with NR_FILE_PAGES and delete the private NR_SHMEM accounting sites. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-10-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8f00dd755818..f6ea68ceed2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS, + MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, MEMCG_RSS_HUGE, MEMCG_SWAP, MEMCG_SOCK, -- cgit v1.2.3 From be5d0a74c62d8da43f9526a5b08cdd18e2bbc37a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:57 -0700 Subject: mm: memcontrol: switch to native NR_ANON_MAPPED counter Memcg maintains a private MEMCG_RSS counter. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counter of NR_ANON_MAPPED. We use lock_page_memcg() to stabilize page->mem_cgroup during rmap changes, the same way we do for NR_FILE_MAPPED. With the previous patch removing MEMCG_CACHE and the private NR_SHMEM counter, this patch finally eliminates the need to have page->mapping set up at charge time. However, we need to have page->mem_cgroup set up by the time rmap runs and does the accounting, so switch the commit and the rmap callbacks around. v2: fix temporary accounting bug by switching rmap<->commit (Joonsoo) Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-11-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f6ea68ceed2c..acacc3018957 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS_HUGE, + MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, MEMCG_SWAP, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ -- cgit v1.2.3 From 468c398233da208521a0f84c2068012a66a7489d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:01 -0700 Subject: mm: memcontrol: switch to native NR_ANON_THPS counter With rmap memcg locking already in place for NR_ANON_MAPPED, it's just a small step to remove the MEMCG_RSS_HUGE wart and switch memcg to the native NR_ANON_THPS accounting sites. [hannes@cmpxchg.org: fixes] Link: http://lkml.kernel.org/r/20200512121750.GA397968@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Tested-by: Naresh Kamboju Reviewed-by: Joonsoo Kim Acked-by: Randy Dunlap [build-tested] Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index acacc3018957..63a31a6c3c69 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, - MEMCG_SWAP, + MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ MEMCG_KERNEL_STACK_KB, -- cgit v1.2.3 From 9d82c69438d0dff8809061edbcce43a5a4bcf09f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:04 -0700 Subject: mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API With the page->mapping requirement gone from memcg, we can charge anon and file-thp pages in one single step, right after they're allocated. This removes two out of three API calls - especially the tricky commit step that needed to happen at just the right time between when the page is "set up" and when it's "published" - somewhat vague and fluid concepts that varied by page type. All we need is a freshly allocated page and a memcg context to charge. v2: prevent double charges on pre-allocated hugepages in khugepaged [hannes@cmpxchg.org: Fix crash - *hpage could be ERR_PTR instead of NULL] Link: http://lkml.kernel.org/r/20200512215813.GA487759@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Cc: Qian Cai Link: http://lkml.kernel.org/r/20200508183105.225460-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ff73187c3fd4..4ef044fa09fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -501,7 +501,6 @@ struct vm_fault { pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ - struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by @@ -946,8 +945,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page); +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif -- cgit v1.2.3 From f0e45fb4da29746a116e810eb91423ccfa4830fc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:07 -0700 Subject: mm: memcontrol: drop unused try/commit/cancel charge API There are no more users. RIP in peace. [arnd@arndb.de: fix an unused-function warning] Link: http://lkml.kernel.org/r/20200528095640.151454-1-arnd@arndb.de Signed-off-by: Johannes Weiner Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 63a31a6c3c69..46620c6343ef 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,14 +355,6 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); - int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare); @@ -846,34 +838,6 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( return MEMCG_PROT_NONE; } -static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline int mem_cgroup_try_charge_delay(struct page *page, - struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline void mem_cgroup_commit_charge(struct page *page, - struct mem_cgroup *memcg, - bool lrucare) -{ -} - -static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg) -{ -} - static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare) { -- cgit v1.2.3 From eccb52e7880973f221ab2606e4d22ce04d96a1a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:11 -0700 Subject: mm: memcontrol: prepare swap controller setup for integration A few cleanups to streamline the swap controller setup: - Replace the do_swap_account flag with cgroup_memory_noswap. This brings it in line with other functionality that is usually available unless explicitly opted out of - nosocket, nokmem. - Remove the really_do_swap_account flag that stores the boot option and is later used to switch the do_swap_account. It's not clear why this indirection is/was necessary. Use do_swap_account directly. - Minor coding style polishing Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-15-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 46620c6343ef..96257f995caa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -558,7 +558,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP -extern int do_swap_account; +extern bool cgroup_memory_noswap; #endif struct mem_cgroup *lock_page_memcg(struct page *page); -- cgit v1.2.3 From d9eb1ea2bf8734afd8ec7d995270437a7242f82b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:24 -0700 Subject: mm: memcontrol: delete unused lrucare handling Swapin faults were the last event to charge pages after they had already been put on the LRU list. Now that we charge directly on swapin, the lrucare portion of the charge code is unused. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Cc: Shakeel Butt Link: http://lkml.kernel.org/r/20200508183105.225460-19-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 96257f995caa..d5bf3b5bfe6d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,8 +355,7 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare); +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -839,7 +838,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, bool lrucare) + gfp_t gfp_mask) { return 0; } -- cgit v1.2.3 From 497a6c1b09902b22ceccc0f25ba4dd623e1ddb7d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:34 -0700 Subject: mm: keep separate anon and file statistics on page reclaim activity Having statistics on pages scanned and pages reclaimed for both anon and file pages makes it easier to evaluate changes to LRU balancing. While at it, clean up the stat-keeping mess for isolation, putback, reclaim stats etc. a bit: first the physical LRU operation (isolation and putback), followed by vmstats, reclaim_stats, and then vm events. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-3-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index ffef0f279747..24fc7c3ae7d6 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -35,6 +35,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_DIRECT_THROTTLE, + PGSCAN_ANON, + PGSCAN_FILE, + PGSTEAL_ANON, + PGSTEAL_FILE, #ifdef CONFIG_NUMA PGSCAN_ZONE_RECLAIM_FAILED, #endif -- cgit v1.2.3 From 6058eaec816f29fbe33c9d35694614c9a4ed75ba Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:40 -0700 Subject: mm: fold and remove lru_cache_add_anon() and lru_cache_add_file() They're the same function, and for the purpose of all callers they are equivalent to lru_cache_add(). [akpm@linux-foundation.org: fix it for local_lock changes] Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Rik van Riel Acked-by: Michal Hocko Acked-by: Minchan Kim Cc: Joonsoo Kim Link: http://lkml.kernel.org/r/20200520232525.798933-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6cea1eb97d45..217bc8e13feb 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,8 +335,6 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ extern void lru_cache_add(struct page *); -extern void lru_cache_add_anon(struct page *page); -extern void lru_cache_add_file(struct page *page); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); -- cgit v1.2.3 From 1431d4d11abb265e79cd44bed2f5ea93f1bcc57b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:53 -0700 Subject: mm: base LRU balancing on an explicit cost model Currently, scan pressure between the anon and file LRU lists is balanced based on a mixture of reclaim efficiency and a somewhat vague notion of "value" of having certain pages in memory over others. That concept of value is problematic, because it has caused us to count any event that remotely makes one LRU list more or less preferrable for reclaim, even when these events are not directly comparable and impose very different costs on the system. One example is referenced file pages that we still deactivate and referenced anonymous pages that we actually rotate back to the head of the list. There is also conceptual overlap with the LRU algorithm itself. By rotating recently used pages instead of reclaiming them, the algorithm already biases the applied scan pressure based on page value. Thus, when rebalancing scan pressure due to rotations, we should think of reclaim cost, and leave assessing the page value to the LRU algorithm. Lastly, considering both value-increasing as well as value-decreasing events can sometimes cause the same type of event to be counted twice, i.e. how rotating a page increases the LRU value, while reclaiming it succesfully decreases the value. In itself this will balance out fine, but it quietly skews the impact of events that are only recorded once. The abstract metric of "value", the murky relationship with the LRU algorithm, and accounting both negative and positive events make the current pressure balancing model hard to reason about and modify. This patch switches to a balancing model of accounting the concrete, actually observed cost of reclaiming one LRU over another. For now, that cost includes pages that are scanned but rotated back to the list head. Subsequent patches will add consideration for IO caused by refaulting of recently evicted pages. Replace struct zone_reclaim_stat with two cost counters in the lruvec, and make everything that affects cost go through a new lru_note_cost() function. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 21 +++++++-------------- include/linux/swap.h | 2 ++ 2 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2f79ff4477ba..e57248ccb63d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -242,19 +242,6 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -struct zone_reclaim_stat { - /* - * The pageout code in vmscan.c keeps track of how many of the - * mem/swap backed and file backed pages are referenced. - * The higher the rotated/scanned ratio, the more valuable - * that cache is. - * - * The anon LRU stats live in [0], file LRU stats in [1] - */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; -}; - enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI @@ -263,7 +250,13 @@ enum lruvec_flags { struct lruvec { struct list_head lists[NR_LRU_LISTS]; - struct zone_reclaim_stat reclaim_stat; + /* + * These track the cost of reclaiming one LRU - file or anon - + * over the other. As the observed cost of reclaiming one LRU + * increases, the reclaim scan balance tips toward the other. + */ + unsigned long anon_cost; + unsigned long file_cost; /* Evictions & activations on the inactive file list */ atomic_long_t inactive_age; /* Refaults at the time of last reclaim cycle */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 217bc8e13feb..ce3c55747006 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,6 +334,8 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); -- cgit v1.2.3 From 314b57fb0460001a090b35ff8be987f2c868ad3c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:03 -0700 Subject: mm: balance LRU lists based on relative thrashing Since the LRUs were split into anon and file lists, the VM has been balancing between page cache and anonymous pages based on per-list ratios of scanned vs. rotated pages. In most cases that tips page reclaim towards the list that is easier to reclaim and has the fewest actively used pages, but there are a few problems with it: 1. Refaults and LRU rotations are weighted the same way, even though one costs IO and the other costs a bit of CPU. 2. The less we scan an LRU list based on already observed rotations, the more we increase the sampling interval for new references, and rotations become even more likely on that list. This can enter a death spiral in which we stop looking at one list completely until the other one is all but annihilated by page reclaim. Since commit a528910e12ec ("mm: thrash detection-based file cache sizing") we have refault detection for the page cache. Along with swapin events, they are good indicators of when the file or anon list, respectively, is too small for its workingset and needs to grow. For example, if the page cache is thrashing, the cache pages need more time in memory, while there may be colder pages on the anonymous list. Likewise, if swapped pages are faulting back in, it indicates that we reclaim anonymous pages too aggressively and should back off. Replace LRU rotations with refaults and swapins as the basis for relative reclaim cost of the two LRUs. This will have the VM target list balances that incur the least amount of IO on aggregate. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index ce3c55747006..0b71bf75fb67 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,8 +334,7 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void lru_note_cost(struct lruvec *lruvec, bool file, - unsigned int nr_pages); +extern void lru_note_cost(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); -- cgit v1.2.3 From 7cf111bc39f6792abedcdfbc4e6291a5603b0ef0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:06 -0700 Subject: mm: vmscan: determine anon/file pressure balance at the reclaim root We split the LRU lists into anon and file, and we rebalance the scan pressure between them when one of them begins thrashing: if the file cache experiences workingset refaults, we increase the pressure on anonymous pages; if the workload is stalled on swapins, we increase the pressure on the file cache instead. With cgroups and their nested LRU lists, we currently don't do this correctly. While recursive cgroup reclaim establishes a relative LRU order among the pages of all involved cgroups, LRU pressure balancing is done on an individual cgroup LRU level. As a result, when one cgroup is thrashing on the filesystem cache while a sibling may have cold anonymous pages, pressure doesn't get equalized between them. This patch moves LRU balancing decision to the root of reclaim - the same level where the LRU order is established. It does this by tracking LRU cost recursively, so that every level of the cgroup tree knows the aggregate LRU cost of all memory within its domain. When the page scanner calculates the scan balance for any given individual cgroup's LRU list, it uses the values from the ancestor cgroup that initiated the reclaim cycle. If one sibling is then thrashing on the cache, it will tip the pressure balance inside its ancestors, and the next hierarchical reclaim iteration will go more after the anon pages in the tree. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d5bf3b5bfe6d..e77197a62809 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1242,6 +1242,19 @@ static inline void dec_lruvec_page_state(struct page *page, mod_lruvec_page_state(page, idx, -1); } +static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) +{ + struct mem_cgroup *memcg; + + memcg = lruvec_memcg(lruvec); + if (!memcg) + return NULL; + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); +} + #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); -- cgit v1.2.3 From 96f8bf4fb1dd2656ae3e92326be9ebf003bbfd45 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:09 -0700 Subject: mm: vmscan: reclaim writepage is IO cost The VM tries to balance reclaim pressure between anon and file so as to reduce the amount of IO incurred due to the memory shortage. It already counts refaults and swapins, but in addition it should also count writepage calls during reclaim. For swap, this is obvious: it's IO that wouldn't have occurred if the anonymous memory hadn't been under memory pressure. From a relative balancing point of view this makes sense as well: even if anon is cold and reclaimable, a cache that isn't thrashing may have equally cold pages that don't require IO to reclaim. For file writeback, it's trickier: some of the reclaim writepage IO would have likely occurred anyway due to dirty expiration. But not all of it - premature writeback reduces batching and generates additional writes. Since the flushers are already woken up by the time the VM starts writing cache pages one by one, let's assume that we'e likely causing writes that wouldn't have happened without memory pressure. In addition, the per-page cost of IO would have probably been much cheaper if written in larger batches from the flusher thread rather than the single-page-writes from kswapd. For our purposes - getting the trend right to accelerate convergence on a stable state that doesn't require paging at all - this is sufficiently accurate. If we later wanted to optimize for sustained thrashing, we can still refine the measurements. Count all writepage calls from kswapd as IO cost toward the LRU that the page belongs to. Why do this dynamically? Don't we know in advance that anon pages require IO to reclaim, and so could build in a static bias? First, scanning is not the same as reclaiming. If all the anon pages are referenced, we may not swap for a while just because we're scanning the anon list. During this time, however, it's important that we age anonymous memory and the page cache at the same rate so that their hot-cold gradients are comparable. Everything else being equal, we still want to reclaim the coldest memory overall. Second, we keep copies in swap unless the page changes. If there is swap-backed data that's mostly read (tmpfs file) and has been swapped out before, we can reclaim it without incurring additional IO. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 +++- include/linux/vmstat.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0b71bf75fb67..4c5974bb9ba9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,7 +334,9 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void lru_note_cost(struct page *); +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); +extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 10cc932e209a..3d12c34cd42a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -26,6 +26,7 @@ struct reclaim_stat { unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; + unsigned nr_pageout; unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; -- cgit v1.2.3 From 8cbd54f52997f43be3d09acd9fa9a10d202c5374 Mon Sep 17 00:00:00 2001 From: chenqiwu Date: Wed, 3 Jun 2020 16:03:28 -0700 Subject: include/linux/memblock.h: fix minor typo and unclear comment Fix a minor typo "usabe->usable" for the current discription of member variable "memory" in struct memblock. BTW, I think it's unclear the member variable "base" in struct memblock_type is currently described as the physical address of memory region, change it to base address of the region is clearer since the variable is decorated as phys_addr_t. Signed-off-by: chenqiwu Signed-off-by: Andrew Morton Reviewed-by: Mike Rapoport Link: http://lkml.kernel.org/r/1588846952-32166-1-git-send-email-qiwuchen55@gmail.com Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 807ab9daf0cd..017fae833d4a 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -41,7 +41,7 @@ enum memblock_flags { /** * struct memblock_region - represents a memory region - * @base: physical address of the region + * @base: base address of the region * @size: size of the region * @flags: memory region attributes * @nid: NUMA node id @@ -75,7 +75,7 @@ struct memblock_type { * struct memblock - memblock allocator metadata * @bottom_up: is bottom up direction? * @current_limit: physical address of the current allocation limit - * @memory: usabe memory regions + * @memory: usable memory regions * @reserved: reserved memory regions * @physmem: all physical memory */ -- cgit v1.2.3 From 4301efa4c7cca11556dd89899eee066d49b47bf7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 21 Apr 2020 10:54:44 +0200 Subject: writeback: Export inode_io_list_del() Ext4 needs to remove inode from writeback lists after it is out of visibility of its journalling machinery (which can still dirty the inode). Export inode_io_list_del() for it. Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20200421085445.5731-3-jack@suse.cz Signed-off-by: Theodore Ts'o --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a19d845dd7eb..902aa317621b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -197,6 +197,7 @@ void wakeup_flusher_threads(enum wb_reason reason); void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); +void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) -- cgit v1.2.3 From 44ebcd06bbb3ab3ee446b933800aca32fc4ca9b1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:10 +0200 Subject: fs: mark __generic_block_fiemap static There is no caller left outside of ioctl.c. Signed-off-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-4-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..3104c6f7527b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3299,10 +3299,6 @@ static inline int vfs_fstat(int fd, struct kstat *stat) extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); -extern int __generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, - loff_t start, loff_t len, - get_block_t *get_block); extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); -- cgit v1.2.3 From 10c5db286452b8c60e8f58e9a4c1cbc5a91e4e5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:11 +0200 Subject: fs: move the fiemap definitions out of fs.h No need to pull the fiemap definitions into almost every file in the kernel build. Signed-off-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-5-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/fiemap.h | 24 ++++++++++++++++++++++++ include/linux/fs.h | 19 +------------------ 2 files changed, 25 insertions(+), 18 deletions(-) create mode 100644 include/linux/fiemap.h (limited to 'include/linux') diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h new file mode 100644 index 000000000000..240d4f7d9116 --- /dev/null +++ b/include/linux/fiemap.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FIEMAP_H +#define _LINUX_FIEMAP_H 1 + +#include +#include + +struct fiemap_extent_info { + unsigned int fi_flags; /* Flags as passed from user */ + unsigned int fi_extents_mapped; /* Number of mapped extents */ + unsigned int fi_extents_max; /* Size of fiemap_extent array */ + struct fiemap_extent __user *fi_extents_start; /* Start of + fiemap_extent array */ +}; + +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags); +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); + +int generic_block_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, u64 start, u64 len, + get_block_t *get_block); + +#endif /* _LINUX_FIEMAP_H 1 */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 3104c6f7527b..09bcd329c062 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include @@ -48,6 +47,7 @@ struct backing_dev_info; struct bdi_writeback; struct bio; struct export_operations; +struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; @@ -1745,19 +1745,6 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); -/* - * VFS FS_IOC_FIEMAP helper definitions. - */ -struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent __user *fi_extents_start; /* Start of - fiemap_extent array */ -}; -int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, - u64 phys, u64 len, u32 flags); -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); /* * This is the "filldir" function type, used by readdir() to let @@ -3299,10 +3286,6 @@ static inline int vfs_fstat(int fd, struct kstat *stat) extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); -extern int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, - u64 len, get_block_t *get_block); - extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); -- cgit v1.2.3 From 2732881894714f545ffac42dad7ba7730069874d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:12 +0200 Subject: iomap: fix the iomap_fiemap prototype iomap_fiemap should take u64 start and len arguments, just like the ->fiemap prototype. Signed-off-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-6-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..63db02528b70 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -178,7 +178,7 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - loff_t start, loff_t len, const struct iomap_ops *ops); + u64 start, u64 len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops); loff_t iomap_seek_data(struct inode *inode, loff_t offset, -- cgit v1.2.3 From cddf8a2c4a8286ae60fc866eab59c8bc524e93a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:13 +0200 Subject: fs: move fiemap range validation into the file systems instances Replace fiemap_check_flags with a fiemap_prep helper that also takes the inode and mapped range, and performs the sanity check and truncation previously done in fiemap_check_range. This way the validation is inside the file system itself and thus properly works for the stacked overlayfs case as well. Signed-off-by: Christoph Hellwig Reviewed-by: Amir Goldstein Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-7-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/fiemap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h index 240d4f7d9116..4e624c466583 100644 --- a/include/linux/fiemap.h +++ b/include/linux/fiemap.h @@ -13,9 +13,10 @@ struct fiemap_extent_info { fiemap_extent array */ }; +int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 *len, u32 supported_flags); int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, u64 phys, u64 len, u32 flags); -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, -- cgit v1.2.3 From df820f8de4e481222b17f9bcee7b909ae8167529 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 4 Jun 2020 10:48:19 +0200 Subject: ovl: make private mounts longterm Overlayfs is using clone_private_mount() to create internal mounts for underlying layers. These are used for operations requiring a path, such as dentry_open(). Since these private mounts are not in any namespace they are treated as short term, "detached" mounts and mntput() involves taking the global mount_lock, which can result in serious cacheline pingpong. Make these private mounts longterm instead, which trade the penalty on mntput() for a slightly longer shutdown time due to an added RCU grace period when putting these mounts. Introduce a new helper kern_unmount_many() that can take care of multiple longterm mounts with a single RCU grace period. Cc: Al Viro Signed-off-by: Miklos Szeredi --- include/linux/mount.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index bf8cc4108b8f..8de95a0bec8d 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -109,4 +109,6 @@ extern unsigned int sysctl_mount_max; extern bool path_is_mountpoint(const struct path *path); +extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); + #endif /* _LINUX_MOUNT_H */ -- cgit v1.2.3 From c25a26e653a61b93339dcd1b734c889df60b3eef Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 29 May 2020 16:03:00 +0800 Subject: vdpa: introduce get_vq_notification method This patch introduces a new method in the vdpa_config_ops which reports the physical address and the size of the doorbell for a specific virtqueue. This will be used by the future patches that maps doorbell to userspace. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200529080303.15449-4-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5453af87a33e..239db794357c 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -17,6 +17,16 @@ struct vdpa_callback { void *private; }; +/** + * vDPA notification area + * @addr: base address of the notification area + * @size: size of the notification area + */ +struct vdpa_notification_area { + resource_size_t addr; + resource_size_t size; +}; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -73,6 +83,10 @@ struct vdpa_device { * @vdev: vdpa device * @idx: virtqueue index * Returns virtqueue state (last_avail_idx) + * @get_vq_notification: Get the notification area for a virtqueue + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the notifcation area * @get_vq_align: Get the virtqueue align requirement * for the device * @vdev: vdpa device @@ -162,6 +176,8 @@ struct vdpa_config_ops { bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state); u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); + struct vdpa_notification_area + (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); -- cgit v1.2.3 From aa218795cb5fd583c94fc838dc76b7379dc4976a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 7 May 2020 16:01:30 +0200 Subject: mm: Allow to offline unmovable PageOffline() pages via MEM_GOING_OFFLINE virtio-mem wants to allow to offline memory blocks of which some parts were unplugged (allocated via alloc_contig_range()), especially, to later offline and remove completely unplugged memory blocks. The important part is that PageOffline() has to remain set until the section is offline, so these pages will never get accessed (e.g., when dumping). The pages should not be handed back to the buddy (which would require clearing PageOffline() and result in issues if offlining fails and the pages are suddenly in the buddy). Let's allow to do that by allowing to isolate any PageOffline() page when offlining. This way, we can reach the memory hotplug notifier MEM_GOING_OFFLINE, where the driver can signal that he is fine with offlining this page by dropping its reference count. PageOffline() pages with a reference count of 0 can then be skipped when offlining the pages (like if they were free, however they are not in the buddy). Anybody who uses PageOffline() pages and does not agree to offline them (e.g., Hyper-V balloon, XEN balloon, VMWare balloon for 2MB pages) will not decrement the reference count and make offlining fail when trying to migrate such an unmovable page. So there should be no observable change. Same applies to balloon compaction users (movable PageOffline() pages), the pages will simply be migrated. Note 1: If offlining fails, a driver has to increment the reference count again in MEM_CANCEL_OFFLINE. Note 2: A driver that makes use of this has to be aware that re-onlining the memory block has to be handled by hooking into onlining code (online_page_callback_t), resetting the page PageOffline() and not giving them to the buddy. Reviewed-by: Alexander Duyck Acked-by: Michal Hocko Tested-by: Pankaj Gupta Acked-by: Andrew Morton Cc: Andrew Morton Cc: Juergen Gross Cc: Konrad Rzeszutek Wilk Cc: Pavel Tatashin Cc: Alexander Duyck Cc: Vlastimil Babka Cc: Johannes Weiner Cc: Anthony Yznaga Cc: Michal Hocko Cc: Oscar Salvador Cc: Mel Gorman Cc: Mike Rapoport Cc: Dan Williams Cc: Anshuman Khandual Cc: Qian Cai Cc: Pingfan Liu Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20200507140139.17083-7-david@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/page-flags.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 222f6f7b2bb3..6be1aa559b1e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -777,6 +777,16 @@ PAGE_TYPE_OPS(Buddy, buddy) * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. + * + * If a driver wants to allow to offline unmovable PageOffline() pages without + * putting them back to the buddy, it can do so via the memory notifier by + * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the + * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() + * pages (now with a reference count of zero) are treated like free pages, + * allowing the containing memory block to get offlined. A driver that + * relies on this feature is aware that re-onlining the memory block will + * require to re-set the pages PageOffline() and not giving them to the + * buddy via online_page_callback_t. */ PAGE_TYPE_OPS(Offline, offline) -- cgit v1.2.3 From 08b3acd7a68fc17902e1cb6b146389322840deab Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 7 May 2020 16:01:32 +0200 Subject: mm/memory_hotplug: Introduce offline_and_remove_memory() virtio-mem wants to offline and remove a memory block once it unplugged all subblocks (e.g., using alloc_contig_range()). Let's provide an interface to do that from a driver. virtio-mem already supports to offline partially unplugged memory blocks. Offlining a fully unplugged memory block will not require to migrate any pages. All unplugged subblocks are PageOffline() and have a reference count of 0 - so offlining code will simply skip them. All we need is an interface to offline and remove the memory from kernel module context, where we don't have access to the memory block devices (esp. find_memory_block() and device_offline()) and the device hotplug lock. To keep things simple, allow to only work on a single memory block. Acked-by: Michal Hocko Tested-by: Pankaj Gupta Acked-by: Andrew Morton Cc: Andrew Morton Cc: David Hildenbrand Cc: Oscar Salvador Cc: Michal Hocko Cc: Pavel Tatashin Cc: Wei Yang Cc: Dan Williams Cc: Qian Cai Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20200507140139.17083-9-david@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/memory_hotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 93d9ada74ddd..cb7499843f5c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -319,6 +319,7 @@ extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int remove_memory(int nid, u64 start, u64 size); extern void __remove_memory(int nid, u64 start, u64 size); +extern int offline_and_remove_memory(int nid, u64 start, u64 size); #else static inline bool is_mem_section_removable(unsigned long pfn, -- cgit v1.2.3 From 6501bf87602f799b7e502014f8bc0aa58b868277 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Wed, 3 Jun 2020 16:49:46 +0200 Subject: u64_stats: Document writer non-preemptibility requirement MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The u64_stats mechanism uses sequence counters to protect against 64-bit values tearing on 32-bit architectures. Updating such statistics is a sequence counter write side critical section. Preemption must be disabled before entering this seqcount write critical section. Failing to do so, the seqcount read side can preempt the write side section and spin for the entire scheduler tick. If that reader belongs to a real-time scheduling class, it can spin forever and the kernel will livelock. Document this statistics update side non-preemptibility requirement. Reword the introductory paragraph to highlight u64_stats raison d'être: 64-bit values tearing protection on 32-bit architectures. Divide documentation on a basis of internal design vs. usage constraints. Reword the u64_stats header file top comment to always mention "Reader" or "Writer" at the start of each bullet point, making it easier to follow which side each point is actually for. Clarify the statement "whole thing is a NOOP on 64bit arches or UP kernels". For 32-bit UP kernels, preemption is always disabled for the statistics read side section. Signed-off-by: Ahmed S. Darwish Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 43 ++++++++++++++++++++++-------------------- 1 file changed, 23 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 9de5c10293f5..c6abb79501b3 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -3,33 +3,36 @@ #define _LINUX_U64_STATS_SYNC_H /* - * To properly implement 64bits network statistics on 32bit and 64bit hosts, - * we provide a synchronization point, that is a noop on 64bit or UP kernels. + * Protect against 64-bit values tearing on 32-bit architectures. This is + * typically used for statistics read/update in different subsystems. * * Key points : - * 1) Use a seqcount on SMP 32bits, with low overhead. - * 2) Whole thing is a noop on 64bit arches or UP kernels. - * 3) Write side must ensure mutual exclusion or one seqcount update could + * + * - Use a seqcount on 32-bit SMP, only disable preemption for 32-bit UP. + * - The whole thing is a no-op on 64-bit architectures. + * + * Usage constraints: + * + * 1) Write side must ensure mutual exclusion, or one seqcount update could * be lost, thus blocking readers forever. - * If this synchronization point is not a mutex, but a spinlock or - * spinlock_bh() or disable_bh() : - * 3.1) Write side should not sleep. - * 3.2) Write side should not allow preemption. - * 3.3) If applicable, interrupts should be disabled. * - * 4) If reader fetches several counters, there is no guarantee the whole values - * are consistent (remember point 1) : this is a noop on 64bit arches anyway) + * 2) Write side must disable preemption, or a seqcount reader can preempt the + * writer and also spin forever. + * + * 3) Write side must use the _irqsave() variant if other writers, or a reader, + * can be invoked from an IRQ context. * - * 5) readers are allowed to sleep or be preempted/interrupted : They perform - * pure reads. But if they have to fetch many values, it's better to not allow - * preemptions/interruptions to avoid many retries. + * 4) If reader fetches several counters, there is no guarantee the whole values + * are consistent w.r.t. each other (remember point #2: seqcounts are not + * used for 64bit architectures). * - * 6) If counter might be written by an interrupt, readers should block interrupts. - * (On UP, there is no seqcount_t protection, a reader allowing interrupts could - * read partial values) + * 5) Readers are allowed to sleep or be preempted/interrupted: they perform + * pure reads. * - * 7) For irq and softirq uses, readers can use u64_stats_fetch_begin_irq() and - * u64_stats_fetch_retry_irq() helpers + * 6) Readers must use both u64_stats_fetch_{begin,retry}_irq() if the stats + * might be updated from a hardirq or softirq context (remember point #1: + * seqcounts are not used for UP kernels). 32-bit UP stat readers could read + * corrupted 64-bit values otherwise. * * Usage : * -- cgit v1.2.3 From a1c979f330cb82cae7a3b19464f9815e43060fe3 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 27 May 2020 07:04:46 -0400 Subject: dm bufio: delete unused and inefficient dm_bufio_discard_buffers There is no user for this interface. If in future it is needed it can be reimplemented to walk the rbtree of buffers instead of doing block-by-block lookups. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-bufio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 07e1f163e299..5ec6bfbde9ae 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -123,13 +123,6 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c); */ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count); -/* - * Free the specified range of buffers. If a buffer is held by other process, it - * is not freed. If a buffer is dirty, it is discarded without writeback. - * Finally, send the discard request to the device. - */ -int dm_bufio_discard_buffers(struct dm_bufio_client *c, sector_t block, sector_t count); - /* * Like dm_bufio_release but also move the buffer to the new * block. dm_bufio_write_dirty_buffers is needed to commit the new block. -- cgit v1.2.3 From 5ff3b30ab57da82d8db4f14662a2858cabfbc2c0 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 4 Jun 2020 16:46:04 -0700 Subject: kcov: collect coverage from interrupts This change extends kcov remote coverage support to allow collecting coverage from soft interrupts in addition to kernel background threads. To collect coverage from code that is executed in softirq context, a part of that code has to be annotated with kcov_remote_start/stop() in a similar way as how it is done for global kernel background threads. Then the handle used for the annotations has to be passed to the KCOV_REMOTE_ENABLE ioctl. Internally this patch adjusts the __sanitizer_cov_trace_pc() compiler inserted callback to not bail out when called from softirq context. kcov_remote_start/stop() are updated to save/restore the current per task kcov state in a per-cpu area (in case the softirq came when the kernel was already collecting coverage in task context). Coverage from softirqs is collected into pre-allocated per-cpu areas, whose size is controlled by the new CONFIG_KCOV_IRQ_AREA_SIZE. [andreyknvl@google.com: turn current->kcov_softirq into unsigned int to fix objtool warning] Link: http://lkml.kernel.org/r/841c778aa3849c5cb8c3761f56b87ce653a88671.1585233617.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Signed-off-by: Andrew Morton Reviewed-by: Dmitry Vyukov Cc: Alan Stern Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Greg Kroah-Hartman Cc: Marco Elver Link: http://lkml.kernel.org/r/469bd385c431d050bc38a593296eff4baae50666.1584655448.git.andreyknvl@google.com Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 57a5ce9f33c5..c5d96e3e7fff 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1247,6 +1247,9 @@ struct task_struct { /* KCOV sequence number: */ int kcov_sequence; + + /* Collect coverage from softirq context: */ + unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG -- cgit v1.2.3 From f089dcc74226b874a4d4b122854e0dea91ff72d8 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 4 Jun 2020 16:47:08 -0700 Subject: mm: remove __ARCH_HAS_5LEVEL_HACK and include/asm-generic/5level-fixup.h There are no architectures that use include/asm-generic/5level-fixup.h therefore it can be removed along with __ARCH_HAS_5LEVEL_HACK define and the code it surrounds Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Brian Cain Cc: Catalin Marinas Cc: Christophe Leroy Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: James Morse Cc: Jonas Bonn Cc: Julien Thierry Cc: Ley Foon Tan Cc: Marc Zyngier Cc: Michael Ellerman Cc: Paul Mackerras Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Suzuki K Poulose Cc: Tony Luck Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200414153455.21744-15-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 66e0977f970a..e220ce5185ad 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2069,11 +2069,6 @@ int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) -/* - * The following ifdef needed to get the 5level-fixup.h header to work. - * Remove it when 5level-fixup.h has been removed. - */ -#ifndef __ARCH_HAS_5LEVEL_HACK static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { @@ -2102,8 +2097,6 @@ static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, return p4d_offset(pgd, address); } -#endif /* !__ARCH_HAS_5LEVEL_HACK */ - static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, unsigned long address, pgtbl_mod_mask *mod_mask) -- cgit v1.2.3 From 525aaf9bad00e7454b9f9b3873e92795afb59f8e Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:30 -0700 Subject: arch/kmap: remove redundant arch specific kmaps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The kmap code for all the architectures is almost 100% identical. Lift the common code to the core. Use ARCH_HAS_KMAP_FLUSH_TLB to indicate if an arch defines kmap_flush_tlb() and call if if needed. This also has the benefit of changing kmap() on a number of architectures to be an inline call rather than an actual function. Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-4-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index ea5cdbd8c2c3..fc3adc51254a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -34,6 +34,24 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifdef CONFIG_HIGHMEM #include +#ifndef ARCH_HAS_KMAP_FLUSH_TLB +static inline void kmap_flush_tlb(unsigned long addr) { } +#endif + +void *kmap_high(struct page *page); +static inline void *kmap(struct page *page) +{ + void *addr; + + might_sleep(); + if (!PageHighMem(page)) + addr = page_address(page); + else + addr = kmap_high(page); + kmap_flush_tlb((unsigned long)addr); + return addr; +} + /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); extern atomic_long_t _totalhigh_pages; -- cgit v1.2.3 From e23c45976f82ac789469c37e4d5a72ea2ce30bba Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:34 -0700 Subject: arch/kunmap: remove duplicate kunmap implementations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All architectures do exactly the same thing for kunmap(); remove all the duplicate definitions and lift the call to the core. This also has the benefit of changing kmap_unmap() on a number of architectures to be an inline call rather than an actual function. [akpm@linux-foundation.org: fix CONFIG_HIGHMEM=n build on various architectures] Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-5-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index fc3adc51254a..216a647ed7db 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -52,6 +52,16 @@ static inline void *kmap(struct page *page) return addr; } +void kunmap_high(struct page *page); + +static inline void kunmap(struct page *page) +{ + might_sleep(); + if (!PageHighMem(page)) + return; + kunmap_high(page); +} + /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); extern atomic_long_t _totalhigh_pages; @@ -102,6 +112,10 @@ static inline void *kmap(struct page *page) return page_address(page); } +static inline void kunmap_high(struct page *page) +{ +} + static inline void kunmap(struct page *page) { } -- cgit v1.2.3 From 78b6d91ec7bbfc5bcc2dd05bb2cf13c9de1dc7cd Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:42 -0700 Subject: arch/kmap_atomic: consolidate duplicate code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Every arch has the same code to ensure atomic operations and a check for !HIGHMEM page. Remove the duplicate code by defining a core kmap_atomic() which only calls the arch specific kmap_atomic_high() when the page is high memory. [akpm@linux-foundation.org: coding style fixes] Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-7-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 216a647ed7db..d2209ae8be99 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -32,6 +32,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #include #ifdef CONFIG_HIGHMEM +extern void *kmap_atomic_high(struct page *page); #include #ifndef ARCH_HAS_KMAP_FLUSH_TLB @@ -62,6 +63,28 @@ static inline void kunmap(struct page *page) kunmap_high(page); } +/* + * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because + * no global lock is needed and because the kmap code must perform a global TLB + * invalidation when the kmap pool wraps. + * + * However when holding an atomic kmap is is not legal to sleep, so atomic + * kmaps are appropriate for short, tight code paths only. + * + * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap + * gives a more generic (and caching) interface. But kmap_atomic can + * be used in IRQ contexts, so in some (very limited) cases we need + * it. + */ +static inline void *kmap_atomic(struct page *page) +{ + preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); + return kmap_atomic_high(page); +} + /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); extern atomic_long_t _totalhigh_pages; -- cgit v1.2.3 From abca2500c0c1b20c3e552f259da4c4a99db3b4d1 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:46 -0700 Subject: arch/kunmap_atomic: consolidate duplicate code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Every single architecture (including !CONFIG_HIGHMEM) calls... pagefault_enable(); preempt_enable(); ... before returning from __kunmap_atomic(). Lift this code into the kunmap_atomic() macro. While we are at it rename __kunmap_atomic() to kunmap_atomic_high() to be consistent. [ira.weiny@intel.com: don't enable pagefault/preempt twice] Link: http://lkml.kernel.org/r/20200518184843.3029640-1-ira.weiny@intel.com [akpm@linux-foundation.org: coding style fixes] Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Guenter Roeck Link: http://lkml.kernel.org/r/20200507150004.1423069-8-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index d2209ae8be99..945b58d8a57b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -33,6 +33,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifdef CONFIG_HIGHMEM extern void *kmap_atomic_high(struct page *page); +extern void kunmap_atomic_high(void *kvaddr); #include #ifndef ARCH_HAS_KMAP_FLUSH_TLB @@ -151,10 +152,12 @@ static inline void *kmap_atomic(struct page *page) } #define kmap_atomic_prot(page, prot) kmap_atomic(page) -static inline void __kunmap_atomic(void *addr) +static inline void kunmap_atomic_high(void *addr) { - pagefault_enable(); - preempt_enable(); + /* + * Nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic() + * handles re-enabling faults + preemption + */ } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) @@ -204,7 +207,9 @@ static inline void kmap_atomic_idx_pop(void) #define kunmap_atomic(addr) \ do { \ BUILD_BUG_ON(__same_type((addr), struct page *)); \ - __kunmap_atomic(addr); \ + kunmap_atomic_high(addr); \ + pagefault_enable(); \ + preempt_enable(); \ } while (0) -- cgit v1.2.3 From 20b271dfe9d932b02b067a1f7ba9805c5b8d79bd Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:58 -0700 Subject: arch/kmap: define kmap_atomic_prot() for all arch's MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To support kmap_atomic_prot(), all architectures need to support protections passed to their kmap_atomic_high() function. Pass protections into kmap_atomic_high() and change the name to kmap_atomic_high_prot() to match. Then define kmap_atomic_prot() as a core function which calls kmap_atomic_high_prot() when needed. Finally, redefine kmap_atomic() as a wrapper of kmap_atomic_prot() with the default kmap_prot exported by the architectures. Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-11-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 945b58d8a57b..9c559c670299 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -32,7 +32,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #include #ifdef CONFIG_HIGHMEM -extern void *kmap_atomic_high(struct page *page); +extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot); extern void kunmap_atomic_high(void *kvaddr); #include @@ -77,14 +77,15 @@ static inline void kunmap(struct page *page) * be used in IRQ contexts, so in some (very limited) cases we need * it. */ -static inline void *kmap_atomic(struct page *page) +static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); - return kmap_atomic_high(page); + return kmap_atomic_high_prot(page, prot); } +#define kmap_atomic(page) kmap_atomic_prot(page, kmap_prot) /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); -- cgit v1.2.3 From 7438f36310ddd9fe536fc7403187f63427cecaba Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:48:10 -0700 Subject: parisc/kmap: remove duplicate kmap code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit parisc reimplements the kmap calls except to flush its dcache. This is arguably an abuse of kmap but regardless it is messy and confusing. Remove the duplicate code and have parisc define ARCH_HAS_FLUSH_ON_KUNMAP for a kunmap_flush_on_unmap() architecture specific call to flush the cache. Suggested-by: Al Viro Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Christoph Hellwig Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-14-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 9c559c670299..091b32dff2d1 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -130,7 +130,6 @@ static inline struct page *kmap_to_page(void *addr) static inline unsigned long totalhigh_pages(void) { return 0UL; } -#ifndef ARCH_HAS_KMAP static inline void *kmap(struct page *page) { might_sleep(); @@ -143,6 +142,9 @@ static inline void kunmap_high(struct page *page) static inline void kunmap(struct page *page) { +#ifdef ARCH_HAS_FLUSH_ON_KUNMAP + kunmap_flush_on_unmap(page_address(page)); +#endif } static inline void *kmap_atomic(struct page *page) @@ -156,15 +158,17 @@ static inline void *kmap_atomic(struct page *page) static inline void kunmap_atomic_high(void *addr) { /* - * Nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic() + * Mostly nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic() * handles re-enabling faults + preemption */ +#ifdef ARCH_HAS_FLUSH_ON_KUNMAP + kunmap_flush_on_unmap(addr); +#endif } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) #define kmap_flush_unused() do {} while(0) -#endif #endif /* CONFIG_HIGHMEM */ -- cgit v1.2.3 From 090e77e166334b83f555de408df64b9ab394ea08 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:48:18 -0700 Subject: kmap: consolidate kmap_prot definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Most architectures define kmap_prot to be PAGE_KERNEL. Let sparc and xtensa define there own and define PAGE_KERNEL as the default if not overridden. [akpm@linux-foundation.org: coding style fixes] Suggested-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-16-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 091b32dff2d1..d6e82e3de027 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -40,6 +40,10 @@ extern void kunmap_atomic_high(void *kvaddr); static inline void kmap_flush_tlb(unsigned long addr) { } #endif +#ifndef kmap_prot +#define kmap_prot PAGE_KERNEL +#endif + void *kmap_high(struct page *page); static inline void *kmap(struct page *page) { -- cgit v1.2.3 From d4eaa2837851db2bfed572898bfc17f9a9f9151e Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 4 Jun 2020 16:48:21 -0700 Subject: mm: add kvfree_sensitive() for freeing sensitive data objects For kvmalloc'ed data object that contains sensitive information like cryptographic keys, we need to make sure that the buffer is always cleared before freeing it. Using memset() alone for buffer clearing may not provide certainty as the compiler may compile it away. To be sure, the special memzero_explicit() has to be used. This patch introduces a new kvfree_sensitive() for freeing those sensitive data objects allocated by kvmalloc(). The relevant places where kvfree_sensitive() can be used are modified to use it. Fixes: 4f0882491a14 ("KEYS: Avoid false positive ENOMEM error on key read") Suggested-by: Linus Torvalds Signed-off-by: Waiman Long Signed-off-by: Andrew Morton Reviewed-by: Eric Biggers Acked-by: David Howells Cc: Jarkko Sakkinen Cc: James Morris Cc: "Serge E. Hallyn" Cc: Joe Perches Cc: Matthew Wilcox Cc: David Rientjes Cc: Uladzislau Rezki Link: http://lkml.kernel.org/r/20200407200318.11711-1-longman@redhat.com Signed-off-by: Linus Torvalds --- 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 e220ce5185ad..5bfc36320e3c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -776,6 +776,7 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) } extern void kvfree(const void *addr); +extern void kvfree_sensitive(const void *addr, size_t len); /* * Mapcount of compound page as a whole, does not include mapped sub-pages. -- cgit v1.2.3 From 04f3465c98665b7c5a3484d7194f1858954069f5 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 4 Jun 2020 16:48:31 -0700 Subject: mm/memory_hotplug: remove is_mem_section_removable() Fortunately, all users of is_mem_section_removable() are gone. Get rid of it, including some now unnecessary functions. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Wei Yang Reviewed-by: Baoquan He Acked-by: Michal Hocko Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Oscar Salvador Link: http://lkml.kernel.org/r/20200407135416.24093-3-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 93d9ada74ddd..7dca9cd6076b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -314,19 +314,12 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} #ifdef CONFIG_MEMORY_HOTREMOVE -extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int remove_memory(int nid, u64 start, u64 size); extern void __remove_memory(int nid, u64 start, u64 size); #else -static inline bool is_mem_section_removable(unsigned long pfn, - unsigned long nr_pages) -{ - return false; -} - static inline void try_offline_node(int nid) {} static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) -- cgit v1.2.3 From 7b7b27214bba1966772f9213cd2d8e5d67f8487f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 4 Jun 2020 16:48:41 -0700 Subject: mm/memory_hotplug: introduce add_memory_driver_managed() Patch series "mm/memory_hotplug: Interface to add driver-managed system ram", v4. kexec (via kexec_load()) can currently not properly handle memory added via dax/kmem, and will have similar issues with virtio-mem. kexec-tools will currently add all memory to the fixed-up initial firmware memmap. In case of dax/kmem, this means that - in contrast to a proper reboot - how that persistent memory will be used can no longer be configured by the kexec'd kernel. In case of virtio-mem it will be harmful, because that memory might contain inaccessible pieces that require coordination with hypervisor first. In both cases, we want to let the driver in the kexec'd kernel handle detecting and adding the memory, like during an ordinary reboot. Introduce add_memory_driver_managed(). More on the samentics are in patch #1. In the future, we might want to make this behavior configurable for dax/kmem- either by configuring it in the kernel (which would then also allow to configure kexec_file_load()) or in kexec-tools by also adding "System RAM (kmem)" memory from /proc/iomem to the fixed-up initial firmware memmap. More on the motivation can be found in [1] and [2]. [1] https://lkml.kernel.org/r/20200429160803.109056-1-david@redhat.com [2] https://lkml.kernel.org/r/20200430102908.10107-1-david@redhat.com This patch (of 3): Some device drivers rely on memory they managed to not get added to the initial (firmware) memmap as system RAM - so it's not used as initial system RAM by the kernel and the driver is under control. While this is the case during cold boot and after a reboot, kexec is not aware of that and might add such memory to the initial (firmware) memmap of the kexec kernel. We need ways to teach kernel and userspace that this system ram is different. For example, dax/kmem allows to decide at runtime if persistent memory is to be used as system ram. Another future user is virtio-mem, which has to coordinate with its hypervisor to deal with inaccessible parts within memory resources. We want to let users in the kernel (esp. kexec) but also user space (esp. kexec-tools) know that this memory has different semantics and needs to be handled differently: 1. Don't create entries in /sys/firmware/memmap/ 2. Name the memory resource "System RAM ($DRIVER)" (exposed via /proc/iomem) ($DRIVER might be "kmem", "virtio_mem"). 3. Flag the memory resource IORESOURCE_MEM_DRIVER_MANAGED /sys/firmware/memmap/ [1] represents the "raw firmware-provided memory map" because "on most architectures that firmware-provided memory map is modified afterwards by the kernel itself". The primary user is kexec on x86-64. Since commit d96ae5309165 ("memory-hotplug: create /sys/firmware/memmap entry for new memory"), we add all hotplugged memory to that firmware memmap - which makes perfect sense for traditional memory hotplug on x86-64, where real HW will also add hotplugged DIMMs to the firmware memmap. We replicate what the "raw firmware-provided memory map" looks like after hot(un)plug. To keep things simple, let the user provide the full resource name instead of only the driver name - this way, we don't have to manually allocate/craft strings for memory resources. Also use the resource name to make decisions, to avoid passing additional flags. In case the name isn't "System RAM", it's special. We don't have to worry about firmware_map_remove() on the removal path. If there is no entry, it will simply return with -EINVAL. We'll adapt dax/kmem in a follow-up patch. [1] https://www.kernel.org/doc/Documentation/ABI/testing/sysfs-firmware-memmap Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Acked-by: Pankaj Gupta Cc: Michal Hocko Cc: Pankaj Gupta Cc: Wei Yang Cc: Baoquan He Cc: Dave Hansen Cc: Eric Biederman Cc: Pavel Tatashin Cc: Dan Williams Link: http://lkml.kernel.org/r/20200508084217.9160-1-david@redhat.com Link: http://lkml.kernel.org/r/20200508084217.9160-3-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 1 + include/linux/memory_hotplug.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index a9b9170b5dd2..cc9a5b4593ca 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -103,6 +103,7 @@ struct resource { #define IORESOURCE_MEM_32BIT (3<<3) #define IORESOURCE_MEM_SHADOWABLE (1<<5) /* dup: IORESOURCE_SHADOWABLE */ #define IORESOURCE_MEM_EXPANSIONROM (1<<6) +#define IORESOURCE_MEM_DRIVER_MANAGED (1<<7) /* PnP I/O specific bits (IORESOURCE_BITS) */ #define IORESOURCE_IO_16BIT_ADDR (1<<0) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7dca9cd6076b..fee7fab5d706 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -342,6 +342,8 @@ extern void __ref free_area_init_core_hotplug(int nid); extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource); +extern int add_memory_driver_managed(int nid, u64 start, u64 size, + const char *resource_name); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern void remove_pfn_range_from_zone(struct zone *zone, -- cgit v1.2.3 From 57e86fa16a707db9e05dec77eb88a398f05a022b Mon Sep 17 00:00:00 2001 From: chenqiwu Date: Thu, 4 Jun 2020 16:48:55 -0700 Subject: mm: replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") [akpm@linux-foundation.org: fix build] Signed-off-by: chenqiwu Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Reviewed-by: Wei Yang Cc: Matthew Wilcox Cc: David Hildenbrand Cc: Michal Hocko Cc: Pankaj Gupta Cc: Yang Shi Cc: Qian Cai Cc: Baoquan He Link: http://lkml.kernel.org/r/1586599916-15456-1-git-send-email-qiwuchen55@gmail.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5bfc36320e3c..1744081a34d4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1726,7 +1726,7 @@ struct frame_vector { unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ - void *ptrs[0]; /* Array of pinned pfns / pages. Use + void *ptrs[]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; -- cgit v1.2.3 From 2b7874490243e014112100925405c4a17a8c40aa Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 4 Jun 2020 16:49:49 -0700 Subject: include/linux/mm.h: return true in cpupid_pid_unset() Fix the following coccicheck warning: include/linux/mm.h:1371:8-9: WARNING: return of 0/1 in function 'cpupid_pid_unset' with return type bool Signed-off-by: Jason Yan Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200422071816.48879-1-yanaijie@huawei.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1744081a34d4..86adc71a972f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1373,7 +1373,7 @@ static inline int cpu_pid_to_cpupid(int nid, int pid) static inline bool cpupid_pid_unset(int cpupid) { - return 1; + return true; } static inline void page_cpupid_reset_last(struct page *page) -- cgit v1.2.3 From bd93f003b7462ae39a43c531abca37fe7073b866 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 4 Jun 2020 16:50:30 -0700 Subject: include/linux/bitops.h: avoid clang shift-count-overflow warnings Clang normally does not warn about certain issues in inline functions when it only happens in an eliminated code path. However if something else goes wrong, it does tend to complain about the definition of hweight_long() on 32-bit targets: include/linux/bitops.h:75:41: error: shift count >= width of type [-Werror,-Wshift-count-overflow] return sizeof(w) == 4 ? hweight32(w) : hweight64(w); ^~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:29:49: note: expanded from macro 'hweight64' define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) ^~~~~~~~~~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:21:76: note: expanded from macro '__const_hweight64' define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) ^ ~~ include/asm-generic/bitops/const_hweight.h:20:49: note: expanded from macro '__const_hweight32' define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) ^ include/asm-generic/bitops/const_hweight.h:19:72: note: expanded from macro '__const_hweight16' define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) ^ include/asm-generic/bitops/const_hweight.h:12:9: note: expanded from macro '__const_hweight8' (!!((w) & (1ULL << 2))) + \ Adding an explicit cast to __u64 avoids that warning and makes it easier to read other output. Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Acked-by: Christian Brauner Cc: Andy Shevchenko Cc: Rasmus Villemoes Cc: Josh Poimboeuf Cc: Nick Desaulniers Link: http://lkml.kernel.org/r/20200505135513.65265-1-arnd@arndb.de Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 9acf654f0b19..99f2ac30b1d9 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -72,7 +72,7 @@ static inline int get_bitmask_order(unsigned int count) static __always_inline unsigned long hweight_long(unsigned long w) { - return sizeof(w) == 4 ? hweight32(w) : hweight64(w); + return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w); } /** -- cgit v1.2.3 From 51da9dfb7f20911ae4e79e9b412a9c2d4c373d4b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 4 Jun 2020 16:50:49 -0700 Subject: elfnote: mark all .note sections SHF_ALLOC ELFNOTE_START allows callers to specify flags for .pushsection assembler directives. All callsites but ELF_NOTE use "a" for SHF_ALLOC. For vdso's that explicitly use ELF_NOTE_START and BUILD_SALT, the same section is specified twice after preprocessing, once with "a" flag, once without. Example: .pushsection .note.Linux, "a", @note ; .pushsection .note.Linux, "", @note ; While GNU as allows this ordering, it warns for the opposite ordering, making these directives position dependent. We'd prefer not to precisely match this behavior in Clang's integrated assembler. Instead, the non __ASSEMBLY__ definition of ELF_NOTE uses __attribute__((section(".note.Linux"))) which is created with SHF_ALLOC, so let's make the __ASSEMBLY__ definition of ELF_NOTE consistent with C and just always use "a" flag. This allows Clang to assemble a working mainline (5.6) kernel via: $ make CC=clang AS=clang Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Reviewed-by: Nathan Chancellor Reviewed-by: Fangrui Song Cc: Jeremy Fitzhardinge Cc: Thomas Gleixner Cc: Vincenzo Frascino Link: https://github.com/ClangBuiltLinux/linux/issues/913 Link: http://lkml.kernel.org/r/20200325231250.99205-1-ndesaulniers@google.com Debugged-by: Ilie Halip Signed-off-by: Linus Torvalds --- include/linux/elfnote.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index 594d4e78654f..69b136e4dd2b 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -54,7 +54,7 @@ .popsection ; #define ELFNOTE(name, type, desc) \ - ELFNOTE_START(name, type, "") \ + ELFNOTE_START(name, type, "a") \ desc ; \ ELFNOTE_END -- cgit v1.2.3 From d2c0e6e91c7990c67921005f44f9b2b326ff2906 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 4 Jun 2020 16:51:05 -0700 Subject: include/linux/seq_file.h: introduce DEFINE_SEQ_ATTRIBUTE() helper macro Patch series "seq_file: Introduce DEFINE_SEQ_ATTRIBUTE() helper macro". As discussed in https://lore.kernel.org/lkml/20191129222310.GA3712618@kroah.com/, we could introduce a new helper macro to reduce losts of boilerplate code, vmstat and kprobes is the example which covert to use it, if this is accepted, I will send out more cleanups. This patch (of 3): Introduce DEFINE_SEQ_ATTRIBUTE() helper macro to decrease code duplication. [akpm@linux-foundation.org: coding style fixes] Signed-off-by: Kefeng Wang Signed-off-by: Andrew Morton Cc: Greg KH Cc: Ingo Molnar Cc: Kefeng Wang Cc: Anil S Keshavamurthy Cc: "David S. Miller" Cc: Masami Hiramatsu Cc: Al Viro Link: http://lkml.kernel.org/r/20200509064031.181091-1-wangkefeng.wang@huawei.com Link: http://lkml.kernel.org/r/20200509064031.181091-2-wangkefeng.wang@huawei.com Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 1672cf6f7614..813614d4b71f 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -145,6 +145,25 @@ void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); +#define DEFINE_SEQ_ATTRIBUTE(__name) \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + int ret = seq_open(file, &__name ## _sops); \ + if (!ret && inode->i_private) { \ + struct seq_file *seq_f = file->private_data; \ + seq_f->private = inode->i_private; \ + } \ + return ret; \ +} \ + \ +static const struct file_operations __name ## _fops = { \ + .owner = THIS_MODULE, \ + .open = __name ## _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = seq_release, \ +} + #define DEFINE_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ -- cgit v1.2.3 From 986db2d14a6dca6456b63b4f5c410ae2aab4ec9d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 4 Jun 2020 16:51:14 -0700 Subject: exec: simplify the copy_strings_kernel calling convention copy_strings_kernel is always used with a single argument, adjust the calling convention to that. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexander Viro Link: http://lkml.kernel.org/r/20200501104105.2621149-2-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index a345d9fed3d8..3d3afe094c97 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -144,8 +144,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, extern int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location); extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); -extern int copy_strings_kernel(int argc, const char *const *argv, - struct linux_binprm *bprm); +int copy_string_kernel(const char *arg, struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); -- cgit v1.2.3 From 5872f1a2e5c783783d51e96468f0ff6aede61182 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 11 May 2020 21:59:51 +0100 Subject: READ_ONCE: Fix comment describing 2x32-bit atomicity READ_ONCE() permits 64-bit accesses on 32-bit architectures, since this crops up in a few places and is generally harmless because either the upper bits are always zero (e.g. for a virtual address or 32-bit time_t) or the architecture provides 64-bit atomicity anyway. Update the corresponding comment above compiletime_assert_rwonce_type(), which incorrectly states that 32-bit x86 provides 64-bit atomicity, and instead reference 32-bit Armv7 with LPAE. Cc: Thomas Gleixner Cc: Peter Zijlstra Reported-by: Jann Horn Signed-off-by: Will Deacon --- include/linux/compiler.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c363d8debc43..657e4fd38a77 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -332,9 +332,9 @@ static inline void *offset_to_ptr(const int *off) /* * Yes, this permits 64-bit accesses on 32-bit architectures. These will - * actually be atomic in many cases (namely x86), but for others we rely on - * the access being split into 2x32-bit accesses for a 32-bit quantity (e.g. - * a virtual address) and a strong prevailing wind. + * actually be atomic in some cases (namely Armv7 + LPAE), but for others we + * rely on the access being split into 2x32-bit accesses for a 32-bit quantity + * (e.g. a virtual address) and a strong prevailing wind. */ #define compiletime_assert_rwonce_type(t) \ compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ -- cgit v1.2.3 From 8d4beed7bbc71666de2630b79899c8852c3bf5cd Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Jun 2020 11:05:51 +0100 Subject: compiler-types.h: Include naked type in __pick_integer_type() match __pick_integer_type() checks whether the type of its first argument is compatible with an explicitly signed or unsigned integer type, returning the compatible type if it exists. Unfortunately, 'char' is neither compatible with 'signed char' nor 'unsigned char', so add a check against the naked type to allow the __unqual_scalar_typeof() macro to strip qualifiers from char types without an explicit signedness. Reported-by: Rasmus Villemoes Signed-off-by: Will Deacon --- include/linux/compiler_types.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 233066c92f6f..6ed0612bc143 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -220,9 +220,14 @@ struct ftrace_likely_data { #define __pick_scalar_type(x, type, otherwise) \ __builtin_choose_expr(__same_type(x, type), (type)0, otherwise) +/* + * 'char' is not type-compatible with either 'signed char' or 'unsigned char', + * so we include the naked type here as well as the signed/unsigned variants. + */ #define __pick_integer_type(x, type, otherwise) \ - __pick_scalar_type(x, unsigned type, \ - __pick_scalar_type(x, signed type, otherwise)) + __pick_scalar_type(x, type, \ + __pick_scalar_type(x, unsigned type, \ + __pick_scalar_type(x, signed type, otherwise))) #define __unqual_scalar_typeof(x) typeof( \ __pick_integer_type(x, char, \ -- cgit v1.2.3 From b16d8ecf4fa17e16fff20638364f9bd2205615e7 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Jun 2020 11:19:46 +0100 Subject: compiler.h: Enforce that READ_ONCE_NOCHECK() access size is sizeof(long) READ_ONCE_NOCHECK() unconditionally performs a sizeof(long)-sized access, so enforce that the size of the pointed-to object that we are loading from is the same size as 'long'. Reported-by: Marco Elver Signed-off-by: Will Deacon --- include/linux/compiler.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 657e4fd38a77..a0aa56e6b782 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -254,9 +254,12 @@ unsigned long __read_once_word_nocheck(const void *addr) */ #define READ_ONCE_NOCHECK(x) \ ({ \ - unsigned long __x = __read_once_word_nocheck(&(x)); \ + unsigned long __x; \ + compiletime_assert(sizeof(x) == sizeof(__x), \ + "Unsupported access size for READ_ONCE_NOCHECK()."); \ + __x = __read_once_word_nocheck(&(x)); \ smp_read_barrier_depends(); \ - __x; \ + (typeof(x))__x; \ }) static __no_kasan_or_inline -- cgit v1.2.3 From 1fd76043ecb04b8567a76b106db09ac778e1e2b8 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 27 May 2020 12:32:36 +0200 Subject: compiler_types.h: Optimize __unqual_scalar_typeof compilation time If the compiler supports C11's _Generic, use it to speed up compilation times of __unqual_scalar_typeof(). GCC version 4.9 or later and all supported versions of Clang support the feature (the oldest supported compiler that doesn't support _Generic is GCC 4.8, for which we use the slower alternative). The non-_Generic variant relies on multiple expansions of __pick_integer_type -> __pick_scalar_type -> __builtin_choose_expr, which increases pre-processed code size, and can cause compile times to increase in files with numerous expansions of READ_ONCE(), or other users of __unqual_scalar_typeof(). Summary of compile-time benchmarking done by Arnd Bergmann: clang-11 gcc-9 this patch 0.78 0.91 ideal 0.76 0.86 See https://lkml.kernel.org/r/CAK8P3a3UYQeXhiufUevz=rwe09WM_vSTCd9W+KvJHJcOeQyWVA@mail.gmail.com Further compile-testing done with: gcc 4.8, 4.9, 5.5, 6.4, 7.5, 8.4; clang 9, 10. Reported-by: Arnd Bergmann Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra Tested-by: Arnd Bergmann Link: https://lkml.kernel.org/r/20200527103236.148700-1-elver@google.com Link: https://lkml.kernel.org/r/CAK8P3a0RJtbVi1JMsfik=jkHCNFv+DJn_FeDg-YLW+ueQW3tNg@mail.gmail.com [will: tweak new macros to make them a bit more readable] Signed-off-by: Will Deacon --- include/linux/compiler_types.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6ed0612bc143..31416b60eabf 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -213,7 +213,9 @@ struct ftrace_likely_data { /* * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving * non-scalar types unchanged. - * + */ +#if defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900 +/* * We build this out of a couple of helper macros in a vain attempt to * help you keep your lunch down while reading it. */ @@ -235,6 +237,25 @@ struct ftrace_likely_data { __pick_integer_type(x, int, \ __pick_integer_type(x, long, \ __pick_integer_type(x, long long, x)))))) +#else +/* + * If supported, prefer C11 _Generic for better compile-times. As above, 'char' + * is not type-compatible with 'signed char', and we define a separate case. + */ +#define __scalar_type_to_expr_cases(type) \ + unsigned type: (unsigned type)0, \ + signed type: (signed type)0 + +#define __unqual_scalar_typeof(x) typeof( \ + _Generic((x), \ + char: (char)0, \ + __scalar_type_to_expr_cases(char), \ + __scalar_type_to_expr_cases(short), \ + __scalar_type_to_expr_cases(int), \ + __scalar_type_to_expr_cases(long), \ + __scalar_type_to_expr_cases(long long), \ + default: (x))) +#endif /* Is this type a native word size -- useful for atomic operations */ #define __native_word(t) \ -- cgit v1.2.3 From b398ace5d2ea0b7f00d9f1ce23c647e289c206ca Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 28 May 2020 09:43:13 +0200 Subject: compiler_types.h: Use unoptimized __unqual_scalar_typeof for sparse If the file is being checked with sparse, use the unoptimized version of __unqual_scalar_typeof(), since sparse does not support _Generic. Reported-by: kbuild test robot Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/202005280727.lXn1VnTw%lkp@intel.com Signed-off-by: Will Deacon --- include/linux/compiler_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 31416b60eabf..cd73e3857a87 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -214,7 +214,7 @@ struct ftrace_likely_data { * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving * non-scalar types unchanged. */ -#if defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900 +#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900) || defined(__CHECKER__) /* * We build this out of a couple of helper macros in a vain attempt to * help you keep your lunch down while reading it. -- cgit v1.2.3 From cf6fada71543ceea0f6228ffdc0b85778f3f5a6e Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Sat, 30 May 2020 10:08:30 +0800 Subject: cpufreq: change '.set_boost' to act on one policy Macro 'for_each_active_policy()' is defined internally. To avoid some cpufreq driver needing this macro to iterate over all the policies in '.set_boost' callback, we redefine '.set_boost' to act on only one policy and pass the policy as an argument. 'cpufreq_boost_trigger_state()' iterates over all the policies to set boost for the system. This is preparation for adding SW BOOST support for CPPC. To protect Boost enable/disable by sysfs from CPU online/offline, add 'cpu_hotplug_lock' before calling '.set_boost' for each CPU. Also move the lock from 'set_boost()' to 'store_cpb()' in acpi_cpufreq. Signed-off-by: Xiongfeng Wang Suggested-by: Viresh Kumar Acked-by: Viresh Kumar [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 67d5950bd878..3494f6763597 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -367,7 +367,7 @@ struct cpufreq_driver { /* platform specific boost support code */ bool boost_enabled; - int (*set_boost)(int state); + int (*set_boost)(struct cpufreq_policy *policy, int state); }; /* flags */ -- cgit v1.2.3 From 33a180623b6c35f2727daecb63763955af3af1df Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 2 Jun 2020 15:34:40 +0200 Subject: dm bufio: introduce forget_buffer_locked Introduce a function forget_buffer_locked that forgets a range of buffers. It is more efficient than calling forget_buffer in a loop. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-bufio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 5ec6bfbde9ae..29d255fdd5d6 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -136,6 +136,13 @@ void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block); */ void dm_bufio_forget(struct dm_bufio_client *c, sector_t block); +/* + * Free the given range of buffers. + * This is just a hint, if the buffer is in use or dirty, this function + * does nothing. + */ +void dm_bufio_forget_buffers(struct dm_bufio_client *c, sector_t block, sector_t n_blocks); + /* * Set the minimum number of buffers before cleanup happens. */ -- cgit v1.2.3 From 90c56b3877995d948dc382fe833a1c5eeaaee2ad Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Jun 2020 07:21:22 -0700 Subject: net: ethtool: Fix comment mentioning typo in IS_ENABLED() This has no code changes, but it's a typo noticed in other clean-ups, so we might as well fix it. IS_ENABLED() takes full names, and should have the "CONFIG_" prefix. Reported-by: Joe Perches Link: https://lore.kernel.org/lkml/b08611018fdb6d88757c6008a5c02fa0e07b32fb.camel@perches.com Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 8fbe4f97ffad..1e7bf78cb382 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -67,5 +67,5 @@ static inline int ethnl_cable_test_step(struct phy_device *phydev, u32 first, { return -EOPNOTSUPP; } -#endif /* IS_ENABLED(ETHTOOL_NETLINK) */ +#endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ -- cgit v1.2.3 From 46f21af862656c477387f2256adc1005503db67d Mon Sep 17 00:00:00 2001 From: Wesley Sheng Date: Tue, 26 May 2020 15:59:43 +0800 Subject: NTB: correct ntb_peer_spad_addr and ntb_peer_spad_read comment typos The comment for ntb_peer_spad_addr and ntb_peer_spad_read incorrectly referred to peer doorbell register and local scratchpad register. Signed-off-by: Wesley Sheng Signed-off-by: Jon Mason --- include/linux/ntb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index a07252f78770..191b524e5c0d 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -1351,7 +1351,7 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val) * @sidx: Scratchpad index. * @spad_addr: OUT - The address of the peer scratchpad register. * - * Return the address of the peer doorbell register. This may be used, for + * Return the address of the peer scratchpad register. This may be used, for * example, by drivers that offload memory copy operations to a dma engine. * * Return: Zero on success, otherwise an error number. @@ -1373,7 +1373,7 @@ static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, * * Read the peer scratchpad register, and return the value. * - * Return: The value of the local scratchpad register. + * Return: The value of the peer scratchpad register. */ static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { -- cgit v1.2.3 From f5152f4ded3ce6d332d5e4f9d7e325c3b81cae1b Mon Sep 17 00:00:00 2001 From: Erwan Velu Date: Sat, 6 Jun 2020 11:35:50 +0200 Subject: firmware/dmi: Report DMI Bios & EC firmware release Some vendors like HPe or Dell, encode the release version of their BIOS in the "System BIOS {Major|Minor} Release" fields of Type 0. This information is used to know which bios release actually runs. It could be used for some quirks, debugging sessions or inventory tasks. A typical output for a Dell system running the 65.27 bios is : [root@t1700 ~]# cat /sys/devices/virtual/dmi/id/bios_release 65.27 [root@t1700 ~]# Servers that have a BMC encode the release version of their firmware in the "Embedded Controller Firmware {Major|Minor} Release" fields of Type 0. This information is used to know which BMC release actually runs. It could be used for some quirks, debugging sessions or inventory tasks. A typical output for a Dell system running the 3.75 bmc release is : [root@t1700 ~]# cat /sys/devices/virtual/dmi/id/ec_firmware_release 3.75 [root@t1700 ~]# Signed-off-by: Erwan Velu Signed-off-by: Jean Delvare --- include/linux/mod_devicetable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4c2ddd0941a7..4b3d0a4945df 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -532,6 +532,8 @@ enum dmi_field { DMI_BIOS_VENDOR, DMI_BIOS_VERSION, DMI_BIOS_DATE, + DMI_BIOS_RELEASE, + DMI_EC_FIRMWARE_RELEASE, DMI_SYS_VENDOR, DMI_PRODUCT_NAME, DMI_PRODUCT_VERSION, -- cgit v1.2.3 From 7ff0d4490ebadae8037a079a70c5cac13385a808 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 3 Jun 2020 07:52:37 +0200 Subject: trace: fix an incorrect __user annotation on stack_trace_sysctl No user pointers for sysctls anymore. Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Reported-by: build test robot Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/ftrace.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ddfc377de0d2..fce81238f304 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -319,9 +319,8 @@ static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, extern int stack_tracer_enabled; -int stack_trace_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ DECLARE_PER_CPU(int, disable_stack_tracer); -- cgit v1.2.3 From e1eb26fa62d04ec0955432be1aa8722a97cb52e7 Mon Sep 17 00:00:00 2001 From: Giuseppe Scrivano Date: Sun, 7 Jun 2020 21:40:10 -0700 Subject: ipc/namespace.c: use a work queue to free_ipc the reason is to avoid a delay caused by the synchronize_rcu() call in kern_umount() when the mqueue mount is freed. the code: #define _GNU_SOURCE #include #include #include #include int main() { int i; for (i = 0; i < 1000; i++) if (unshare(CLONE_NEWIPC) < 0) error(EXIT_FAILURE, errno, "unshare"); } goes from Command being timed: "./ipc-namespace" User time (seconds): 0.00 System time (seconds): 0.06 Percent of CPU this job got: 0% Elapsed (wall clock) time (h:mm:ss or m:ss): 0:08.05 to Command being timed: "./ipc-namespace" User time (seconds): 0.00 System time (seconds): 0.02 Percent of CPU this job got: 96% Elapsed (wall clock) time (h:mm:ss or m:ss): 0:00.03 Signed-off-by: Giuseppe Scrivano Signed-off-by: Andrew Morton Reviewed-by: Paul E. McKenney Reviewed-by: Waiman Long Cc: Davidlohr Bueso Cc: Manfred Spraul Link: http://lkml.kernel.org/r/20200225145419.527994-1-gscrivan@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index c309f43bde45..a06a78c67f19 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -68,6 +68,8 @@ struct ipc_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; + struct llist_node mnt_llist; + struct ns_common ns; } __randomize_layout; -- cgit v1.2.3 From ceabef7dd71720aef58bd182943352c9c307a3de Mon Sep 17 00:00:00 2001 From: Orson Zhai Date: Sun, 7 Jun 2020 21:40:14 -0700 Subject: dynamic_debug: add an option to enable dynamic debug for modules only Instead of enabling dynamic debug globally with CONFIG_DYNAMIC_DEBUG, CONFIG_DYNAMIC_DEBUG_CORE will only enable core function of dynamic debug. With the DYNAMIC_DEBUG_MODULE defined for any modules, dynamic debug will be tied to them. This is useful for people who only want to enable dynamic debug for kernel modules without worrying about kernel image size and memory consumption is increasing too much. [orson.zhai@unisoc.com: v2] Link: http://lkml.kernel.org/r/1587408228-10861-1-git-send-email-orson.unisoc@gmail.com Signed-off-by: Orson Zhai Signed-off-by: Andrew Morton Acked-by: Greg Kroah-Hartman Acked-by: Petr Mladek Cc: Jonathan Corbet Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Jason Baron Cc: Randy Dunlap Link: http://lkml.kernel.org/r/1586521984-5890-1-git-send-email-orson.unisoc@gmail.com Signed-off-by: Linus Torvalds --- include/linux/dev_printk.h | 6 ++++-- include/linux/dynamic_debug.h | 2 +- include/linux/net.h | 3 ++- include/linux/netdevice.h | 6 ++++-- include/linux/printk.h | 9 ++++++--- 5 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 5aad06b4ca7b..3028b644b4fb 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -109,7 +109,8 @@ void _dev_info(const struct device *dev, const char *fmt, ...) #define dev_info(dev, fmt, ...) \ _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define dev_dbg(dev, fmt, ...) \ dynamic_dev_dbg(dev, dev_fmt(fmt), ##__VA_ARGS__) #elif defined(DEBUG) @@ -181,7 +182,8 @@ do { \ 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) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define dev_dbg_ratelimited(dev, fmt, ...) \ do { \ diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 4cf02ecd67de..abcd5fde30eb 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -48,7 +48,7 @@ struct _ddebug { -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG_CORE) int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname); extern int ddebug_remove_module(const char *mod_name); diff --git a/include/linux/net.h b/include/linux/net.h index e10f378194a5..016a9c5faa34 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -264,7 +264,8 @@ do { \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define net_dbg_ratelimited(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a96e9c4ec36..5b364a2e0006 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4942,7 +4942,8 @@ do { \ #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define netdev_dbg(__dev, format, args...) \ do { \ dynamic_netdev_dbg(__dev, format, ##args); \ @@ -5012,7 +5013,8 @@ do { \ #define netif_info(priv, type, dev, fmt, args...) \ netif_level(info, priv, type, dev, fmt, ##args) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define netif_dbg(priv, type, netdev, format, args...) \ do { \ if (netif_msg_##type(priv)) \ diff --git a/include/linux/printk.h b/include/linux/printk.h index 3cc2f178bf06..fc8f03c54543 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -399,7 +399,8 @@ extern int kptr_restrict; /* If you are writing a driver, please use dev_dbg instead */ -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #include /** @@ -535,7 +536,8 @@ extern int kptr_restrict; #endif /* If you are writing a driver, please use dev_dbg instead */ -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define pr_debug_ratelimited(fmt, ...) \ do { \ @@ -582,7 +584,8 @@ static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, #endif -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ -- cgit v1.2.3 From db38d5c106dfdd7cb7207c83267d82fdf4950b61 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Sun, 7 Jun 2020 21:40:17 -0700 Subject: kernel: add panic_on_taint Analogously to the introduction of panic_on_warn, this patch introduces a kernel option named panic_on_taint in order to provide a simple and generic way to stop execution and catch a coredump when the kernel gets tainted by any given flag. This is useful for debugging sessions as it avoids having to rebuild the kernel to explicitly add calls to panic() into the code sites that introduce the taint flags of interest. For instance, if one is interested in proceeding with a post-mortem analysis at the point a given code path is hitting a bad page (i.e. unaccount_page_cache_page(), or slab_bug()), a coredump can be collected by rebooting the kernel with 'panic_on_taint=0x20' amended to the command line. Another, perhaps less frequent, use for this option would be as a means for assuring a security policy case where only a subset of taints, or no single taint (in paranoid mode), is allowed for the running system. The optional switch 'nousertaint' is handy in this particular scenario, as it will avoid userspace induced crashes by writes to sysctl interface /proc/sys/kernel/tainted causing false positive hits for such policies. [akpm@linux-foundation.org: tweak kernel-parameters.txt wording] Suggested-by: Qian Cai Signed-off-by: Rafael Aquini Signed-off-by: Andrew Morton Reviewed-by: Luis Chamberlain Cc: Dave Young Cc: Baoquan He Cc: Jonathan Corbet Cc: Kees Cook Cc: Randy Dunlap Cc: "Theodore Ts'o" Cc: Adrian Bunk Cc: Greg Kroah-Hartman Cc: Laura Abbott Cc: Jeff Mahoney Cc: Jiri Kosina Cc: Takashi Iwai Link: http://lkml.kernel.org/r/20200515175502.146720-1-aquini@redhat.com Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 9b7a8d74a9d6..f7835db7102e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -528,6 +528,8 @@ extern int panic_on_oops; extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int panic_on_warn; +extern unsigned long panic_on_taint; +extern bool panic_on_taint_nousertaint; extern int sysctl_panic_on_rcu_stall; extern int sysctl_panic_on_stackoverflow; @@ -596,6 +598,7 @@ extern enum system_states { #define TAINT_AUX 16 #define TAINT_RANDSTRUCT 17 #define TAINT_FLAGS_COUNT 18 +#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) struct taint_flag { char c_true; /* character printed when tainted */ -- cgit v1.2.3 From 01f39c1c11ee5bf44a1df49e47eb53a86515b9dc Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Sun, 7 Jun 2020 21:40:20 -0700 Subject: xarray.h: correct return code documentation for xa_store_{bh,irq}() __xa_store() and xa_store() document that the functions can fail, and that the return code can be an xa_err() encoded error code. xa_store_bh() and xa_store_irq() do not document that the functions can fail and that they can also return xa_err() encoded error codes. Thus: Update the documentation. Signed-off-by: Manfred Spraul Signed-off-by: Andrew Morton Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200430111424.16634-1-manfred@colorfullife.com Signed-off-by: Linus Torvalds --- include/linux/xarray.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 14c893433139..b4d70e7568b2 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -576,7 +576,7 @@ void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. - * Return: The entry which used to be at this index. + * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) @@ -602,7 +602,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. - * Return: The entry which used to be at this index. + * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) -- cgit v1.2.3 From 3db978d480e2843979a2b56f2f7da726f2b295b2 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Sun, 7 Jun 2020 21:40:24 -0700 Subject: kernel/sysctl: support setting sysctl parameters from kernel command line Patch series "support setting sysctl parameters from kernel command line", v3. This series adds support for something that seems like many people always wanted but nobody added it yet, so here's the ability to set sysctl parameters via kernel command line options in the form of sysctl.vm.something=1 The important part is Patch 1. The second, not so important part is an attempt to clean up legacy one-off parameters that do the same thing as a sysctl. I don't want to remove them completely for compatibility reasons, but with generic sysctl support the idea is to remove the one-off param handlers and treat the parameters as aliases for the sysctl variants. I have identified several parameters that mention sysctl counterparts in Documentation/admin-guide/kernel-parameters.txt but there might be more. The conversion also has varying level of success: - numa_zonelist_order is converted in Patch 2 together with adding the necessary infrastructure. It's easy as it doesn't really do anything but warn on deprecated value these days. - hung_task_panic is converted in Patch 3, but there's a downside that now it only accepts 0 and 1, while previously it was any integer value - nmi_watchdog maps to two sysctls nmi_watchdog and hardlockup_panic, so there's no straighforward conversion possible - traceoff_on_warning is a flag without value and it would be required to handle that somehow in the conversion infractructure, which seems pointless for a single flag This patch (of 5): A recently proposed patch to add vm_swappiness command line parameter in addition to existing sysctl [1] made me wonder why we don't have a general support for passing sysctl parameters via command line. Googling found only somebody else wondering the same [2], but I haven't found any prior discussion with reasons why not to do this. Settings the vm_swappiness issue aside (the underlying issue might be solved in a different way), quick search of kernel-parameters.txt shows there are already some that exist as both sysctl and kernel parameter - hung_task_panic, nmi_watchdog, numa_zonelist_order, traceoff_on_warning. A general mechanism would remove the need to add more of those one-offs and might be handy in situations where configuration by e.g. /etc/sysctl.d/ is impractical. Hence, this patch adds a new parse_args() pass that looks for parameters prefixed by 'sysctl.' and tries to interpret them as writes to the corresponding sys/ files using an temporary in-kernel procfs mount. This mechanism was suggested by Eric W. Biederman [3], as it handles all dynamically registered sysctl tables, even though we don't handle modular sysctls. Errors due to e.g. invalid parameter name or value are reported in the kernel log. The processing is hooked right before the init process is loaded, as some handlers might be more complicated than simple setters and might need some subsystems to be initialized. At the moment the init process can be started and eventually execute a process writing to /proc/sys/ then it should be also fine to do that from the kernel. Sysctls registered later on module load time are not set by this mechanism - it's expected that in such scenarios, setting sysctl values from userspace is practical enough. [1] https://lore.kernel.org/r/BL0PR02MB560167492CA4094C91589930E9FC0@BL0PR02MB5601.namprd02.prod.outlook.com/ [2] https://unix.stackexchange.com/questions/558802/how-to-set-sysctl-using-kernel-command-line-parameter [3] https://lore.kernel.org/r/87bloj2skm.fsf@x220.int.ebiederm.org/ Signed-off-by: Vlastimil Babka Signed-off-by: Andrew Morton Reviewed-by: Luis Chamberlain Reviewed-by: Masami Hiramatsu Acked-by: Kees Cook Acked-by: Michal Hocko Cc: Iurii Zaikin Cc: Ivan Teterevkov Cc: Michal Hocko Cc: David Rientjes Cc: Matthew Wilcox Cc: "Eric W . Biederman" Cc: "Guilherme G . Piccoli" Cc: Alexey Dobriyan Cc: Thomas Gleixner Cc: Greg Kroah-Hartman Cc: Christian Brauner Link: http://lkml.kernel.org/r/20200427180433.7029-1-vbabka@suse.cz Link: http://lkml.kernel.org/r/20200427180433.7029-2-vbabka@suse.cz Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index f2401e45a3c2..50bb7f383a1b 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -197,6 +197,7 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); +void do_sysctl_args(void); extern int pwrsw_enabled; extern int unaligned_enabled; @@ -235,6 +236,9 @@ static inline void setup_sysctl_set(struct ctl_table_set *p, { } +static inline void do_sysctl_args(void) +{ +} #endif /* CONFIG_SYSCTL */ int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, -- cgit v1.2.3 From 0ec9dc9bcba0a62b0844e54c1caf6b8b0bf6b5b4 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Sun, 7 Jun 2020 21:40:45 -0700 Subject: kernel/hung_task.c: introduce sysctl to print all traces when a hung task is detected Commit 401c636a0eeb ("kernel/hung_task.c: show all hung tasks before panic") introduced a change in that we started to show all CPUs backtraces when a hung task is detected _and_ the sysctl/kernel parameter "hung_task_panic" is set. The idea is good, because usually when observing deadlocks (that may lead to hung tasks), the culprit is another task holding a lock and not necessarily the task detected as hung. The problem with this approach is that dumping backtraces is a slightly expensive task, specially printing that on console (and specially in many CPU machines, as servers commonly found nowadays). So, users that plan to collect a kdump to investigate the hung tasks and narrow down the deadlock definitely don't need the CPUs backtrace on dmesg/console, which will delay the panic and pollute the log (crash tool would easily grab all CPUs traces with 'bt -a' command). Also, there's the reciprocal scenario: some users may be interested in seeing the CPUs backtraces but not have the system panic when a hung task is detected. The current approach hence is almost as embedding a policy in the kernel, by forcing the CPUs backtraces' dump (only) on hung_task_panic. This patch decouples the panic event on hung task from the CPUs backtraces dump, by creating (and documenting) a new sysctl called "hung_task_all_cpu_backtrace", analog to the approach taken on soft/hard lockups, that have both a panic and an "all_cpu_backtrace" sysctl to allow individual control. The new mechanism for dumping the CPUs backtraces on hung task detection respects "hung_task_warnings" by not dumping the traces in case there's no warnings left. Signed-off-by: Guilherme G. Piccoli Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Cc: Tetsuo Handa Link: http://lkml.kernel.org/r/20200327223646.20779-1-gpiccoli@canonical.com Signed-off-by: Linus Torvalds --- include/linux/sched/sysctl.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 7b4d3a49b6c5..660ac49f2b53 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -7,6 +7,13 @@ struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK + +#ifdef CONFIG_SMP +extern unsigned int sysctl_hung_task_all_cpu_backtrace; +#else +#define sysctl_hung_task_all_cpu_backtrace 0 +#endif /* CONFIG_SMP */ + extern int sysctl_hung_task_check_count; extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; -- cgit v1.2.3 From 60c958d8df9cfc40b745d6cd583cfbfa7525ead6 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Sun, 7 Jun 2020 21:40:48 -0700 Subject: panic: add sysctl to dump all CPUs backtraces on oops event Usually when the kernel reaches an oops condition, it's a point of no return; in case not enough debug information is available in the kernel splat, one of the last resorts would be to collect a kernel crash dump and analyze it. The problem with this approach is that in order to collect the dump, a panic is required (to kexec-load the crash kernel). When in an environment of multiple virtual machines, users may prefer to try living with the oops, at least until being able to properly shutdown their VMs / finish their important tasks. This patch implements a way to collect a bit more debug details when an oops event is reached, by printing all the CPUs backtraces through the usage of NMIs (on architectures that support that). The sysctl added (and documented) here was called "oops_all_cpu_backtrace", and when set will (as the name suggests) dump all CPUs backtraces. Far from ideal, this may be the last option though for users that for some reason cannot panic on oops. Most of times oopses are clear enough to indicate the kernel portion that must be investigated, but in virtual environments it's possible to observe hypervisor/KVM issues that could lead to oopses shown in other guests CPUs (like virtual APIC crashes). This patch hence aims to help debug such complex issues without resorting to kdump. Signed-off-by: Guilherme G. Piccoli Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Cc: Luis Chamberlain Cc: Iurii Zaikin Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Randy Dunlap Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200327224116.21030-1-gpiccoli@canonical.com Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f7835db7102e..82d91547d122 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -520,6 +520,12 @@ static inline u32 int_sqrt64(u64 x) } #endif +#ifdef CONFIG_SMP +extern unsigned int sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 +#endif /* CONFIG_SMP */ + extern void bust_spinlocks(int yes); extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; -- cgit v1.2.3 From dadbb612f6e50bbf9101c2f5d82690ce9ea4d66b Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Sun, 7 Jun 2020 21:40:55 -0700 Subject: mm/gup.c: convert to use get_user_{page|pages}_fast_only() API __get_user_pages_fast() renamed to get_user_pages_fast_only() to align with pin_user_pages_fast_only(). As part of this we will get rid of write parameter. Instead caller will pass FOLL_WRITE to get_user_pages_fast_only(). This will not change any existing functionality of the API. All the callers are changed to pass FOLL_WRITE. Also introduce get_user_page_fast_only(), and use it in a few places that hard-code nr_pages to 1. Updated the documentation of the API. Signed-off-by: Souptick Joarder Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Paul Mackerras [arch/powerpc/kvm] Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Mark Rutland Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Stephen Rothwell Cc: Mike Rapoport Cc: Aneesh Kumar K.V Cc: Michal Suchanek Link: http://lkml.kernel.org/r/1590396812-31277-1-git-send-email-jrdr.linux@gmail.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 86adc71a972f..22010c4175f2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1824,10 +1824,16 @@ extern int mprotect_fixup(struct vm_area_struct *vma, /* * doesn't attempt to fault and will return short. */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages); +int get_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); int pin_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); + +static inline bool get_user_page_fast_only(unsigned long addr, + unsigned int gup_flags, struct page **pagep) +{ + return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; +} /* * per-process(per-mm_struct) statistics. */ -- cgit v1.2.3 From 420c2091b65a95b1daea4c36d27df4ac5f38033d Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Sun, 7 Jun 2020 21:41:02 -0700 Subject: mm/gup: introduce pin_user_pages_locked() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm/gup: introduce pin_user_pages_locked(), use it in frame_vector.c", v2. This adds yet one more pin_user_pages*() variant, and uses that to convert mm/frame_vector.c. With this, along with maybe 20 or 30 other recent patches in various trees, we are close to having the relevant gup call sites converted--with the notable exception of the bio/block layer. This patch (of 2): Introduce pin_user_pages_locked(), which is nearly identical to get_user_pages_locked() except that it sets FOLL_PIN and rejects FOLL_GET. As with other pairs of get_user_pages*() and pin_user_pages() API calls, it's prudent to assert that FOLL_PIN is *not* set in the get_user_pages*() call, so add that as part of this. [jhubbard@nvidia.com: v2] Link: http://lkml.kernel.org/r/20200531234131.770697-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Acked-by: Pankaj Gupta Cc: Daniel Vetter Cc: Jérôme Glisse Cc: Vlastimil Babka Cc: Jan Kara Cc: Dave Chinner Cc: Souptick Joarder Link: http://lkml.kernel.org/r/20200531234131.770697-1-jhubbard@nvidia.com Link: http://lkml.kernel.org/r/20200527223243.884385-1-jhubbard@nvidia.com Link: http://lkml.kernel.org/r/20200527223243.884385-2-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 22010c4175f2..9d6042178ca7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1706,6 +1706,8 @@ long pin_user_pages(unsigned long start, unsigned long nr_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 pin_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, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, -- cgit v1.2.3 From 2062a4e8ae9f486847652927aaf88e21ab8d195d Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 8 Jun 2020 21:29:56 -0700 Subject: kallsyms/printk: add loglvl to print_ip_sym() Patch series "Add log level to show_stack()", v3. Add log level argument to show_stack(). Done in three stages: 1. Introducing show_stack_loglvl() for every architecture 2. Migrating old users with an explicit log level 3. Renaming show_stack_loglvl() into show_stack() Justification: - It's a design mistake to move a business-logic decision into platform realization detail. - I have currently two patches sets that would benefit from this work: Removing console_loglevel jumps in sysrq driver [1] Hung task warning before panic [2] - suggested by Tetsuo (but he probably didn't realise what it would involve). - While doing (1), (2) the backtraces were adjusted to headers and other messages for each situation - so there won't be a situation when the backtrace is printed, but the headers are missing because they have lesser log level (or the reverse). - As the result in (2) plays with console_loglevel for kdb are removed. The least important for upstream, but maybe still worth to note that every company I've worked in so far had an off-list patch to print backtrace with the needed log level (but only for the architecture they cared about). If you have other ideas how you will benefit from show_stack() with a log level - please, reply to this cover letter. See also discussion on v1: https://lore.kernel.org/linux-riscv/20191106083538.z5nlpuf64cigxigh@pathway.suse.cz/ This patch (of 50): print_ip_sym() needs to have a log level parameter to comply with other parts being printed. Otherwise, half of the expected backtrace would be printed and other may be missing with some logging level. The following callee(s) are using now the adjusted log level: - microblaze/unwind: the same level as headers & userspace unwind. Note that pr_debug()'s there are for debugging the unwinder itself. - nds32/traps: symbol addresses are printed with the same log level as backtrace headers. - lockdep: ip for locking issues is printed with the same log level as other part of the warning. - sched: ip where preemption was disabled is printed as error like the rest part of the message. - ftrace: bug reports are now consistent in the log level being used. Signed-off-by: Dmitry Safonov Signed-off-by: Andrew Morton Acked-by: Steven Rostedt (VMware) Cc: Albert Ou Cc: Ben Segall Cc: Dietmar Eggemann Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Hogan Cc: Juri Lelli Cc: Mel Gorman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Thomas Gleixner Cc: Vincent Chen Cc: Vincent Guittot Cc: Will Deacon Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Dmitry Safonov Cc: Jiri Slaby Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Richard Henderson Cc: Vineet Gupta Cc: Russell King Cc: Catalin Marinas Cc: Aurelien Jacquiot Cc: Mark Salter Cc: Guo Ren Cc: Yoshinori Sato Cc: Brian Cain Cc: Fenghua Yu Cc: Tony Luck Cc: Geert Uytterhoeven Cc: Ley Foon Tan Cc: Jonas Bonn Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Paul Mackerras Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Rich Felker Cc: "David S. Miller" Cc: Anton Ivanov Cc: Jeff Dike Cc: Richard Weinberger Cc: Guan Xuetao Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Chris Zankel Cc: Max Filippov Cc: Len Brown Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: "Rafael J. Wysocki" Cc: Daniel Thompson Cc: Douglas Anderson Cc: Jason Wessel Link: http://lkml.kernel.org/r/20200418201944.482088-2-dima@arista.com Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 657a83b943f0..98338dc6b5d2 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -165,9 +165,9 @@ static inline int kallsyms_show_value(void) #endif /*CONFIG_KALLSYMS*/ -static inline void print_ip_sym(unsigned long ip) +static inline void print_ip_sym(const char *loglvl, unsigned long ip) { - printk("[<%px>] %pS\n", (void *) ip, (void *) ip); + printk("%s[<%px>] %pS\n", loglvl, (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ -- cgit v1.2.3 From ab34b46d1a74e98996e67a7da7e5d683ecfd9f57 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 8 Jun 2020 21:32:10 -0700 Subject: sysrq: use show_stack_loglvl() Show the stack trace on a CPU with the same log level as "CPU%d" header. Signed-off-by: Dmitry Safonov Signed-off-by: Andrew Morton Cc: Greg Kroah-Hartman Cc: Jiri Slaby Link: http://lkml.kernel.org/r/20200418201944.482088-45-dima@arista.com Signed-off-by: Linus Torvalds --- include/linux/sched/debug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index 95fb9e025247..373e4e3faf2a 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -31,6 +31,8 @@ extern void show_regs(struct pt_regs *); * trace (or NULL if the entire call-chain of the task should be shown). */ extern void show_stack(struct task_struct *task, unsigned long *sp); +extern void show_stack_loglvl(struct task_struct *task, unsigned long *sp, + const char *loglvl); extern void sched_show_task(struct task_struct *p); -- cgit v1.2.3 From 9cb8f069deeed708bf19486d5893e297dc467ae0 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 8 Jun 2020 21:32:29 -0700 Subject: kernel: rename show_stack_loglvl() => show_stack() Now the last users of show_stack() got converted to use an explicit log level, show_stack_loglvl() can drop it's redundant suffix and become once again well known show_stack(). Signed-off-by: Dmitry Safonov Signed-off-by: Andrew Morton Link: http://lkml.kernel.org/r/20200418201944.482088-51-dima@arista.com Signed-off-by: Linus Torvalds --- include/linux/sched/debug.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index 373e4e3faf2a..00c45a0e6abe 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -30,9 +30,8 @@ extern void show_regs(struct pt_regs *); * task), SP is the stack pointer of the first frame that should be shown in the back * trace (or NULL if the entire call-chain of the task should be shown). */ -extern void show_stack(struct task_struct *task, unsigned long *sp); -extern void show_stack_loglvl(struct task_struct *task, unsigned long *sp, - const char *loglvl); +extern void show_stack(struct task_struct *task, unsigned long *sp, + const char *loglvl); extern void sched_show_task(struct task_struct *p); -- cgit v1.2.3 From e31cf2f4ca422ac9b14ecc4a1295b8977a20f812 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:32:33 -0700 Subject: mm: don't include asm/pgtable.h if linux/mm.h is already included Patch series "mm: consolidate definitions of page table accessors", v2. The low level page table accessors (pXY_index(), pXY_offset()) are duplicated across all architectures and sometimes more than once. For instance, we have 31 definition of pgd_offset() for 25 supported architectures. Most of these definitions are actually identical and typically it boils down to, e.g. static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } These definitions can be shared among 90% of the arches provided XYZ_SHIFT, PTRS_PER_XYZ and xyz_page_vaddr() are defined. For architectures that really need a custom version there is always possibility to override the generic version with the usual ifdefs magic. These patches introduce include/linux/pgtable.h that replaces include/asm-generic/pgtable.h and add the definitions of the page table accessors to the new header. This patch (of 12): The linux/mm.h header includes to allow inlining of the functions involving page table manipulations, e.g. pte_alloc() and pmd_alloc(). So, there is no point to explicitly include in the files that include . The include statements in such cases are remove with a simple loop: for f in $(git grep -l "include ") ; do sed -i -e '/include / d' $f done Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mike Rapoport Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-1-rppt@kernel.org Link: http://lkml.kernel.org/r/20200514170327.31389-2-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/dax.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index d7af5d243f24..6904d4e0b2e0 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -5,7 +5,6 @@ #include #include #include -#include /* Flag for synchronous flush */ #define DAXDEV_F_SYNC (1UL << 0) -- cgit v1.2.3 From ca5999fde0a1761665a38e4c9a72dbcd7d190a81 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:32:38 -0700 Subject: mm: introduce include/linux/pgtable.h The include/linux/pgtable.h is going to be the home of generic page table manipulation functions. Start with moving asm-generic/pgtable.h to include/linux/pgtable.h and make the latter include asm/pgtable.h. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-3-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 2 +- include/linux/dma-noncoherent.h | 2 +- include/linux/hmm.h | 2 +- include/linux/hugetlb.h | 2 +- include/linux/io-mapping.h | 2 +- include/linux/kasan.h | 2 +- include/linux/mm.h | 2 +- include/linux/pgtable.h | 1323 +++++++++++++++++++++++++++++++++++++++ 8 files changed, 1330 insertions(+), 7 deletions(-) create mode 100644 include/linux/pgtable.h (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index bc156285d097..be79a45d7aa3 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -7,7 +7,7 @@ #include #include -#include /* for pgprot_t */ +#include /* for pgprot_t */ #ifdef CONFIG_CRASH_DUMP #define ELFCORE_ADDR_MAX (-1ULL) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index b59f1b6be3e9..ca09a4e07d2d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -3,7 +3,7 @@ #define _LINUX_DMA_NONCOHERENT_H 1 #include -#include +#include #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H #include diff --git a/include/linux/hmm.h b/include/linux/hmm.h index e912b9dc4633..f4a09ed223ac 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -10,7 +10,7 @@ #define LINUX_HMM_H #include -#include +#include #include #include diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0cced410e0bd..50650d0d01b9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include struct ctl_table; struct user_struct; diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index b336622612f3..94e24e58966d 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -99,7 +99,7 @@ io_mapping_unmap(void __iomem *vaddr) #else #include -#include +#include /* Create the io_mapping object*/ static inline struct io_mapping * diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 31314ca7c635..17d8915eaebb 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -12,7 +12,7 @@ struct task_struct; #ifdef CONFIG_KASAN #include -#include +#include extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d6042178ca7..af0a09b89837 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -92,7 +92,7 @@ extern int mmap_rnd_compat_bits __read_mostly; #endif #include -#include +#include #include /* diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h new file mode 100644 index 000000000000..6e274da637fd --- /dev/null +++ b/include/linux/pgtable.h @@ -0,0 +1,1323 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGTABLE_H +#define _LINUX_PGTABLE_H + +#include +#include + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_MMU + +#include +#include +#include +#include + +#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ + defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS +#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED +#endif + +/* + * On almost all architectures and configurations, 0 can be used as the + * upper ceiling to free_pgtables(): on many architectures it has the same + * effect as using TASK_SIZE. However, there is one configuration which + * must impose a more careful limit, to avoid freeing kernel pgtables. + */ +#ifndef USER_PGTABLES_CEILING +#define USER_PGTABLES_CEILING 0UL +#endif + +#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); +#else +static inline int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + BUILD_BUG(); + return 0; +} +static inline int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + int r = 1; + if (!pte_young(pte)) + r = 0; + else + set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); + return r; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + int r = 1; + if (!pmd_young(pmd)) + r = 0; + else + set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); + return r; +} +#else +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#else +/* + * Despite relevant to THP only, this API is called from generic rmap code + * under PageTransHuge(), hence needs a dummy implementation for !THP + */ +static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + pte_clear(mm, address, ptep); + return pte; +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + pmd_clear(pmdp); + return pmd; +} +#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ +#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, + pud_t *pudp) +{ + pud_t pud = *pudp; + + pud_clear(pudp); + return pud; +} +#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL +static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + int full) +{ + return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); +} +#endif + +#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL +static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm, + unsigned long address, pud_t *pudp, + int full) +{ + return pudp_huge_get_and_clear(mm, address, pudp); +} +#endif +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL +static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long address, pte_t *ptep, + int full) +{ + pte_t pte; + pte = ptep_get_and_clear(mm, address, ptep); + return pte; +} +#endif + + +/* + * If two threads concurrently fault at the same page, the thread that + * won the race updates the PTE and its local TLB/Cache. The other thread + * gives up, simply does nothing, and continues; on architectures where + * software can update TLB, local TLB can be updated here to avoid next page + * fault. This function updates TLB only, do nothing with cache or others. + * It is the difference with function update_mmu_cache. + */ +#ifndef __HAVE_ARCH_UPDATE_MMU_TLB +static inline void update_mmu_tlb(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ +} +#define __HAVE_ARCH_UPDATE_MMU_TLB +#endif + +/* + * Some architectures may be able to avoid expensive synchronization + * primitives when modifications are made to PTE's which are already + * not present, or in the process of an address space destruction. + */ +#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL +static inline void pte_clear_not_present_full(struct mm_struct *mm, + unsigned long address, + pte_t *ptep, + int full) +{ + pte_clear(mm, address, ptep); +} +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH +extern pte_t ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH +extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp); +extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pud_t *pudp); +#endif + +#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT +struct mm_struct; +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) +{ + pte_t old_pte = *ptep; + set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); +} +#endif + +/* + * On some architectures hardware does not set page access bit when accessing + * memory page, it is responsibilty of software setting this bit. It brings + * out extra page fault penalty to track page access bit. For optimization page + * access bit can be set during all page fault flow on these arches. + * To be differentiate with macro pte_mkyoung, this macro is used on platforms + * where software maintains page access bit. + */ +#ifndef pte_sw_mkyoung +static inline pte_t pte_sw_mkyoung(pte_t pte) +{ + return pte; +} +#define pte_sw_mkyoung pte_sw_mkyoung +#endif + +#ifndef pte_savedwrite +#define pte_savedwrite pte_write +#endif + +#ifndef pte_mk_savedwrite +#define pte_mk_savedwrite pte_mkwrite +#endif + +#ifndef pte_clear_savedwrite +#define pte_clear_savedwrite pte_wrprotect +#endif + +#ifndef pmd_savedwrite +#define pmd_savedwrite pmd_write +#endif + +#ifndef pmd_mk_savedwrite +#define pmd_mk_savedwrite pmd_mkwrite +#endif + +#ifndef pmd_clear_savedwrite +#define pmd_clear_savedwrite pmd_wrprotect +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); +} +#else +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + BUILD_BUG(); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif +#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline void pudp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pud_t *pudp) +{ + pud_t old_pud = *pudp; + + set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); +} +#else +static inline void pudp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pud_t *pudp) +{ + BUILD_BUG(); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#endif + +#ifndef pmdp_collapse_flush +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#else +static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUILD_BUG(); + return *pmdp; +} +#define pmdp_collapse_flush pmdp_collapse_flush +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +#endif + +#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * This is an implementation of pmdp_establish() that is only suitable for an + * architecture that doesn't have hardware dirty/accessed bits. In this case we + * can't race with CPU which sets these bits and non-atomic aproach is fine. + */ +static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(vma->vm_mm, address, pmdp, pmd); + return old_pmd; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_INVALIDATE +extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); +#endif + +#ifndef __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + return pte_val(pte_a) == pte_val(pte_b); +} +#endif + +#ifndef __HAVE_ARCH_PTE_UNUSED +/* + * Some architectures provide facilities to virtualization guests + * so that they can flag allocated pages as unused. This allows the + * host to transparently reclaim unused pages. This function returns + * whether the pte's page is unused. + */ +static inline int pte_unused(pte_t pte) +{ + return 0; +} +#endif + +#ifndef pte_access_permitted +#define pte_access_permitted(pte, write) \ + (pte_present(pte) && (!(write) || pte_write(pte))) +#endif + +#ifndef pmd_access_permitted +#define pmd_access_permitted(pmd, write) \ + (pmd_present(pmd) && (!(write) || pmd_write(pmd))) +#endif + +#ifndef pud_access_permitted +#define pud_access_permitted(pud, write) \ + (pud_present(pud) && (!(write) || pud_write(pud))) +#endif + +#ifndef p4d_access_permitted +#define p4d_access_permitted(p4d, write) \ + (p4d_present(p4d) && (!(write) || p4d_write(p4d))) +#endif + +#ifndef pgd_access_permitted +#define pgd_access_permitted(pgd, write) \ + (pgd_present(pgd) && (!(write) || pgd_write(pgd))) +#endif + +#ifndef __HAVE_ARCH_PMD_SAME +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return pmd_val(pmd_a) == pmd_val(pmd_b); +} + +static inline int pud_same(pud_t pud_a, pud_t pud_b) +{ + return pud_val(pud_a) == pud_val(pud_b); +} +#endif + +#ifndef __HAVE_ARCH_P4D_SAME +static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) +{ + return p4d_val(p4d_a) == p4d_val(p4d_b); +} +#endif + +#ifndef __HAVE_ARCH_PGD_SAME +static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) +{ + return pgd_val(pgd_a) == pgd_val(pgd_b); +} +#endif + +/* + * Use set_p*_safe(), and elide TLB flushing, when confident that *no* + * TLB flush will be required as a result of the "set". For example, use + * in scenarios where it is known ahead of time that the routine is + * setting non-present entries, or re-setting an existing entry to the + * same value. Otherwise, use the typical "set" helpers and flush the + * TLB. + */ +#define set_pte_safe(ptep, pte) \ +({ \ + WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ + set_pte(ptep, pte); \ +}) + +#define set_pmd_safe(pmdp, pmd) \ +({ \ + WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ + set_pmd(pmdp, pmd); \ +}) + +#define set_pud_safe(pudp, pud) \ +({ \ + WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ + set_pud(pudp, pud); \ +}) + +#define set_p4d_safe(p4dp, p4d) \ +({ \ + WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ + set_p4d(p4dp, p4d); \ +}) + +#define set_pgd_safe(pgdp, pgd) \ +({ \ + WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ + set_pgd(pgdp, pgd); \ +}) + +#ifndef __HAVE_ARCH_DO_SWAP_PAGE +/* + * Some architectures support metadata associated with a page. When a + * page is being swapped out, this metadata must be saved so it can be + * restored when the page is swapped back in. SPARC M7 and newer + * processors support an ADI (Application Data Integrity) tag for the + * page as metadata for the page. arch_do_swap_page() can restore this + * metadata when a page is swapped back in. + */ +static inline void arch_do_swap_page(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte) +{ + +} +#endif + +#ifndef __HAVE_ARCH_UNMAP_ONE +/* + * Some architectures support metadata associated with a page. When a + * page is being swapped out, this metadata must be saved so it can be + * restored when the page is swapped back in. SPARC M7 and newer + * processors support an ADI (Application Data Integrity) tag for the + * page as metadata for the page. arch_unmap_one() can save this + * metadata on a swap-out of a page. + */ +static inline int arch_unmap_one(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t orig_pte) +{ + return 0; +} +#endif + +#ifndef __HAVE_ARCH_PGD_OFFSET_GATE +#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) +#endif + +#ifndef __HAVE_ARCH_MOVE_PTE +#define move_pte(pte, prot, old_addr, new_addr) (pte) +#endif + +#ifndef pte_accessible +# define pte_accessible(mm, pte) ((void)(pte), 1) +#endif + +#ifndef flush_tlb_fix_spurious_fault +#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#endif + +#ifndef pgprot_nx +#define pgprot_nx(prot) (prot) +#endif + +#ifndef pgprot_noncached +#define pgprot_noncached(prot) (prot) +#endif + +#ifndef pgprot_writecombine +#define pgprot_writecombine pgprot_noncached +#endif + +#ifndef pgprot_writethrough +#define pgprot_writethrough pgprot_noncached +#endif + +#ifndef pgprot_device +#define pgprot_device pgprot_noncached +#endif + +#ifndef pgprot_modify +#define pgprot_modify pgprot_modify +static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) +{ + if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) + newprot = pgprot_noncached(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) + newprot = pgprot_writecombine(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) + newprot = pgprot_device(newprot); + return newprot; +} +#endif + +/* + * When walking page tables, get the address of the next boundary, + * or the end address of the range if that comes earlier. Although no + * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. + */ + +#define pgd_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +#ifndef p4d_addr_end +#define p4d_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +#ifndef pud_addr_end +#define pud_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +#ifndef pmd_addr_end +#define pmd_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +/* + * When walking page tables, we usually want to skip any p?d_none entries; + * and any p?d_bad entries - reporting the error before resetting to none. + * Do the tests inline, but report and clear the bad entry in mm/memory.c. + */ +void pgd_clear_bad(pgd_t *); + +#ifndef __PAGETABLE_P4D_FOLDED +void p4d_clear_bad(p4d_t *); +#else +#define p4d_clear_bad(p4d) do { } while (0) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +void pud_clear_bad(pud_t *); +#else +#define pud_clear_bad(p4d) do { } while (0) +#endif + +void pmd_clear_bad(pmd_t *); + +static inline int pgd_none_or_clear_bad(pgd_t *pgd) +{ + if (pgd_none(*pgd)) + return 1; + if (unlikely(pgd_bad(*pgd))) { + pgd_clear_bad(pgd); + return 1; + } + return 0; +} + +static inline int p4d_none_or_clear_bad(p4d_t *p4d) +{ + if (p4d_none(*p4d)) + return 1; + if (unlikely(p4d_bad(*p4d))) { + p4d_clear_bad(p4d); + return 1; + } + return 0; +} + +static inline int pud_none_or_clear_bad(pud_t *pud) +{ + if (pud_none(*pud)) + return 1; + if (unlikely(pud_bad(*pud))) { + pud_clear_bad(pud); + return 1; + } + return 0; +} + +static inline int pmd_none_or_clear_bad(pmd_t *pmd) +{ + if (pmd_none(*pmd)) + return 1; + if (unlikely(pmd_bad(*pmd))) { + pmd_clear_bad(pmd); + return 1; + } + return 0; +} + +static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + /* + * Get the current pte state, but zero it out to make it + * non-present, preventing the hardware from asynchronously + * updating it. + */ + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, pte_t pte) +{ + /* + * The pte is non-present, so there's no hardware state to + * preserve. + */ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} + +#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +/* + * Start a pte protection read-modify-write transaction, which + * protects against asynchronous hardware modifications to the pte. + * The intention is not to prevent the hardware from making pte + * updates, but to prevent any updates it may make from being lost. + * + * This does not protect against other software modifications of the + * pte; the appropriate pte lock must be held over the transation. + * + * Note that this interface is intended to be batchable, meaning that + * ptep_modify_prot_commit may not actually update the pte, but merely + * queue the update to be done at some later time. The update must be + * actually committed before the pte lock is released, however. + */ +static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + return __ptep_modify_prot_start(vma, addr, ptep); +} + +/* + * Commit an update to a pte, leaving any hardware-controlled bits in + * the PTE unmodified. + */ +static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) +{ + __ptep_modify_prot_commit(vma, addr, ptep, pte); +} +#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ +#endif /* CONFIG_MMU */ + +/* + * No-op macros that just return the current protection value. Defined here + * because these macros can be used used even if CONFIG_MMU is not defined. + */ +#ifndef pgprot_encrypted +#define pgprot_encrypted(prot) (prot) +#endif + +#ifndef pgprot_decrypted +#define pgprot_decrypted(prot) (prot) +#endif + +/* + * A facility to provide lazy MMU batching. This allows PTE updates and + * page invalidations to be delayed until a call to leave lazy MMU mode + * is issued. Some architectures may benefit from doing this, and it is + * beneficial for both shadow and direct mode hypervisors, which may batch + * the PTE updates which happen during this window. Note that using this + * interface requires that read hazards be removed from the code. A read + * hazard could result in the direct mode hypervisor case, since the actual + * write to the page tables may not yet have taken place, so reads though + * a raw PTE pointer after it has been modified are not guaranteed to be + * up to date. This mode can only be entered and left under the protection of + * the page table locks for all page tables which may be modified. In the UP + * case, this is required so that preemption is disabled, and in the SMP case, + * it must synchronize the delayed page table writes properly on other CPUs. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() do {} while (0) +#define arch_leave_lazy_mmu_mode() do {} while (0) +#define arch_flush_lazy_mmu_mode() do {} while (0) +#endif + +/* + * A facility to provide batching of the reload of page tables and + * other process state with the actual context switch code for + * paravirtualized guests. By convention, only one of the batched + * update (lazy) modes (CPU, MMU) should be active at any given time, + * entry should never be nested, and entry and exits should always be + * paired. This is for sanity of maintaining and reasoning about the + * kernel code. In this case, the exit (end of the context switch) is + * in architecture-specific code, and so doesn't need a generic + * definition. + */ +#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH +#define arch_start_context_switch(prev) do {} while (0) +#endif + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline int pmd_swp_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} +#endif +#else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ +static inline int pte_soft_dirty(pte_t pte) +{ + return 0; +} + +static inline int pmd_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_soft_dirty(pte_t pte) +{ + return 0; +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline int pmd_swp_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} +#endif + +#ifndef __HAVE_PFNMAP_TRACKING +/* + * Interfaces that can be used by architecture code to keep track of + * memory type of pfn mappings specified by the remap_pfn_range, + * vmf_insert_pfn. + */ + +/* + * track_pfn_remap is called when a _new_ pfn mapping is being established + * by remap_pfn_range() for physical range indicated by pfn and size. + */ +static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn, unsigned long addr, + unsigned long size) +{ + return 0; +} + +/* + * track_pfn_insert is called when a _new_ single pfn is established + * by vmf_insert_pfn(). + */ +static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, + pfn_t pfn) +{ +} + +/* + * track_pfn_copy is called when vma that is covering the pfnmap gets + * copied through copy_page_range(). + */ +static inline int track_pfn_copy(struct vm_area_struct *vma) +{ + return 0; +} + +/* + * untrack_pfn is called while unmapping a pfnmap for a region. + * untrack can be called for a specific region indicated by pfn and size or + * can be for the entire vma (in which case pfn, size are zero). + */ +static inline void untrack_pfn(struct vm_area_struct *vma, + unsigned long pfn, unsigned long size) +{ +} + +/* + * untrack_pfn_moved is called while mremapping a pfnmap for a new region. + */ +static inline void untrack_pfn_moved(struct vm_area_struct *vma) +{ +} +#else +extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn, unsigned long addr, + unsigned long size); +extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, + pfn_t pfn); +extern int track_pfn_copy(struct vm_area_struct *vma); +extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, + unsigned long size); +extern void untrack_pfn_moved(struct vm_area_struct *vma); +#endif + +#ifdef __HAVE_COLOR_ZERO_PAGE +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + unsigned long offset_from_zero_pfn = pfn - zero_pfn; + return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); +} + +#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) + +#else +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + return pfn == zero_pfn; +} + +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + extern unsigned long zero_pfn; + return zero_pfn; +} +#endif + +#ifdef CONFIG_MMU + +#ifndef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_huge(pmd_t pmd) +{ + return 0; +} +#ifndef pmd_write +static inline int pmd_write(pmd_t pmd) +{ + BUG(); + return 0; +} +#endif /* pmd_write */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifndef pud_write +static inline int pud_write(pud_t pud) +{ + BUG(); + return 0; +} +#endif /* pud_write */ + +#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline int pmd_devmap(pmd_t pmd) +{ + return 0; +} +static inline int pud_devmap(pud_t pud) +{ + return 0; +} +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} +#endif + +#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ + (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) +static inline int pud_trans_huge(pud_t pud) +{ + return 0; +} +#endif + +/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */ +static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud) +{ + pud_t pudval = READ_ONCE(*pud); + + if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) + return 1; + if (unlikely(pud_bad(pudval))) { + pud_clear_bad(pud); + return 1; + } + return 0; +} + +/* See pmd_trans_unstable for discussion. */ +static inline int pud_trans_unstable(pud_t *pud) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + return pud_none_or_trans_huge_or_dev_or_clear_bad(pud); +#else + return 0; +#endif +} + +#ifndef pmd_read_atomic +static inline pmd_t pmd_read_atomic(pmd_t *pmdp) +{ + /* + * Depend on compiler for an atomic pmd read. NOTE: this is + * only going to work, if the pmdval_t isn't larger than + * an unsigned long. + */ + return *pmdp; +} +#endif + +#ifndef arch_needs_pgtable_deposit +#define arch_needs_pgtable_deposit() (false) +#endif +/* + * This function is meant to be used by sites walking pagetables with + * the mmap_sem hold in read mode to protect against MADV_DONTNEED and + * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd + * into a null pmd and the transhuge page fault can convert a null pmd + * into an hugepmd or into a regular pmd (if the hugepage allocation + * fails). While holding the mmap_sem in read mode the pmd becomes + * stable and stops changing under us only if it's not null and not a + * transhuge pmd. When those races occurs and this function makes a + * difference vs the standard pmd_none_or_clear_bad, the result is + * undefined so behaving like if the pmd was none is safe (because it + * can return none anyway). The compiler level barrier() is critically + * important to compute the two checks atomically on the same pmdval. + * + * For 32bit kernels with a 64bit large pmd_t this automatically takes + * care of reading the pmd atomically to avoid SMP race conditions + * against pmd_populate() when the mmap_sem is hold for reading by the + * caller (a special atomic read not done by "gcc" as in the generic + * version above, is also needed when THP is disabled because the page + * fault can populate the pmd from under us). + */ +static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + /* + * The barrier will stabilize the pmdval in a register or on + * the stack so that it will stop changing under the code. + * + * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE, + * pmd_read_atomic is allowed to return a not atomic pmdval + * (for example pointing to an hugepage that has never been + * mapped in the pmd). The below checks will only care about + * the low part of the pmd with 32bit PAE x86 anyway, with the + * exception of pmd_none(). So the important thing is that if + * the low part of the pmd is found null, the high part will + * be also null or the pmd_none() check below would be + * confused. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + barrier(); +#endif + /* + * !pmd_present() checks for pmd migration entries + * + * The complete check uses is_pmd_migration_entry() in linux/swapops.h + * But using that requires moving current function and pmd_trans_unstable() + * to linux/swapops.h to resovle dependency, which is too much code move. + * + * !pmd_present() is equivalent to is_pmd_migration_entry() currently, + * because !pmd_present() pages can only be under migration not swapped + * out. + * + * pmd_none() is preseved for future condition checks on pmd migration + * entries and not confusing with this function name, although it is + * redundant with !pmd_present(). + */ + if (pmd_none(pmdval) || pmd_trans_huge(pmdval) || + (IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval))) + return 1; + if (unlikely(pmd_bad(pmdval))) { + pmd_clear_bad(pmd); + return 1; + } + return 0; +} + +/* + * This is a noop if Transparent Hugepage Support is not built into + * the kernel. Otherwise it is equivalent to + * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in + * places that already verified the pmd is not none and they want to + * walk ptes while holding the mmap sem in read mode (write mode don't + * need this). If THP is not enabled, the pmd can't go away under the + * code even if MADV_DONTNEED runs, but if THP is enabled we need to + * run a pmd_trans_unstable before walking the ptes after + * split_huge_pmd returns (because it may have run when the pmd become + * null, but then a page fault can map in a THP and not a regular page). + */ +static inline int pmd_trans_unstable(pmd_t *pmd) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + return pmd_none_or_trans_huge_or_clear_bad(pmd); +#else + return 0; +#endif +} + +#ifndef CONFIG_NUMA_BALANCING +/* + * Technically a PTE can be PROTNONE even when not doing NUMA balancing but + * the only case the kernel cares is for NUMA balancing and is only ever set + * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked + * _PAGE_PROTNONE so by by default, implement the helper as "always no". It + * is the responsibility of the caller to distinguish between PROT_NONE + * protections and NUMA hinting fault protections. + */ +static inline int pte_protnone(pte_t pte) +{ + return 0; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#endif /* CONFIG_MMU */ + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +#ifndef __PAGETABLE_P4D_FOLDED +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); +int p4d_clear_huge(p4d_t *p4d); +#else +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +#endif /* !__PAGETABLE_P4D_FOLDED */ + +int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); +int pud_clear_huge(pud_t *pud); +int pmd_clear_huge(pmd_t *pmd); +int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); +int pud_free_pmd_page(pud_t *pud, unsigned long addr); +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); +#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +static inline int pud_clear_huge(pud_t *pud) +{ + return 0; +} +static inline int pmd_clear_huge(pmd_t *pmd) +{ + return 0; +} +static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) +{ + return 0; +} +static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) +{ + return 0; +} +static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + +#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * ARCHes with special requirements for evicting THP backing TLB entries can + * implement this. Otherwise also, it can help optimize normal TLB flush in + * THP regime. stock flush_tlb_range() typically has optimization to nuke the + * entire TLB TLB if flush span is greater than a threshold, which will + * likely be true for a single huge page. Thus a single thp flush will + * invalidate the entire TLB which is not desitable. + * e.g. see arch/arc: flush_pmd_tlb_range + */ +#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#else +#define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() +#define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() +#endif +#endif + +struct file; +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); + +#ifndef CONFIG_X86_ESPFIX64 +static inline void init_espfix_bsp(void) { } +#endif + +extern void __init pgtable_cache_init(void); + +#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED +static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + return true; +} + +static inline bool arch_has_pfn_modify_check(void) +{ + return false; +} +#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ + +/* + * Architecture PAGE_KERNEL_* fallbacks + * + * Some architectures don't define certain PAGE_KERNEL_* flags. This is either + * because they really don't support them, or the port needs to be updated to + * reflect the required functionality. Below are a set of relatively safe + * fallbacks, as best effort, which we can count on in lieu of the architectures + * not defining them on their own yet. + */ + +#ifndef PAGE_KERNEL_RO +# define PAGE_KERNEL_RO PAGE_KERNEL +#endif + +#ifndef PAGE_KERNEL_EXEC +# define PAGE_KERNEL_EXEC PAGE_KERNEL +#endif + +/* + * Page Table Modification bits for pgtbl_mod_mask. + * + * These are used by the p?d_alloc_track*() set of functions an in the generic + * vmalloc/ioremap code to track at which page-table levels entries have been + * modified. Based on that the code can better decide when vmalloc and ioremap + * mapping changes need to be synchronized to other page-tables in the system. + */ +#define __PGTBL_PGD_MODIFIED 0 +#define __PGTBL_P4D_MODIFIED 1 +#define __PGTBL_PUD_MODIFIED 2 +#define __PGTBL_PMD_MODIFIED 3 +#define __PGTBL_PTE_MODIFIED 4 + +#define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) +#define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) +#define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) +#define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) +#define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) + +/* Page-Table Modification Mask */ +typedef unsigned int pgtbl_mod_mask; + +#endif /* !__ASSEMBLY__ */ + +#ifndef io_remap_pfn_range +#define io_remap_pfn_range remap_pfn_range +#endif + +#ifndef has_transparent_hugepage +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define has_transparent_hugepage() 1 +#else +#define has_transparent_hugepage() 0 +#endif +#endif + +/* + * On some architectures it depends on the mm if the p4d/pud or pmd + * layer of the page table hierarchy is folded or not. + */ +#ifndef mm_p4d_folded +#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) +#endif + +#ifndef mm_pud_folded +#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) +#endif + +#ifndef mm_pmd_folded +#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) +#endif + +/* + * p?d_leaf() - true if this entry is a final mapping to a physical address. + * This differs from p?d_huge() by the fact that they are always available (if + * the architecture supports large pages at the appropriate level) even + * if CONFIG_HUGETLB_PAGE is not defined. + * Only meaningful when called on a valid entry. + */ +#ifndef pgd_leaf +#define pgd_leaf(x) 0 +#endif +#ifndef p4d_leaf +#define p4d_leaf(x) 0 +#endif +#ifndef pud_leaf +#define pud_leaf(x) 0 +#endif +#ifndef pmd_leaf +#define pmd_leaf(x) 0 +#endif + +#endif /* _LINUX_PGTABLE_H */ -- cgit v1.2.3 From 65fddcfca8ad14778f71a57672fd01e8112d30fa Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:32:42 -0700 Subject: mm: reorder includes after introduction of linux/pgtable.h The replacement of with made the include of the latter in the middle of asm includes. Fix this up with the aid of the below script and manual adjustments here and there. import sys import re if len(sys.argv) is not 3: print "USAGE: %s
" % (sys.argv[0]) sys.exit(1) hdr_to_move="#include " % sys.argv[2] moved = False in_hdrs = False with open(sys.argv[1], "r") as f: lines = f.readlines() for _line in lines: line = _line.rstrip(' ') if line == hdr_to_move: continue if line.startswith("#include Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-4-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 1 + include/linux/io-mapping.h | 2 +- include/linux/kasan.h | 2 +- include/linux/mm.h | 2 +- 4 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index be79a45d7aa3..a5192b718dbe 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include /* for pgprot_t */ diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 94e24e58966d..0beaa3eba155 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -10,6 +10,7 @@ #include #include #include +#include #include /* @@ -99,7 +100,6 @@ io_mapping_unmap(void __iomem *vaddr) #else #include -#include /* Create the io_mapping object*/ static inline struct io_mapping * diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 17d8915eaebb..82522e996c76 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -11,8 +11,8 @@ struct task_struct; #ifdef CONFIG_KASAN -#include #include +#include extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; diff --git a/include/linux/mm.h b/include/linux/mm.h index af0a09b89837..1844c522d0de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -28,6 +28,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -92,7 +93,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #endif #include -#include #include /* -- cgit v1.2.3 From e05c7b1f2bc4b7b28199b9a7572f73436d97317e Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:33:05 -0700 Subject: mm: pgtable: add shortcuts for accessing kernel PMD and PTE The powerpc 32-bit implementation of pgtable has nice shortcuts for accessing kernel PMD and PTE for a given virtual address. Make these helpers available for all architectures. [rppt@linux.ibm.com: microblaze: fix page table traversal in setup_rt_frame()] Link: http://lkml.kernel.org/r/20200518191511.GD1118872@kernel.org [akpm@linux-foundation.org: s/pmd_ptr_k/pmd_off_k/ in various powerpc places] Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-9-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 6e274da637fd..ee85b222d098 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -28,6 +28,30 @@ #define USER_PGTABLES_CEILING 0UL #endif +/* + * In many cases it is known that a virtual address is mapped at PMD or PTE + * level, so instead of traversing all the page table levels, we can get a + * pointer to the PMD entry in user or kernel page table or translate a virtual + * address to the pointer in the PTE in the kernel page tables with simple + * helpers. + */ +static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) +{ + return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); +} + +static inline pmd_t *pmd_off_k(unsigned long va) +{ + return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); +} + +static inline pte_t *virt_to_kpte(unsigned long vaddr) +{ + pmd_t *pmd = pmd_off_k(vaddr); + + return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); +} + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, -- cgit v1.2.3 From 974b9b2c68f3d35a65e80af9657fe378d2439b60 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:33:10 -0700 Subject: mm: consolidate pte_index() and pte_offset_*() definitions All architectures define pte_index() as (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1) and all architectures define pte_offset_kernel() as an entry in the array of PTEs indexed by the pte_index(). For the most architectures the pte_offset_kernel() implementation relies on the availability of pmd_page_vaddr() that converts a PMD entry value to the virtual address of the page containing PTEs array. Let's move x86 definitions of the PTE accessors to the generic place in and then simply drop the respective definitions from the other architectures. The architectures that didn't provide pmd_page_vaddr() are updated to have that defined. The generic implementation of pte_offset_kernel() can be overridden by an architecture and alpha makes use of this because it has special ordering requirements for its version of pte_offset_kernel(). [rppt@linux.ibm.com: v2] Link: http://lkml.kernel.org/r/20200514170327.31389-11-rppt@kernel.org [rppt@linux.ibm.com: update] Link: http://lkml.kernel.org/r/20200514170327.31389-12-rppt@kernel.org [rppt@linux.ibm.com: update] Link: http://lkml.kernel.org/r/20200514170327.31389-13-rppt@kernel.org [akpm@linux-foundation.org: fix x86 warning] [sfr@canb.auug.org.au: fix powerpc build] Link: http://lkml.kernel.org/r/20200607153443.GB738695@linux.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-10-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 91 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index ee85b222d098..90a5d0c78fca 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -28,6 +28,97 @@ #define USER_PGTABLES_CEILING 0UL #endif +/* + * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] + * + * The pXx_index() functions return the index of the entry in the page + * table page which would control the given virtual address + * + * As these functions may be used by the same code for different levels of + * the page table folding, they are always available, regardless of + * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 + * because in such cases PTRS_PER_PxD equals 1. + */ + +static inline unsigned long pte_index(unsigned long address) +{ + return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); +} + +#ifndef pmd_index +static inline unsigned long pmd_index(unsigned long address) +{ + return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); +} +#define pmd_index pmd_index +#endif + +#ifndef pud_index +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} +#define pud_index pud_index +#endif + +#ifndef pgd_index +/* Must be a compile-time constant, so implement it as a macro */ +#define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) +#endif + +#ifndef pte_offset_kernel +static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) +{ + return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); +} +#define pte_offset_kernel pte_offset_kernel +#endif + +#if defined(CONFIG_HIGHPTE) +#define pte_offset_map(dir, address) \ + ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \ + pte_index((address))) +#define pte_unmap(pte) kunmap_atomic((pte)) +#else +#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) +#define pte_unmap(pte) ((void)(pte)) /* NOP */ +#endif + +/* Find an entry in the second-level page table.. */ +#ifndef pmd_offset +static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) +{ + return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); +} +#define pmd_offset pmd_offset +#endif + +#ifndef pud_offset +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); +} +#define pud_offset pud_offset +#endif + +static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) +{ + return (pgd + pgd_index(address)); +}; + +/* + * a shortcut to get a pgd_t in a given mm + */ +#ifndef pgd_offset +#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) +#endif + +/* + * a shortcut which implies the use of the kernel's pgd, instead + * of a process's + */ +#define pgd_offset_k(address) pgd_offset(&init_mm, (address)) + /* * In many cases it is known that a virtual address is mapped at PMD or PTE * level, so instead of traversing all the page table levels, we can get a -- cgit v1.2.3 From 9740ca4e95b43b91a4a848694a20d01ba6818f7b Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:14 -0700 Subject: mmap locking API: initial implementation as rwsem wrappers This patch series adds a new mmap locking API replacing the existing mmap_sem lock and unlocks. Initially the API is just implemente in terms of inlined rwsem calls, so it doesn't provide any new functionality. There are two justifications for the new API: - At first, it provides an easy hooking point to instrument mmap_sem locking latencies independently of any other rwsems. - In the future, it may be a starting point for replacing the rwsem implementation with a different one, such as range locks. This is something that is being explored, even though there is no wide concensus about this possible direction yet. (see https://patchwork.kernel.org/cover/11401483/) This patch (of 12): This change wraps the existing mmap_sem related rwsem calls into a new mmap locking API. There are two justifications for the new API: - At first, it provides an easy hooking point to instrument mmap_sem locking latencies independently of any other rwsems. - In the future, it may be a starting point for replacing the rwsem implementation with a different one, such as range locks. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Davidlohr Bueso Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Cc: Peter Zijlstra Cc: Matthew Wilcox Cc: Liam Howlett Cc: Jerome Glisse Cc: David Rientjes Cc: Hugh Dickins Cc: Ying Han Cc: Jason Gunthorpe Cc: John Hubbard Cc: Michel Lespinasse Link: http://lkml.kernel.org/r/20200520052908.204642-1-walken@google.com Link: http://lkml.kernel.org/r/20200520052908.204642-2-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/linux/mmap_lock.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) create mode 100644 include/linux/mmap_lock.h (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1844c522d0de..256c4b5b3b11 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h new file mode 100644 index 000000000000..97ac53b66052 --- /dev/null +++ b/include/linux/mmap_lock.h @@ -0,0 +1,54 @@ +#ifndef _LINUX_MMAP_LOCK_H +#define _LINUX_MMAP_LOCK_H + +static inline void mmap_init_lock(struct mm_struct *mm) +{ + init_rwsem(&mm->mmap_sem); +} + +static inline void mmap_write_lock(struct mm_struct *mm) +{ + down_write(&mm->mmap_sem); +} + +static inline int mmap_write_lock_killable(struct mm_struct *mm) +{ + return down_write_killable(&mm->mmap_sem); +} + +static inline bool mmap_write_trylock(struct mm_struct *mm) +{ + return down_write_trylock(&mm->mmap_sem) != 0; +} + +static inline void mmap_write_unlock(struct mm_struct *mm) +{ + up_write(&mm->mmap_sem); +} + +static inline void mmap_write_downgrade(struct mm_struct *mm) +{ + downgrade_write(&mm->mmap_sem); +} + +static inline void mmap_read_lock(struct mm_struct *mm) +{ + down_read(&mm->mmap_sem); +} + +static inline int mmap_read_lock_killable(struct mm_struct *mm) +{ + return down_read_killable(&mm->mmap_sem); +} + +static inline bool mmap_read_trylock(struct mm_struct *mm) +{ + return down_read_trylock(&mm->mmap_sem) != 0; +} + +static inline void mmap_read_unlock(struct mm_struct *mm) +{ + up_read(&mm->mmap_sem); +} + +#endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From b72327fc8dfc1babce18526239b08724b95ef5f0 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:18 -0700 Subject: MMU notifier: use the new mmap locking API This use is converted manually ahead of the next patch in the series, as it requires including a new header which the automated conversion would miss. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Davidlohr Bueso Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-3-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 736f6918335e..2f462710a1a4 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -277,9 +278,9 @@ mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; - down_write(&mm->mmap_sem); + mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); -- cgit v1.2.3 From aaa2cc56c1cd757efec88a4978ffce4cbf884352 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:33 -0700 Subject: mmap locking API: convert nested write lock sites Add API for nested write locks and convert the few call sites doing that. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-7-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 97ac53b66052..a757cb30ae77 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -11,6 +11,11 @@ static inline void mmap_write_lock(struct mm_struct *mm) down_write(&mm->mmap_sem); } +static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) +{ + down_write_nested(&mm->mmap_sem, subclass); +} + static inline int mmap_write_lock_killable(struct mm_struct *mm) { return down_write_killable(&mm->mmap_sem); -- cgit v1.2.3 From 0cc55a0213a02b760ade1d4755fdccfbf7d3157e Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:37 -0700 Subject: mmap locking API: add mmap_read_trylock_non_owner() Add a couple APIs used by kernel/bpf/stackmap.c only: - mmap_read_trylock_non_owner() - mmap_read_unlock_non_owner() (may be called from a work queue). It's still not ideal that bpf/stackmap subverts the lock ownership in this way. Thanks to Peter Zijlstra for suggesting this API as the least-ugly way of addressing this in the short term. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Vlastimil Babka Reviewed-by: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-8-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index a757cb30ae77..d1826ce42f00 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -56,4 +56,18 @@ static inline void mmap_read_unlock(struct mm_struct *mm) up_read(&mm->mmap_sem); } +static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) +{ + if (down_read_trylock(&mm->mmap_sem)) { + rwsem_release(&mm->mmap_sem.dep_map, _RET_IP_); + return true; + } + return false; +} + +static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) +{ + up_read_non_owner(&mm->mmap_sem); +} + #endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From 14c3656b7284a8649496584869e8c6642ec1abbb Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:40 -0700 Subject: mmap locking API: add MMAP_LOCK_INITIALIZER Define a new initializer for the mmap locking api. Initially this just evaluates to __RWSEM_INITIALIZER as the API is defined as wrappers around rwsem. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Reviewed-by: Daniel Jordan Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-9-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index d1826ce42f00..acac1bf5ecd2 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -1,6 +1,9 @@ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H +#define MMAP_LOCK_INITIALIZER(name) \ + .mmap_sem = __RWSEM_INITIALIZER((name).mmap_sem), + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_sem); -- cgit v1.2.3 From 42fc541404f249778e752ab39c8bc25fcb2dbe1e Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:44 -0700 Subject: mmap locking API: add mmap_assert_locked() and mmap_assert_write_locked() Add new APIs to assert that mmap_sem is held. Using this instead of rwsem_is_locked and lockdep_assert_held[_write] makes the assertions more tolerant of future changes to the lock type. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Daniel Jordan Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-10-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index acac1bf5ecd2..43ef914e6468 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -1,6 +1,8 @@ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H +#include + #define MMAP_LOCK_INITIALIZER(name) \ .mmap_sem = __RWSEM_INITIALIZER((name).mmap_sem), @@ -73,4 +75,16 @@ static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) up_read_non_owner(&mm->mmap_sem); } +static inline void mmap_assert_locked(struct mm_struct *mm) +{ + lockdep_assert_held(&mm->mmap_sem); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ + lockdep_assert_held_write(&mm->mmap_sem); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); +} + #endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From da1c55f1b272f4bd54671d459b39ea7b54944ef9 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:47 -0700 Subject: mmap locking API: rename mmap_sem to mmap_lock Rename the mmap_sem field to mmap_lock. Any new uses of this lock should now go through the new mmap locking api. The mmap_lock is still implemented as a rwsem, though this could change in the future. [akpm@linux-foundation.org: fix it for mm-gup-might_lock_readmmap_sem-in-get_user_pages_fast.patch] Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Davidlohr Bueso Reviewed-by: Daniel Jordan Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-11-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/mmap_lock.h | 38 +++++++++++++++++++------------------- 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ef6d3aface8a..b6639b30a83b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -440,7 +440,7 @@ struct mm_struct { spinlock_t page_table_lock; /* Protects page tables and some * counters */ - struct rw_semaphore mmap_sem; + struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 43ef914e6468..0707671851a8 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -4,67 +4,67 @@ #include #define MMAP_LOCK_INITIALIZER(name) \ - .mmap_sem = __RWSEM_INITIALIZER((name).mmap_sem), + .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), static inline void mmap_init_lock(struct mm_struct *mm) { - init_rwsem(&mm->mmap_sem); + init_rwsem(&mm->mmap_lock); } static inline void mmap_write_lock(struct mm_struct *mm) { - down_write(&mm->mmap_sem); + down_write(&mm->mmap_lock); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { - down_write_nested(&mm->mmap_sem, subclass); + down_write_nested(&mm->mmap_lock, subclass); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { - return down_write_killable(&mm->mmap_sem); + return down_write_killable(&mm->mmap_lock); } static inline bool mmap_write_trylock(struct mm_struct *mm) { - return down_write_trylock(&mm->mmap_sem) != 0; + return down_write_trylock(&mm->mmap_lock) != 0; } static inline void mmap_write_unlock(struct mm_struct *mm) { - up_write(&mm->mmap_sem); + up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { - downgrade_write(&mm->mmap_sem); + downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { - down_read(&mm->mmap_sem); + down_read(&mm->mmap_lock); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { - return down_read_killable(&mm->mmap_sem); + return down_read_killable(&mm->mmap_lock); } static inline bool mmap_read_trylock(struct mm_struct *mm) { - return down_read_trylock(&mm->mmap_sem) != 0; + return down_read_trylock(&mm->mmap_lock) != 0; } static inline void mmap_read_unlock(struct mm_struct *mm) { - up_read(&mm->mmap_sem); + up_read(&mm->mmap_lock); } static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) { - if (down_read_trylock(&mm->mmap_sem)) { - rwsem_release(&mm->mmap_sem.dep_map, _RET_IP_); + if (down_read_trylock(&mm->mmap_lock)) { + rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); return true; } return false; @@ -72,19 +72,19 @@ static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { - up_read_non_owner(&mm->mmap_sem); + up_read_non_owner(&mm->mmap_lock); } static inline void mmap_assert_locked(struct mm_struct *mm) { - lockdep_assert_held(&mm->mmap_sem); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); + lockdep_assert_held(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline void mmap_assert_write_locked(struct mm_struct *mm) { - lockdep_assert_held_write(&mm->mmap_sem); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); + lockdep_assert_held_write(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } #endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From c1e8d7c6a7a682e1405e3e242d32fc377fd196ff Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:54 -0700 Subject: mmap locking API: convert mmap_sem comments Convert comments that reference mmap_sem to reference mmap_lock instead. [akpm@linux-foundation.org: fix up linux-next leftovers] [akpm@linux-foundation.org: s/lockaphore/lock/, per Vlastimil] [akpm@linux-foundation.org: more linux-next fixups, per Michel] Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Daniel Jordan Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-13-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++-- include/linux/huge_mm.h | 2 +- include/linux/mempolicy.h | 2 +- include/linux/mm.h | 10 +++++----- include/linux/mm_types.h | 2 +- include/linux/mmu_notifier.h | 8 ++++---- include/linux/pagemap.h | 2 +- include/linux/pgtable.h | 6 +++--- include/linux/rmap.h | 2 +- include/linux/sched/mm.h | 10 +++++----- 10 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 01f5d296f9bb..0b026329dbed 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1679,10 +1679,10 @@ static inline int sb_start_write_trylock(struct super_block *sb) * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault + * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * - * mmap_sem + * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index cfbb0a87c5f0..71f20776b06c 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -248,7 +248,7 @@ static inline int is_swap_pmd(pmd_t pmd) return !pmd_none(pmd) && !pmd_present(pmd); } -/* mmap_sem must be held on entry */ +/* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 8165278c348a..ea9c15b60a96 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -31,7 +31,7 @@ struct mm_struct; * Locking policy for interlave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on - * mmap_sem. + * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when diff --git a/include/linux/mm.h b/include/linux/mm.h index 256c4b5b3b11..dc7b87310c10 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -402,7 +402,7 @@ extern pgprot_t protection_map[16]; * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_sem and wait when retrying. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. @@ -452,10 +452,10 @@ extern pgprot_t protection_map[16]; * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * * This is mostly used for places where we want to try to avoid taking - * the mmap_sem for too long a time when waiting for another condition + * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the - * mmap_sem in the first round to avoid potential starvation of other - * processes that would also want the mmap_sem. + * mmap_lock in the first round to avoid potential starvation of other + * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. @@ -582,7 +582,7 @@ struct vm_operations_struct { * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not - * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. + * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b6639b30a83b..64ede5f150dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -344,7 +344,7 @@ struct vm_area_struct { * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ - struct list_head anon_vma_chain; /* Serialized by mmap_sem & + struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 2f462710a1a4..fc68f3570e19 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -122,7 +122,7 @@ struct mmu_notifier_ops { /* * invalidate_range_start() and invalidate_range_end() must be - * paired and are called only when the mmap_sem and/or the + * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the @@ -213,13 +213,13 @@ struct mmu_notifier_ops { }; /* - * The notifier chains are protected by mmap_sem and/or the reverse map + * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and - * the mmap_sem locks are taken. + * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * - * 1. mmap_sem is held. + * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8e085713150c..cf2468da68e9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -538,7 +538,7 @@ static inline int lock_page_killable(struct page *page) * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. * - * Return value and mmap_sem implications depend on flags; see + * Return value and mmap_lock implications depend on flags; see * __lock_page_or_retry(). */ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 90a5d0c78fca..32b6c52d41b9 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1134,11 +1134,11 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp) #endif /* * This function is meant to be used by sites walking pagetables with - * the mmap_sem hold in read mode to protect against MADV_DONTNEED and + * the mmap_lock held in read mode to protect against MADV_DONTNEED and * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd * into a null pmd and the transhuge page fault can convert a null pmd * into an hugepmd or into a regular pmd (if the hugepage allocation - * fails). While holding the mmap_sem in read mode the pmd becomes + * fails). While holding the mmap_lock in read mode the pmd becomes * stable and stops changing under us only if it's not null and not a * transhuge pmd. When those races occurs and this function makes a * difference vs the standard pmd_none_or_clear_bad, the result is @@ -1148,7 +1148,7 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp) * * For 32bit kernels with a 64bit large pmd_t this automatically takes * care of reading the pmd atomically to avoid SMP race conditions - * against pmd_populate() when the mmap_sem is hold for reading by the + * against pmd_populate() when the mmap_lock is hold for reading by the * caller (a special atomic read not done by "gcc" as in the generic * version above, is also needed when THP is disabled because the page * fault can populate the pmd from under us). diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 988d176472df..3a6adfa70fb0 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -77,7 +77,7 @@ struct anon_vma { struct anon_vma_chain { struct vm_area_struct *vma; struct anon_vma *anon_vma; - struct list_head same_vma; /* locked by mmap_sem & page_table_lock */ + struct list_head same_vma; /* locked by mmap_lock & page_table_lock */ struct rb_node rb; /* locked by anon_vma->rwsem */ unsigned long rb_subtree_last; #ifdef CONFIG_DEBUG_VM_RB diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a132d875d351..480a4d1b7dd8 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -53,7 +53,7 @@ void mmdrop(struct mm_struct *mm); /* * This has to be called after a get_task_mm()/mmget_not_zero() - * followed by taking the mmap_sem for writing before modifying the + * followed by taking the mmap_lock for writing before modifying the * vmas or anything the coredump pretends not to change from under it. * * It also has to be called when mmgrab() is used in the context of @@ -61,14 +61,14 @@ void mmdrop(struct mm_struct *mm); * the context of the process to run down_write() on that pinned mm. * * NOTE: find_extend_vma() called from GUP context is the only place - * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * that can modify the "mm" (notably the vm_start/end) under mmap_lock * for reading and outside the context of the process, so it is also - * the only case that holds the mmap_sem for reading that must call - * this function. Generally if the mmap_sem is hold for reading + * the only case that holds the mmap_lock for reading that must call + * this function. Generally if the mmap_lock is hold for reading * there's no need of this check after get_task_mm()/mmget_not_zero(). * * This function can be obsoleted and the check can be removed, after - * the coredump code will hold the mmap_sem for writing before + * the coredump code will hold the mmap_lock for writing before * invoking the ->core_dump methods. */ static inline bool mmget_still_valid(struct mm_struct *mm) -- cgit v1.2.3 From 48c49c0e5f318e7c329d9a0ee6facce30bbb28e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:01 -0700 Subject: maccess: remove various unused weak aliases maccess tends to define lots of underscore prefixed symbols that then have other weak aliases. But except for two cases they are never actually used, so remove them. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-3-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 9861c89f93be..88d9ef56d07b 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -324,7 +324,6 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size); * happens, handle that and return -EFAULT. */ extern long probe_user_read(void *dst, const void __user *src, size_t size); -extern long __probe_user_read(void *dst, const void __user *src, size_t size); /* * probe_kernel_write(): safely attempt to write to a location @@ -336,7 +335,6 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size); * happens, handle that and return -EFAULT. */ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); -extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); /* * probe_user_write(): safely attempt to write to a location in user space @@ -348,7 +346,6 @@ extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size * happens, handle that and return -EFAULT. */ extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); -extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, -- cgit v1.2.3 From 3ed740841bf94a8028ec44164d84f9af9bd552fd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:04 -0700 Subject: maccess: remove duplicate kerneldoc comments Many of the maccess routines have a copy of the kerneldoc comment in the header. Remove it as it is not useful and will get out of sync sooner or later. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-4-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 88d9ef56d07b..4f4622b01a50 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,50 +301,12 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } -/* - * probe_kernel_read(): safely attempt to read from a location - * @dst: pointer to the buffer that shall take the data - * @src: address to read from - * @size: size of the data chunk - * - * Safely read from address @src to the buffer at @dst. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long probe_kernel_read(void *dst, const void *src, size_t size); extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size); - -/* - * probe_user_read(): safely attempt to read from a location in user space - * @dst: pointer to the buffer that shall take the data - * @src: address to read from - * @size: size of the data chunk - * - * Safely read from address @src to the buffer at @dst. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long probe_user_read(void *dst, const void __user *src, size_t size); -/* - * probe_kernel_write(): safely attempt to write to a location - * @dst: address to write to - * @src: pointer to the data that shall be written - * @size: size of the data chunk - * - * Safely write to address @dst from the buffer at @src. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); - -/* - * probe_user_write(): safely attempt to write to a location in user space - * @dst: address to write to - * @src: pointer to the data that shall be written - * @size: size of the data chunk - * - * Safely write to address @dst from the buffer at @src. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -- cgit v1.2.3 From bd88bb5d4007949be7154deae7cef7173c751a95 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:14 -0700 Subject: maccess: rename strncpy_from_unsafe_user to strncpy_from_user_nofault This matches the naming of strncpy_from_user, and also makes it more clear what the function is supposed to do. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-7-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 4f4622b01a50..d1a4fa66067c 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -313,8 +313,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count); extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, - long count); +long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, + long count); extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); /** -- cgit v1.2.3 From c4cb164426aebd635baa53685b0ebf1a127e9803 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:17 -0700 Subject: maccess: rename strncpy_from_unsafe_strict to strncpy_from_kernel_nofault This matches the naming of strncpy_from_user_nofault, and also makes it more clear what the function is supposed to do. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-8-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d1a4fa66067c..d9ae3c69802d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -310,8 +310,8 @@ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, - long count); +long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, + long count); extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); -- cgit v1.2.3 From 02dddb160ec1dccb51e75f3113654a090bc3963a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:20 -0700 Subject: maccess: rename strnlen_unsafe_user to strnlen_user_nofault This matches the naming of strnlen_user, and also makes it more clear what the function is supposed to do. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-9-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d9ae3c69802d..575cc308d98b 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -315,7 +315,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); -extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); +long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * probe_kernel_address(): safely attempt to read from a location -- cgit v1.2.3 From eab0c6089b68974ebc6a9a7eab68456eeb6a99c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:27 -0700 Subject: maccess: unify the probe kernel arch hooks Currently architectures have to override every routine that probes kernel memory, which includes a pure read and strcpy, both in strict and not strict variants. Just provide a single arch hooks instead to make sure all architectures cover all the cases. [akpm@linux-foundation.org: fix !CONFIG_X86_64 build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-11-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 575cc308d98b..bb3ab8227850 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,9 +301,11 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } +bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, + bool strict); + extern long probe_kernel_read(void *dst, const void *src, size_t size); extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); -extern long __probe_kernel_read(void *dst, const void *src, size_t size); extern long probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); @@ -312,7 +314,7 @@ extern long notrace probe_user_write(void __user *dst, const void *src, size_t s extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); -extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); + long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); -- cgit v1.2.3 From 7676fbf21b5fa04341c8046c2cbcd1949293e7ec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:47 -0700 Subject: maccess: remove strncpy_from_unsafe All users are gone now. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-16-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index bb3ab8227850..4183e585dee6 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -311,7 +311,6 @@ extern long probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); -extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); -- cgit v1.2.3 From 98a23609b10364a51a1bb3688f8dd1cd1aa94a9a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:50 -0700 Subject: maccess: always use strict semantics for probe_kernel_read Except for historical confusion in the kprobes/uprobes and bpf tracers, which has been fixed now, there is no good reason to ever allow user memory accesses from probe_kernel_read. Switch probe_kernel_read to only read from kernel memory. [akpm@linux-foundation.org: update it for "mm, dump_page(): do not crash with invalid mapping pointer"] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-17-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 4183e585dee6..dac1db05bf7e 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,11 +301,9 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, - bool strict); +bool probe_kernel_read_allowed(const void *unsafe_src, size_t size); extern long probe_kernel_read(void *dst, const void *src, size_t size); -extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); -- cgit v1.2.3 From 4fa7252338a56fbc90220e6330f136a379175a7a Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Mon, 8 Jun 2020 21:35:07 -0700 Subject: include/linux/cache.h: expand documentation over __read_mostly __read_mostly can easily be misused by folks, its not meant for just read-only data. There are performance reasons for using it, but we also don't provide any guidance about its use. Provide a bit more guidance over its use. Signed-off-by: Luis Chamberlain Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Acked-by: Christoph Lameter Acked-by: Rafael Aquini Cc: Arnd Bergmann Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200507161424.2584-1-mcgrof@kernel.org Signed-off-by: Linus Torvalds --- include/linux/cache.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cache.h b/include/linux/cache.h index 750621e41d1c..1aa8009f6d06 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -15,8 +15,14 @@ /* * __read_mostly is used to keep rarely changing variables out of frequently - * updated cachelines. If an architecture doesn't support it, ignore the - * hint. + * updated cachelines. Its use should be reserved for data that is used + * frequently in hot paths. Performance traces can help decide when to use + * this. You want __read_mostly data to be tightly packed, so that in the + * best case multiple frequently read variables for a hot path will be next + * to each other in order to reduce the number of cachelines needed to + * execute a critical path. We should be mindful and selective of its use. + * ie: if you're going to use it please supply a *good* justification in your + * commit log */ #ifndef __read_mostly #define __read_mostly -- cgit v1.2.3 From 765dcd209947e7b3666c08fb109ab8b879f7a471 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 26 Nov 2019 15:04:05 +0100 Subject: asm-generic/atomic: Use __always_inline for fallback wrappers Use __always_inline for atomic fallback wrappers. When building for size (CC_OPTIMIZE_FOR_SIZE), some compilers appear to be less inclined to inline even relatively small static inline functions that are assumed to be inlinable such as atomic ops. This can cause problems, for example in UACCESS regions. While the fallback wrappers aren't pure wrappers, they are trivial nonetheless, and the function they wrap should determine the final inlining policy. For x86 tinyconfig we observe: - vmlinux baseline: 1315988 - vmlinux with patch: 1315928 (-60 bytes) [ tglx: Cherry-picked from KCSAN ] Suggested-by: Mark Rutland Signed-off-by: Marco Elver Acked-by: Mark Rutland Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner --- include/linux/atomic-fallback.h | 340 ++++++++++++++++++++-------------------- 1 file changed, 171 insertions(+), 169 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h index a7d240e465c0..656b5489b673 100644 --- a/include/linux/atomic-fallback.h +++ b/include/linux/atomic-fallback.h @@ -6,6 +6,8 @@ #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H +#include + #ifndef xchg_relaxed #define xchg_relaxed xchg #define xchg_acquire xchg @@ -76,7 +78,7 @@ #endif /* cmpxchg64_relaxed */ #ifndef atomic_read_acquire -static inline int +static __always_inline int atomic_read_acquire(const atomic_t *v) { return smp_load_acquire(&(v)->counter); @@ -85,7 +87,7 @@ atomic_read_acquire(const atomic_t *v) #endif #ifndef atomic_set_release -static inline void +static __always_inline void atomic_set_release(atomic_t *v, int i) { smp_store_release(&(v)->counter, i); @@ -100,7 +102,7 @@ atomic_set_release(atomic_t *v, int i) #else /* atomic_add_return_relaxed */ #ifndef atomic_add_return_acquire -static inline int +static __always_inline int atomic_add_return_acquire(int i, atomic_t *v) { int ret = atomic_add_return_relaxed(i, v); @@ -111,7 +113,7 @@ atomic_add_return_acquire(int i, atomic_t *v) #endif #ifndef atomic_add_return_release -static inline int +static __always_inline int atomic_add_return_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -121,7 +123,7 @@ atomic_add_return_release(int i, atomic_t *v) #endif #ifndef atomic_add_return -static inline int +static __always_inline int atomic_add_return(int i, atomic_t *v) { int ret; @@ -142,7 +144,7 @@ atomic_add_return(int i, atomic_t *v) #else /* atomic_fetch_add_relaxed */ #ifndef atomic_fetch_add_acquire -static inline int +static __always_inline int atomic_fetch_add_acquire(int i, atomic_t *v) { int ret = atomic_fetch_add_relaxed(i, v); @@ -153,7 +155,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_add_release -static inline int +static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -163,7 +165,7 @@ atomic_fetch_add_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_add -static inline int +static __always_inline int atomic_fetch_add(int i, atomic_t *v) { int ret; @@ -184,7 +186,7 @@ atomic_fetch_add(int i, atomic_t *v) #else /* atomic_sub_return_relaxed */ #ifndef atomic_sub_return_acquire -static inline int +static __always_inline int atomic_sub_return_acquire(int i, atomic_t *v) { int ret = atomic_sub_return_relaxed(i, v); @@ -195,7 +197,7 @@ atomic_sub_return_acquire(int i, atomic_t *v) #endif #ifndef atomic_sub_return_release -static inline int +static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -205,7 +207,7 @@ atomic_sub_return_release(int i, atomic_t *v) #endif #ifndef atomic_sub_return -static inline int +static __always_inline int atomic_sub_return(int i, atomic_t *v) { int ret; @@ -226,7 +228,7 @@ atomic_sub_return(int i, atomic_t *v) #else /* atomic_fetch_sub_relaxed */ #ifndef atomic_fetch_sub_acquire -static inline int +static __always_inline int atomic_fetch_sub_acquire(int i, atomic_t *v) { int ret = atomic_fetch_sub_relaxed(i, v); @@ -237,7 +239,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_sub_release -static inline int +static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -247,7 +249,7 @@ atomic_fetch_sub_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_sub -static inline int +static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { int ret; @@ -262,7 +264,7 @@ atomic_fetch_sub(int i, atomic_t *v) #endif /* atomic_fetch_sub_relaxed */ #ifndef atomic_inc -static inline void +static __always_inline void atomic_inc(atomic_t *v) { atomic_add(1, v); @@ -278,7 +280,7 @@ atomic_inc(atomic_t *v) #endif /* atomic_inc_return */ #ifndef atomic_inc_return -static inline int +static __always_inline int atomic_inc_return(atomic_t *v) { return atomic_add_return(1, v); @@ -287,7 +289,7 @@ atomic_inc_return(atomic_t *v) #endif #ifndef atomic_inc_return_acquire -static inline int +static __always_inline int atomic_inc_return_acquire(atomic_t *v) { return atomic_add_return_acquire(1, v); @@ -296,7 +298,7 @@ atomic_inc_return_acquire(atomic_t *v) #endif #ifndef atomic_inc_return_release -static inline int +static __always_inline int atomic_inc_return_release(atomic_t *v) { return atomic_add_return_release(1, v); @@ -305,7 +307,7 @@ atomic_inc_return_release(atomic_t *v) #endif #ifndef atomic_inc_return_relaxed -static inline int +static __always_inline int atomic_inc_return_relaxed(atomic_t *v) { return atomic_add_return_relaxed(1, v); @@ -316,7 +318,7 @@ atomic_inc_return_relaxed(atomic_t *v) #else /* atomic_inc_return_relaxed */ #ifndef atomic_inc_return_acquire -static inline int +static __always_inline int atomic_inc_return_acquire(atomic_t *v) { int ret = atomic_inc_return_relaxed(v); @@ -327,7 +329,7 @@ atomic_inc_return_acquire(atomic_t *v) #endif #ifndef atomic_inc_return_release -static inline int +static __always_inline int atomic_inc_return_release(atomic_t *v) { __atomic_release_fence(); @@ -337,7 +339,7 @@ atomic_inc_return_release(atomic_t *v) #endif #ifndef atomic_inc_return -static inline int +static __always_inline int atomic_inc_return(atomic_t *v) { int ret; @@ -359,7 +361,7 @@ atomic_inc_return(atomic_t *v) #endif /* atomic_fetch_inc */ #ifndef atomic_fetch_inc -static inline int +static __always_inline int atomic_fetch_inc(atomic_t *v) { return atomic_fetch_add(1, v); @@ -368,7 +370,7 @@ atomic_fetch_inc(atomic_t *v) #endif #ifndef atomic_fetch_inc_acquire -static inline int +static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { return atomic_fetch_add_acquire(1, v); @@ -377,7 +379,7 @@ atomic_fetch_inc_acquire(atomic_t *v) #endif #ifndef atomic_fetch_inc_release -static inline int +static __always_inline int atomic_fetch_inc_release(atomic_t *v) { return atomic_fetch_add_release(1, v); @@ -386,7 +388,7 @@ atomic_fetch_inc_release(atomic_t *v) #endif #ifndef atomic_fetch_inc_relaxed -static inline int +static __always_inline int atomic_fetch_inc_relaxed(atomic_t *v) { return atomic_fetch_add_relaxed(1, v); @@ -397,7 +399,7 @@ atomic_fetch_inc_relaxed(atomic_t *v) #else /* atomic_fetch_inc_relaxed */ #ifndef atomic_fetch_inc_acquire -static inline int +static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { int ret = atomic_fetch_inc_relaxed(v); @@ -408,7 +410,7 @@ atomic_fetch_inc_acquire(atomic_t *v) #endif #ifndef atomic_fetch_inc_release -static inline int +static __always_inline int atomic_fetch_inc_release(atomic_t *v) { __atomic_release_fence(); @@ -418,7 +420,7 @@ atomic_fetch_inc_release(atomic_t *v) #endif #ifndef atomic_fetch_inc -static inline int +static __always_inline int atomic_fetch_inc(atomic_t *v) { int ret; @@ -433,7 +435,7 @@ atomic_fetch_inc(atomic_t *v) #endif /* atomic_fetch_inc_relaxed */ #ifndef atomic_dec -static inline void +static __always_inline void atomic_dec(atomic_t *v) { atomic_sub(1, v); @@ -449,7 +451,7 @@ atomic_dec(atomic_t *v) #endif /* atomic_dec_return */ #ifndef atomic_dec_return -static inline int +static __always_inline int atomic_dec_return(atomic_t *v) { return atomic_sub_return(1, v); @@ -458,7 +460,7 @@ atomic_dec_return(atomic_t *v) #endif #ifndef atomic_dec_return_acquire -static inline int +static __always_inline int atomic_dec_return_acquire(atomic_t *v) { return atomic_sub_return_acquire(1, v); @@ -467,7 +469,7 @@ atomic_dec_return_acquire(atomic_t *v) #endif #ifndef atomic_dec_return_release -static inline int +static __always_inline int atomic_dec_return_release(atomic_t *v) { return atomic_sub_return_release(1, v); @@ -476,7 +478,7 @@ atomic_dec_return_release(atomic_t *v) #endif #ifndef atomic_dec_return_relaxed -static inline int +static __always_inline int atomic_dec_return_relaxed(atomic_t *v) { return atomic_sub_return_relaxed(1, v); @@ -487,7 +489,7 @@ atomic_dec_return_relaxed(atomic_t *v) #else /* atomic_dec_return_relaxed */ #ifndef atomic_dec_return_acquire -static inline int +static __always_inline int atomic_dec_return_acquire(atomic_t *v) { int ret = atomic_dec_return_relaxed(v); @@ -498,7 +500,7 @@ atomic_dec_return_acquire(atomic_t *v) #endif #ifndef atomic_dec_return_release -static inline int +static __always_inline int atomic_dec_return_release(atomic_t *v) { __atomic_release_fence(); @@ -508,7 +510,7 @@ atomic_dec_return_release(atomic_t *v) #endif #ifndef atomic_dec_return -static inline int +static __always_inline int atomic_dec_return(atomic_t *v) { int ret; @@ -530,7 +532,7 @@ atomic_dec_return(atomic_t *v) #endif /* atomic_fetch_dec */ #ifndef atomic_fetch_dec -static inline int +static __always_inline int atomic_fetch_dec(atomic_t *v) { return atomic_fetch_sub(1, v); @@ -539,7 +541,7 @@ atomic_fetch_dec(atomic_t *v) #endif #ifndef atomic_fetch_dec_acquire -static inline int +static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { return atomic_fetch_sub_acquire(1, v); @@ -548,7 +550,7 @@ atomic_fetch_dec_acquire(atomic_t *v) #endif #ifndef atomic_fetch_dec_release -static inline int +static __always_inline int atomic_fetch_dec_release(atomic_t *v) { return atomic_fetch_sub_release(1, v); @@ -557,7 +559,7 @@ atomic_fetch_dec_release(atomic_t *v) #endif #ifndef atomic_fetch_dec_relaxed -static inline int +static __always_inline int atomic_fetch_dec_relaxed(atomic_t *v) { return atomic_fetch_sub_relaxed(1, v); @@ -568,7 +570,7 @@ atomic_fetch_dec_relaxed(atomic_t *v) #else /* atomic_fetch_dec_relaxed */ #ifndef atomic_fetch_dec_acquire -static inline int +static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { int ret = atomic_fetch_dec_relaxed(v); @@ -579,7 +581,7 @@ atomic_fetch_dec_acquire(atomic_t *v) #endif #ifndef atomic_fetch_dec_release -static inline int +static __always_inline int atomic_fetch_dec_release(atomic_t *v) { __atomic_release_fence(); @@ -589,7 +591,7 @@ atomic_fetch_dec_release(atomic_t *v) #endif #ifndef atomic_fetch_dec -static inline int +static __always_inline int atomic_fetch_dec(atomic_t *v) { int ret; @@ -610,7 +612,7 @@ atomic_fetch_dec(atomic_t *v) #else /* atomic_fetch_and_relaxed */ #ifndef atomic_fetch_and_acquire -static inline int +static __always_inline int atomic_fetch_and_acquire(int i, atomic_t *v) { int ret = atomic_fetch_and_relaxed(i, v); @@ -621,7 +623,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_and_release -static inline int +static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -631,7 +633,7 @@ atomic_fetch_and_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_and -static inline int +static __always_inline int atomic_fetch_and(int i, atomic_t *v) { int ret; @@ -646,7 +648,7 @@ atomic_fetch_and(int i, atomic_t *v) #endif /* atomic_fetch_and_relaxed */ #ifndef atomic_andnot -static inline void +static __always_inline void atomic_andnot(int i, atomic_t *v) { atomic_and(~i, v); @@ -662,7 +664,7 @@ atomic_andnot(int i, atomic_t *v) #endif /* atomic_fetch_andnot */ #ifndef atomic_fetch_andnot -static inline int +static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { return atomic_fetch_and(~i, v); @@ -671,7 +673,7 @@ atomic_fetch_andnot(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_acquire -static inline int +static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { return atomic_fetch_and_acquire(~i, v); @@ -680,7 +682,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_release -static inline int +static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { return atomic_fetch_and_release(~i, v); @@ -689,7 +691,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_relaxed -static inline int +static __always_inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) { return atomic_fetch_and_relaxed(~i, v); @@ -700,7 +702,7 @@ atomic_fetch_andnot_relaxed(int i, atomic_t *v) #else /* atomic_fetch_andnot_relaxed */ #ifndef atomic_fetch_andnot_acquire -static inline int +static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { int ret = atomic_fetch_andnot_relaxed(i, v); @@ -711,7 +713,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_release -static inline int +static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -721,7 +723,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot -static inline int +static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { int ret; @@ -742,7 +744,7 @@ atomic_fetch_andnot(int i, atomic_t *v) #else /* atomic_fetch_or_relaxed */ #ifndef atomic_fetch_or_acquire -static inline int +static __always_inline int atomic_fetch_or_acquire(int i, atomic_t *v) { int ret = atomic_fetch_or_relaxed(i, v); @@ -753,7 +755,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_or_release -static inline int +static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -763,7 +765,7 @@ atomic_fetch_or_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_or -static inline int +static __always_inline int atomic_fetch_or(int i, atomic_t *v) { int ret; @@ -784,7 +786,7 @@ atomic_fetch_or(int i, atomic_t *v) #else /* atomic_fetch_xor_relaxed */ #ifndef atomic_fetch_xor_acquire -static inline int +static __always_inline int atomic_fetch_xor_acquire(int i, atomic_t *v) { int ret = atomic_fetch_xor_relaxed(i, v); @@ -795,7 +797,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_xor_release -static inline int +static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -805,7 +807,7 @@ atomic_fetch_xor_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_xor -static inline int +static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { int ret; @@ -826,7 +828,7 @@ atomic_fetch_xor(int i, atomic_t *v) #else /* atomic_xchg_relaxed */ #ifndef atomic_xchg_acquire -static inline int +static __always_inline int atomic_xchg_acquire(atomic_t *v, int i) { int ret = atomic_xchg_relaxed(v, i); @@ -837,7 +839,7 @@ atomic_xchg_acquire(atomic_t *v, int i) #endif #ifndef atomic_xchg_release -static inline int +static __always_inline int atomic_xchg_release(atomic_t *v, int i) { __atomic_release_fence(); @@ -847,7 +849,7 @@ atomic_xchg_release(atomic_t *v, int i) #endif #ifndef atomic_xchg -static inline int +static __always_inline int atomic_xchg(atomic_t *v, int i) { int ret; @@ -868,7 +870,7 @@ atomic_xchg(atomic_t *v, int i) #else /* atomic_cmpxchg_relaxed */ #ifndef atomic_cmpxchg_acquire -static inline int +static __always_inline int atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { int ret = atomic_cmpxchg_relaxed(v, old, new); @@ -879,7 +881,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) #endif #ifndef atomic_cmpxchg_release -static inline int +static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { __atomic_release_fence(); @@ -889,7 +891,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new) #endif #ifndef atomic_cmpxchg -static inline int +static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -911,7 +913,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new) #endif /* atomic_try_cmpxchg */ #ifndef atomic_try_cmpxchg -static inline bool +static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { int r, o = *old; @@ -924,7 +926,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { int r, o = *old; @@ -937,7 +939,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_release -static inline bool +static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { int r, o = *old; @@ -950,7 +952,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_relaxed -static inline bool +static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { int r, o = *old; @@ -965,7 +967,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) #else /* atomic_try_cmpxchg_relaxed */ #ifndef atomic_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { bool ret = atomic_try_cmpxchg_relaxed(v, old, new); @@ -976,7 +978,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_release -static inline bool +static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { __atomic_release_fence(); @@ -986,7 +988,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg -static inline bool +static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { bool ret; @@ -1010,7 +1012,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) * true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { return atomic_sub_return(i, v) == 0; @@ -1027,7 +1029,7 @@ atomic_sub_and_test(int i, atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline bool +static __always_inline bool atomic_dec_and_test(atomic_t *v) { return atomic_dec_return(v) == 0; @@ -1044,7 +1046,7 @@ atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic_inc_and_test(atomic_t *v) { return atomic_inc_return(v) == 0; @@ -1062,7 +1064,7 @@ atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool +static __always_inline bool atomic_add_negative(int i, atomic_t *v) { return atomic_add_return(i, v) < 0; @@ -1080,7 +1082,7 @@ atomic_add_negative(int i, atomic_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ -static inline int +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c = atomic_read(v); @@ -1105,7 +1107,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -static inline bool +static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { return atomic_fetch_add_unless(v, a, u) != u; @@ -1121,7 +1123,7 @@ atomic_add_unless(atomic_t *v, int a, int u) * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ -static inline bool +static __always_inline bool atomic_inc_not_zero(atomic_t *v) { return atomic_add_unless(v, 1, 0); @@ -1130,7 +1132,7 @@ atomic_inc_not_zero(atomic_t *v) #endif #ifndef atomic_inc_unless_negative -static inline bool +static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { int c = atomic_read(v); @@ -1146,7 +1148,7 @@ atomic_inc_unless_negative(atomic_t *v) #endif #ifndef atomic_dec_unless_positive -static inline bool +static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { int c = atomic_read(v); @@ -1162,7 +1164,7 @@ atomic_dec_unless_positive(atomic_t *v) #endif #ifndef atomic_dec_if_positive -static inline int +static __always_inline int atomic_dec_if_positive(atomic_t *v) { int dec, c = atomic_read(v); @@ -1186,7 +1188,7 @@ atomic_dec_if_positive(atomic_t *v) #endif #ifndef atomic64_read_acquire -static inline s64 +static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) { return smp_load_acquire(&(v)->counter); @@ -1195,7 +1197,7 @@ atomic64_read_acquire(const atomic64_t *v) #endif #ifndef atomic64_set_release -static inline void +static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { smp_store_release(&(v)->counter, i); @@ -1210,7 +1212,7 @@ atomic64_set_release(atomic64_t *v, s64 i) #else /* atomic64_add_return_relaxed */ #ifndef atomic64_add_return_acquire -static inline s64 +static __always_inline s64 atomic64_add_return_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_add_return_relaxed(i, v); @@ -1221,7 +1223,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_add_return_release -static inline s64 +static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1231,7 +1233,7 @@ atomic64_add_return_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_add_return -static inline s64 +static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { s64 ret; @@ -1252,7 +1254,7 @@ atomic64_add_return(s64 i, atomic64_t *v) #else /* atomic64_fetch_add_relaxed */ #ifndef atomic64_fetch_add_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_add_relaxed(i, v); @@ -1263,7 +1265,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_add_release -static inline s64 +static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1273,7 +1275,7 @@ atomic64_fetch_add_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_add -static inline s64 +static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { s64 ret; @@ -1294,7 +1296,7 @@ atomic64_fetch_add(s64 i, atomic64_t *v) #else /* atomic64_sub_return_relaxed */ #ifndef atomic64_sub_return_acquire -static inline s64 +static __always_inline s64 atomic64_sub_return_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_sub_return_relaxed(i, v); @@ -1305,7 +1307,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_sub_return_release -static inline s64 +static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1315,7 +1317,7 @@ atomic64_sub_return_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_sub_return -static inline s64 +static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { s64 ret; @@ -1336,7 +1338,7 @@ atomic64_sub_return(s64 i, atomic64_t *v) #else /* atomic64_fetch_sub_relaxed */ #ifndef atomic64_fetch_sub_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_sub_relaxed(i, v); @@ -1347,7 +1349,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_sub_release -static inline s64 +static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1357,7 +1359,7 @@ atomic64_fetch_sub_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_sub -static inline s64 +static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { s64 ret; @@ -1372,7 +1374,7 @@ atomic64_fetch_sub(s64 i, atomic64_t *v) #endif /* atomic64_fetch_sub_relaxed */ #ifndef atomic64_inc -static inline void +static __always_inline void atomic64_inc(atomic64_t *v) { atomic64_add(1, v); @@ -1388,7 +1390,7 @@ atomic64_inc(atomic64_t *v) #endif /* atomic64_inc_return */ #ifndef atomic64_inc_return -static inline s64 +static __always_inline s64 atomic64_inc_return(atomic64_t *v) { return atomic64_add_return(1, v); @@ -1397,7 +1399,7 @@ atomic64_inc_return(atomic64_t *v) #endif #ifndef atomic64_inc_return_acquire -static inline s64 +static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { return atomic64_add_return_acquire(1, v); @@ -1406,7 +1408,7 @@ atomic64_inc_return_acquire(atomic64_t *v) #endif #ifndef atomic64_inc_return_release -static inline s64 +static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { return atomic64_add_return_release(1, v); @@ -1415,7 +1417,7 @@ atomic64_inc_return_release(atomic64_t *v) #endif #ifndef atomic64_inc_return_relaxed -static inline s64 +static __always_inline s64 atomic64_inc_return_relaxed(atomic64_t *v) { return atomic64_add_return_relaxed(1, v); @@ -1426,7 +1428,7 @@ atomic64_inc_return_relaxed(atomic64_t *v) #else /* atomic64_inc_return_relaxed */ #ifndef atomic64_inc_return_acquire -static inline s64 +static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { s64 ret = atomic64_inc_return_relaxed(v); @@ -1437,7 +1439,7 @@ atomic64_inc_return_acquire(atomic64_t *v) #endif #ifndef atomic64_inc_return_release -static inline s64 +static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { __atomic_release_fence(); @@ -1447,7 +1449,7 @@ atomic64_inc_return_release(atomic64_t *v) #endif #ifndef atomic64_inc_return -static inline s64 +static __always_inline s64 atomic64_inc_return(atomic64_t *v) { s64 ret; @@ -1469,7 +1471,7 @@ atomic64_inc_return(atomic64_t *v) #endif /* atomic64_fetch_inc */ #ifndef atomic64_fetch_inc -static inline s64 +static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { return atomic64_fetch_add(1, v); @@ -1478,7 +1480,7 @@ atomic64_fetch_inc(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { return atomic64_fetch_add_acquire(1, v); @@ -1487,7 +1489,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_release -static inline s64 +static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { return atomic64_fetch_add_release(1, v); @@ -1496,7 +1498,7 @@ atomic64_fetch_inc_release(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_inc_relaxed(atomic64_t *v) { return atomic64_fetch_add_relaxed(1, v); @@ -1507,7 +1509,7 @@ atomic64_fetch_inc_relaxed(atomic64_t *v) #else /* atomic64_fetch_inc_relaxed */ #ifndef atomic64_fetch_inc_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { s64 ret = atomic64_fetch_inc_relaxed(v); @@ -1518,7 +1520,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_release -static inline s64 +static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { __atomic_release_fence(); @@ -1528,7 +1530,7 @@ atomic64_fetch_inc_release(atomic64_t *v) #endif #ifndef atomic64_fetch_inc -static inline s64 +static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { s64 ret; @@ -1543,7 +1545,7 @@ atomic64_fetch_inc(atomic64_t *v) #endif /* atomic64_fetch_inc_relaxed */ #ifndef atomic64_dec -static inline void +static __always_inline void atomic64_dec(atomic64_t *v) { atomic64_sub(1, v); @@ -1559,7 +1561,7 @@ atomic64_dec(atomic64_t *v) #endif /* atomic64_dec_return */ #ifndef atomic64_dec_return -static inline s64 +static __always_inline s64 atomic64_dec_return(atomic64_t *v) { return atomic64_sub_return(1, v); @@ -1568,7 +1570,7 @@ atomic64_dec_return(atomic64_t *v) #endif #ifndef atomic64_dec_return_acquire -static inline s64 +static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { return atomic64_sub_return_acquire(1, v); @@ -1577,7 +1579,7 @@ atomic64_dec_return_acquire(atomic64_t *v) #endif #ifndef atomic64_dec_return_release -static inline s64 +static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { return atomic64_sub_return_release(1, v); @@ -1586,7 +1588,7 @@ atomic64_dec_return_release(atomic64_t *v) #endif #ifndef atomic64_dec_return_relaxed -static inline s64 +static __always_inline s64 atomic64_dec_return_relaxed(atomic64_t *v) { return atomic64_sub_return_relaxed(1, v); @@ -1597,7 +1599,7 @@ atomic64_dec_return_relaxed(atomic64_t *v) #else /* atomic64_dec_return_relaxed */ #ifndef atomic64_dec_return_acquire -static inline s64 +static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { s64 ret = atomic64_dec_return_relaxed(v); @@ -1608,7 +1610,7 @@ atomic64_dec_return_acquire(atomic64_t *v) #endif #ifndef atomic64_dec_return_release -static inline s64 +static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { __atomic_release_fence(); @@ -1618,7 +1620,7 @@ atomic64_dec_return_release(atomic64_t *v) #endif #ifndef atomic64_dec_return -static inline s64 +static __always_inline s64 atomic64_dec_return(atomic64_t *v) { s64 ret; @@ -1640,7 +1642,7 @@ atomic64_dec_return(atomic64_t *v) #endif /* atomic64_fetch_dec */ #ifndef atomic64_fetch_dec -static inline s64 +static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { return atomic64_fetch_sub(1, v); @@ -1649,7 +1651,7 @@ atomic64_fetch_dec(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { return atomic64_fetch_sub_acquire(1, v); @@ -1658,7 +1660,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_release -static inline s64 +static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { return atomic64_fetch_sub_release(1, v); @@ -1667,7 +1669,7 @@ atomic64_fetch_dec_release(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_dec_relaxed(atomic64_t *v) { return atomic64_fetch_sub_relaxed(1, v); @@ -1678,7 +1680,7 @@ atomic64_fetch_dec_relaxed(atomic64_t *v) #else /* atomic64_fetch_dec_relaxed */ #ifndef atomic64_fetch_dec_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { s64 ret = atomic64_fetch_dec_relaxed(v); @@ -1689,7 +1691,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_release -static inline s64 +static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { __atomic_release_fence(); @@ -1699,7 +1701,7 @@ atomic64_fetch_dec_release(atomic64_t *v) #endif #ifndef atomic64_fetch_dec -static inline s64 +static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { s64 ret; @@ -1720,7 +1722,7 @@ atomic64_fetch_dec(atomic64_t *v) #else /* atomic64_fetch_and_relaxed */ #ifndef atomic64_fetch_and_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_and_relaxed(i, v); @@ -1731,7 +1733,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_and_release -static inline s64 +static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1741,7 +1743,7 @@ atomic64_fetch_and_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_and -static inline s64 +static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { s64 ret; @@ -1756,7 +1758,7 @@ atomic64_fetch_and(s64 i, atomic64_t *v) #endif /* atomic64_fetch_and_relaxed */ #ifndef atomic64_andnot -static inline void +static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) { atomic64_and(~i, v); @@ -1772,7 +1774,7 @@ atomic64_andnot(s64 i, atomic64_t *v) #endif /* atomic64_fetch_andnot */ #ifndef atomic64_fetch_andnot -static inline s64 +static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { return atomic64_fetch_and(~i, v); @@ -1781,7 +1783,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { return atomic64_fetch_and_acquire(~i, v); @@ -1790,7 +1792,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_release -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { return atomic64_fetch_and_release(~i, v); @@ -1799,7 +1801,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { return atomic64_fetch_and_relaxed(~i, v); @@ -1810,7 +1812,7 @@ atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) #else /* atomic64_fetch_andnot_relaxed */ #ifndef atomic64_fetch_andnot_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_andnot_relaxed(i, v); @@ -1821,7 +1823,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_release -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1831,7 +1833,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot -static inline s64 +static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { s64 ret; @@ -1852,7 +1854,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #else /* atomic64_fetch_or_relaxed */ #ifndef atomic64_fetch_or_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_or_relaxed(i, v); @@ -1863,7 +1865,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_or_release -static inline s64 +static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1873,7 +1875,7 @@ atomic64_fetch_or_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_or -static inline s64 +static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { s64 ret; @@ -1894,7 +1896,7 @@ atomic64_fetch_or(s64 i, atomic64_t *v) #else /* atomic64_fetch_xor_relaxed */ #ifndef atomic64_fetch_xor_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_xor_relaxed(i, v); @@ -1905,7 +1907,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_xor_release -static inline s64 +static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1915,7 +1917,7 @@ atomic64_fetch_xor_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_xor -static inline s64 +static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 ret; @@ -1936,7 +1938,7 @@ atomic64_fetch_xor(s64 i, atomic64_t *v) #else /* atomic64_xchg_relaxed */ #ifndef atomic64_xchg_acquire -static inline s64 +static __always_inline s64 atomic64_xchg_acquire(atomic64_t *v, s64 i) { s64 ret = atomic64_xchg_relaxed(v, i); @@ -1947,7 +1949,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i) #endif #ifndef atomic64_xchg_release -static inline s64 +static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 i) { __atomic_release_fence(); @@ -1957,7 +1959,7 @@ atomic64_xchg_release(atomic64_t *v, s64 i) #endif #ifndef atomic64_xchg -static inline s64 +static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i) { s64 ret; @@ -1978,7 +1980,7 @@ atomic64_xchg(atomic64_t *v, s64 i) #else /* atomic64_cmpxchg_relaxed */ #ifndef atomic64_cmpxchg_acquire -static inline s64 +static __always_inline s64 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { s64 ret = atomic64_cmpxchg_relaxed(v, old, new); @@ -1989,7 +1991,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) #endif #ifndef atomic64_cmpxchg_release -static inline s64 +static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { __atomic_release_fence(); @@ -1999,7 +2001,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) #endif #ifndef atomic64_cmpxchg -static inline s64 +static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { s64 ret; @@ -2021,7 +2023,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) #endif /* atomic64_try_cmpxchg */ #ifndef atomic64_try_cmpxchg -static inline bool +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2034,7 +2036,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2047,7 +2049,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_release -static inline bool +static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2060,7 +2062,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_relaxed -static inline bool +static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2075,7 +2077,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) #else /* atomic64_try_cmpxchg_relaxed */ #ifndef atomic64_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { bool ret = atomic64_try_cmpxchg_relaxed(v, old, new); @@ -2086,7 +2088,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_release -static inline bool +static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { __atomic_release_fence(); @@ -2096,7 +2098,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg -static inline bool +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { bool ret; @@ -2120,7 +2122,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) * true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { return atomic64_sub_return(i, v) == 0; @@ -2137,7 +2139,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline bool +static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { return atomic64_dec_return(v) == 0; @@ -2154,7 +2156,7 @@ atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { return atomic64_inc_return(v) == 0; @@ -2172,7 +2174,7 @@ atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool +static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { return atomic64_add_return(i, v) < 0; @@ -2190,7 +2192,7 @@ atomic64_add_negative(s64 i, atomic64_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ -static inline s64 +static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { s64 c = atomic64_read(v); @@ -2215,7 +2217,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -static inline bool +static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { return atomic64_fetch_add_unless(v, a, u) != u; @@ -2231,7 +2233,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ -static inline bool +static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { return atomic64_add_unless(v, 1, 0); @@ -2240,7 +2242,7 @@ atomic64_inc_not_zero(atomic64_t *v) #endif #ifndef atomic64_inc_unless_negative -static inline bool +static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { s64 c = atomic64_read(v); @@ -2256,7 +2258,7 @@ atomic64_inc_unless_negative(atomic64_t *v) #endif #ifndef atomic64_dec_unless_positive -static inline bool +static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { s64 c = atomic64_read(v); @@ -2272,7 +2274,7 @@ atomic64_dec_unless_positive(atomic64_t *v) #endif #ifndef atomic64_dec_if_positive -static inline s64 +static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { s64 dec, c = atomic64_read(v); @@ -2292,4 +2294,4 @@ atomic64_dec_if_positive(atomic64_t *v) #define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 25de4a2804d70f57e994fe3b419148658bb5378a +// baaf45f4c24ed88ceae58baca39d7fd80bb8101b -- cgit v1.2.3 From 37f8173dd84936ea78000ed1cad24f8b18d48ebb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 24 Jan 2020 22:13:03 +0100 Subject: locking/atomics: Flip fallbacks and instrumentation Currently instrumentation of atomic primitives is done at the architecture level, while composites or fallbacks are provided at the generic level. The result is that there are no uninstrumented variants of the fallbacks. Since there is now need of such variants to isolate text poke from any form of instrumentation invert this ordering. Doing this means moving the instrumentation into the generic code as well as having (for now) two variants of the fallbacks. Notes: - the various *cond_read* primitives are not proper fallbacks and got moved into linux/atomic.c. No arch_ variants are generated because the base primitives smp_cond_load*() are instrumented. - once all architectures are moved over to arch_atomic_ one of the fallback variants can be removed and some 2300 lines reclaimed. - atomic_{read,set}*() are no longer double-instrumented Reported-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Mark Rutland Link: https://lkml.kernel.org/r/20200505134058.769149955@linutronix.de --- include/linux/atomic-arch-fallback.h | 2291 ++++++++++++++++++++++++++++++++++ include/linux/atomic-fallback.h | 8 +- include/linux/atomic.h | 11 + 3 files changed, 2303 insertions(+), 7 deletions(-) create mode 100644 include/linux/atomic-arch-fallback.h (limited to 'include/linux') diff --git a/include/linux/atomic-arch-fallback.h b/include/linux/atomic-arch-fallback.h new file mode 100644 index 000000000000..bcb6aa27cfa6 --- /dev/null +++ b/include/linux/atomic-arch-fallback.h @@ -0,0 +1,2291 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-fallback.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +#ifndef _LINUX_ATOMIC_FALLBACK_H +#define _LINUX_ATOMIC_FALLBACK_H + +#include + +#ifndef arch_xchg_relaxed +#define arch_xchg_relaxed arch_xchg +#define arch_xchg_acquire arch_xchg +#define arch_xchg_release arch_xchg +#else /* arch_xchg_relaxed */ + +#ifndef arch_xchg_acquire +#define arch_xchg_acquire(...) \ + __atomic_op_acquire(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg_release +#define arch_xchg_release(...) \ + __atomic_op_release(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg +#define arch_xchg(...) \ + __atomic_op_fence(arch_xchg, __VA_ARGS__) +#endif + +#endif /* arch_xchg_relaxed */ + +#ifndef arch_cmpxchg_relaxed +#define arch_cmpxchg_relaxed arch_cmpxchg +#define arch_cmpxchg_acquire arch_cmpxchg +#define arch_cmpxchg_release arch_cmpxchg +#else /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg_acquire +#define arch_cmpxchg_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg_release +#define arch_cmpxchg_release(...) \ + __atomic_op_release(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg +#define arch_cmpxchg(...) \ + __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg64_relaxed +#define arch_cmpxchg64_relaxed arch_cmpxchg64 +#define arch_cmpxchg64_acquire arch_cmpxchg64 +#define arch_cmpxchg64_release arch_cmpxchg64 +#else /* arch_cmpxchg64_relaxed */ + +#ifndef arch_cmpxchg64_acquire +#define arch_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64_release +#define arch_cmpxchg64_release(...) \ + __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64 +#define arch_cmpxchg64(...) \ + __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg64_relaxed */ + +#ifndef arch_atomic_read_acquire +static __always_inline int +arch_atomic_read_acquire(const atomic_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic_read_acquire arch_atomic_read_acquire +#endif + +#ifndef arch_atomic_set_release +static __always_inline void +arch_atomic_set_release(atomic_t *v, int i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic_set_release arch_atomic_set_release +#endif + +#ifndef arch_atomic_add_return_relaxed +#define arch_atomic_add_return_acquire arch_atomic_add_return +#define arch_atomic_add_return_release arch_atomic_add_return +#define arch_atomic_add_return_relaxed arch_atomic_add_return +#else /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_add_return_acquire +static __always_inline int +arch_atomic_add_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_add_return_acquire arch_atomic_add_return_acquire +#endif + +#ifndef arch_atomic_add_return_release +static __always_inline int +arch_atomic_add_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_add_return_relaxed(i, v); +} +#define arch_atomic_add_return_release arch_atomic_add_return_release +#endif + +#ifndef arch_atomic_add_return +static __always_inline int +arch_atomic_add_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_add_return arch_atomic_add_return +#endif + +#endif /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add +#define arch_atomic_fetch_add_release arch_atomic_fetch_add +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add +#else /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_fetch_add_acquire +static __always_inline int +arch_atomic_fetch_add_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire +#endif + +#ifndef arch_atomic_fetch_add_release +static __always_inline int +arch_atomic_fetch_add_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_add_relaxed(i, v); +} +#define arch_atomic_fetch_add_release arch_atomic_fetch_add_release +#endif + +#ifndef arch_atomic_fetch_add +static __always_inline int +arch_atomic_fetch_add(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_add arch_atomic_fetch_add +#endif + +#endif /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_sub_return_relaxed +#define arch_atomic_sub_return_acquire arch_atomic_sub_return +#define arch_atomic_sub_return_release arch_atomic_sub_return +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return +#else /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_sub_return_acquire +static __always_inline int +arch_atomic_sub_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire +#endif + +#ifndef arch_atomic_sub_return_release +static __always_inline int +arch_atomic_sub_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_sub_return_relaxed(i, v); +} +#define arch_atomic_sub_return_release arch_atomic_sub_return_release +#endif + +#ifndef arch_atomic_sub_return +static __always_inline int +arch_atomic_sub_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_sub_return arch_atomic_sub_return +#endif + +#endif /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_fetch_sub_relaxed +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub +#else /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_fetch_sub_acquire +static __always_inline int +arch_atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire +#endif + +#ifndef arch_atomic_fetch_sub_release +static __always_inline int +arch_atomic_fetch_sub_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_sub_relaxed(i, v); +} +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release +#endif + +#ifndef arch_atomic_fetch_sub +static __always_inline int +arch_atomic_fetch_sub(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_sub arch_atomic_fetch_sub +#endif + +#endif /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_inc +static __always_inline void +arch_atomic_inc(atomic_t *v) +{ + arch_atomic_add(1, v); +} +#define arch_atomic_inc arch_atomic_inc +#endif + +#ifndef arch_atomic_inc_return_relaxed +#ifdef arch_atomic_inc_return +#define arch_atomic_inc_return_acquire arch_atomic_inc_return +#define arch_atomic_inc_return_release arch_atomic_inc_return +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return +#endif /* arch_atomic_inc_return */ + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + return arch_atomic_add_return(1, v); +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + return arch_atomic_add_return_acquire(1, v); +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + return arch_atomic_add_return_release(1, v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return_relaxed +static __always_inline int +arch_atomic_inc_return_relaxed(atomic_t *v) +{ + return arch_atomic_add_return_relaxed(1, v); +} +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed +#endif + +#else /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_inc_return_relaxed(v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#endif /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_fetch_inc_relaxed +#ifdef arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc +#endif /* arch_atomic_fetch_inc */ + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + return arch_atomic_fetch_add(1, v); +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + return arch_atomic_fetch_add_acquire(1, v); +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + return arch_atomic_fetch_add_release(1, v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc_relaxed +static __always_inline int +arch_atomic_fetch_inc_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_add_relaxed(1, v); +} +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed +#endif + +#else /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_inc_relaxed(v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#endif /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_dec +static __always_inline void +arch_atomic_dec(atomic_t *v) +{ + arch_atomic_sub(1, v); +} +#define arch_atomic_dec arch_atomic_dec +#endif + +#ifndef arch_atomic_dec_return_relaxed +#ifdef arch_atomic_dec_return +#define arch_atomic_dec_return_acquire arch_atomic_dec_return +#define arch_atomic_dec_return_release arch_atomic_dec_return +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return +#endif /* arch_atomic_dec_return */ + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + return arch_atomic_sub_return(1, v); +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + return arch_atomic_sub_return_acquire(1, v); +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + return arch_atomic_sub_return_release(1, v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return_relaxed +static __always_inline int +arch_atomic_dec_return_relaxed(atomic_t *v) +{ + return arch_atomic_sub_return_relaxed(1, v); +} +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed +#endif + +#else /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_dec_return_relaxed(v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#endif /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_fetch_dec_relaxed +#ifdef arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec +#endif /* arch_atomic_fetch_dec */ + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + return arch_atomic_fetch_sub(1, v); +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + return arch_atomic_fetch_sub_acquire(1, v); +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + return arch_atomic_fetch_sub_release(1, v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec_relaxed +static __always_inline int +arch_atomic_fetch_dec_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_sub_relaxed(1, v); +} +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed +#endif + +#else /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_dec_relaxed(v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#endif /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and +#define arch_atomic_fetch_and_release arch_atomic_fetch_and +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and +#else /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_fetch_and_acquire +static __always_inline int +arch_atomic_fetch_and_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire +#endif + +#ifndef arch_atomic_fetch_and_release +static __always_inline int +arch_atomic_fetch_and_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_and_relaxed(i, v); +} +#define arch_atomic_fetch_and_release arch_atomic_fetch_and_release +#endif + +#ifndef arch_atomic_fetch_and +static __always_inline int +arch_atomic_fetch_and(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_and arch_atomic_fetch_and +#endif + +#endif /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_andnot +static __always_inline void +arch_atomic_andnot(int i, atomic_t *v) +{ + arch_atomic_and(~i, v); +} +#define arch_atomic_andnot arch_atomic_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +#ifdef arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot +#endif /* arch_atomic_fetch_andnot */ + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + return arch_atomic_fetch_and(~i, v); +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_acquire(~i, v); +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_release(~i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +static __always_inline int +arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_relaxed(~i, v); +} +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed +#endif + +#else /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_andnot_relaxed(i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#endif /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or +#define arch_atomic_fetch_or_release arch_atomic_fetch_or +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or +#else /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_or_acquire +static __always_inline int +arch_atomic_fetch_or_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire +#endif + +#ifndef arch_atomic_fetch_or_release +static __always_inline int +arch_atomic_fetch_or_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_or_relaxed(i, v); +} +#define arch_atomic_fetch_or_release arch_atomic_fetch_or_release +#endif + +#ifndef arch_atomic_fetch_or +static __always_inline int +arch_atomic_fetch_or(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_or arch_atomic_fetch_or +#endif + +#endif /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_xor_relaxed +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor +#else /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_fetch_xor_acquire +static __always_inline int +arch_atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire +#endif + +#ifndef arch_atomic_fetch_xor_release +static __always_inline int +arch_atomic_fetch_xor_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_xor_relaxed(i, v); +} +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release +#endif + +#ifndef arch_atomic_fetch_xor +static __always_inline int +arch_atomic_fetch_xor(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_xor arch_atomic_fetch_xor +#endif + +#endif /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_xchg_relaxed +#define arch_atomic_xchg_acquire arch_atomic_xchg +#define arch_atomic_xchg_release arch_atomic_xchg +#define arch_atomic_xchg_relaxed arch_atomic_xchg +#else /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_xchg_acquire +static __always_inline int +arch_atomic_xchg_acquire(atomic_t *v, int i) +{ + int ret = arch_atomic_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire +#endif + +#ifndef arch_atomic_xchg_release +static __always_inline int +arch_atomic_xchg_release(atomic_t *v, int i) +{ + __atomic_release_fence(); + return arch_atomic_xchg_relaxed(v, i); +} +#define arch_atomic_xchg_release arch_atomic_xchg_release +#endif + +#ifndef arch_atomic_xchg +static __always_inline int +arch_atomic_xchg(atomic_t *v, int i) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_xchg arch_atomic_xchg +#endif + +#endif /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_relaxed +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg +#else /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_acquire +static __always_inline int +arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + int ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire +#endif + +#ifndef arch_atomic_cmpxchg_release +static __always_inline int +arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + __atomic_release_fence(); + return arch_atomic_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release +#endif + +#ifndef arch_atomic_cmpxchg +static __always_inline int +arch_atomic_cmpxchg(atomic_t *v, int old, int new) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_cmpxchg arch_atomic_cmpxchg +#endif + +#endif /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_relaxed +#ifdef arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg +#endif /* arch_atomic_try_cmpxchg */ + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + __atomic_release_fence(); + return arch_atomic_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#endif /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_sub_and_test +/** + * arch_atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_sub_and_test(int i, atomic_t *v) +{ + return arch_atomic_sub_return(i, v) == 0; +} +#define arch_atomic_sub_and_test arch_atomic_sub_and_test +#endif + +#ifndef arch_atomic_dec_and_test +/** + * arch_atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic_dec_and_test(atomic_t *v) +{ + return arch_atomic_dec_return(v) == 0; +} +#define arch_atomic_dec_and_test arch_atomic_dec_and_test +#endif + +#ifndef arch_atomic_inc_and_test +/** + * arch_atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_inc_and_test(atomic_t *v) +{ + return arch_atomic_inc_return(v) == 0; +} +#define arch_atomic_inc_and_test arch_atomic_inc_and_test +#endif + +#ifndef arch_atomic_add_negative +/** + * arch_atomic_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative(int i, atomic_t *v) +{ + return arch_atomic_add_return(i, v) < 0; +} +#define arch_atomic_add_negative arch_atomic_add_negative +#endif + +#ifndef arch_atomic_fetch_add_unless +/** + * arch_atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline int +arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless +#endif + +#ifndef arch_atomic_add_unless +/** + * arch_atomic_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic_add_unless(atomic_t *v, int a, int u) +{ + return arch_atomic_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic_add_unless arch_atomic_add_unless +#endif + +#ifndef arch_atomic_inc_not_zero +/** + * arch_atomic_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic_inc_not_zero(atomic_t *v) +{ + return arch_atomic_add_unless(v, 1, 0); +} +#define arch_atomic_inc_not_zero arch_atomic_inc_not_zero +#endif + +#ifndef arch_atomic_inc_unless_negative +static __always_inline bool +arch_atomic_inc_unless_negative(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative +#endif + +#ifndef arch_atomic_dec_unless_positive +static __always_inline bool +arch_atomic_dec_unless_positive(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive +#endif + +#ifndef arch_atomic_dec_if_positive +static __always_inline int +arch_atomic_dec_if_positive(atomic_t *v) +{ + int dec, c = arch_atomic_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive +#endif + +#ifdef CONFIG_GENERIC_ATOMIC64 +#include +#endif + +#ifndef arch_atomic64_read_acquire +static __always_inline s64 +arch_atomic64_read_acquire(const atomic64_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic64_read_acquire arch_atomic64_read_acquire +#endif + +#ifndef arch_atomic64_set_release +static __always_inline void +arch_atomic64_set_release(atomic64_t *v, s64 i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic64_set_release arch_atomic64_set_release +#endif + +#ifndef arch_atomic64_add_return_relaxed +#define arch_atomic64_add_return_acquire arch_atomic64_add_return +#define arch_atomic64_add_return_release arch_atomic64_add_return +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return +#else /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_add_return_acquire +static __always_inline s64 +arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire +#endif + +#ifndef arch_atomic64_add_return_release +static __always_inline s64 +arch_atomic64_add_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_add_return_relaxed(i, v); +} +#define arch_atomic64_add_return_release arch_atomic64_add_return_release +#endif + +#ifndef arch_atomic64_add_return +static __always_inline s64 +arch_atomic64_add_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_add_return arch_atomic64_add_return +#endif + +#endif /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add +#else /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_fetch_add_acquire +static __always_inline s64 +arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire +#endif + +#ifndef arch_atomic64_fetch_add_release +static __always_inline s64 +arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_add_relaxed(i, v); +} +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release +#endif + +#ifndef arch_atomic64_fetch_add +static __always_inline s64 +arch_atomic64_fetch_add(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_add arch_atomic64_fetch_add +#endif + +#endif /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_sub_return_relaxed +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return +#define arch_atomic64_sub_return_release arch_atomic64_sub_return +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return +#else /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_sub_return_acquire +static __always_inline s64 +arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire +#endif + +#ifndef arch_atomic64_sub_return_release +static __always_inline s64 +arch_atomic64_sub_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_sub_return_relaxed(i, v); +} +#define arch_atomic64_sub_return_release arch_atomic64_sub_return_release +#endif + +#ifndef arch_atomic64_sub_return +static __always_inline s64 +arch_atomic64_sub_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_sub_return arch_atomic64_sub_return +#endif + +#endif /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_fetch_sub_relaxed +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub +#else /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_fetch_sub_acquire +static __always_inline s64 +arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire +#endif + +#ifndef arch_atomic64_fetch_sub_release +static __always_inline s64 +arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_sub_relaxed(i, v); +} +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release +#endif + +#ifndef arch_atomic64_fetch_sub +static __always_inline s64 +arch_atomic64_fetch_sub(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub +#endif + +#endif /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_inc +static __always_inline void +arch_atomic64_inc(atomic64_t *v) +{ + arch_atomic64_add(1, v); +} +#define arch_atomic64_inc arch_atomic64_inc +#endif + +#ifndef arch_atomic64_inc_return_relaxed +#ifdef arch_atomic64_inc_return +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return +#define arch_atomic64_inc_return_release arch_atomic64_inc_return +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return +#endif /* arch_atomic64_inc_return */ + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + return arch_atomic64_add_return(1, v); +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + return arch_atomic64_add_return_acquire(1, v); +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + return arch_atomic64_add_return_release(1, v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return_relaxed +static __always_inline s64 +arch_atomic64_inc_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_add_return_relaxed(1, v); +} +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed +#endif + +#else /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_inc_return_relaxed(v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#endif /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_fetch_inc_relaxed +#ifdef arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc +#endif /* arch_atomic64_fetch_inc */ + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + return arch_atomic64_fetch_add(1, v); +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_add_acquire(1, v); +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + return arch_atomic64_fetch_add_release(1, v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc_relaxed +static __always_inline s64 +arch_atomic64_fetch_inc_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_add_relaxed(1, v); +} +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed +#endif + +#else /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_inc_relaxed(v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#endif /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_dec +static __always_inline void +arch_atomic64_dec(atomic64_t *v) +{ + arch_atomic64_sub(1, v); +} +#define arch_atomic64_dec arch_atomic64_dec +#endif + +#ifndef arch_atomic64_dec_return_relaxed +#ifdef arch_atomic64_dec_return +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return +#define arch_atomic64_dec_return_release arch_atomic64_dec_return +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return +#endif /* arch_atomic64_dec_return */ + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + return arch_atomic64_sub_return(1, v); +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + return arch_atomic64_sub_return_acquire(1, v); +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + return arch_atomic64_sub_return_release(1, v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return_relaxed +static __always_inline s64 +arch_atomic64_dec_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_sub_return_relaxed(1, v); +} +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed +#endif + +#else /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_dec_return_relaxed(v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#endif /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_fetch_dec_relaxed +#ifdef arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec +#endif /* arch_atomic64_fetch_dec */ + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + return arch_atomic64_fetch_sub(1, v); +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_acquire(1, v); +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_release(1, v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec_relaxed +static __always_inline s64 +arch_atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_relaxed(1, v); +} +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed +#endif + +#else /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_dec_relaxed(v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#endif /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and +#else /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_fetch_and_acquire +static __always_inline s64 +arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire +#endif + +#ifndef arch_atomic64_fetch_and_release +static __always_inline s64 +arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_and_relaxed(i, v); +} +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release +#endif + +#ifndef arch_atomic64_fetch_and +static __always_inline s64 +arch_atomic64_fetch_and(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_and arch_atomic64_fetch_and +#endif + +#endif /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_andnot +static __always_inline void +arch_atomic64_andnot(s64 i, atomic64_t *v) +{ + arch_atomic64_and(~i, v); +} +#define arch_atomic64_andnot arch_atomic64_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +#ifdef arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot +#endif /* arch_atomic64_fetch_andnot */ + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and(~i, v); +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_acquire(~i, v); +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_release(~i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +static __always_inline s64 +arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_relaxed(~i, v); +} +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed +#endif + +#else /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_andnot_relaxed(i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#endif /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or +#else /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_or_acquire +static __always_inline s64 +arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire +#endif + +#ifndef arch_atomic64_fetch_or_release +static __always_inline s64 +arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_or_relaxed(i, v); +} +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release +#endif + +#ifndef arch_atomic64_fetch_or +static __always_inline s64 +arch_atomic64_fetch_or(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_or arch_atomic64_fetch_or +#endif + +#endif /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_xor_relaxed +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor +#else /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_fetch_xor_acquire +static __always_inline s64 +arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire +#endif + +#ifndef arch_atomic64_fetch_xor_release +static __always_inline s64 +arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_xor_relaxed(i, v); +} +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release +#endif + +#ifndef arch_atomic64_fetch_xor +static __always_inline s64 +arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor +#endif + +#endif /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_xchg_relaxed +#define arch_atomic64_xchg_acquire arch_atomic64_xchg +#define arch_atomic64_xchg_release arch_atomic64_xchg +#define arch_atomic64_xchg_relaxed arch_atomic64_xchg +#else /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_xchg_acquire +static __always_inline s64 +arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) +{ + s64 ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire +#endif + +#ifndef arch_atomic64_xchg_release +static __always_inline s64 +arch_atomic64_xchg_release(atomic64_t *v, s64 i) +{ + __atomic_release_fence(); + return arch_atomic64_xchg_relaxed(v, i); +} +#define arch_atomic64_xchg_release arch_atomic64_xchg_release +#endif + +#ifndef arch_atomic64_xchg +static __always_inline s64 +arch_atomic64_xchg(atomic64_t *v, s64 i) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_xchg arch_atomic64_xchg +#endif + +#endif /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_relaxed +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg +#else /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_acquire +static __always_inline s64 +arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) +{ + s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_cmpxchg_release +static __always_inline s64 +arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release +#endif + +#ifndef arch_atomic64_cmpxchg +static __always_inline s64 +arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg +#endif + +#endif /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_relaxed +#ifdef arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg +#endif /* arch_atomic64_try_cmpxchg */ + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#endif /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_sub_and_test +/** + * arch_atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return arch_atomic64_sub_return(i, v) == 0; +} +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test +#endif + +#ifndef arch_atomic64_dec_and_test +/** + * arch_atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic64_dec_and_test(atomic64_t *v) +{ + return arch_atomic64_dec_return(v) == 0; +} +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test +#endif + +#ifndef arch_atomic64_inc_and_test +/** + * arch_atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_inc_and_test(atomic64_t *v) +{ + return arch_atomic64_inc_return(v) == 0; +} +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test +#endif + +#ifndef arch_atomic64_add_negative +/** + * arch_atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return(i, v) < 0; +} +#define arch_atomic64_add_negative arch_atomic64_add_negative +#endif + +#ifndef arch_atomic64_fetch_add_unless +/** + * arch_atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline s64 +arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless +#endif + +#ifndef arch_atomic64_add_unless +/** + * arch_atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + return arch_atomic64_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic64_add_unless arch_atomic64_add_unless +#endif + +#ifndef arch_atomic64_inc_not_zero +/** + * arch_atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic64_inc_not_zero(atomic64_t *v) +{ + return arch_atomic64_add_unless(v, 1, 0); +} +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero +#endif + +#ifndef arch_atomic64_inc_unless_negative +static __always_inline bool +arch_atomic64_inc_unless_negative(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative +#endif + +#ifndef arch_atomic64_dec_unless_positive +static __always_inline bool +arch_atomic64_dec_unless_positive(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive +#endif + +#ifndef arch_atomic64_dec_if_positive +static __always_inline s64 +arch_atomic64_dec_if_positive(atomic64_t *v) +{ + s64 dec, c = arch_atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive +#endif + +#endif /* _LINUX_ATOMIC_FALLBACK_H */ +// 90cd26cfd69d2250303d654955a0cc12620fb91b diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h index 656b5489b673..2c4927bf7b8d 100644 --- a/include/linux/atomic-fallback.h +++ b/include/linux/atomic-fallback.h @@ -1180,9 +1180,6 @@ atomic_dec_if_positive(atomic_t *v) #define atomic_dec_if_positive atomic_dec_if_positive #endif -#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) -#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) - #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif @@ -2290,8 +2287,5 @@ atomic64_dec_if_positive(atomic64_t *v) #define atomic64_dec_if_positive atomic64_dec_if_positive #endif -#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) -#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) - #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// baaf45f4c24ed88ceae58baca39d7fd80bb8101b +// 1fac0941c79bf0ae100723cc2ac9b94061f0b67a diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 4c0d009a46f0..571a11008ab5 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -25,6 +25,12 @@ * See Documentation/memory-barriers.txt for ACQUIRE/RELEASE definitions. */ +#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) +#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) + +#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) +#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) + /* * The idea here is to build acquire/release variants by adding explicit * barriers on top of the relaxed variant. In the case where the relaxed @@ -71,7 +77,12 @@ __ret; \ }) +#ifdef ARCH_ATOMIC +#include +#include +#else #include +#endif #include -- cgit v1.2.3 From 0372007f5a79d61d3cb48a507717b9afb5d6addd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Mar 2020 11:05:22 +0100 Subject: context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner Reviewed-by: Masami Hiramatsu Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de --- include/linux/context_tracking.h | 6 +++--- include/linux/context_tracking_state.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8cac62ee6add..981b880d5b60 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -33,13 +33,13 @@ static inline void user_exit(void) } /* Called with interrupts disabled. */ -static inline void user_enter_irqoff(void) +static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_USER); } -static inline void user_exit_irqoff(void) +static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_USER); @@ -75,7 +75,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) * is enabled. If context tracking is disabled, returns * CONTEXT_DISABLED. This should be used primarily for debugging. */ -static inline enum ctx_state ct_state(void) +static __always_inline enum ctx_state ct_state(void) { return context_tracking_enabled() ? this_cpu_read(context_tracking.state) : CONTEXT_DISABLED; diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index e7fe6678b7ad..65a60d3313b0 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -26,12 +26,12 @@ struct context_tracking { extern struct static_key_false context_tracking_key; DECLARE_PER_CPU(struct context_tracking, context_tracking); -static inline bool context_tracking_enabled(void) +static __always_inline bool context_tracking_enabled(void) { return static_branch_unlikely(&context_tracking_key); } -static inline bool context_tracking_enabled_cpu(int cpu) +static __always_inline bool context_tracking_enabled_cpu(int cpu) { return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } @@ -41,7 +41,7 @@ static inline bool context_tracking_enabled_this_cpu(void) return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } -static inline bool context_tracking_in_user(void) +static __always_inline bool context_tracking_in_user(void) { return __this_cpu_read(context_tracking.state) == CONTEXT_USER; } -- cgit v1.2.3 From df65bba1dcd8ffadd922a71196b78c6d7630c33b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Feb 2020 18:25:09 +0100 Subject: lib/bsearch: Provide __always_inline variant For code that needs the ultimate performance (it can inline the @cmp function too) or simply needs to avoid calling external functions for whatever reason, provide an __always_inline variant of bsearch(). [ tglx: Renamed to __inline_bsearch() as suggested by Andy ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20200505135313.624443814@linutronix.de --- include/linux/bsearch.h | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bsearch.h b/include/linux/bsearch.h index 8ed53d7524ea..e66b711d091e 100644 --- a/include/linux/bsearch.h +++ b/include/linux/bsearch.h @@ -4,7 +4,29 @@ #include -void *bsearch(const void *key, const void *base, size_t num, size_t size, - cmp_func_t cmp); +static __always_inline +void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) +{ + const char *pivot; + int result; + + while (num > 0) { + pivot = base + (num >> 1) * size; + result = cmp(key, pivot); + + if (result == 0) + return (void *)pivot; + + if (result > 0) { + base = pivot + size; + num--; + } + num >>= 1; + } + + return NULL; +} + +extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ -- cgit v1.2.3 From 2ab70319bc1f79228da4dce7b9d604740c9beeef Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:14 +0200 Subject: nmi, tracing: Make hardware latency tracing noinstr safe The hardware latency tracer calls into instrumentable functions. Move the calls into the RCU watching sections and annotate them. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Acked-by: Andy Lutomirski Cc: Paul E. McKenney Link: https://lore.kernel.org/r/20200521202116.904176298@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/hardirq.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index e07cf853aa16..29b862aba740 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -87,20 +87,24 @@ extern void rcu_nmi_exit(void); arch_nmi_enter(); \ printk_nmi_enter(); \ lockdep_off(); \ - ftrace_nmi_enter(); \ BUG_ON(in_nmi() == NMI_MASK); \ __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ rcu_nmi_enter(); \ lockdep_hardirq_enter(); \ + instrumentation_begin(); \ + ftrace_nmi_enter(); \ + instrumentation_end(); \ } while (0) #define nmi_exit() \ do { \ + instrumentation_begin(); \ + ftrace_nmi_exit(); \ + instrumentation_end(); \ lockdep_hardirq_exit(); \ rcu_nmi_exit(); \ BUG_ON(!in_nmi()); \ __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ - ftrace_nmi_exit(); \ lockdep_on(); \ printk_nmi_exit(); \ arch_nmi_exit(); \ -- cgit v1.2.3 From 8a6bc4787f05d087fda8e11ead225c8830250703 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:21 +0200 Subject: genirq: Provide irq_enter/exit_rcu() irq_enter()/exit() currently include RCU handling. To properly separate the RCU handling code, provide variants which contain only the non-RCU related functionality. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Reviewed-by: Andy Lutomirski Link: https://lore.kernel.org/r/20200521202117.567023613@linutronix.de --- include/linux/hardirq.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 29b862aba740..3dc9102d16cf 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -40,7 +40,11 @@ static __always_inline void rcu_irq_enter_check_tick(void) /* * Enter irq context (on NO_HZ, update jiffies): */ -extern void irq_enter(void); +void irq_enter(void); +/* + * Like irq_enter(), but RCU is already watching. + */ +void irq_enter_rcu(void); /* * Exit irq context without processing softirqs: @@ -55,7 +59,12 @@ extern void irq_enter(void); /* * Exit irq context and process softirqs if needed: */ -extern void irq_exit(void); +void irq_exit(void); + +/* + * Like irq_exit(), but return with RCU watching. + */ +void irq_exit_rcu(void); #ifndef arch_nmi_enter #define arch_nmi_enter() do { } while (0) -- cgit v1.2.3 From 98a3bf195e1a14755da3d2b83e1dbb4a3158866d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:22 +0200 Subject: genirq: Provide __irq_enter/exit_raw() Like __irq_enter/exit() but without time accounting. To be used for "empty" system vectors like the scheduler IPI to avoid the overhead. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Reviewed-by: Andy Lutomirski Link: https://lore.kernel.org/r/20200521202117.671682341@linutronix.de --- include/linux/hardirq.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 3dc9102d16cf..03c9fece7d43 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -37,6 +37,17 @@ static __always_inline void rcu_irq_enter_check_tick(void) lockdep_hardirq_enter(); \ } while (0) +/* + * Like __irq_enter() without time accounting for fast + * interrupts, e.g. reschedule IPI where time accounting + * is more expensive than the actual interrupt. + */ +#define __irq_enter_raw() \ + do { \ + preempt_count_add(HARDIRQ_OFFSET); \ + lockdep_hardirq_enter(); \ + } while (0) + /* * Enter irq context (on NO_HZ, update jiffies): */ @@ -56,6 +67,15 @@ void irq_enter_rcu(void); preempt_count_sub(HARDIRQ_OFFSET); \ } while (0) +/* + * Like __irq_exit() without time accounting + */ +#define __irq_exit_raw() \ + do { \ + lockdep_hardirq_exit(); \ + preempt_count_sub(HARDIRQ_OFFSET); \ + } while (0) + /* * Exit irq context and process softirqs if needed: */ -- cgit v1.2.3 From bf2b3008440072068580c609d79a079656af0588 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 29 May 2020 23:27:40 +0200 Subject: x86/entry: Rename trace_hardirqs_off_prepare() The typical pattern for trace_hardirqs_off_prepare() is: ENTRY lockdep_hardirqs_off(); // because hardware ... do entry magic instrumentation_begin(); trace_hardirqs_off_prepare(); ... do actual work trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); ... do exit magic lockdep_hardirqs_on(); which shows that it's named wrong, rename it to trace_hardirqs_off_finish(), as it concludes the hardirq_off transition. Also, given that the above is the only correct order, make the traditional all-in-one trace_hardirqs_off() follow suit. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200529213321.415774872@infradead.org --- include/linux/irqflags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index d7f7e436c3af..6384d2813ded 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -32,7 +32,7 @@ #ifdef CONFIG_TRACE_IRQFLAGS extern void trace_hardirqs_on_prepare(void); - extern void trace_hardirqs_off_prepare(void); + extern void trace_hardirqs_off_finish(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define lockdep_hardirq_context(p) ((p)->hardirq_context) @@ -101,7 +101,7 @@ do { \ #else # define trace_hardirqs_on_prepare() do { } while (0) -# define trace_hardirqs_off_prepare() do { } while (0) +# define trace_hardirqs_off_finish() do { } while (0) # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) # define lockdep_hardirq_context(p) 0 -- cgit v1.2.3 From 6eebad1ad303db360ebe3e51c2b9656c3d407157 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 3 Jun 2020 13:40:21 +0200 Subject: lockdep: __always_inline more for noinstr vmlinux.o: warning: objtool: debug_locks_off()+0xd: call to __debug_locks_off() leaves .noinstr.text section vmlinux.o: warning: objtool: match_held_lock()+0x6a: call to look_up_lock_class.isra.0() leaves .noinstr.text section vmlinux.o: warning: objtool: lock_is_held_type()+0x90: call to lockdep_recursion_finish() leaves .noinstr.text section Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200603114052.185201076@infradead.org --- include/linux/debug_locks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 257ab3c92cb8..e7e45f0cc7da 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -12,7 +12,7 @@ extern int debug_locks __read_mostly; extern int debug_locks_silent __read_mostly; -static inline int __debug_locks_off(void) +static __always_inline int __debug_locks_off(void) { return xchg(&debug_locks, 0); } -- cgit v1.2.3 From f0178fc01fe46bab6a95415f5647d1a74efcad1b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 10 Jun 2020 08:37:01 +0200 Subject: x86/entry: Unbreak __irqentry_text_start/end magic The entry rework moved interrupt entry code from the irqentry to the noinstr section which made the irqentry section empty. This breaks boundary checks which rely on the __irqentry_text_start/end markers to find out whether a function in a stack trace is interrupt/exception entry code. This affects the function graph tracer and filter_irq_stacks(). As the IDT entry points are all sequentialy emitted this is rather simple to unbreak by injecting __irqentry_text_start/end as global labels. To make this work correctly: - Remove the IRQENTRY_TEXT section from the x86 linker script - Define __irqentry so it breaks the build if it's used - Adjust the entry mirroring in PTI - Remove the redundant kprobes and unwinder bound checks Reported-by: Qian Cai Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 80f637c3a6f3..5db970b6615a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -760,8 +760,10 @@ extern int arch_early_irq_init(void); /* * We want to know which function is an entrypoint of a hardirq or a softirq. */ -#define __irq_entry __attribute__((__section__(".irqentry.text"))) -#define __softirq_entry \ - __attribute__((__section__(".softirqentry.text"))) +#ifndef __irq_entry +# define __irq_entry __attribute__((__section__(".irqentry.text"))) +#endif + +#define __softirq_entry __attribute__((__section__(".softirqentry.text"))) #endif -- cgit v1.2.3